Applicable functionality reporting method and apparatus used in node for wireless communication

Abstract

Disclosed in the present application are an applicable functionality reporting method and apparatus used in a node for wireless communication. The method comprises: a first node sending a first information block, wherein the first information block is used for indicating N1 applicable functionalities of the first node from among N functionalities, N being a positive integer greater than 1, and N1 being a positive integer not greater than N; and storage resources in the first node that are required by the N1 applicable functionalities and any one of the N functionalities other than the N1 applicable functionalities are greater than available storage resources in the first node.

Description

A method and apparatus for reporting applicable functions in nodes used in wireless communication.

[0001] Technical Field This application relates to transmission methods and apparatus in wireless communication systems, and more particularly to schemes and apparatus for applicable function reporting in wireless communication systems. Background Technology

[0002] In traditional wireless communication, the UE (User Equipment) calculates CSI (channel state information) by measuring downlink reference signals. The CSI 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).

[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 R (release) 18, research on AI (Artificial Intelligence) / ML (Machine Learning) technologies was initiated to explore their impact on system performance and design. Compared to traditional processing methods, AI / ML offers advantages such as training-based and deployment-required features. Furthermore, AI / ML is also a key candidate technology for future 6G communications. Summary of the Invention

[0004] The applicant's research revealed that transceivers typically need a consistent understanding of applicable functionality; therefore, determining the applicable functionality of a terminal is a key issue that needs to be addressed. To address this issue, this application discloses a solution. It should be noted that while many embodiments of this application are geared towards AI / ML, this application is also applicable to other solutions, such as traditional channel information reporting schemes. Furthermore, adopting a unified solution across different scenarios (including but not limited to AI / ML-based schemes and traditional information reporting schemes) helps reduce hardware complexity and cost. Where there is no conflict, the embodiments and features in the embodiments of the first node of this application can be applied to the second node, and vice versa. Where there is no conflict, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0005] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS38 series.

[0006] As an example, the interpretation of the terms in this application is based on the definitions in the 3GPP specification protocol TS28 series.

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

[0008] Send the first information block;

[0009] The first information block is used to indicate N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node.

[0010] As an example, the problem this application aims to solve includes: how to determine the applicable functions.

[0011] As an example, in the above method, the first node reports its N1 applicable functions, and the determination of these N1 applicable functions is related to the available storage resources of the first node.

[0012] As an example, the advantages of the above method include ensuring that the transmitting and receiving ends have a consistent understanding of the applicable functions.

[0013] As an example, the advantages of the above method include: better support for various functions, application scenarios or terminals.

[0014] As an example, the advantages of the above method include: high flexibility and strong adaptability.

[0015] As an example, the advantages of the above method include: better adaptability to various terminal capabilities, such as storage resources.

[0016] As one example, the first node is a user equipment.

[0017] As an example, the first node is a relay node.

[0018] As one example, the first node is a terminal.

[0019] As one example, the terminal is a user equipment.

[0020] According to one aspect of this application, the first information block further indicates the N1.

[0021] According to one aspect of this application, the first information block further indicates the maximum number of applicable functions that are activated.

[0022] According to one aspect of this application, it is characterized by comprising:

[0023] Perform inference;

[0024] Wherein, at least one of the N1 applicable functions is used to determine the parameters(s) of the inference.

[0025] As an example, the advantages of the above method include: the inference parameters depend on the applicable functions of the first node, ensuring that appropriate inference parameters are used for inference and guaranteeing inference performance.

[0026] According to one aspect of this application, it is characterized by comprising:

[0027] Receive a third information block; the transmission of the third information block precedes the execution inference of the first node;

[0028] The third information block is used to activate at least one of the N1 applicable functions, or the third information block is used to configure the parameters of the inference.

[0029] As an example, in the above method, the third information block is used to activate at least one of the N1 applicable functions, and the activated applicable function is used to determine the parameters of the inference.

[0030] As an example, in the above method, the inference parameters configured in the third information block depend on at least one of the N1 applicable functions.

[0031] As an example, in the above method, the target recipient of the first information block activates applicable functions or configures the inference parameters of the first node. The advantages include: allowing the target recipient of the first information block to control the applicable functions that can be activated or the inference parameters of the first node.

[0032] According to one aspect of this application, each of the N functions corresponds to a first type identifier; the storage resources required by two functions corresponding to different first type identifiers in the N functions in the first node are orthogonal.

[0033] According to one aspect of this application, two functions of the N functions that correspond to the same first type identifier share the same storage resources in the first node.

[0034] As an example, in the above method, the first type of identifier is associated with the storage resources in the first node.

[0035] As an example, the advantages of the above method include: ensuring consistent understanding of storage resource usage between the sending and receiving ends, simplifying the design, providing high flexibility and adaptability.

[0036] According to one aspect of this application, the first information block is used to indicate N0 applicable functions of the first node from the N functions, the N0 applicable functions including the N1 applicable functions, where N1 is less than N, and N0 is a positive integer greater than N1 and not greater than N; the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node.

[0037] According to one aspect of this application, it is characterized by comprising:

[0038] Receive the second information block.

[0039] As one embodiment, the second information block instructs the first node to provide the applicable functions of the first node, or the second information block instructs the first node to report UAI (UE Assistance Information).

[0040] As one embodiment, the second information block indicates the N functions; wherein,

[0041] The N functions each include N CSI (channel state information) reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from the N CSI reporting configurations.

[0042] or,

[0043] The N functions each include N inference parameter groups, and each of the N inference parameter groups includes at least one inference parameter. The N1 applicable functions include N1 inference parameter groups from the N inference parameter groups that are applicable to the first node.

[0044] According to one aspect of this application, it is characterized by comprising:

[0045] Receive the first message;

[0046] In response to receiving the first message, a second message is sent;

[0047] The second message includes the supported functionalities of the first node; the transmission of the second message precedes the transmission of the first information block.

[0048] This application discloses a method used in a second node for wireless communication, characterized by comprising:

[0049] Receive the first information block;

[0050] Wherein, the first information block is used to indicate N1 applicable functions of the sender of the first information block from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the sender of the first information block from the N1 applicable functions and any function other than the N1 applicable functions from the N functions are greater than the available storage resources in the sender of the first information block.

[0051] According to one aspect of this application, the first information block further indicates the N1.

[0052] According to one aspect of this application, the first information block further indicates the maximum number of applicable functions that are activated.

[0053] According to one aspect of this application, the sender of the first information block performs inference; wherein at least one of the N1 applicable functions is used to determine the parameters of the inference.

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

[0055] Send a third information block; the transmission of the third information block precedes the execution reasoning of the sender of the first information block;

[0056] The third information block is used to activate at least one of the N1 applicable functions, or the third information block is used to configure the parameters of the inference.

[0057] According to one aspect of this application, each of the N functions corresponds to a first type identifier; the storage resources required by two functions corresponding to different first type identifiers in the sender of the first information block are orthogonal.

[0058] According to one aspect of this application, two functions of the N functions that correspond to the same first type identifier share the same storage resources in the sender of the first information block.

[0059] According to one aspect of this application, the first information block is used to indicate N0 applicable functions of the sender of the first information block from the N functions, the N0 applicable functions including the N1 applicable functions, where N1 is less than N, and N0 is a positive integer greater than N1 and not greater than N; the storage resources in the sender of the first information block required by the N0 applicable functions are greater than the available storage resources in the sender of the first information block.

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

[0061] Send the second information block.

[0062] According to one aspect of this application, the second information block instructs the sender of the first information block to provide the applicable functions of the sender of the first information block, or the second information block instructs the sender of the first information block to perform UAI reporting.

[0063] According to one aspect of this application, the second information block indicates the N functions; wherein,

[0064] The N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the sender of the first information block from among the N CSI reporting configurations;

[0065] or,

[0066] The N functions each include N inference parameter groups, and each of the N inference parameter groups includes at least one inference parameter. The N1 applicable functions include N1 inference parameter groups applicable to the sender of the first information block from the N inference parameter groups.

[0067] According to one aspect of this application, it is characterized by comprising:

[0068] Send the first message;

[0069] Receive the second message;

[0070] In this process, the sender of the first information block receives the first message in response to it, and then sends the second message; the second message includes functions supported by the sender of the first information block; the transmission of the second message precedes the transmission of the first information block.

[0071] This application discloses a first node used for wireless communication, characterized in that it comprises:

[0072] The first processor sends the first information block;

[0073] The first information block is used to indicate N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node.

[0074] This application discloses a second node used for wireless communication, characterized in that it comprises:

[0075] The second processor receives the first information block;

[0076] Wherein, the first information block is used to indicate N1 applicable functions of the sender of the first information block from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the sender of the first information block from the N1 applicable functions and any function other than the N1 applicable functions from the N functions are greater than the available storage resources in the sender of the first information block.

[0077] As an example, compared with conventional solutions, this application has the following advantages:

[0078] To better adapt to various different functions, application scenarios, or terminals;

[0079] To better adapt to the capabilities of various terminals, such as storage resources;

[0080] High flexibility;

[0081] Highly adaptable;

[0082] This ensures that the transmitting and receiving ends have a consistent understanding of the applicable functions;

[0083] This ensures that appropriate inference parameters are used for inference, thus guaranteeing inference performance;

[0084] This ensures that the transmitting and receiving ends have a consistent understanding of the selection of applicable functions;

[0085] The design has been simplified;

[0086] Enhanced reliability and robustness;

[0087] Enhanced overall system performance. Attached Figure Description

[0088] 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:

[0089] Figure 1 shows a flowchart of a first information block according to an embodiment of this application;

[0090] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0091] Figure 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application;

[0092] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of this application;

[0093] Figure 5 illustrates the transmission between a first node and a second node according to an embodiment of this application;

[0094] Figure 6 shows a schematic diagram of a first information block according to an embodiment of this application;

[0095] Figure 7 shows a schematic diagram of a first information block according to another embodiment of this application;

[0096] Figure 8 shows a schematic diagram of a first information block according to another embodiment of this application;

[0097] Figure 9 illustrates a schematic diagram of the relationship between N1 applicable functions and reasoning according to an embodiment of this application;

[0098] Figure 10 illustrates a schematic diagram of the relationship between the storage resources required for two functions according to an embodiment of this application;

[0099] Figure 11 illustrates a schematic diagram of the relationship between the storage resources required for two functions according to another embodiment of this application;

[0100] Figure 12 illustrates a schematic diagram of the relationship between reasoning and the first type of identifier according to an embodiment of this application;

[0101] Figures 13A-13B respectively show schematic diagrams of the first node deploying the first inference according to an embodiment of this application;

[0102] Figure 14 illustrates a schematic diagram of the deployment of AI / ML functions in a RAN (Radio Access Network) domain according to an embodiment of this application;

[0103] Figure 15 shows a schematic diagram of the AI / ML function deployment of a UE according to an embodiment of this application;

[0104] Figure 16 shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application;

[0105] Figure 17 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0106] Figure 18 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application. Detailed Implementation

[0107] The technical solutions of this application will be further described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Considering performance, flexibility, complexity, overhead, and compatibility, those skilled in the art are motivated to flexibly combine the embodiments in different drawings without conflict, such as, but not limited to, the embodiments in Figure 1 and the embodiments in Figures 5-18, the embodiments in Figure 5 and the embodiments in Figures 6-18, etc.

[0108] Example 1

[0109] Example 1 illustrates a flowchart of a first information block according to an embodiment of this application, as shown in Figure 1. In Figure 1, each block represents a step. In particular, the order of the steps in the blocks does not represent a specific temporal sequence between the steps.

[0110] In Embodiment 1, the first node sends a first information block in step 101; wherein, the first information block is used to indicate N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node.

[0111] As one embodiment, the first information block is carried by higher-layer signaling.

[0112] As an example, the first information block is carried by an RRC message.

[0113] As an example, the first information block belongs to UAI (UE Assistance Information).

[0114] As an example, the first information block belongs to the UEAssistanceInformation message.

[0115] As one example, the first information block includes UAI.

[0116] As one embodiment, the first information block includes a UEAssistanceInformation message.

[0117] As an example, the UAI report is the reporting of the UEAssistanceInformation message.

[0118] As an example, the first information block includes a MAC CE.

[0119] As one embodiment, the first information block includes physical layer information.

[0120] As one embodiment, the first information block includes uplink control information.

[0121] As one example, the first information block is transmitted over a physical channel.

[0122] As an example, the first information block is transmitted on PUSCH (Physical Uplink Shared Channel).

