A method and apparatus used in a node for wireless communication

Abstract

The application discloses a method and device used in a node for wireless communication. A first processor receives a first configuration information block and a second configuration information block, the first configuration information block being connected to the second configuration information block; receives first signaling, the first signaling triggering first reported information; in response to the reception of the first signaling, performs a first inference, parameters of the first inference depending on the second configuration information block; and sends the first reported information, the first reported information including a first metric; wherein the first metric depends on measurements on M1 RS resources and an output of the first inference, an input of the first inference depending on measurements on M2 RS resources; the first configuration information block indicating the M1 RS resources, and the second configuration information block indicating the M2 RS resources. The application optimizes reporting and improves overall system performance.

Description

Technical Field

[0001] This application relates to transmission methods and apparatus in wireless communication systems, and more particularly to methods and apparatus for measurement and reporting in wireless communication systems. Background Technology

[0002] In traditional wireless communication, the UE (User Equipment) reports various auxiliary information obtained through measurements of downlink signals and / or channels. This includes channel information, beam management-related auxiliary information, positioning-related auxiliary information, HARQ-ACK (Hybrid Automatic Repeat reQuest Acknowledgement) information, and beam / radio link failure auxiliary information. Channel information includes, but is not limited to, one or more of CRI (Channel State Information Reference Signal Resource Indicator), RI (Rank Indicator), PMI (Precoding Matrix Indicator), 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 based on the reported information, such as the cell to be used, MCS (Modulation and Coding Scheme), TPMI (Transmitted Precoding Matrix Indicator), and TCI (Transmission Configuration Indication). In addition, UE reports can be used to optimize network parameters, such as better cell coverage, switching base stations on and off based on UE location, and so on.

[0003] With the adoption of new technologies, the increase in the number of antennas, the diversification of application scenarios, and the increasing demands on system performance, traditional measurement and reporting methods incur significant redundancy overhead. Therefore, in NR Release 18, research on AI (Artificial Intelligence) / ML (Machine Learning) technologies was initiated to explore their impact on system performance and design. AI / ML technologies may also play a crucial role in future 6G communications. Compared to traditional processing methods, AI / ML offers advantages such as training-based and deployment-required features. According to the 3GPP (3rd Generation Partner Project) standard TS38.300, AI / ML models and algorithms extend beyond the scope of 3GPP. Summary of the Invention

[0004] The inventors discovered through research that AI / ML technologies have unique requirements compared to existing technologies, such as the need for timely retraining, deployment, and performance monitoring to ensure consistency between inference and training. Therefore, enhancing measurement and reporting mechanisms to meet these requirements and improve the performance gains offered by AI / ML is a problem that needs to be solved.

[0005] To address the aforementioned problems, this application discloses a solution. It should be noted that while this application is motivated by the application of AI / ML models, and many embodiments are specifically designed for AI / ML, it is also applicable to other solutions, such as traditional measurement and reporting schemes. Although the specification of this application involves descriptions of some AI / ML models and algorithms, those skilled in the art will understand that these descriptions are not essential or irreplaceable for solutions related to wireless cellular communication. Furthermore, adopting a unified solution across different scenarios (including but not limited to AI / ML-based solutions and traditional measurement and reporting schemes) helps reduce signaling overhead / complexity, hardware complexity, and cost. Unless otherwise specified, embodiments and features in any node of this application can be applied to any other node. Unless otherwise specified, embodiments and features in any embodiment of this application can be arbitrarily combined with each other.

[0006] Furthermore, although some embodiments of this application are described based on the 5G protocol, this application is also applicable to communication standards after 5G without conflict.

[0007] When necessary, the interpretation of terms in this application shall refer to the definitions in the 3GPP specification protocol TS38 series, or the definitions in the 3GPP specification protocol TS28 series.

[0008] This application discloses a method used in a first node of wireless communication, characterized by comprising:

[0009] Receive a first configuration information block and a second configuration information block, wherein the first configuration information block is connected to the second configuration information block;

[0010] Receive a first signaling message, the first signaling message triggers a first reporting message, the first reporting message depends on the first configuration information block;

[0011] In response to the receipt of the first signaling, a first inference is performed, the parameters of which depend on the second configuration information block;

[0012] Send the first reported information, which includes a first metric;

[0013] Wherein, the first metric depends on the measurement on M1 RS (Reference Signal) resources and the output of the first inference, and the input of the first inference depends on the measurement on M2 RS resources; the first configuration information block indicates the M1 RS resources, the second configuration information block indicates the M2 RS resources, and M1 and M2 are positive integers greater than 1.

[0014] As an example, the problem this application aims to solve includes: how to enhance the reporting mechanism to meet the performance monitoring needs of AI models or ML models; in the above method, the first node reports the first reporting information including a first metric, the first metric depending on the measurement on M1 RS resources and the output of the first inference, thus solving this problem.

[0015] As an example, the benefits of the above method include: optimized AI / ML performance.

[0016] As an example, the benefits of the above method include: optimizing the reporting related to performance monitoring of AI models or ML models, thereby improving the overall performance of the system.

[0017] As an example, the advantages of the above method include: more flexible signaling design.

[0018] As an example, the advantages of the above method include good backward compatibility.

[0019] As an example, the advantages of the above method include: reduced signaling and reporting overhead.

[0020] According to one aspect of this application, the first configuration information block indicates whether the first reported information includes the output of the first inference.

[0021] As an example, the advantages of the above method include: better flexibility, while avoiding ambiguity between the first node and the target recipient of the first reported information regarding whether the first reported information includes the output of the first inference.

[0022] As an example, the advantages of the above method include: reduced reporting overhead.

[0023] According to one aspect of this application, the first reported information does not include the output of the first inference.

[0024] As an example, the advantages of the above method include: reduced reporting overhead.

[0025] As an example, the advantages of the above method include: reduced signaling overhead.

[0026] According to one aspect of this application, the first signaling indicates a first triggering state, the first triggering state indicating only the first configuration information block of both the first configuration information block and the second configuration information block.

[0027] As an example, the problem to be solved by the above method includes: how to ensure that the inference results and monitoring results compared with each other in the performance monitoring of AI models or ML models are comparable; in the above method, when a performance monitoring-related report of an AI model or ML model is triggered, the inference of the AI ​​model or ML model will be triggered even if the inference-related report of the AI ​​model or ML model is not triggered, thus solving this problem.

[0028] As an example, the advantages of the above method include: it does not directly trigger reporting related to AI model or ML model inference, thus reducing reporting overhead.

[0029] According to one aspect of this application, the first trigger state indicates whether the first reported information includes the output of the first inference.

[0030] As an example, the advantages of the above method include: better flexibility, while avoiding ambiguity between the first node and the target recipient of the first reported information regarding whether the first reported information includes the output of the first inference.

[0031] As an example, the advantages of the above method include: reduced reporting overhead.

[0032] According to one aspect of this application, the first signaling indicates a second triggering state, and the second triggering state indicates the first configuration information block and the second configuration information block.

[0033] As an example, the problem to be solved by the above method is: how to ensure that the inference results and monitoring results compared with each other in the performance monitoring of AI model or ML model are comparable; the above method solves this problem by using a trigger state to simultaneously trigger the performance monitoring-related reporting and inference-related reporting of an AI model or ML model.

[0034] As an example, the advantages of the above method include: when performance monitoring-related reports and inference-related reports of an AI model or ML model are triggered simultaneously, only performance monitoring-related reports are sent, and inference-related reports are not sent; this method can ensure the reliability of performance monitoring and avoid unnecessary reporting, thus reducing reporting overhead.

[0035] According to one aspect of this application, it is characterized by comprising:

[0036] As a response to the reception of the first signaling, measurements are taken on the M2 RS resources.

[0037] As an example, the problems to be solved by the above method include: how to ensure that the inference results and monitoring results compared with each other in the performance monitoring of AI models or ML models are comparable; in the above method, when a performance monitoring-related report of an AI model or ML model is triggered, a set of RS resources for channel measurement used as the input of the inference of this AI model or ML model is triggered simultaneously, ensuring that the inference of this model can obtain the measurement of RS resources obtained in a matching channel environment as the performance monitoring, thus guaranteeing the reliability of performance monitoring.

[0038] As an example, the advantages of the above method include: reducing the overhead of RS resources.

[0039] According to one aspect of this application, the M1 RS resources and the M2 RS resources are associated with the same association identifier.

[0040] As an example, the benefits of the above method include: ensuring consistency between inference and performance monitoring, and improving the performance of AI / ML models.

[0041] As an example, the advantages of the above method include: simple design and reduced signaling overhead.

[0042] As an example, the advantages of the above method include: good forward compatibility.

[0043] According to one aspect of this application, the first metric depends on measurements on the M1 RS resources in a first time window and the output of the first inference for a first time interval, wherein the first metric is obtained under the condition that the difference between the first time window and the first time interval is less than or not greater than a first threshold.

[0044] As an example, the problem to be solved by this application includes: how to ensure that the inference results and monitoring results compared with each other in the performance monitoring of AI models or ML models are comparable, for example, but not limited to, the inference results and monitoring results are for channels located in the same coherent time period; in the above method, the difference between the first time window and the first time interval is limited to a first threshold, thus solving this problem.

[0045] As an example, the advantages of the above method include: simple design and minimal changes to the standard.

[0046] As an example, the benefits of the above method include: optimized AI / ML performance.

[0047] According to one aspect of this application, a terminal is characterized in that the terminal comprises:

[0048] One or more processors and memory;

[0049] The memory is coupled to the one or more processors and is used to store computer program code, which includes computer instructions. The one or more processors invoke the computer instructions to cause the terminal to execute the method in the first node.

[0050] This application discloses a method used in a second node for wireless communication, characterized by comprising:

[0051] Send a first configuration information block and a second configuration information block, wherein the first configuration information block is connected to the second configuration information block;

[0052] Send a first signaling message, which triggers a first reporting message, the first reporting message depending on the first configuration information block;

[0053] Receive the first reported information, which includes a first metric;

[0054] Wherein, the first signaling triggers the sender of the first reported information to execute the first inference, the parameters of the first inference depend on the second configuration information block; the first metric depends on the measurement on M1 RS resources and the output of the first inference, the input of the first inference depends on the measurement on M2 RS resources; the first configuration information block indicates the M1 RS resources, the second configuration information block indicates the M2 RS resources, and M1 and M2 are positive integers greater than 1.

[0055] According to one aspect of this application, the first configuration information block indicates whether the first reported information includes the output of the first inference.

[0056] According to one aspect of this application, the first reported information does not include the output of the first inference.

[0057] According to one aspect of this application, the first signaling indicates a first triggering state, the first triggering state indicating only the first configuration information block of both the first configuration information block and the second configuration information block.

[0058] According to one aspect of this application, the first trigger state indicates whether the first reported information includes the output of the first inference.

[0059] According to one aspect of this application, the first signaling indicates a second triggering state, and the second triggering state indicates the first configuration information block and the second configuration information block.

[0060] According to one aspect of this application, it is characterized by comprising:

[0061] The first signaling triggers the sender of the first reported information to measure on the M2 RS resources.

[0062] According to one aspect of this application, the M1 RS resources and the M2 RS resources are associated with the same association identifier.

[0063] According to one aspect of this application, the first metric depends on measurements on the M1 RS resources in a first time window and the output of the first inference for a first time interval, wherein the first metric is obtained under the condition that the difference between the first time window and the first time interval is less than or not greater than a first threshold.

[0064] According to one aspect of this application, a base station is characterized in that the base station comprises:

[0065] One or more processors and memory;

[0066] The memory is coupled to the one or more processors and is used to store computer program code, which includes computer instructions. The one or more processors invoke the computer instructions to cause the base station to perform the method in the second node.

[0067] This application discloses a first node used for wireless communication, characterized in that it comprises:

[0068] A first processor receives a first configuration information block and a second configuration information block, wherein the first configuration information block is connected to the second configuration information block.

[0069] The first processor receives a first signaling, which triggers a first reporting information, which depends on the first configuration information block.

[0070] The first processor, in response to the receipt of the first signaling, performs a first inference, the parameters of which depend on the second configuration information block;

[0071] The first processor sends the first reported information, which includes a first metric.

[0072] Wherein, the first metric depends on the measurement on M1 RS resources and the output of the first inference, and the input of the first inference depends on the measurement on M2 RS resources; the first configuration information block indicates the M1 RS resources, the second configuration information block indicates the M2 RS resources, and M1 and M2 are positive integers greater than 1.

[0073] This application discloses a second node used for wireless communication, characterized in that it comprises:

[0074] The second processor sends a first configuration information block and a second configuration information block, wherein the first configuration information block is connected to the second configuration information block.

[0075] The second processor sends a first signaling message, which triggers a first reporting message, the first reporting message depending on the first configuration information block;

[0076] The second processor receives the first reported information, which includes a first metric.

[0077] Wherein, the first signaling triggers the sender of the first reported information to execute the first inference, the parameters of the first inference depend on the second configuration information block; the first metric depends on the measurement on M1 RS resources and the output of the first inference, the input of the first inference depends on the measurement on M2 RS resources; the first configuration information block indicates the M1 RS resources, the second configuration information block indicates the M2 RS resources, and M1 and M2 are positive integers greater than 1.

[0078] As an example, compared with conventional solutions, this application has the following advantages:

[0079] AI / ML performance has been optimized;

[0080] The reporting of performance monitoring for AI or ML models has been optimized, thereby improving the overall performance of the system.

[0081] More flexible signaling design;

[0082] It reduces signaling and reporting overhead. Attached Figure Description

[0083] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0084] Figure 1 A flowchart illustrating a first configuration information block, a second configuration information block, a first signaling, and a first reporting information according to an embodiment of this application is shown.

[0085] Figure 2 A schematic diagram of a network architecture according to an embodiment of this application is shown;

[0086] Figure 3 A schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application is shown;

[0087] Figure 4 A schematic diagram of a first communication device and a second communication device according to an embodiment of this application is shown;

[0088] Figure 5 A flowchart of the transmission according to an embodiment of this application is shown;

[0089] Figure 6 A schematic diagram is shown illustrating whether a first configuration information block, according to an embodiment of this application, indicates whether a first reported information includes the output of a first inference.

[0090] Figure 7A schematic diagram illustrating a first reported information according to an embodiment of this application does not include the output of the first inference;

[0091] Figure 8 A schematic diagram showing a first signaling indication of a first triggering state according to an embodiment of this application is illustrated;

[0092] Figure 9 A schematic diagram illustrating whether a first trigger state, according to an embodiment of this application, indicates whether a first reported information includes the output of a first inference;

[0093] Figure 10 A schematic diagram illustrating a first signaling indication of a second triggering state according to an embodiment of this application is shown;

[0094] Figure 11 A schematic diagram of measurements on M2 RS resources according to an embodiment of this application is shown;

[0095] Figure 12 A schematic diagram illustrating the association of RS resources with the same association identifier according to one embodiment of this application is shown;

[0096] Figure 13 A schematic diagram illustrating a first metric, a first time window, a first time interval, and a first threshold according to an embodiment of this application is shown;

[0097] Figure 14 A schematic diagram of a first time interval and a first time window according to an embodiment of this application is shown;

[0098] Figure 15 A schematic diagram of a first time interval and a first time window according to an embodiment of this application is shown;

[0099] Figure 16 A schematic diagram of a first time interval and a first time window according to an embodiment of this application is shown;

[0100] Figure 17 A schematic diagram showing a first configuration information block indicating a first threshold according to an embodiment of this application is illustrated;

[0101] Figure 18 A schematic diagram showing a first reporting information indicating a first threshold according to an embodiment of this application is illustrated;

[0102] Figure 19 A schematic diagram of a first metric according to an embodiment of this application is shown;

[0103] Figure 20 A schematic diagram of an artificial intelligence or machine learning-based processing system according to an embodiment of this application is shown;

[0104] Figure 21 A schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application is shown;

[0105] Figure 22 A schematic diagram illustrating the deployment of AI functionality according to an embodiment of this application is shown;

[0106] Figure 23 A schematic diagram illustrating the deployment of AI functionality according to an embodiment of this application is shown;

[0107] Figure 24 A schematic diagram illustrating the deployment of AI functionality according to an embodiment of this application is shown;

[0108] Figure 25 A schematic diagram illustrating the deployment of AI functionality according to an embodiment of this application is shown;

[0109] Figure 26 A structural block diagram of a processing apparatus for a first node according to an embodiment of this application is shown;

[0110] Figure 27 A structural block diagram of a processing apparatus for a second node according to an embodiment of this application is shown. Detailed Implementation

[0111] The technical solutions of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Based on considerations of flexibility, complexity, cost, and compatibility, those skilled in the art are motivated to flexibly combine the embodiments in different drawings without conflict, for example (but not limited to) the accompanying drawings. Figure 1 Examples and appendices Figure 5 -Appendix Figure 25 The embodiments in the appendix Figure 5 Examples and appendices Figure 6 -Appendix Figure 25 Examples, etc.

[0112] Example 1

[0113] Example 1 illustrates a flowchart of a first configuration information block, a second configuration information block, a first signaling, and a first reporting information according to an embodiment of this application, as shown in the attached diagram. Figure 1 As shown. In the appendix Figure 1 In the 100 shown, each box represents a step. In particular, the order of the steps in the boxes does not represent a specific temporal relationship between the steps.

[0114] In Embodiment 1, the first node in this application receives a first configuration information block and a second configuration information block in step 101, the first configuration information block being connected to the second configuration information block; in step 102, it receives a first signaling, the first signaling triggering a first reporting information, the first reporting information depending on the first configuration information block; in step 103, as a response to the receipt of the first signaling, it performs a first inference, the parameters of the first inference depending on the second configuration information block; in step 104, it sends the first reporting information, the first reporting information including a first metric; wherein the first metric depends on measurements on M1 RS resources and the output of the first inference, the input of the first inference depends on measurements on M2 RS resources; the first configuration information block indicates the M1 RS resources, the second configuration information block indicates the M2 RS resources, and M1 and M2 are positive integers greater than 1.

[0115] As one embodiment, the first configuration information block is carried by higher layer signaling.

[0116] As an example, the first configuration information block is carried by RRC (Radio Resource Control) signaling.

[0117] As an example, the first configuration information block is carried by one or more RRC IEs (Information Elements).

[0118] As one embodiment, the first configuration information block includes some or all of the information of each of one or more RRC IEs.

[0119] As one embodiment, the first configuration information block includes some or all of the information in the CSI-ReportConfig IE.

[0120] As an example, the first configuration information block is a CSI-ReportConfig IE.

[0121] As one embodiment, the first configuration information block includes some or all of the information in the CSI-AperiodicTriggerStateList IE.

[0122] As one example, the first configuration information block includes some or all of the information in CellGroupConfig IE.

[0123] As one embodiment, the first configuration information block includes some or all of the information in the ServingCellConfig IE.

[0124] As one embodiment, the first configuration information block includes some or all of the information in the CSI-MeasConfig IE.

[0125] As one embodiment, the first configuration information block includes some or all of the information in the CSI-ResourceConfig IE.

[0126] As one embodiment, the first configuration information block includes some or all of the information in the CSI-SSB-ResourceSet IE.

[0127] As one embodiment, the first configuration information block includes some or all of the information in the NZP-CSI-RS-ResourceSet IE.

[0128] As an example, the first configuration information block is used to configure a report.

[0129] As an example, the first configuration information block is used to configure a CSI (Channel State Information) report.

[0130] As an example, the first configuration information block is used for configuration monitoring.

[0131] As an example, the first configuration information block is used for configuration monitoring and reporting.

[0132] As an example, the first configuration information block is used to configure the monitoring of the first inference.

[0133] As an example, monitoring a reasoning operation refers to monitoring the performance of that reasoning operation.

[0134] As an example, monitoring a reasoning refers to monitoring the model of the reasoning.

[0135] As an example, monitoring a reasoning operation refers to monitoring the performance of the model used for that reasoning operation.

[0136] As an example, the model refers to an AI model or an ML model.

[0137] As one embodiment, the second configuration information block is carried by higher-level signaling.

[0138] As one embodiment, the second configuration information block is carried by RRC signaling.

[0139] As one example, the second configuration information block is carried by one or more RRC IEs.

[0140] As one embodiment, the second configuration information block includes some or all of the information of each of one or more RRC IEs.

[0141] As one embodiment, the second configuration information block includes some or all of the information in the CSI-ReportConfig IE.

[0142] As an example, the second configuration information block is a CSI-ReportConfig IE.

[0143] As one embodiment, the second configuration information block includes some or all of the information in the CSI-AperiodicTriggerStateList IE.

[0144] As one embodiment, the second configuration information block includes some or all of the information in CellGroupConfig IE.

[0145] As one embodiment, the second configuration information block includes some or all of the information in the ServingCellConfig IE.

[0146] As one embodiment, the second configuration information block includes some or all of the information in the CSI-MeasConfig IE.

[0147] As an example, the second configuration information block is used to configure the first inference.

[0148] As an example, the second configuration information block is used to configure the parameters of the first inference.

[0149] As one embodiment, the second configuration information block includes the parameters of the first inference.

[0150] As one example, the second configuration information block is used to configure a report.

[0151] As an example, the second configuration information block is used to configure a CSI report.

[0152] As an example, the second configuration information block is used to configure the first inference and a reporting.

[0153] As one embodiment, the second configuration information block and the first configuration information block are each carried by two RRC IEs.

[0154] As one embodiment, the second configuration information block and the first configuration information block are carried by different domains of the same RRC IE.

[0155] As one embodiment, the second configuration information block and the first configuration information block are configured for the same cell.

[0156] As one embodiment, the second configuration information block and the first configuration information block are configured in the same cell.

[0157] As one embodiment, the second configuration information block and the first configuration information block are received on the same PDSCH (Physical Downlink Shared Channel).

[0158] As one embodiment, the second configuration information block and the first configuration information block are received on different PDSCHs.

[0159] As one embodiment, the reception of the second configuration information block is earlier than the reception of the first configuration information block.

[0160] As an example, the first configuration information block is used to configure the monitoring of the first inference, and the second configuration information block is used to configure the first inference.

[0161] As an example, the second configuration information block indicates the first inference.

[0162] As one embodiment, the second configuration information block indicates a first identifier, and the first inference corresponds to the first identifier.

[0163] As one embodiment, the second configuration information block indicates the first inference by indicating the first identifier.

[0164] As an example, the second configuration information block indicates the model of the first inference.

