Method and device applied to node of wireless communication and artificial intelligence

Abstract

The invention discloses a method and a device in a node used for wireless communication and artificial intelligence. A first node receives a first information unit, and the first information unit configures CSI reporting; determining whether first information is reported in a first resource set, wherein the first information comprises first CSI; the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI related opportunity in a target time window, and the CSI related opportunity is used for channel measurement or interference measurement; the target time window depends on a generation mode of the first CSI; the generation mode of the first CSI comprises dependence on AI. According to the invention, fusion of AI and communication is supported, the efficiency and reliability of a communication system are improved, and the adaptability of the communication system under different channel characteristics is enhanced.

Description

Technical Field

[0001] The present application relates to a signal transmission method and device in a wireless communication system, and in particular to a method and device related to channel information in a wireless communication system. Background Art

[0002] In traditional wireless communication, 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, etc. The channel information includes but is not limited to one or more of CRI (CSI-RS Resource Indicator, channel state information reference signal resource indication), RI (Rank Indicator, rank indication), PMI (Precoding Matrix Indicator, precoding indication) or CQI (Channel quality indicator). The UE can use this information 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, modulation and coding scheme), TPMI (Transmitted Precoding Matrix Indicator, transmission precoding matrix indication), TCI (Transmission Configuration Indication) and other parameters. In addition, UE reporting can be used to optimize network parameters, such as better cell coverage, switching base stations according to UE location, etc.

[0003] In traditional cellular communications, antenna ports are used to describe reference signal resources; different from physical antennas, antenna ports can be considered as virtualization / superposition operations of physical antennas.

[0004] 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, traditional measurement and reporting methods will bring a lot of redundant overhead. Therefore, in NR (New Radio) Rel-18 (Release-18), the research on AI (Artificial Intelligence) / ML (Machine Learning) technology was established to explore its impact on system performance and system design. Compared with traditional processing methods, AI / ML has the characteristics of being based on training and requiring deployment. According to the 3GPP (3rd Generation Partnership Project) standard TS 38.300, AI / ML models and algorithms are beyond the scope of 3GPP. Summary of the invention

[0005] Through research, the applicant found that when AI / ML functions are introduced, the existing measurement mechanism, reporting mechanism and related configuration signaling may not be able to adapt to the needs of AI / ML.

[0006] In response to the above problems, the present application discloses a solution. It should be noted that, in the description of the above problems, 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 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; further, the use of a unified design scheme for different scenarios (such as other non-AI / ML scenarios, including but not limited to vehicle networking (Vehicle to Everything, V2X), capacity enhancement systems, short-range communication systems, NTN (Non Terrestrial Network, non-terrestrial network), IoT (Internet of Things, Internet of Things), URLLC (Ultra Reliable Low Latency Communication, ultra-robust low-latency communication) networks, etc.) can also help reduce hardware complexity and cost. In the absence of conflict, the embodiments and features in any node of the present application can be applied to any other node. In the absence of conflict, the embodiments and features in the embodiments of the present application can be arbitrarily combined with each other.

[0007] In particular, the interpretation of the terms, nouns, functions, and variables in this application (if not otherwise specified) may refer to the definitions in the TS38 series and TS37 series in the technical specifications (TS) of 3GPP (the 3rd Generation Partnership Project). If necessary, reference may be made to TS38.211, TS38.212, TS38.213, TS38.214, TS38.215, TS38.300, TS38.304, TS38.305, TS38.321, TS38.331, TS37.355, and TS38.423 in the 3GPP technical standards to assist in the understanding of this application.

[0008] As an example, the interpretation of the terms in the present application refers to the definitions of the TS38 series of specification protocols of 3GPP.

[0009] As an example, the interpretation of the terms in the present application refers to the definitions of the TS37 series of specification protocols of 3GPP.

[0010] As an example, the interpretation of the terms in the present application refers to the definition of the TS40 series of specification protocols of 3GPP.

[0011] As an example, the interpretation of the terms in the present application refers to the definitions of the TS39 series of specification protocols of 3GPP.

[0012] As an example, the interpretation of the terms in the present application refers to the definitions in the Rel-17 version of the specification protocol of 3GPP.

[0013] As an example, the interpretation of the terms in the present application refers to the definitions in the Rel-18 version of the specification protocol of 3GPP.

[0014] As an example, the interpretation of the terms in the present application refers to the definitions in the Rel-19 version of the specification protocol of 3GPP.

[0015] As an example, the interpretation of the terms in the present application refers to the definitions in the Rel-20 version of the specification protocol of 3GPP.

[0016] The present application discloses a method in a first node used for wireless communication and artificial intelligence, which includes:

[0017] receiving a first information unit, wherein the first information unit configures CSI reporting;

[0018] Determine whether to report first information in a first resource set, where the first information includes first CSI;

[0019] Among them, the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in the target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0020] As an embodiment, the problem to be solved by the present application includes: how to improve the reliability of CSI reporting.

[0021] As an embodiment, the problem to be solved by the present application includes: how the first node determines the length of the target time window.

[0022] As an embodiment, the problem to be solved by the present application includes: how the first node determines whether to report the first information in the first resource set.

[0023] As an embodiment, the characteristics of the above method include: the present application makes the target time window dependent on the CSI generation method, and the first node determines whether to report the first information in the first resource set based on whether at least one CSI-related opportunity is received in the target time window, thereby solving the above problem.

[0024] As an embodiment, the characteristics of the above method include: the first node receives at least one CSI-related opportunity in the target time window, and the first node reports the first information in the first resource set; the first node does not receive any CSI-related opportunity in the target time window, and the first node gives up reporting the first information in the first resource set.

[0025] As an embodiment, the characteristics of the above method include: the generation method of the first CSI includes CSI generated based on AI and CSI not generated based on AI.

[0026] As an embodiment, the characteristics of the above method include: the generation method of the first CSI includes generating a model-Id of the CSI.

[0027] As an embodiment, the characteristics of the above method include: the first node can perform measurement in the target time window, and the measurement includes at least one of channel measurement and interference measurement.

[0028] As an embodiment, the characteristics of the above method include: the time domain resources occupied by the first resource set are not earlier than the time domain resources occupied by the target time window.

[0029] As an embodiment, the benefits of the above method include: the application supports the integration of AI and communication, improves the adaptability and intelligence level of the communication system, and thereby improves the performance, efficiency and user experience of the communication system.

[0030] As an embodiment, the benefits of the above method include: the present application supports AI-based generation of CSI to better cope with long-term environmental changes, while being compatible with non-AI-based CSI to adapt to short-term rapid changes in the channel, thereby enhancing the adaptability of the communication system under different channel characteristics.

[0031] As an embodiment, the benefits of the above method include: generating CSI based on AI does not require additional hardware support or complex measurement equipment, thereby reducing the cost and complexity of the system.

[0032] As an embodiment, the benefits of the above method include: CSI generated based on AI can be adjusted and optimized according to the scenario and is easy to deploy.

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

[0034] Determine to report the first information in the first resource set, and report the first information.

[0035] According to one aspect of the present application, the above method is characterized in that it includes:

[0036] Determine not to report the first information in the first resource set, and give up reporting the first information.

[0037] According to one aspect of the present application, the above method is characterized in that the duration of the target time window depends on the generation method of the first CSI; when the generation method of the first CSI is based on AI, the duration of the target time window is a first time length; when the generation method of the first CSI is not based on AI, the duration of the target time window is a second time length.

[0038] As an embodiment, the problem to be solved by the present application includes: how to determine the duration of the target time window.

[0039] As an embodiment, the characteristics of the above method include: in the present application, the duration of the target time window is made dependent on the generation method of the first CSI, thereby solving the above problem.

[0040] As an embodiment, the characteristics of the above method include: in this application, the CSI reporting based on AI generation and the CSI reporting not based on AI generation use different time measurement window lengths.

[0041] As an embodiment, the benefits of the above method include: in AI scenarios, a longer measurement time window can obtain more data, helping the AI ​​model to better understand the channel characteristics, and then capture the long-term changes and trends of the channel, so that the generated CSI has higher adaptability and generalization ability, while reducing the impact of outliers or extreme values ​​on the AI ​​model output.

[0042] As an embodiment, the benefits of the above method include: in an AI scenario, channel information can be obtained based on a shorter measurement time window to support faster CSI generation and achieve real-time reporting and prediction of channel status.

[0043] As an embodiment, the benefits of the above method include: in non-AI scenarios, the length of the target time window can be compatible with the current standard and has little impact on the current standard.

[0044] According to one aspect of the present application, the above method is characterized in that the generation method of the first CSI is based on AI, the duration of the target time window is the first time length, and the first time length depends on the model for generating the first CSI.

[0045] As an embodiment, the problem to be solved by the present application includes: how to determine the first time length.

[0046] As an embodiment, the characteristics of the above method include: The present application solves the above problem by configuring different measurement time window lengths for different AI models.

[0047] As an embodiment, the characteristics of the above method include: RNN, LSTM and other networks can learn short-term dependencies between input sequences, and use a short measurement window length to accurately capture channel changes and fluctuations in high-speed moving channels or channels with large instantaneous fluctuations, providing rapid response.

[0048] As an embodiment, the characteristics of the above method include: CNN, Transformer and other networks can learn the spatial relationship between input sequences, and use a longer time window to extract the long-term characteristics and periodicity of the channel in slowly changing or periodically changing communication scenarios, which is conducive to channel prediction.

[0049] As an embodiment, the benefits of the above method include: different channel states can adopt different AI models in combination with the learning characteristics of different neural networks, which is conducive to achieving more accurate and reliable CSI prediction in complex communication environments.

[0050] As an embodiment, the benefits of the above method include: optimizing the performance of the communication system and improving the user experience.

[0051] As an embodiment, the benefits of the above method include: it is conducive to promoting the deep integration of AI and communications.

[0052] According to one aspect of the present application, the above method is characterized in that the first information unit configures K CSI resource configuration identifiers, K is a positive integer greater than 1, the K CSI resource configuration identifiers are all for a type of measurement, and the K CSI resource configuration identifiers include at least 2 resource configuration identifiers corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which CSI resource corresponding to one of the K CSI resource configuration identifiers is used to generate the first CSI depends on the generation method of the first CSI.

[0053] As an embodiment, the characteristics of the above method include: any CSI resource configuration identifier among the K CSI resource configuration identifiers indicates a CSI resource setting, and the one CSI resource setting includes the configuration of at least one CSI resource set.

[0054] As an embodiment, the characteristics of the above method include: the K resource configuration identifiers are all for channel measurement.

[0055] As an embodiment, the characteristics of the above method include: the K resource configuration identifiers are all for interference measurement.

[0056] As an embodiment, the characteristics of the above method include: which CSI resource configuration identifier among the K CSI resource configuration identifiers corresponds to an identifier of an AI model that generates the first CSI and depends on which CSI resource is used to generate the first CSI.

[0057] As an embodiment, the above method has the following advantages: for the same type of measurement, CSI can be generated based on AI or not based on AI, and has good compatibility.

[0058] As an embodiment, the benefits of the above method include: for CSI generated based on AI, different AI models can also use different reference signal resource set inputs, which is conducive to selecting appropriate input data according to the characteristics of different models.

[0059] As an embodiment, the benefits of the above method include: improving the accuracy of CSI reporting and enhancing the ability of the system to adapt to environmental changes.

[0060] According to one aspect of the present application, the above method is characterized in that the first information unit configures M report types, where M is a positive integer greater than 1, and there are at least 2 report types among the M report types, corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which report type among the M report types is used to generate the first CSI depends on the generation method of the first CSI.

[0061] As an embodiment, the characteristics of the above method include: the M report types correspond to combinations of M different types of CSI respectively.

[0062] As an embodiment, the characteristics of the above method include: the M report types indicate M CSI type sets, the M type sets include at least one CSI type, and the candidates of the CSI types include at least one or more of CRI, RI, LI, PMI, CQI, i1, RSRP, and SINR.

[0063] As an embodiment, the characteristics of the above method include: which report type among the M report types is used to generate an identifier of an AI model that the first CSI depends on to generate the first CSI.

[0064] As an embodiment, the benefits of the above method include: different report types are configured based on AI-generated CSI and not based on AI-generated CSI, and have good compatibility.

[0065] As an embodiment, the benefits of the above method include: for CSI generated based on AI, different AI models can output different CSI types, which is beneficial for the base station to select a suitable model for the required CSI report type.

[0066] As an embodiment, the benefits of the above method include: improving the accuracy of CSI reporting and enhancing the ability of the system to adapt to environmental changes.

[0067] According to one aspect of the present application, the above method is characterized in that there is at least one report type among the M report types corresponding to the CSI generated based on AI, and the report type corresponding to the CSI generated based on AI includes a confidence interval.

[0068] As an embodiment, the problem to be solved by the present application includes: how to improve the reliability of CSI reporting.

