Method and apparatus used in node for inference of wireless communication

Abstract

Disclosed in the present application are a method and apparatus used in a node for inference of wireless communication. The method comprises: a node receiving a first information block, wherein the first information block configures a first parameter set, and the first parameter set is used for inference; a priority value corresponding to the first parameter set depends on a power state of a first node; an execution state of a process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set, and the remaining inference resources of the first node; and the inference resources comprise at least the former of computing resources or storage resources. The present application rationally allocates inference resources by optimizing the determination of the priority value for an inference process, thereby improving transmission performance and spectral efficiency.

Description

A method and apparatus for inference in a node used in wireless communication Technical Field

[0001] This application relates to signal transmission methods and apparatus in wireless communication systems, and more particularly to reasoning methods and apparatus that integrate artificial intelligence and communication. Background Technology

[0002] Leveraging AI / ML (Artificial Intelligence / Machine Learning) technologies to enhance 5G network performance is a crucial component of achieving deep integration of 5G and AI / ML and building intelligent dimensions for 5G-Advanced (5.5G) networks. The 3GPP (3rd Generation Partnership Project) standards organization initiated research on standards for RAN (Radio Access Networks) intelligence starting with Rel-16 (Release-16), primarily focusing on intelligent use cases, enhanced data collection, and the potential impact on RAN nodes and interfaces. Rel-18 formally established a project for AI / ML-based 5G air interface enhancement, initiating international standardization work on the integration of 5G air interface and AI / ML, mainly focusing on research into use cases, lifecycle management (LCM), simulation verification, and data collection.

[0003] Currently, AI / ML development has entered the large-scale model stage. Large-scale communication models can achieve autonomous networks and intelligent services, supporting network operation optimization and improving network efficiency. Deep integration of communication and AI is a crucial direction for future communication evolution. AI will empower the development and upgrade of 5G, 5.5G, and 6G, bringing new management models such as automated frequency band and traffic management, real-time analysis of user data and network load, and prediction of network status. However, compared to traditional terminal-side operations, the consumption of terminal resources by AI / ML-based operations is clearly a significant issue that needs to be considered. Summary of the Invention

[0004] The current Release-18 (Rel-18) standard provides a clear definition of resource consumption and corresponding priority design for physical layer channel information processing. Specifically, when the remaining CPU (Central Processing Unit) resources are insufficient to meet the number of CPUs required for channel processing, the processing of the corresponding channel information will be abandoned. In the future, when AI / ML is used in terminals, the hardware requirements and resource consumption for AI / ML computation and inference will be even more stringent. Therefore, how to reasonably define AI / ML computing power or resources is a problem that needs to be considered.

[0005] To address the aforementioned scenarios, and considering the characteristics of the dataset as well as the reliability and efficiency of model training, this application discloses a solution. It should be noted that while this application is initially intended for AI / ML scenarios, it can also be applied to other non-AI / ML scenarios. Furthermore, adopting a unified design scheme for different scenarios (such as other non-AI / ML scenarios, including but not limited to sensor integration, Vehicle to Everything (V2X), capacity enhancement systems, short-range communication systems, NTN (Non-Terrestrial Network), IoT (Internet of Things), and URLLC (Ultra-Reliable Low-Latency Communication) networks) helps reduce hardware complexity and cost. Where there is no conflict, embodiments and features in any node of this application can be applied to any other node. Where there is no conflict, embodiments and features in any embodiment of this application can be arbitrarily combined with each other.

[0006] In particular, the interpretation of terms, nouns, functions, and variables in this application (unless otherwise specified) can be found in the definitions of the TS38 and TS37 series of 3GPP (3rd Generation Partnership Project) Technical Specifications (TS). Where necessary, reference can be made to TS38.211, TS38.212, TS38.213, TS38.214, TS38.215, TS38.300, TS38.304, TS38.305, TS38.321, TS38.331, TS37.355, and TS38.423 in the 3GPP technical specifications to aid in understanding this application.

[0007] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS38 series.

[0008] As an example, the interpretation of terms in this application is based on the definitions in the 3GPP specification protocol TS37 series.

[0009] As an example, the interpretation of the terms used in this application is based on the definitions in 3GPP specification protocol Rel-17.

[0010] As an example, the interpretation of the terms used in this application is based on the definitions in 3GPP specification protocol Rel-18.

[0011] This application discloses a method for inference in a first node for wireless communication, comprising:

[0012] Receive a first information block, the first information block is configured with a first parameter set, the first parameter set is for inference;

[0013] Wherein, the priority value corresponding to the first parameter set depends on the power state of the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0014] As an example, the problem this application aims to solve includes: how to efficiently configure inference resources.

[0015] As an example, the problem this application aims to solve includes: how to reasonably allocate inference resources based on the power state of the terminal.

[0016] As an example, the problem to be solved by this application includes: determining the power state of the terminal, and then reasonably determining the AI / ML process to be executed, so as to avoid exhausting the terminal's power too quickly.

[0017] As an example, the features of the above method include: when the first node is in a state that requires power saving, the priority value corresponding to the AI / ML process will be increased to reduce the priority of the AI / ML process, thereby achieving the effect of power saving; conversely, when the first node is not in a state that requires power saving, the priority value corresponding to the AI / ML process will be decreased to increase the priority of the AI / ML process, thereby achieving the effect of performance improvement.

[0018] As an example, the features of the above method include: establishing a connection between the priority value corresponding to the AI / ML process and the power state of the terminal, with different priority values ​​corresponding to different power states of the terminal, to achieve a balance between performance and energy consumption, thereby enabling the enjoyment of the performance gains brought by AI / ML while ensuring battery working time.

[0019] According to one aspect of this application, the above method is characterized by comprising:

[0020] Send a first signal, which indicates the power state of the first node.

[0021] As an example, the features of the above method include: the first node informs the second node in this application of the power state, thereby ensuring that the first node and the second node have a consistent understanding of the priority value corresponding to the first parameter set under different power states, so as to ensure that the first node and the second node also have a consistent understanding of the executed process and avoid misunderstanding.

[0022] According to one aspect of this application, the above method is characterized in that the first parameter set is associated with an AI / ML model, or the first parameter set is associated with a function, or the first parameter set is associated with an entity.

[0023] According to one aspect of this application, the above method is characterized in that the process corresponding to the first parameter set includes at least one of model training, data collection, inference, or performance monitoring.

[0024] As an example, the features of the above method include: compared with traditional CSI (Channel State Information) related processes, the AI / ML process consumes more resources. Therefore, the above method of establishing a relationship between the priority value of the process and the power state of the terminal is mainly for the AI / ML process, taking into account the power state of the terminal in order to execute the AI / ML process reasonably.

[0025] According to one aspect of this application, the method is characterized in that the priority value corresponding to the first parameter set is one of K1 priority values, and the power state of the first node is used to determine the priority value corresponding to the first parameter set from the K1 priority values, wherein K1 is a positive integer greater than 1.

[0026] According to one aspect of this application, the above method is characterized in that the power state of the first node is the first power state among K1 power states, the K1 power states correspond one-to-one with the K1 priority values, and the first power state is used to determine the priority value corresponding to the first parameter set from the K1 priority values.

[0027] As an example, the features of the above method include: establishing a one-to-one correspondence between priority values ​​and power states, so as to realize the adjustment of priority values ​​in a relatively simple way to cope with different power states.

[0028] According to one aspect of this application, the above method is characterized in that the power state of the first node includes the first node being in a first power state; when the first node is in the first power state, the priority value corresponding to the first parameter set is set to a predefined value.

[0029] As an example, the features of the above method include: when the first node is in the first power state, such as in power saving mode, by setting the priority value corresponding to the first parameter set to a predefined value, the process corresponding to the first parameter set is prevented from being executed, thereby achieving the effect of power saving.

[0030] According to one aspect of this application, the above method is characterized by comprising:

[0031] Receive a second information block, the second information block is configured with a second parameter set, the second parameter set is for inference;

[0032] The comparison between the priority value corresponding to the first parameter set and the priority value corresponding to the second parameter set is used to determine the execution state of the process corresponding to the first parameter set and the execution state of the process corresponding to the second parameter set.

[0033] As an example, the features of the above method include: using the traditional method of comparing priority values ​​to determine which process will be abandoned, thereby improving compatibility with traditional systems and reducing design complexity.

[0034] As an example, the features of the above method include: the first node is a user equipment.

