Access control method, device, and apparatus for ai serving cell, storage medium, and program product

Abstract

The present application relates to an access control method, device, and apparatus for an AI serving cell, a storage medium, and a program product. The method comprises: a terminal device receiving artificial intelligence (AI) capability information of a cell sent by a network device; the terminal device determining, according to the AI capability information of the cell, a target cell supporting an AI service requested by the terminal device; and the terminal device accessing or reselecting to the target cell.

Description

AI-enabled community access control methods, equipment, devices, storage media, and program products Cross-references

[0001] This application incorporates Chinese Patent Application No. 2025101244213, filed on January 26, 2025, entitled “Access Control Method, Device, Apparatus, Storage Medium and Program Product for AI Service Cells,” which is incorporated herein by reference in its entirety. Technical Field

[0002] This application relates to the field of communication technology, and in particular to an access control method, device, apparatus, storage medium, and program product for an AI service cell. Background Technology

[0003] Currently, the convergence of Artificial Intelligence (AI) and communications is one of the typical use cases of 6G. 6G networks will support the direct provision of AI services such as intelligence and computing to terminal devices, support the use of basic capabilities such as AI training, inference, and computing resources provided by the network side, improve the resource reuse efficiency of edge networks, and also support the joint management and scheduling of communication and AI resources to improve service performance.

[0004] In related technologies, in the integration of AI and communication, in order to ensure sufficient network-side control and management, terminal devices need to be able to instruct the network side about the AI ​​models and related AI functions supported by the terminal devices, so that the network side can execute relevant decisions on AI functions, such as activating or deactivating, or converting AI functions or models.

[0005] However, when providing AI services over the network, simply having the terminal device indicate the AI ​​models and related AI functions it supports cannot guarantee that the terminal device requesting the AI ​​service will select a suitable cell for providing the AI ​​service during cell access or cell reselection. Summary of the Invention

[0006] Based on this, this application provides an access control method, device, apparatus, storage medium, and program product for an AI service cell.

[0007] Firstly, this application provides an access control method for an AI-serving cell. Applied to a terminal device, it includes:

[0008] The terminal device receives AI capability information of the cell sent by the network device;

[0009] The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell.

[0010] The terminal device accesses or reselects to the target cell.

[0011] Secondly, this application provides an access control method for an AI-serving cell. Applied to network equipment, it includes:

[0012] The network device sends the cell's AI capability information to the terminal device;

[0013] The network device receives an access request for a target cell sent by the terminal device. The target cell is a cell that supports the AI ​​service requested by the terminal device, and the target cell is determined based on the AI ​​capability information of the cell.

[0014] The network device connects or reselects the terminal device to the target cell.

[0015] Thirdly, this application provides an access control device for an AI service cell, applied to a terminal device, including a memory, a transceiver, and a processor:

[0016] A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations:

[0017] The transceiver receives information about the cell's artificial intelligence (AI) capabilities from network devices.

[0018] Based on the AI ​​capability information of the cell, determine the target cell that supports the AI ​​service requested by the terminal device;

[0019] Access or reselect to the target cell.

[0020] Fourthly, this application provides an access device for an AI service cell, applied to network equipment, including a memory, a transceiver, and a processor:

[0021] A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations:

[0022] The transceiver sends the cell's AI capability information to the terminal device.

[0023] The transceiver receives an access request from the target cell sent by the terminal device. The target cell is a cell that supports the AI ​​service requested by the terminal device, and the target cell is determined based on the AI ​​capability information of the cell.

[0024] The terminal device is connected to or reselected to the target cell.

[0025] Fifthly, this application provides an access control device for an AI service cell, applied to a terminal device, comprising:

[0026] The first receiving module is used to receive the artificial intelligence (AI) capability information of the cell sent by the network device;

[0027] The first processing module is used for the terminal device to determine the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell; and to access or reselect the target cell.

[0028] Sixthly, this application provides an access control device for an AI-serving cell, applied to network equipment, comprising:

[0029] The first sending module is used to send the cell's AI capability information to the terminal device;

[0030] The second receiving module is used to receive the access request of the target cell sent by the terminal device. The target cell is a cell that supports the AI ​​service requested by the terminal device. The target cell is determined based on the AI ​​capability information of the cell.