[0165] As an example, the first inference corresponds to a first identifier, and the second configuration information block indicates the model of the first inference by indicating the first identifier.

[0166] As an example, the first identifier is an associated identifier.

[0167] As an example, the first configuration information block indicates the first inference.

[0168] As one embodiment, the first configuration information block indicates a first identifier, and the first inference corresponds to the first identifier.

[0169] As an example, the first configuration information block indicates the first inference by indicating the first identifier.

[0170] As one embodiment, the first reasoning corresponding to the first identifier includes: the first reasoning being identified by the first identifier.

[0171] As an example, the first inference corresponding to the first identifier includes: the inference dataset of the first inference is identified by the first identifier.

[0172] As one embodiment, the first inference corresponding to the first identifier includes: the AI ​​function or AI entity performing the first inference is identified by the first identifier.

[0173] As an example, the first inference corresponding to the first identifier includes: the model of the first inference is identified by the first identifier.

[0174] As an example, the first inference corresponding to the first identifier includes: the training of the model of the first inference is identified by the first identifier.

[0175] As an example, the first inference corresponding to the first identifier includes: the training dataset of the model of the first inference is identified by the first identifier.

[0176] As one embodiment, the first inference corresponding to the first identifier includes: the AI ​​function or AI entity trained by the model performing the first inference is identified by the first identifier.

[0177] As an example, the first inference corresponding to the first identifier includes: the performance monitoring of the model of the first inference is identified by the first identifier.

[0178] As an example, the first inference corresponding to the first identifier includes: the performance monitoring dataset of the model of the first inference is identified by the first identifier.

[0179] As one embodiment, the first inference corresponding to the first identifier includes: the function targeted by the first inference is identified by the first identifier.

[0180] As an example, the first inference corresponding to the first identifier includes: the function targeted by the model of the first inference is identified by the first identifier.

[0181] As one embodiment, the first inference corresponding to the first identifier includes: one or more RS resources associated with the first identifier being used to obtain channel measurements of the inference dataset that generates the first inference or the training dataset of the model of the first inference.

[0182] As one embodiment, the first inference corresponding to the first identifier includes: the output of the first inference involves multiple RS resources associated with the first identifier.

[0183] As an example, an RS resource associated with an association identifier includes: the RS resource and another RS ​​resource associated with the association identifier are used to generate the training dataset or inference dataset of the same model.

[0184] As an example, an RS resource associated with an association identifier includes: the RS resource being used to generate a training dataset for a model, and another RS ​​resource associated with the association identifier being used to generate an inference dataset for the model.

[0185] As an example, an RS resource associated with an association identifier includes: the RS resource being used to generate an inference dataset for a model, and another RS ​​resource associated with the association identifier being used to generate a training dataset for the model.

[0186] As an example, an RS resource associated with an association identifier includes: the RS resource and another RS ​​resource quasi-co-located to the association identifier.

[0187] As an example, an RS resource associated with an association identifier includes: the RS resource and another RS ​​resource associated with the association identifier are quasi-co-located, and the corresponding quasi-co-location type includes TypeD.

[0188] As an example, an RS resource being associated with an association identifier includes the following: the RS resource and another RS ​​resource associated with the association identifier have the same or similar characteristics.

[0189] As an example, associating an RS resource with an association identifier includes: the RS resource being used to generate a training dataset or inference dataset for a model associated with the association identifier.

[0190] As an example, associating an RS resource with an association identifier includes: the output of an inference model relating to the RS resource, and the model being associated with the association identifier.

[0191] As an example, associating an RS resource with an association identifier includes: the RS resource being used to generate a dataset, the dataset belonging to a training dataset or inference dataset of a model, and the model being associated with the association identifier.

[0192] As an example, associating an RS resource with an association identifier includes: a measurement on the RS resource being used to generate a dataset, the dataset belonging to a training dataset or inference dataset of a model, and the model being associated with the association identifier.

[0193] As one embodiment, linking the first configuration information block to the second configuration information block includes: the first configuration information block instructing the second configuration information block.

[0194] As one embodiment, linking the first configuration information block to the second configuration information block includes: the first configuration information block indicating the identifier of the second configuration information block.

[0195] As one embodiment, the second configuration information block is identified by the identifier of the second configuration information block.

[0196] As an example, the second configuration information block is a CSI-ReportConfig IE, and the identifier of the second configuration information block is CSI-ReportConfigId.

[0197] As one embodiment, linking the first configuration information block to the second configuration information block includes: the second configuration information block indicating the first configuration information block.

[0198] As one embodiment, linking the first configuration information block to the second configuration information block includes: the second configuration information block indicating the identifier of the first configuration information block.

[0199] As an example, the first configuration information block is identified by the identifier of the first configuration information block.

[0200] As an example, the first configuration information block is a CSI-ReportConfig IE, and the identifier of the first configuration information block is CSI-ReportConfigId.

[0201] As one embodiment, linking the first configuration information block to the second configuration information block includes: the second configuration information block being used to configure an inference, and the first configuration information block being used to configure monitoring of the inference configured by the second configuration information block.

[0202] As one embodiment, linking the first configuration information block to the second configuration information block includes: the first configuration information block and the second configuration information block indicating the same associated identifier.

[0203] As a sub-example of the above embodiment, both the M1 RS resources and the M2 RS resources are associated with the same association identifier.

[0204] As a sub-implementation of the above embodiments, the first inference is associated with the same association identifier.

[0205] As one embodiment, linking the first configuration information block to the second configuration information block includes: the first configuration information block and the second configuration information block indicating (multiple) RS resources associated with the same association identifier.

[0206] As one embodiment, linking the first configuration information block to the second configuration information block includes: the first configuration information block indicating the M1 RS resources, the second configuration information block indicating the M2 RS resources, and the M1 RS resources and the M2 RS resources being associated with the same association identifier.

[0207] As an example, the first configuration information block indicates the M2 RS resources by connecting to the second configuration information block.

[0208] As an example, the first configuration information block indicates the first inference by being connected to the second configuration information block.

[0209] In a preferred embodiment, the first signaling is DCI (Downlink Control Information).

[0210] As one embodiment, the first signaling includes DCI used to schedule PUSCH (Physical Uplink Shared Channel).

[0211] As one embodiment, the first signaling includes a DCI with CRC (Cyclic redundancy check) scrambled by C-RNTI.

[0212] As an example, the first signaling includes DCI with CRC scrambled by SP-CSI-RNTI.

[0213] As an example, the first signaling includes DCI format 0_1.

[0214] As an example, the first signaling includes DCI format 0_2.

[0215] As an example, the first signaling includes DCI format 0_3.

[0216] As an example, the first signaling is DCI format 0_1 ​​or DCI format 0_2.

[0217] As an example, the first signaling is one of DCI format 0_1, DCI format 0_2, or DCI format 0_3.

[0218] As an example, the first signaling is DCI, and the CRC (Cyclic redundancy check) of the first signaling is scrambled by one of C (Cell)-RNTI (Radio Network Temporary Identifier), CS (Configured Scheduling)-RNTI, SP-CSI-RNTI, or MCS (Modulation and Coding Scheme)-C-RNTI.

[0219] As an example, the first signaling is MAC CE (Medium Access Control layer Control Element).

[0220] As an example, the first signaling triggers a report for the first configuration information block.

[0221] As an example, the first configuration information block is used to configure an aperiodic reporting, and the first signaling triggers a reporting for the first configuration information block.

[0222] As an example, the first configuration information block is used to configure a semi-persistent report, and the first signaling activates the report for the first configuration information block.

[0223] As an example, the DCI field CSI request of the first signaling indicates a trigger state, which indicates the first configuration information block.

[0224] As a sub-implementation of the above embodiment, the triggering state is the triggering state of the first configuration information block.

[0225] As a sub-implementation of the above embodiments, the triggering state of the first configuration information block includes the aforementioned triggering state.

[0226] As a sub-implementation of the above embodiments, the first signaling indicates a CSI request domain code point, which is mapped to the trigger state.

[0227] As a sub-implementation of the above embodiments, the first signaling indicates a CSI request domain code point mapped to the one trigger state to indicate the one trigger state.

[0228] As a sub-example of the above embodiment, the trigger state is a trigger state configured by a CSI-AperiodicTriggerStateList IE.

[0229] As a sub-implementation of the above embodiment, the triggering state is a CSI-AperiodicTriggerState in a CSI-AperiodicTriggerStateList IE.

[0230] As one example, the first reported information is directed to the first configuration information block.

[0231] As an example, the first reported information is reported for the first configuration information block.

[0232] As an example, the first reported information for the first configuration information block means that the first reported information is reported for the first configuration information block.

[0233] As one embodiment, the first reported information includes reported information reported for the first configuration information block.

[0234] As an example, the first reported information is a single report for the first configuration information block.

[0235] As one embodiment, the first reported information includes a single report for the first configuration information block.

[0236] As an example, the first configuration information block is used to configure a report, and the first report information is a report for the first configuration information block.

[0237] As one embodiment, the first configuration information block is used to configure a report, and the first report information includes a report for the first configuration information block.

[0238] As an example, the first reported information is generated according to the first configuration information block.

[0239] As an example, the first reported information in relation to the first configuration information block means that the first reported information is generated according to the first configuration information block.

[0240] As an example, the first configuration information block indicates the reporting quantity of the first reported information.

[0241] As an example, the reported quantity includes one or more of CRI (CSI-RS Resource Indicator), SSBRI (SS / PBCH Block Resource Indicator), RSRP (Reference Signal Received Power), and SINR (Signal-to-Interference and Noise Ratio).

[0242] As an example, the reported quantity includes one or more of CQI (Channel Quality Indicator), PMI (Precoding Matrix Indicator), CRI, LI (Layer Indicator), RI (Rank Indicator), SSBRI, RSRP, SINR, CapabilityIndex, and TDCP (Time Domain Channel Properties).

[0243] As one embodiment, the first configuration information block indicates the number of reports of the first reported information.

[0244] As an example, the number of reported quantities includes at least one of the following: the number of reported CRIs or SSBRIs, and the number of reported RSRPs or SINRs.

[0245] As one embodiment, the first configuration information block indicates that the first reported information includes the first metric.

[0246] As an example, the first configuration information block indicates the content of the first metric.

[0247] As an example, the first metric includes at least one of beam prediction accuracy, RSRP accuracy, and the success rate of correct prediction.

[0248] As an example, the content of the first metric includes at least one of the following: the probability that the first (top-1) strongest beam is the first (top-1) predicted beam, the probability that the first (top-1) strongest beam is one of the top K (top-K) predicted beams, and the probability that the first (top-1) predicted beam is one of the top K (top-K) strongest beams.

[0249] As an example, the first configuration information block indicates the time domain behavior of the first reported information.

[0250] As an example, the time-domain behavior is one of periodic, semi-persistent, or aperiodic.

[0251] As one embodiment, the first configuration information block indicates the physical layer channel carrying the first reported information.

[0252] As an example, the physical layer channel carrying the first reported information is PUSCH (Physical Uplink Shared Channel) or PUCCH (Physical Uplink Control Channel).

[0253] As one embodiment, the first configuration information block indicates the triggering status of the first reported information.

[0254] As one embodiment, the first configuration information block indicates the slot offset of the first reported information.

[0255] As an example, the first reported information includes UCI (Uplink Control Information).

[0256] As one example, the first reported information includes CSI.

[0257] As an example, the first reported information includes one or more of CQI, PMI, CRI, LI, RI, SSBRI, RSRP, SINR, CapabilityIndex, and TDCP (Time Domain Channel Properties).

[0258] As an example, in response to the receipt of the first signaling, performing the first inference means that the first signaling triggers the first inference.

[0259] As an example, in response to the receipt of the first signaling, performing the first inference means that the first signaling triggers the execution of the first inference.

[0260] As an example, in response to the receipt of the first signaling, performing the first inference means that the first signaling triggers one inference of the model of the first inference.

[0261] As an example, in response to the receipt of the first signaling, performing the first inference means that the first node performs the first inference in conjunction with the receipt of the first signaling.

[0262] As an example, in response to the receipt of the first signaling, performing the first inference means that, along with the receipt of the first signaling, the first node performs one inference of the model of the first inference.

[0263] As an example, in response to the receipt of the first signaling, performing the first inference means that the first signaling triggers an update for the reporting of the second configuration information block, and the update for the reporting of the second configuration information block includes the first inference.

[0264] As a sub-implementation of the above embodiments, the update reported for the second configuration information block includes one inference of the model of the first inference.

[0265] As a sub-implementation of the above embodiments, the update reported for the second configuration information block includes performing the first inference.

[0266] In a preferred embodiment, the first signaling triggers the second configuration information block by triggering the first configuration information block connected to the second configuration information block.

[0267] In a preferred embodiment, the first signaling triggers an update reported for the second configuration information block by triggering the first configuration information block connected to the second configuration information block.

[0268] In a preferred embodiment, the first signaling triggers the first inference configured by the second configuration information block by triggering the first configuration information block connected to the second configuration information block.

[0269] The problems to be solved in this application include: how to ensure that matching inference results and monitoring results are used for comparison in the performance monitoring of AI models or ML models; in the above method, when a performance monitoring-related report of an AI model or ML model is triggered, the inference of the AI ​​model or ML model is triggered at the same time, thus solving this problem.

[0270] The benefits of the above embodiments include improved AI / ML performance, thereby improving the overall system performance.

[0271] The advantages of the above embodiments include: simplified signaling design and reduced signaling overhead.

[0272] As an example, the first inference is an AI (Artificial Intelligence) inference.

[0273] As an example, the first inference is an ML (Machine Learning) inference.

[0274] As an example, the first inference is an AI inference or an ML inference.

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

[0276] As an example, the model refers to an AI model or an ML model.

[0277] As an example, the first inference is the inference of an AI model or an ML model.

[0278] As an example, the model for the first inference is based on training.

[0279] As an example, the model for the first inference is obtained through training.

[0280] In a preferred embodiment, the training of the model for the first inference is performed by the first node.

[0281] The advantages of the above method include: avoiding the transmission of the first inference model to the first node via the air interface, thus saving air interface overhead.

[0282] As an example, the training of the first inference model is performed by the serving cell of the first node.

[0283] As an example, the training of the first inference model is performed by the maintenance base station of the serving cell of the first node.

[0284] As an example, the training of the first inference model is performed by the MnS (Management Service) producer.

[0285] As an example, the training of the model for the first inference is performed by the core network device.

[0286] As an example, the training of the first inference model is performed by a NAS (Network Access Server) device.

[0287] As an example, the training of the first inference model is performed by an OTT (Over-The-Top server).

[0288] As an example, the M1 RS resources are used to generate the training dataset for the model of the first inference.

[0289] As an example, the M1 RS resources are not used to generate the training dataset for the model of the first inference.

[0290] As an example, the M2 RS resources are used to generate the training dataset for the model of the first inference.

[0291] As an example, the M2 RS resources are not used to generate the training dataset for the model of the first inference.

[0292] As an example, the second configuration information block is used to determine the parameters of the first inference.

[0293] As one embodiment, the second configuration information block is used to determine some parameters of the first inference.

[0294] As an example, the second configuration information block indicates the parameters of the first inference.

[0295] As an example, the second configuration information block indicates some parameters of the first inference.

[0296] As one embodiment, the second configuration information block includes the parameters of the first inference.

[0297] As one embodiment, the second configuration information block includes some parameters of the first inference.

[0298] As an example, the parameters of the first inference are used to determine at least one of the input, output, and model of the first inference.

[0299] As an example, the parameters of the first inference are used to determine a set of RS (Reference Signal) resources for generating the inference dataset of the first inference.

[0300] As an example, the parameters of the first inference include the number of RS resources used to generate the inference dataset of the first inference.

[0301] As an example, the parameters of the first inference include the beamwidth of the RS resource used to generate the inference dataset of the first inference.

[0302] As an example, the parameters of the first inference are used to determine a set of RS resources for the training dataset used to generate the model of the first inference.

[0303] As an example, the parameters of the first inference include the number of RS resources for the training dataset used to generate the model of the first inference.

[0304] As an example, the parameters of the first inference include the beamwidth of the RS resource used to generate the training dataset of the model for the first inference.

[0305] As an example, the parameters of the first inference are used to determine the multiple RS resources involved in the output of the first inference.

[0306] As an example, the parameters of the first inference include the number of RS resources involved in the output of the first inference.

[0307] As an example, the parameters of the first inference include the beamwidth of the RS resource involved in the output of the first inference.

[0308] As an example, the parameters of the first inference include the model parameters of the first inference.

[0309] As an example, the model parameters of the first inference include parameters used to construct the model of the first inference.

[0310] As an example, the model parameters of the first inference include some or all of the parameters used to construct the model of the first inference.

[0311] As an example, the first inference corresponds to a first identifier, and the model parameters of the first inference include the first identifier.

[0312] As an example, the model parameters of the first inference include the associated ID to which the first inference is associated.

[0313] As an example, the association identifier associated with the first inference refers to the association identifier associated with the model of the first inference.

[0314] As an example, associating a model with an association identifier includes: the model being identified by the association identifier.

[0315] As an example, associating a model with an association identifier includes: the reasoning of the model being identified by the association identifier.

[0316] As an example, associating a model with an association identifier includes: the inference dataset of the model being identified by the association identifier.

[0317] As an example, a model being associated with an association identifier includes: an AI function or AI entity that performs inference for the model being identified by the association identifier.

[0318] As an example, associating a model with an association identifier includes: the training of the model is identified by the association identifier.

[0319] As an example, associating a model with an association identifier includes: the training dataset of the model being identified by the association identifier.

[0320] As an example, a model being associated with an association identifier includes: an AI function or AI entity that performs the training of the model being identified by the association identifier.

[0321] As an example, associating a model with an association identifier includes: performance monitoring of the model being identified by the association identifier.

[0322] As an example, associating a model with an association identifier includes: the performance monitoring dataset of the model being identified by the association identifier.

[0323] As an example, associating a model with an association identifier includes: the function targeted by the model is identified by the association identifier.

[0324] As an example, associating a model with an association identifier includes: the RS resource or set of RS resources associated with the association identifier being used to obtain channel measurements of the inference dataset or training dataset that generates the model.

[0325] As an example, a model being associated with an association identifier includes: the output of the model relating to an RS resource or a set of RS resources associated with the association identifier.

[0326] As an example, the first metric includes prediction accuracy.

[0327] As an example, the prediction accuracy includes beam prediction accuracy.

[0328] As an example, the beam prediction accuracy includes at least one of the following: the probability that the first (top-1) strongest beam is the first (top-1) predicted beam, the probability that the first (top-1) strongest beam is one of the top K (top-K) predicted beams, and the probability that the first (top-1) predicted beam is one of the top K (top-K) strongest beams.

[0329] As an example, the predicted beam depends on the first inference.

[0330] As an example, the predicted beam depends on the output of the first inference.

[0331] As an example, the output of the first inference includes the predicted beam.

[0332] As an example, the strongest beam depends on measurements on the M1 RS resources.

[0333] As an example, the strongest beam depends on measurements on the M1 RS resources used for monitoring.

[0334] As an example, the first node determines the strongest beam based on measurements on the M1 RS resources.

[0335] As an example, the prediction accuracy includes RSRP accuracy.

[0336] As an example, the RSRP accuracy includes at least one of the difference or average of the RSRP of the first (top-1) predicted beam and the RSRP of the first (top-1) strongest beam, and the CDF (Cumulative Distribution Function) of the difference between the RSRP of the first (top-1) predicted beam and the RSRP of the first (top-1) strongest beam.

[0337] As an example, the RSRP accuracy includes the difference or average of the predicted RSRP and the measured RSRP.

[0338] As an example, the RSRP accuracy includes at least one of the following: the difference or average of the predicted RSRP of the first (top-1) predicted beam and the measured RSRP of the first (top-1) strongest beam; the difference or average of the difference between the predicted RSRP of the first (top-1) predicted beam and the measured RSRP of the first (top-1) predicted beam; and the difference or average of the difference between the predicted RSRP of the first (top-1) strongest beam and the measured RSRP of the first (top-1) strongest beam.

[0339] As an example, the predicted RSRP depends on the first inference.

[0340] As an example, the predicted RSRP depends on the output of the first inference.

[0341] As an example, the output of the first inference includes the predicted RSRP.

[0342] As an example, the measurement RSRP depends on measurements on the M1 RS resources.

[0343] As an example, the measurement RSRP depends on measurements on the M1 RS resources used for monitoring.

[0344] As an example, the first node determines the measured RSRP based on measurements on the M1 RS resources.

[0345] As an example, the prediction accuracy includes the success rate of correct predictions.

[0346] As an example, the correct prediction includes at least one of the following three: the first (top-1) strongest beam is the first (top-1) predicted beam, the first (top-1) strongest beam is one of the top K (top-K) predicted beams, and the first (top-1) predicted beam is one of the top K (top-K) strongest beams.

[0347] As an example, the correct prediction includes at least one of the following: the difference between the RSRP of the first (top-1) predicted beam and the RSRP of the strongest beam does not exceed xdB, and the difference between the maximum RSRP of the top K (top-K) predicted beams and the RSRP of the strongest beam does not exceed xdB, wherein x is configurable.

[0348] As an example, the correct prediction includes: the difference between the predicted RSRP and the measured RSRP, or the average of the differences, does not exceed x dB, where x is configurable.

[0349] As an example, x is a real number.

[0350] As an example, x is an integer.

[0351] As an example, the first metric includes one or more of SGCS (Squared Generalized Cosine Similarity), NMSE (Normalized Mean Square Error), UPT (User Perceived Throughput), throughput, hypothetical BLER (BLock Error Rate), BLER, and ACK (acknowledgement) / NACK (negative acknowledgement).

[0352] As an example, the UPT includes at least one of average UPT and 5% UPT.

[0353] As an example, the first metric is used to monitor the first inference.

[0354] As an example, the first metric reflects the performance of the first inference.

[0355] As an example, the first metric reflects the performance of the model of the first inference.

[0356] As an example, the M1 RS resources and the first inference are associated with the same association identifier.

[0357] As a sub-implementation of the above embodiments, the first configuration information block indicates the first inference by indicating the M1 RS resources.

[0358] As an example, the output of the first inference involves the M1 RS resources.

[0359] As a sub-implementation of the above embodiment, M1 is greater than M2.

[0360] As an example, the output of the first inference involves the M2 RS resources.