[0069] As an embodiment, the characteristics of the above method include: the report type of CSI generated based on AI in this application also includes a confidence interval, and the confidence interval is used for model evaluation.

[0070] As an embodiment, the characteristics of the above method include: the confidence interval indicates the degree of confidence of the AI ​​model in the first CSI.

[0071] As an embodiment, the characteristics of the above method include: the output of the AI ​​model that generates the CSI includes the confidence interval.

[0072] As an embodiment, the benefits of the above method include: the base station can determine the credibility of the channel state according to the confidence level, and then make a relevant judgment on whether to trigger non-periodic CSI reporting, etc.

[0073] As an embodiment, the benefits of the above method include: it is helpful to understand the performance of the model and to improve the deficiencies of the model.

[0074] As an embodiment, the benefits of the above method include: being conducive to model lifecycle management and understanding the uncertainty of model predictions.

[0075] According to one aspect of the present application, the above method is characterized in that the first information unit configures L reporting frequency configurations, where L is a positive integer greater than 1, and there are at least 2 reporting frequency configurations among the L reporting frequency configurations, corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which reporting frequency configuration among the L reporting frequency configurations is used to generate the first CSI depends on the generation method of the first CSI.

[0076] As an embodiment, the characteristics of the above method include: any reporting frequency configuration among the L reporting frequency configurations indicates the reporting granularity of CSI reporting in the frequency domain.

[0077] As an embodiment, the characteristics of the above method include: any reporting frequency configuration among the L reporting frequency configurations configures a CSI reporting frequency band.

[0078] As an embodiment, the characteristics of the above method include: which reporting frequency configuration among the L reporting frequency configurations is used to generate the first CSI and an identifier of an AI model that generates the first CSI.

[0079] As an embodiment, the benefits of the above method include: different reporting frequency configurations are configured based on AI-generated CSI and not based on AI-generated CSI, and have good compatibility.

[0080] As an embodiment, the benefits of the above method include: for CSI generated based on AI, different AI models can be configured with different reporting frequency configurations, which is conducive to selecting a suitable AI model according to the frequency requirements of the CSI report.

[0081] As an embodiment, the benefits of the above method include: improving the accuracy of CSI reporting and enhancing the ability of the system to adapt to environmental changes.

[0082] According to one aspect of the present application, the above method is characterized in that the first node is a user equipment.

[0083] According to one aspect of the present application, the above method is characterized in that the first node is a relay node.

[0084] According to one aspect of the present application, the above method is characterized in that the first node has AI / ML capabilities.

[0085] According to one aspect of the present application, the above method is characterized in that the first node supports CSI calculation based on AI / ML.

[0086] According to one aspect of the present application, the above method is characterized in that the first node supports AI / ML-based CSI reporting.

[0087] The present application discloses a method used in a second node for wireless communication and artificial intelligence, which includes:

[0088] Sending a first information unit, where the first information unit configures CSI reporting;

[0089] Among them, the receiver of the first information unit is the first node, the first node determines whether to report the first information in the first resource set, and the first information includes the first CSI; the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in the target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0090] According to one aspect of the present application, the above method is characterized in that it includes:

[0091] Determine to receive the first information in the first resource set, and receive the first information.

[0092] According to one aspect of the present application, the above method is characterized in that it includes:

[0093] Determine not to receive the first information in the first resource set, and give up receiving the first information.

[0094] According to one aspect of the present application, the above method is characterized in that it includes:

[0095] The first information is received in the first resource set.

[0096] According to one aspect of the present application, the above method is characterized in that the duration of the target time window depends on the generation method of the first CSI; when the generation method of the first CSI is based on AI, the duration of the target time window is a first time length; when the generation method of the first CSI is not based on AI, the duration of the target time window is a second time length.

[0097] According to one aspect of the present application, the above method is characterized in that the generation method of the first CSI is based on AI, the duration of the target time window is the first time length, and the first time length depends on the model for generating the first CSI.

[0098] According to one aspect of the present application, the above method is characterized in that the first information unit configures K CSI resource configuration identifiers, K is a positive integer greater than 1, the K CSI resource configuration identifiers are all for a type of measurement, and the K CSI resource configuration identifiers include at least 2 resource configuration identifiers corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which CSI resource corresponding to one of the K CSI resource configuration identifiers is used to generate the first CSI depends on the generation method of the first CSI.

[0099] According to one aspect of the present application, the above method is characterized in that the first information unit configures M report types, where M is a positive integer greater than 1, and there are at least 2 report types among the M report types, corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which report type among the M report types is used to generate the first CSI depends on the generation method of the first CSI.

[0100] According to one aspect of the present application, the above method is characterized in that there is at least one report type among the M report types corresponding to the CSI generated based on AI, and the report type corresponding to the CSI generated based on AI includes a confidence interval.

[0101] According to one aspect of the present application, the above method is characterized in that the first information unit configures L reporting frequency configurations, where L is a positive integer greater than 1, and there are at least 2 reporting frequency configurations among the L reporting frequency configurations, corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which reporting frequency configuration among the L reporting frequency configurations is used to generate the first CSI depends on the generation method of the first CSI.

[0102] According to one aspect of the present application, the above method is characterized in that the second node is a base station.

[0103] According to one aspect of the present application, the above method is characterized in that the second node is a user equipment.

[0104] According to one aspect of the present application, the above method is characterized in that the second node is a TRP.

[0105] The present application discloses a device for a first node used for wireless communication and artificial intelligence, including:

[0106] A first receiver receives a first information unit, wherein the first information unit configures CSI reporting;

[0107] A first transmitter determines whether to report first information in a first resource set, where the first information includes a first CSI;

[0108] Among them, the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in the target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0109] The present application discloses a device for a second node used for wireless communication and artificial intelligence, including:

[0110] A second transmitter sends a first information unit, where the first information unit configures CSI reporting;

[0111] Among them, the receiver of the first information unit is the first node, the first node determines whether to report the first information in the first resource set, and the first information includes the first CSI; the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in the target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0112] As an embodiment, compared with the traditional solution, the present application has the following advantages but not limited to:

[0113] This application supports the integration of AI and communications, improves the adaptability and intelligence level of communication systems, and thus improves the performance, efficiency and user experience of communication systems;

[0114] This application supports AI-generated CSI to better cope with long-term environmental changes, while being compatible with non-AI-based CSI to quickly adapt to short-term changes in the channel, thereby enhancing the adaptability of the communication system under different channel characteristics;

[0115] There are only minor changes to the current standards, and it has good compatibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0116] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0117] Figure 1 A flowchart showing first node transmission according to an embodiment of the present application is shown;

[0118] Figure 2 A schematic diagram of a network architecture according to an embodiment of the present application is shown;

[0119] Figure 3 A schematic diagram showing an embodiment of a wireless protocol architecture of a user plane and a control plane according to an embodiment of the present application;

[0120] Figure 4 A schematic diagram showing a first communication device and a second communication device according to an embodiment of the present application is shown;

[0121] Figure 5 A first flow chart showing transmission between a first node and a second node according to an embodiment of the present application is shown;

[0122] Figure 5a A second flow chart showing transmission between a first node and a second node according to an embodiment of the present application;

[0123] Figure 6 A schematic diagram showing two situations of the duration of the target time window according to an embodiment of the present application;

[0124] Figure 7 A schematic diagram showing a first information unit configuring a CSI resource configuration identifier according to an embodiment of the present application is shown;

[0125] Figure 8 A schematic diagram showing a first information unit configuration report type according to an embodiment of the present application;

[0126] Fig. 9 A schematic diagram showing a configuration of a report frequency of a first information unit according to an embodiment of the present application is shown;

[0127] Fig.10A schematic diagram of RAN domain AI / ML function deployment according to an embodiment of the present application is shown;

[0128] Fig.11 A schematic diagram showing the deployment of AI / ML functions of a UE according to an embodiment of the present application is shown;

[0129] Fig.12 A schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of the present application is shown;

[0130] Fig.13 A schematic diagram based on artificial intelligence or machine learning according to an embodiment of the present application is shown;

[0131] Fig.14 A structural block diagram of a processing device used in a first node according to an embodiment of the present application is shown;

[0132] Fig.15 A structural block diagram of a processing device used in a second node according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0133] The technical solution of the present application will be further described in detail below in conjunction with the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be arbitrarily combined with each other without conflict. Based on considerations such as performance, flexibility, complexity, overhead, and compatibility, those skilled in the art are motivated to flexibly combine the embodiments in different drawings without conflict, including but not limited to the attached drawings. Figure 1 The embodiments and appendix Figure 5 -Attached Fig.15 The embodiments in Figure 5 The embodiments and appendix Figure 6 -Attached Fig.15 The embodiments in , etc.

[0134] Example 1

[0135] Embodiment 1 illustrates a flowchart of the first node transmission according to an embodiment of the present application, as shown in the attached Figure 1 As shown in the attached Figure 1 In the example, each box represents a step. In particular, the order of the steps in the box does not represent a specific time sequence between the steps.

[0136] In step 101, the first node receives a first information unit, where the first information unit configures CSI reporting; in step 102, it is determined whether to report first information in a first resource set, where the first information includes first CSI.

[0137] In Example 1, the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in a target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0138] As an embodiment, the first node is the first node in the present application.

[0139] As an embodiment, the CSI refers to: Channel State Information, channel state information.

[0140] As an embodiment, the AI ​​refers to: Artificial Intelligence.

[0141] As an embodiment, the AI ​​includes: Machine Learning.

[0142] As an embodiment, the AI ​​includes: Deep Learning.

[0143] As an embodiment, the first node receives the first information unit.

[0144] As an embodiment, the first information unit is transmitted via higher layer signaling.

[0145] As an embodiment, the first information unit is carried by RRC (Radio Resource Control) layer signaling.

[0146] As an embodiment, the first information unit is transmitted via RRC signaling.

[0147] As an embodiment, the first information unit includes RRC layer signaling.

[0148] As an embodiment, the first information unit includes one or more RRC IE (Information Element, information unit).

[0149] As an embodiment, the first information unit includes one or more fields in an RRC IE.

[0150] As an embodiment, the first information unit includes one or more fields in each RRC IE of multiple RRC IEs.

[0151] As an embodiment, the first information unit configures the CSI report.

[0152] As an embodiment, the first information unit configures the time domain type of CSI reporting, and the time domain type is periodic (Periodic, P) or semi-persistent (Semi-Persistent, SP).

[0153] As an embodiment, the first information unit configures the CSI reporting period.

[0154] As an embodiment, the first information unit configures the time domain offset of CSI reporting.

[0155] As an embodiment, the first information unit configures a periodic or semi-continuous report sent on a PUCCH (Physical Uplink Control CHannel).

[0156] As an embodiment, the first information unit configures a periodic or semi-continuous report sent on the PUCCH and activated by a MAC CE (Medium Access Control layer Control Element).

[0157] As an embodiment, the first information unit configures a periodic or semi-continuous report sent on a PUSCH (Physical Uplink Shared CHannel).

[0158] As an embodiment, the first information unit configures a periodic or semi-continuous report sent on the PUSCH and triggered by DCI (Downlink Control Information).

[0159] As an embodiment, the first information unit includes ServingCellConfig IE.

[0160] As an embodiment, the first information unit includes one or more fields in the ServingCellConfig IE.

[0161] As an embodiment, the first information unit includes CSI-MeasConfig IE.

[0162] As an embodiment, the first information unit includes one or more fields in the CSI-MeasConfig IE.

[0163] As an embodiment, the first information unit includes CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0164] As an embodiment, the first information unit includes one or more fields in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0165] As an embodiment, the first information unit includes CSI-SemiPersistentOnPUSCH-TriggerState IE.

[0166] As an embodiment, the first information unit includes one or more fields in the CSI-SemiPersistentOnPUSCH-TriggerState IE.

[0167] As an embodiment, the first information unit includes CSI-ReportSubConfigTriggerList IE.

[0168] As an embodiment, the first information unit includes one or more fields in the CSI-ReportSubConfigTriggerList IE.

[0169] As an embodiment, the first information unit includes CSI-ReportConfig IE.

[0170] As an embodiment, the first information unit includes one or more fields in the CSI-ReportConfig IE.

[0171] As an embodiment, the first information unit includes CSI-ReportSubConfig IE.

[0172] As an embodiment, the first information unit includes one or more fields in the CSI-ReportSubConfig IE.

[0173] As an embodiment, the name of the RRC signaling used to transmit the first information unit includes CSI.

[0174] As an embodiment, the name of the RRC signaling used to transmit the first information unit includes Report.

[0175] As an embodiment, the name of the RRC signaling used to transmit the first information unit includes Config.

[0176] As an embodiment, the first node determines whether to report the first information in the first resource set.

[0177] As an embodiment, the first resource set includes a positive integer number of REs (Resource Elements) greater than 1.