[0035] As an example, the features of the above method include: the first node is a terminal.

[0036] As an example, the features of the above method include: the first node is configured with an entity for AI / ML.

[0037] As an example, the features of the above method include: the first node is configured with an AI / ML model.

[0038] As an example, the features of the above method include: the first node is configured with a Functionality for AI / ML.

[0039] As an example, the features of the above method include: the first node includes an entity for AI / ML.

[0040] As an example, the features of the above method include: the first node includes a core network device that provides AI services to the terminal.

[0041] As an example, the features of the above method include: the first node includes an application layer device that provides AI services to the terminal.

[0042] As an example, the features of the above method include: the first node includes an Agent that provides AI services to the terminal.

[0043] As an example, the features of the above method include: the first node includes a Handset.

[0044] This application discloses a method for inference in a second node for wireless communication, comprising:

[0045] Send a first information block, the first information block is configured with a first parameter set, the first parameter set is for inference;

[0046] Wherein, the priority value corresponding to the first parameter set depends on the power state of the first node, and the sender of the first information block includes the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0047] As an example, the features of the above method include: the second node includes a core network.

[0048] As an example, the features of the above method include: the second node includes an entity for deploying AI / ML models.

[0049] As an example, the features of the above method include: the second node includes a node for deploying AI / ML models.

[0050] As an example, the features of the above method include: the second node includes a base station.

[0051] As an example, the features of the above method include: the second node is a base station.

[0052] As an example, the features of the above method include: the second node is an eNB.

[0053] As an example, the features of the above method include: the second node is a gNB.

[0054] As an example, the features of the above method include: the second node is a network device, which includes at least one of a core network device and an access network device.

[0055] As an example, the features of the above method include: the second node is a device that provides wireless communication function services, can communicate with terminal devices, and is usually located on the network side.

[0056] As an example, the features of the above method include: the base station in this application includes a core network.

[0057] As an example, the features of the above method include: the base station in this application includes core network equipment.

[0058] As an example, the features of the above method include: the base station in this application includes an entity for deploying AI / ML models.

[0059] As an example, the features of the above method include: the base station in this application includes nodes for deploying AI / ML models.

[0060] As an example, the features of the above method include: the second node includes an OTT (Over-The-Top) Server.

[0061] As an example, the features of the above method include: the second node includes an eNB.

[0062] As an example, the second node in this application includes OAM (Operation Administration and Maintenance).

[0063] According to one aspect of this application, the above method is characterized by comprising:

[0064] Receive a first signal, the first signal indicating the power state of the first node.

[0065] According to one aspect of this application, the above method is characterized in that the first parameter set is associated with an AI / ML model, or the first parameter set is associated with a function, or the first parameter set is associated with an entity.

[0066] According to one aspect of this application, the above method is characterized in that the process corresponding to the first parameter set includes at least one of model training, data collection, inference, or performance monitoring.

[0067] According to one aspect of this application, the method is characterized in that the priority value corresponding to the first parameter set is one of K1 priority values, and the power state of the first node is used to determine the priority value corresponding to the first parameter set from the K1 priority values, wherein K1 is a positive integer greater than 1.

[0068] According to one aspect of this application, the above method is characterized in that the power state of the first node is the first power state among K1 power states, the K1 power states correspond one-to-one with the K1 priority values, and the first power state is used to determine the priority value corresponding to the first parameter set from the K1 priority values.

[0069] According to one aspect of this application, the above method is characterized in that the power state of the first node includes the first node being in a first power state; when the first node is in the first power state, the priority value corresponding to the first parameter set is set to a predefined value.

[0070] According to one aspect of this application, the above method is characterized by comprising:

[0071] Send a second information block, which configures a second parameter set for inference;

[0072] The comparison between the priority value corresponding to the first parameter set and the priority value corresponding to the second parameter set is used to determine the execution state of the process corresponding to the first parameter set and the execution state of the process corresponding to the second parameter set.

[0073] According to one aspect of this application, the above method is characterized in that the second node is a base station.

[0074] According to one aspect of this application, the above method is characterized in that the second node includes a TRP (transmitter-receiver point).

[0075] This application discloses a first node for model training in wireless communication, comprising:

[0076] A first receiver receives a first information block, the first information block is configured with a first parameter set, the first parameter set is for inference;

[0077] Wherein, the priority value corresponding to the first parameter set depends on the power state of the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0078] This application discloses a second node for model training in wireless communication, comprising:

[0079] The second transmitter sends a first information block, which is configured with a first parameter set for inference.

[0080] Wherein, the priority value corresponding to the first parameter set depends on the power state of the first node, and the sender of the first information block includes the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0081] As an example, compared with conventional solutions, this application has the following advantages, but is not limited to:

[0082] This application supports the deep integration of AI and communication to improve the adaptability and intelligence of communication systems, thereby enhancing the performance, efficiency, and user experience of communication systems.

[0083] The priority value corresponding to the AI / ML process is linked to the power state of the terminal. Different priority values ​​are corresponding to different power states of the terminal, so as to achieve a balance between performance and energy consumption, and thus enjoy the performance gain brought by AI / ML while ensuring battery working time.

[0084] Determine the power state of the terminal and rationally determine the AI / ML processes to be executed in order to avoid exhausting the terminal's power too quickly;

[0085] When the first node is in a state that requires power conservation, the priority value of the AI / ML process will be increased to reduce the priority of the AI / ML process, thereby achieving the effect of power conservation; conversely, when the first node is not in a state that requires power conservation, the priority value of the AI / ML process will be decreased to increase the priority of the AI / ML process, thereby achieving the effect of performance improvement. Attached Figure Description

[0086] 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:

[0087] Figure 1 illustrates a flowchart of the first node transmission according to an embodiment of this application;

[0088] Figure 2 shows a schematic diagram of a network architecture according to an embodiment of this application;

[0089] 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;

[0090] Figure 4 shows a schematic diagram of a first communication device and a second communication device according to an embodiment of this application;

[0091] Figure 5 shows a flowchart of transmission between a first node and a second node according to an embodiment of this application;

[0092] Figure 6 illustrates a flowchart of a first signal transmission according to an embodiment of this application;

[0093] Figure 7 illustrates a flowchart of the transmission of a second information block according to an embodiment of this application;

[0094] Figure 8 shows a schematic diagram of the power state according to an embodiment of this application;

[0095] Figure 9 shows a schematic diagram of inference resources according to an embodiment of this application;

[0096] Figure 10 shows a schematic diagram of RAN domain AI / ML function deployment according to an embodiment of this application;

[0097] Figure 11 shows a schematic diagram of the AI / ML function deployment of a UE according to an embodiment of this application;

[0098] Figure 12 shows a schematic diagram of a processing system based on artificial intelligence or machine learning according to an embodiment of this application;

[0099] Figure 13 illustrates a schematic diagram of artificial intelligence or machine learning according to an embodiment of this application;

[0100] Figure 14 shows a structural block diagram of a processing apparatus for a first node according to an embodiment of the present application;

[0101] Figure 15 shows a structural block diagram of a processing apparatus for a second node according to an embodiment of this application. Detailed Implementation

[0102] 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, including but not limited to the embodiments in Figure 1 and the embodiments in Figures 5-15, the embodiments in Figure 5 and the embodiments in Figures 6-15, etc.

[0103] Example 1

[0104] Example 1 illustrates a flowchart of a first node transmission according to an embodiment of this application, as shown in Figure 1. In Figure 1, each block represents a step.

[0105] The first node receives a first information block in step 101. The first information block is configured with a first parameter set, which is used for inference.

[0106] In Example 1, the priority value corresponding to the first parameter set depends on the power state of the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0107] As one example, the first node is a user equipment (UE).

[0108] As one example, the first node is a terminal.

[0109] As an example, the first node is the first node in this application.

[0110] As one embodiment, the first information block includes RRC (Radio Resource Control) signaling.

[0111] As an example, the first information block includes one or more RRC IEs (Information Elements).

[0112] As an example, the first information block includes one or more fields in an RRC IE.

[0113] As an example, the first information block indicates the first parameter set.

[0114] As an example, the first information block explicitly indicates the first parameter set.

[0115] As an example, the first information block implicitly indicates the first parameter set.

[0116] As one example, the first information block includes one or more CSI-ReportConfigs.

[0117] As an example, the first information block is associated with one or more CSI-ReportConfig IEs.