[0123] As an example, the first information block is transmitted on PUCCH (Physical Uplink Control Channel).

[0124] As an example, the first information block indicates the index or identifier of the N1 applicable functions.

[0125] As an example, the first information block indicates the index of the N1 applicable functions among the N functions.

[0126] As an example, all N functions are related to reasoning.

[0127] As an example, any one of the N functions is a reasoning function.

[0128] As an example, any one of the N functions is a function for reasoning.

[0129] As an example, the N functions are for inference configuration.

[0130] As an example, the N functions are configured for inference configuration.

[0131] As an example, the N functions are configured by the serving cell of the first node.

[0132] As an example, the N functions are configured by the serving base station of the first node.

[0133] As an example, the N functions are configured by the target recipient of the first information block.

[0134] As an example, the second information block in this application configures or indicates the N functions.

[0135] As an example, the N functions are configured by RRC signaling.

[0136] As an example, the N functions are determined by the first node itself.

[0137] As an example, the N1 applicable functions are all the functions among the N functions that are applicable to the first node.

[0138] As an example, the N0 applicable functions are all the functions applicable to the first node among the N functions, and the N1 applicable functions include some of the applicable functions among the N0 applicable functions, where N0 is a positive integer greater than N1 and not greater than N.

[0139] As an example, the N1 applicable functions are only a portion of all the functions applicable to the first node among the N functions.

[0140] As an example, the N functions each include N CSI reporting configurations, and the N1 applicable functions each include N1 CSI reporting configurations applicable to the first node from the N CSI reporting configurations.

[0141] As an example, the N functions each include N CSI reporting configurations, and the N1 applicable functions each include N1 CSI reporting configurations applicable to the first node from the N CSI reporting configurations. The first information block is used to indicate the N1 CSI reporting configurations from the N CSI reporting configurations.

[0142] As a sub-implementation of the above embodiment, the first information block is used to indicate the N1 CSI reporting configurations from the N CSI reporting configurations, including: the first information block indicates the identifier of each of the N1 CSI reporting configurations.

[0143] As a sub-implementation of the above embodiments, the first information block is used to indicate the N1 CSI reporting configurations from the N CSI reporting configurations, including: the first information block indicates the index of the N1 CSI reporting configurations in the N CSI reporting configurations.

[0144] As an example, the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups. The first information block is used to indicate the N1 inference parameter groups from the N inference parameter groups.

[0145] As a sub-implementation of the above embodiments, the first information block being used to indicate the N1 inference parameter groups from the N inference parameter groups includes: the first information block indicating the identifier of each of the N1 inference parameter groups.

[0146] As a sub-implementation of the above embodiments, the first information block being used to indicate the N1 inference parameter groups from the N inference parameter groups includes: the first information block indicating the index of the N1 inference parameter groups in the N inference parameter groups.

[0147] As an example, the first information block indicates a first bitmap, which includes N bits, each of which corresponds to one of the N functions; the values ​​of the N bits indicate whether each of the N functions is an applicable function, and the values ​​of N1 bits out of the N bits indicate that N1 of the N functions are applicable to the first node, and the N1 functions are the N1 applicable functions.

[0148] As a sub-implementation of the above embodiment, a value of 1 for any of the N bits indicates that the corresponding function is an applicable function; a value of 0 for any of the N bits indicates that the corresponding function is not an applicable function.

[0149] As a sub-implementation of the above embodiment, a value of 0 for any of the N bits indicates that the corresponding function is an applicable function; a value of 1 for any of the N bits indicates that the corresponding function is not an applicable function.

[0150] As one embodiment, the first information block is used to indicate N1 applicable functions of the first node from N functions, including: the first information block indicates at least one function that is not applicable to the first node, and the N1 applicable functions of the first node include N1 functions other than the at least one function that is not applicable to the first node.

[0151] As one embodiment, the first information block being used to indicate N1 applicable functions of the first node from N functions includes: the first information block being used to indicate only N1 applicable functions of the first node from N functions.

[0152] As one embodiment, the first information block is used to indicate N1 applicable functions of the first node from N functions, including: the first information block is used to indicate N0 applicable functions of the first node from the N functions, the N0 applicable functions include the N1 applicable functions, where N1 is less than N, and N0 is a positive integer greater than N1 and not greater than N; the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node.

[0153] As one embodiment, the first information block is used to indicate N0 applicable functions of the first node from the N functions, including: the first information block indicates at least one function that is not applicable to the first node, and the N0 applicable functions of the first node include all functions other than the at least one function that is not applicable to the first node.

[0154] As an example, any one of the N functions corresponds to a first-class identifier.

[0155] As an example, any one of the N functions corresponds to a first type of identifier, including: any one of the N functions includes a first type of identifier.

[0156] As an example, the fact that any one of the N functions corresponds to a first-type identifier includes: any one of the N functions is configured with a first-type identifier.

[0157] As an example, the fact that any one of the N functions corresponds to a first type identifier includes: the first node reports N first type identifiers for each of the N functions, and the N functions correspond to the N first type identifiers respectively.

[0158] As an example, the correspondence between any one of the N functions and a first-type identifier includes: any one of the N functions is associated with a first-type identifier.

[0159] As an example, the fact that any one of the N functions corresponds to a first-type identifier includes: any one of the N functions is for inference configuration corresponding to a first-type identifier.

[0160] As an example, the configuration of any one of the N functions corresponding to a first-type identifier includes: the configuration of any one of the N functions is for inference configuration corresponding to a first-type identifier.

[0161] As an example, the fact that any one of the N functions corresponds to a first-type identifier includes: any one of the N functions corresponds to a reasoning associated with a first-type identifier.

[0162] As an example, the first type of identifier corresponding to any of the N functions includes: the N functions each include N CSI reporting configurations, and the N CSI reporting configurations each include the first type of identifier corresponding to the N functions.

[0163] As an example, among the N functions, there are two functions that correspond to the same first type of identifier.

[0164] As an example, among the N functions, there are two functions that correspond to different first-type identifiers.

[0165] As an example, any two of the N functions correspond to different first-type identifiers.

[0166] As an example, the first type of identifier is an associated identifier (associated ID).

[0167] As an example, the first type of identifier is an identifier associated with an AI model.

[0168] As an example, the first type of identifier is an identifier associated with reasoning.

[0169] As an example, the first type of identifier is a non-negative integer.

[0170] As an example, the first type of identifier is a string.

[0171] As an example, the first type of identifier is used to identify at least one of the storage resources or processing resources.

[0172] As an example, the first type of identifier is used to identify a function.

[0173] As an example, the N functions are N CSI reporting configurations, and the first type of identifier is different from the identifier of the CSI reporting configuration.

[0174] As an example, the first type of identifier is used to identify AI models.

[0175] As an example, the first type of identifier is used by the first node to identify an AI model.

[0176] As an example, the first type of identifier is used by the first node to determine the AI ​​model used for inference.

[0177] As an example, the first type of identifier is used to identify AI entities.

[0178] As an example, the first type of identifier is used to identify AI functions.

[0179] As an example, the advantages of the above method include that identifying an AI model / entity / function through the first type of identifier simplifies the design and unifies the understanding of different AI entities or functions across multiple nodes.

[0180] As an example, the first type of identifier is used to identify or indicate a beam set.

[0181] As an example, the first type of identifier is used to identify or indicate the antenna configuration of a base station.

[0182] As an example, the first type of identifier is used to identify or indicate a set of RS resources for measurement.

[0183] As an example, the first type of identifier is used to identify or indicate a set of resources for prediction.

[0184] As an example, the first type of identifier is used to identify or indicate a set of RS resources for prediction.

[0185] As an example, the first type of identifier is used to identify or indicate a set of RS (reference signal) resources.

[0186] As an example, the first type of identifier is used to identify or indicate a set of RS resources, the set of RS resources including at least one RS resource, and the measurement of the set of RS resources is used to obtain a training dataset.

[0187] As an example, the first type of identifier is used to identify or indicate a training dataset.

[0188] As an example, the first type of identifier is used to identify or indicate the training of an AI model.

[0189] As an example, the benefits of the above method include establishing consensus among different AI functions by identifying an AI training or AI training dataset to recognize the inferences generated by that AI training or AI training dataset, further simplifying the design.

[0190] As an example, the determination of the N1 applicable functions depends on at least the available storage resources of the first node.

[0191] As an example, the determination of the N1 applicable functions depends on at least the available storage resources of the first node, and the battery or available power.

[0192] As an example, the determination of the N1 applicable functions depends on at least the available storage resources of the first node and whether the AI ​​model for the function has been deployed or trained.

[0193] As an example, the determination of the N1 applicable functions depends on at least the available storage resources, battery or available power of the first node, and whether the AI ​​model for the function has been deployed or trained.

[0194] As an example, whether one of the N functions is applicable to the first node depends on whether the first node has sufficient available storage resources; the applicable function among the N functions must at least satisfy the following: the required storage resources are not greater than the available storage resources of the first node.

[0195] As an example, whether one of the N functions is applicable to the first node depends on at least whether the first node has sufficient available storage resources and battery or available power; the applicable function among the N functions must at least satisfy the following: the required storage resources are not greater than the available storage resources of the first node, and the required power is not greater than the battery or available power of the first node.

[0196] As an example, whether one of the N functions is applicable to the first node depends at least on whether the first node has sufficient available storage resources and whether the AI ​​model of the function has been deployed or trained. An applicable function among the N functions must at least satisfy the following conditions: the required storage resources are not greater than the available storage resources of the first node, and its AI model has been deployed or trained.

[0197] As an example, whether one of the N functions is applicable to the first node depends on at least whether the first node has sufficient available storage resources, battery or available power, and whether the AI ​​model of the function has been deployed or trained. An applicable function among the N functions must at least satisfy the following conditions: the required storage resources are no greater than the available storage resources of the first node, the required power is no greater than the battery or available power of the first node, and its AI model has been deployed or trained.

[0198] As an example, the storage resources required for one of the N functions are used to store some or all of the parameters used in the inference corresponding to that function.

[0199] As an example, the storage resources required for one of the N functions are used to store some or all of the parameters of the AI ​​model corresponding to that function.

[0200] As an example, the storage resources required for one of the N functions are used to store at least one of the following: some or all parameters of the AI ​​model corresponding to that function, some or all intermediate inference results, or some or all inference outputs.

[0201] As an example, the storage resources required for one of the N functions are used to store 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 of the AI ​​model corresponding to that function.

[0202] As an example, the storage resources required for one of the N functions are used to store one or more of the following: convolution kernel, pooling kernel, pooling function, activation function, pooling function parameters, or activation function parameters of the AI ​​model corresponding to that function.

[0203] As an example, the storage resources required for one of the N functions are used to store some or all of the parameters in the target first type of parameter group in Embodiment 16 of this application.

[0204] As an example, one of the N functions is used to determine the parameters of the inference corresponding to that function.

[0205] As an example, any one of the N functions corresponds to a first type of identifier, which is an identifier associated with reasoning, and the reasoning corresponding to one of the N functions is the reasoning associated with the first type of identifier corresponding to that function.

[0206] As an example, any one of the N functions corresponds to a first type of identifier, which is an identifier associated with an AI model. The AI ​​model corresponding to one of the N functions is the AI ​​model associated with the first type of identifier corresponding to that function.

[0207] As an example, the available storage resources in the first node refer to the unoccupied storage resources in the first node.

[0208] As an example, the unoccupied storage resources in the first node refer to the free storage resources in the first node.

[0209] As an example, the unoccupied storage resources in the first node refer to the storage resources in the first node that are not used for storage.

[0210] As an example, the occupied storage resources in the first node refer to the non-idle storage resources in the first node.

[0211] As an example, the occupied storage resources in the first node refer to the storage resources in the first node that have been used for storage.

[0212] As an example, the available storage resources in the first node refer to at least a portion of the unoccupied storage resources in the first node.

[0213] As an example, the available storage resources in the first node refer to the storage resources in the first node that can be used for the functions among the N functions.

[0214] As an example, the N1 applicable functions must at least satisfy the following: the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node.

[0215] As an example, the N1 applicable functions shall at least satisfy the following: the storage resources required by the N1 applicable functions in the first node are not greater than the available storage resources in the first node, and the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions among the N functions are greater than the available storage resources in the first node.