[0178] As an embodiment, the first resource set occupies frequency domain resources corresponding to a positive integer number of RBs (Resource Blocks) in the frequency domain, and occupies a positive integer number of multi-carrier symbols in the time domain.

[0179] Typically, one RE described in the present application occupies one symbol in the time domain and one subcarrier in the frequency domain.

[0180] Typically, one RB described in the present application occupies 12 consecutive subcarriers in the frequency domain.

[0181] As an embodiment, the RB described in the present application includes: PRB (Physical Resource Block).

[0182] As an embodiment, the RB described in the present application includes: CRB (Common Resource Block).

[0183] As an embodiment, the multi-carrier symbol described in the present application includes an OFDM (Orthogonal Frequency Division Multiplexing) symbol.

[0184] As an embodiment, the multi-carrier symbol described in the present application is an OFDM symbol.

[0185] As an embodiment, the multi-carrier symbol described in the present application is an OFDM symbol including a CP (Cyclic Prefix).

[0186] As an embodiment, the multi-carrier symbol described in the present application includes a FBMC (Filter Bank Multi Carrier) symbol.

[0187] As an embodiment, the multi-carrier symbol described in the present application includes a UFMC (Universal Filtered MultiCarrier) symbol.

[0188] As an embodiment, the multi-carrier symbols described in the present application include F-OFDM (Filtered-OFDM, filtered-orthogonal frequency division multiplexing) symbols.

[0189] As an embodiment, the first resource set corresponds to one PUSCH resource.

[0190] As an embodiment, the first resource set corresponds to a time-frequency resource occupied by a PUSCH.

[0191] As an embodiment, the first resource set is a PUSCH opportunity.

[0192] As an embodiment, the first resource set corresponds to one PUCCH resource.

[0193] As an embodiment, the first resource set corresponds to the time-frequency resources occupied by a PUCCH.

[0194] As an embodiment, the first resource set is a PUCCH opportunity.

[0195] As an embodiment, the first information includes the first CSI.

[0196] As an embodiment, the first information is carried by a baseband signal.

[0197] As an embodiment, the first information is carried by a radio frequency signal.

[0198] As an embodiment, the first information is carried by a wireless signal.

[0199] As an embodiment, the first information includes the first CSI.

[0200] As an embodiment, the first information includes a channel quality report.

[0201] As an embodiment, the first information includes a measurement report.

[0202] As an embodiment, the first information includes a report on mobility management.

[0203] As an embodiment, the first information includes a result of BFR (Beam Failure Recovery).

[0204] As an embodiment, the first information includes a result of cell selection.

[0205] As an embodiment, the first information includes a beam quality report.

[0206] As an embodiment, the first information includes beam management reporting.

[0207] As an embodiment, the first information includes a channel impulse response.

[0208] As an embodiment, the first information includes UCI (Uplink Control Information, uplink control information).

[0209] As an embodiment, the first CSI is periodic CSI.

[0210] As an embodiment, the first CSI is semi-persistent CSI.

[0211] As an embodiment, the first CSI includes LI (layer indicator).

[0212] As an embodiment, the first CSI includes RI (rank indicator).

[0213] As an embodiment, the first CSI includes CQI (Channel Quality Indicator).

[0214] As an embodiment, the first CSI includes PMI (Precoding Matrix Indicator).

[0215] As an embodiment, the first CSI includes CRI (CSI-RS resource indicator, channel state information reference signal resource indicator).

[0216] As an embodiment, the first CSI includes SSBRI (SS / PBCH Block Resource indicator, synchronization / physical broadcast channel block resource indication).

[0217] As an embodiment, the first CSI includes L1-RSRP (Layer 1 Reference Signal Received Power, layer 1 reference signal received power).

[0218] As an embodiment, the first information unit determines the first resource set.

[0219] As an embodiment, the first information unit indicates the time domain resources occupied by the first resource set.

[0220] As an embodiment, the first information unit configures a period of CSI reporting, and the time domain resources occupied by the CSI reporting include the first resource set.

[0221] As an embodiment, the first information unit indicates the frequency domain resources occupied by the first resource set.

[0222] As an embodiment, the first information unit indicates a plurality of candidate resource sets, and the first resource set is one of the plurality of candidate resource sets.

[0223] As a sub-embodiment of this embodiment, the first information unit indicates the period of the multiple candidate resource sets.

[0224] As a sub-embodiment of this embodiment, the first information unit indicates the time slots in which the multiple candidate resource sets are located.

[0225] As an embodiment, the first information unit configures a plurality of candidate resource collection groups, and the target resource collection group is a resource collection group among the plurality of candidate resource groups.

[0226] As a sub-embodiment of this embodiment, the MAC CE that activates the first information indicates the target resource set group from the multiple candidate resource set groups, and the first resource set is a resource set in the target resource set group.

[0227] As a sub-embodiment of this embodiment, the DCI triggering the first information indicates the target resource set group from the multiple candidate resource set groups, and the first resource set is a resource set in the target resource set group.

[0228] As an embodiment, whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in the target time window.

[0229] As an embodiment, the first node receives at least one CSI-related opportunity in the target time window, and the first node reports the first information in the first resource set.

[0230] As an embodiment, the first node does not receive a CSI-related opportunity in the target time window, and the first node gives up reporting the first information in the first resource set.

[0231] As an embodiment, the first node performs channel measurement or interference measurement in the target time window.

[0232] As an embodiment, the CSI-related opportunity is for channel measurement (channel measurement) or interference measurement (Interference Measurement, IM).

[0233] As an embodiment, the CSI-related opportunity is for channel measurement.

[0234] As an embodiment, the CSI-related opportunity is for interference measurement.

[0235] As an embodiment, the CSI related opportunity is for channel prediction.

[0236] As an embodiment, the CSI related timing is for interference prediction.

[0237] Typically, the CSI-related opportunities include at least the first two of the CSI-RS (Channel State Information-Reference Signal) transmission opportunities for channel measurement, CSI-RS, and CSI-IM (Channel State Information-Interference Measurement) opportunities for interference measurement.

[0238] As an embodiment, the CSI-related opportunities include at least the first two of a CSI-RS transmission opportunity for channel measurement of the first CSI, a CSI-RS, and a CSI-IM opportunity for interference measurement.

[0239] As an embodiment, the CSI-related opportunity includes a CSI-RS transmission opportunity for channel measurement and a CSI-RS.

[0240] As an embodiment, the CSI-related opportunities include CSI-RS transmission opportunities, CSI-RS, and CSI-IM opportunities for interference measurement.

[0241] As an embodiment, the CSI-related opportunity includes at least one transmitted CSI-RS.

[0242] As an embodiment, the CSI-related opportunity includes at least one reference signal for channel measurement.

[0243] As an embodiment, the first node receives a CSI-RS in the CSI-related opportunity, and the first CSI is used for channel measurement or interference measurement.

[0244] As an embodiment, the target time window depends on the generation method of the first CSI.

[0245] As an embodiment, the target time window occupies continuous time domain resources.

[0246] As an embodiment, the meaning that the target time window depends on the generation method of the first CSI includes: the starting time of the target time window depends on the generation method of the first CSI.

[0247] Typically, the starting time of the target time window depends on the generation method of the first CSI; when the generation method of the first CSI is based on AI, the starting time of the target time window is the first time slot; when the generation method of the first CSI is not based on AI, the starting time of the target time window is the second time slot.

[0248] As an embodiment, the meaning that the target time window depends on the generation method of the first CSI includes: the deadline of the target time window depends on the generation method of the first CSI.

[0249] Typically, the deadline of the target time window depends on the generation method of the first CSI; when the generation method of the first CSI is based on AI, the deadline of the target time window is the first time slot; when the generation method of the first CSI is not based on AI, the deadline of the target time window is the second time slot.

[0250] As an embodiment, the meaning that the target time window depends on the generation method of the first CSI includes: the duration of the target time window depends on the generation method of the first CSI.

[0251] As an embodiment, the meaning that the target time window depends on the generation method of the first CSI includes: the position and duration of the target time window in the time domain depend on the generation method of the first CSI.

[0252] As an embodiment, the generation method of the first CSI includes relying on AI.

[0253] As an embodiment, the generation method of the first CSI includes: generation based on AI, and generation not based on AI.

[0254] As an embodiment, the method for generating the first CSI includes: generating an identifier of an AI model for generating the first CSI.

[0255] As an embodiment, the identifier of the AI ​​model in the present application is the ID of the model.

[0256] As an embodiment, the identifier of the AI ​​model in this application is the Identity of the AI ​​model.

[0257] As an embodiment, the identifier of the AI ​​model in the present application is the Identifier of the AI ​​model.

[0258] As an embodiment, the identifier of the AI ​​model in the present application is the Index of the AI ​​model.

[0259] As an embodiment, the identifier of the AI ​​model in the present application is the AI-model-Id of the AI ​​model.

[0260] As an embodiment, the identifier of the AI ​​model in the present application is the model-Id of the AI ​​model.

[0261] As an embodiment, the identifier of the AI ​​model in the present application is an AI non-zero integer.

[0262] As an embodiment, the identifier of the AI ​​model in the present application is an AI non-negative integer.

[0263] As an embodiment, the identifier of the AI ​​model in the present application indexes the AI / ML model used for the AI / ML inferring.

[0264] As an embodiment, the identification indication of the AI ​​model in the present application is used to generate the first CSI data set.

[0265] Typically, the first information unit is configured with at least one identifier of the AI ​​model in the present application, and the MAC CE that activates the first information indicates a first identifier from the at least one identifier of the AI ​​model in the present application, and the first identifier is used to generate the first CSI.

[0266] Typically, the first information unit is configured with a first identifier, the first identifier indicates an identifier of the AI ​​model in the present application, and the MAC CE that activates the first information indicates that the first identifier is used for generating the first CSI.

[0267] Typically, the first information unit is configured with at least one identifier of the AI ​​model in the present application, the field indicating the identifier of the AI ​​model in the present application in the MAC CE for activating the first information is reserved, and the first CSI is not CSI generated based on AI.

[0268] Typically, the first information unit is configured with at least one identifier of the AI ​​model in the present application, and the DCI that triggers the first information indicates a first identifier from among the multiple identifiers of the AI ​​model in the present application, and the first identifier is used to generate the first CSI.

[0269] Typically, the first information unit is configured with a first identifier, and the DCI that triggers the first information indicates that the first identifier is used for generating the first CSI.

[0270] Typically, the first information unit is configured with at least one identifier of the AI ​​model in the present application, the field indicating the identifier of the AI ​​model in the present application in the DCI that triggers the first information is reserved, and the first CSI is not CSI generated based on AI.

[0271] As an embodiment, in the present application, the meaning that the first identifier is used for generating the first CSI includes: the AI ​​model indicated by the first identifier generates the first CSI.

[0272] As an embodiment, in the present application, the meaning that the first identifier is used for generating the first CSI includes: the data set indicated by the first identifier is used to generate the first CSI.

[0273] As an embodiment, the generation method of the first CSI relies on AI, which means that the first CSI is generated by prediction.

[0274] As an embodiment, the generation method of the first CSI relying on AI means that the first CSI is generated by reasoning.

[0275] As an embodiment, the generation method of the first CSI relying on AI means that the first CSI is generated by a model, and the model is (for) AI.

[0276] As an embodiment, the generation method of the first CSI relying on AI means that the first CSI is generated by a model, and the model is ML.

[0277] As an embodiment, the generation method of the first CSI depends on AI, which means that the first CSI is generated based on AI on the basis of measurement.

[0278] As an embodiment, the first CSI is generated based on AI, which means that the channel information recovered by the receiver based on the received first CSI is unknown to the first node.

[0279] As an embodiment, the first CSI is generated based on AI, which means that: a generator for generating the first CSI is obtained based on training.

[0280] As an embodiment, the first CSI being generated based on AI means that the first CSI does not belong to the CSI defined in 3GPP Rel-18 or a version earlier than 3GPP Rel-18.

[0281] As an embodiment, the meaning that the first CSI is not generated based on AI includes: the first CSI is not generated by reasoning or prediction.

[0282] As an embodiment, the first CSI is not generated based on AI, which means that the channel information recovered by the receiver based on the received first CSI is known to the first node.

[0283] As an embodiment, the meaning that the first CSI is not generated based on AI includes: the first CSI is obtained through measurement.

[0284] As an embodiment, the meaning that the first CSI is not generated based on AI includes: the first CSI is obtained by measuring a downlink reference signal.

[0285] As an embodiment, the meaning that the first CSI is not generated based on AI includes: the first CSI belongs to the CSI defined in 3GPP Rel-18 or a version earlier than 3GPP Rel-18.