[0118] As one example, the first information block includes one or more CSI-MeasConfigs.

[0119] As an example, the first information block is associated with one or more CSI-MeasConfig IEs.

[0120] As one example, the first information block includes one or more CSI-ResourceConfigs.

[0121] As an example, the first information block is associated with one or more CSI-ResourceConfig IEs.

[0122] As an example, the name of the RRC signaling used to configure the first information block includes CSI.

[0123] As an example, the name of the RRC signaling used to configure the first information block includes CSI-RS (Channel State Information Reference Signal).

[0124] As an example, the name of the RRC signaling used to configure the first information block includes Report.

[0125] As an example, the name of the RRC signaling used to configure the first information block includes Config.

[0126] As an example, the first information block indicates at least one inference configuration.

[0127] As an example, the first parameter set includes configuration parameters for inference.

[0128] As one embodiment, the first parameter set includes a configuration of reference signal resources used for inference.

[0129] As an example, the reasoning includes reasoning based on AI / ML models.

[0130] As an example, the reasoning includes prediction.

[0131] As an example, the priority value corresponding to the first parameter set includes: the priority value of the AI / ML model associated with the first parameter set.

[0132] As an example, the priority value corresponding to the first parameter set includes: the priority value of the function associated with the first parameter set.

[0133] As an example, the priority value corresponding to the first parameter set includes: the priority value of the module associated with the first parameter set.

[0134] As an example, the priority value corresponding to the first parameter set includes: the priority value of the process associated with the first parameter set.

[0135] As an example, the priority value corresponding to the first parameter set includes: the priority value of the process associated with the first parameter set.

[0136] As an example, the priority value corresponding to the first parameter set includes: the reported priority value associated with the first parameter set.

[0137] As an example, the priority value corresponding to the first parameter set includes: the priority value of the inference computation associated with the first parameter set.

[0138] As an example, the priority value is a non-negative integer.

[0139] As an example, the smaller the priority value, the higher the corresponding priority; the larger the priority value, the lower the corresponding priority.

[0140] As an example, the priority value depends on the configuration of the first parameter set.

[0141] As an example, the priority value depends on at least one coefficient in a set of coefficients, the value of which depends on the power state of the first node.

[0142] As an example, the priority value depends on at least one coefficient in a set of coefficients, and the power state of the first node is used to determine the coefficient on which the priority value depends from the set of coefficients.

[0143] As a sub-implementation of the two embodiments described above, the coefficient set includes multiple coefficients.

[0144] As a sub-implementation of the two embodiments described above, the coefficient set includes predefined coefficients.

[0145] As a sub-implementation of the two embodiments described above, the coefficients included in the coefficient set are configured.

[0146] As an example, the power state of the first node includes: the state of the remaining power of the first node.

[0147] As an example, the power state of the first node includes: the remaining power of the first node is lower than a first threshold, which is predefined or configured.

[0148] As a sub-implementation of this embodiment, the first threshold is a percentage.

[0149] As a sub-implementation of this embodiment, the remaining power of the first node is estimated by the first node.

[0150] As a sub-implementation of this embodiment, the remaining power of the first node is obtained by the first node through implementation.

[0151] As an example, the power state of the first node includes one of a plurality of power levels.

[0152] As a sub-implementation of this embodiment, the plurality of power levels correspond to a plurality of remaining power values.

[0153] As a sub-implementation of this embodiment, the multiple power levels correspond to multiple power consumption states of the first node, including: high power consumption state and low power consumption state.

[0154] As a sub-implementation of this embodiment, the multiple power levels correspond to the multiple power consumption states of the first node, including: high power consumption state, normal power consumption state, and low power consumption state.

[0155] As one embodiment, the power state of the first node includes: the first node being in a power saving mode, or the first node not being in a power saving mode.

[0156] As one embodiment, the power state of the first node includes: the first node is overheating, or the first node is not overheating.

[0157] As an example, the execution status of the process corresponding to the first parameter set includes: the process corresponding to the first parameter set is being executed, or the process corresponding to the first parameter set is being abandoned.

[0158] As an example, the execution state of the process corresponding to the first parameter set includes: the process corresponding to the first parameter set is executed, or the process corresponding to the first parameter set is not executed.

[0159] As an example, the execution status of the process corresponding to the first parameter set includes: the process corresponding to the first parameter set is being executed, the process corresponding to the first parameter set is being suspended, or the process corresponding to the first parameter set is being abandoned.

[0160] As an example, the priority value corresponding to the first parameter set is used to determine the execution status of the process corresponding to the first parameter set.

[0161] As an example, the remaining inference resources of the first node are used to determine the execution status of the process corresponding to the first parameter set.

[0162] As an example, the remaining inference resources of the first node satisfy the inference resources required by the process corresponding to the first parameter set, and the priority value corresponding to the first parameter set is the lowest priority value in the parameter set configured by the first node, and the process corresponding to the first parameter set is executed.

[0163] As an embodiment, the first node is further configured with at least one target parameter set, wherein the remaining inference resources of the first node do not satisfy the sum of the inference resources required by the process corresponding to the first parameter set and the inference resources required by the process corresponding to the target parameter set, and the remaining inference resources of the first node satisfy the inference resources required by either the process corresponding to the first parameter set or the process corresponding to the target parameter set; when the priority value corresponding to the first parameter set is less than the priority value corresponding to the target parameter set, the process corresponding to the first parameter set is executed; when the priority value corresponding to the first parameter set is greater than the priority value corresponding to the target parameter set, the process corresponding to the target parameter set is executed, and the process corresponding to the first parameter set is not executed.

[0164] As an example, the process not being executed in this application includes: the first node not being required to execute the process.

[0165] As one example, the inference resources include the computing resources.

[0166] As one embodiment, the inference resources include the computing resources and the storage resources.

[0167] As one example, the inference resources include power resources.

[0168] As an example, the process corresponding to the first parameter set occupies a positive integer number of inference resources.

[0169] As an example, the process corresponding to the first parameter set occupies a positive integer number of computing resources.

[0170] As an example, the process corresponding to the first parameter set occupies M1 computing resources and M2 storage resources, where M1 and M2 are both positive integers.

[0171] As an example, the process corresponding to the first parameter set occupies M1 computing resources, M2 storage resources, and M3 power resources, where M1, M2, and M3 are all positive integers.

[0172] As one embodiment, the inference resource includes a CPU (Central Processing Unit).

[0173] As one example, the inference resource includes a GPU (Graphics Processing Unit).

[0174] As an example, the inference resource includes one NPU in an NPU (Neural Network Processing Unit) Set.

[0175] As one example, the inference resource includes an AI-PU (AI Processing Unit).

[0176] As one example, the inference resource includes an APU (AI Processing Unit).

[0177] As one embodiment, the inference resource includes an arithmetic and logic unit (ALU).

[0178] As one embodiment, the inference resource includes a Special Function Unit (SFU).

[0179] As an example, the inference resource is used for storage.

[0180] As an example, the inference resource is used for reading and writing.

[0181] As one example, the inference resource is used for data interaction.

[0182] As one embodiment, the inference resource includes a storage unit.

[0183] As one example, the inference resources include bandwidth resources.

[0184] As one example, the inference resources include read and write resources.

[0185] As one example, the inference resources include cache resources.

[0186] As one example, the inference resources include data interaction resources.

[0187] As an example, the structure of the AI / ML model corresponding to the first parameter set is one of the following: Transformer structure, RNN (Recurrent Neural Network) structure, or CNN (Conventional Neural Networks) structure.

[0188] As an example, the structure of the AI / ML model corresponding to the first parameter set is the structure of a hybrid model composed of multiple models, including at least one of the Transformer structure, RNN structure, or CNN structure.

[0189] Example 2

[0190] Example 2 illustrates a schematic diagram of a network architecture according to an embodiment of this application, as shown in Figure 2.

[0191] Figure 2 illustrates network architecture 200. Network architecture 200 is the network architecture for LTE (Long-Term Evolution), LTE-A (Long-Term Evolution Advanced), 5G systems, 5G-Advanced, and future 6G systems. The network architectures for LTE, LTE-A, 5G systems, 5G-Advanced, and future 6G systems are referred to as EPS (Evolved Packet System). The 5G NR or LTE network architecture may be referred to as 5GS (5G System) / EPS or some other suitable terminology; the 6G network architecture may be referred to as 6GS (6G System) / EPS or some other suitable terminology.