[0031] The second processing module is used to connect or reselect the terminal device to the target cell.

[0032] Seventhly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the access control method for the AI ​​serving cell described in the first or second aspect above.

[0033] Eighthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the access control method for the AI ​​serving cell described in the first or second aspect above.

[0034] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0035] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the embodiments described below. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0036] Figure 1 is an application scenario diagram of an access control method for an AI-serving cell provided in an embodiment of this application;

[0037] Figure 2 is a signaling interaction diagram of an access control method for an AI serving cell provided in an embodiment of this application;

[0038] Figure 3 is a signaling interaction diagram of another AI service cell access control method provided in an embodiment of this application;

[0039] Figure 4 is a signaling interaction diagram of another AI service cell access control method provided in an embodiment of this application;

[0040] Figure 5 is a signaling interaction diagram of another AI service cell access control method provided in an embodiment of this application;

[0041] Figure 6 is a signaling interaction diagram of another AI service cell access control method provided in an embodiment of this application;

[0042] Figure 7 is a schematic diagram of the adjustment of the split points of a distributed model or federated learning model provided in an embodiment of this application;

[0043] Figure 8 is a schematic diagram of adjusting a collaborative set for AI training or inference provided in an embodiment of this application;

[0044] Figure 9 is a signaling interaction diagram of another AI service cell access control method provided in an embodiment of this application;

[0045] Figure 10 is a signaling interaction diagram of another AI service cell access control method provided in an embodiment of this application;

[0046] Figure 11 is a schematic diagram of adjusting the data transmission bit width of a model corresponding to an AI service provided in an embodiment of this application;

[0047] Figure 12 is a signaling interaction diagram of another AI service cell access control method provided in an embodiment of this application;

[0048] Figure 13 is a signaling interaction diagram of another AI service cell access control method provided in an embodiment of this application;

[0049] Figure 14 is a structural block diagram of an access control device for an AI service cell provided in an embodiment of this application;

[0050] Figure 15 is a structural block diagram of another AI service cell access control device provided in an embodiment of this application;

[0051] Figure 16 is a structural block diagram of another AI service cell access control device provided in an embodiment of this application;

[0052] Figure 17 is a structural block diagram of another AI service cell access control device provided in an embodiment of this application. Detailed Implementation

[0053] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0055] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0056] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0057] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0058] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0059] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0060] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0061] The AI ​​service cell access control method, device, apparatus, storage medium, and program product provided in this application embodiment can enable the selection of a suitable cell providing AI services during cell access or reselection.

[0062] The method and apparatus are based on the same concept of the application. Since the methods and apparatus solve problems in similar ways, the implementation of the apparatus and methods can refer to each other, and the repeated parts will not be described again.

[0063] The relevant technologies will be explained below.

[0064] Currently, the convergence of AI and communications is one of the typical use cases of 6G. With the development of 6G technology, 6G will become a distributed, efficient, energy-saving, and secure artificial intelligence service platform, thereby providing an environment for promoting AI application innovation, deployment, and expansion.

[0065] The integration of AI and communication can be seen in the fact that 6G networks will support the direct provision of AI services such as intelligence and computing to terminal devices, support the use of basic capabilities such as AI training, inference and computing resources provided by the network side, improve the resource reuse efficiency of edge networks, and also support the improvement of service performance through the joint management and scheduling of communication and AI resources.

[0066] In related technologies, the integration of AI and communication mainly focuses on using AI technology to improve the performance, efficiency, scalability and intelligence of networks. For example, AI algorithms are used to replace traditional communication algorithms, and AI models are adjusted for specific use cases based on special scenarios, locations, configurations, deployments and other factors.

[0067] In the convergence of AI and communication, to ensure sufficient network-side control and management, terminal devices need to be able to instruct the network side on the AI ​​models and related AI functions they support. This allows the network side to execute relevant decisions regarding AI functions, such as activating or deactivating, or converting AI functions or models. Furthermore, terminal devices can also report the availability status of at least one AI model and AI function to the network side; alternatively, they can report whether at least one AI model and AI function is available in the current context.