[0361] As a sub-implementation of the above embodiment, M1 is equal to M2, and the M1 RS resources are the M2 RS resources.

[0362] As an example, the output of the first inference involves M3 RS resources, where M3 is greater than M2.

[0363] As a sub-example of the above embodiment, the M1 RS resources, the M2 RS resources and the M3 RS resources are configured separately.

[0364] As an example, M3 is a positive integer greater than 1.

[0365] As an example, the M3 RS resources include CSI-RS resources.

[0366] As an example, the M3 RS resources include SS / PBCH block resources.

[0367] As an example, any one of the M3 RS resources is a CSI-RS resource.

[0368] As an example, any one of the M3 RS resources is an SS / PBCH block resource.

[0369] As an example, any one of the M3 RS resources is a CSI-RS resource or an SS / PBCHblock resource.

[0370] As an example, the M3 RS resources are used to generate the training dataset for the model of the first inference.

[0371] As an example, the M3 RS resources are not used to generate the training dataset for the model of the first inference.

[0372] As an example, the output of the first inference relates to a plurality of RS resources, and the output of the first inference indicates at least one of the plurality of RS resources.

[0373] As an example, the output of the first inference involves multiple RS resources, including the output of the first inference indicating the CRI or SSBRI of at least one of the multiple RS resources.

[0374] As an example, the output of the first inference involves multiple RS resources, including any RS resource indicated by the output of the first inference being one of the multiple RS resources.

[0375] As an example, the output of the first inference involves multiple RS resources, including any CRI or SSBRI indicated by the output of the first inference, which is the CRI or SSBRI of one of the multiple RS resources.

[0376] As an example, the output of the first inference involves multiple RS resources, including an RSRP or SINR for at least one of the multiple RS resources.

[0377] As an example, the output of the first inference involves multiple RS resources, including any RSRP or SINR indicated by the output of the first inference, which is the RSRP or SINR of one of the multiple RS resources.

[0378] As an example, the output of the first inference depends on the measurements on the M2 RS resources.

[0379] As an example, the output of the first inference depends on channel measurements on the M2 RS resources.

[0380] As an example, the output of the first inference is obtained based on the measurements on the M2 RS resources, which are dependent on the input of the first inference.

[0381] As an example, the output of the first inference is the output obtained by the first inference with the measurement obtained based on the M2 RS resources as input.

[0382] As an example, the output of the first inference is the output obtained by the first inference with the measurement results obtained based on the measurement of the M2 RS resources as input.

[0383] As an example, the output of the first inference is the output obtained by the first inference with the measurement results on the M2 RS resources or the information of the measurement results after preprocessing as input.

[0384] As a preferred embodiment, at least one strongest beam depends on the measurement on the M1 RS resources, and the first metric depends on the at least one strongest beam.

[0385] As an example, the measurements on the M1 RS resources are used to determine the at least one strongest beam.

[0386] As an example, the first node determines the at least one strongest beam based on the measurements on the M1 RS resources.

[0387] As an example, any one of the strongest beams in the at least one strongest beam indicates one of the M1 RS resources.

[0388] As an example, any one of the strongest beams is the beam of one of the M1 RS resources.

[0389] As an example, any of the strongest beams in the at least one strongest beam indicates one of the M3 RS resources, and the output of the first inference relates to the M3 RS resources.

[0390] As an example, any of the at least one strongest beam is a beam of one of the M3 RS resources, and the output of the first inference relates to the M3 RS resources.

[0391] As an example, at least one RS resource identifier depends on the measurement on the M1 RS resources, and the at least one RS resource identifier indicates the at least one strongest beam.

[0392] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is a CRI or an SSBRI.

[0393] As a reference embodiment of the above sub-example, the at least one strongest beam is the RS resource indicated by the at least one RS resource identifier.

[0394] As a reference embodiment of the above sub-example, the at least one strongest beam is the beam of the RS resource indicated by the at least one RS resource identifier.

[0395] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M1 RS resources.

[0396] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M3 RS resources, and the output of the first inference involves the M3 RS resources.

[0397] As an example, the at least one strongest beam includes only one strongest beam, and the at least one strongest beam includes the first (top-1) strongest beam.

[0398] As an example, the at least one strongest beam includes K strongest beams, where K is greater than 1, and the K strongest beams included in the at least one strongest beam are the top K strongest beams.

[0399] In a preferred embodiment, the first reported information does not include the at least one strongest beam.

[0400] The advantages of the above method include: reduced reporting costs.

[0401] As an example, at least one RSRP measurement depends on the measurement on the M1 RS resources, and the first metric depends on the at least one RSRP measurement.

[0402] As an example, at least one strongest beam and at least one measured RSRP both depend on the measurement on the M1 RS resources, and the first metric depends on the at least one strongest beam and the at least one measured RSRP.

[0403] As a sub-implementation of the above embodiments, the at least one measured RSRP is the RSRP of the at least one strongest beam.

[0404] As an example, the first node obtains M1 RSRPs based on the measurements on the M1 RS resources, the M1 RSRPs being the RSRPs of the M1 RS resources respectively, and the at least one strongest beam indicating the RS resource corresponding to the largest one or K RSRPs among the M1 RSRPs.

[0405] As an example, the first node obtains M1 RSRPs based on the measurements on the M1 RS resources, the M1 RSRPs being the RSRPs of the M1 RS resources respectively, the M1 RSRPs being used to determine the RSRPs of M3 RS resources, the at least one strongest beam indicating the RS resource with the largest corresponding RSRP among the M3 RS resources; the output of the first inference relates to the M3 RS resources.

[0406] How the first node determines the RSRPs of the M3 RS resources based on the M1 RSRPs is determined by the hardware equipment vendor. Some non-limiting implementation methods are described below:

[0407] As an example, the first node interpolates the M1 RSRPs to determine the RSRPs of the M3 RS resources.

[0408] As an example, the first node performs a table lookup on the M1 RSRPs to determine the RSRPs of the M3 RS resources.

[0409] As an example, the first node filters the M1 RSRPs to determine the RSRPs of the M3 RS resources.

[0410] In a preferred embodiment, the output of the first inference indicates at least one predicted beam, and the first metric depends on the at least one predicted beam.

[0411] As an example, any one of the at least one prediction beams indicates one of the M1 RS resources.

[0412] As an example, any one of the at least one predicted beams is a beam of one of the M1 RS resources.

[0413] As an example, any one of the at least one prediction beams indicates one of the M2 RS resources.

[0414] As an example, any one of the at least one predicted beams is a beam of one of the M2 RS resources.

[0415] As an example, any one of the at least one prediction beams indicates one of the M3 RS resources, where M3 is a positive integer greater than 1; the M3 RS resources, the M1 RS resources, and the M2 RS resources are configured separately.

[0416] As an example, any one of the at least one predicted beams is a beam of one of the M3 RS resources, where M3 is a positive integer greater than 1; the M3 RS resources, the M1 RS resources, and the M2 RS resources are configured separately.

[0417] As an example, the output of the first inference indicates at least one RS resource identifier, which indicates the at least one predicted beam.

[0418] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is a CRI or an SSBRI.

[0419] As a reference embodiment of the above sub-example, the at least one predicted beam is an RS resource indicated by the at least one RS resource identifier.

[0420] As a reference embodiment of the above sub-example, the at least one predicted beam is the beam of the RS resource indicated by the at least one RS resource identifier.

[0421] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M1 RS resources.

[0422] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M2 RS resources.

[0423] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M3 RS resources, where M3 is a positive integer greater than 1; the M3 RS resources, the M1 RS resources and the M2 RS resources are configured separately.

[0424] As an example, the at least one predicted beam includes only one predicted beam, and the at least one predicted beam includes the first (top-1) predicted beam.

[0425] As an example, the at least one predicted beam includes K predicted beams, where K is greater than 1, and the K predicted beams included in the at least one predicted beam are the top K predicted beams.

[0426] In a preferred embodiment, the first reported information does not include the at least one predicted beam.

[0427] The advantages of the above method include reduced reporting costs.

[0428] As an example, the at least one predicted beam depends on measurements on the M2 RS resources.

[0429] As an example, the output of the first inference indicates at least one predicted RSRP, and the first metric depends on the at least one predicted RSRP.

[0430] As an example, the output of the first inference indicates at least one predicted beam and at least one predicted RSRP, and the first metric depends on the at least one predicted beam and the at least one predicted RSRP.

[0431] As a sub-implementation of the above embodiments, the at least one predicted RSRP is the RSRP of the at least one predicted beam.

[0432] As a sub-implementation of the above embodiments, the at least one predicted RSRP is the predicted RSRP of the at least one predicted beam.

[0433] As an example, the first metric depends on at least one strongest beam and at least one predicted beam, the at least one strongest beam depending on the measurement on the M1 RS resources, and the output of the first inference indicates the at least one predicted beam.

[0434] As an example, the first metric depends on at least one strongest beam and at least one predicted beam.

[0435] As a sub-example of the above embodiment, the output of the first inference indicates the at least one predicted beam, and the measurement on the M1 RS resources is used to determine the at least one strongest beam.

[0436] As an example, the first metric depends on whether the at least one predicted beam and the at least one strongest beam include the same beam.

[0437] As an example, the first metric depends on whether the at least one strongest beam is the at least one predicted beam.

[0438] As an example, the first metric depends on whether the at least one strongest beam includes one of the at least one predicted beams.

[0439] As an example, the first metric depends on whether the at least one predicted beam includes the strongest beam of the at least one strongest beam.

[0440] As an example, the at least one predicted beam includes only one predicted beam, the at least one strongest beam includes only one strongest beam, and the first metric depends on whether the predicted beam is the strongest beam.

[0441] As one embodiment, the at least one predicted beam includes only one predicted beam, and the at least one strongest beam includes multiple strongest beams, wherein the first metric depends on whether the multiple strongest beams include the one predicted beam.

[0442] As one embodiment, the at least one predicted beam includes multiple predicted beams, and the at least one strongest beam includes only one strongest beam, wherein the first metric depends on whether the multiple predicted beams include the one strongest beam.

[0443] As an example, the output of the first inference indicates at least one predicted RSRP, and the measurement on the M1 RS resources is used to determine at least one measured RSRP; the first metric depends on the at least one predicted RSRP and the at least one measured RSRP.

[0444] As an example, the first metric depends on the difference between the at least one measured RSRP and the at least one predicted RSRP.

[0445] As an example, the at least one measured RSRP includes only one measured RSRP, and the at least one predicted RSRP includes only one predicted RSRP; the first metric depends on the difference between the one measured RSRP and the one predicted RSRP.

[0446] As an example, the at least one measured RSRP includes only one measured RSRP, and the at least one predicted RSRP includes multiple predicted RSRPs; the first metric depends on the difference between the one measured RSRP and the maximum predicted RSRP among the multiple predicted RSRPs.

[0447] As an example, the at least one measured RSRP includes multiple measured RSRPs, and the at least one predicted RSRP includes only one predicted RSRP; the first metric depends on the difference between the maximum measured RSRP among the multiple measured RSRPs and the one predicted RSRP.

[0448] As an example, the first metric depends on the difference between the maximum measured RSRP among the at least one measured RSRP and the maximum predicted RSRP among the at least one predicted RSRP.

[0449] As an example, the input to the first inference depends on measurements on the M2 RS resources.

[0450] As an example, the input to the first inference depends on channel measurements on the M2 RS resources.

[0451] As an example, the input to the first inference includes measurements obtained based on the M2 RS resources.

[0452] As an example, the input to the first inference includes channel measurements obtained based on the M2 RS resources.

[0453] As an example, the input to the first inference includes measurement results obtained based on the measurements of the M2 RS resources.

[0454] As an example, the input to the first inference depends on the measurement results on the M2 RS resources.

[0455] As an example, the input to the first inference includes measurement results on the M2 RS resources.

[0456] As an example, the input to the first inference includes some or all of the measurement results on the M2 RS resources.

[0457] As an example, the input to the first inference includes preprocessed measurement results on the M2 RS resources.

[0458] As an example, the input to the first inference includes some or all of the preprocessed measurement results on the M2 RS resources.

[0459] As an example, the measurement results on the M2 RS resources are used to generate the input for the first inference.

[0460] As an example, some or all of the measurement results on the M2 RS resources are used to generate the input for the first inference.

[0461] As an example, the measurement results on the M2 RS resources are preprocessed and used to generate the input for the first inference.

[0462] As an example, some or all of the measurement results on the M2 RS resources are preprocessed and used to generate the input for the first inference.

[0463] As an example, the preprocessing includes one or more of the following: matrix factorization, domain transformation, DFT (Discrete Fourier Transform), quantization, shortening, and puncture.

[0464] As an example, the domain transformation includes one or more of the following: angular domain to spatial domain transformation, spatial domain to angular domain transformation, time domain to frequency domain transformation, frequency domain to time domain transformation, delay domain to frequency domain transformation, frequency domain to delay domain transformation, Doppler domain to time domain transformation, and time domain to Doppler domain transformation.

[0465] As an example, the measurement results include one or more of the following: raw channel matrix, eigenvector of the channel matrix, eigenvalue of the channel matrix, Type I codebook index, Type II codebook index, and enhanced Type II codebook.

[0466] As an example, the measurement results include one or more of RSRP (Reference Signal Received Power), RSRQ (Reference Signal Received Quality), and SINR.

[0467] As an example, the measurement results include one or more of the following: reception time, angle of arrival, and received energy for each of the first path or the J strongest paths, where J is a positive integer.

[0468] As an example, the M1 RS resources include CSI-RS (Channel State Information-Reference Signal) resources.

[0469] As an example, the M1 RS resources include SS / PBCH block (Synchronization Signal / Physical Broadcast Channel block) resources.

[0470] As an example, any one of the M1 RS resources is a CSI-RS resource.

[0471] As an example, any one of the M1 RS resources is an SS / PBCH block resource.

[0472] As an example, any one of the M1 RS resources is a CSI-RS resource or an SS / PBCHblock resource.

[0473] As an example, the measurement on the M1 RS resources refers to the measurement of RS transmitted on the M1 RS resources.

[0474] As one example, the measurement includes channel measurement.

[0475] As one example, the measurement includes the measurement of received power.

[0476] As an example, the measurement includes the measurement of the channel matrix.

[0477] As one example, the measurement includes interference measurement.

[0478] As an example, the M2 RS resources include CSI-RS resources.

[0479] As an example, the M2 RS resources include SS / PBCH block resources.

[0480] As an example, any one of the M2 RS resources is a CSI-RS resource.

[0481] As an example, any one of the M2 RS resources is an SS / PBCH block resource.

[0482] As an example, any one of the M2 RS resources is a CSI-RS resource or an SS / PBCHblock resource.

[0483] As an example, the measurement on the M2 RS resources refers to the measurement of RS transmitted on the M2 RS resources.

[0484] As an example, the M1 RS resources and the M2 RS resources are configured separately.

[0485] As an example, M1 is greater than M2.

[0486] As an example, M1 is greater than M2, and the M1 RS resources and the M2 RS resources are configured separately.

[0487] The above method supports spatial prediction, that is, predicting the strongest RS resource or beam among a larger M1 RS resources based on measurements on a smaller M2 RS resources.

[0488] The above method supports joint spatial and temporal prediction, that is, predicting the strongest RS resource or beam among a larger M1 RS resources after a period of time based on measurements on a smaller M2 resource.

[0489] As an example, M1 is equal to M2, and the M1 RS resources are the M2 RS resources.

[0490] The above method supports time prediction, that is, predicting the strongest RS resource or beam among the M2 RS resources after a period of time based on the current measurements on the M2 RS resources.

[0491] As an example, any one of the M1 RS resources and one of the M2 RS resources are quasi-co-located.

[0492] As an example, any one of the M1 RS resources and one of the M2 RS resources are quasi-co-located, and the corresponding quasi-co-location type includes TypeD.

[0493] As an example, the beam of any one of the M1 RS resources is covered by the beam of one of the M2 RS resources.

[0494] As an example, the beam coverage of any one of the M1 RS resources is included within the beam coverage of one of the M2 RS resources.

[0495] As an example, the first configuration information block indicates each of the M1 RS resources.

[0496] As an example, the first configuration information block indicates the identifier of each of the M1 RS resources.

[0497] As an example, the identifier of any RS resource among the M1 RS resources is NZP-CSI-RS-ResourceId.

[0498] As an example, the identifier of any RS resource among the M1 RS resources is the SSB-Index.

[0499] As an example, the identifier of any RS resource among the M1 RS resources is NZP-CSI-RS-ResourceId or SSB-Index.

[0500] As an example, the M1 RS resources belong to a first RS resource set, and the first configuration information block indicates the first RS resource set.

[0501] As an example, the first configuration information block indicates the M1 RS resources by indicating the first RS resource set.

[0502] As an example, the first RS resource set consists of the M1 RS resources.

[0503] As an example, the first RS resource set is a CSI-RS resource set.

[0504] As an example, the first RS resource set is a CSI-SSB (Channel State Information-Synchronization Signal Block) resource set.

[0505] As one embodiment, the first configuration information block indicates the identifier of the first RS resource set.

[0506] As an example, the first configuration information block indicates the M1 RS resources by indicating the identifier of the first RS resource set.

[0507] As an example, the identifier of the first RS resource set is NZP-CSI-RS-ResourceSetId.

[0508] As an example, the identifier of the first RS resource set is CSI-SSB-ResourceSetId.

[0509] As an example, the identifier of the first RS resource set is CSI-ResourceConfigId.

[0510] As an example, the M1 RS resources are used for monitoring.

[0511] As an example, the first configuration information block indicates that the M1 RS resources are used for monitoring.

[0512] As an example, the monitoring refers to the monitoring of a reasoning process.

[0513] As an example, the second configuration information block indicates each of the M2 RS resources.

[0514] As an example, the second configuration information block indicates the identifier of each of the M2 RS resources.

[0515] As an example, the identifier of any RS resource among the M2 RS resources is NZP-CSI-RS-ResourceId.

[0516] As an example, the identifier of any RS resource among the M2 RS resources is the SSB-Index.

[0517] As an example, the identifier of any RS resource among the M2 RS resources is NZP-CSI-RS-ResourceId or SSB-Index.

[0518] As an example, the M2 RS resources belong to the second RS resource set, and the second configuration information block indicates the second RS resource set.

[0519] As an example, the second configuration information block indicates the M2 RS resources by indicating the second RS resource set.

[0520] As an example, the second RS resource set consists of the M2 RS resources.

[0521] As an example, the second RS resource set is a CSI-RS resource set.

[0522] As an example, the second RS resource set is a CSI-SSB resource set.

[0523] As one embodiment, the second configuration information block indicates the identifier of the second RS resource set.

[0524] As an example, the second configuration information block indicates the M2 RS resources by indicating the identifier of the second RS resource set.

[0525] As an example, the identifier of the second RS resource set is NZP-CSI-RS-ResourceSetId.

[0526] As an example, the identifier of the second RS resource set is CSI-SSB-ResourceSetId.

[0527] As an example, the identifier of the second RS resource set is CSI-ResourceConfigId.

[0528] As an example, the M2 RS resources are used for inference.

[0529] As an example, the M2 RS resources are used to generate the inference dataset.

[0530] As an example, the M2 RS resources are used for beam prediction.

[0531] As an example, the M2 RS resources are used to generate the inference input for a model, and the M1 RS resources are used for performance monitoring of the model.

[0532] As an example, the M2 RS resources are used to generate an inference dataset for a model, and the M1 RS resources are used to generate a performance monitoring dataset for the model.

[0533] The problems this application aims to solve include: how to calculate performance monitoring metrics for AI / ML models.

[0534] The problems this application aims to solve include: how to select matching measurement results and inference outputs for comparison to ensure the reliability and fairness of performance monitoring.

[0535] The above method solves the problem by limiting the difference between the time-domain resources corresponding to the measurement results and the time-domain resources corresponding to the model output.

[0536] Example 2

[0537] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in the attached diagram. Figure 2 As shown.

[0538] Appendix Figure 2The network architecture 200 is described. The network architecture 200 is a 5G NR (New Radio) / LTE (Long-Term Evolution) / LTE-A (Long-Term Evolution Advanced) system, or a 5G+ network architecture, or a 6G network architecture, or a network architecture adopted in future evolutions by 3GPP; the network architecture 200 may be referred to as 5GS (5G System) / EPS (Evolved Packet System), or 6GS (6G System); the network architecture 200 includes at least one of UE (User Equipment) 201, RAN (Radio Access Network) 202, core network 210, HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet service 230. The network architecture 200 can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown, the network architecture 200 provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The RAN includes node 203. The RAN may also include other nodes 204. Node 203 provides user and control plane protocol termination toward UE 201. Node 203 may be connected to other nodes 204 via an Xn interface (e.g., backhaul) / X2 interface. Node 203 may also be referred to as a base station, base transceiver station, radio base station, radio transceiver, transceiver function, basic service set (BSS), extended service set (ESS), TRP (transmitter-receiver node), or some other suitable term. The core network 210 is a 5GC (5G Core Network) / EPC (Evolved Packet Core), or the core network 210 is a 6GC; node 203 provides UE 201 with an access point to the core network 210.Examples of UE201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, non-terrestrial base station communications, satellite mobile communications, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband IoT devices, machine-type communication devices, land vehicles, automobiles, wearable devices, or any other similar functional devices. Those skilled in the art may also refer to UE201 as a mobile station, subscriber station, mobile unit, subscriber unit, radio unit, remote unit, mobile device, radio device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. Node 203 is connected to the core network 210 via an S1 / NG interface. The core network 210 includes an MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MMEs / AMFs / SMFs 214, an S-GW (Service Gateway) / UPF (User Plane Function) 212, and a P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF 211 is the control node that handles signaling between the UE 201 and the core network 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through the S-GW / UPF 212, which is itself connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF 213 is connected to the Internet service 230. Internet services 230 include operator-compliant Internet protocol services, which may specifically include Internet, intranet, IMS (IP Multimedia Subsystem), and packet switching services.

[0539] As an example, the first node in this application includes the UE201.

[0540] As an example, the second node in this application includes node 203.

[0541] As an example, the wireless link between the UE201 and the node203 includes a cellular link.

[0542] As an example, the sender of the first configuration information block includes the node 203.

[0543] As an example, the recipient of the first configuration information block includes the UE201.

[0544] As one embodiment, the sender of the second configuration information block includes the node 203.