[0192] The network architecture 200 may include one or more UEs 201, a RAN (Radio Access Network) 202, a core network 210, an HSS (Home Subscriber Server) / UDM (Unified Data Management) 220, and an Internet service 230. The network architecture 200 may interconnect with other access networks, but these entities / interfaces are not shown for simplicity.

[0193] As shown in Figure 2, the network architecture 200 provides packet switching services; however, those skilled in the art will readily understand that the various concepts presented throughout this application can be extended to networks providing circuit-switched services or other cellular networks. The RAN 202 includes Node B 203 and other nodes 204. Node B 203 provides user and control plane protocol termination toward the UE 201. Node B 203 may be connected to other nodes 204 via an Xn interface (e.g., backhaul). Node B 203 may also be referred to as eNB (evolved Node B), gNB, base station, base transceiver station, radio base station, radio transceiver, transceiver function, Basic Service Set (BSS), Extended Service Set (ESS), TRP (Transmitter Receiver Point), or some other suitable term. Node B 203 provides UE 201 with an access point to the core network 210; the core network 210 is a 5GC (5G Core network) / EPC (Evolved Packet Core), or the core network 210 is a 6GC (6G Core network). Examples of the UE 201 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, GPS devices, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, drones, aircraft, narrowband physical network devices, machine-type communication devices, land vehicles, automobiles, wearable devices, or any other similar functional devices. Those skilled in the art may also refer to the UE 201 as a mobile station, subscriber station, mobile unit, subscriber unit, radio unit, remote unit, mobile device, radio device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, radio terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term. The Node B 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. The Internet service 230 includes carrier-compliant Internet protocol services, specifically including the Internet, intranet, IMS (IP Multimedia Subsystem), and packet-switched streaming services.

[0194] As an example, the first node in this application includes the UE 201.

[0195] As an example, the second node in this application includes node B 203.

[0196] As an example, node B 203 is a macrocell base station.

[0197] As an example, node B 203 is a microcell base station.

[0198] As an example, node B 203 is a pico cell base station.

[0199] As an example, node B 203 is a femtocell.

[0200] As an example, node B 203 is a base station device that supports large latency differences.

[0201] As an example, node B 203 is a flight platform device.

[0202] As an example, node B 203 is a satellite device.

[0203] As one embodiment, the node B 203 is a test device (e.g., a transceiver device simulating part of the functions of a base station, a signaling tester).

[0204] As an example, the UE 201 includes a mobile phone.

[0205] As an example, the UE 201 is a vehicle including a car.

[0206] As an example, the wireless link from the UE 201 to the node B 203 is an uplink, which is used to perform uplink transmissions.

[0207] As an example, the radio link from the node B 203 to the UE 201 is a downlink, which is used to perform downlink transmissions.

[0208] As an example, the wireless link between the node B 203 and the UE 201 includes a cellular link.

[0209] As an example, the node B 203 and the UE 201 are connected via the Uu air interface.

[0210] As an example, the node B 203 supports the deployment of network-side (NW-side) AI / ML models.

[0211] As an example, the UE 201 supports the deployment of UE-side AI / ML models.

[0212] As an example, the UE 201 supports a 5G system.

[0213] As an example, the node B 203 supports a 5G system.

[0214] As an example, the UE 201 supports at least a 6G system.

[0215] As an example, the node B 203 supports at least a 6G system.

[0216] As an example, the sender of the first information block in this application includes the node B 203.

[0217] As an example, the recipient of the first information block in this application includes the UE 201.

[0218] As an example, the sender of the first signal in this application includes the UE 201.

[0219] As an example, the receiver of the first signal in this application includes the node B 203.

[0220] As an example, the sender of the second information block in this application includes the node B 203.

[0221] As an example, the recipient of the second information block in this application includes the UE 201.

[0222] Example 3

[0223] 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.

[0224] Figure 3 is a schematic diagram illustrating an embodiment of the wireless protocol architecture for the user plane 350 and the control plane 300. Figure 3 shows the wireless protocol architecture for the control plane 300 between a first communication node device (UE or RSU in V2X, on-board equipment or on-board communication module) and a second node device (gNB, RSU in UE or V2X, on-board equipment or on-board communication module), or between two UEs, using three layers: Layer 1 (L1), Layer 2 (L2), and Layer 3 (L3). L1 is the lowest layer and implements various PHY (Physical layer) signal processing functions. L1 will be referred to herein as PHY 301. L2305 is above PHY 301 and is responsible for the link between the first node device and the second node device, or between two UEs, through PHY 301. L2305 includes a MAC (Medium Access Control) sublayer 302, an RLC (Radio Link Control) sublayer 303, and a PDCP (Packet Data Convergence Protocol) sublayer 304, which terminate at the second node device. The PDCP sublayer 304 provides multiplexing between different radio bearers and logical channels. 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 (Hybrid Automatic Repeat reQuest). 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 between the first communication node devices. Furthermore, the MAC sublayer 302 handles HARQ operations. The RRC (Radio Resource Control) sublayer 306 in L3 of the control plane 300 is responsible for obtaining radio resources (i.e., radio bearers) and using RRC signaling between the second communication node device and the first communication node device to configure the lower layer.The wireless protocol architecture of user plane 350 includes Layer 1 (L1) and Layer 2 (L2). The wireless protocol architecture for the first and second communication node devices in user plane 350 is largely the same as the corresponding layers and sublayers in control plane 300 for Physical Layer 351, PDCP sublayer 354 in L2355, RLC sublayer 353 in L2355, and MAC sublayer 352 in L2355. However, PDCP sublayer 354 also provides header compression for upper-layer packets to reduce wireless transmission overhead. L2355 in user plane 350 also includes SDAP (Service Data Adaptation Protocol) sublayer 356. SDAP sublayer 356 is responsible for mapping between QoS (Quality of Service) streams and Data Radio Bearer (DRB) to support service diversity. Although not illustrated, the first communication node device may have several upper layers above L2355, including a network layer (e.g., IP (Internet Protocol) layer) terminating at the P-GW on the network side and an application layer terminating at the other end of the connection (e.g., remote UE, server, etc.).

[0225] As an example, the wireless protocol architecture in Figure 3 is applicable to the first node in this application.

[0226] As an example, the wireless protocol architecture in Figure 3 is applicable to the second node in this application.

[0227] As an example, the higher layer mentioned in this application refers to the layer above the physical layer.

[0228] As an example, in this application, the first information block is generated in MAC302 or MAC352.

[0229] As an example, in this application, the first information block is generated in the RRC306.

[0230] As an example, in this application, the first information block is generated in the core network above the RRC306.

[0231] As an example, in this application, the first signal is generated in the PHY301 or PHY351.

[0232] As an example, in this application, the first signal is generated by MAC302 or MAC352.

[0233] As an example, in this application, the first signal is generated in the RRC306.

[0234] As an example, in this application, the second information block is generated in MAC302 or MAC352.

[0235] As an example, the second information block in this application is generated in the RRC306.

[0236] As an example, in this application, the second information block is generated in the core network above the RRC306.

[0237] Example 4

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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 functionality. In the DL, the controller / processor 475 provides header compression, encryption, packet segmentation and reordering, multiplexing between logical and transport channels, and radio resource allocation to the second communication device 450 based on various priority metrics. The controller / processor 475 is also responsible for HARQ 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 (i.e., the physical layer). Transmit processor 416 performs encoding and interleaving to facilitate forward error correction (FEC) at the second communication device 450, and mapping of signal clusters based on various modulation schemes (e.g., Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), 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 streams. 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.

[0242] 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 L1 signal processing functions. 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 by the first communication device 410 over the physical channel. The upper-layer data and control signals are then provided to the controller / processor 459. The controller / processor 459 implements L2 functionality. 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, 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 L2. Various control signals may also be provided to L3 for L3 processing. The controller / processor 459 is also responsible for error detection using Acknowledgement (ACK) and / or Negative Acknowledgement (NACK) protocols to support HARQ operation.

[0243] In the transmission from the second communication device 450 to the first communication device 410, at the second communication device 450, a data source 467 is used to provide upper-layer data packets to the controller / processor 459. The data source 467 represents all protocol layers above L2. Similar to the transmission 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 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.

[0244] 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 function. The controller / processor 475 implements the L2 function. The controller / processor 475 may be associated with a memory 476 storing 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.