[0068] However, when providing AI services over the network, simply having the terminal device indicate the AI ​​models and related functions it supports cannot guarantee that the requesting terminal device will select a suitable cell for providing AI services during cell access or reselection. Furthermore, in related technologies, the network side only supports obtaining AI capability information from the terminal device via unicast to allow the AI ​​model to adjust according to specific scenarios, locations, configurations, deployments, and other factors. However, it cannot yet guide the scheduling of more granular resource information interactions. For example, during distributed inference, it is not yet possible to dynamically control and schedule related elements in real time based on information such as the terminal device's computing power, load, and power consumption.

[0069] To address the aforementioned issues, embodiments of this application provide an access control method, device, apparatus, storage medium, and program product for AI-enabled cells. The network device sends AI capability information of the cell to the terminal device, enabling the terminal device to select a target cell by referring to the AI ​​capability information of the cell when accessing or reselecting a cell. This allows the terminal device to select a suitable cell that provides AI services when accessing or reselecting a cell.

[0070] The following describes the application scenarios of the access control method for AI-enabled cell provided in this application.

[0071] Figure 1 illustrates an application scenario of an access control method for an AI service cell provided in this embodiment of the application. As shown in Figure 1, communication occurs between the terminal device and the network device. The network device can send AI capability information of the cell to the terminal device. Subsequently, the terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell. Finally, the terminal device accesses or reselects the target cell.

[0072] The terminal device involved in the embodiments of this application can be a device that provides at least one of voice and data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem. The name of the terminal device may differ in different systems; for example, in a 5G system, the terminal device can be called User Equipment (UE). The wireless terminal device can be a USB storage device, other personal computer memory devices, and a dongle. It can also communicate with one or more core networks (CNs) via a Radio Access Network (RAN). The wireless terminal device can be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device. For example, it can be a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device that exchanges at least one of voice and data with the radio access network. Examples of such devices include Personal Communication Service (PCS) telephones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs), personal computers, tablets, and Machine-type Communication (MTC) terminal devices. Wireless terminal devices can also be referred to as systems, subscriber units, subscriber stations, mobile stations, mobile devices, remote stations, access points, remote terminals, access terminals, user terminals, user agents, user devices, and wireless access devices and routers / modems that meet the limitations of this definition, but are not limited to these in the embodiments of this application.

[0073] The network device involved in the embodiments of this application can be a base station, which may include multiple cells providing services to terminal devices. Depending on the specific application, a base station may also be called an access point, or a device in the access network that communicates with wireless terminal devices through one or more sectors on the air interface, or other names. The network device can be used to exchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an Internet Protocol (IP) communication network. The network device can also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of this application may be an evolved Node B (eNB or e-NodeB) in a long term evolution (LTE) system, a 5G base station (gNB) in a next generation system, or a Home evolved Node B (HeNB), relay node, femto, pico, network testing equipment, etc., and is not limited in the embodiments of this application. In some network architectures, network devices may include centralized unit (CU) nodes and distributed unit (DU) nodes, which may also be geographically separated.

[0074] It should be understood that the technical solutions provided in this application can be applied to various communication systems. For example, applicable systems may include Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, Long Term Evolution Advanced (LTE-A) systems, Universal Mobile Telecommunications System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) systems, 5G New Radio (NR) systems, 6G systems, and their evolved communication systems. These various systems may include terminal equipment and network equipment. The systems may also include a core network component, such as Evolved Packet System (EPS) and 5G systems (5GS).

[0075] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0076] In one embodiment, as shown in Figure 2, a flowchart of an access control method for an AI serving cell is provided to illustrate how to perform access control for an AI serving cell. The access control method for the AI ​​serving cell includes steps S201-S203:

[0077] S201. The network device sends the cell's AI capability information to the terminal device.

[0078] Among them, a cell can be a wireless communication service area covering a specific geographical range. The AI ​​capability information of a cell refers to information related to the AI ​​services that the corresponding cell can provide.