[0545] As an example, the recipient of the second configuration information block includes the UE201.

[0546] As an example, the sender of the first signaling includes the node 203.

[0547] As an example, the recipient of the first signaling includes the UE201.

[0548] As an example, the executor of the first inference includes the UE201.

[0549] As an example, the sender of the first reported information includes the UE201.

[0550] As an example, the recipient of the first reported information includes the node 203.

[0551] As an example, the UE201 supports AI- or ML-based operations.

[0552] As an example, node 203 supports AI- or ML-based operations.

[0553] Example 3

[0554] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application, as shown in the attached diagram. Figure 3 As shown.

[0555] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for a user plane and a control plane according to this application, as shown in the attached diagram. Figure 3 As shown. Figure 3 This is a schematic diagram illustrating an embodiment of a radio protocol architecture for the user plane 350 and the control plane 300. Figure 3The radio protocol architecture of the control plane 300 between the first communication node device (UE, gNB, or RSU in V2X) and the second communication node device (gNB, UE, or RSU in V2X), or between two UEs, is illustrated using three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (Physical Layer) signal processing functions. Layer 1 will be referred to as PHY 301 in this document. Layer 2 (L2 layer) 305, above PHY 301, is responsible for the link between the first and second communication node devices, or between two UEs. Layer 2 305 includes the MAC (Medium Access Control) sublayer 302, the RLC (Radio Link Control) sublayer 303, and the PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second communication node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. PDCP sublayer 304 also provides security through encrypted data packets and supports cross-cell mobility between second communication node devices and the first communication node device. RLC sublayer 303 provides upper layer data packet segmentation and reassembly, retransmission of lost data packets, and data packet reordering to compensate for out-of-order reception due to HARQ. MAC sublayer 302 provides multiplexing between the logical and transport channels. MAC sublayer 302 is also responsible for allocating various radio resources (e.g., resource blocks) within a cell between the first communication node devices. MAC sublayer 302 is also responsible for HARQ operations. The RRC (Radio Resource Control) sublayer 306 in Layer 3 (L3) of the control plane 300 is responsible for acquiring radio resources (i.e., radio bearers) and configuring the lower layer using RRC signaling between the second and first communication node devices. The radio protocol architecture of user plane 350 includes layer 1 (L1 layer) and layer 2 (L2 layer). The radio protocol architecture for the first and second communication node devices in user plane 350 is largely the same as the corresponding layers and sublayers in control plane 300 for physical layer 351, PDCP sublayer 354 in L2 layer 355, RLC sublayer 353 in L2 layer 355 and MAC sublayer 352 in L2 layer 355. However, PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead.The L2 layer 355 in the user plane 350 also includes an SDAP (Service Data Adaptation Protocol) sublayer 356, which is responsible for mapping between QoS streams and data radio bearers (DRBs) to support service diversity. Although not illustrated, the first communication node device may have several upper layers above the L2 layer 355, including a network layer (e.g., IP layer) terminating at the P-GW on the network side and an application layer terminating at the other end of the connection (e.g., a remote UE, server, etc.).

[0556] As an example, Appendix Figure 3 The wireless protocol architecture described herein is applicable to the first node in this application.

[0557] As an example, Appendix Figure 3 The wireless protocol architecture described herein is applicable to the second node in this application.

[0558] As an example, the higher layer mentioned in this application refers to the layer above the physical layer.

[0559] As an example, the first configuration information block is generated in the RRC sublayer 306.

[0560] As an example, the second configuration information block is generated in the RRC sublayer 306.

[0561] As an example, the first signaling is generated in the PHY301 or the PHY351.

[0562] As an example, the first reporting information is generated in the PHY301 or the PHY351.

[0563] Example 4

[0564] Example 4 illustrates a schematic diagram of a first communication device and a second communication device according to an embodiment of this application, as shown in the attached diagram. Figure 4 As shown. (Attached) Figure 4 This is a block diagram of a first communication device 410 and a second communication device 450 communicating with each other in an access network.

[0565] The first communication device 410 includes a controller / processor 475, a memory 476, a receiver processor 470, a transmitter processor 416, a multi-antenna receiver processor 472, a multi-antenna transmitter processor 471, a transmitter / receiver 418, and an antenna 420.

[0566] The second communication device 450 includes a controller / processor 459, a memory 460, a data source 467, a transmitting processor 468, a receiving processor 456, a multi-antenna transmitting processor 457, a multi-antenna receiving processor 458, a transmitter / receiver 454, and an antenna 452.

[0567] In the transmission from the first communication device 410 to the second communication device 450, at the first communication device 410, upper-layer data packets from the core network are provided to the controller / processor 475. The controller / processor 475 implements L2 layer functionality. In DL (Downlink), the controller / processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for HARQ operation, retransmission of lost packets, and signaling to the second communication device 450. The transmit processor 416 and the multi-antenna transmit processor 471 implement various signal processing functions for L1 layer (i.e., physical layer). Transmit processor 416 performs encoding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, and constellation mapping based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase shift keying (M-PSK), and M-quadrature amplitude modulation (M-QAM). Multi-antenna transmit processor 471 performs digital spatial precoding on the encoded and modulated symbols, including codebook-based precoding and non-codebook-based precoding, and beamforming processing, generating one or more parallel... The transmit processor 416 then maps each parallel stream to a subcarrier, multiplexes the modulated symbols with a reference signal (e.g., a pilot) in the time and / or frequency domains, and then uses an inverse fast Fourier transform (IFFT) to generate a physical channel carrying the time-domain multicarrier symbol stream. The multi-antenna transmit processor 471 then performs transmit analog precoding / beamforming operations on the time-domain multicarrier symbol stream. Each transmitter 418 converts the baseband multicarrier symbol stream provided by the multi-antenna transmit processor 471 into an RF stream, which is then provided to a different antenna 420.

[0568] In the transmission from the first communication device 410 to the second communication device 450, at the second communication device 450, each receiver 454 receives a signal through its corresponding antenna 452. Each receiver 454 recovers the information modulated onto the radio frequency carrier and converts the radio frequency stream into a baseband multicarrier symbol stream, which is then provided to the receiver processor 456. The receiver processor 456 and the multi-antenna receiver processor 458 implement various signal processing functions of the L1 layer. The multi-antenna receiver processor 458 performs receive analog precoding / beamforming operations on the baseband multicarrier symbol stream from the receiver 454. The receiver processor 456 uses a Fast Fourier Transform (FFT) to convert the baseband multicarrier symbol stream after the receive analog precoding / beamforming operations from the time domain to the frequency domain. In the frequency domain, the physical layer data signal and the reference signal are demultiplexed by the receiver processor 456, where the reference signal is used for channel estimation, and the data signal is recovered in the multi-antenna receiver processor 458 after multi-antenna detection to recover any parallel stream destined for the second communication device 450. Symbols on each parallel stream are demodulated and recovered in the receive processor 456, generating soft decisions. The receive processor 456 then decodes and deinterleaves the soft decisions to recover the upper-layer data and control signals transmitted over the physical channel by the first communication device 410. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements the functions of Layer 2 (L2). The controller / processor 459 may be associated with a memory 460 storing program code and data. The memory 460 may be referred to as computer-readable media. In the DL (Layered Logic), the controller / processor 459 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer packets from the core network. The upper-layer packets are then provided to all protocol layers above Layer 2. Various control signals may also be provided to Layer 3 (L3) for L3 processing. The controller / processor 459 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0569] In the transmission from the second communication device 450 to the first communication device 410, at the second communication device 450, a data source 467 is used to provide upper-layer data packets to the controller / processor 459. The data source 467 represents all protocol layers above the L2 layer. Similar to the transmission functions at the first communication device 410 described in the DL, the controller / processor 459 implements header compression, encryption, packet segmentation and reordering, and multiplexing between logical and transport channels based on the radio resource allocation of the first communication device 410, implementing L2 layer functions for the user plane and control plane. The controller / processor 459 is also responsible for HARQ operations, retransmission of lost packets, and signaling to the first communication device 410. Transmit processor 468 performs modulation mapping and channel coding processing, while multi-antenna transmit processor 457 performs digital multi-antenna spatial precoding, including codebook-based and non-codebook-based precoding, and beamforming processing. Subsequently, transmit processor 468 modulates the generated parallel stream into a multi-carrier / single-carrier symbol stream. After analog precoding / beamforming operations in multi-antenna transmit processor 457, the stream is provided to different antennas 452 via transmitter 454. Each transmitter 454 first converts the baseband symbol stream provided by multi-antenna transmit processor 457 into a radio frequency symbol stream before providing it to antenna 452.

[0570] In the transmission from the second communication device 450 to the first communication device 410, the function at the first communication device 410 is similar to the receiving function at the second communication device 450 described in the transmission from the first communication device 410 to the second communication device 450. Each receiver 418 receives radio frequency signals through its corresponding antenna 420, converts the received radio frequency signals into baseband signals, and provides the baseband signals to the multi-antenna receiving processor 472 and the receiving processor 470. The receiving processor 470 and the multi-antenna receiving processor 472 jointly implement the L1 layer functions. The controller / processor 475 implements the L2 layer functions. The controller / processor 475 may be associated with a memory 476 that stores program code and data. The memory 476 may be referred to as computer-readable media. The controller / processor 475 provides multiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transmission and logical channels to recover upper-layer data packets from the second communication device 450. The upper-layer data packets from the controller / processor 475 may be provided to the core network. The controller / processor 475 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0571] As one embodiment, the second communication device 450 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The second communication device 450 means at least: receiving a first configuration information block and a second configuration information block, the first configuration information block being connected to the second configuration information block; receiving a first signaling that triggers first reporting information, the first reporting information depending on the first configuration information block; as a response to the receipt of the first signaling, performing first inference, the parameters of the first inference depending on the second configuration information block; and sending the first reporting information, the first reporting information including a first metric; wherein the first metric depends on measurements on M1 RS resources and the output of the first inference, the input of the first inference depending on measurements on M2 RS resources; the first configuration information block indicating the M1 RS resources, the second configuration information block indicating the M2 RS resources, and M1 and M2 being positive integers greater than 1.

[0572] As one embodiment, the second communication device 450 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: receiving a first configuration information block and a second configuration information block, the first configuration information block being connected to the second configuration information block; receiving a first signaling that triggers first reporting information, the first reporting information depending on the first configuration information block; performing first inference as a response to the reception of the first signaling, the parameters of the first inference depending on the second configuration information block; and sending the first reporting information, the first reporting information including a first metric; wherein the first metric depends on measurements on M1 RS resources and the output of the first inference, the input of the first inference depending on measurements on M2 RS resources; the first configuration information block indicating the M1 RS resources, the second configuration information block indicating the M2 RS resources, and M1 and M2 being positive integers greater than 1.

[0573] As one embodiment, the first communication device 410 includes: at least one processor and at least one memory, the at least one memory including computer program code; the at least one memory and the computer program code are configured to be used with the at least one processor. The first communication device 410 means at least: transmitting a first configuration information block and a second configuration information block, the first configuration information block being connected to the second configuration information block; transmitting a first signaling, the first signaling triggering a first reporting information, the first reporting information depending on the first configuration information block; receiving the first reporting information, the first reporting information including a first metric; wherein the first signaling triggers the sender of the first reporting information to perform a first inference, the parameters of the first inference depending on the second configuration information block; the first metric depending on measurements on M1 RS resources and the output of the first inference, the input of the first inference depending on measurements on M2 RS resources; the first configuration information block indicating the M1 RS resources, the second configuration information block indicating the M2 RS resources, and M1 and M2 being positive integers greater than 1.

[0574] As one embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program that, when executed by at least one processor, produces actions including: sending a first configuration information block and a second configuration information block, the first configuration information block being connected to the second configuration information block; sending a first signaling that triggers a first reporting message, the first reporting message depending on the first configuration information block; receiving the first reporting message, the first reporting message including a first metric; wherein the first signaling triggers the sender of the first reporting message to perform a first inference, the parameters of the first inference depending on the second configuration information block; the first metric depending on measurements on M1 RS resources and the output of the first inference, the input of the first inference depending on measurements on M2 RS resources; the first configuration information block indicating the M1 RS resources, the second configuration information block indicating the M2 RS resources, and M1 and M2 being positive integers greater than 1.

[0575] As an example, the first node in this application includes the second communication device 450.

[0576] As an example, the second node in this application includes the first communication device 410.

[0577] As an example, at least one of {the antenna 452, the receiver 454, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first configuration information block in this application; at least one of {the antenna 420, the transmitter 418, the transmitting processor 416, the multi-antenna transmitting processor 471, the controller / processor 475, and the memory 476} is used to transmit the first configuration information block in this application.

[0578] As an example, at least one of {the antenna 452, the receiver 454, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the second configuration information block in this application; at least one of {the antenna 420, the transmitter 418, the transmitting processor 416, the multi-antenna transmitting processor 471, the controller / processor 475, and the memory 476} is used to transmit the second configuration information block in this application.

[0579] As an example, at least one of {the antenna 452, the receiver 454, the receiving processor 456, the multi-antenna receiving processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first signaling in this application; at least one of {the antenna 420, the transmitter 418, the transmitting processor 416, the multi-antenna transmitting processor 471, the controller / processor 475, and the memory 476} is used to transmit the first signaling in this application.

[0580] As an example, at least one of {the antenna 452, the transmitter 454, the transmitter processor 468, the multi-antenna transmitter processor 457, the controller / processor 459, and the memory 460} is used to transmit the first reporting information in this application; at least one of {the antenna 420, the receiver 418, the receiver processor 470, the multi-antenna receiver processor 472, the controller / processor 475, and the memory 476} is used to receive the first reporting information in this application.

[0581] Example 5

[0582] Example 5 illustrates a flowchart of a transmission according to an embodiment of this application, as shown in the attached diagram. Figure 5 As shown. In the appendix Figure 5In the diagram, the first node U01 and the second node N02 are two communication nodes that transmit data through the air interface, and the steps in the dashed boxes F51 and F52 are optional.

[0583] for First node U01 In step S5101, a first configuration information block and a second configuration information block are received; in step S5102, a first signaling is received; in step S5103, measurements are taken on M2 RS resources; in step S5104, measurements are taken on M1 RS resources; in step S5105, a first inference is performed; and in step S5106, a first reporting information is sent.

[0584] for Second node N02 In step S5201, a first configuration information block and a second configuration information block are sent; in step S5202, a first signaling is sent; in step S5203, RS is sent on M2 RS resources; in step S5204, RS is sent on M1 RS resources; and in step S5205, a first reporting information is received.

[0585] In Embodiment 5, the first configuration information block is connected to the second configuration information block; the first signaling triggers the first reporting information, which depends on the first configuration information block; the parameters of the first inference depend on the second configuration information block; the first reporting information includes a first metric; the first metric depends on measurements on M1 RS resources and the output of the first inference, and the input of the first inference depends on measurements on M2 RS resources; the first configuration information block indicates the M1 RS resources, and the second configuration information block indicates the M2 RS resources, where M1 and M2 are positive integers greater than 1.

[0586] As an example, the first node U01 is the first node in this application.

[0587] As an example, the second node N02 is the second node in this application.

[0588] As one embodiment, the air interface between the second node N02 and the first node U01 includes a wireless interface between the base station equipment and the user equipment.

[0589] As one embodiment, the air interface between the second node N02 and the first node U01 includes a wireless interface between the relay node device and the user equipment.

[0590] As one embodiment, the air interface between the second node N02 and the first node U01 includes a wireless interface between user equipment and user equipment.

[0591] As one embodiment, the air interface between the second node N02 and the first node U01 includes the interface between the core network equipment and the user equipment.

[0592] As one embodiment, the air interface between the second node N02 and the first node U01 includes the interface between the OTT server (Over-The-Top server) and the user equipment.

[0593] As one embodiment, the air interface between the second node N02 and the first node U01 includes the interface between the NAS (Network Access Server) device and the user equipment.

[0594] As an example, the first node U01 includes a terminal.

[0595] As one embodiment, the first node U01 includes a user equipment.

[0596] As one example, the second node N02 is the serving cell sustaining base station of the first node U01.

[0597] As one embodiment, the second node N02 includes an OTT server (Over-The-Top server).

[0598] As an example, the second node N02 includes OAM (Operation Administration and Maintenance).

[0599] As one embodiment, the second node N02 includes a NAS device.

[0600] As one embodiment, the second node N02 includes core network equipment.

[0601] As an example, the steps in dashed box F51 are present, and the method described above for the second node used in wireless communication includes: transmitting RS on M2 RS resources.

[0602] As an example, sending RS on M2 RS resources means sending RS on each of the M2 RS resources.

[0603] As an example, sending RS on M2 RS resources means sending RS on at least one of the M2 RS resources.

[0604] As an example, the step in dashed box F51 is not present, and the sender of the M2 RS resources is different from the second node N02.

[0605] As one embodiment, the second node N02 is a core network device, and the sender of the M2 RS resources is the serving cell of the first node.

[0606] As an example, the sender of the M2 RS resources refers to the sender of the RS in the M2 RS resources.

[0607] As an example, the steps in dashed box F52 are present, and the method described above for the second node used in wireless communication includes: transmitting RS on M1 RS resources.

[0608] As an example, sending RS on M1 RS resources means sending RS on each of the M1 RS resources.

[0609] As an example, sending RS on M1 RS resources means sending RS on at least one of the M1 RS resources.

[0610] As an example, the step in dashed box F52 is not present, and the sender of the M1 RS resources is different from the second node N02.

[0611] In one embodiment, the second node N02 is a core network device, and the sender of the M1 RS resources is the serving cell of the first node.

[0612] As an example, the sender of the M1 RS resources refers to the sender of the RS in the M1 RS resources.

[0613] As an example, the first configuration information block indicates whether the first reported information includes the output of the first inference.

[0614] As an example, the first reported information does not include the output of the first inference.

[0615] As one embodiment, the first signaling indicates a first trigger state, which indicates only the first configuration information block among the first configuration information block and the second configuration information block.

[0616] As an example, the first trigger state indicates whether the first reported information includes the output of the first inference.

[0617] As one embodiment, the first signaling indicates a second trigger state, and the second trigger state indicates the first configuration information block and the second configuration information block.

[0618] As one embodiment, it includes:

[0619] In response to the receipt of the first signaling, the first node U01 measures on the M2 RS resources.

[0620] As an example, the M1 RS resources and the M2 RS resources are associated with the same association identifier.

[0621] As an example, the first metric depends on the measurement on the M1 RS resources in the first time window and the output of the first inference for the first time interval, and the first metric is obtained under the condition that the difference between the first time window and the first time interval is less than or not greater than a first threshold.

[0622] As an example, the measurement on the M2 RS resources is later than the measurement on the M1 RS resources.

[0623] As an example, the measurement on the M2 RS resources is earlier than the measurement on the M1 RS resources.

[0624] As an example, the M2 RS resources are aperiodic.

[0625] As an example, the M1 RS resources are aperiodic.

[0626] As an example, the M2 RS resources are quasi-static.

[0627] As an example, the M1 RS resources are quasi-static.

[0628] As an example, the execution of the first inference precedes the measurement on the M1 RS resources.

[0629] As an example, the execution of the first inference is later than the measurement on the M1 RS resources.

[0630] As an example, the first configuration information block and the second configuration information block are received separately.

[0631] As an example, the first configuration information block and the second configuration information block are received together.

[0632] As an example, the first configuration information block is transmitted on PDSCH (Physical Downlink Shared Channel).

[0633] As an example, the second configuration information block is transmitted on the PDSCH.

[0634] As an example, the first configuration information block and the second configuration information block are transmitted on the same PDSCH.

[0635] As an example, the first signaling is transmitted on the PDCCH (Physical Downlink Control Channel).

[0636] As an example, the first reported information is transmitted on PUSCH (Physical Uplink Shared Channel).

[0637] As an example, the first reporting information is transmitted on the PUCCH (Physical Uplink Control Channel).

[0638] Example 6

[0639] Example 6 illustrates a schematic diagram of a first configuration information block indicating whether the first reported information includes the output of the first inference, according to an embodiment of this application; as shown in the appendix. Figure 6 As shown.

[0640] In Example 6, the first configuration information block indicates whether the first reported information includes the output of the first inference.

[0641] As an example, the first configuration information block indicates that the first reported information includes the output of the first inference.

[0642] As a sub-implementation of the above embodiments, the output of the first inference indicates at least one predicted beam, and the first reported information includes the at least one predicted beam.

[0643] As a sub-example of the above embodiments, the output of the first inference indicates at least one predicted RSRP, and the first reported information includes the at least one predicted RSRP.

[0644] As a sub-implementation of the above embodiments, the output of the first inference indicates at least one predicted beam and at least one predicted RSRP, wherein the at least one predicted RSRP is the RSRP of the at least one predicted beam, and the first reported information includes the at least one predicted beam and the at least one predicted RSRP.

[0645] As an example, the first reported information includes the output of the first inference only when the first configuration information block indicates that the first reported information includes the output of the first inference.

[0646] As an example, when the first configuration information block indicates that the first reported information includes the output of the first inference, the first reported information includes the output of the first inference; when the first configuration information block indicates that the first reported information does not include the output of the first inference, the first reported information does not include the output of the first inference.

[0647] As one embodiment, the second configuration information block is used to configure a report, and the first configuration information block indicates whether the first report includes a report for the second configuration information block.

[0648] As an example, the first reporting information includes the output of the first inference only when the first configuration information block indicates that the first reporting information includes a reporting for the second configuration information block.

[0649] As an example, when the first configuration information block indicates that the first reported information includes a report for the second configuration information block, the first reported information includes the output of the first inference; when the first configuration information block indicates that the first reported information does not include a report for the second configuration information block, the first reported information does not include the output of the first inference.

[0650] As an example, the reporting of the second configuration information block depends on the output of the first inference.

[0651] As an example, the reporting of the second configuration information block includes the output of the first inference.

[0652] As an example, the reporting of the second configuration information block is the output of the first inference.

[0653] As an example, the reporting of the second configuration information block includes the post-processed output of the first inference.

[0654] As an example, the output of the first inference is used to generate a report for the second configuration information block.

[0655] As an example, the output of the first inference is post-processed and used to generate a report for the second configuration information block.

[0656] As an example, the post-processing includes one or more of quantization, shortening, puncture, padding, matrix decomposition, domain transformation, and DFT (Discrete Fourier Transform).