[0245] 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 at least first receives a first information block, the first information block configuring a first parameter set for inference; the priority value corresponding to the first parameter set depends on the power state of the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0246] As one embodiment, the second communication device 450 includes: a memory storing a computer-readable instruction program that produces actions when executed by at least one processor, the actions including: receiving a first information block, the first information block configuring a first parameter set for inference.

[0247] 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 at least first transmits a first information block, the first information block configuring a first parameter set for inference; the priority value corresponding to the first parameter set depends on the power state of a first node, the sender of the first information block includes the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0248] As one embodiment, the first communication device 410 includes: a memory storing a computer-readable instruction program that produces an action when executed by at least one processor, the action including: sending a first information block configured with a first parameter set for inference.

[0249] As an example, the first node in this application includes the second communication device 450.

[0250] As an example, the second node in this application includes the first communication device 410.

[0251] As an example, at least one of {the antenna 420, the transmitter 418, the transmitter processor 416, the multi-antenna transmitter processor 471, the controller / processor 475, and the memory 476} is used to transmit the first information block; at least one of {the antenna 452, the receiver 454, the receiver processor 456, the multi-antenna receiver processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the first information block.

[0252] 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 a first signal; 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 signal.

[0253] As an example, at least one of {the antenna 420, the transmitter 418, the transmitter processor 416, the multi-antenna transmitter processor 471, the controller / processor 475, and the memory 476} is used to transmit the second information block; at least one of {the antenna 452, the receiver 454, the receiver processor 456, the multi-antenna receiver processor 458, the controller / processor 459, the memory 460, and the data source 467} is used to receive the second information block.

[0254] Example 5

[0255] 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 first node U1 and the second node N2 communicate via a wireless link.

[0256] For the first node U1, the first information block is received in step S510.

[0257] For the second node N2, the first information block is sent in step S520.

[0258] In embodiment 5, the first information block is configured with a first parameter set, which is used for inference; the priority value corresponding to the first parameter set depends on the power state of the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0259] As an example, the first node U1 is the first node in this application.

[0260] As an example, the second node N2 is the second node in this application.

[0261] As one embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between the base station equipment and the user equipment.

[0262] As one embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between the relay node device and the user equipment.

[0263] As one embodiment, the air interface between the second node N2 and the first node U1 includes a wireless interface between user equipment and user equipment.

[0264] As one example, the second node N2 and the first node U1 communicate via the Uu interface.

[0265] As one example, the second node N2 is the maintenance base station of the serving cell of the first node U1.

[0266] Typically, the first parameter set is associated with an AI / ML model, a function, or an entity.

[0267] As an example, the first parameter set is associated with an associated ID.

[0268] As an example, the first parameter set is associated with a model ID, which corresponds to an AI / ML model.

[0269] As an example, the first parameter set is associated with a Functionality ID, which corresponds to a function.

[0270] As an example, the first parameter set is associated with an Entity ID, which corresponds to an entity.

[0271] As an example, the first parameter set configures at least one AI / ML model.

[0272] As an example, the first parameter set configures at least one function.

[0273] As an example, the first parameter set configures at least one entity.

[0274] Typically, the process corresponding to the first parameter set includes at least one of model training, data collection, inference, or performance monitoring.

[0275] As an example, the process corresponding to the first parameter set includes the model training.

[0276] As an example, the process corresponding to the first parameter set includes the data collection.

[0277] As an example, the process corresponding to the first parameter set includes the inference process.

[0278] As an example, the process corresponding to the first parameter set includes the performance monitoring.

[0279] As an example, the process corresponding to the first parameter set includes at least two of the following: model training, data collection, inference, or performance monitoring.

[0280] Typically, the priority value corresponding to the first parameter set is one of K1 priority values, and the power state of the first node is used to determine the priority value corresponding to the first parameter set from the K1 priority values, where K1 is a positive integer greater than 1.

[0281] As an example, the K1 priority values ​​are predefined.

[0282] As an example, the K1 priority values ​​are configured.

[0283] As an example, the K1 priority values ​​each depend on K1 coefficients, and the power state of the first node is used to determine the coefficients on which the priority values ​​corresponding to the first parameter set depend from the K1 coefficients.

[0284] As an example, the priority value corresponding to the first parameter set is linearly related to a first coefficient and a second coefficient, wherein the first coefficient depends on the power state of the first node and the second coefficient depends on the characteristics of the first parameter set.

[0285] As a sub-implementation of this embodiment, the first coefficient is a non-negative integer.

[0286] As a sub-implementation of this embodiment, the first coefficient is an offset value.

[0287] As a sub-implementation of this embodiment, the second coefficient is a non-negative integer.

[0288] As a sub-implementation of this embodiment, the second coefficient is configured or predefined.

[0289] As a sub-implementation of this embodiment, the features of the first parameter set include at least one of the following:

[0290] - The reporting period corresponding to the first parameter set;

[0291] - The content reported corresponding to the first parameter set;

[0292] - The number of cells corresponding to the first parameter set.

[0293] As a sub-implementation of this embodiment, the features of the first parameter set include: the execution cycle of the process corresponding to the first parameter set.

[0294] Typically, the power state of the first node includes the first node being in a first power state; when the first node is in the first power state, the priority value corresponding to the first parameter set is set to a predefined value.

[0295] As an example, the first power state includes a low power loss state.

[0296] As one embodiment, the first power state includes: the remaining power value is less than a first threshold, where the first threshold is fixed or predefined.

[0297] As an example, the first power state includes a power saving state.

[0298] As an example, the power in this application depends on the power of the battery of the first node.

[0299] As an example, the power in this application is power other than the transmission power.

[0300] As an example, the power in this application depends on the energy of the battery of the first node.

[0301] As an example, setting the priority value corresponding to the first parameter set to a predefined value includes setting the priority value corresponding to the first parameter set to positive infinity.

[0302] As an example, setting the priority value corresponding to the first parameter set to a predefined value includes setting the priority value corresponding to the first parameter set to the value corresponding to the lowest priority.

[0303] As an example, the associated ID in this application is a non-negative integer.

[0304] As an example, the association ID in this application is associated with at least one RS (Reference Signal) resource set.

[0305] As an example, the associated ID in this application is associated with at least one CSI (Channel State Information) report configuration.

[0306] As an example, the ID mentioned in this application refers to IDentify, proof.

[0307] As an example, the ID mentioned in this application refers to: IDentification, identity verification.

[0308] As an example, the ID mentioned in this application refers to: IDentity, identity, or identifier.

[0309] As an example, the ID mentioned in this application refers to: Identifier, identifier.

[0310] As an example, the ID mentioned in this application refers to: InDex, index.

[0311] As an example, the ID mentioned in this application refers to: InDicator, indicator.

[0312] Example 6

[0313] Example 6 illustrates a flowchart of a first signal transmission according to an embodiment of this application, as shown in Figure 6. In Figure 6, the first node U3 and the second node N4 communicate via a wireless link.

[0314] For the first node U3, a first signal is sent in step S610.

[0315] For the second node N4, the first signal is received in step S620.

[0316] In Example 6, the first signal indicates the power state of the first node.

[0317] As an example, the first signal is transmitted via UCI (Uplink Control Information).

[0318] As an example, the physical layer channel occupied by the first signal includes PUCCH (Physical Uplink Control Channel).

[0319] As an example, the physical layer channel occupied by the first signal includes PUSCH (Physical Uplink Shared Channel).

[0320] As an example, the first signal is transmitted via MAC CE.

[0321] As an example, the first signal is transmitted via RRC signaling.

[0322] As an example, the first signal is transmitted via higher-layer signaling.

[0323] As one embodiment, the first signal is transmitted via higher-layer signaling.

[0324] As an example, step S610 is located after step S510 in Example 5.

[0325] As an example, step S620 is located after step S520 in Example 5.

[0326] Example 7

[0327] Example 7 illustrates a flowchart of the transmission of a second information block according to an embodiment of this application, as shown in Figure 7. In Figure 7, the first node U5 and the second node N6 communicate via a wireless link.

[0328] For the first node U5, the second information block is received in step S710.

[0329] For the second node N6, the second information block is sent in step S720.

[0330] In embodiment 7, the second information block configures a second parameter set, which is used for inference; the comparison between the priority value corresponding to the first parameter set and the priority value corresponding to the second parameter set is used to determine the execution state of the process corresponding to the first parameter set and the execution state of the process corresponding to the second parameter set.