[0079] In some embodiments, the AI ​​capability information of a cell includes at least one of identification information, characteristic information, and service priority information.

[0080] The identification information is used to indicate whether a cell has AI service capabilities. In some embodiments, the identification information may include identification bits corresponding to each AI service, and the values ​​of different identification bits can indicate whether the cell has the corresponding AI service capabilities.

[0081] The characteristic information is used to indicate the capability characteristics of the AI ​​service capabilities possessed by the cell. It should be understood that the embodiments of this application do not limit the type of characteristic information. In some embodiments, the characteristic information includes at least one of the following: the capability type supported by the cell's AI service; the model development framework supported by the cell's AI service; the model structure supported by the cell's AI service; and the pre-built AI models and AI algorithms supported by the cell's AI service.

[0082] The service priority information indicates the priority of each carrier supported by different capability characteristics. In some embodiments, for multiple carriers supporting the same capability characteristic, the terminal device may preferentially select the carrier with the higher priority.

[0083] It should be understood that the embodiments of this application do not limit how the network device sends the AI ​​capability information of the cell to the terminal device. In some embodiments, the AI ​​capability information is transmitted through unicast messages or broadcast messages of the network device.

[0084] Unicast messages are messages sent by a network device to a single terminal device, while broadcast messages are messages sent by a network device to multiple terminal devices.

[0085] In some embodiments, when a network device sends AI capability information to a terminal device via broadcast, and the AI ​​capability information includes at least one of identification information and characteristic information, the identification information is carried in the main information block (MIB) of the broadcast message, and the characteristic information is carried in the system information block (SIB1) of the broadcast message. Alternatively, at least one of the identification information and characteristic information may be carried in the SIB of the broadcast message, which may include SIB1 and a newly defined SIBx.

[0086] In some embodiments, when a network device sends AI capability information to a terminal device via broadcast and the AI ​​capability information includes at least one of identification information, characteristic information, and service priority information, the AI ​​capability information may be carried in an SIB that is also carried in the broadcast message. The SIB may include SIB2 and a newly defined SIBx.

[0087] S202. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell.

[0088] In this step, after the terminal device receives the AI ​​capability information of the cell, it can determine the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell.

[0089] The aforementioned target cell can be the cell that the terminal device can choose to camp on and access.

[0090] It should be understood that the embodiments of this application do not limit how the terminal device determines the target cell supporting the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell. For example, it can be determined based on whether the terminal device is performing cell access or cell reselection. For example, if the terminal device is performing cell access, the target cell supporting the AI ​​service requested by the terminal device can be determined based on the AI ​​capability information and general access information of the cell; if the terminal device is performing cell reselection, the target cell supporting the AI ​​service requested by the terminal device can be determined based on the AI ​​capability information and general access information of the cell.

[0091] In some embodiments, if the terminal device is powering on for the first time or attempting to access the network from a previously unconnected state, the terminal device performs cell access. In this case, the terminal device can select a target cell that supports the AI ​​service requested by the terminal device, either during or after the general selection process for cell-oriented access, based on the cell's general access information and the cell's AI capability information.

[0092] In other embodiments, upon powering on, the terminal device performs cell reselection if it detects that the signal strength of the access cell has dropped below a signal quality threshold, or if it detects a cell with better signal quality. The terminal device can select the target cell that supports the AI ​​service requested by the terminal device during or after the general cell reselection process, based on cell reselection information and the cell's AI capability information.

[0093] The aforementioned signal quality threshold can be set according to the actual situation, and this application embodiment does not impose any restrictions on it.

[0094] The cell reselection information may include general information related to cell reselection in neighboring cells at the same frequency, different frequencies, and different systems.

[0095] S203, The terminal device accesses or reselects to the target cell.

[0096] In this step, once the terminal device determines the target cell that supports the AI ​​service requested by the terminal device, the terminal can access or reselect the target cell.