[0657] As an example, the domain transformation includes one or more of the following: angular domain to spatial domain transformation, spatial domain to angular domain transformation, time domain to frequency domain transformation, frequency domain to time domain transformation, delay domain to frequency domain transformation, frequency domain to delay domain transformation, Doppler domain to time domain transformation, and time domain to Doppler domain transformation.

[0658] Example 7

[0659] Example 7 illustrates a schematic diagram of a first reported information that does not include the output of the first inference, according to an embodiment of this application; as shown in the attached diagram. Figure 7 As shown.

[0660] In Example 7, the first reported information does not include the output of the first inference.

[0661] As an example, the output of the first inference indicates at least one predicted beam, and the first reported information does not include the at least one predicted beam.

[0662] As an example, the output of the first inference indicates at least one predicted RSRP, and the first reported information does not include the at least one predicted RSRP.

[0663] As an example, the output of the first inference indicates at least one predicted beam and at least one predicted RSRP, and the first reported information does not include the at least one predicted beam and the at least one predicted RSRP.

[0664] As an example, the first reported information never includes the output of the first inference.

[0665] As an example, the second configuration information block is used to configure a report, and the first report information does not include a report for the second configuration information block.

[0666] As an example, the second configuration information block is used to configure a report, and the first report information never includes a report for the second configuration information block.

[0667] Example 8

[0668] Example 8 illustrates a schematic diagram of a first signaling indication of a first triggering state according to an embodiment of this application; as shown in the attached diagram. Figure 8 As shown.

[0669] In embodiment 8, the first signaling indicates a first triggering state, which indicates only the first configuration information block among the first configuration information block and the second configuration information block.

[0670] As an example, the first triggering state is a CSI triggering state.

[0671] As an example, the first trigger state is an aperiodic trigger state.

[0672] As an example, the first trigger state is a trigger state for non-periodic reporting.

[0673] As an example, the first trigger state is a trigger state for non-periodic CSI reporting.

[0674] As an example, the first trigger state is one of the trigger states configured in the CSI-AperiodicTriggerStateList IE.

[0675] As a sub-implementation of the above embodiments, the first triggering state is a CSI-AperiodicTriggerState in the CSI-AperiodicTriggerStateList IE.

[0676] As a sub-implementation of the above embodiments, the first trigger state is configured by a CSI-AperiodicTriggerState in the CSI-AperiodicTriggerStateList IE.

[0677] As an example, the first triggering state is a semi-persistent triggering state.

[0678] As an example, the first trigger state is a trigger state for quasi-static reporting.

[0679] As an example, the first trigger state is a trigger state for quasi-static CSI reporting.

[0680] As an example, the first trigger state is one of the trigger states configured in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0681] As a sub-implementation of the above embodiment, the first triggering state is a CSI-SemiPersistentOnPUSCH-TriggerState in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0682] As a sub-implementation of the above embodiment, the first trigger state is configured by a CSI-SemiPersistentOnPUSCH-TriggerState in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0683] As an example, the first signaling directly indicates the first triggering state.

[0684] As an example, the first signaling indicates the codepoint mapped by the first trigger state.

[0685] As an example, the first signaling indicates the first trigger state by indicating the code point mapped to the first trigger state.

[0686] As an example, the DCI field CSI request of the first signaling indicates the first triggering state.

[0687] As an example, the DCI field CSI request of the first signaling indicates the code point of the first trigger state mapping.

[0688] As an example, the first signaling indicates a CSI request domain code point, which is mapped to the first trigger state.

[0689] As an example, the first signaling indicates the first triggering state by indicating a CSIrequest domain code point mapped to the first triggering state.

[0690] As an example, the first signaling indicates a trigger state from the CSI-AperiodicTriggerStateList IE, the first trigger state being the trigger state.

[0691] As an example, one or more trigger states in the CSI-AperiodicTriggerStateList IE are mapped to code points of a DCI domain CSI request. The one or more trigger states mapped to code points of a DCI domain CSI request include the first trigger state, and the first signaling indicates the code point mapped to the first trigger state.

[0692] As a sub-implementation of the above embodiments, the first signaling indicates a CSI request domain code point, wherein the CSI request domain code point is a code point mapped by the first trigger state.

[0693] As a sub-implementation of the above embodiments, the DCI field CSI request of the first signaling indicates the code point mapped by the first trigger state.

[0694] As an example, the DCI domain CSI request of the first signaling includes N TS 1 bit, when the number of trigger states in the CSI-AperiodicTriggerStateList IE is less than or equal to 1 bit. At that time, the DCI field CSI request of the first signaling directly indicates a trigger state, and the trigger state is the first trigger state.

[0695] As an example, the DCI domain CSI request of the first signaling includes N TS Bits, when the number of trigger states in the CSI-AperiodicTriggerStateList IE is greater than At that time, the first MAC CE maps one or more trigger states in the CSI-AperiodicTriggerStateList IE to code points in the DCI domain CSI request, wherein the DCI domain CSI request of the first signaling indicates a code point mapped to a trigger state, and the trigger state is the first trigger state.

[0696] As a sub-implementation of the above embodiments, the one or more trigger states of the code points mapped to the DCI field CSI request of the first signaling include at most the following: A trigger state.

[0697] As an example, the first MAC CE is a MAC CE for indicating the trigger state subselection in the CSI-AperiodicTriggerStateList IE.

[0698] As an example, the first MAC CE is an Aperiodic CSI Trigger StateSubselection MAC CE.

[0699] As an example, the N TS It is a non-negative integer.

[0700] As an example, the N TS is a positive integer.

[0701] As an example, the N TS It is a non-negative integer not greater than 6.

[0702] As an example, the N TS It is a positive integer not greater than 6.

[0703] As an example, the N TS Configured by a higher-level parameter whose name includes reportTriggerSize.

[0704] As an example, the N TS Configured by the higher-level parameter reportTriggerSize.

[0705] As an example, the N TS Configured by the higher-level parameter reportTriggerSizeDCI-0-2.

[0706] As an example, the first signaling indicates a trigger state from the CSI-SemiPersistentOnPUSCH-TriggerStateList IE, the first trigger state being the trigger state.

[0707] As an example, the trigger state in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE is mapped to the code point of the DCI domain CSI request. The first trigger state is a trigger state in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE, and the first signaling indicates the code point mapped to the first trigger state.

[0708] As a sub-implementation of the above embodiments, the first signaling indicates a CSI request domain code point, wherein the CSI request domain code point is a code point mapped by the first trigger state.

[0709] As a sub-implementation of the above embodiments, the DCI field CSI request of the first signaling indicates the code point mapped by the first trigger state.

[0710] As a sub-implementation of the above embodiments, the CRC of the first signaling is scrambled by SP-CSI-RNTI.

[0711] As an example, the first trigger state indicates the identifier of the first configuration information block.

[0712] As an example, the identifier of the first configuration information block is a CSI-ReportConfigId.

[0713] As an example, the first trigger state does not indicate the identifier of the second configuration information block.

[0714] As an example, the identifier of the second configuration information block is a CSI-ReportConfigId.

[0715] As an example, the first trigger state indicates the identifier of the first configuration information block, but the first trigger state does not indicate the identifier of the second configuration information block.

[0716] As an example, the advantages of the above method include: it does not directly trigger inference-related reporting, thus reducing reporting overhead.

[0717] As an example, the first configuration information block is a CSI-ReportConfig IE, and the identifier of the first configuration information block is CSI-ReportConfigId.

[0718] As an example, the second configuration information block is a CSI-ReportConfig IE, and the identifier of the second configuration information block is CSI-ReportConfigId.

[0719] As an example, the first configuration information block is a CSI-ReportConfig IE, the second configuration information block is a CSI-ReportConfig IE, the first trigger state indicates at least one CSI-ReportConfig IE, the at least one CSI-ReportConfig IE includes the first configuration information block, and the at least one CSI-ReportConfig IE does not include the second configuration information block.

[0720] As an example, the first configuration information block is a CSI-ReportConfig IE, the second configuration information block is a CSI-ReportConfig IE, the first trigger state indicates only one CSI-ReportConfig IE, and the only CSI-ReportConfig IE is the first configuration information block.

[0721] As an example, the identifier of the first configuration information block is a CSI-ReportConfigId, the identifier of the second configuration information block is a CSI-ReportConfigId, the first trigger state indicates at least one CSI-ReportConfigId, the at least one CSI-ReportConfigId includes the identifier of the first configuration information block, and the at least one CSI-ReportConfigId does not include the identifier of the second configuration information block.

[0722] As an example, the identifier of the first configuration information block is a CSI-ReportConfigId, the identifier of the second configuration information block is a CSI-ReportConfigId, and the first trigger state indicates only one CSI-ReportConfigId, wherein the only CSI-ReportConfigId is the identifier of the first configuration information block.

[0723] As an example, the first signaling indicates the first triggering state, the first triggering state indicates only the first configuration information block of both the first configuration information block and the second configuration information block, and the first configuration information block indicates whether the first reported information includes the output of the first inference.

[0724] Example 9

[0725] Example 9 illustrates a schematic diagram of a first trigger state indicating whether the first reported information includes the output of the first inference, according to an embodiment of this application; as shown in the attached diagram. Figure 9 As shown.

[0726] In Example 9, the first trigger state indicates whether the first reported information includes the output of the first inference.

[0727] As an example, the first signaling indicates the first triggering state, the first triggering state indicates only the first configuration information block of both the first configuration information block and the second configuration information block, and the first triggering state indicates whether the first reported information includes the output of the first inference.

[0728] As an example, the first trigger state block indicates that the first reported information includes the output of the first inference.

[0729] As a sub-implementation of the above embodiments, the output of the first inference indicates at least one predicted beam, and the first reported information includes the at least one predicted beam.

[0730] As a sub-example of the above embodiments, the output of the first inference indicates at least one predicted RSRP, and the first reported information includes the at least one predicted RSRP.

[0731] As a sub-implementation of the above embodiments, the output of the first inference indicates at least one predicted beam and at least one predicted RSRP, wherein the at least one predicted RSRP is the RSRP of the at least one predicted beam, and the first reported information includes the at least one predicted beam and the at least one predicted RSRP.

[0732] As an example, the first reporting information includes the output of the first inference only when the first trigger state indicates that the first reporting information includes the output of the first inference.

[0733] As an example, when the first trigger state indicates that the first reported information includes the output of the first inference, the first reported information includes the output of the first inference; when the first trigger state indicates that the first reported information does not include the output of the first inference, the first reported information does not include the output of the first inference.

[0734] As one embodiment, the second configuration information block is used to configure a report, and the first trigger state indicates whether the first report information includes a report for the second configuration information block.

[0735] As an example, the first reporting information includes the output of the first inference only when the first trigger state indicates that the first reporting information includes a reporting for the second configuration information block.

[0736] As an example, when the first trigger state indicates that the first reported information includes a report for the second configuration information block, the first reported information includes the output of the first inference; when the first trigger state indicates that the first reported information does not include a report for the second configuration information block, the first reported information does not include the output of the first inference.

[0737] Example 10

[0738] Example 10 illustrates a schematic diagram of a first signaling indicating a second triggering state according to an embodiment of this application; as attached. Figure 10 As shown.

[0739] In Embodiment 10, the first signaling indicates a second triggering state, and the second triggering state indicates the first configuration information block and the second configuration information block.

[0740] As an example, the second triggering state is a CSI triggering state.

[0741] As an example, the second trigger state is an aperiodic trigger state.

[0742] As an example, the second trigger state is a trigger state for non-periodic reporting.

[0743] As an example, the second trigger state is a trigger state for non-periodic CSI reporting.

[0744] As an example, the second trigger state is one of the trigger states configured in the CSI-AperiodicTriggerStateList IE.

[0745] As a sub-implementation of the above embodiments, the second triggering state is a CSI-AperiodicTriggerState in the CSI-AperiodicTriggerStateList IE.

[0746] As a sub-implementation of the above embodiments, the second trigger state is configured by a CSI-AperiodicTriggerState in the CSI-AperiodicTriggerStateList IE.

[0747] As an example, the second triggering state is a semi-persistent triggering state.

[0748] As an example, the second trigger state is a trigger state for quasi-static reporting.

[0749] As an example, the second trigger state is a trigger state for quasi-static CSI reporting.

[0750] As an example, the second trigger state is one of the trigger states configured in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0751] As a sub-implementation of the above embodiment, the second triggering state is a CSI-SemiPersistentOnPUSCH-TriggerState in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0752] As a sub-implementation of the above embodiment, the second trigger state is configured by a CSI-SemiPersistentOnPUSCH-TriggerState in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE.

[0753] As an example, the first signaling directly indicates the second triggering state.

[0754] As one embodiment, the first signaling indicates the codepoint of the second trigger state mapping.

[0755] As one embodiment, the first signaling indicates the second trigger state by indicating the code point mapped to the second trigger state.

[0756] As an example, the DCI field CSI request of the first signaling indicates the second triggering state.

[0757] As an example, the DCI field CSI request of the first signaling indicates the code point of the second trigger state mapping.

[0758] As an example, the first signaling indicates a CSI request domain code point, which is mapped to the second trigger state.

[0759] As an example, the first signaling indicates the second trigger state by indicating a CSIrequest domain code point mapped to the second trigger state.

[0760] As an example, the first signaling indicates a trigger state from the CSI-AperiodicTriggerStateList IE, and the second trigger state is the trigger state.

[0761] As an example, one or more trigger states in the CSI-AperiodicTriggerStateList IE are mapped to code points of a DCI domain CSI request. The one or more trigger states mapped to code points of a DCI domain CSI request include the second trigger state, and the first signaling indicates the code point mapped to the second trigger state.

[0762] As a sub-implementation of the above embodiments, the first signaling indicates a CSI request domain code point, wherein the CSI request domain code point is a code point mapped by the second trigger state.

[0763] As a sub-implementation of the above embodiments, the DCI field CSI request of the first signaling indicates the code point of the second trigger state mapping.

[0764] As an example, the DCI domain CSI request of the first signaling includes N TS 1 bit, when the number of trigger states in the CSI-AperiodicTriggerStateList IE is less than or equal to 1 bit. At that time, the DCI field CSI request of the first signaling directly indicates a trigger state, and the trigger state is the second trigger state.

[0765] As an example, the DCI domain CSI request of the first signaling includes N TS Bits, when the number of trigger states in the CSI-AperiodicTriggerStateList IE is greater than At that time, the second MAC CE maps one or more trigger states in the CSI-AperiodicTriggerStateList IE to code points in the DCI domain CSI request, wherein the DCI domain CSI request of the first signaling indicates a code point mapped to a trigger state, and the trigger state is the second trigger state.

[0766] As a sub-implementation of the above embodiments, the one or more trigger states of the code points mapped to the DCI field CSI request of the first signaling include at most the following: A trigger state.

[0767] As an example, the second MAC CE is a MAC CE for indicating the trigger state subselection in the CSI-AperiodicTriggerStateList IE.

[0768] As an example, the second MAC CE is an Aperiodic CSI Trigger StateSubselection MAC CE.

[0769] As an example, the first signaling indicates a trigger state from the CSI-SemiPersistentOnPUSCH-TriggerStateList IE, and the second trigger state is the trigger state.

[0770] As an example, the trigger state in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE is mapped to the code point of the DCI domain CSI request, the second trigger state is a trigger state in the CSI-SemiPersistentOnPUSCH-TriggerStateList IE, and the first signaling indicates the code point mapped to the second trigger state.

[0771] As a sub-implementation of the above embodiments, the first signaling indicates a CSI request domain code point, wherein the CSI request domain code point is a code point mapped by the second trigger state.

[0772] As a sub-implementation of the above embodiments, the DCI field CSI request of the first signaling indicates the code point of the second trigger state mapping.

[0773] As a sub-implementation of the above embodiments, the CRC of the first signaling is scrambled by SP-CSI-RNTI.

[0774] As one embodiment, the second trigger state indicates the identifier of the first configuration information block and the identifier of the second configuration information block.

[0775] As one embodiment, the first configuration information block is a CSI-ReportConfig IE, the second configuration information block is a CSI-ReportConfig IE, and the second trigger state indicates multiple CSI-ReportConfig IEs, the multiple CSI-ReportConfig IEs including the first configuration information block and the second configuration information block.

[0776] As one embodiment, the first configuration information block is a CSI-ReportConfig IE, the second configuration information block is a CSI-ReportConfig IE, and the second trigger state indicates two CSI-ReportConfig IEs, namely the first configuration information block and the second configuration information block.

[0777] As an example, the identifier of the first configuration information block is a CSI-ReportConfigId, the identifier of the second configuration information block is a CSI-ReportConfigId, and the second trigger state indicates multiple CSI-ReportConfigIds, the multiple CSI-ReportConfigIds including the identifier of the first configuration information block and the identifier of the second configuration information block.

[0778] As an example, the identifier of the first configuration information block is a CSI-ReportConfigId, the identifier of the second configuration information block is a CSI-ReportConfigId, and the second trigger state indicates two CSI-ReportConfigIds, the two CSI-ReportConfigIds being the identifier of the first configuration information block and the identifier of the second configuration information block, respectively.

[0779] As an example, the first signaling indicates the second triggering state, the second triggering state indicates the first configuration information block and the second configuration information block, and the first reported information does not include the output of the first inference.

[0780] As one embodiment, the first signaling indicates the second triggering state, the second triggering state indicates the first configuration information block and the second configuration information block; the second triggering state indicates that the first reported information does not include the output of the first inference.

[0781] The advantages of the above method include: avoiding unnecessary reporting and saving reporting costs.

[0782] As an example, the first reported information not including the output of the first inference means that the first reported information does not include the reporting for the second configuration information block.

[0783] Example 11

[0784] Example 11 illustrates a schematic diagram of measurements on M2 RS resources according to an embodiment of this application; as attached. Figure 11 As shown.

[0785] In Example 11, as a response to the reception of the first signaling, measurements are taken on the M2 RS resources.

[0786] As an example, in response to the receipt of the first signaling, the first node measures on the M2 RS resources.

[0787] As an example, in response to the receipt of the first signaling, the measurement on the M2 RS resources includes: the first signaling triggering the M2 RS resources.

[0788] As an example, in response to the receipt of the first signaling, the measurement on the M2 RS resources includes: the first signaling triggers the measurement on the M2 RS resources.

[0789] As one embodiment, in response to the reception of the first signaling, the measurement on the M2 RS resources includes: the first node measuring on the M2 RS resources in conjunction with the reception of the first signaling.

[0790] As an example, in response to the receipt of the first signaling, the measurement on the M2 RS resources includes: when the first signaling is received by the first node, the measurement on the M2 RS resources is triggered.

[0791] As an example, in response to the receipt of the first signaling, the measurement on the M2 RS resources includes: after the first signaling is received by the first node, the first node performs the measurement on the M2 RS resources.

[0792] In a preferred embodiment, the second configuration information block indicates the M2 RS resources, and the first signaling triggers the M2 RS resources by triggering the first configuration information block connected to the second configuration information block.

[0793] As one embodiment, the second configuration information block indicates the M2 RS resources, and the first signaling triggers the M2 RS resources by triggering the first configuration information block and the second configuration information block.

[0794] As an example, the M2 RS resources are aperiodic.

[0795] As an example, each of the M2 RS resources is aperiodic.

[0796] As an example, the M2 RS resources belong to a second RS resource set, which is aperiodic.

[0797] Example 12

[0798] Example 12 illustrates a schematic diagram of RS resources associated with the same association identifier according to an embodiment of this application; as shown in the attached diagram. Figure 12 As shown.

[0799] In Example 12, the M1 RS resources and the M2 RS resources are associated with the same association identifier.

[0800] As an example, the AI / ML model used by the first node is determined by the hardware equipment manufacturer. However, the first node and the second node may still need to reach some consensus on the AI / ML model used by the first node in order to facilitate the deployment of the AI / ML model. In the above method, the association identifier provides a means to facilitate the first node and the second node to reach some consensus on the AI / ML model used by the first node.

[0801] As an example, the associated ID is a non-negative integer.

[0802] As an example, the associated ID is a string.

[0803] As an example, any two RS resources among the M1 RS resources are associated with the same association identifier.

[0804] As an example, any two RS resources among the M2 RS resources are associated with the same association identifier.

[0805] As an example, the associated ID indicates an association between two or more RS resources.

[0806] As a sub-implementation of the above embodiments, the association includes having the same or similar characteristics.

[0807] As a sub-implementation of the above embodiments, the association includes quasi-co-located.

[0808] As a sub-implementation of the above embodiments, the association includes quasi-co-addressing and the corresponding quasi-co-addressing type includes TypeD.

[0809] As a sub-implementation of the above embodiments, the association includes nesting or overlapping of beam coverage areas.

[0810] As a sub-example of the above embodiments, the association includes training datasets used to generate the same model.

[0811] As a sub-example of the above embodiments, the association includes inference datasets used to generate the same model.

[0812] As a sub-example of the above embodiments, the association includes performance monitoring datasets used to generate the same model.

[0813] As a sub-example of the above embodiments, the association includes training datasets and inference datasets used to generate the same model, respectively.

[0814] As a sub-example of the above embodiments, the association includes inference datasets and performance monitoring datasets used to generate the same model, respectively.

[0815] As an example, the features include one or more of delay spread, Doppler spread, Doppler shift, average delay, or spatial reception parameters.

[0816] As one embodiment, the feature includes a downlink transmit beam or a set of downlink transmit beams.

[0817] As an example, the M1 RS resources and the M2 RS resources being associated with the same association identifier means that the M1 RS resources and the M2 RS resources have the same or similar characteristics.

[0818] As an example, the M1 RS resources and the M2 RS resources being associated with the same association identifier include the M1 RS resources and the M2 RS resources being used to generate the training dataset and inference dataset of the same model, respectively.

[0819] As an example, the M1 RS resources and the M2 RS resources are associated with the same association identifier, and the M1 RS resources and the M2 RS resources are respectively used to generate the performance monitoring dataset and inference dataset of the same model.

[0820] As an example, the association of the M1 RS resources and the M2 RS resources with the same association identifier includes the quasi-co-addressing of any RS resource among the M1 RS resources and one RS resource among the M2 RS resources.

[0821] As an example, the association of the M1 RS resources and the M2 RS resources with the same association identifier includes the quasi-co-addressability of any RS resource in the M1 RS resources and one RS resource in the M2 RS resources, and the corresponding quasi-co-addressability type includes TypeD.