[0286] Those skilled in the art know that the first CSI represents the parameters of the wireless channel between the base station and the first node. The specific form depends on different receiver algorithms and can be determined by the supplier of the first node; it can also be clearly defined by the standard. The following takes CQI as an example to provide some non-limiting implementation methods:

[0287] The first node first performs channel measurement on a CSI-RS resource to obtain a channel parameter matrix H r×t , where r and t are the number of receiving antennas and the number of antenna ports used for transmission respectively; when using the precoding matrix W t×l Under the condition of , the channel parameter matrix after precoding is H r×t ·W t×l , where l is the rank or number of layers; the first node calculates H based on a specific algorithm r×t ·W t×lThe equivalent channel capacity is then used to determine the CQI by looking up the equivalent channel capacity. Generally speaking, the calculation of the equivalent channel capacity requires the first node to estimate noise and interference. Generally speaking, the mapping between the equivalent channel capacity and the CQI value depends on the receiver performance or hardware-related factors such as the modulation method. The precoding matrix W t×l Usually, the first node feeds back the information through RI or PMI.

[0288] Compared with CQI, L1-SINR does not carry the information of the receiver, so the calculation of the equivalent channel capacity is omitted.

[0289] As an embodiment, the first CSI is generated based on AI, and the first node obtains the channel parameter matrix H based on AI / ML reasoning r×t .

[0290] As an embodiment, the first CSI is generated based on AI, and the input of the first node based on AI / ML reasoning includes a channel parameter matrix H obtained by channel measurement r×t and the precoding matrix W t×l , the output of the AI / ML reasoning includes equivalent channel capacity.

[0291] As an embodiment, the first CSI is not generated based on AI, and the first node performs channel measurement on a CSI-RS resource to obtain a channel parameter matrix H r×t .

[0292] As a sub-embodiment of this embodiment, the CSI-RS transmitted in the one CSI-RS resource occupies a CSI-related opportunity described in this application.

[0293] As an embodiment, the first CSI is not generated based on AI, and the first node uses SINR, EESM (Exponential Effective SINR Mapping), or RBIR (Received Blockmean mutual Information Ratio) criteria to calculate the equivalent channel capacity.

[0294] Example 2

[0295] Embodiment 2 illustrates a schematic diagram of a network architecture according to an embodiment of the present application, as shown in the attached Figure 2 shown.

[0296] Attached Figure 2A network architecture 200 is illustrated. The network architecture 200 is a network architecture for LTE (Long-Term Evolution), LTE-A (Long-Term Evolution Advanced), 5G system, 5G-Advanced and future 6G system. The network architecture for LTE, LTE-A, 5G system, 5G-Advanced and future 6G system is referred to as EPS (Evolved Packet System). The 5G NR or LTE network architecture may be referred to as 5GS (5G System) / EPS or some other suitable term; the 6G network architecture may be referred to as 6GS (6G System) / EPS or some other suitable term. The network architecture 200 may include one or more UEs 201, a RAN (Next Generation Radio Access Network) 202, a core network 210, an HSS (Home Subscriber Server) / UDM (Unified Data Management) 220 and an Internet service 230. . The network architecture 200 can be interconnected with other access networks, but for simplicity these entities / interfaces are not shown. Figure 2As shown, the network architecture 200 provides packet switching services, however, those skilled in the art will readily appreciate that the various concepts presented throughout this application can be extended to networks that provide circuit switching services. RAN 202 includes Node B 203 and other nodes 204. Node 203 provides user and control plane protocol terminations toward UE 201. Node 203 can be connected to other nodes 204 via an Xn interface (e.g., backhaul). Node 203 may also be referred to as a base station, a base transceiver station, a wireless base station, a wireless transceiver, a transceiver function, a Basic Service Set (BSS), an Extended Service Set (ESS), a TRP (Transmitter Receiver Point), or some other suitable terminology. Node 203 provides an access point to a core network 210 for UE 201; the core network 210 is a 5GC (5G Core Network, 5G Core Network) / EPC (Evolved Packet Core), or the core network 210 is a 6GC. Examples of UE 201 include cellular phones, smart phones, Session Initiation Protocol (SIP) phones, laptop computers, Personal Digital Assistants (PDAs), satellite radios, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband physical network devices, machine type communication devices, land vehicles, cars, wearable devices, or any other similar functional devices. Those skilled in the art may also refer to UE 201 as a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, or some other suitable term. Node 203 is connected to core network 210 via an S1 / NG interface.The core network 210 includes MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MME / AMF / SMF 214, S-GW (Service Gateway) / UPF (User Plane Function) 212, and P-GW (Packet Data Network Gateway) / UPF 213. MME / AMF / SMF 211 is a control node that handles signaling between UE 201 and 5G-CN / EPC 210. In general, MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through S-GW / UPF 212, which itself is connected to P-GW / UPF 213. P-GW provides UE IP address allocation and other functions. P-GW / UPF 213 is connected to Internet service 230. Internet service 230 includes operator-specific Internet protocol services, which may specifically include Internet, Intranet, IMS (IP Multimedia Subsystem) and packet switching services.

[0297] As an embodiment, the first node in the present application includes the UE 201.

[0298] As an embodiment, the second node in the present application includes the node 203.

[0299] As an embodiment, the node 203 is a macro cell base station.

[0300] As an embodiment, the node 203 is a micro cell base station.

[0301] As an embodiment, the node 203 is a pico cell base station.

[0302] As an embodiment, the node 203 is a home base station (Femtocell).

[0303] As an embodiment, the node 203 is a base station device that supports a large delay difference.

[0304] As an embodiment, the node 203 is a flying platform device.

[0305] As an embodiment, the node 203 is a satellite device.

[0306] As an embodiment, the node 203 is a test device (eg, a transceiver device simulating some functions of a base station, a signaling tester).

[0307] As an embodiment, the UE 201 includes a mobile phone.

[0308] As an embodiment, the UE 201 is a vehicle including a car.

[0309] As an embodiment, the wireless link from the UE 201 to the node 203 is an uplink, and the uplink is used to perform uplink transmission.

[0310] As an embodiment, the wireless link from the node 203 to the UE 201 is a downlink, and the downlink is used to perform downlink transmission.

[0311] As an embodiment, the wireless link between the node 203 and the UE 201 includes a cellular network link.

[0312] As an embodiment, the node 203 and the UE 201 are connected via a Uu air interface.

[0313] As an embodiment, the sender of the first information unit includes the node 203.

[0314] As an embodiment, the receiver of the first information unit includes the UE 201.

[0315] As an embodiment, the sender of the first information includes the UE 201.

[0316] As an embodiment, the receiver of the first information includes the node 203.

[0317] As an embodiment, the UE 201 supports generating reports using AI / ML.

[0318] As an embodiment, the UE 201 supports generating a trained model or partial parameters in the model using training data.

[0319] As an embodiment, the UE 201 supports determining at least part of the parameters for CSI reporting through training.

[0320] As an embodiment, the UE 201 supports AI / ML-based CSI reporting.

[0321] As an embodiment, the UE 201 supports CSI reporting based on NN (Neural Networks).

[0322] As an embodiment, the UE 201 supports CSI reporting based on ANN (Artificial Neural Networks).

[0323] As an embodiment, the UE 201 supports CSI reporting based on CNN (Convolutional Neural Networks).

[0324] As an embodiment, the UE 201 supports Transformer-based CSI reporting.

[0325] As an embodiment, the UE 201 supports CSI reporting based on LSTM (Long Short-Term Memory).

[0326] As an embodiment, the UE 201 supports CSI reporting based on MLP (MultiLayer Perceptron).

[0327] As an embodiment, the UE 201 supports CSI reporting based on GAN (Generative Adversarial Nets).

[0328] As an embodiment, the UE 201 supports CSI reporting based on a lightweight neural network.

[0329] As a sub-embodiment of this embodiment, the lightweight neural network includes one or more of MobileNet, ShuffleNet and SqueezeNet.

[0330] As an embodiment, the UE 201 supports a 5G system.

[0331] As an embodiment, the node 203 supports a 5G system.

[0332] As an embodiment, the UE 201 at least supports the 6G system.

[0333] As an embodiment, the node 203 at least supports the 6G system.

[0334] Example 3

[0335] Embodiment 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture of a user plane and a control plane according to an embodiment of the present application, as shown in the attached figure. Figure 3 shown.

[0336] 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 3The wireless protocol architecture of the control plane 300 for a first communication node device (RSU (Road Side Unit) in UE or V2X (Vehicle to Everything), vehicle-mounted device or vehicle-mounted communication module) and a second node device (gNB, RSU in UE or V2X, vehicle-mounted device or vehicle-mounted communication module), or between two UEs is presented in three layers: Layer 1 (Layer 1, L1), Layer 2 (Layer 2, L2) and Layer 3 (Layer 3, L3). L1 is the lowest layer and implements various PHY (PHYsical layer) signal processing functions. L1 will be referred to as PHY 301 in this article. L2 305 is above PHY 301 and is responsible for the link between the first node device and the second node device, or between two UEs through PHY301. L2 305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second 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 inter-zone mobility support for the first communication node device between the second communication node device. 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 out-of-order reception caused by HARQ (Hybrid Automatic Repeat reQuest). 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 L3 in the control plane 300 is responsible for obtaining radio resources (ie, radio bearers) and configuring lower layers using RRC signaling between the second communication node device and the first communication node device.The wireless protocol architecture of the user plane 350 includes layer 1 (L1) and layer 2 (L2). The wireless protocol architecture for the first communication node device and the second communication node device in the user plane 350 is substantially the same as the corresponding layers and sublayers in the control plane 300 for the physical layer 351, the PDCP sublayer 354 in L2 355, the RLC sublayer 353 in L2 355, and the MAC sublayer 352 in L2 355, but the PDCP sublayer 354 also provides header compression for upper layer data packets to reduce wireless transmission overhead. The L2 355 in the user plane 350 also includes a SDAP (Service Data Adaptation Protocol) sublayer 356, which is responsible for mapping between QoS (Quality of Service) flows and data radio bearers (DRBs) to support the diversity of services. Although not shown in the figure, the first communication node device may have several upper layers above L2 355, including a network layer (e.g., IP (Internet Protocol) 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, a server, etc.).

[0337] As an example, Figure 3 The wireless protocol architecture in is applicable to the first node in this application.

[0338] As an example, Figure 3 The wireless protocol architecture in is applicable to the second node in this application.

[0339] As an embodiment, the first information unit is generated in the RRC 306.

[0340] As an embodiment, the higher layer mentioned in this application refers to a layer above the physical layer.

[0341] As an embodiment, the higher layer described in the present application includes a MAC layer.

[0342] As an embodiment, the higher layer described in the present application includes an RRC layer.

[0343] Example 4

[0344] Embodiment 4 illustrates a schematic diagram of a first communication device and a second communication device according to an embodiment of the present application, as shown in the attached figure. Figure 4 Attached Figure 4 is a block diagram of a first communication device 410 and a second communication device 450 communicating with each other in an access network.

[0345] The first communication device 410 includes a controller / processor 475 , a memory 476 , a receive processor 470 , a transmit processor 416 , a multi-antenna receive processor 472 , a multi-antenna transmit processor 471 , a transmitter / receiver 418 and an antenna 420 .

[0346] The second communication device 450 includes a controller / processor 459, a memory 460, a data source 467, a transmit processor 468, a receive processor 456, a multi-antenna transmit processor 457, a multi-antenna receive processor 458, a transmitter / receiver 454 and an antenna 452.

[0347] In 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 functionality of L2. In 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 transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for L1 (i.e., physical layer). The transmit processor 416 implements coding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, as well as mapping of signal constellations based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-PSK, M-quadrature amplitude modulation (M-QAM)). The multi-antenna transmit processor 471 performs digital spatial precoding on the coded and modulated symbols, including codebook-based precoding and non-codebook-based precoding and beamforming processing, to generate one or more parallel streams. The transmit processor 416 then maps each parallel stream to a subcarrier, multiplexes the modulated symbols with a reference signal (e.g., pilot) in the time domain and / or frequency domain, and then uses an Inverse Fast Fourier Transform (IFFT) to generate a physical channel carrying a time domain multi-carrier symbol stream. The multi-antenna transmit processor 471 then performs a transmit analog precoding / beamforming operation on the time domain multi-carrier symbol stream. Each transmitter 418 converts the baseband multi-carrier symbol stream provided by the multi-antenna transmit processor 471 into a radio frequency stream, and then provides it to different antennas 420.