[0216] As an example, the N1 applicable functions shall at least satisfy the following: the storage resources required by the N1 applicable functions in the first node are not greater than the available storage resources in the first node; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions among the N functions are greater than the available storage resources in the first node; and the power required by the N1 applicable functions is not greater than the battery or available power of the first node.

[0217] As an example, the N1 applicable functions must at least satisfy the following: the storage resources required by the N1 applicable functions in the first node are not greater than the available storage resources in the first node; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions among the N functions are greater than the available storage resources in the first node; and the AI ​​models of the N1 applicable functions have all been deployed or trained.

[0218] As an example, the N1 applicable functions must at least satisfy the following: the storage resources required by the N1 applicable functions in the first node are not greater than the available storage resources in the first node; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions among the N functions are greater than the available storage resources in the first node; the power required by the N1 applicable functions is not greater than the battery or available power of the first node; and the AI ​​models of the N1 applicable functions have all been deployed or trained.

[0219] Example 2

[0220] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2.

[0221] Figure 2 illustrates network architecture 200. Network architecture 200 is a 5G NR (New Radio) / LTE (Long-Term Evolution) / LTE-A (Long-Term Evolution Advanced) system, or a 5G+ network architecture, or a 6G network architecture, or a network architecture adopted in future evolutions by 3GPP; network architecture 200 may be referred to as 5GS (5G System) / EPS (Evolved Packet System), or 6GS (6G System); network architecture 200 includes at least one of UE (User Equipment) 201, RAN (Radio Access Network) 202, core network 210, HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and Internet service 230. The network architecture 200 can interconnect with other access networks, but these entities / interfaces are not shown for simplicity. As shown, the network architecture 200 provides packet-switched services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The RAN includes node 203. The RAN may also include other nodes 204. Node 203 provides user and control plane protocol termination toward UE 201. Node 203 may be connected to other nodes 204 via an Xn interface (e.g., backhaul) / X2 interface. Node 203 may also be referred to as a base station, base transceiver station, radio base station, radio transceiver, transceiver function, basic service set (BSS), extended service set (ESS), TRP (transmitter-receiver node), or some other suitable term. The core network 210 is a 5GC (5G Core Network) / EPC (Evolved Packet Core), or the core network 210 is a 6GC; node 203 provides UE 201 with an access point to the core network 210.Examples of UE201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, non-terrestrial base station communications, satellite mobile communications, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband IoT devices, machine-type communication devices, land vehicles, automobiles, wearable devices, or any other similar functional devices. Those skilled in the art may also refer to UE201 as a mobile station, subscriber station, mobile unit, subscriber unit, radio unit, remote unit, mobile device, radio device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. Node 203 is connected to the core network 210 via an S1 / NG interface. The core network 210 includes an MME (Mobility Management Entity) / AMF (Authentication Management Field) / SMF (Session Management Function) 211, other MMEs / AMFs / SMFs 214, an S-GW (Service Gateway) / UPF (User Plane Function) 212, and a P-GW (Packet Data Network Gateway) / UPF 213. The MME / AMF / SMF 211 is the control node that handles signaling between the UE 201 and the core network 210. Generally, the MME / AMF / SMF 211 provides bearer and connection management. All user IP (Internet Protocol) packets are transmitted through the S-GW / UPF 212, which is itself connected to the P-GW / UPF 213. The P-GW provides UE IP address allocation and other functions. The P-GW / UPF 213 is connected to the Internet service 230. Internet services 230 include operator-compliant Internet protocol services, which may specifically include Internet, intranet, IMS (IP Multimedia Subsystem), and packet switching services.

[0222] As an example, the first node includes the UE201.

[0223] As one embodiment, the second node includes the node 203.

[0224] As one embodiment, the second node includes the core network 210.

[0225] As one embodiment, the second node includes the node 203 and the core network 210.

[0226] As an example, the wireless link between the UE201 and the node203 includes a cellular link.

[0227] As an example, the storage resources described in this application are in the UE201.

[0228] As an example, the first message is generated in node 203.

[0229] As an example, the target recipient of the first message includes the UE201.

[0230] As an example, the second message is generated in the UE201.

[0231] As an example, the target recipient of the second message includes the node 203.

[0232] As an example, the second information block is generated in node 203.

[0233] As an example, the target recipient of the second information block includes the UE201.

[0234] As an example, the first information block is generated in the UE201.

[0235] As an example, the target recipient of the first information block includes the node 203.

[0236] As an example, the third information block is generated in node 203.

[0237] As an example, the target recipient of the third information block includes the UE201.

[0238] Example 3

[0239] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for the user plane and control plane according to an embodiment of this application, as shown in Figure 3.

[0240] Example 3 illustrates a schematic diagram of an embodiment of a wireless protocol architecture for a user plane and control plane according to this application, as shown in Figure 3. Figure 3 is a schematic diagram illustrating an embodiment of a radio protocol architecture for a user plane 350 and a control plane 300. Figure 3 shows the radio protocol architecture for the control plane 300 between a first communication node device (UE, gNB, or RSU in V2X) and a second communication node device (gNB, UE, or RSU in V2X), or between two UEs, using three layers: Layer 1, Layer 2, and Layer 3. Layer 1 (L1 layer) is the lowest layer and implements various PHY (physical layer) signal processing functions. Layer 1 will be referred to herein as PHY 301. Layer 2 (L2 layer) 305 is above PHY 301 and is responsible for the link between the first communication node device and the second communication node device, or between two UEs. Layer L2 305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second communication node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. It also provides security through encrypted data packets and supports cross-cell mobility between the second communication node devices and the first communication node device. The RLC sublayer 303 provides upper-layer packet segmentation and reassembly, retransmission of lost packets, and packet reordering to compensate for out-of-order reception due to HARQ. The MAC sublayer 302 provides multiplexing between logical and transport channels. It is also responsible for allocating various radio resources (e.g., resource blocks) within a cell among the first communication node devices. Furthermore, the MAC sublayer 302 handles HARQ operations. In the control plane 300, the Radio Resource Control (RRC) sublayer 306 of Layer 3 (L3) is responsible for acquiring radio resources (i.e., radio bearers) and configuring the lower layers using RRC signaling between the second and first communication node devices. The user plane 350's radio protocol architecture includes Layer 1 (L1) and Layer 2 (L2). The radio protocol architecture for the first and second communication node devices in the user plane 350 is largely the same as the corresponding layers and sublayers in the control plane 300 for Physical Layer 351, PDCP sublayer 354 in L2 Layer 355, RLC sublayer 353 in L2 Layer 355, and MAC sublayer 352 in L2 Layer 355. However, PDCP sublayer 354 also provides header compression for upper layer data packets to reduce radio transmission overhead.The L2 layer 355 in the user plane 350 also includes an SDAP (Service Data Adaptation Protocol) sublayer 356, which is responsible for mapping between QoS flows 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.).

[0241] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node.

[0242] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node.

[0243] As an example, the higher layer mentioned in this application refers to the layer above the physical layer.

[0244] As an example, the first message is generated in the RRC sublayer 306.

[0245] As an example, the second message is generated in the RRC sublayer 306.

[0246] As an example, the second information block is generated in the RRC sublayer 306.

[0247] As an example, the first information block is generated in the RRC sublayer 306.

[0248] As an example, the first information block is generated in the MAC sublayer 302 or the MAC sublayer 352.

[0249] As an example, the first information block is generated in the PHY301 or the PHY351.

[0250] As an example, the third information block is generated in the RRC sublayer 306.

[0251] As an example, the third information block is generated in the MAC sublayer 302 or the MAC sublayer 352.

[0252] As an example, the third information block is generated in the PHY301 or the PHY351.

[0253] Example 4

[0254] Example 4 illustrates a schematic diagram of a first communication device and a second communication device according to an embodiment of this application, as shown in Figure 4. Figure 4 is a block diagram of a first communication device 410 and a second communication device 450 communicating with each other in an access network.

[0255] 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.

[0256] 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.

[0257] 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.

[0258] 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.

[0259] 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.

[0260] 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.

[0261] 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: transmitting a first information block; wherein the first information block is used to indicate N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1, and N1 is a positive integer not greater than N; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node.

[0262] 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 an action including: sending a first information block; wherein the first information block is used to indicate N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; and the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions from the N functions are greater than the available storage resources in the first node.

[0263] 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: receiving a first information block; wherein the first information block is used to indicate N1 applicable functions of the sender of the first information block from N functions, where N is a positive integer greater than 1, and N1 is a positive integer not greater than N; the storage resources required by the sender of the first information block from the N1 applicable functions and any function other than the N1 applicable functions among the N functions are greater than the available storage resources in the sender of the first information block.

[0264] 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 an action including: receiving a first information block; wherein the first information block is used to indicate N1 applicable functions of the sender of the first information block from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the sender of the first information block from the N1 applicable functions and any function other than the N1 applicable functions from the N functions are greater than the available storage resources in the sender of the first information block.

[0265] As an example, the first node in this application includes the second communication device 450.

[0266] As an example, the second node in this application includes the first communication device 410.

[0267] 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 message 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 message in this application.

[0268] 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, the memory 460, and the data source 467} is used to transmit the second message 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 second message in this application.

[0269] 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 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 information block in this application.

[0270] 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, the memory 460, and the data source 467} is used to transmit the first information block 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 information block in this application.

[0271] 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 third 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 third information block in this application.

[0272] As an example, at least one of {the antenna 452, the receiver / transmitter 454, the receiving processor 456, the multi-antenna receiving processor 458, the transmitting processor 468, the multi-antenna transmitting processor 457, the controller / processor 459, the memory 460, and the data source 467} is used for inference performed in the first node of this application;

[0273] As an example, at least one of {the antenna 420, the transmitter / receiver 418, the receiver processor 470, the multi-antenna receiver processor 472, the transmitter processor 416, the multi-antenna transmitter processor 471, the controller / processor 475, and the memory 476} is used for inference performed in the second node of this application.

[0274] Example 5

[0275] Example 5 illustrates a flowchart of a transmission between a first node and a second node according to an embodiment of this application, as shown in Figure 5. In Figure 5, the second node N1 and the first node U1 are communication nodes transmitting via an air interface. In Figure 5, the steps in blocks F51 to F54 are optional.

[0276] For the second node N1, a first message is sent in step S511; a second message is received in step S512; a second information block is sent in step S513; a first information block is received in step S514; and a third information block is sent in step S515.

[0277] For the first node U1, in step S521, a first message is received; in step S522, a second message is sent; in step S523, a second information block is received; in step S524, a first information block is sent; in step S525, a third information block is received; and inference is performed in step S526.

[0278] In Embodiment 5, the sending of the second message is a response to receiving the first message; the second message includes functions supported by the first node; the transmission of the second message precedes the transmission of the first information block. The first information block is used to indicate N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node. The transmission of the third information block precedes the execution of inference by the first node; the third information block is used to activate at least one of the N1 applicable functions, or the third information block is used to configure the parameters of the inference of the first node. At least one of the N1 applicable functions is used to determine the parameters of the inference of the first node.

[0279] As an example, the first node U1 is the first node in this application.

[0280] As an example, the second node N1 is the second node in this application.

[0281] As one embodiment, the air interface between the second node N1 and the first node U1 includes a wireless interface between the base station equipment and the user equipment.

[0282] As one embodiment, the air interface between the second node N1 and the first node U1 includes a wireless interface between the relay node device and the user equipment.

[0283] As one embodiment, the air interface between the second node N1 and the first node U1 includes a wireless interface between user equipment and user equipment.

[0284] As one example, the second node N1 is the serving cell sustaining base station of the first node U1.

[0285] As an example, the steps in blocks F51 and F52 are present, while the steps in block F53 are not present.

[0286] As an example, the steps in blocks F51, F52 and F53 are all present.

[0287] As an example, the steps in blocks F51 and F53 are present, while the step in F52 is not present.

[0288] As an example, the steps in blocks F51, F52 and F54 are present, while the step in block F53 is not present.

[0289] As an example, the steps in blocks F51, F52, F53 and F54 are all present.

[0290] As an example, the steps in blocks F51, F53 and F54 are present, while the step in F52 is not present.

[0291] As an example, the steps in blocks F51, F52, F53 and F54 are not present.

[0292] As an example, at least one of the steps in blocks F51, F52, F53, or F54 is absent.

[0293] As an example, the first message triggers the second message.

[0294] As one example, the first message instructs the first node to send the second message.

[0295] As one embodiment, the first message includes an RRC message, and the second message includes an RRC message.