[0822] As an example, the association of the M1 RS resources and the M2 RS resources with the same association identifier includes the beam coverage range of any RS resource among the M1 RS resources being included within the beam coverage range of one RS resource among the M2 RS resources.

[0823] As an example, the configuration IE of the M1 RS resources indicates the same associated identifier.

[0824] As an example, the configuration IE for the M1 RS resources is NZP-CSI-RS-ResourceSet IE, CSI-SSB-ResourceSet IE, or CSI-ResourceConfig IE.

[0825] As an example, the configuration IE of each of the M1 RS resources indicates the same association identifier.

[0826] As an example, the configuration IE of any one of the M1 RS resources is the NZP-CSI-RS-Resource IE.

[0827] As an example, the configuration IE of the M2 RS resources indicates the same associated identifier.

[0828] As an example, the configuration IE for the M2 RS resources is NZP-CSI-RS-ResourceSet IE, CSI-SSB-ResourceSet IE, or CSI-ResourceConfig IE.

[0829] As an example, the configuration IE of each of the M2 RS resources indicates the same associated identifier.

[0830] As an example, the configuration IE of any one of the M2 RS resources is the NZP-CSI-RS-Resource IE.

[0831] As an example, the first configuration information block indicates the same associated identifier.

[0832] As an example, the first configuration information block indicates the M1 RS resources by indicating the same associated identifier.

[0833] As an example, the first configuration information block indicates the M2 RS resources by indicating the same associated identifier.

[0834] As an example, the first configuration information block indicates the first inference by indicating the same association identifier.

[0835] As an example, the first configuration information block indicates the model of the first inference by indicating the same association identifier.

[0836] As one example, the second configuration information block indicates the same associated identifier.

[0837] As an example, the second configuration information block indicates the M2 RS resources by indicating the same associated identifier.

[0838] As an example, the second configuration information block indicates the first inference by indicating the same association identifier.

[0839] As an example, the second configuration information block indicates the model of the first inference by indicating the same association identifier.

[0840] As an example, the association identifier indicates the association between a set of RS resources and an inference.

[0841] As a sub-example of the above embodiments, the association includes the use of the set of RS resources to generate a training dataset for the inference model.

[0842] As a sub-implementation of the above embodiments, the association includes the use of the set of RS resources to generate the inference dataset of the inference model.

[0843] As a sub-example of the above embodiments, the association includes the use of the set of RS resources to generate a performance monitoring dataset for the inference model.

[0844] As a sub-example of the above embodiments, the association includes the output of the inference relating to the set of RS resources.

[0845] In a preferred embodiment, the first inference is associated with the same association identifier.

[0846] As an example, the first inference associated with the same association identifier includes at least one of a set of RS resources associated with the same association identifier used to generate the inference dataset, training dataset, and performance monitoring dataset of the model for the first inference.

[0847] As an example, the first inference associated with the same association identifier includes a set of RS resources associated with the same association identifier used to obtain channel measurements of at least one of the inference dataset, training dataset, and performance monitoring dataset that generate the model for the first inference.

[0848] As an example, the first inference associated with the same association identifier includes the output of the first inference involving a set of RS resources associated with the same association identifier.

[0849] As an example, the first identifier is the same associated identifier.

[0850] As an example, the first identifier is different from the same associated identifier.

[0851] As an example, the first identifier is an associated identifier that is different from the same associated identifier.

[0852] As an example, the association identifier indicates the association between a dataset and an inference.

[0853] As a sub-example of the above embodiments, the association includes the fact that the dataset belongs to the training dataset of the inference model.

[0854] As a sub-example of the above embodiments, the association includes that the dataset belongs to the reasoning dataset of the reasoning.

[0855] As a sub-example of the above embodiments, the association includes the fact that the dataset belongs to the performance monitoring dataset of the inference model.

[0856] As an example, the association identifier indicates the association between a group of RS resources and a dataset.

[0857] As a sub-example of the above embodiments, the association includes the use of the set of RS resources to generate the dataset.

[0858] As a sub-example of the above embodiments, the association includes that measurements on the set of RS resources are used to generate the dataset.

[0859] Example 13

[0860] Example 13 illustrates a schematic diagram of a first metric, a first time window, a first time interval, and a first threshold according to an embodiment of this application; as attached. Figure 13 As shown.

[0861] In Example 13, the first metric depends on the measurement on the M1 RS resources in the first time window and the output of the first inference for the first time interval, and the first metric is obtained under the condition that the difference between the first time window and the first time interval is less than or not greater than a first threshold.

[0862] As an example, the first time window is a continuous time period.

[0863] As an example, the first time window is a continuous time period expressed as s (seconds), ms (milliseconds), or μs (microseconds).

[0864] As one embodiment, the first time window includes one or more time slots.

[0865] As one embodiment, the first time window includes one or more consecutive time slots.

[0866] As one embodiment, the first time window includes one or more discontinuous time slots.

[0867] As one embodiment, the first time window includes one or more symbols.

[0868] As one embodiment, the first time window includes one or more consecutive symbols.

[0869] As one embodiment, the first time window includes one or more discontinuous symbols.

[0870] As an example, the symbols include OFDM (Orthogonal Frequency Division Multiplexing) symbols.

[0871] As an example, the symbols include symbols obtained by passing the output of the transform precoding through OFDM symbol generation.

[0872] As an example, the symbol includes a cyclic prefix.

[0873] As an example, the symbol refers to an OFDM symbol.

[0874] As an example, the first time window includes a transmission occasion for at least one of the M1 RS resources.

[0875] As an example, the first time window includes a transmission opportunity of one of the M1 RS resources.

[0876] As an example, the first time window includes a transmission opportunity for each of the M1 RS resources.

[0877] As an example, the first time window includes the transmission timing of a CSI reference resource of one of the M1 RS resources that is no later than the transmission time of the first reported information.

[0878] As an example, the first time window includes the transmission timing of a CSI reference resource for each of the M1 RS resources no later than the transmission time of the first reported information.

[0879] As one embodiment, the first time window includes the time domain resources of the CSI reference resources of the first reported information.

[0880] As an example, at least one strongest beam depends on the measurement on the M1 RS resources in the first time window, and the first metric depends on the at least one strongest beam.

[0881] As an example, the measurements on the M1 RS resources in the first time window are used to determine the at least one strongest beam.

[0882] As an example, the first node determines the at least one strongest beam based on the measurements taken on the M1 RS resources in the first time window.

[0883] As an example, the at least one strongest beam depends solely on measurements of the transmission timing of the M1 RS resources within the first time window.

[0884] As an example, the at least one strongest beam does not depend on measurements of the M1 RS resources during transmission times outside the first time window.

[0885] As an example, the at least one strongest beam depends solely on measurements taken on the M1 RS resources during the first time window.

[0886] As an example, the at least one strongest beam does not depend on measurements on the M1 RS resources obtained outside the first time window.

[0887] As an example, any one of the strongest beams in the at least one strongest beam indicates one of the M1 RS resources.

[0888] As an example, any one of the strongest beams is the beam of one of the M1 RS resources.

[0889] As an example, any of the strongest beams in the at least one strongest beam indicates one of the M3 RS resources, and the output of the first inference relates to the M3 RS resources.

[0890] As an example, any of the at least one strongest beam is a beam of one of the M3 RS resources, and the output of the first inference relates to the M3 RS resources.

[0891] As an example, at least one RS resource identifier depends on the measurement on the M1 RS resources in the first time window, and the at least one RS resource identifier indicates the at least one strongest beam.

[0892] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is a CRI or an SSBRI.

[0893] As a reference embodiment of the above sub-example, the at least one strongest beam is the RS resource indicated by the at least one RS resource identifier.

[0894] As a reference embodiment of the above sub-example, the at least one strongest beam is the beam of the RS resource indicated by the at least one RS resource identifier.

[0895] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M1 RS resources.

[0896] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M3 RS resources, and the output of the first inference involves the M3 RS resources.

[0897] As an example, the at least one strongest beam includes only one strongest beam, and the at least one strongest beam includes the first (top-1) strongest beam.

[0898] As an example, the at least one strongest beam includes K strongest beams, where K is greater than 1, and the K strongest beams included in the at least one strongest beam are the top K strongest beams.

[0899] In a preferred embodiment, the first reported information does not include the at least one strongest beam.

[0900] The advantages of the above method include: reduced reporting costs.

[0901] As an example, at least one RSRP measurement depends on the measurement on the M1 RS resources in the first time window, and the first metric depends on the at least one RSRP measurement.

[0902] As an example, at least one strongest beam and at least one measured RSRP both depend on the measurement on the M1 RS resources in the first time window, and the first metric depends on the at least one strongest beam and the at least one measured RSRP.

[0903] As a sub-implementation of the above embodiments, the at least one measured RSRP is the RSRP of the at least one strongest beam.

[0904] As an example, the first node obtains M1 RSRPs based on the measurements on the M1 RS resources in the first time window, wherein the M1 RSRPs are the RSRPs of the M1 RS resources respectively, and the at least one strongest beam indicates the RS resource corresponding to the largest one or K RSRPs among the M1 RSRPs.

[0905] As an example, the first node obtains M1 RSRPs based on the measurements on the M1 RS resources in the first time window, the M1 RSRPs being the RSRPs of the M1 RS resources respectively, the M1 RSRPs being used to determine the RSRPs of M3 RS resources, the at least one strongest beam indicating the RS resource with the largest corresponding RSRP among the M3 RS resources; the output of the first inference relates to the M3 RS resources.

[0906] How the first node determines the RSRPs of the M3 RS resources based on the M1 RSRPs is determined by the hardware equipment vendor. Some non-limiting implementation methods are described below:

[0907] As an example, the first node interpolates the M1 RSRPs to determine the RSRPs of the M3 RS resources.

[0908] As an example, the first node performs a table lookup on the M1 RSRPs to determine the RSRPs of the M3 RS resources.

[0909] As an example, the first node filters the M1 RSRPs to determine the RSRPs of the M3 RS resources.

[0910] As one example, the first time interval includes one or more time slots.

[0911] As one example, the first time interval includes one or more consecutive time slots.

[0912] As one example, the first time interval includes one or more symbols.

[0913] As one example, the first time interval includes one or more consecutive symbols.

[0914] As an example, the output for the first time interval refers to the first time interval.

[0915] As an example, the output for the first time interval is generated for the first time interval.

[0916] As an example, the output for the first time interval indicates channel state information within the first time interval.

[0917] As an example, the output for the first time interval indicates the predicted beam within the first time interval.

[0918] As an example, the output for the first time interval indicates the predicted RSRP within the first time interval.

[0919] As an example, the effective range of the output for the first time interval is limited to the first time interval.

[0920] As an example, the time-domain resource of the CSI reference resource for the output of the first time interval is the first time interval.

[0921] As a sub-implementation of the above embodiments, the output for the first time interval is used to generate a report.

[0922] As an example, the definition of the CSI reference resource is based on Section 5 of 3GPP TS38.214.

[0923] As an example, the output of the first inference for the first time interval depends on the measurements on the M2 RS resources during the first time interval.

[0924] As an example, the output of the first inference for the first time interval is the output obtained by the first inference with the measurement results or preprocessed information of the measurement results on the M2 RS resources during the first time interval as input.

[0925] As an example, the output of the first inference for the first time interval is an output obtained based on the input of the first inference depending on the measurements on the M2 RS resources within the first time interval.

[0926] In a preferred embodiment, the output of the first inference for the first time interval indicates at least one predicted beam, the at least one predicted beam for the first time interval, and the first metric depends on the at least one predicted beam.

[0927] As an example, the at least one predicted beam for the first time interval includes the time-domain resource of the CSI reference resource of the at least one predicted beam being the first time interval.

[0928] As one embodiment, the at least one predicted beam for the first time interval includes the at least one predicted beam depending on measurements on the M2 RS resources during the first time interval.

[0929] As one embodiment, the at least one predicted beam for the first time interval includes the at least one predicted beam being predicted for the first time interval.

[0930] As one embodiment, the at least one predicted beam for the first time interval includes at least one strongest beam in the predicted first time interval.

[0931] As an example, any one of the at least one prediction beams indicates one of the M1 RS resources.

[0932] As an example, any one of the at least one predicted beams is a beam of one of the M1 RS resources.

[0933] As an example, any one of the at least one prediction beams indicates one of the M2 RS resources.

[0934] As an example, any one of the at least one predicted beams is a beam of one of the M2 RS resources.

[0935] As an example, any one of the at least one prediction beams indicates one of the M3 RS resources, where M3 is a positive integer greater than 1; the M3 RS resources, the M1 RS resources, and the M2 RS resources are configured separately.

[0936] As an example, any one of the at least one predicted beams is a beam of one of the M3 RS resources, where M3 is a positive integer greater than 1; the M3 RS resources, the M1 RS resources, and the M2 RS resources are configured separately.

[0937] As an example, the output of the first inference for the first time interval indicates at least one RS resource identifier, the at least one RS resource identifier indicating the at least one predicted beam.

[0938] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is a CRI or an SSBRI.

[0939] As a reference embodiment of the above sub-example, the at least one predicted beam is an RS resource indicated by the at least one RS resource identifier.

[0940] As a reference embodiment of the above sub-example, the at least one predicted beam is the beam of the RS resource indicated by the at least one RS resource identifier.

[0941] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M1 RS resources.

[0942] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M2 RS resources.

[0943] As a sub-implementation of the above embodiments, any one of the at least one RS resource identifiers is the CRI or SSBRI of one of the M3 RS resources, where M3 is a positive integer greater than 1; the M3 RS resources, the M1 RS resources and the M2 RS resources are configured separately.

[0944] As an example, the at least one predicted beam includes only one predicted beam, and the at least one predicted beam includes the first (top-1) predicted beam.

[0945] As an example, the at least one predicted beam includes K predicted beams, where K is greater than 1, and the K predicted beams included in the at least one predicted beam are the top K predicted beams.

[0946] In a preferred embodiment, the first reported information does not include the at least one predicted beam.

[0947] The advantages of the above method include: reduced reporting costs.

[0948] As an example, the at least one predicted beam depends on measurements on the M2 RS resources.

[0949] As an example, the output of the first inference for the first time interval indicates at least one predicted RSRP, the at least one predicted RSRP for the first time interval, and the first metric depends on the at least one predicted RSRP.

[0950] As an example, the at least one predicted RSRP for the first time interval includes the at least one predicted RSRP being predicted for the first time interval.

[0951] As an example, the at least one predicted RSRP for the first time interval includes the at least one predicted RSRP being the RSRP of at least one predicted beam in the predicted first time interval.

[0952] As an example, the output of the first inference for the first time interval indicates at least one predicted beam and at least one predicted RSRP, and the first metric depends on the at least one predicted beam and the at least one predicted RSRP.

[0953] As a sub-implementation of the above embodiments, the at least one predicted RSRP is the RSRP of the at least one predicted beam.

[0954] As a sub-implementation of the above embodiments, the at least one predicted RSRP is the predicted RSRP of the at least one predicted beam.

[0955] As an example, the first metric depends on at least one predicted beam and at least one strongest beam, the at least one strongest beam depending on the measurement on the M1 RS resources in the first time window, and the output of the first inference for the first time interval indicates the at least one predicted beam.

[0956] As an example, the first metric depends on at least one predicted beam and at least one strongest beam.

[0957] As a sub-example of the above embodiment, the output of the first inference for the first time interval indicates the at least one predicted beam, and the measurement on the M1 RS resources in the first time window is used to determine the at least one strongest beam.

[0958] The problems to be addressed in this application include: how to monitor the performance of AI / ML models used for beam prediction.

[0959] The problems to be addressed in this application include: how to determine the predicted beams and the strongest beams for mutual comparison, so as to ensure the reliability and fairness of the performance monitoring results of AI / ML models for beam prediction.

[0960] The advantages of the above method include ensuring that the predicted beams and the strongest beams being compared are comparable.

[0961] The advantages of the above method include: ensuring the reliability of the performance monitoring results of AI / ML models, thereby ensuring the performance of AI / ML models.

[0962] The benefits of the above methods include improved system performance.

[0963] As an example, the output of the first inference for the first time interval indicates at least one predicted beam, and the measurement on the M1 RS resources in the first time window is used to determine at least one strongest beam; the first metric depends on the at least one predicted beam and the at least one strongest beam.

[0964] As an example, the first metric depends on whether the at least one predicted beam and the at least one strongest beam include the same beam.

[0965] As an example, the first metric depends on whether the at least one strongest beam is the at least one predicted beam.

[0966] As an example, the first metric depends on whether the at least one strongest beam includes one of the at least one predicted beams.

[0967] As an example, the first metric depends on whether the at least one predicted beam includes the strongest beam of the at least one strongest beam.

[0968] As an example, the at least one predicted beam includes only one predicted beam, the at least one strongest beam includes only one strongest beam, and the first metric depends on whether the predicted beam is the strongest beam.

[0969] As one embodiment, the at least one predicted beam includes only one predicted beam, and the at least one strongest beam includes multiple strongest beams, wherein the first metric depends on whether the multiple strongest beams include the one predicted beam.

[0970] As one embodiment, the at least one predicted beam includes multiple predicted beams, and the at least one strongest beam includes only one strongest beam, wherein the first metric depends on whether the multiple predicted beams include the one strongest beam.

[0971] As an example, the output of the first inference for the first time interval indicates at least one predicted RSRP, and the measurement on the M1 RS resources in the first time window is used to determine at least one measured RSRP; the first metric depends on the at least one predicted RSRP and the at least one measured RSRP.

[0972] As an example, the first metric depends on the difference between the at least one measured RSRP and the at least one predicted RSRP.

[0973] As an example, the at least one measured RSRP includes only one measured RSRP, and the at least one predicted RSRP includes only one predicted RSRP; the first metric depends on the difference between the one measured RSRP and the one predicted RSRP.

[0974] As an example, the at least one measured RSRP includes only one measured RSRP, and the at least one predicted RSRP includes multiple predicted RSRPs; the first metric depends on the difference between the one measured RSRP and the maximum predicted RSRP among the multiple predicted RSRPs.

[0975] As an example, the at least one measured RSRP includes multiple measured RSRPs, and the at least one predicted RSRP includes only one predicted RSRP; the first metric depends on the difference between the maximum measured RSRP among the multiple measured RSRPs and the one predicted RSRP.

[0976] As an example, the first metric depends on the difference between the maximum measured RSRP among the at least one measured RSRP and the maximum predicted RSRP among the at least one predicted RSRP.

[0977] As an example, the first metric is conditional upon the difference between the first time window and the first time interval being less than the first threshold.

[0978] As an example, the first metric is obtained under the condition that the difference between the first time window and the first time interval is less than the first threshold.

[0979] As an example, the calculation of the first metric is conditional on the difference between the first time window and the first time interval being less than the first threshold.

[0980] As an example, the first metric depends on at least one predicted beam and at least one strongest beam, the at least one predicted beam being for the first time interval, the at least one strongest beam being for measurements on the M1 RS resources within the first time window, and the first metric being obtained under the condition that the difference between the first time window and the first time interval is less than the first threshold.

[0981] As an example, the output of the first inference for the first time interval includes at least one predicted beam, and the measurement on the M1 RS resources in the first time window is used to determine at least one strongest beam. The at least one predicted beam and the at least one strongest beam are used to determine the first metric only if the difference between the first time window and the first time interval is less than the first threshold.

[0982] As an example, the first metric is conditional on the difference between the first time window and the first time interval not being greater than the first threshold.

[0983] As an example, the first metric is obtained under the condition that the difference between the first time window and the first time interval is not greater than the first threshold.

[0984] As an example, the calculation of the first metric is based on the condition that the difference between the first time window and the first time interval is not greater than the first threshold.

[0985] As an example, the first metric depends on at least one predicted beam and at least one strongest beam, the at least one predicted beam being for the first time interval, and the at least one strongest beam being for measurements on the M1 RS resources within the first time window, the first metric being obtained under the condition that the difference between the first time window and the first time interval is not greater than the first threshold.

[0986] As an example, the output of the first inference for the first time interval includes at least one predicted beam, and the measurement on the M1 RS resources in the first time window is used to determine at least one strongest beam. The first metric depends on whether the at least one predicted beam and the at least one strongest beam include the same beam, only if the difference between the first time window and the first time interval is not greater than the first threshold.

[0987] In a preferred embodiment, the M1 transmission opportunities are transmission opportunities in which the difference between the M1 RS resources and the first time interval is less than or not greater than the first threshold, and the first time window includes the M1 transmission opportunities.

[0988] As a sub-implementation of the above embodiment, the first time window includes the time slot in which each of the M1 transmission opportunities is located.

[0989] As an example, for any RS resource among the M1 RS resources, if the difference between multiple transmission opportunities of any RS resource and the first time interval is less than or not greater than the first threshold, the first time window includes the transmission opportunity with the smallest difference between the multiple transmission opportunities and the first time interval.

[0990] As a sub-implementation of the above embodiment, the first time window includes the time slot containing the transmission opportunity with the smallest difference between the plurality of transmission opportunities and the first time interval.

[0991] As an example, for any one of the M1 RS resources, if the difference between multiple transmission opportunities of any one RS resource and the first time interval is less than or not greater than the first threshold, the first time window includes the multiple transmission opportunities.

[0992] As a sub-implementation of the above embodiment, the first time window includes the time slot in which each of the plurality of transmission opportunities is located.

[0993] As an example, for any RS resource among the M1 RS resources, if the difference between the multiple transmission opportunities of the RS resource and the first time interval is less than or not greater than the first threshold, the first node determines a transmission opportunity from the multiple transmission opportunities, and the first time window includes only the one transmission opportunity among the multiple transmission opportunities.

[0994] As a preferred embodiment, if one of the M1 RS resources does not have a transmission opportunity and the difference between the first time interval and the first time interval is less than or not greater than the first threshold, the first metric does not depend on the output of the first inference for the first time interval.

[0995] As a sub-implementation of the above embodiment, the output of the first inference for the first time interval is not used to calculate the first metric.

[0996] As an example, the first threshold is configurable.

[0997] As an example, the first threshold is configured by RRC signaling.

[0998] As an example, the first configuration information block indicates the first threshold.

[0999] As one example, the second configuration information block indicates the first threshold.

[1000] As an example, the first threshold is configured for the first node.

[1001] The advantages of the above methods include: facilitating joint optimization on the network side and further improving the overall system performance.

[1002] As an example, the first reported information indicates the first threshold.