[0348] In the transmission from the first communication device 410 to the second communication device 450, at the second communication device 450, each receiver 454 receives a signal through its corresponding antenna 452. Each receiver 454 recovers the information modulated onto the RF carrier and converts the RF stream into a baseband multi-carrier symbol stream and provides it to the receiving processor 456. The receiving processor 456 and the multi-antenna receiving processor 458 implement various signal processing functions of L1. The multi-antenna receiving processor 458 performs a receiving analog precoding / beamforming operation on the baseband multi-carrier symbol stream from the receiver 454. The receiving processor 456 uses a fast Fourier transform (FFT) to convert the baseband multi-carrier symbol stream after the receiving analog precoding / beamforming operation 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 receiving processor 456, where the reference signal will be used for channel estimation, and the data signal is recovered after multi-antenna detection in the multi-antenna receiving processor 458 to any parallel stream with the second communication device 450 as the destination. The symbols on each parallel stream are demodulated and recovered in the receiving processor 456, and soft decisions are generated. The receiving processor 456 then 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. The upper layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of L2. The controller / processor 459 may be associated with a memory 460 storing program codes and data. The memory 460 may be referred to as a computer-readable medium. In DL, the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover the upper layer data packets from the core network. The upper layer data packets are then provided to all protocol layers above L2. Various control signals may also be provided to L3 for L3 processing. The controller / processor 459 is also responsible for error detection using ACKnowledgement (ACK) and / or negative ACKnowledgement (Negative ACKnowledgement, NACK) protocols to support HARQ operations.

[0349] In the transmission from the second communication device 450 to the first communication device 410, at the second communication device 450, a data source 467 is used to provide upper layer data packets to the controller / processor 459. The data source 467 represents all protocol layers above L2. Similar to the transmission 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 L2 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. The transmit processor 468 performs modulation mapping and channel coding processing, and the multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based precoding and non-codebook-based precoding, and beamforming processing. Then, the transmit processor 468 modulates the generated parallel stream into a multi-carrier / single-carrier symbol stream, which is then provided to different antennas 452 via the transmitter 454 after analog precoding / beamforming operations in the multi-antenna transmit processor 457. 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.

[0350] In the transmission from the second communication device 450 to the first communication device 410, the function at the first communication device 410 is similar to the reception function at the second communication device 450 described in the transmission from the first communication device 410 to the second communication device 450. Each receiver 418 receives 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 the multi-antenna reception processor 472 and the reception processor 470. The reception processor 470 and the multi-antenna reception processor 472 jointly implement the functions of L1. The controller / processor 475 implements the L2 functions. The controller / processor 475 can be associated with a memory 476 storing program codes and data. The memory 476 can be referred to as a computer-readable medium. The controller / processor 475 provides demultiplexing between transmission and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover the upper layer data packets from the second communication device 450. The upper layer data packets from the controller / processor 475 can be provided to the core network. The controller / processor 475 is also responsible for error detection using an ACK and / or NACK protocol to support HARQ operations.

[0351] As an embodiment, the second communication device 450 includes: at least one processor and at least one memory, the at least one memory includes computer program code; the at least one memory and the computer program code are configured to be used together with the at least one processor. The second communication device 450 device at least receives a first information unit, the first information unit configures CSI reporting; determines whether to report first information in a first resource set, the first information includes a first CSI; the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in a target time window, the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0352] As an embodiment, the second communication device 450 includes: a memory storing a computer-readable instruction program, wherein the computer-readable instruction program generates an action when executed by at least one processor, and the action includes: receiving a first information unit; determining whether to report the first information in a first resource set.

[0353] As an embodiment, the first communication device 410 includes: at least one processor and at least one memory, the at least one memory includes computer program code; the at least one memory and the computer program code are configured to be used together with the at least one processor. The first communication device 410 device at least sends a first information unit, the first information unit configures CSI reporting; the sender of the first information is the second communication device 450, the second communication device 450 determines whether to report the first information in the first resource set, the first information includes the first CSI; the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in the target time window, the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0354] As an embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program, wherein the computer-readable instruction program generates an action when executed by at least one processor, and the action includes: sending a first information unit.

[0355] As an embodiment, the first node in the present application includes the second communication device 450.

[0356] As an embodiment, the second node in the present application includes the first communication device 410.

[0357] As an embodiment, at least one of {the antenna 420, the transmitter 418, the transmit processor 416, the multi-antenna transmit processor 471, the controller / processor 475, and the memory 476} is used to send a first information unit; and at least one of {the antenna 452, the receiver 454, the receive processor 456, the multi-antenna receive processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive a first information unit.

[0358] As an embodiment, at least one of {the antenna 452, the transmitter 454, the transmit processor 468, the multi-antenna transmit processor 457, the controller / processor 459, the memory 460, and the data source 467} is used to determine whether to report the first information in the first resource set.

[0359] As an embodiment, at least one of {the antenna 452, the transmitter 454, the transmit processor 468, the multi-antenna transmit processor 457, the controller / processor 459, the memory 460, and the data source 467} is used to report first information in a first resource set; at least one of {the antenna 420, the receiver 418, the receive processor 470, the multi-antenna receive processor 472, the controller / processor 475, and the memory 476} is used to receive first information in a first resource set.

[0360] Example 5

[0361] Embodiment 5 illustrates a first flow chart of transmission between a first node and a second node according to an embodiment of the present application, as shown in the attached Figure 5 As shown in the attached Figure 5 In the embodiment, the first node U1 and the second node N2 communicate with each other via a wireless link. It should be noted that the sequence in this embodiment does not limit the signal transmission sequence and implementation sequence in this application.

[0362] For the first node U1, a first information unit is received in step S510; and in step S511, it is determined whether to report the first information in the first resource set.

[0363] For the second node N2, a first information unit is sent in step S520.

[0364] In Example 5, the first information unit configures CSI reporting; the first information includes the first CSI; the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in the target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0365] As an embodiment, the first node U1 is the first node in this application.

[0366] As an embodiment, the second node N2 is the second node in this application.

[0367] As an embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between a base station device and a user equipment.

[0368] As an embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between a relay node device and a user equipment.

[0369] As an embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between user equipments.

[0370] As an embodiment, the second node N2 and the first node U1 communicate with each other via a Uu interface.

[0371] As an embodiment, the second node N2 is a base station maintaining a service cell of the first node U1.

[0372] As an embodiment, the transmission channel occupied by the first information unit includes DL-SCH (DownLink-Shared CHannel, downlink shared channel).

[0373] As an embodiment, the physical layer channel occupied by the first information unit includes PDSCH (Physical Downlink Shared CHannel).

[0374] As an embodiment, step S511 is performed after step S510.

[0375] Example 5a

[0376] Embodiment 5a illustrates a second flow chart of transmission between a first node and a second node according to an embodiment of the present application, as shown in the attached Figure 5aAs shown in the attached Figure 5a In the embodiment, the first node U1a communicates with the second node N2a via a wireless link. It should be noted that the sequence in this embodiment does not limit the signal transmission sequence and implementation sequence in this application.

[0377] For the first node U1a, in step S510a, first information is reported in the first resource set.

[0378] For the second node N2a, in step S520a, first information is received in the first resource set.

[0379] In embodiment 5a, the first node U1a receives at least one CSI-related opportunity in the target time window, and the first node U1a determines to report the first information in the first resource set.

[0380] As an embodiment, the first node U1a is the first node in this application.

[0381] As an embodiment, the second node N2a is the second node in this application.

[0382] As an embodiment, the air interface between the second node N2a and the first node U1a includes a wireless interface between a base station device and a user equipment.

[0383] As an embodiment, the air interface between the second node N2a and the first node U1a includes a wireless interface between a relay node device and a user equipment.

[0384] As an embodiment, the air interface between the second node N2a and the first node U1a includes a wireless interface between user equipments.

[0385] As an embodiment, the second node N2a and the first node U1a communicate with each other via a Uu interface.

[0386] As an embodiment, the second node N2a is a base station maintaining a service cell of the first node U1a.

[0387] As an embodiment, the first node receives at least one CSI-related opportunity in the target time window, and the first node determines to report the first information in the first resource set.

[0388] As an embodiment, the first node U1a determines to report the first information in the first resource set, and reports the first information.

[0389] As an embodiment, the transmission channel occupied by the first information includes UL-SCH (Up Link-Shared CHannel, uplink shared channel).

[0390] As an embodiment, the physical layer channel occupied by the first information includes PUSCH.

[0391] As an embodiment, the physical layer channel occupied by the first information includes PUCCH.

[0392] As an embodiment, the first node U1a determines to report the first information in the first resource set, and reports the first information.

[0393] As a sub-embodiment of this embodiment, the step S510a is as follows: Figure 5 After step S510 described in.

[0394] As an embodiment, the second node N2a determines to receive the first information in the first resource set, and receives the first information.

[0395] As a sub-embodiment of this embodiment, the step S520a is as follows: Figure 5 After step S520 described in.

[0396] Example 6

[0397] Example 6 illustrates two schematic diagrams of the duration of the target time window according to an embodiment of the present application, as shown in the attached figure. Figure 6 As shown in the attached Figure 6 In the figure, the horizontal axis represents time, the unfilled rectangle represents the time domain resources occupied by the target time window, and the duration of the target time window depends on the generation method of the first CSI; case (a) indicates that when the generation method of the first CSI is based on AI, the duration of the target time window is a first time length; case (b) indicates that when the generation method of the first CSI is not based on AI, the duration of the target time window is a second time length.

[0398] As an embodiment, when the generation method of the first CSI is based on AI, the duration of the target time window is a first time length.

[0399] As an embodiment, the first time length includes a positive integer number of time slots greater than 1.

[0400] Typically, one time slot in the present application includes 14 consecutive multi-carrier symbols in the time domain.

[0401] As an embodiment, the first time length includes a positive integer number of milliseconds (ms) greater than 1.

[0402] As an embodiment, the first time length is related to the subcarrier spacing adopted by the first resource set.

[0403] As an embodiment, the first time length is predefined, or the first time length is configured through RRC signaling.

[0404] As an embodiment, the first time length depends on a model for generating the first CSI.

[0405] As an embodiment, the meaning that the first time length depends on the model for generating the first CSI includes: the first time length is one of Y candidate time lengths, the Y candidate time lengths correspond one-to-one to Y AI models respectively, the model for generating the first CSI is one of the Y AI models, and the model for generating the first CSI is used to determine the first time length from the Y candidate time lengths; Y is a positive integer greater than 1.

[0406] As a sub-embodiment of this embodiment, the Y AI models correspond to Y model identifiers.

[0407] As an embodiment, the meaning that the first time length depends on the model for generating the first CSI includes: the first time length is one of Y candidate time lengths, the Y candidate time lengths correspond one-to-one to Y AI model types, respectively, the model for generating the first CSI is one of the Y AI model types, and the model type for generating the first CSI is used to determine the first time length from the Y candidate time lengths; and Y is a positive integer greater than 1.

[0408] As a sub-embodiment of this embodiment, the type of the AI ​​model includes the type of input data of the AI ​​model, and the type of data input to the AI ​​model includes one or more of a precoding matrix, a precoding vector, a small-scale characteristic of a channel, a spatial-frequency domain channel matrix, an angular-delay domain projection channel matrix, SSBRI, and L1-RSRP.

[0409] As a sub-embodiment of this embodiment, the type of the AI ​​model includes the type of output data of the AI ​​model, and the type of data output by the AI ​​model includes one or more of LI, RI, CQI, PMI, CRI, SSBRI, and L1-RSRP.

[0410] As a sub-embodiment of this embodiment, the type of AI model includes a network model of AI, and the network model of AI includes one or more of NN, ANN, CNN, Transformer, LSTM, MLP, GAN, MobileNet, ShuffleNet and SqueezeNet.

[0411] As an embodiment, when the generation method of the first CSI is not based on AI, the duration of the target time window is a second time length.

[0412] As an embodiment, when the generation method of the first CSI is not based on AI, the duration of the target time window is a second time length.

[0413] As an embodiment, the second time length includes a positive integer number of time slots greater than 1.

[0414] As an embodiment, the second time length includes a positive integer number of milliseconds greater than 1.

[0415] As an embodiment, the second time length is related to the subcarrier spacing adopted by the first resource set.

[0416] As an embodiment, the second time length is predefined, or the second time length is configured through RRC signaling.

[0417] Example 7

[0418] Embodiment 7 illustrates a schematic diagram of configuring a CSI resource configuration identifier in a first information unit according to an embodiment of the present application, as shown in the attached figure. Figure 7 As shown in the attached Figure 7 In the embodiment, the first information unit is configured with K CSI resource configuration identifiers, and the K CSI resource configuration identifiers are CSI resource configuration identifier #1, ..., CSI resource configuration identifier #k, ..., CSI resource configuration identifier #K; among the K CSI resource configuration identifiers, at least 2 CSI resource configuration identifiers respectively correspond to CSI generated based on AI and CSI not generated based on AI; the k is a positive integer not greater than K, and the K is a positive integer greater than 1.

[0419] In Embodiment 7, the K CSI resource configuration identifiers are all for one type of measurement, and which CSI resource corresponding to one of the K CSI resource configuration identifiers is used to generate the first CSI depends on the generation method of the first CSI.