[0331] As one embodiment, the second information block includes RRC signaling.

[0332] As one embodiment, the second information block includes one or more RRC IEs.

[0333] As one example, the second information block includes one or more fields in an RRC IE.

[0334] As one embodiment, the second information block indicates the second parameter set.

[0335] As an example, the second information block explicitly indicates the second parameter set.

[0336] As an example, the second information block implicitly indicates the second parameter set.

[0337] As one embodiment, the second information block includes one or more CSI-ReportConfigs.

[0338] As one example, the second information block is associated with one or more CSI-ReportConfig IEs.

[0339] As one embodiment, the second information block includes one or more CSI-MeasConfigs.

[0340] As one example, the second information block is associated with one or more CSI-MeasConfig IEs.

[0341] As one embodiment, the second information block includes one or more CSI-ResourceConfigs.

[0342] As one example, the second information block is associated with one or more CSI-ResourceConfig IEs.

[0343] As an example, the name of the RRC signaling used to configure the second information block includes CSI.

[0344] As an example, the name of the RRC signaling used to configure the second information block includes CSI-RS.

[0345] As an example, the name of the RRC signaling used to configure the second information block includes Report.

[0346] As an example, the name of the RRC signaling used to configure the second information block includes Config.

[0347] As an example, the second information block indicates at least one inference configuration.

[0348] As one example, the second parameter set includes configuration parameters for inference.

[0349] As one embodiment, the second parameter set includes a configuration of reference signal resources used for inference.

[0350] As an example, the reasoning includes reasoning based on AI / ML models.

[0351] As an example, the reasoning includes prediction.

[0352] As an example, the priority value corresponding to the second parameter set includes: the priority value of the AI / ML model associated with the second parameter set.

[0353] As an example, the priority value corresponding to the second parameter set includes: the priority value of the function associated with the second parameter set.

[0354] As an example, the priority value corresponding to the second parameter set includes: the priority value of the module associated with the second parameter set.

[0355] As an example, the priority value corresponding to the second parameter set includes: the priority value of the process associated with the second parameter set.

[0356] As an example, the priority value corresponding to the second parameter set includes: the priority value of the process associated with the second parameter set.

[0357] As an example, the priority value corresponding to the second parameter set includes: the reported priority value associated with the second parameter set.

[0358] As an example, the priority value corresponding to the second parameter set includes: the priority value of the inference computation associated with the second parameter set.

[0359] As an example, the priority value is a non-negative integer.

[0360] As an example, the priority value corresponding to the first parameter set is different from the priority value corresponding to the second parameter set.

[0361] As an example, the remaining inference resources of the first node do not satisfy the sum of the inference resources required by the process corresponding to the first parameter set and the process corresponding to the second parameter set, and the remaining inference resources of the first node satisfy the inference resources required by either the process corresponding to the first parameter set or the process corresponding to the second parameter set; when the priority value corresponding to the first parameter set is less than the priority value corresponding to the second parameter set, the process corresponding to the first parameter set is executed, and the process corresponding to the second parameter set is not executed; when the priority value corresponding to the first parameter set is greater than the priority value corresponding to the second parameter set, the process corresponding to the second parameter set is executed, and the process corresponding to the first parameter set is not executed.

[0362] As an example, step S710 is located after step S510 in Example 5.

[0363] As an example, step S720 is located after step S520 in Example 5.

[0364] As an example, step S710 is located before step S510 in Example 5.

[0365] As an example, step S720 is located before step S520 in Example 5.

[0366] Example 8

[0367] Example 8 illustrates a schematic diagram of power states according to an embodiment of this application, as shown in Figure 8. In Figure 8, the power state of the first node is the first power state among K1 power states, and the K1 power states correspond one-to-one with the K1 priority values. The first power state is used to determine the priority value corresponding to the first parameter set from the K1 priority values. Power states #1 to #K1 shown in the figure correspond to K1 power states, and priority values ​​#1 to #K1 shown in the figure correspond to K1 priority values.

[0368] As an example, the K1 power states are predefined.

[0369] As an example, the K1 power states correspond to K1 power levels, and the K1 power levels correspond to K1 remaining power values.

[0370] As an example, the K1 power states include: a high power consumption state and a low power consumption state.

[0371] As an example, the K1 power states include: high power consumption state, normal power consumption state, and low power consumption state.

[0372] As an example, the K1 power states include: the first node is in power saving, and the first node is not in power saving.

[0373] As one embodiment, the K1 power states include: the first node being overheated, and the first node not being overheated.

[0374] Example 9

[0375] Example 9 illustrates a schematic diagram of an inference resource according to an embodiment of this application, as shown in Figure 9. Figure 9, without limitation, lists two implementation methods of the inference resource. For method 1, one inference resource corresponds to one computing resource. The first node in this application includes a positive integer number of computing resources, the process corresponding to the first parameter set occupies a positive integer number of computing resources, and the process corresponding to the second parameter set occupies a positive integer number of computing resources. For method 2, the inference resource includes computing resources and storage resources. The first node in this application includes a positive integer number of computing resources and a positive integer number of storage resources. The process corresponding to the first parameter set occupies a positive integer number of computing resources and a positive integer number of storage resources, and the process corresponding to the second parameter set occupies a positive integer number of computing resources and a positive integer number of storage resources.

[0376] As an example, for method 1, the meaning of the remaining inference resources of the first node satisfying the inference resources required by the process corresponding to the given parameter set includes: the amount of computing power resources remaining in the first node is not less than the amount of computing power resources required by the process corresponding to the given parameter set.

[0377] As an example, for method 1, the meaning that the remaining inference resources of the first node do not meet the inference resources required by the process corresponding to the given parameter set includes: the amount of computing power resources remaining in the first node is less than the amount of computing power resources required by the process corresponding to the given parameter set.

[0378] As a sub-implementation of the above two embodiments, the given parameter set is the first parameter set in this application.

[0379] As a sub-implementation of the above two embodiments, the given parameter set is the second parameter set in this application.

[0380] As an example, for method 1, the meaning of the remaining inference resources of the first node satisfying the inference resources required by the multiple processes corresponding to the multiple parameter sets includes: the number of remaining computing resources of the first node is not less than the sum of the computing resources required by the multiple processes corresponding to the multiple parameter sets.

[0381] As an example, for method 1, the meaning that the remaining inference resources of the first node do not meet the inference resources required by the multiple processes corresponding to the multiple parameter sets includes: the amount of computing power resources remaining in the first node is less than the sum of the computing power resources required by the multiple processes corresponding to the multiple parameter sets.

[0382] As a sub-implementation of the above two embodiments, the plurality of parameter sets include the first parameter set and the second parameter set in this application.

[0383] As an example, for method 2, the meaning of the remaining inference resources of the first node satisfying the inference resources required by the process corresponding to the given parameter set includes: the number of remaining computing resources and the number of remaining storage resources of the first node are not less than the number of computing resources and the number of storage resources required by the process corresponding to the given parameter set, respectively.

[0384] As an example, for method 2, the meaning that the remaining inference resources of the first node do not meet the inference resources required by the process corresponding to the given parameter set includes: the number of remaining computing resources and the number of remaining storage resources of the first node are less than the number of computing resources and the number of storage resources required by the process corresponding to the given parameter set, respectively.

[0385] As a sub-implementation of the above two embodiments, the given parameter set is the first parameter set in this application.

[0386] As a sub-implementation of the above two embodiments, the given parameter set is the second parameter set in this application.

[0387] As an example, for method 2, the meaning of the remaining inference resources of the first node satisfying the inference resources required by the multiple processes corresponding to the multiple parameter sets includes: the number of remaining computing resources and the number of remaining storage resources of the first node are not less than the sum of the computing resources and the sum of the storage resources required by the multiple processes corresponding to the multiple parameter sets, respectively.

[0388] As an example, for method 2, the meaning that the remaining inference resources of the first node do not meet the inference resources required by the multiple processes corresponding to the multiple parameter sets includes: the number of remaining computing resources and the number of remaining storage resources of the first node are respectively less than the sum of the number of computing resources and the sum of the number of storage resources required by the multiple processes corresponding to the multiple parameter sets.

[0389] As a sub-implementation of the above two embodiments, the plurality of parameter sets include the first parameter set and the second parameter set in this application.