[1003] As one example, the first threshold depends on the UE capabilities of the first node.

[1004] As an example, the first threshold is determined by the first node itself.

[1005] As an example, the first threshold is reported by the first node.

[1006] The advantages of the above method include: greater flexibility and adaptability to different terminals and different channel environments.

[1007] As an example, the first threshold is predefined.

[1008] As an example, the first threshold is fixed.

[1009] The advantages of the above method include: reduced air interface overhead.

[1010] As an example, the first threshold is a positive real number.

[1011] As an example, the first threshold is a non-negative real number.

[1012] As an example, the first threshold is a positive integer.

[1013] As an example, the unit of the first threshold is s (seconds), ms (milliseconds), or μs (microseconds).

[1014] As an example, the first threshold is represented as the number of symbols.

[1015] As an example, the first threshold is represented as the number of time slots.

[1016] As an example, the gap between the first time window and the first time interval refers to the absolute value of the length of the time gap between the start time of the first time window and the start time of the first time interval.

[1017] As an example, the gap between the first time window and the first time interval refers to the absolute value of the length of the time gap between the end time of the first time window and the end time of the first time interval.

[1018] As an example, the gap between the first time window and the first time interval refers to the absolute value of the length of the time gap between the end time of the first time window and the start time of the first time interval.

[1019] As a sub-implementation of the above embodiments, the end time of the first time window is earlier than the start time of the first time interval.

[1020] As an example, the gap between the first time window and the first time interval refers to the absolute value of the length of the time gap between the start time of the first time window and the end time of the first time interval.

[1021] As a sub-implementation of the above embodiments, the end time of the first time interval is earlier than the start time of the first time window.

[1022] Example 14

[1023] Example 14 illustrates a schematic diagram of a first time interval and a first time window according to an embodiment of this application; as attached. Figure 14 As shown.

[1024] In Example 14, the first time interval includes the time-domain resources of the first CSI reference resource, the most recent of the M2 RS resources is used to determine that the transmission timing of the first metric is no later than the first CSI reference resource, the first time window includes the transmission timing of the M1 RS resources; the output of the first inference for the first time interval indicates at least one predicted beam, and the measurement on the M1 RS resources in the first time window is used to determine at least one strongest beam; the first metric depends on the at least one predicted beam and the at least one strongest beam.

[1025] In the appendix Figure 14 In the diagram, the diagonally filled boxes represent a transmission opportunity for each of the M2 RS resources, and the cross-line filled boxes represent a transmission opportunity for each of the M1 RS resources.

[1026] As an example, Appendix Figure 14 The cross-line filled box in the text includes one of the M1 RS resources used to generate the first metric.

[1027] As an example, Appendix Figure 14 The cross-line filled box in the text includes one of the M1 RS resources used for the transmission timing of generating the at least one strongest beam.

[1028] As an example, Appendix Figure 14 The diagonally filled box in the text includes the most recent transmission timing of each of the M2 RS resources used to generate the first metric.

[1029] As an example, Appendix Figure 14 The diagonally filled box in the text includes the transmission timing of the most recent RS resource among the M2 RS resources used to generate the at least one predicted beam.

[1030] As an example, any of the strongest beams in the at least one strongest beam indicates one of the M1 RS resources.

[1031] As an example, any of the strongest beams in the at least one strongest beam indicates one of the M3 RS resources, where M3 is greater than M2.

[1032] As an example, any one of the at least one prediction beams indicates one of the M1 RS resources, where M1 is greater than M2.

[1033] As an example, any one of the at least one prediction beams indicates one of the M3 RS resources, where M3 is greater than M2.

[1034] As an example, any one of the strongest beams in the at least one strongest beam indicates one of the M1 RS resources, and any one of the prediction beams in the at least one prediction beam indicates one of the M1 RS resources.

[1035] As a sub-implementation of the above embodiment, M1 is greater than M2.

[1036] As an example, any of the strongest beams in the at least one strongest beam indicates one of the M3 RS resources, and any of the at least one prediction beam indicates one of the M3 RS resources.

[1037] As a sub-implementation of the above embodiment, M3 is greater than M2.

[1038] As a sub-example of the above embodiment, the M1 RS resources, the M2 RS resources and the M3 RS resources are configured separately.

[1039] As an example, the prediction refers to spatial prediction.

[1040] As an example, the first metric depends on whether the at least one strongest beam includes one of the at least one predicted beams, and whether the at least one predicted beam includes one of the at least one strongest beams.

[1041] As an example, the first metric depends on at least one of the following: whether the at least one strongest beam is the at least one predicted beam; whether the first (top-1) strongest beam among the at least one strongest beam is a predicted beam among the at least one predicted beam; and whether the first (top-1) predicted beam among the at least one predicted beam is a strongest beam among the at least one strongest beam.

[1042] As an example, the first time window includes a transmission opportunity for each of the M1 RS resources.

[1043] As an example, the first time window consists of a transmission opportunity for each of the M1 RS resources.

[1044] As an example, the first time window includes the time slot in which a transmission opportunity occurs for each of the M1 RS resources.

[1045] As an example, the first time window consists of the time slot in which a transmission opportunity of each of the M1 RS resources occurs.

[1046] As an example, the first time window includes the transmission timing of the M1 RS resources used to generate the first metric.

[1047] As an example, the first time window consists of the transmission timing of the M1 RS resources used to generate the first metric.

[1048] As an example, the first time window includes one of the M1 RS resources used to generate the transmission timing of the first metric.

[1049] As an example, the first time window consists of one transmission opportunity of each of the M1 RS resources used to generate the first metric.

[1050] As an example, the first time window includes a time slot in each of the M1 RS resources where the transmission timing for generating the first metric is located.

[1051] As an example, the first time window consists of a time slot in each of the M1 RS resources where the transmission timing for generating the first metric is located.

[1052] As an example, the first time window includes one of the M1 RS resources for the transmission timing used to generate the at least one strongest beam.

[1053] As an example, the first time window consists of one of the M1 RS resources being used for the transmission timing of generating the at least one strongest beam.

[1054] As an example, the first time window includes a time slot in which the transmission timing for generating the at least one strongest beam occurs in each of the M1 RS resources.

[1055] As an example, the first time window consists of a time slot in which the transmission timing for generating the at least one strongest beam occurs in each of the M1 RS resources.

[1056] As an example, the first time window is the union of the transmission opportunities of each of the M1 RS resources used to generate the first metric or the at least one strongest beam.

[1057] As an example, the first time window is the union of the time slots of each of the M1 RS resources in which the transmission timing for generating the first metric or the at least one strongest beam is located.

[1058] As an example, a transmission timing used to generate the first metric or the at least one predicted beam or the at least one strongest beam means that a measurement in the transmission timing is used to generate the first metric or the at least one predicted beam or the at least one strongest beam.

[1059] As an example, the first node generates the first metric based on the transmission opportunities of the M1 RS resources that are only located within the first time window.

[1060] As an example, the first node generates the first metric based on only one transmission opportunity for each of the M1 RS resources, and the first time window includes the only transmission opportunity for each of the M1 RS resources.

[1061] As a sub-implementation of the above embodiment, the first time window includes the time slot in which the only transmission opportunity of each of the M1 RS resources is located.

[1062] As an example, the first node generates the at least one strongest beam based on the transmission opportunities of the M1 RS resources that are only located within the first time window.

[1063] As an example, the first node generates the at least one strongest beam based on only one transmission opportunity of each of the M1 RS resources, and the first time window includes only one transmission opportunity of each of the M1 RS resources.

[1064] As a sub-implementation of the above embodiment, the first time window includes the time slot in which the only transmission opportunity of each of the M1 RS resources is located.

[1065] As an example, the first node transmits the at least one predicted beam, and the first time interval is earlier than the transmission of the at least one predicted beam.

[1066] As an example, the first time interval is the time-domain resource of the first CSI reference resource.

[1067] As an example, the first node transmits the at least one predicted beam, and the first CSI reference resource is the CSI reference resource of the at least one predicted beam.

[1068] As a sub-implementation of the above embodiments, the at least one predicted beam and the first reported information are transmitted on two different physical layer channels.

[1069] As an example, the first node transmits the at least one predicted beam in time slot n1, and the time domain resources of the first CSI reference resource depend on time slot n1.

[1070] As an example, the first CSI reference resource is the CSI reference resource of the first reported information.

[1071] As an example, the first node sends the first reporting information in time slot n1, and the time domain resources of the first CSI reference resource depend on time slot n1.

[1072] As an example, the definition of the CSI reference resource is based on 3GPP TS38.214.

[1073] As an example, the temporal resource of the first CSI reference resource depends on n0 and a first offset, where n0 depends on n1, and the first offset is an integer.

[1074] As an example, the time-domain resource of the first CSI reference resource is a time slot (n0 - the first offset).

[1075] As one embodiment, n0 depends on the product of n1 and a first ratio, the first ratio depending on the downlink subcarrier spacing configuration and the uplink subcarrier spacing configuration.

[1076] As a sub-example of the above embodiment, the first ratio is equal to the ratio of 2 raised to the power of the downlink subcarrier spacing configuration and 2 raised to the power of the uplink subcarrier spacing configuration.

[1077] As an example, n0 is equal to the product of n1 and the first ratio rounded down.

[1078] As an example, n0 is equal to the product of n1 and the first ratio, rounded down, plus a third offset; the third offset is an integer.

[1079] As a sub-example of the above embodiment, the third offset depends on the higher-level parameter "ca-SlotOffset".

[1080] As a sub-implementation of the above embodiments, the third offset depends on the downlink subcarrier spacing configuration.

[1081] As a sub-implementation of the above embodiment, the third offset is equal to the first given value rounded down, and the first given value is linearly related to the downlink subcarrier spacing configuration power of 2.

[1082] As one example, the first offset depends on the downlink subcarrier spacing configuration.

[1083] As an example, the first offset ensures that the time-domain resources of the first CSI reference resource and the DCI (Downlink Control Information) that triggers the first reporting information or the at least one predicted beam are in the same valid downlink time slot.

[1084] As an example, the first offset is the minimum value that is greater than or equal to a first given threshold and such that a slot (n0 - the first offset) corresponds to a valid downlink slot; the first given threshold is an integer.

[1085] As a sub-implementation of the above embodiments, the first given threshold is related to the downlink subcarrier spacing configuration.

[1086] As a sub-example of the above embodiments, the first given threshold is related to the delay requirement.

[1087] As an example, the time-domain resource of the first CSI reference resource is a time slot (n0 - first offset - second offset), where the second offset is a positive integer.

[1088] As a sub-example of the above embodiment, the second offset depends on the higher-level parameter "CellSpecificKoffset".

[1089] As a sub-example of the above embodiment, the second offset depends on the Differential Koffset MACCE command.

[1090] As a sub-implementation of the above embodiments, the second offset depends on the downlink subcarrier spacing configuration.

[1091] As an example, the subcarrier spacing configuration of the M1 RS resources is the downlink subcarrier spacing configuration.

[1092] As an example, the subcarrier spacing configuration of the M2 RS resources is the downlink subcarrier spacing configuration.

[1093] As an example, the subcarrier spacing configuration of the first reported information is the uplink subcarrier spacing configuration.

[1094] As an example, the downlink subcarrier spacing configuration is a non-negative integer.

[1095] As an example, the downlink subcarrier spacing configuration has no unit.

[1096] As an example, the uplink subcarrier spacing configuration is a non-negative integer.

[1097] As an example, the uplink subcarrier spacing configuration has no unit.

[1098] As an example, the downlink subcarrier spacing is equal to 2 raised to the power of 15 kHz.

[1099] As an example, the uplink subcarrier spacing configuration is equal to 2 raised to the power of 15 kHz.

[1100] Example 15

[1101] Example 15 illustrates a schematic diagram of a first time interval and a first time window according to an embodiment of this application; as attached. Figure 15 As shown.

[1102] In Example 15, the first time interval includes the most recent one of the M2 RS resources used to determine the transmission timing of the first metric, and the first time window includes the transmission timing of the M1 RS resources; the output of the first inference for the first time interval indicates at least one predicted beam, and the measurement on the M1 RS resources in the first time window is used to determine at least one strongest beam; the first metric depends on the at least one predicted beam and the at least one strongest beam.

[1103] In the appendix Figure 15 In the diagram, the diagonally filled boxes represent a transmission opportunity for each of the M2 RS resources, and the cross-line filled boxes represent a transmission opportunity for each of the M1 RS resources.

[1104] As an example, Appendix Figure 15 The cross-line filled box in the text includes one of the M1 RS resources used to generate the first metric.

[1105] As an example, Appendix Figure 15 The cross-line filled box in the text includes one of the M1 RS resources used for the transmission timing of generating the at least one strongest beam.

[1106] As an example, Appendix Figure 15The diagonally filled box in the text includes the most recent transmission timing of each of the M2 RS resources used to generate the first metric.

[1107] As an example, Appendix Figure 15 The diagonally filled box in the text includes the transmission timing of the most recent RS resource among the M2 RS resources used to generate the at least one predicted beam.

[1108] As an example, any one of the strongest beams in the at least one strongest beam indicates one of the M1 RS resources, and any one of the prediction beams in the at least one prediction beam indicates one of the M1 RS resources.

[1109] As an example, any one of the strongest beams in the at least one strongest beam indicates one of the M3 RS resources, and any one of the prediction beams in the at least one prediction beam indicates one of the M3 RS resources.

[1110] As an example, M1 is greater than M2.

[1111] As an example, M3 is greater than M2.

[1112] As an example, the prediction refers to spatial prediction.

[1113] As an example, the first node transmits the at least one predicted beam, and the first time interval is earlier than the transmission of the at least one predicted beam.

[1114] As an example, the first time window includes a transmission opportunity for each of the M1 RS resources.

[1115] As an example, the first time window includes the time slot in which a transmission opportunity occurs for each of the M1 RS resources.

[1116] As an example, the first time interval is no later than the first CSI reference resource.

[1117] As an example, the first CSI reference resource is the CSI reference resource of the at least one predicted beam, the time domain resource of the CSI reference resource of the at least one predicted beam depends on time slot n0 and a first offset, the time slot n0 depends on time slot n1, and the first node transmits the at least one predicted beam in the time slot n1.

[1118] As an example, the first CSI reference resource is the CSI reference resource of the first reported information. The time domain resource of the CSI reference resource of the first reported information depends on time slot n0 and a first offset. The time slot n0 depends on time slot n1. The first node sends the first reported information in the time slot n1.

[1119] The embodiment of n0 and the first offset is described in Example 14.

[1120] As an example, the at least one predicted beam depends on measurements on the M2 RS resources during the first time interval.

[1121] As an example, the output of the first inference for the first time interval is obtained based on the input of the first inference depending on the measurements on the M2 RS resources within the first time interval.

[1122] As an example, the first time interval includes the most recent transmission time of each of the M2 RS resources no later than the first CSI reference resource.

[1123] As an example, the first time interval consists of the most recent transmission time of each of the M2 RS resources no later than the first CSI reference resource.

[1124] As an example, the first time interval includes the time slot of each of the M2 RS resources, which is no later than the most recent transmission time of the first CSI reference resource.

[1125] As an example, the first time interval consists of the time slot of each of the M2 RS resources, which is no later than the most recent transmission time of the first CSI reference resource.

[1126] As an example, the first time interval includes the most recent transmission timing of each of the M2 RS resources used to generate the first metric.

[1127] As an example, the first time interval consists of the most recent transmission timing of each of the M2 RS resources used to generate the first metric.

[1128] As an example, the first time interval includes the time slot in which the most recent transmission opportunity for each of the M2 RS resources was used to generate the first metric was located.

[1129] As an example, the first time interval consists of the time slot in which the most recent transmission opportunity of each of the M2 RS resources was used to generate the first metric occurred.

[1130] As an example, the first time interval includes the most recent transmission timing of each of the M2 RS resources used to generate the at least one prediction beam.

[1131] As an example, the first time interval consists of the most recent transmission timing of each of the M2 RS resources used to generate the at least one prediction beam.

[1132] As an example, the first time interval includes the time slot in which the most recent transmission opportunity of each of the M2 RS resources was used to generate the at least one prediction beam.

[1133] As an example, the first time interval consists of the time slot in which the most recent transmission opportunity of each of the M2 RS resources was used to generate the at least one prediction beam.

[1134] As an example, the first time interval is the union of the most recent transmission timings of each of the M2 RS resources used to generate the first metric or the at least one predicted beam.

[1135] As an example, the first time interval is the union of the time slots in which the most recent transmission timing of each of the M2 RS resources was used to generate the first metric or the at least one predicted beam.

[1136] Example 16

[1137] Example 16 illustrates a schematic diagram of a first time interval and a first time window according to an embodiment of this application; as attached. Figure 16 As shown.

[1138] In Example 16, the output of the first inference for the first time interval indicates at least one predicted beam, the at least one predicted beam for the first time interval; the first time window includes the transmission timing of the M1 RS resources, and the measurement on the M1 RS resources in the first time window is used to determine at least one strongest beam; the first metric depends on the at least one predicted beam and the at least one strongest beam.

[1139] In the appendix Figure 16In the diagram, each diagonally filled box includes a transmission opportunity for each of the M2 RS resources, and each cross-line filled box includes a transmission opportunity for each of the M1 RS resources.

[1140] As an example, Appendix Figure 16 The cross-line filled box in the text includes one of the M1 RS resources used to generate the first metric.

[1141] As an example, Appendix Figure 16 The cross-line filled box in the text includes one of the M1 RS resources used for the transmission timing of generating the at least one strongest beam.

[1142] As an example, Appendix Figure 16 Each diagonally filled box in the table includes one of the M2 RS resources used to generate the transmission timing of the first metric.

[1143] As an example, Appendix Figure 16 Each diagonally filled box in the diagram includes one of the M2 RS resources used to generate the transmission timing of the at least one predicted beam.

[1144] As one embodiment, the first node transmits the at least one predicted beam, and the first time interval is later than the transmission of the at least one predicted beam.

[1145] As an example, the first metric depends on whether the at least one strongest beam includes one of the at least one predicted beams, and whether the at least one predicted beam includes one of the at least one strongest beams.

[1146] As an example, the first metric depends on at least one of the following: whether the at least one strongest beam is the at least one predicted beam; whether the first (top-1) strongest beam among the at least one strongest beam is a predicted beam among the at least one predicted beam; and whether the first (top-1) predicted beam among the at least one predicted beam is a strongest beam among the at least one strongest beam.

[1147] As an example, any one of the strongest beams in the at least one strongest beam indicates one of the M1 RS resources, and any one of the at least one predicted beams indicates one of the M2 RS resources.

[1148] As a sub-implementation of the above embodiment, M1 is equal to M2, and the M1 RS resources are the M2 RS resources.

[1149] As an example, any one of the strongest beams in the at least one strongest beam indicates one of the M1 RS resources, and any one of the at least one predicted beams indicates one of the M1 RS resources.

[1150] As a sub-implementation of the above embodiment, M1 is greater than M2.

[1151] As an example, any one of the strongest beams in the at least one strongest beam indicates one of the M3 RS resources, and any one of the at least one predicted beams indicates one of the M3 RS resources.

[1152] As a sub-implementation of the above embodiment, M3 is greater than M2.

[1153] As a sub-example of the above embodiment, the M1 RS resources, the M2 RS resources and the M3 RS resources are configured separately.

[1154] As an example, the prediction refers to time prediction.

[1155] As an example, the at least one predicted beam is a predicted beam for the first time interval obtained based on the transmission timing of the M2 RS resources before the first time interval.

[1156] As an example, the first time window includes one of the M1 RS resources used to generate the transmission timing of the first metric.

[1157] As an example, the first time window consists of one transmission opportunity of each of the M1 RS resources used to generate the first metric.

[1158] As an example, the first time window includes a time slot in each of the M1 RS resources where the transmission timing for generating the first metric is located.

[1159] As an example, the first time window consists of a time slot in each of the M1 RS resources where the transmission timing for generating the first metric is located.

[1160] As an example, the first time window includes one of the M1 RS resources for the transmission timing used to generate the at least one strongest beam.

[1161] As an example, the first time window consists of one of the M1 RS resources being used for the transmission timing of generating the at least one strongest beam.

[1162] As an example, the first time window includes a time slot in which the transmission timing for generating the at least one strongest beam occurs in each of the M1 RS resources.

[1163] As an example, the first time window consists of a time slot in which the transmission timing for generating the at least one strongest beam occurs in each of the M1 RS resources.

[1164] As an example, the first time window is the union of the transmission opportunities of each of the M1 RS resources used to generate the at least one strongest beam or the first metric.

[1165] As an example, the first time window is the union of the time slots of each of the M1 RS resources in which the transmission timing for generating the at least one strongest beam or the first metric is located.

[1166] As an example, the at least one predicted beam is predicted for the first time interval.

[1167] As an example, the at least one predicted beam is at least one of the strongest beams in the predicted first time interval.

[1168] As an example, the first time interval is later than the CSI reference resource of the at least one predicted beam.

[1169] As an example, the CSI reference resource of the at least one predicted beam is described in embodiments 15 and 14.

[1170] As an example, the first time interval is later than the CSI reference resource of the first reported information.

[1171] As an example, the CSI reference resource of the first reported information is illustrated in Examples 15 and 14.

[1172] As an example, the first time interval is later than the most recent transmission timing of any of the M2 RS resources used to generate the first metric.

[1173] As an example, the first time interval is later than the most recent transmission timing of any of the M2 RS resources used to generate the at least one prediction beam.

[1174] Example 17

[1175] Example 17 illustrates a schematic diagram of a first configuration information block indicating a first threshold according to an embodiment of this application; as shown in the appendix. Figure 17 As shown.

[1176] As an example, the first configuration information block explicitly indicates the first threshold.

[1177] As an example, the first configuration information block indicates the first threshold from a plurality of candidate thresholds.

[1178] As an example, the plurality of candidate thresholds are configured by RRC signaling.

[1179] As an example, the plurality of candidate thresholds are fixed.

[1180] As an example, the plurality of candidate thresholds are predefined.

[1181] As an example, the first configuration information block implicitly indicates the first threshold.

[1182] As an example, the first configuration information block indicates the first threshold by indicating other information.

[1183] As an example, the other information includes, but is not limited to, one or more of the following: UE capability level, channel environment type, mobile speed, subcarrier spacing, carrier frequency, delay spread, Doppler spread, Doppler shift, average delay, and spatial reception parameters.