[0296] As one embodiment, the first message instructs the first node to report the supported functionalities, and the second message includes the supported functionalities of the first node.

[0297] As one example, the first message includes a UECapabilityEnqiry message, and the second message includes a UECapabilityInformation message, wherein the UECapabilityInformation message includes the functions supported by the first node.

[0298] As one embodiment, the second message includes the functions supported by the first node, and the N functions are all functions supported by the first node.

[0299] As an example, the second message indicates the N functions.

[0300] As an example, the second message indicates the N.

[0301] As an example, the second message indicates the N functions, and the second information block indicates M first-class identifiers, where M is a positive integer greater than 1; any one of the N1 applicable functions corresponds to one of the M first-class identifiers.

[0302] As an example, the first node determines the N functions on its own, and the second information block indicates M first-class identifiers, where M is a positive integer greater than 1; any one of the N1 applicable functions corresponds to one of the M first-class identifiers.

[0303] As one example, the indication of the second information block depends on the functions supported by the first node.

[0304] As one embodiment, the first message is used to query the capabilities of the first node, and the second message includes the capabilities of the first node.

[0305] As one embodiment, the first message includes a UECapabilityEnqiry message, the second message includes a UECapabilityInformation message, the second information block belongs to an RRCReconfiguration message, and the first information block belongs to a UEAssistanceInformation message.

[0306] As one example, the first message includes a UECapabilityEnqiry message, the second message includes a UECapabilityInformation message, the second information block belongs to IE OtherConfig, and the first information block belongs to a UEAssistanceInformation message.

[0307] As one embodiment, the second information block is carried by higher-layer signaling.

[0308] As an example, the second information block belongs to an RRC message.

[0309] As an example, the second information block belongs to the RRCReconfiguration message.

[0310] As an example, the second information block belongs to IE OtherConfig.

[0311] As one embodiment, the second information block includes an RRCReconfiguration message.

[0312] As one example, the second information block includes IE OtherConfig.

[0313] As one embodiment, the second information block instructs the first node to provide the applicable functions of the first node.

[0314] As one embodiment, the second information block instructing the first node to provide the applicable functions of the first node includes: the second information block instructing the first node to be allowed to provide the applicable functions of the first node.

[0315] As one example, the second information block instructs the first node to report UAI.

[0316] As one embodiment, the second information block instructing the first node to perform UAI reporting includes: the second information block instructing the first node to perform UAI reporting.

[0317] As one embodiment, the second information block indicates M first-class identifiers, where M is a positive integer greater than 1.

[0318] As an example, the second information block indicates M first-class identifiers, where M is a positive integer greater than 1; any one of the N functions corresponds to one of the M first-class identifiers.

[0319] As an example, the second information block indicates M first-class identifiers, where M is a positive integer greater than 1; any one of the N1 applicable functions corresponds to one of the M first-class identifiers.

[0320] As one example, the second information block indicates the N functions.

[0321] As one embodiment, the second information block indicates the N functions; any one of the N functions includes a first type of identifier.

[0322] As one embodiment, the second information block indicates the N functions; wherein, the N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from the N CSI reporting configurations.

[0323] As an example, the CSI reporting configuration is CSI-ReportConfig.

[0324] As an example, the CSI reporting configuration is used to configure a CSI report.

[0325] As an example, the CSI reporting configuration is used to configure the reporting of an inference-generated CSI.

[0326] As an example, the second information block indicates the N functions; wherein, the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups.

[0327] As one embodiment, the inference parameter group includes a first type of identifier.

[0328] As one embodiment, the inference parameter group includes a first type of identifier, which is an associated identifier (associated ID).

[0329] As an example, the inference parameter group includes a first type of identifier, which is an identifier associated with the AI ​​model.

[0330] As one embodiment, the inference parameter group includes a first type of identifier, which is an identifier associated with inference.

[0331] As an example, the inference parameter set includes at least one of the following: inference input, inference output, inference purpose, or first-class identifier.

[0332] As an example, the use of the inference includes at least one of CSI prediction, beam prediction, or CSI compression.

[0333] As an example, the purpose of the inference includes at least one of CSI prediction, beam prediction, CSI compression, or RLF (radio link failure).

[0334] As an example, the inference parameter set includes at least one of the following: resource set related information for prediction, RS resource set related information for measurement, report content related information, time instance related information for measurement, time instance related information for prediction, or a first type of identifier.

[0335] As an example, the information related to the resource set used for prediction includes an RS resource set.

[0336] As an example, the information related to the resource set used for prediction includes an air interface resource set.

[0337] As an example, the information related to the resource set used for prediction includes a beam set.

[0338] As one example, the information related to the resource set used for prediction includes the number of beams used for prediction.

[0339] As an example, the information related to the set of resources used for prediction includes the quantity of resources used for prediction.

[0340] As an example, the information related to the resource set used for prediction includes the number of RS resources used for prediction.

[0341] As an example, the information related to the resource set used for prediction includes set A.

[0342] As an example, the first node is not required to measure the set of resources used for prediction.

[0343] As an example, the information related to the RS resource set used for measurement includes an RS resource set.

[0344] As an example, the information related to the set of RS resources used for measurement includes the number of RS resources used for measurement.

[0345] As an example, the information related to the set of RS resources used for measurement includes the maximum number of RS resources used for measurement.

[0346] As one example, the information related to the reported content includes the reported content itself.

[0347] As one example, the information related to the reported content includes the reporting volume.

[0348] As one example, the information related to the reported content includes the size of the reported content.

[0349] As an example, the information related to the reported content includes the purpose of inference, which includes at least one of CSI prediction, beam prediction, or CSI compression.

[0350] As one example, the information related to the time instances to be measured includes the number of time instances to be measured.

[0351] As one example, the time instance information to be measured includes the maximum number of time instances to be measured.

[0352] As one example, the information related to the time instance to be measured includes the duration of the time instance being measured.

[0353] As one example, the information related to the time instance to be measured includes the maximum duration of the time instance to be measured.

[0354] As one example, the time-related information for prediction includes the number of predicted time instances.

[0355] As one example, the time-related information for prediction includes the maximum number of time instances to be predicted.

[0356] As one example, the time-related information for prediction includes the duration of the predicted time instance.

[0357] As an example, the time-related information for prediction includes the maximum duration of the predicted time instance.

[0358] As an example, the step in block F53 is not present; the second information block indicates the N functions; wherein, the N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from the N CSI reporting configurations; only the CSIs corresponding to the N1 CSI reporting configurations are reported.

[0359] As an example, the steps in block F53 and block F54 are not present; the second information block indicates the N functions; wherein, the N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from among the N CSI reporting configurations; the reasoning in the first node is used to obtain only the CSI corresponding to the N1 CSI reporting configurations from among the N CSI reporting configurations.

[0360] As an example, the third information block is used to activate at least one of the N1 applicable functions, including: the third information block is used to determine when or how to perform the inference report of the first node.

[0361] As one embodiment, the third information block being used to activate at least one of the N1 applicable functions includes: the third information block being used to activate the inference report corresponding to at least one of the N1 applicable functions.

[0362] As an example, the steps in block F53 are present; the second information block indicates the N functions; wherein, the N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from the N CSI reporting configurations; the third information block being used to activate at least one of the N1 applicable functions includes: the third information block being used to activate at least one of the N1 CSI reporting configurations.

[0363] As an example, the steps in blocks F53 and F54 are both present; the third information block is used to configure the parameters of the inference of the first node, and at least one of the N1 applicable functions is used to determine the parameters of the inference of the first node.

[0364] As an example, the steps in blocks F53 and F54 are both present; the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups; the third information block is used to configure the parameters of the inference of the first node, and at least one of the N1 applicable functions is used to determine the parameters of the inference in the first node.

[0365] As an example, the steps in blocks F53 and F54 are both present; the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups; the third information block is used to configure the parameters of the inference of the first node, and at least one of the N1 applicable functions is used to determine the parameters of the inference in the first node; wherein,

[0366] The parameters of the inference in the first node are configured by the third information block: the third information block is configured by at least one CSI reporting configuration, and the parameters of the inference in the first node include some or all of the parameters in the at least one CSI reporting configuration.

[0367] At least one of the N1 applicable functions is used to determine the parameters of the inference in the first node, including: the parameters of the inference in the first node include at least one first-class identifier corresponding to at least one of the N1 inference parameter groups.

[0368] As a sub-implementation of the above embodiments, the use of at least one of the N1 applicable functions to determine the parameters of the inference in the first node includes: the parameters of the inference in the first node include some or all of the inference parameters included in at least one of the N1 inference parameter groups.

[0369] As a sub-implementation of the above embodiments, the use of at least one of the N1 applicable functions to determine the parameters of the inference in the first node includes: the parameters of the inference in the first node include at least one first-class identifier included in at least one of the N1 inference parameter groups.

[0370] As an example, the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups; the third information block is used to configure the parameters of the inference of the first node.

[0371] As an example, the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups; the third information block is used to configure the parameters of the inference of the first node; the parameters of the inference of the first node configured by the third information block include: the third information block is used to configure at least one CSI reporting configuration, and the at least one CSI reporting configuration includes the parameters of the inference of the first node.

[0372] As one embodiment, the method in the first node includes:

[0373] Send at least one CSI report;

[0374] The output of the inference in the first node is used to generate the at least one CSI report.

[0375] As one embodiment, the first node includes:

[0376] The first processor sends at least one CSI report;

[0377] The output of the inference in the first node is used to generate the at least one CSI report.

[0378] As one embodiment, the method in the second node includes:

[0379] Receive at least one CSI report;

[0380] The output of the inference in the first node is used to generate the at least one CSI report.

[0381] As one embodiment, the second node includes:

[0382] The second processor receives at least one CSI report;

[0383] The output of the inference in the first node is used to generate the at least one CSI report.

[0384] As an example, the at least one CSI report includes multiple CSI reports, and the execution reasoning in the first node includes executing multiple inferences, the outputs of the multiple inferences being used to generate the multiple CSI reports respectively.

[0385] As an example, the at least one CSI report includes multiple CSI reports, and the execution reasoning in the first node includes executing multiple inferences, the outputs of the multiple inferences being used to generate the multiple CSI reports respectively; the first inference is any one of the multiple inferences, and the output of the first inference is used to generate the first CSI report among the multiple CSI reports.

[0386] As one embodiment, the method in the first node includes:

[0387] Send the first CSI report;

[0388] The execution reasoning in the first node includes executing first reasoning, the output of which is used to generate the first CSI report.

[0389] As one embodiment, the first node includes:

[0390] The first processor sends the first CSI report;

[0391] The execution reasoning in the first node includes executing first reasoning, the output of which is used to generate the first CSI report.

[0392] As one embodiment, the method in the second node includes:

[0393] Receive the first CSI report;

[0394] The execution reasoning in the first node includes executing first reasoning, the output of which is used to generate the first CSI report.

[0395] As one embodiment, the second node includes:

[0396] The second processor receives the first CSI report;

[0397] The execution reasoning in the first node includes executing first reasoning, the output of which is used to generate the first CSI report.

[0398] As an example, the first inference is used in one of CSI prediction, beam prediction, or CSI compression.

[0399] As one embodiment, the second node performs a second inference; wherein the output of the first inference includes a first CSI, the first CSI is reported carrying the first CSI, and the first CSI is used as input to the second inference to generate a second CSI.

[0400] As one embodiment, the second node performs a second inference; wherein the first inference is used for CSI compression and the second inference is used for CSI recovery.

[0401] As an example, the first CSI report includes the output of the first inference.

[0402] As an example, the first CSI report includes the post-processed output of the first inference.

[0403] As an example, the first CSI report includes the truncated and / or quantized output of the first inference.

[0404] As an example, the output of the first inference is post-processed and used to generate the first CSI report.

[0405] As an example, the output of the first inference is truncated and / or quantized and used to generate the first CSI report.

[0406] As an example, some or all of the output of the first inference is post-processed and used to generate the first CSI report.

[0407] As an example, some or all of the output of the first inference is truncated and / or quantized and used to generate the first CSI report.

[0408] As an example, the output of the first inference includes a first CSI, which is used to generate the first CSI report.

[0409] As an example, the benefits of the above method include improving the performance of CSI reporting by leveraging the advantages of the first inference, including more accurate reporting and / or lower overhead.

[0410] As an example, the first CSI report includes the first CSI.

[0411] As an example, the first CSI is post-processed and used to generate the first CSI report.