[0390] Example 10

[0391] Example 10 illustrates a schematic diagram of RAN domain AI / ML function deployment according to one embodiment of this application, as shown in Figure 10. In Figure 10, the gNB can be replaced with, for example, an eNB, or a network device such as a 6G base station.

[0392] In Example 10, the management of ML inference functions of multiple base stations is completed by the RAN domain management function 1002, that is, data interaction with the RAN domain MnS (Management Service) consumer / cross-domain management 1001 (as shown by the dashed arrow in Figure 10). The RAN domain ML training function 1003 is located in the RAN domain management function 1002; while the ML inference functions are located in the base stations, that is, the AI / ML inference function 1004 is located in gNB 1005, the AI / ML inference function 1006 is located in gNB 1007, and so on.

[0393] 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.

[0394] ML training functions 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 functions for MDA (Management Data Analytics) can be deployed in MDAF (Management Data Analytic Function); ML training for network data analytics can be deployed in NWDAF (Network Data Analytics Function), meaning the ML training function is an MTLF (Model Training Logical Function).

[0395] 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.

[0396] Similarly, ML testing capabilities can also be deployed in cross-domain management systems or domain-specific management systems.

[0397] 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 1001.

[0398] It should be noted that Embodiment 10 is merely a non-limiting implementation method; optionally, the ML training function of the RAN domain may also be deployed in the base station; or optionally, some base stations may deploy both the ML inference function and the ML training function of the RAN domain, while some base stations may only deploy the ML inference function.

[0399] As an example, one of the gNBs (or base stations) in Example 10 is the second node of this application.

[0400] Example 11

[0401] Example 11 illustrates a schematic diagram of the deployment of AI / ML functions in a UE according to one embodiment of this application, as shown in Figure 11. In Figure 11, the RAN domain ML training function 1104 is optional.

[0402] UE function 1103 is deployed in the first node of this application, and the UE function 1103 includes AI / ML inference function 1105; the AI / ML inference function 1105 uses an ML model (also called an AI model) for inference; an ML model is typically trained before being used for AI / ML inference.

[0403] As an example, the UE function 1103 includes a RAN domain ML training function 1104, 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.

[0404] 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 higher demands on the processing capabilities of the UE side.

[0405] Optionally, the UE function 1103 also includes a CN domain ML training function (not shown in Figure 11).

[0406] Optionally, the UE function 1103 also includes an AI / ML deployment function—not shown in Figure 11—for loading ML models and data.

[0407] 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.

[0408] As an example, the ML model and related metadata are loaded by the first node from a network device or a remote server.

[0409] Optionally, the UE function 1103 is an MnS producer that provides data to the CN domain MnF (Management Function) and / or the RAN domain MnF and / or the cross-domain management system 1101 for management or analysis (as shown by the double arrow 1102).

[0410] Optionally, the UE function 1103 is an MnS consumer that loads data from the CN domain MnF and / or RAN domain MnF and / or cross-domain management system 1101 for AI / ML-related management, such as managing data requests, ML model activation, and / or ML training (as shown by double arrow 1102).

[0411] As an example, the ML model is based on NN (Neural Networks).

[0412] As an example, the ML model is based on ANN (Artificial Neural Networks).

[0413] As an example, the ML model is based on CNN.

[0414] As an example, the ML model is based on the LLM (Large Language Model) architecture.

[0415] As an example, the ML model is based on the Transformer architecture.

[0416] As an example, the ML model is based on the GPT (Generative Pre-Trained) architecture.

[0417] As an example, the ML model is based on LSTM (Long Short-Term Memory network).

[0418] As an example, the ML model is based on MLP (MultiLayer Perceptron).

[0419] As an example, the ML model is based on GAN (Generative Adversarial Nets).

[0420] As an example, the ML model is based on a lightweight neural network.

[0421] As a sub-example of this embodiment, the lightweight neural network includes one or more of MobileNet, ShuffleNet, and SqueezeNet.

[0422] Example 12

[0423] Example 12 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 12. In Figure 12, the processing system based on artificial intelligence or machine learning includes a first processor, a second processor, a third processor, and a fourth processor.

[0424] In Example 12, the first processor sends a first dataset to the second processor and a second dataset to the third processor; the second processor generates a target first-class parameter set based on the first dataset, and sends the generated target first-class parameter set to the third processor; the third processor processes the second dataset using the target first-class parameter set to obtain a first-class output, optionally sending the first-class output to the fourth processor. In Figure 12, the first-class feedback and the second-class feedback are optional; the second processor includes ML training functionality; the third processor includes ML inference functionality.

[0425] As one embodiment, the fourth processor includes ML testing functionality.

[0426] As one embodiment, the fourth processor includes performance monitoring / evaluation of the ML model.

[0427] As an example, the third processor sends a first type of feedback to the second processor; the first type of feedback is used to trigger the recalculation or update of the target first type of parameter set, that is, to trigger ML initial training or ML retraining.

[0428] As one embodiment, the fourth processor sends a second type of feedback to the first processor; the second type of feedback is used to generate the first dataset or the second dataset, or the second type of feedback is used to trigger the sending of the first dataset or the sending of the second dataset.

[0429] As one embodiment, the first processor generates the first dataset and the second dataset based on the measurement of the reference signal.

[0430] As one embodiment, the third processor belongs to the first node, and the fourth processor belongs to the second node.

[0431] As an example, the third processor belongs to the first node.

[0432] As an example, the first dataset includes training data.

[0433] As one embodiment, the second processor is used to train an ML model, and the trained model is described by the target first class of parameter sets.

[0434] As an example, the second processor belongs to the first node; the above method avoids passing the first dataset to the second node.

[0435] As an example, the second processor belongs to the second node in this application; the above method supports joint training and optimizes system performance.

[0436] As an example, the second processor belongs to the core network; the above method supports network-wide joint training, further optimizing system performance.

[0437] As an example, the second dataset includes inference data.

[0438] As an example, the third processor constructs a model based on the target first type of parameter group, and then inputs the second dataset into the constructed model to obtain the first type of output.

[0439] As an example, the output of the third processor includes the performance parameters described in this application.

[0440] As an example, the third 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.

[0441] As an example, the first type of feedback is used to reflect the performance of the trained model; when the performance of the trained model fails to meet the requirements, the second processing opportunity will recalculate the target first type of parameter set.

[0442] 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.

[0443] 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 the pooling function, or parameters of the activation function.

[0444] 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.

[0445] As an example, the target first type of parameter group corresponds to the first parameter set in this application.

[0446] As an example, the target first type of parameter group corresponds to the second parameter set in this application.

[0447] Example 13

[0448] Example 13 illustrates a schematic diagram based on artificial intelligence or machine learning according to an embodiment of this application, as shown in Figure 13. In Figure 13, the first and second operations belong to a first stage, the third operation belongs to a second stage, the fourth operation belongs to a third stage, and the fifth operation belongs to a fourth stage; the arrowed lines indicate the sequence of the process.

[0449] As an example, the first operation includes AI / ML training, the second operation includes AI / ML testing, the third operation includes AI / ML emulation, the fourth operation includes AI / ML entity loading, and the fifth operation includes AI / ML inference.

[0450] As an example, the first stage includes a training phase, the second stage includes an emulation phase, the third stage includes a deployment phase, and the fourth stage includes an inference phase.

[0451] As an example, the first stage includes AI / ML model training.

[0452] As an example, the first stage includes AI / ML model training and AI / ML testing.

[0453] As an example, the AI / ML model training includes initial training and re-training of one or a group of AI / ML entities.

[0454] As an example, the training of the AI / ML model depends on training data.

[0455] As an example, the AI / ML model training includes AI / ML entity validation.

[0456] As an example, the AI / ML entity verification is used to evaluate the performance of the AI / ML entity.

[0457] As an example, the AI / ML entity verification relies on verification data.

[0458] As an example, if the AI / ML entity verification results do not meet expectations, the AI / ML model will be retrained.

[0459] As an example, the AI / ML testing includes testing the validated AI / ML entities to estimate the performance of the trained AI / ML model.

[0460] As an example, if the AI / ML test results meet expectations, the AI / ML entity proceeds to the next stage; otherwise, the AI / ML model will be retrained.

[0461] As an example, the AI / ML test relies on test data.

[0462] As one embodiment, the second stage includes AI / ML simulation, which performs AI / ML entity reasoning in a simulation environment.