[1184] Example 18

[1185] Example 18 illustrates a schematic diagram of a first reporting information indicating a first threshold according to an embodiment of this application; as attached. Figure 18 As shown.

[1186] As an example, the first reported information explicitly indicates the first threshold.

[1187] As one embodiment, the first reported information indicates the first threshold from a plurality of candidate thresholds.

[1188] As an example, the plurality of candidate thresholds are configured by RRC signaling.

[1189] As an example, the plurality of candidate thresholds are fixed.

[1190] As an example, the plurality of candidate thresholds are predefined.

[1191] As an example, the first reported information implicitly indicates the first threshold.

[1192] As one embodiment, the first reported information indicates the first threshold by indicating other information.

[1193] As an example, the other information includes, but is not limited to, one or more of the following: UE capability level, channel environment type, mobile speed, subcarrier spacing, carrier frequency, delay spread, Doppler spread, Doppler shift, average delay, and spatial reception parameters.

[1194] Example 19

[1195] Example 19 illustrates a schematic diagram of a first metric according to an embodiment of this application; as attached Figure 19 As shown.

[1196] In Example 19, the output of the first inference for the first time interval indicates the at least one predicted beam, the at least one strongest beam depending on the measurement on the M1 RS resources in the first time window, the first metric depending on the at least one strongest beam and the at least one predicted beam; the difference between the first time window and the first time interval is less than or not greater than the first threshold.

[1197] As an example, the first metric depends on whether the at least one strongest beam includes a predicted beam from the at least one predicted beam.

[1198] As an example, the first metric indicates whether the at least one strongest beam includes a predicted beam from the at least one predicted beam.

[1199] As an example, the first metric depends on whether the at least one predicted beam includes the strongest beam among the at least one strongest beam.

[1200] As an example, the first metric indicates whether the at least one predicted beam includes the strongest beam among the at least one strongest beam.

[1201] As an example, the at least one predicted beam includes only one predicted beam, the at least one strongest beam includes only one strongest beam, and the first metric depends on whether the predicted beam is the strongest beam.

[1202] As a sub-implementation of the above embodiments, the first metric indicates whether the predicted beam is the strongest beam.

[1203] As one embodiment, the at least one predicted beam includes only one predicted beam, and the at least one strongest beam includes multiple strongest beams, wherein the first metric depends on whether the multiple strongest beams include the one predicted beam.

[1204] As a sub-implementation of the above embodiment, the first metric indicates whether the plurality of strongest beams include the predicted beam.

[1205] As one embodiment, the at least one predicted beam includes multiple predicted beams, and the at least one strongest beam includes only one strongest beam, wherein the first metric depends on whether the multiple predicted beams include the one strongest beam.

[1206] As a sub-example of the above embodiment, the first metric indicates whether the plurality of predicted beams include the strongest beam.

[1207] As an example, the output of the first inference for the first time interval also indicates at least one predicted RSRP, and the measurement on the M1 RS resources in the first time window is also used to determine at least one measured RSRP; the first metric depends on the at least one predicted RSRP and the at least one measured RSRP.

[1208] As an example, the at least one measured RSRP includes only one measured RSRP, and the at least one predicted RSRP includes only one predicted RSRP; the first metric indicates the difference between the one measured RSRP and the one predicted RSRP.

[1209] As an example, the at least one measured RSRP includes only one measured RSRP, and the at least one predicted RSRP includes multiple predicted RSRPs; the first metric indicates the difference between the one measured RSRP and the maximum predicted RSRP among the multiple predicted RSRPs.

[1210] As an example, the at least one measured RSRP includes multiple measured RSRPs, and the at least one predicted RSRP includes only one predicted RSRP; the first metric indicates the difference between the maximum measured RSRP among the multiple measured RSRPs and the one predicted RSRP.

[1211] As an example, the first metric indicates the difference between the maximum measured RSRP among the at least one measured RSRP and the maximum predicted RSRP among the at least one predicted RSRP.

[1212] Example 20

[1213] Example 20 illustrates a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application; as shown in the appendix. Figure 20 As shown in the figure. In Embodiment 20, the first processor sends a first dataset to the second processor and a second dataset to the third processor; the second processor generates a target first-class parameter set based on the first dataset, and sends the generated target first-class parameter set to the third processor; the third processor processes the second dataset using the target first-class parameter set to obtain a first-class output, and sends the first-class output to the fourth processor. (See Appendix...) Figure 20 In this configuration, the first type of feedback and the second type of feedback are optional; the second processor includes ML training functionality; and the third processor includes ML inference functionality.

[1214] As an example, the third processor executes the first inference.

[1215] As one embodiment, the fourth processor includes ML testing functionality.

[1216] As one example, the fourth processor includes performance monitoring / evaluation of the ML model.

[1217] As one embodiment, the fourth processor includes the inverse operation of the third processor.

[1218] As an example, the third processor sends a first type of feedback to the second processor. The first type of feedback is used to trigger the recalculation or update of the target first type of parameter set, that is, to trigger ML initial training or ML retraining.

[1219] As one embodiment, the first type of feedback includes the first reported information.

[1220] As one embodiment, the fourth processor sends a second type of feedback to the first processor, the second type of feedback being used to generate the first dataset or the second dataset, or the second type of feedback being used to trigger the sending of the first dataset or the second dataset.

[1221] As one example, the second type of feedback includes the first reported information.

[1222] As one embodiment, the first processor generates the first dataset and the second dataset based on the measurement of the reference signal.

[1223] As one embodiment, the third processor is located at the first node.

[1224] As one embodiment, the fourth processor is located at either the first node or the second node.

[1225] As an example, the second dataset includes measurements for RS.

[1226] As an example, the second dataset includes the reception of PDSCH.

[1227] As an example, the first dataset includes training data.

[1228] As an example, the first dataset is a training dataset.

[1229] As one embodiment, the second processor is used to train an ML model, and the trained model is described by the target first class of parameter sets.

[1230] As one embodiment, the second processor is located at the first node.

[1231] The above embodiments avoid passing the first dataset to the second node.

[1232] As one embodiment, the second processor is located in the core network.

[1233] The above embodiments support network-wide joint training, further optimizing system performance.

[1234] As an example, the second dataset includes inference data.

[1235] As an example, the second dataset is an inference dataset.

[1236] As an example, the input to an inference belongs to an inference dataset.

[1237] As an example, the third processor constructs a model based on the target first type of parameter group, and then inputs the second dataset into the constructed model to obtain the first type of output.

[1238] As an example, the third processor compares the real data with the first type of output, and the resulting error is used to generate the first type of feedback.

[1239] As an example, the third processor generates the first type of feedback through performance monitoring.

[1240] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the second processing opportunity will recalculate the target first type of parameter set.

[1241] As an example, the fourth processor compares the real data with the first type of output, and the resulting error is used to generate the second type of feedback.

[1242] As an example, the fourth processor generates the second type of feedback through performance monitoring.

[1243] As an example, the second type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the first processor sends the first dataset to trigger or assist the second processor in recalculating the target first type of parameter set.

[1244] As an example, when the error is too large or the update has not been performed for too long, the performance of the trained model is considered to be unsatisfactory.

[1245] As an example, the target first type of parameter group includes one or more of the following: convolution kernel size, number of convolution layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, or number of feature maps.

[1246] As an example, the target first type of parameter group includes one or more of the following: convolution kernel, pooling kernel, pooling function, activation function, parameters of pooling function, or parameters of activation function.

[1247] As one example, the ML includes AI.

[1248] As an example, the ML includes ML and AI.

[1249] Example 21

[1250] Example 21 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application; as attached. Figure 21 As shown. (Attached) Figure 21 This includes a first operation, a second operation, a third operation, a fourth operation, and a fifth operation. In Example 21, the first and second operations belong to a first stage, the third operation belongs to a second stage, the fourth operation belongs to a third stage, and the fifth operation belongs to a fourth stage. (See attached...) Figure 21 In the diagram, the lines with arrows indicate the sequence of processes.

[1251] As an example, the first operation includes ML training, the second operation includes ML testing, the third operation includes ML emulation, the fourth operation includes ML entity loading, and the fifth operation includes AI inference.

[1252] As an example, the first stage includes a training phase, the second stage includes an emulation phase, the third stage includes a deployment phase, and the fourth stage includes an inference phase.

[1253] As an example, the first stage includes ML model training.

[1254] As an example, the first stage includes ML model training and ML testing.

[1255] As an example, the ML model training includes initial training and re-training of one or a group of ML models.

[1256] As an example, the training of the ML model depends on training data.

[1257] As an example, the ML model training includes ML entity validation.

[1258] As an example, the ML entity verification is used to evaluate the performance of the ML entity.

[1259] As an example, the ML entity verification depends on verification data.

[1260] As an example, if the results of ML entity verification do not meet expectations, the ML model will be retrained.

[1261] As an example, the ML testing includes testing the validated ML entities to estimate the performance of the trained ML model.

[1262] As an example, if the ML test results meet expectations, the ML entity proceeds to the next stage; otherwise, the ML model will be retrained.

[1263] As an example, the ML test relies on test data.

[1264] As one embodiment, the second stage includes ML simulation, which performs inference of ML entities in a simulation environment.

[1265] As an example, the ML simulation estimates the performance of ML entity reasoning in a simulation environment before using ML entities.

[1266] As one embodiment, the second stage is optional.

[1267] As an example, the third stage includes ML entity loading, which is to obtain trained ML entities to obtain the desired AI inference capabilities.

[1268] As an example, the third stage is optional.

[1269] As an example, the third stage is no longer needed when the training and inference functions are co-located.

[1270] As an example, the fourth stage includes AI inference.

[1271] As an example, the AI ​​inference relies on inference data.

[1272] As an example, the input to an AI inference belongs to the inference dataset of the AI ​​inference model.

[1273] As one example, the ML includes AI.

[1274] As one example, the AI ​​includes ML.

[1275] Example 22

[1276] Example 22 illustrates a schematic diagram of AI function deployment according to one embodiment of this application; as shown in the appendix. Figure 22 As shown.

[1277] In Example 22, the AI ​​training function of the RAN (Radio Access Network) domain is located in the 3GPP RAN domain-specific management function, while the AI ​​inference function is located in the UE.

[1278] In Example 22, RAN domain-specific management functions provide AI training function management capabilities and AI inference function management capabilities.

[1279] Example 23

[1280] Example 23 illustrates a schematic diagram of AI function deployment according to an embodiment of this application; as shown in the appendix. Figure 23 As shown.

[1281] In Example 23, the AI ​​training function is located in the RAN domain-specific management function, while the AI ​​inference function is located locally in the UE.

[1282] In Example 23, the management capability of the AI ​​training function is provided by the RAN domain-specific management function, while the management capability of the AI ​​inference function is provided locally by the UE.

[1283] In the appendix Figure 23 In this context, MnF refers to Management Function.

[1284] Example 24

[1285] Example 24 illustrates a schematic diagram of AI function deployment according to one embodiment of this application; as attached. Figure 24 As shown.

[1286] In Example 24, both the AI ​​training function and the AI ​​inference function are located in the UE, wherein the UE provides the ability to train and infer.

[1287] In Example 24, RAN domain-specific management functions provide management capabilities for both AI training and AI inference functions.

[1288] Example 25

[1289] Example 25 illustrates a schematic diagram of AI function deployment according to one embodiment of this application; as attached. Figure 25 As shown.

[1290] In Example 25, both the AI ​​training function and the AI ​​inference function are located in the UE.

[1291] In Example 25, the management capabilities of both the AI ​​training function and the AI ​​inference function are provided locally by the UE.

[1292] In the appendix Figure 25 In this context, MnF refers to Management Function.

[1293] Example 26

[1294] Example 26 illustrates a structural block diagram of a processing apparatus for a first node according to an embodiment of this application; as shown in the appendix. Figure 26 As shown. In the appendix Figure 26 In the first node, the processing device 2600 includes a first processor 2601.

[1295] As one example, the first node is a user equipment.

[1296] As one example, the user equipment is a terminal.

[1297] As one example, the first node is a terminal.

[1298] As an example, the first node is a relay node device.

[1299] As one embodiment, the first processor 2601 includes at least one of the following in embodiment 4: {antenna 452, receiver 454, receiver processor 456, multi-antenna receiver processor 458, controller / processor 459, memory 460, data source 467}.

[1300] As one embodiment, the first processor 2601 includes at least one of the following in embodiment 4: {antenna 452, transmitter 454, transmitter processor 468, multi-antenna transmitter processor 457, controller / processor 459, memory 460, data source 467}.

[1301] The first processor 2601 receives a first configuration information block and a second configuration information block, wherein the first configuration information block is connected to the second configuration information block.

[1302] The first processor 2601 receives a first signaling, which triggers a first reporting information, which depends on the first configuration information block.

[1303] The first processor 2601, in response to the receipt of the first signaling, performs a first inference, the parameters of which depend on the second configuration information block.

[1304] The first processor 2601 sends the first reporting information, which includes a first metric.

[1305] In Example 26, the first metric depends on measurements on M1 RS resources and the output of the first inference, and the input of the first inference depends on measurements on M2 RS resources; the first configuration information block indicates the M1 RS resources, the second configuration information block indicates the M2 RS resources, and M1 and M2 are positive integers greater than 1.

[1306] As an example, the first configuration information block indicates whether the first reported information includes the output of the first inference.

[1307] As an example, the first reported information does not include the output of the first inference.

[1308] As one embodiment, the first signaling indicates a first trigger state, which indicates only the first configuration information block among the first configuration information block and the second configuration information block.

[1309] As an example, the first trigger state indicates whether the first reported information includes the output of the first inference.

[1310] As one embodiment, the first signaling indicates a second trigger state, and the second trigger state indicates the first configuration information block and the second configuration information block.

[1311] As one embodiment, it includes:

[1312] The first processor 2601, in response to the receipt of the first signaling, measures on the M2 RS resources.

[1313] As an example, the M1 RS resources and the M2 RS resources are associated with the same association identifier.

[1314] As an example, the first metric depends on the measurement on the M1 RS resources in the first time window and the output of the first inference for the first time interval, and the first metric is obtained under the condition that the difference between the first time window and the first time interval is less than or not greater than a first threshold.

[1315] Example 27

[1316] Example 27 illustrates a structural block diagram of a processing apparatus for a second node according to an embodiment of this application; as shown in the appendix. Figure 27 As shown. In the appendix Figure 27 In the second node, the processing device 2700 includes a second processor 2701.

[1317] In one embodiment, the second node is a base station.

[1318] In one embodiment, the second node is a base station device.

[1319] In one embodiment, the second node is a user equipment.

[1320] As one embodiment, the second node is a relay node device.

[1321] As one embodiment, the second node includes the sustaining base station of the serving cell of the first node.

[1322] As one embodiment, the second node includes an OTT (Over-The-Top) server.

[1323] As an example, the second node provides OAM (Operation Administration and Maintenance).

[1324] As one embodiment, the second node includes a NAS (Network Access Server).

[1325] As one embodiment, the second node includes a NAS device.

[1326] As one example, the second node provides network access services.

[1327] As one embodiment, the second node includes core network equipment.

[1328] As one embodiment, the second node includes base station equipment and core network equipment.

[1329] As one embodiment, the second node includes a base station device and a NAS device.

[1330] As one embodiment, the second node includes an MDA function producer.

[1331] As one embodiment, the second node includes an NWDAF producer.

[1332] As one example, the second node includes an MDAS producer.

[1333] As one embodiment, the second node includes an MnS producer.

[1334] As one embodiment, the second processor 2701 includes at least one of the following in embodiment 4: {antenna 420, transmitter 418, transmitter processor 416, multi-antenna transmitter processor 471, controller / processor 475, memory 476}.

[1335] As one embodiment, the second processor 2701 includes at least one of the following in embodiment 4: {antenna 420, receiver 418, receiver processor 470, multi-antenna receiver processor 472, controller / processor 475, memory 476}.

[1336] The second processor 2701 sends a first configuration information block and a second configuration information block, wherein the first configuration information block is connected to the second configuration information block.

[1337] The second processor 2701 sends a first signaling, which triggers a first reporting information, which depends on the first configuration information block.

[1338] The second processor 2701 receives the first reported information, which includes a first metric.

[1339] In embodiment 27, the first signaling triggers the sender of the first reported information to perform a first inference, the parameters of the first inference depending on the second configuration information block; the first metric depends on the measurement on M1 RS resources and the output of the first inference, the input of the first inference depends on the measurement on M2 RS resources; the first configuration information block indicates the M1 RS resources, the second configuration information block indicates the M2 RS resources, and M1 and M2 are positive integers greater than 1.

[1340] As an example, the first configuration information block indicates whether the first reported information includes the output of the first inference.

[1341] As an example, the first reported information does not include the output of the first inference.

[1342] As one embodiment, the first signaling indicates a first trigger state, which indicates only the first configuration information block among the first configuration information block and the second configuration information block.

[1343] As an example, the first trigger state indicates whether the first reported information includes the output of the first inference.

[1344] As one embodiment, the first signaling indicates a second trigger state, and the second trigger state indicates the first configuration information block and the second configuration information block.

[1345] As one embodiment, it includes:

[1346] The first signaling triggers the sender of the first reported information to measure on the M2 RS resources.

[1347] As an example, the M1 RS resources and the M2 RS resources are associated with the same association identifier.

[1348] As an example, the first metric depends on the measurement on the M1 RS resources in the first time window and the output of the first inference for the first time interval, and the first metric is obtained under the condition that the difference between the first time window and the first time interval is less than or not greater than a first threshold.

[1349] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, hard disk, or optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Accordingly, each module unit in the above embodiments can be implemented in hardware or in the form of software functional modules. This application is not limited to any specific combination of software and hardware. The user equipment, terminal, and UE in this application include, but are not limited to, drones, communication modules on drones, remote-controlled aircraft, aircraft, small aircraft, mobile phones, tablets, laptops, vehicle-mounted communication devices, wireless sensors, internet cards, IoT terminals, RFID terminals, NB-IoT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet cards, vehicle-mounted communication devices, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base stations or system equipment in this application include, but are not limited to, macrocell base stations, microcell base stations, home base stations, relay base stations, gNB (NR Node B), TRP (Transmitter Receiver Point), GNSS, relay satellites, satellite base stations, airborne base stations, RSU (Road Side Unit), drones, and test equipment (such as transceivers or signaling testers that simulate some functions of a base station) and other wireless communication equipment.

[1350] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any changes and modifications made based on the embodiments described in the specification, if they achieve similar partial or complete technical effects, should be considered obvious and fall within the scope of protection of this invention.

Claims

1. A method used in a first node of wireless communication, characterized in that, include: Receive a first configuration information block and a second configuration information block, wherein the first configuration information block is connected to the second configuration information block; Receive a first signaling message, the first signaling message triggers a first reporting message, the first reporting message depends on the first configuration information block; In response to the receipt of the first signaling, a first inference is performed, the parameters of which depend on the second configuration information block; Send the first reported information, which includes a first metric; Wherein, the first metric depends on the measurement on M1 RS resources and the output of the first inference, and the input of the first inference depends on the measurement on M2 RS resources; the first configuration information block indicates the M1 RS resources, the second configuration information block indicates the M2 RS resources, and M1 and M2 are positive integers greater than 1.

2. The method according to claim 1, characterized in that, The first configuration information block indicates whether the first reported information includes the output of the first inference.

3. The method according to claim 1, characterized in that, The first reported information does not include the output of the first inference.

4. The method according to any one of claims 1 to 3, characterized in that, The first signaling indicates a first trigger state, which indicates only the first configuration information block among the first configuration information block and the second configuration information block.

5. The method according to claim 4, characterized in that, The first trigger state indicates whether the first reported information includes the output of the first inference.

6. The method according to claim 3, characterized in that, The first signaling indicates the second trigger state, and the second trigger state indicates the first configuration information block and the second configuration information block.

7. The method according to any one of claims 1 to 6, characterized in that, include: As a response to the reception of the first signaling, measurements are taken on the M2 RS resources.

8. The method according to any one of claims 1 to 7, characterized in that, The M1 RS resources and the M2 RS resources are associated with the same association identifier.

9. The method according to any one of claims 1 to 8, characterized in that, The first metric depends on the measurements on the M1 RS resources in the first time window and the output of the first inference for the first time interval, and the first metric is obtained under the condition that the difference between the first time window and the first time interval is less than or not greater than a first threshold.

10. A terminal, characterized in that, The terminal includes: One or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the terminal to perform the method as described in any one of claims 1-9.

11. A method used in a second node for wireless communication, characterized in that, include: Send a first configuration information block and a second configuration information block, wherein the first configuration information block is connected to the second configuration information block; Send a first signaling message, which triggers a first reporting message, the first reporting message depending on the first configuration information block; Receive the first reported information, which includes a first metric; Wherein, the first signaling triggers the sender of the first reported information to execute the first inference, the parameters of the first inference depend on the second configuration information block; the first metric depends on the measurement on M1 RS resources and the output of the first inference, the input of the first inference depends on the measurement on M2 RS resources; the first configuration information block indicates the M1 RS resources, the second configuration information block indicates the M2 RS resources, and M1 and M2 are positive integers greater than 1.

12. The method according to claim 11, characterized in that, The first configuration information block indicates whether the first reported information includes the output of the first inference.

13. The method according to claim 11, characterized in that, The first reported information does not include the output of the first inference.

14. The method according to any one of claims 11 to 13, characterized in that, The first signaling indicates a first trigger state, which indicates only the first configuration information block among the first configuration information block and the second configuration information block.

15. The method according to claim 14, characterized in that, The first trigger state indicates whether the first reported information includes the output of the first inference.

16. The method according to claim 13, characterized in that, The first signaling indicates the second trigger state, and the second trigger state indicates the first configuration information block and the second configuration information block.

17. The method according to any one of claims 11 to 16, characterized in that, include: The first signaling triggers the sender of the first reported information to measure on the M2 RS resources.

18. The method according to any one of claims 11 to 17, characterized in that, The M1 RS resources and the M2 RS resources are associated with the same association identifier.

19. The method according to any one of claims 11 to 18, characterized in that, The first metric depends on the measurements on the M1 RS resources in the first time window and the output of the first inference for the first time interval, and the first metric is obtained under the condition that the difference between the first time window and the first time interval is less than or not greater than a first threshold.

20. A base station, characterized in that, The base station includes: One or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the base station to perform the method as described in any one of claims 11-19.

Images