[0420] As an embodiment, the first information unit configures K CSI resource configuration identifiers.

[0421] As an embodiment, the first information unit includes K CSI resource configuration identifiers.

[0422] As an embodiment, the first information unit carries K CSI resource configuration identifiers.

[0423] As an embodiment, the K CSI resource configuration identifiers are K non-negative integers respectively.

[0424] As an embodiment, the K CSI resource configuration identifiers respectively indicate K CSI resource configurations.

[0425] As an embodiment, the K CSI resource configuration identifiers are K CSI-ResourceConfigIds respectively.

[0426] As an embodiment, any one of the K CSI resource configuration identifiers indicates a CSI resource setting, and the one CSI resource setting includes a configuration of at least one CSI resource set.

[0427] As a sub-embodiment of this embodiment, any CSI resource set among the at least one CSI resource set is a CSI-IM resource set.

[0428] As a sub-embodiment of this embodiment, the at least one CSI resource set includes at least one of an NZP (None ZeroPower) CSI-RS resource set and an SSB resource set.

[0429] As an embodiment, the SSB described in this application refers to: Synchronization Signal Block.

[0430] As an embodiment, the SSB described in this application refers to: SS (Synchronization Signal) / PBCH (Physical Broadcast Channel) block, synchronization signal / physical broadcast channel block.

[0431] Typically, the reception timings of the PBCH, PSS (Primary Synchronization Signal) and SSS (Secondary Synchronization Signal) are in consecutive symbols and form an SS / PBCH block.

[0432] As an embodiment, the meaning that the K CSI resource configuration identifiers are all for one type of measurement includes: the K CSI resource configuration identifiers are all for channel measurement.

[0433] As an embodiment, the meaning that the K CSI resource configuration identifiers are all for one type of measurement includes: the K CSI resource configuration identifiers are all for resourcesForChannelMeasurement.

[0434] As an embodiment, the meaning that the K CSI resource configuration identifiers are all for one type of measurement includes: the K CSI resource configuration identifiers are all for IM (Interference Measurement).

[0435] As an embodiment, the meaning that the K CSI resource configuration identifiers are all for one type of measurement includes: the K CSI resource configuration identifiers are all for CSI-IM resources.

[0436] As an embodiment, the meaning that the K CSI resource configuration identifiers are all for one type of measurement includes: the K CSI resource configuration identifiers indicate K CSI-IM resource set groups, and the CSI-IM resource set groups are all for IM.

[0437] As an embodiment, the meaning that the K CSI resource configuration identifiers are all for one type of measurement includes: the K CSI resource configuration identifiers are all for csi-IM-ResourcesForInterference.

[0438] As an embodiment, the meaning that the K CSI resource configuration identifiers are all for one type of measurement includes: the K CSI resource configuration identifiers indicate K NZP CSI-RS resource set groups, and the K NZP CSI-RS resource set group resources are all for IM.

[0439] As an embodiment, the meaning that the K CSI resource configuration identifiers are all for one type of measurement includes: the K CSI resource configuration identifiers are all for NZP CSI-RS resources.

[0440] As an embodiment, the meaning that the K CSI resource configuration identifiers are all for one type of measurement includes: the K CSI resource configuration identifiers are all for nzp-CSI-RS-ResourcesForInterference.

[0441] As an embodiment, there are at least two CSI resource configuration identifiers among the K CSI resource configuration identifiers, corresponding to CSI generated based on AI and CSI not generated based on AI, respectively.

[0442] As an embodiment, which CSI resource corresponding to one of the K CSI resource configuration identifiers is used to generate the first CSI depends on the generation method of the first CSI.

[0443] As an embodiment, which CSI resource corresponding to one of the K CSI resource configuration identifiers is used to generate the first CSI depends on whether the first CSI is a CSI generated based on AI.

[0444] As an embodiment, the K CSI resource configuration identifiers include at least a first CSI resource configuration identifier and a second CSI resource configuration identifier, the first CSI resource configuration identifier corresponds to the CSI generated based on AI, and the second CSI resource configuration identifier corresponds to the CSI not generated based on AI; when the generation method of the first CSI is based on AI, the first CSI refers to the CSI resource corresponding to the first CSI resource configuration identifier, and when the generation method of the first CSI is not based on AI, the first CSI refers to the CSI resource corresponding to the second CSI resource configuration identifier.

[0445] As an embodiment, the K CSI resource configuration identifiers include K1 CSI resource configuration identifiers, where K1 is a positive integer not greater than K, and the K1 CSI resource configuration identifiers respectively correspond to identifiers of K1 AI models, the identifier of the AI ​​model for generating the first CSI is one of the identifiers of the K1 AI models, and the identifier of the AI ​​model for generating the first CSI is used to determine the CSI resource corresponding to the CSI resource configuration identifier referenced by the first CSI from the K1 CSI resource configuration identifiers.

[0446] As an embodiment, the CSI resource referenced by the first CSI in the present application means that generation of the first CSI is based on measurement in the CSI resource.

[0447] As an embodiment, the CSI resource referenced by the first CSI in the present application means that generation of the first CSI includes receiving a CSI-RS included in the CSI resource.

[0448] As an embodiment, the CSI resource referenced by the first CSI in the present application means that generation of the first CSI depends on measurements performed on the CSI resource.

[0449] As an embodiment, the CSI resource referenced by the first CSI in the present application means: the first CSI is CSI generated based on an AI model, and the input data of the AI ​​model includes the CSI-RS received in the CSI resource referenced by the first CSI.

[0450] As an embodiment, the CSI resource referenced by the first CSI in the present application means: the first CSI is CSI generated based on an AI model, and the input data of the AI ​​model includes a channel matrix obtained based on the CSI-RS received in the CSI resource referenced by the first CSI.

[0451] Example 8

[0452] Embodiment 8 illustrates a schematic diagram of a first information unit configuration report type according to an embodiment of the present application, as shown in the attached Figure 8 As shown in the attached Figure 8 In the embodiment, the first information unit configures M report types, and the M report types are report type #1, ..., report type #m, ..., report type #M; among the M report types, at least 2 report types correspond to CSI generated based on AI and CSI not generated based on AI, respectively; m is a positive integer not greater than M, and M is a positive integer greater than 1.

[0453] In Embodiment 8, which report type among the M report types is used to generate the first CSI depends on the generation method of the first CSI.

[0454] As an embodiment, the first information unit configures M report types.

[0455] As an embodiment, the first information unit includes M report types.

[0456] As an embodiment, the first information unit carries M report types.

[0457] As an embodiment, the M report types respectively correspond to combinations of M different types of CSI.

[0458] As an embodiment, the M report types indicate M CSI type sets, the M type sets include at least one CSI type, and the candidates of the CSI types include at least one or more of CRI, RI, LI, PMI, CQI, i1, RSRP, and SINR.

[0459] As an embodiment, the M report types correspond to M reportQuantities respectively.

[0460] As an embodiment, there are at least two report types among the M report types, corresponding to CSI generated based on AI and CSI not generated based on AI, respectively.

[0461] As an embodiment, which report type among the M report types is used to generate the first CSI depends on the generation method of the first CSI.

[0462] As an embodiment, which report type among the M report types is used to generate the first CSI depends on whether the first CSI is a CSI generated based on AI.

[0463] As an embodiment, the M report types include at least a first report type and a second report type, the first report type corresponds to CSI generated based on AI, and the second report type corresponds to CSI not generated based on AI; when the generation method of the first CSI is based on AI, the CSI type included in the first CSI reference adopts the first report type, and when the generation method of the first CSI is not based on AI, the CSI type included in the first CSI reference adopts the second report type.

[0464] As an embodiment, the M report types include M1 report types, where M1 is a positive integer not greater than the M, and the M1 report types respectively correspond to identifiers of M1 AI models, the identifier of the AI ​​model for generating the first CSI is one of the identifiers of the M1 AI models, and the identifier of the AI ​​model for generating the first CSI is used to determine the report type adopted by the CSI type included in the first CSI reference from the M1 report types.

[0465] As an embodiment, at least one report type among the M report types corresponds to the CSI generated based on AI, and the report type corresponding to the CSI generated based on AI includes a confidence interval.

[0466] As an embodiment, the English description corresponding to the confidence interval is possibilities.

[0467] As an embodiment, the English description corresponding to the confidence interval is possibility.

[0468] As an embodiment, the English description corresponding to the confidence interval is confidence.

[0469] As an embodiment, the English description corresponding to the confidence interval is accuracy.

[0470] As an embodiment, the English description corresponding to the confidence interval is precision.

[0471] As an embodiment, the confidence interval is a percentage.

[0472] As an embodiment, the confidence interval is a number between 0 and 100.

[0473] As an embodiment, the confidence interval is used to indicate the accuracy of the first CSI.

[0474] As an embodiment, the confidence interval indicates the degree of confidence of the AI ​​model in the first CSI.

[0475] As an embodiment, the report type in the present application includes at least one of the following:

[0476] -cri-RI-PMI-QCI;

[0477] -cri-RI-i1;

[0478] -cri-RI-CQI;

[0479] -cri-RSRP;

[0480] -cri-RSRP;

[0481] -cri-RI-LI-PMI-CQI.

[0482] As an embodiment, the report type in the present application includes at least one of the following:

[0483] -cri-RI-PMI-QCI-confidence interval;

[0484] -cri-RI-i1-confidence interval;

[0485] -cri-RI-CQI-confidence interval;

[0486] -cri-RSRP-confidence interval;

[0487] -cri-RSRP-confidence interval;

[0488] -cri-RI-LI-PMI-CQI-confidence interval.

[0489] Example 9

[0490] Embodiment 9 illustrates a schematic diagram of configuring the report frequency of the first information unit according to an embodiment of the present application, as shown in the attached Fig. 9 As shown in the attached Fig. 9In the embodiment, the first information unit configures L reporting frequency configurations, and the L reporting frequency configurations are reporting frequency configuration #1, ..., reporting frequency configuration #l, ..., reporting frequency configuration #L; there are at least 2 reporting frequency configurations among the L reporting frequency configurations, corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; l is a positive integer not greater than L, and L is a positive integer greater than 1.

[0491] In Embodiment 9, which reporting frequency configuration among the L reporting frequency configurations is used to generate the first CSI depends on the generation method of the first CSI.

[0492] As an embodiment, the first information unit configures L reporting frequency configurations.

[0493] As an embodiment, the first information unit includes L reporting frequency configurations.

[0494] As an embodiment, the first information unit carries L reporting frequency configurations.

[0495] As an embodiment, any reporting frequency configuration among the L reporting frequency configurations indicates a reporting granularity of CSI reporting in the frequency domain.

[0496] As an embodiment, any reporting frequency configuration among the L reporting frequency configurations indicates a frequency domain granularity (frequency granularity) of the CSI reporting.

[0497] As an embodiment, any reporting frequency configuration among the L reporting frequency configurations configures a CSI reporting band.

[0498] As an embodiment, the L reporting frequency configurations correspond to L reportFreqConfigurations respectively.

[0499] As an embodiment, there are at least two reporting frequency configurations among the L reporting frequency configurations, corresponding to CSI generated based on AI and CSI not generated based on AI, respectively.

[0500] As an embodiment, which reporting frequency configuration among the L reporting frequency configurations is used to generate the first CSI depends on the generation method of the first CSI.

[0501] As an embodiment, which reporting frequency configuration among the L reporting frequency configurations is used to generate the first CSI depends on whether the first CSI is a CSI generated based on AI.

[0502] As an embodiment, the L reporting frequency configurations include at least a first reporting frequency configuration and a second reporting frequency configuration, the first reporting frequency configuration corresponds to CSI generated based on AI, and the second reporting frequency configuration corresponds to CSI not generated based on AI; when the generation method of the first CSI is based on AI, the first CSI adopts the first reporting frequency configuration, and when the generation method of the first CSI is not based on AI, the first CSI adopts the second reporting frequency configuration.

[0503] As an embodiment, the L reporting frequency configurations include L1 reporting frequency configurations, where L1 is a positive integer not greater than the L, and the L1 reporting frequency configurations respectively correspond to identifiers of L1 AI models, the identifier of the AI ​​model for generating the first CSI is one of the identifiers of the L1 AI models, and the identifier of the AI ​​model for generating the first CSI is used to determine the reporting frequency configuration adopted by the first CSI from the L1 reporting frequency configurations.

[0504] Example 10

[0505] Embodiment 10 illustrates a schematic diagram of RAN domain AI / ML function deployment according to an embodiment of the present application, as shown in the attached figure. Fig.10 As shown in the attached Fig.10 In this case, gNB can be replaced by network equipment such as eNB or 6G base station.