[0412] As an example, the first CSI report includes the post-processed first CSI.

[0413] As an example, the first CSI report carries the post-processed version of the first CSI.

[0414] As an example, the first CSI is truncated and / or quantized and used to generate the first CSI report.

[0415] As an example, the first CSI report includes the first CSI after truncation and / or quantization.

[0416] As an example, the first CSI report carries a truncated and / or quantized version of the first CSI.

[0417] As an example, the first CSI includes one or more of PMI, CRI, CQI, RI, LI, SSBRI, RSRP, SINR, Capability Index, and TDCP.

[0418] As an example, the first CSI includes one or more of PMI, CRI, CQI, RI, LI, SSBRI, RSRP, SINR, capability index, TDCP, predicted channel information, predicted beam information, or confidence information.

[0419] As one embodiment, the first CSI includes a channel matrix.

[0420] As one example, the first CSI includes a feature vector.

[0421] As an example, the first CSI includes a feature vector and feature values.

[0422] As an example, the first CSI includes precoded information.

[0423] As one embodiment, the first CSI includes pre-encoded information based on a non-codebook.

[0424] As an example, the first CSI is used to determine at least one precoding matrix.

[0425] As an example, the first CSI indicates at least one precoding matrix.

[0426] As an example, the precoding matrix is ​​in the spatial-frequency domain.

[0427] As an example, the precoding matrix is ​​an angular-delay domain projection.

[0428] As one embodiment, the first CSI includes information on the relative phase, amplitude, and / or coefficients between multiple antenna ports.

[0429] As an example, the first CSI includes a compressed CSI.

[0430] As an example, the first CSI includes predicted / estimated CSI.

[0431] As an example, how the first CSI report is generated based on the first inference is determined by the manufacturer of the first node, or is implementation-related. A typical but non-limiting implementation is described below:

[0432] The first node first measures the RS resources used for channel measurement to obtain the channel parameter matrix H. r×t Where r and t are the number of receiving antennas and the number of antenna ports, respectively; at least the channel parameter matrix H r×t Alternatively, its feature vector is input into an AI model, and the output of the AI ​​model is used to obtain the first CSI report.

[0433] If the first CSI report requires the first node to estimate interference (including noise), the first node can measure the RS resources used for interference measurement to obtain the measured interference.

[0434] In one implementation, measurement interference is also input into the AI ​​model.

[0435] In another implementation, the measurement interference is not input into the AI ​​model; the output of the AI ​​model and the measurement interference are used together to generate the first CSI report.

[0436] Without loss of generality, the AI ​​model or the parameters of the AI ​​model used to generate the first CSI report are determined by the manufacturer of the first node.

[0437] As an example, the reasoning is based on training or AI.

[0438] As one example, the reasoning includes an AI entity used for inference.

[0439] As an example, the reasoning includes at least a portion of an AI entity.

[0440] As an example, the reasoning includes a portion of an AI entity used for reasoning.

[0441] As an example, the reasoning includes AI (Artificial Intelligence) inference.

[0442] As an example, the reasoning model is obtained through training.

[0443] As an example, the training of the inference in the first node is performed by the first node.

[0444] As an example, the training of the inference in the first node is performed by the second node.

[0445] As an example, the training of the inference in the first node is performed by the core network.

[0446] As an example, the training of the inference in the first node is performed by an AI training producer.

[0447] As an example, the training of the inference in the first node is performed by the MDA (Management Data Analytics Function).

[0448] As an example, the training of the inference in the first node is performed by the MDA function located in the first node.

[0449] As an example, the training of the inference in the first node is performed by the MDA function located in the second node.

[0450] As an example, the training of the inference in the first node is performed by NWDAF (Network Data Analytics Function).

[0451] As an example, the training of the inference in the first node is performed by the MDAS (Management Data Analytics Service) producer.

[0452] As an example, the training of the inference in the first node is performed by the MnS (Management Service) producer.

[0453] As an example, the inference in the first node needs to be deployed.

[0454] As an example, the reasoning in the first node is obtained by loading.

[0455] As an example, the inference in the first node is obtained from the serving cell of the first node.

[0456] As an example, the inference in the first node is obtained from the sustaining base station of the serving cell of the first node.

[0457] As an example, the first node deploys the inference.

[0458] As an example, the inference does not require deployment.

[0459] As an example, the inference is obtained from the core network.

[0460] As an example, the reasoning is based on artificial intelligence or machine learning.

[0461] As an example, the reasoning is based on a neural network.

[0462] As an example, the inference is based on CNN (Conventional Neural Networks).

[0463] As one example, the inference includes preprocessing.

[0464] As one example, the reasoning includes post-processing.

[0465] As one example, the post-processing includes DFT.

[0466] As one example, the post-processing includes quantization.

[0467] As an example, the post-processing includes one or more of the following: angular domain to spatial domain transformation, spatial domain to angular domain transformation, time domain to frequency domain transformation, and frequency domain to time domain transformation.

[0468] As one example, the post-processing includes truncation and / or padding.

[0469] As an example, the inference includes one or more of convolution, pooling, cascading, and activation.

[0470] As one example, the inference includes a fully connected layer.

[0471] As one example, the inference includes a pooling layer.

[0472] As one example, the inference includes at least one convolutional layer.

[0473] As one example, the reasoning includes at least one coding layer.

[0474] As an example, an encoding layer includes at least one convolutional layer and one pooling layer.

[0475] As an example, in a convolutional layer, at least one convolutional kernel is used to convolve the input to generate a corresponding feature map, and at least one feature map output by the convolutional layer is reshaped into a vector and input to a fully connected layer; the fully connected layer transforms the vector into an output.

[0476] As an example, some or all of the following parameters in the inference—convolution kernel size, number of convolutional layers, convolution stride, pooling kernel size, pooling kernel stride, pooling function, activation function, and number of feature maps—are obtained through training.

[0477] As an example, some or all of the convolution kernel, pooling kernel, pooling function, activation function, parameters of the pooling function, and parameters of the activation function in the inference are obtained through training.

[0478] As one example, the AI ​​function includes AI inference functionality.

[0479] As one example, the AI ​​functionality includes AI training functionality.

[0480] As one example, the AI ​​functionality includes AI management functionality.

[0481] As one example, the AI ​​function includes AI performance monitoring.

[0482] As one example, the AI ​​includes ML (Machine Learning).

[0483] As one example, the AI ​​includes AI and ML.

[0484] As one example, the AI ​​includes AI or ML.

[0485] As an example, the preprocessing includes one or more of the following: quantization, DFT (Discrete Fourier Transform), matrix decomposition, matrix transformation or projection, spatial-to-angular-domain transformation, angular-to-spatial-domain transformation, frequency-to-time-domain transformation, time-to-frequency-domain transformation, truncation, padding, mapping, or labeling.

[0486] As an example, the preprocessing includes DFT (Discrete Fourier Transform).

[0487] As one example, the preprocessing includes one or more of matrix decomposition, matrix transformation, or projection.

[0488] As an example, the preprocessing includes one or more of the following: quantization, spatial-to-angular-domain transformation, angular-to-spatial-domain transformation, frequency-to-time-domain transformation, or time-to-frequency-domain transformation.

[0489] As one example, the preprocessing includes truncation and / or padding.

[0490] As one example, the preprocessing includes mapping.

[0491] As one example, the preprocessing includes mapping to vectors.

[0492] As one example, the preprocessing includes labeling.

[0493] As an example, the label refers to a mark made with a label.

[0494] Example 6

[0495] Example 6 illustrates a schematic diagram of a first information block according to an embodiment of this application; as shown in Figure 6.

[0496] In embodiment 6, the first information block is used to indicate only N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node. The first node is the sender of the first information block.

[0497] In the above method, all the functions applicable to the first node among the N functions are composed of the N1 applicable functions.

[0498] As an example, the first information block is used to indicate only N1 applicable functions of the first node from N functions, and the first information block also indicates the N1.

[0499] Typically, the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions refer to the total amount of storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions.

[0500] As an example, the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node, while the storage resources required by the N1 applicable functions are not greater than the available storage resources in the first node.

[0501] In the above method, the first node reports all applicable functions that meet the above requirements. The benefits include: the target recipient of the first information block can be informed of as many applicable functions as possible, improving reliability, robustness, and overall system performance.

[0502] As an example, N1 is greater than 1, and the storage resources required by the N1 applicable functions in the first node are orthogonal (i.e., do not overlap).

[0503] As an example, N1 is greater than 1, and at least two of the N1 applicable functions share the same storage resources in the first node.

[0504] Example 7

[0505] Example 7 illustrates a schematic diagram of a first information block according to another embodiment of this application; as shown in Figure 7.

[0506] In embodiment 7, the first information block is used to indicate N0 applicable functions of the first node from the N functions, the N0 applicable functions including the N1 applicable functions, where N1 is less than N, and N0 is a positive integer greater than N1 and not greater than N; the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node. The first node is the sender of the first information block.

[0507] In the above method, all the functions applicable to the first node among the N functions are composed of the N0 applicable functions.

[0508] As an example, the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node, the storage resources required by the N1 applicable functions are not greater than the available storage resources in the first node, and the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions among the N functions are greater than the available storage resources in the first node.

[0509] As an example, the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node, the storage resources required by the N1 applicable functions are not greater than the available storage resources in the first node, and the storage resources required by the first node for any applicable function other than the N1 applicable functions among the N0 applicable functions are greater than the available storage resources in the first node.

[0510] As an example, the storage resources required by any of the N0 applicable functions in the first node are no greater than the available storage resources in the first node, while the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node.

[0511] As an example, the storage resources required by any of the N0 applicable functions in the first node are no greater than the available storage resources in the first node; the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node; the storage resources required by the N1 applicable functions are no greater than the available storage resources in the first node; and the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions among the N functions are greater than the available storage resources in the first node.

[0512] As an example, the storage resources required by any one of the N0 applicable functions in the first node are no greater than the available storage resources in the first node; the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node; the storage resources required by the N1 applicable functions are no greater than the available storage resources in the first node; and the storage resources required by the first node for any applicable function other than the N1 applicable functions among the N0 applicable functions are greater than the available storage resources in the first node.

[0513] In the above method, one applicable function among the N functions needs to satisfy the following conditions: its required storage resources are no greater than the available storage resources of the first node; the first node reports all N0 applicable functions that meet the requirements, of which only a portion of the applicable functions (i.e., N1 applicable functions) can simultaneously occupy the storage resources of the first node, because the required storage resources must not exceed the available storage resources in the first node. The advantages include: the target recipient of the first information block can be informed of all applicable functions and select appropriate portions of the applicable functions to simultaneously occupy the storage resources of the first node, improving flexibility and adaptability.

[0514] Example 8

[0515] Example 8 illustrates a schematic diagram of a first information block according to another embodiment of this application; as shown in Figure 8.

[0516] In embodiment 8, the first information block further indicates the N1, or the first information block further indicates the maximum number of applicable functions that are activated.

[0517] As an example, the first information block is used to indicate N0 applicable functions of the first node from the N functions, the N0 applicable functions including the N1 applicable functions, where N1 is less than N, and N0 is a positive integer greater than N1 and not greater than N; the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node; the first information block also indicates N1.

[0518] As one embodiment, the first information block is used to indicate N0 applicable functions of the first node from the N functions, the N0 applicable functions including the N1 applicable functions, where N1 is less than N, and N0 is a positive integer greater than N1 and not greater than N; the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node; the first information block also indicates the maximum number of activated applicable functions. The first node is the sender of the first information block.

[0519] As an example, the first information block also indicates the N1.

[0520] As an example, the first information block further indicates that the required storage resources in the first node are no greater than the maximum number of applicable functions of the available storage resources in the first node, and the maximum number of required storage resources in the first node is N1.

[0521] As an example, the first information block also indicates the maximum number of applicable functions that are activated, the maximum number of applicable functions being N1.

[0522] As a sub-implementation of the above embodiments, the maximum number of activated applicable functions refers to the maximum number of applicable functions that can be activated.

[0523] As a sub-implementation of the above embodiments, the maximum number of applicable functions activated refers to the maximum number of applicable functions activated at the same time.

[0524] As a sub-example of the above embodiments, the maximum number of activated applicable functions refers to the maximum number of applicable functions that can be activated simultaneously.

[0525] As a sub-implementation of the above embodiments, the maximum number of activated applicable functions refers to the total amount of storage resources in the first node that meet the requirements not exceeding the maximum number of applicable functions of available storage resources in the first node.