[0463] As an example, the AI / ML simulation estimates the performance of AI / ML entity reasoning in a simulation environment before using AI / ML entities.

[0464] As one embodiment, the second stage is optional.

[0465] As an example, the third stage includes AI / ML entity loading, which is to obtain trained AI / ML entities to obtain the desired AI / ML inference function.

[0466] As an example, the third stage is optional.

[0467] As an example, the third stage is no longer needed when the training and inference functions are co-located.

[0468] As an example, the fourth stage includes AI / ML inference.

[0469] Example 14

[0470] Example 14 illustrates a structural block diagram of a processing apparatus for a first node according to an embodiment of this application, as shown in Figure 14. In Figure 14, the processing apparatus 1400 in the first node includes a first receiver 1401 and a first transmitter 1402.

[0471] The first receiver 1401 receives a first information block, the first information block is configured with a first parameter set, and the first parameter set is used for inference;

[0472] In Example 14, the priority value corresponding to the first parameter set depends on the power state of the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0473] As an example, the first transmitter 1402 transmits a first signal indicating the power state of the first node.

[0474] As an example, the first parameter set is associated with an AI / ML model, or the first parameter set is associated with a function, or the first parameter set is associated with an entity.

[0475] As an example, the process corresponding to the first parameter set includes at least one of model training, data collection, inference, or performance monitoring.

[0476] As an example, the priority value corresponding to the first parameter set is one of K1 priority values, and the power state of the first node is used to determine the priority value corresponding to the first parameter set from the K1 priority values, where K1 is a positive integer greater than 1.

[0477] As an example, the power state of the first node is the first power state among K1 power states, and the K1 power states correspond one-to-one with the K1 priority values. The first power state is used to determine the priority value corresponding to the first parameter set from the K1 priority values.

[0478] As an example, the power state of the first node includes the first node being in a first power state; when the first node is in the first power state, the priority value corresponding to the first parameter set is set to a predefined value.

[0479] As an example, the first receiver 1401 receives a second information block, the second information block is configured with a second parameter set, the second parameter set is used for inference; the comparison between the priority value corresponding to the first parameter set and the priority value corresponding to the second parameter set is used to determine the execution state of the process corresponding to the first parameter set and the execution state of the process corresponding to the second parameter set.

[0480] As an example, the first node 1400 is a user equipment.

[0481] As an example, the first node 1400 is a Handset.

[0482] As an example, the first node 1400 is a terminal.

[0483] As an example, the first receiver 1401 includes at least one of the following in embodiment 4: the antenna 452, the receiver 454, the receiver processor 456, the multi-antenna receiver processor 458, the controller / processor 459, the memory 460, and the data source 467.

[0484] As an example, the first transmitter 1402 includes at least one of the following in embodiment 4: the antenna 452, the transmitter 454, the transmission processor 468, the multi-antenna transmission processor 457, the controller / processor 459, the memory 460, and the data source 467.

[0485] Example 15

[0486] Example 15 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 15. In Figure 15, the processing apparatus 1500 in the second node includes a second transmitter 1501 and a second receiver 1502.

[0487] The second transmitter 1501 transmits a first information block, the first information block being configured with a first parameter set, the first parameter set being for inference;

[0488] In Example 15, the priority value corresponding to the first parameter set depends on the power state of the first node, and the sender of the first information block includes the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

[0489] As one embodiment, the second receiver 1502 receives a first signal indicating the power state of the first node.

[0490] As an example, the first parameter set is associated with an AI / ML model, or the first parameter set is associated with a function, or the first parameter set is associated with an entity.

[0491] As an example, the process corresponding to the first parameter set includes at least one of model training, data collection, inference, or performance monitoring.

[0492] As an example, the priority value corresponding to the first parameter set is one of K1 priority values, and the power state of the first node is used to determine the priority value corresponding to the first parameter set from the K1 priority values, where K1 is a positive integer greater than 1.

[0493] As an example, the power state of the first node is the first power state among K1 power states, and the K1 power states correspond one-to-one with the K1 priority values. The first power state is used to determine the priority value corresponding to the first parameter set from the K1 priority values.

[0494] As an example, the power state of the first node includes the first node being in a first power state; when the first node is in the first power state, the priority value corresponding to the first parameter set is set to a predefined value.

[0495] As an example, the second transmitter 1501 sends a second information block, the second information block is configured with a second parameter set, the second parameter set is for inference; the comparison between the priority value corresponding to the first parameter set and the priority value corresponding to the second parameter set is used to determine the execution state of the process corresponding to the first parameter set and the execution state of the process corresponding to the second parameter set.

[0496] As an example, the second node 1500 is a base station device.

[0497] As one embodiment, the second node 1500 is a user equipment.

[0498] As an example, the second node 1500 is a TRP.

[0499] As an example, the second transmitter 1501 includes at least one of the following in embodiment 4: the antenna 420, the transmitter 418, the transmission processor 416, the multi-antenna transmission processor 471, the controller / processor 475, and the memory 476.

[0500] As one embodiment, the second receiver 1502 includes at least one of the following in embodiment 4: the antenna 420, the receiver 418, the receiver processor 470, the multi-antenna receiver processor 472, the controller / processor 475, and the memory 476.

[0501] 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. Correspondingly, 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 cards, IoT terminals, RFID (Radio Frequency Identification) terminals, NB-IoT (Narrow Band Internet of Things) terminals, MTC (Machine Type Communication) terminals, eMTC (enhanced MTC) terminals, data cards, internet cards, vehicle-mounted communication equipment, low-cost mobile phones, low-cost tablets, and other wireless communication devices. The base station or system equipment in this application includes, but is not limited to, macrocell base stations, microcell base stations, small cell base stations, home base stations, relay base stations, eNB (evolved Node B), gNB, TRP, GNSS (Global Navigation Satellite System), relay satellites, satellite base stations, airborne base stations, RSUs, unmanned aerial vehicles, and test equipment, such as transceivers or signaling testers that simulate some functions of a base station, and other wireless communication equipment.

[0502] 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 for inference in wireless communication, characterized in that... include: A first receiver receives a first information block, the first information block is configured with a first parameter set, the first parameter set is for inference; Wherein, the priority value corresponding to the first parameter set depends on the power state of the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

2. The first node according to claim 1, characterized in that... include: A first transmitter sends a first signal indicating the power status of the first node.

3. The first node according to claim 1 or 2, characterized in that, The first parameter set is associated with an AI / ML model, or the first parameter set is associated with a function, or the first parameter set is associated with an entity.

4. The first node according to any one of claims 1 to 3, characterized in that, The process corresponding to the first parameter set includes at least one of model training, data collection, inference, or performance monitoring.

5. The first node according to any one of claims 1 to 4, characterized in that, The priority value corresponding to the first parameter set is one of K1 priority values. The power state of the first node is used to determine the priority value corresponding to the first parameter set from the K1 priority values, where K1 is a positive integer greater than 1.

6. The first node according to any one of claims 1 to 5, characterized in that, The power state of the first node includes the first node being in a first power state; when the first node is in the first power state, the priority value corresponding to the first parameter set is set to a predefined value.

7. The first node according to any one of claims 1 to 6, characterized in that... include: The first receiver receives a second information block, the second information block is configured with a second parameter set, and the second parameter set is used for inference; The comparison between the priority value corresponding to the first parameter set and the priority value corresponding to the second parameter set is used to determine the execution state of the process corresponding to the first parameter set and the execution state of the process corresponding to the second parameter set.

8. A second node used for inference in wireless communication, characterized in that, include: The second transmitter sends a first information block, which is configured with a first parameter set for inference. Wherein, the priority value corresponding to the first parameter set depends on the power state of the first node, and the sender of the first information block includes the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

9. A method for inference in a first node used in wireless communication, characterized in that, include: Receive a first information block, the first information block is configured with a first parameter set, the first parameter set is for inference; Wherein, the priority value corresponding to the first parameter set depends on the power state of the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

10. A method for inference in a second node used in wireless communication, characterized in that, include: Send a first information block, the first information block is configured with a first parameter set, the first parameter set is for inference; Wherein, the priority value corresponding to the first parameter set depends on the power state of the first node, and the sender of the first information block includes the first node; the execution state of the process corresponding to the first parameter set depends on the priority value corresponding to the first parameter set and the remaining inference resources of the first node; the inference resources include at least the former of computing resources or storage resources.

Images