[0506] In embodiment 10, the management of the ML reasoning functions of multiple base stations is completed by the RAN domain management function 1002, that is, data interaction with the RAN domain MnS (Management Service) consumer / cross-domain management 1001 (see attached Fig.10 ). The RAN domain ML training function 1003 is located in the RAN domain management function 1002; and the ML reasoning function is located in the base station, that is, the AI / ML reasoning function 1004 is located in the gNB 1005, the AI / ML reasoning function 1006 is located in the gNB 1007, and so on.

[0507] AI / ML related functions include ML training function (also called AI training, or AI / ML training), ML testing function, ML inference function (also called AI inference, or AI / ML inference), etc. ML training function, ML testing function, and ML inference function can be deployed independently or co-located. The deployment of AI / ML related functions can be achieved through software, such as downloading and / or running executable files; it can also be achieved through a combination of software and hardware, such as accelerating specific computing units through hardware to increase computing speed or save power consumption.

[0508] For ML training functions, they can be deployed in a cross-domain management system or a domain-specific management system; the domain-specific management system is used to manage the RAN domain or the CN (Core Network) domain. For example, the ML training function for MDA (Management Data Analytics) can be deployed in MDAF (Management Data Analytic Function); ML training for network data analysis can be deployed in NWDAF (Network Data Analytics Function), that is, the ML training function is MTLF (Model Training Logical Function).

[0509] The ML reasoning function can also be deployed in a cross-domain management system or a domain-specific management system; for example, the ML reasoning function is MDAF, or the ML reasoning function is AnLF (Analytics Logical Function) located in NWDAF.

[0510] Similarly, ML testing capabilities can also be deployed in cross-domain management systems, or domain-specific management systems.

[0511] Optionally, the management of the ML reasoning function may also be performed by the base station itself, that is, each base station may independently interact with the RAN domain MnS consumer / cross-domain management 1001 for data.

[0512] It should be noted that Example 10 is merely a non-restrictive implementation method; optionally, the ML training function of the RAN domain may also be deployed in the base station; or optionally, some base stations deploy the ML reasoning function and the ML training function of the RAN domain, while some base stations only deploy the ML reasoning function.

[0513] As an embodiment, a gNB (or base station) in Embodiment 10 is the second node of the present application.

[0514] Embodiment 11

[0515] Embodiment 11 illustrates a schematic diagram of the AI / ML function deployment of a UE according to an embodiment of the present application, as shown in the attached Fig.11 As shown in the attached Fig.11 In the example, the RAN domain ML training function 1104 is optional.

[0516] The UE function 1103 is deployed in the first node of the present application, and the UE function 1103 includes an AI / ML reasoning function 1105; the AI / ML reasoning function 1105 uses an ML model (also called an AI model) for reasoning; an ML model is usually trained before being used for AI / ML reasoning.

[0517] As an embodiment, the UE function 1103 includes a RAN domain ML training function 1104, and the RAN domain ML training function 1104 runs training data through an ML model to derive relevant losses, and adjusts parameters of the ML model based on the calculated losses; the ML training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0518] The above embodiments can reduce the complexity of the base station, or save air interface resources caused by reporting training data; however, the above embodiments place high demands on the processing capability of the UE side.

[0519] Optionally, the UE function 1103 also includes a CN domain ML training function ( Fig.11 not included).

[0520] Optionally, the UE function 1103 further includes an AI / ML deployment function: Fig.11 Not included, used to load ML models and data.

[0521] As an embodiment, the first node indicates whether the ML training function is supported (RAN domain or CN domain) through capability reporting, and the capability reporting is RRC signaling, or NAS (Non-Access Stratum) signaling.

[0522] As an embodiment, the ML model and related metadata are loaded by the first node from a network device or a remote server.

[0523] Optionally, the UE function 1103 is an MnS producer, providing data to the CN domain MnF (Management Function) and / or the RAN domain MnF and / or the cross-domain management system 1101 for management or analysis (as shown by the double arrow 1102).

[0524] Optionally, the UE function 1103 is an MnS consumer, loading data from the CN domain MnF and / or the RAN domain MnF and / or the cross-domain management system 1101 for AI / ML-related management, such as management data requests, ML model activation, and / or ML training, etc. (as shown by the double arrow 1102).

[0525] As an embodiment, the first CSI in the present application is obtained through reasoning of the AI / ML reasoning function 1105.

[0526] As an embodiment, the ML model is NN-based.

[0527] As an embodiment, the ML model is based on ANN.

[0528] As an embodiment, the ML model is based on CNN.

[0529] As an embodiment, the ML model is based on the Transformer architecture.

[0530] As an embodiment, the ML model is based on LSTM.

[0531] As an embodiment, the ML model is based on MLP.

[0532] As an embodiment, the ML model is based on GAN.

[0533] As an embodiment, the ML model is based on a lightweight neural network.

[0534] As a sub-embodiment of this embodiment, the lightweight neural network includes one or more of MobileNet, ShuffleNet and SqueezeNet.

[0535] Example 12

[0536] Embodiment 12 illustrates a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of the present application, as shown in the attached Fig.12 As shown in the attached Fig.12 In the invention, the processing system based on artificial intelligence or machine learning includes a first processor, a second processor, a third processor and a fourth processor.

[0537] In Example 12, the first processor sends a first data set to the second processor, and sends a second data set to the third processor; the second processor generates a target first-category parameter group based on the first data set, and the second processor sends the generated target first-category parameter group to the third processor; the third processor processes the second data set using the target first-category parameter group to obtain a first-category output, and optionally, the third processor sends the first-category output to the fourth processor. Fig.12 In the embodiment, the first type of feedback and the second type of feedback are optional; the second processor includes ML training function; and the third processor includes ML reasoning function.

[0538] As an embodiment, the fourth processor includes ML testing functionality.

[0539] As an embodiment, the fourth processor includes performance monitoring / evaluation of the ML model.

[0540] As an embodiment, the third processor sends the first type of feedback to the second processor; the first type of feedback is used to trigger recalculation or updating of the target first type parameter group, that is, triggering ML initial training or ML retraining.

[0541] As an embodiment, the fourth processor sends a second type of feedback to the first processor; 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.

[0542] As an embodiment, the first processor generates the first data set and the second data set based on measurement of a reference signal.

[0543] As an embodiment, the third processor belongs to the first node, and the fourth processor belongs to the second node.

[0544] As an embodiment, the first type of output includes the first information.

[0545] As an embodiment, the first data set includes training data.

[0546] As an embodiment, the second processor is used to train an ML model, and the trained model is described by the target first-category parameter group.

[0547] As an embodiment, the second processor belongs to the first node; the above method avoids transferring the first data set to the second node.

[0548] As an embodiment, the second processor belongs to the second node; the above method supports joint training and optimizes system performance.

[0549] As an embodiment, the second processor belongs to the core network; the above method supports joint training of the entire network, further optimizing system performance.

[0550] As an embodiment, the second data set includes inference data.

[0551] As an embodiment, the third processor belongs to the first node.

[0552] As an embodiment, the third processing machine constructs a model according to the target first-category parameter group, and then inputs the second data set into the constructed model to obtain the first-category output.

[0553] As an embodiment, the second data set includes a channel matrix measured by the first node in the target time window.

[0554] As an embodiment, the first type of output includes the first CSI.

[0555] As an embodiment, the second data set includes a received reference signal.

[0556] As an embodiment, the second data set includes a reference signal received in a CSI resource referenced by the first CSI in this application.

[0557] As an embodiment, the first type of output includes a channel matrix.

[0558] As an embodiment, the first type of output includes the confidence interval described in this application.

[0559] As an embodiment, the first type of feedback includes the confidence interval described in this application.

[0560] As an embodiment, the third processing machine generates a restored data set according to the first type of output, and an error between the restored data set and the second data set is used to generate the first type of feedback.

[0561] As an embodiment, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model cannot meet the requirements, the second processor will recalculate the target first type parameter group.

[0562] As an embodiment, when the error is too large or has not been updated for too long, the performance of the trained model is considered to be unable to meet the requirements.

[0563] As an embodiment, the target first-category parameter group includes: a convolution kernel, a pooling kernel, a pooling function, an activation function, parameters of a pooling function, or one or more parameters of an activation function.

[0564] As an embodiment, the target first category parameter group includes: one or more of: convolution kernel size, number of convolution layers, convolution step size, pooling kernel size, pooling kernel step size, pooling function, activation function, or number of feature maps.

[0565] Example 13

[0566] Embodiment 13 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of the present application, as shown in the attached Fig.13 As shown in the attached Fig.13 In the embodiment, the first operation and the second operation belong to the first stage, the third operation belongs to the second stage, the fourth operation belongs to the third stage, and the fifth operation belongs to the fourth stage; the lines with arrows indicate the order of the process.

[0567] As an embodiment, the first operation includes AI / ML training, the second operation includes AI / ML testing, the third operation includes AI / ML simulation, the fourth operation includes AI / ML entity loading, and the fifth operation includes AI / ML inference.

[0568] As an embodiment, the first phase includes a training phase, the second phase includes an emulation phase, the third phase includes a deployment phase, and the fourth phase includes an inference phase.

[0569] As an embodiment, the first stage includes AI / ML model training.

[0570] As an embodiment, the first stage includes AI / ML model training and AI / ML testing.

[0571] As an embodiment, the AI / ML model training includes initial training and re-training of one or a group of AI / ML entities.

[0572] As an embodiment, the AI / ML model training relies on training data.

[0573] As an embodiment, the AI / ML model training includes AI / ML entity validation.

[0574] As an embodiment, the AI / ML entity verification is used to evaluate the performance of the AI / ML entity.

[0575] As an embodiment, the AI / ML entity verification relies on verification data.

[0576] As an example, if the result of AI / ML entity verification does not meet expectations, the AI / ML model will be retrained.

[0577] As an embodiment, the AI / ML testing includes testing the verified AI / ML entity to estimate the performance of the trained AI / ML model.

[0578] As an example, if the result of the AI / ML test meets expectations, the AI / ML entity proceeds to the next stage; otherwise the AI / ML model will be retrained.

[0579] As an embodiment, the AI / ML testing relies on test data.

[0580] As an embodiment, the second stage includes AI / ML simulation, which performs reasoning of AI / ML entities in a simulation environment.

[0581] As an embodiment, the AI / ML simulation estimates the performance of AI / ML entity reasoning in a simulation environment before using the AI / ML entity.

[0582] As an embodiment, the second stage is optional.

[0583] As an embodiment, the third stage includes AI / ML entity loading, and the AI / ML entity loading is to obtain the trained AI / ML entity to obtain the desired AI / ML reasoning function.

[0584] As an embodiment, the third stage is optional.

[0585] As an example, when the training function and the inference function are co-located, the third stage is no longer required.

[0586] As an embodiment, the fourth stage includes AI / ML reasoning.

[0587] Embodiment 14

[0588] Embodiment 14 illustrates a structural block diagram of a processing device used in a first node according to an embodiment of the present application, as shown in the attached figure. Fig.14 As shown in the attached Fig.14 In the embodiment, the processing device 1400 in the first node includes a first receiver 1401 and a first transmitter 1402.

[0589] In Embodiment 14, the first receiver 1401 receives a first information unit, and the first information unit configures CSI reporting; the first transmitter 1402 determines whether to report first information in a first resource set, and the first information includes first CSI.

[0590] In Example 14, the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in a target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0591] As an embodiment, the duration of the target time window depends on the generation method of the first CSI; when the generation method of the first CSI is based on AI, the duration of the target time window is a first time length; when the generation method of the first CSI is not based on AI, the duration of the target time window is a second time length.

[0592] As an embodiment, the generation method of the first CSI is based on AI, the duration of the target time window is the first time length, and the first time length depends on a model for generating the first CSI.

[0593] As an embodiment, the first information unit configures K CSI resource configuration identifiers, where K is a positive integer greater than 1, and the K CSI resource configuration identifiers are all for a type of measurement. The K CSI resource configuration identifiers include at least 2 resource configuration identifiers corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which CSI resource configuration identifier among the K CSI resource configuration identifiers corresponds to the CSI resource used to generate the first CSI depends on the generation method of the first CSI.

[0594] As an embodiment, the first information unit configures M report types, where M is a positive integer greater than 1, and at least two of the M report types correspond to CSI generated based on AI and CSI not generated based on AI, respectively; which report type among the M report types is used to generate the first CSI depends on the generation method of the first CSI.

[0595] As an embodiment, at least one report type among the M report types corresponds to the CSI generated based on AI, and the report type corresponding to the CSI generated based on AI includes a confidence interval.

[0596] As an embodiment, the first information unit configures L reporting frequency configurations, where L is a positive integer greater than 1, and at least two of the L reporting frequency configurations correspond to CSI generated based on AI and CSI not generated based on AI, respectively; which reporting frequency configuration of the L reporting frequency configurations is used to generate the first CSI depends on the generation method of the first CSI.

[0597] As an embodiment, the first information unit configures a periodic or semi-continuous report sent on the PUCCH and activated by the MAC CE.