[0526] As one embodiment, the maximum number of applicable functions that are activated at the same time includes: the maximum number of applicable functions that can be activated at the same time.

[0527] As one embodiment, the maximum number of applicable functions that can be activated simultaneously includes: the maximum number of applicable functions that can be activated simultaneously.

[0528] As an example, the maximum number of activated applicable functions is N1, and the N1 activated applicable functions must satisfy the following condition: the storage resources required by the N1 activated applicable functions in the first node are not greater than the available storage resources in the first node.

[0529] In the above method, the maximum number of activated applicable functions is N1. The N1 applicable functions can be activated simultaneously by the target recipient of the first information block because the storage resources required by the N1 applicable functions in the first node are no greater than the available storage resources in the first node.

[0530] As an example, the maximum number of activated applicable functions is S, where S is a positive integer greater than 1, and S is equal to or greater than N1; the S activated applicable functions must satisfy the following condition: the storage resources in the first node required by the S activated applicable functions are not greater than the available storage resources in the first node.

[0531] In the above method, the maximum number of activated applicable functions is equal to or greater than N1. The N1 applicable functions can be activated simultaneously by the target recipient of the first information block because the storage resources required by the N1 applicable functions in the first node are not greater than the available storage resources in the first node.

[0532] In the above method, the number of applicable functions that the target recipient of the first information block can activate simultaneously cannot exceed the maximum number of activated applicable functions indicated by the first information block. Advantages include: fully considering the capabilities of the terminal (such as storage resources), better adapting to various terminal capabilities, high flexibility, and strong adaptability.

[0533] Example 9

[0534] Example 9 illustrates a schematic diagram of the relationship between N1 applicable functions and reasoning according to an embodiment of this application; as shown in Figure 9.

[0535] In embodiment 9, the first node performs inference; at least one of the N1 applicable functions is used to determine the parameters of the inference. The first node is the sender of the first information block.

[0536] As one example, the parameters of the inference include a first type of identifier.

[0537] As one embodiment, the parameters of the inference include a first type of identifier, which is an associated identifier (associated ID).

[0538] As one example, the parameters of the inference include a first type of identifier, which is an identifier associated with the AI ​​model.

[0539] As one embodiment, the parameters of the inference include a first type of identifier, which is an identifier associated with the inference.

[0540] As an example, the parameters of the inference include at least one of the inference input, the inference output, the purpose of the inference, or a first-class identifier.

[0541] As an example, the parameters of the inference include at least one of the following: resource set related information for prediction, RS resource set related information for measurement, report content related information, time instance related information for measurement, time instance related information for prediction, or a first type of identifier.

[0542] As an example, the use of at least one of the N1 applicable functions to determine the parameters of the inference includes: the parameters of the inference include at least one first-class identifier corresponding to at least one of the N1 applicable functions.

[0543] As an example, the use of at least one of the N1 applicable functions to determine the parameters of the inference includes: the parameters of the inference include some or all of the inference parameters included in at least one of the N1 applicable functions.

[0544] As an example, the use of at least one of the N1 applicable functions to determine the parameters of the inference includes: the parameters of the inference are determined based on some or all of the inference parameters included in at least one of the N1 applicable functions.

[0545] As an example, the activated applicable function among the N1 applicable functions is used to determine the parameters of the inference.

[0546] As an example, the N1 applicable functions are all used to determine the parameters of the inference.

[0547] As an example, some of the N1 applicable functions are used to determine the parameters of the inference.

[0548] [Option 1: At least one of the N1 applicable functions is used to determine the parameters of the inference]

[0549] As an example, the N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from among the N CSI reporting configurations; the inference in the first node is used to obtain the CSI corresponding to at least one of the N1 CSI reporting configurations; the parameters used by at least one of the N1 applicable functions to determine the inference include: the parameters of the inference include some or all of the parameters in the at least one of the N1 CSI reporting configurations.

[0550] As an example, the N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from among the N CSI reporting configurations; the inference in the first node is used to obtain the CSI corresponding to at least one of the N1 CSI reporting configurations; the parameters used by at least one of the N1 applicable functions to determine the inference include: the parameters of the inference include a first type identifier in the at least one of the N1 CSI reporting configurations.

[0551] As an example, the N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from among the N CSI reporting configurations; the inference in the first node is used to obtain the CSI corresponding to the activated CSI reporting configuration among the N1 CSI reporting configurations; at least one of the N1 applicable functions is used to determine the parameters of the inference, including: the parameters of the inference include some or all of the parameters in the activated CSI reporting configuration among the N1 CSI reporting configurations.

[0552] As an example, the N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from among the N CSI reporting configurations; the inference in the first node is used to obtain the CSI corresponding to the activated CSI reporting configuration among the N1 CSI reporting configurations; at least one of the N1 applicable functions is used to determine the parameters of the inference, including: the parameters of the inference include a first type identifier in the activated CSI reporting configuration among the N1 CSI reporting configurations.

[0553] [Option 2: At least one of the N1 applicable functions is used to determine the parameters of the inference]

[0554] As an example, the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups; the parameters of the inference in the first node include some or all parameters in at least one CSI reporting configuration; at least one of the N1 applicable functions is used to determine the parameters of the inference, including: the at least one or all parameters in the at least one CSI reporting configuration includes at least one first-class identifier corresponding to at least one of the N1 inference parameter groups.

[0555] As an example, the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups; the parameters of the inference in the first node include some or all parameters in at least one CSI reporting configuration; at least one of the N1 applicable functions is used to determine the parameters of the inference, including: the at least one or all parameters in the at least one CSI reporting configuration includes at least one first-class identifier included in at least one of the N1 inference parameter groups.

[0556] As an example, the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups; the parameters of the inference in the first node include some or all parameters in at least one CSI reporting configuration; at least one of the N1 applicable functions is used to determine the parameters of the inference, including: the some or all parameters in the at least one CSI reporting configuration include some or all inference parameters included in at least one of the N1 inference parameter groups.

[0557] As an example, the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups; the parameters of the inference in the first node include some or all parameters in at least one CSI reporting configuration; at least one of the N1 applicable functions is used to determine the parameters of the inference, including: the some or all parameters in the at least one CSI reporting configuration are determined based on some or all inference parameters included in at least one of the N1 inference parameter groups.

[0558] Example 10

[0559] Example 10 illustrates a schematic diagram of the relationship between storage resources required for two functions according to an embodiment of this application; as shown in Figure 10.

[0560] In Embodiment 10, any one of the N functions corresponds to a first-type identifier; the storage resources required by two functions with different first-type identifiers from the N functions in the first node are orthogonal. The first node is the sender of the first information block. In Figure 10, storage resource #1, storage resource #2, ..., storage resource #T are all storage resources in the first node; function #1 and function #2 are two functions with different first-type identifiers from the N functions; storage resource #2 and storage resource #T represent the storage resources required by function #1 and function #2 respectively.

[0561] As an example, the storage resources required by any two of the N functions corresponding to different first-type identifiers in the first node are orthogonal.

[0562] In the above method, the storage resources corresponding to the functions of different first-class identifiers are necessarily orthogonal. The advantages include: simplified design and reduced complexity.

[0563] As an example, the storage resources required by two functions with different first-type identifiers among the N functions are orthogonal in the first node.

[0564] As an example, among the N functions, the storage resources required by two functions with different first-type identifiers in the first node are orthogonal, and the two functions with different first-type identifiers in the N functions share the same storage resources in the first node.

[0565] In the above method, the storage resources corresponding to the functions of different first-class identifiers may be orthogonal, overlapping, or overlapping. The advantages include: minimizing storage resources, high flexibility, and wider applicability.

[0566] Example 11

[0567] Example 11 illustrates a schematic diagram of the relationship between storage resources required for two functions according to another embodiment of this application; as shown in Figure 11.

[0568] In Embodiment 11, two functions with the same first-class identifier among the N functions share the same storage resource in the first node. The first node is the sender of the first information block. In Figure 11, storage resource #1, storage resource #2, ..., storage resource #T are all storage resources in the first node; function #1 and function #2 are two functions with the same first-class identifier among the N functions; storage resource #2 represents the storage resource shared by function #1 and function #2.

[0569] As one embodiment, sharing the same storage resources in the first node for two functions with the same first-type identifier among the N functions includes: the storage resources required by the two functions with the same first-type identifier among the N functions in the first node are at least partially the same.

[0570] In the above method, the storage resources corresponding to the functions of different first-class identifiers are at least partially the same. The advantages include: high flexibility, wider applicability, and minimal saving of storage resources.

[0571] As an example, sharing the same storage resources in the first node for two functions with the same first-type identifier among the N functions includes: the two functions with the same first-type identifier among the N functions each require the same storage resources in the first node.

[0572] In the above method, the storage resources corresponding to functions with the same first-class identifier are always the same. The advantages include: significantly saving storage resources, simplifying the design, and reducing complexity.

[0573] Example 12

[0574] Example 12 illustrates a schematic diagram of the relationship between reasoning and the first type of identifier according to an embodiment of this application; as shown in Figure 12.

[0575] In Example 12, a reasoning association is used with a first-class identifier.

[0576] As an example, a reasoning association with a first-class identifier includes: a reasoning parameter includes a first-class identifier.

[0577] As an example, a reasoning association with a first type of identifier includes: a reasoning being identified by a first type of identifier.

[0578] As an example, a first-class identifier for inference association includes: an AI model used for inference is identified by a first-class identifier.

[0579] As an example, a reasoning association first type identifier includes: a reasoning AI entity is identified by a first type identifier.

[0580] As an example, a reasoning association with a first-class identifier includes: an AI function for which a reasoning is used is identified by a first-class identifier.

[0581] As an example, the advantages of the above method include simplifying the design and unifying the understanding of different AI entities or AI functions across multiple nodes by identifying an AI entity or AI function through a first type of identifier.

[0582] As an example, a reasoning association first type identifier includes: an AI entity performing a reasoning is identified by a first type identifier.

[0583] As an example, a reasoning association first type identifier includes: the first type identifier is used by the first node to determine the AI ​​model used for reasoning.

[0584] As an example, the advantages of the above method include simplifying the design and unifying the understanding of different AI entities / functions across multiple nodes by identifying an AI model / entity / function through a first type of identifier.

[0585] As an example, a first-class identifier for inference association includes: the first-class identifier is used to identify or indicate a set of RS resources, and measurements of the set of RS resources are used to obtain a training dataset for inference.

[0586] As an example, a first-class identifier for inference association includes: training used to obtain inference is identified by the first-class identifier.

[0587] As an example, a first-class identifier for inference association includes: the dataset used for training an inference is identified by a first-class identifier.

[0588] As an example, the benefits of the above method include identifying the inference generated by an AI training or AI training dataset by identifying the AI ​​training or AI training dataset, establishing consensus among different AI functions, and further simplifying the design.

[0589] As an example, an inference association with a first type of identifier includes: an inference based on measurements of a first resource set for spatial beam prediction against a second resource set, the first resource set being an RS resource set for measurement, the second resource set being a resource set for prediction, and the second resource set depending on a first type of identifier.

[0590] As an example, the advantages of the above method include reduced RS overhead and reduced feedback latency.

[0591] As an example, an inference association with a first type of identifier includes: an inference based on measurements of a first resource set to predict channel information for a second resource set, the first resource set being a set of RS resources for measurement, the second resource set being a set of resources for prediction, and the second resource set depending on a first type of identifier.

[0592] As an example, an inference association with a first type of identifier includes: an inference based on historical measurements of a first resource set to perform temporal beam prediction for a second resource set, the first resource set being an RS resource set for measurement, the second resource set being a resource set for prediction, and the second resource set depending on the first type of identifier.

[0593] As an example, the advantages of the above method include reducing beam feedback delay and improving the real-time performance of beam acquisition.

[0594] As an example, an inference association with a first type of identifier includes: an inference based on historical measurements of a first resource set to predict temporal channel information for a second resource set, the first resource set being a set of RS resources for measurement, the second resource set being a set of resources for prediction, and the second resource set depending on the first type of identifier.

[0595] As an example, the advantages of the above method include reducing channel information feedback delay and improving the real-time performance of channel information acquisition.

[0596] Examples 13A-13B

[0597] Examples 13A-13B illustrate schematic diagrams of the deployment of first inference on the first node according to an embodiment of this application, as shown in Figures 13A-13B respectively.

[0598] In embodiment 13A, the first node requests the first inference to be loaded from the first producer and obtains the first inference from the first producer. In Figure 13A, the first node deploys the first inference.

[0599] As an example, the first inference of the deployment includes obtaining the first inference.

[0600] As an example, the deployment of the first inference includes obtaining an AI entity.

[0601] As one example, the deployment of the first inference includes obtaining an AI entity that performs the first inference.

[0602] As an example, the deployment of the first inference includes obtaining an AI entity that includes AI functionality to perform the first inference.

[0603] As an example, deploying the first inference includes loading the first inference.

[0604] As one embodiment, deploying the first inference includes making a request to load the first inference.

[0605] As an example, the first inference is obtained from the serving cell of the first node.

[0606] As an example, the first inference is obtained from the sustaining base station of the serving cell of the first node.

[0607] As an example, the first inference is obtained from the core network.

[0608] As an example, the first inference is obtained from the first producer.

[0609] As an example, the deployment of the first inference is performed by an AI function.

[0610] As an example, the deployment of the first inference is accomplished by an AI function deployed on the first node.

[0611] As an example, the first deployment inference is performed by the AI ​​deployment function.

[0612] As an example, the deployment of the first inference is accomplished by the AI ​​deployment function deployed on the first node.

[0613] As an example, the first inference of the deployment is performed by the AI ​​inference function.

[0614] As an example, the deployment of the first inference is accomplished by the AI ​​inference function deployed on the first node.

[0615] As an example, the first inference for the deployment is performed by an AI entity.

[0616] As an example, the deployment of the first inference is performed by an AI entity deployed on the first node.

[0617] As an example, the first deployment reasoning is performed by an AI entity with a deployment function.

[0618] As an example, the deployment of the first inference is performed by an AI entity with deployment capabilities deployed on the first node.

[0619] As an example, the deployment of the first inference is performed by an AI entity with an inference function.

[0620] As an example, the deployment of the first inference is performed by an AI entity with inference capabilities deployed on the first node.

[0621] As one embodiment, the deployment of the first inference includes obtaining the first inference from a first producer.

[0622] As one embodiment, deploying the first inference includes making a request to a first producer to load the first inference.

[0623] As one embodiment, deploying the first inference includes loading the first inference from a first producer.

[0624] As an example, the first producer generates and provides the AL entity.

[0625] As an example, the first producer generates and provides AL functionality.

[0626] As an example, the first producer is the producer of the first inference.

[0627] As an example, the first producer includes an AL entity producer.

[0628] As one example, the first producer includes an AL function producer.

[0629] As one example, the first producer includes an AL deployment producer.

[0630] As one example, the first producer includes an AL loading producer.

[0631] As one example, the first producer includes an AL-trained producer.

[0632] As an example, the first producer includes an AL inference producer.

[0633] As an example, the first producer includes the producer of the AL entity deployment.

[0634] As one example, the first producer includes the producer that loads the AL entity.

[0635] As an example, the first producer includes an MnS (Management Service) producer.

[0636] As an example, the target recipient of the first information block is the first producer.

[0637] As an example, the target recipient of the first information block is different from the first producer.

[0638] As an example, the training for obtaining the first inference is performed by the first producer.

[0639] As an example, the executor used to obtain the training for the first inference is different from the first producer.

[0640] As one example, the AI ​​includes ML (Machine Learning).

[0641] In Example 13B, the first node requests the second producer to load the first inference and obtains the first inference from the first producer. In Figure 13B, the first node deploys the first inference.

[0642] As an example, the first inference of the deployment includes obtaining the first inference.

[0643] As one example, the deployment of the first inference includes obtaining an AI entity or AI function that performs the first inference.

[0644] As an example, deploying the first inference includes loading the first inference.

[0645] As one embodiment, deploying the first inference includes making a request to load the first inference.

[0646] As an example, the deployment of the first inference is accomplished by an AI function deployed on the first node.

[0647] As an example, the deployment of the first inference is accomplished by the AI ​​deployment function deployed on the first node.

[0648] As an example, the first deployment reasoning is performed by an AI entity with a deployment function.

[0649] As one example, the second producer generates and provides AI entities or AI functions.

[0650] As one example, the second producer includes an MnS (Management Service) producer.

[0651] As an example, the second producer includes the producer of the AI ​​model training.

[0652] As one example, the second producer is the target recipient of the first information block.

[0653] As one example, the second producer is different from the target receiver of the first information block.

[0654] As one example, the second producer is the serving cell of the first node.

[0655] As one example, the second producer is the maintenance base station of the serving cell of the first node.

[0656] As one example, the second producer is the core network.

[0657] As an example, the first inference is obtained from the serving cell of the first node.

[0658] As an example, the first inference is obtained from the sustaining base station of the serving cell of the first node.

[0659] As an example, the first inference is obtained from the core network.

[0660] As an example, the training for obtaining the first inference is performed by the second producer.

[0661] As an example, the second producer is different from the first producer.

[0662] As an example, the first producer generates and provides the AL entity.

[0663] As an example, the first producer generates and provides AL functionality.

[0664] As an example, the first producer is the producer of the first inference.

[0665] As an example, the first producer includes an AL entity producer.

[0666] As one example, the first producer includes an AL function producer.

[0667] As one example, the first producer includes an AL deployment producer.

[0668] As one example, the first producer includes an AL loading producer.

[0669] As one example, the first producer includes an AL-trained producer.

[0670] As an example, the first producer includes an AL inference producer.

[0671] As an example, the first producer includes the producer of the AL entity deployment.

[0672] As one example, the first producer includes the producer that loads the AL entity.

[0673] As an example, the first producer includes an MnS (Management Service) producer.

[0674] Example 14

[0675] Example 14 illustrates a schematic diagram of RAN (Radio Access Network) domain AI / ML function deployment according to an embodiment of this application; as shown in Figure 14. The gNB in ​​Example 14 can be replaced with, for example, an eNB, or a network device such as a 6G base station.

[0676] AI / ML related functions include ML training (also known as AI training, or AI / ML training), ML testing, and ML inference (also known as AI inference, or AI / ML inference), etc. ML training, ML testing, and ML inference functions can be deployed independently or co-located. Deployment of AI / ML related functions can be implemented through software, such as downloading and / or running executable files; or it can be implemented through a combination of software and hardware, such as accelerating specific computing units through hardware to improve computing speed or save power.

[0677] ML training functionality can be deployed in a cross-domain management system or a domain-specific management system; the domain-specific management system is used to manage the RAN domain or the CN (Core Network) domain. For example, ML training functionality for MDA (Management Data Analytics) can be deployed on MDAF (MDA Function); ML training for network data analytics can be deployed on NWDAF (Network Data Analytics Function), meaning the ML training functionality is an MTLF (Model Training Logical Function).

[0678] The ML inference function can also be deployed in a cross-domain management system or a domain-specific management system; for example, the ML inference function is MDAF, or the ML inference function is AnLF (Analytics logical function) located in NWDAF.

[0679] Similarly, ML testing capabilities can also be deployed in cross-domain management systems or domain-specific management systems.

[0680] In Example 14, the RAN domain ML training function 1402 is located in the RAN domain management function 1403; while the ML inference function is located in the base station, that is, the AI / ML inference function 1404 is located in gNB 1405, the AI / ML inference function 1406 is located in gNB 1407, and so on.

[0681] In Figure 14, the management of ML inference functions of multiple base stations is completed by RAN domain management function 1403, that is, data interaction with RAN domain MnS (Management Service) consumer / cross-domain management 1401 (as shown by the dashed arrow in Figure 14).

[0682] Optionally, the management of ML inference function can also be completed by the base station itself, that is, each base station can independently interact with the RAN domain MnS consumer / cross-domain management 1401.

[0683] It should be noted that Example 14 is merely a non-limiting implementation; optionally, the ML training function of the RAN domain may also be deployed at the base station; or optionally, some base stations may deploy both the ML inference function and the ML training function of the RAN domain, while some base stations may only deploy the ML inference function.

[0684] As an example, one of the gNBs (or base stations) in Example 14 is the second node of this application.

[0685] As an example, the second processor in this application includes an AL / ML inference function, namely 1404 or 1406, as shown in Figure 14.

[0686] Example 15

[0687] Example 15 illustrates a schematic diagram of the deployment of AI / ML functionality in a UE according to one embodiment of this application; as shown in Figure 15. The RAN domain ML training function 1505 in Figure 15 is optional.

[0688] UE function 1504 is deployed in the first node of this application, and the UE function 1504 includes AI / ML inference function 1506; the AI / ML inference function 1506 uses an ML model (also called an AI model) for inference; an ML model is typically trained before being used for AI / ML inference.

[0689] As an example, the at least one CSI report in this application is obtained through inference by the AI / ML inference function 1506.

[0690] As an example, the first CSI report in this application is obtained through inference by the AI / ML inference function 1506.

[0691] As an example, the first processor in this application includes an AL / ML inference function 1506 in Figure 15.

[0692] As an example, the UE function 1504 includes a RAN domain ML training function 1505, which runs training data through an ML model to obtain a relevant loss and adjusts the parameters of the ML model based on the calculated loss; the ML training includes at least one of ML initial training, ML re-training, and reinforcement learning.

[0693] The above embodiments can reduce the complexity of the base station, or save air interface resources caused by reporting training data; however, the above embodiments place high demands on the processing capabilities of the UE side.

[0694] Optionally, the UE function 1504 also includes a CN domain ML training function (not shown in Figure 15).

[0695] Optionally, the UE function 1504 also includes an AI / ML deployment function—not shown in Figure 15—for loading ML models and data.

[0696] As an example, the first node indicates whether it supports ML training function (RAN domain or CN domain) through capability reporting. The capability reporting is RRC signaling or NAS (Non-Access Stratum) signaling.

[0697] As an example, the ML model and the associated metadata are loaded by the first node from a network device or a remote server.

[0698] Optionally, the UE function 1504 is an MnS (Management Service) producer that provides data to the CN domain MnF (Management Function) 1501, and / or the RAN domain MnF 1502, and / or the cross-domain management system 1503 for management or analysis (as shown by double arrow 1507).

[0699] Optionally, the UE function 1504 is an MnS consumer that loads data from the CN domain MnF (Management Function) 1501, and / or the RAN domain MnF 1502, and / or the cross-domain management system 1503 for AI / ML-related management, such as managing data requests, ML model activation, and / or ML training (as shown by double arrow 1507).

[0700] As an example, the ML model is based on a neural network.

[0701] As an example, the ML model is based on CNN (Conventional Neural Networks).

[0702] As an example, the ML model is based on the Transformer architecture.

[0703] Example 16

[0704] Example 16 illustrates a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application; as shown in Figure 16. Figure 16(a) includes a third processor, a fourth processor, and a fifth processor, and Figure 16(b) includes a third processor, a fourth processor, a fifth processor, and a sixth processor.

[0705] In Example 16(a), the third processor sends a first dataset to the fourth processor and a second dataset to the fifth processor; the fourth processor generates a target first-type parameter set based on the first dataset, and sends the generated target first-type parameter set to the fifth processor; the fifth processor processes the second dataset using the target first-type parameter set to obtain a first-type output. In Figure 16(a), the first-type feedback is optional.

[0706] In Example 16(b), the third processor sends a first dataset to the fourth processor and a second dataset to the fifth processor; the fourth processor generates a target first-type parameter set based on the first dataset, and sends the generated target first-type parameter set to the fifth processor; the fifth processor processes the second dataset using the target first-type parameter set to obtain a first-type output, and sends the first-type output to the sixth processor. In Figure 16(b), the first-type feedback and the second-type feedback are optional.

[0707] As an example, in Figure 16(a), the fifth processor sends the first type of output to the second node in this application.

[0708] As an example, Figure 16(a) employs a single-side AI model, in which the fifth processor performs inference in the first node of this application.

[0709] As an example, Figure 16(b) employs a two-sided AI model, where the fifth processor performs the inference in the first node of this application, and the sixth processor includes the inference in the second node of this application.

[0710] As an example, the AI ​​includes ML (Machine Learning) inference.

[0711] As an example, the fifth processor executes the first inference in this application.

[0712] As one embodiment, the sixth processor includes the second inference described in this application.

[0713] As an example, the fifth processor performs the inference in the first node of this application.

[0714] As one embodiment, the sixth processor includes the inference function in the second node of this application.

[0715] As an example, the fifth processor sends a first type of feedback to the fourth processor, and the first type of feedback is used to trigger a recalculation or update of the target first type of parameter group.