[0598] As an embodiment, the first information unit configures a periodic or semi-continuous report sent on the PUSCH and triggered by the DCI.

[0599] As an embodiment, the first node receives at least one CSI-related opportunity in the target time window, and the first node reports the first information in the first resource set.

[0600] As an embodiment, the first node does not receive a CSI-related opportunity in the target time window, and the first node gives up reporting the first information in the first resource set.

[0601] As an embodiment, the first node performs channel measurement or interference measurement in the target time window.

[0602] As an embodiment, the CSI-related opportunities include at least the first two of a CSI-RS transmission opportunity for channel measurement, a CSI-RS, and a CSI-IM opportunity for interference measurement.

[0603] As an embodiment, the generation method of the first CSI relies on AI, which means one of the following:

[0604] - the first CSI is generated by prediction;

[0605] - the first CSI is generated by inference;

[0606] -The first CSI is generated by a model, and the model is AI or ML or DL;

[0607] -The first CSI is generated based on AI based on measurement;

[0608] - the channel information recovered by the receiver based on the received first CSI is unknown to the first node;

[0609] - a generator for generating the first CSI is obtained based on training;

[0610] -The first CSI does not belong to the CSI defined in 3GPP Rel-18 or earlier versions.

[0611] As an embodiment, the first transmitter 1402 determines to report the first information in the first resource set, and reports the first information.

[0612] As an embodiment, the first transmitter 1402 determines not to report the first information in the first resource set, and abandons reporting the first information.

[0613] As an embodiment, the first node is a terminal device.

[0614] As an embodiment, the first node is user equipment.

[0615] As an embodiment, the first node is a relay node device.

[0616] As an embodiment, the first receiver 1401 includes at least one of {the antenna 452, the receiver 454, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, and the data source 467} in Example 4.

[0617] As an embodiment, the first transmitter 1402 includes at least one of {the antenna 452, the transmitter 454, the transmit processor 468, the multi-antenna transmit processor 457, the controller / processor 459, the memory 460, and the data source 467} in Embodiment 4.

[0618] Embodiment 15

[0619] Embodiment 15 illustrates a structural block diagram of a processing device used in a second node according to an embodiment of the present application, as shown in the attached Fig.15 As shown in the attached Fig.15 In the embodiment, the processing device 1500 in the second node includes a second transmitter 1501 and a second receiver 1502, wherein the second receiver 1502 is optional.

[0620] In Embodiment 15, the second transmitter 1501 sends a first information unit, and the first information unit configures CSI reporting.

[0621] In Example 15, the sender of the first information is a first node, and the first node determines whether to report the first information in a first resource set, and the first information includes a first CSI; the first information unit determines the first resource set; whether the first CSI is reported depends on whether the first node receives at least one CSI-related opportunity in a target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on a generation method of the first CSI; the generation method of the first CSI includes relying on AI.

[0622] As an embodiment, the duration of the target time window depends on the generation method of the first CSI; when the generation method of the first CSI is based on AI, the duration of the target time window is a first time length; when the generation method of the first CSI is not based on AI, the duration of the target time window is a second time length.

[0623] As an embodiment, the generation method of the first CSI is based on AI, the duration of the target time window is the first time length, and the first time length depends on a model for generating the first CSI.

[0624] As an embodiment, the first information unit configures K CSI resource configuration identifiers, where K is a positive integer greater than 1, and the K CSI resource configuration identifiers are all for a type of measurement. The K CSI resource configuration identifiers include at least 2 resource configuration identifiers corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which CSI resource configuration identifier among the K CSI resource configuration identifiers corresponds to the CSI resource used to generate the first CSI depends on the generation method of the first CSI.

[0625] As an embodiment, the first information unit configures M report types, where M is a positive integer greater than 1, and at least two of the M report types correspond to CSI generated based on AI and CSI not generated based on AI, respectively; which report type among the M report types is used to generate the first CSI depends on the generation method of the first CSI.

[0626] As an embodiment, at least one report type among the M report types corresponds to the CSI generated based on AI, and the report type corresponding to the CSI generated based on AI includes a confidence interval.

[0627] As an embodiment, the first information unit configures L reporting frequency configurations, where L is a positive integer greater than 1, and at least two of the L reporting frequency configurations correspond to CSI generated based on AI and CSI not generated based on AI, respectively; which reporting frequency configuration of the L reporting frequency configurations is used to generate the first CSI depends on the generation method of the first CSI.

[0628] As an embodiment, the first information unit configures a periodic or semi-continuous report sent on the PUCCH and activated by the MAC CE.

[0629] As an embodiment, the first information unit configures a periodic or semi-continuous report sent on the PUSCH and triggered by the DCI.

[0630] As an embodiment, the receiver of the first information unit receives at least one CSI-related opportunity in the target time window, and the second node receives the first information in the first resource set.

[0631] As an embodiment, the receiver of the first information unit does not receive the CSI-related opportunity in the target time window, and the first node gives up receiving the first information in the first resource set.

[0632] As an embodiment, the receiver of the first information unit performs channel measurement or interference measurement in the target time window.

[0633] As an embodiment, the CSI-related opportunities include at least the first two of a CSI-RS transmission opportunity for channel measurement, a CSI-RS, and a CSI-IM opportunity for interference measurement.

[0634] As an embodiment, the generation method of the first CSI relies on AI, which means that:

[0635] - the first CSI is generated by prediction;

[0636] - the first CSI is generated by inference;

[0637] -The first CSI is generated by a model, and the model is AI or ML or DL;

[0638] -The first CSI is generated based on AI based on measurement;

[0639] - the channel information recovered by the second node based on the received first CSI is unknown to the transmission;

[0640] - a generator for generating the first CSI is obtained based on training;

[0641] -The first CSI does not belong to the CSI defined in 3GPP Rel-18 or a version earlier than 3GPP Rel-18.

[0642] As an embodiment, the second receiver 1502 determines to receive the first information in the first resource set, and receives the first information.

[0643] As an embodiment, the second receiver 1502 determines not to receive the first information in the first resource set, and abandons receiving the first information.

[0644] As an embodiment, the second receiver 1502 determines to receive the first information in the first resource set.

[0645] As an embodiment, the second node is a base station device.

[0646] As an embodiment, the second node is user equipment.

[0647] As an embodiment, the second node is a TRP.

[0648] As an embodiment, the second transmitter 1501 includes at least one of {the antenna 420, the transmitter 418, the transmit processor 416, the multi-antenna transmit processor 471, the controller / processor 475, and the memory 476} in Embodiment 4.

[0649] As an embodiment, the second receiver 1502 includes at least one of {the antenna 420, the receiver 418, the receiving processor 470, the multi-antenna receiving processor 472, the controller / processor 475, and the memory 476} in Embodiment 4.

[0650] A person of ordinary skill in the art can understand that all or part of the steps in the above method can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a hard disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module unit in the above embodiment can be implemented in the form of hardware or in the form of a software function module, and the present application is not limited to any specific form of software and hardware combination. The user equipment, terminal and UE in the present application include but are not limited to drones, communication modules on drones, remote-controlled aircraft, aircraft, small aircraft, mobile phones, tablet computers, notebooks, vehicle-mounted communication equipment, transportation tools, vehicles, RSUs, wireless sensors, Internet cards, Internet of Things terminals, RFID (Radio Frequency Identification, Radio Frequency Identification Technology) terminals, NB-IoT (Narrow Band Internet of Things, Narrow Band Internet of Things) terminals, MTC (Machine Type Communication, Machine Type Communication) terminals, eMTC (enhanced MTC, enhanced MTC) terminals, data cards, Internet cards, vehicle-mounted communication equipment, low-cost mobile phones, low-cost tablet computers and other wireless communication devices. The base stations or system equipment in this application include but are not limited to macrocell base stations, microcell base stations, small cell base stations, home base stations, relay base stations, eNB (evolved Node B), gNB, TRP, GNSS (Global Navigation Satellite System), relay satellites, satellite base stations, aerial base stations, RSU, drones, test equipment, such as transceivers that simulate some functions of base stations or signaling testers and other wireless communication equipment.

[0651] It should be understood by those skilled in the art that the present invention may be implemented in other specified forms without departing from its core or essential features. Therefore, the embodiments disclosed herein should be considered illustrative rather than restrictive in any way. The scope of the invention is determined by the appended claims rather than the preceding description, and all modifications within their equivalent meanings and regions are considered to be included therein.

Claims

1. A method for a terminal in wireless communication and artificial intelligence, characterized in that: include: receiving a first information unit, wherein the first information unit configures CSI reporting; Determine whether to report first information in a first resource set, where the first information includes first CSI; Among them, the first information unit determines the first resource set; whether the first CSI is reported depends on whether the terminal receives at least one CSI-related opportunity in the target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on the generation method of the first CSI; the generation method of the first CSI includes relying on AI.

2. The method according to claim 1, characterized in that The duration of the target time window depends on the generation method of the first CSI; when the generation method of the first CSI is based on AI, the duration of the target time window is a first time length; when the generation method of the first CSI is not based on AI, the duration of the target time window is a second time length.

3. The method according to claim 2, characterized in that The generation method of the first CSI is based on AI, the duration of the target time window is the first time length, and the first time length depends on a model for generating the first CSI.

4. The method according to any one of claims 1 to 3, characterized in that: The first information unit is configured with K CSI resource configuration identifiers, where K is a positive integer greater than 1, and the K CSI resource configuration identifiers are all for a type of measurement, and the K CSI resource configuration identifiers include at least 2 resource configuration identifiers corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which CSI resource corresponding to one of the K CSI resource configuration identifiers is used to generate the first CSI depends on the generation method of the first CSI.

5. The method according to any one of claims 1 to 4, characterized in that: The first information unit configures M report types, where M is a positive integer greater than 1, and at least two of the M report types correspond to CSI generated based on AI and CSI not generated based on AI, respectively; which report type among the M report types is used to generate the first CSI depends on the generation method of the first CSI.

6. The method according to claim 5, characterized in that At least one report type among the M report types corresponds to the CSI generated based on AI, and the report type corresponding to the CSI generated based on AI includes a confidence interval.

7. The method according to any one of claims 1 to 6, characterized in that: The first information unit configures L reporting frequency configurations, where L is a positive integer greater than 1, and at least two of the L reporting frequency configurations correspond to CSI generated based on AI and CSI not generated based on AI, respectively; which reporting frequency configuration of the L reporting frequency configurations is used to generate the first CSI depends on the generation method of the first CSI.

8. 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 7.

9. A method for a base station in wireless communication and artificial intelligence, characterized in that: include: Sending a first information unit, where the first information unit configures CSI reporting; Among them, the receiver of the first information unit is a terminal, and the terminal determines whether to report first information in a first resource set, and the first information includes a first CSI; the first information unit determines the first resource set; whether the first CSI is reported depends on whether the terminal receives at least one CSI-related opportunity in a target time window, and the CSI-related opportunity is for channel measurement or interference measurement; the target time window depends on a generation method of the first CSI; the generation method of the first CSI includes relying on AI.

10. The method according to claim 9, characterized in that The duration of the target time window depends on the generation method of the first CSI; when the generation method of the first CSI is based on AI, the duration of the target time window is a first time length; when the generation method of the first CSI is not based on AI, the duration of the target time window is a second time length.

11. The method according to claim 10, characterized in that The generation method of the first CSI is based on AI, the duration of the target time window is the first time length, and the first time length depends on a model for generating the first CSI.

12. The method according to any one of claims 9 to 11, characterized in that The first information unit is configured with K CSI resource configuration identifiers, where K is a positive integer greater than 1, and the K CSI resource configuration identifiers are all for a type of measurement, and the K CSI resource configuration identifiers include at least 2 resource configuration identifiers corresponding to CSI generated based on AI and CSI not generated based on AI, respectively; which CSI resource corresponding to one of the K CSI resource configuration identifiers is used to generate the first CSI depends on the generation method of the first CSI.

13. The method according to any one of claims 9 to 12, characterized in that The first information unit configures M report types, where M is a positive integer greater than 1, and at least two of the M report types correspond to CSI generated based on AI and CSI not generated based on AI, respectively; which report type among the M report types is used to generate the first CSI depends on the generation method of the first CSI.

14. The method according to claim 13, characterized in that At least one report type among the M report types corresponds to the CSI generated based on AI, and the report type corresponding to the CSI generated based on AI includes a confidence interval.

15. The method according to any one of claims 9 to 14, characterized in that The first information unit configures L reporting frequency configurations, where L is a positive integer greater than 1, and at least two of the L reporting frequency configurations correspond to CSI generated based on AI and CSI not generated based on AI, respectively; which reporting frequency configuration of the L reporting frequency configurations is used to generate the first CSI depends on the generation method of the first CSI.

16. 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 9 to 15.

Images