[0716] As one embodiment, the sixth processor sends a second type of feedback to the third processor, the second type of feedback being used to generate the first dataset or the second dataset, or the second type of feedback being used to trigger the sending of the first dataset or the second dataset.

[0717] As one embodiment, the third processor generates the first dataset and the second dataset based on measurements of a first type of wireless signal, the first type of wireless signal including downlink RS.

[0718] As one embodiment, the fifth processor belongs to the first node, and the sixth processor belongs to the second node.

[0719] As an example, the CSI report in this application belongs to the first type of output.

[0720] As an example, the first CSI report in this application belongs to the first type of output.

[0721] As an example, the second dataset includes the input for inference in the first node.

[0722] As an example, for inference in the first node of this application, the second dataset includes information obtained based on CSI reporting configuration.

[0723] As an example, the first dataset includes training data.

[0724] As an example, the fourth processor belongs to the inference producer in the first node.

[0725] As one embodiment, the fourth processor includes an AI training producer.

[0726] As one embodiment, the fourth processor includes an AI training function.

[0727] As an example, the fourth processor is used for model training, and the trained model is described by the target first class of parameter sets.

[0728] As one embodiment, the fourth processor belongs to the first node.

[0729] The above embodiments avoid passing the first dataset to the second node.

[0730] As one example, the fourth processor belongs to the second node.

[0731] The above embodiments support joint training and optimize system performance.

[0732] As an example, the fourth processor belongs to the core network.

[0733] The above embodiments support network-wide joint training, further optimizing system performance.

[0734] As an example, the second dataset includes inference data.

[0735] As one embodiment, the fifth processor includes an AI inference producer.

[0736] As one embodiment, the fifth processor includes an AI inference function.

[0737] As an example, the fifth processor belongs to the first node.

[0738] As an example, the fifth processor constructs a model based on the target first type of parameter group, and then inputs the second dataset into the constructed model to obtain the first type of output.

[0739] As an example, the reasoning in the first node is described by the target first type parameter group.

[0740] As an example, the target first type of parameter group is used to construct the inference in the first node.

[0741] As one embodiment, the fifth processor includes inference from the second node.

[0742] As an example, the fifth processor generates a recovery dataset based on the first type of output, and the error between the recovery dataset and the second dataset is used to generate the first type of feedback.

[0743] As a sub-example of the above embodiment, the generation of the recovery dataset employs inference similar to that in the second node.

[0744] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the fourth processing opportunity recalculates the target first type of parameter set.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] Example 17

[0749] Example 17 illustrates a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application; as shown in Figure 17. In Figure 17, the processing apparatus 1800 in the first node includes a first processor 1801.

[0750] As one example, the first node is a user equipment.

[0751] As an example, the first node is a relay node device.

[0752] As an example, the first processor 1801 includes at least one of the following in embodiment 4: {antenna 452, receiver / transmitter 454, receiver processor 456, transmitter processor 468, multi-antenna receiver processor 458, multi-antenna transmitter processor 457, controller / processor 459, memory 460, data source 467}.

[0753] As an example, the first processor 1801 includes the antenna 452, receiver / transmitter 454, receiver processor 456, transmitter processor 468, multi-antenna receiver processor 458, multi-antenna transmitter processor 457, controller / processor 459, memory 460, and data source 467 as described in Example 4.

[0754] The first processor 1801 sends the first information block;

[0755] In embodiment 17, the first information block is used to indicate N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node.

[0756] As an example, the first information block also indicates the N1.

[0757] As an example, the first information block also indicates the maximum number of applicable functions that are activated.

[0758] As one embodiment, the first processor 1801 performs inference;

[0759] Wherein, at least one of the N1 applicable functions is used to determine the parameters of the inference.

[0760] As one embodiment, the first processor 1801 receives a third information block; the transmission of the third information block precedes the execution inference of the first node;

[0761] The third information block is used to activate at least one of the N1 applicable functions, or the third information block is used to configure the parameters of the inference.

[0762] As an example, any one of the N functions corresponds to a first type identifier; the storage resources required by two functions corresponding to different first type identifiers in the N functions in the first node are orthogonal.

[0763] As an example, two functions with the same first-class identifier among the N functions share the same storage resources in the first node.

[0764] As an example, the first information block is used to indicate N0 applicable functions of the first node from the N functions, the N0 applicable functions including the N1 applicable functions, where N1 is less than N, and N0 is a positive integer greater than N1 and not greater than N; the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node.

[0765] As one embodiment, the first processor 1801 receives the second information block;

[0766] As one embodiment, the second information block instructs the first node to provide the applicable functions of the first node, or the second information block instructs the first node to report UAI.

[0767] As one embodiment, the second information block indicates the N functions; wherein,

[0768] The N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from the N CSI reporting configurations.

[0769] or,

[0770] The N functions each include N inference parameter groups, and each of the N inference parameter groups includes at least one inference parameter. The N1 applicable functions include N1 inference parameter groups from the N inference parameter groups that are applicable to the first node.

[0771] As one embodiment, the first processor 1801 receives a first message; in response to receiving the first message, it sends a second message;

[0772] The second message includes the functions supported by the first node; the transmission of the second message precedes the transmission of the first information block.

[0773] Example 18

[0774] Example 18 illustrates a structural block diagram of a processing apparatus for a second node according to an embodiment of the present application; as shown in Figure 18. In Figure 18, the processing apparatus 1900 in the second node includes a second processor 1901.

[0775] In one embodiment, the second node is a base station device.

[0776] In one embodiment, the second node is a user equipment.

[0777] As one embodiment, the second node is a relay node device.

[0778] As one embodiment, the second processor 1901 includes at least one of the following in embodiment 4: {antenna 420, receiver / transmitter 418, receiver processor 470, transmitter processor 416, multi-antenna receiver processor 472, multi-antenna transmitter processor 471, controller / processor 475, memory 476}.

[0779] As one embodiment, the second processor 1901 includes the antenna 420, receiver / transmitter 418, receiver processor 470, transmitter processor 416, multi-antenna receiver processor 472, multi-antenna transmitter processor 471, controller / processor 475, and memory 476 as in embodiment 4.

[0780] The second processor 1901 receives the first information block;

[0781] In embodiment 18, the first information block is used to indicate N1 applicable functions of the sender of the first information block from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the sender of the first information block from the N1 applicable functions and any function other than the N1 applicable functions from the N functions are greater than the available storage resources in the sender of the first information block.

[0782] As an example, the first information block also indicates the N1.

[0783] As an example, the first information block also indicates the maximum number of applicable functions that are activated.

[0784] As an example, the sender of the first information block performs inference; wherein at least one of the N1 applicable functions is used to determine the parameters of the inference.

[0785] As one embodiment, the second processor 1901 sends a third information block; the transmission of the third information block precedes the execution inference of the sender of the first information block;

[0786] The third information block is used to activate at least one of the N1 applicable functions, or the third information block is used to configure the parameters of the inference.

[0787] As an example, any one of the N functions corresponds to a first type identifier; the storage resources required by two functions corresponding to different first type identifiers in the sender of the first information block are orthogonal.

[0788] As an example, two functions that correspond to the same first-class identifier among the N functions share the same storage resources in the sender of the first information block.

[0789] As an example, the first information block is used to indicate N0 applicable functions of the sender of the first information block from the N functions, the N0 applicable functions including the N1 applicable functions, where N1 is less than N, and N0 is a positive integer greater than N1 and not greater than N; the storage resources in the sender of the first information block required by the N0 applicable functions are greater than the available storage resources in the sender of the first information block.

[0790] As one embodiment, the second processor 1901 sends a second information block.

[0791] As one embodiment, the second information block instructs the sender of the first information block to provide the applicable functions of the sender of the first information block, or the second information block instructs the sender of the first information block to perform UAI reporting.

[0792] As one embodiment, the second information block indicates the N functions; wherein,

[0793] The N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the sender of the first information block from among the N CSI reporting configurations;

[0794] or,

[0795] The N functions each include N inference parameter groups, and each of the N inference parameter groups includes at least one inference parameter. The N1 applicable functions include N1 inference parameter groups applicable to the sender of the first information block from the N inference parameter groups.

[0796] As one embodiment, the second processor 1901 sends a first message and receives a second message;

[0797] In this process, the sender of the first information block receives the first message in response to it, and then sends the second message; the second message includes functions supported by the sender of the first information block; the transmission of the second message precedes the transmission of the first information block.

[0798] Those skilled in the art will understand that all or part of the steps in the above methods can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium, such as a read-only memory, hard disk, or optical disk. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Accordingly, each module unit in the above embodiments can be implemented in hardware or in the form of software functional modules. This application is not limited to any specific combination of software and hardware. The user equipment, terminal, and UE in this application include, but are not limited to, drones, communication modules on drones, remote-controlled aircraft, aircraft, small aircraft, mobile phones, tablets, laptops, vehicle-mounted communication equipment, vehicles, RSUs, wireless sensors, internet access cards, IoT terminals, RFID terminals, NB-IoT terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet access cards, vehicle-mounted communication equipment, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base stations or system equipment in this application include, but are not limited to, macrocell base stations, microcell base stations, small cell base stations, home base stations, relay base stations, eNBs, gNBs, TRPs (Transmitter Receiver Points), GNSS, relay satellites, satellite base stations, airborne base stations, RSUs (Road Side Units), drones, and testing equipment, such as transceivers or signaling testers that simulate some functions of a base station, and other wireless communication equipment.

[0799] Those skilled in the art will understand that the present invention can be practiced in other specified forms without departing from its core or essential characteristics. Therefore, the embodiments disclosed herein should in any way be considered descriptive rather than restrictive. The scope of the invention is defined by the appended claims rather than the foregoing description, and all modifications within their equivalent meaning and scope are considered to be included therein.

Claims

1. A first node used for wireless communication, characterized in that, include: The first processor sends the first information block; The first information block is used to indicate N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node.

2. The first node according to claim 1, characterized in that, include: The first processor performs inference; Wherein, at least one of the N1 applicable functions is used to determine the parameters of the inference.

3. The first node according to claim 2, characterized in that, include: The first processor receives a third information block; the transmission of the third information block precedes the execution inference of the first node. The third information block is used to activate at least one of the N1 applicable functions, or the third information block is used to configure the parameters of the inference.

4. The first node according to any one of claims 1 to 3, characterized in that, Each of the N functions corresponds to a first-type identifier; the storage resources required by two functions corresponding to different first-type identifiers in the N functions are orthogonal in the first node.

5. The first node according to any one of claims 1 to 4, characterized in that, Two functions with the same first-class identifier among the N functions share the same storage resources in the first node.

6. The first node according to any one of claims 1 to 5, characterized in that, The first information block is used to indicate N0 applicable functions of the first node from the N functions, the N0 applicable functions including the N1 applicable functions, where N1 is less than N, and N0 is a positive integer greater than N1 and not greater than N; the storage resources required by the N0 applicable functions in the first node are greater than the available storage resources in the first node.

7. The first node according to any one of claims 1 to 6, characterized in that, include: The first processor receives the second information block; The second information block indicates the N functions; wherein, The N functions each include N CSI reporting configurations, and the N1 applicable functions include N1 CSI reporting configurations applicable to the first node from the N CSI reporting configurations. Alternatively, the N functions each include N inference parameter groups, each of the N inference parameter groups includes at least one inference parameter, and the N1 applicable functions include N1 inference parameter groups applicable to the first node from the N inference parameter groups.

8. A second node used for wireless communication, characterized in that, include: The second processor receives the first information block; Wherein, the first information block is used to indicate N1 applicable functions of the sender of the first information block from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the sender of the first information block from the N1 applicable functions and any function other than the N1 applicable functions from the N functions are greater than the available storage resources in the sender of the first information block.

9. A method used in a first node of wireless communication, characterized in that, include: Send the first information block; The first information block is used to indicate N1 applicable functions of the first node from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the N1 applicable functions and any function other than the N1 applicable functions in the N functions are greater than the available storage resources in the first node.

10. A method used in a second node for wireless communication, characterized in that, include: Receive the first information block; Wherein, the first information block is used to indicate N1 applicable functions of the sender of the first information block from N functions, where N is a positive integer greater than 1 and N1 is a positive integer not greater than N; the storage resources required by the sender of the first information block from the N1 applicable functions and any function other than the N1 applicable functions from the N functions are greater than the available storage resources in the sender of the first information block.

Images