[0097] The AI ​​service cell access control method provided in this application embodiment involves a terminal device first receiving AI capability information of the cell from a network device; then, the terminal device determines a target cell that supports the AI ​​service requested by the terminal device based on the cell's AI capability information; finally, the terminal device accesses or reselects the target cell. Because the network device sends the cell's AI capability information to the terminal device, the terminal device can refer to the cell's AI capability information to select a target cell during access or reselection, thereby enabling the terminal device to select a suitable cell that provides AI services during cell access or reselection.

[0098] The access control of the AI ​​service cell during the cell access process is described below. Figure 3 is a signaling interaction diagram of another AI service cell access control method provided in an embodiment of this application. As shown in Figure 3, the AI ​​service cell access control method includes:

[0099] S301. The network device sends the cell's AI capability information to the terminal device.

[0100] In some embodiments, the AI ​​capability information of a cell includes at least one of identification information and characteristic information.

[0101] The identification information is used to indicate whether a cell has AI service capabilities. In some embodiments, the identification information may include identification bits corresponding to each AI service, and the values ​​of different identification bits can indicate whether the cell has the corresponding AI service capabilities.

[0102] The characteristic information is used to indicate the capability characteristics of the AI ​​service capabilities possessed by the cell. It should be understood that the embodiments of this application do not limit the type of characteristic information. In some embodiments, the characteristic information includes at least one of the following: the capability type supported by the cell's AI service; the model development framework supported by the cell's AI service; the model structure supported by the cell's AI service; and the pre-built AI models and AI algorithms supported by the cell's AI service.

[0103] For example, the types of capabilities supported by the AI ​​services in a community may include one or more of the following: AI model training services, AI model inference services, AI data processing services, and AI data storage services.

[0104] For example, the model development framework supported by the AI ​​services of the community may include one or more of the following development frameworks: TensorFlow, PyTorch, PaddlePaddle, etc.

[0105] For example, the model architecture supported by the AI ​​services of a community may include one or more of the following: Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Transformer.

[0106] For example, the pre-built AI models and AI algorithms supported by the community's AI services may include one or more of the following: Natural Language Processing (NLP), Computer Vision, Speech Recognition, Smart Industry, Intelligent Driving, Smart Healthcare, etc.

[0107] It should be understood that the embodiments of this application do not limit how the network device sends the AI ​​capability information of the cell to the terminal device. In some embodiments, the AI ​​capability information is transmitted through unicast messages or broadcast messages of the network device.

[0108] Unicast messages are messages sent by a network device to a terminal device, while broadcast messages are messages sent by a network device to multiple terminal devices.

[0109] In some embodiments, if a network device sends AI capability information to a terminal device via broadcast, the identification information is carried in the main information block (MIB) of the broadcast message, and the feature information is carried in the system information block (SIB1) of the broadcast message; or, the identification information and feature information are both carried in the SIB of the broadcast message, which may include SIB1 and a newly defined SIBx.

[0110] For example, AI capability information can be sent to the terminal device via broadcast in three ways: in the first way, AI capability information is sent to the terminal device by adding at least one of identification information to the MIB message and characteristic information to the SIB1 message; in the second way, AI capability information is sent to the terminal device by adding at least one of identification information and characteristic information to the SIB1 message; and in the third way, AI capability information is sent to the terminal device by adding at least one of identification information and characteristic information to a newly defined SIBx.

[0111] S302. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the cell's AI capability information and the cell's general access information.

[0112] In this step, after the terminal device receives the AI ​​capability information of the cell, it can determine the target cell that supports the AI ​​service requested by the terminal device based on the cell's AI capability information and the cell's general access information.

[0113] Among them, the aforementioned target cell can be the cell that the terminal device can choose to camp on and access.

[0114] In some embodiments, if the terminal device is powering on for the first time or attempting to access the network from a previously unconnected state, the terminal device performs cell access. In this case, the terminal device can select a target cell that supports the AI ​​service requested by the terminal device, either during or after the general selection process for cell-oriented access, based on the cell's general access information and the cell's AI capability information.

[0115] For example, in a general selection process for cells for connection access, the terminal device can select the target cell that supports the AI ​​service requested by the terminal device from multiple cells based on the cell's general access information and the cell's AI capability information.

[0116] For example, in a general selection process for cells oriented towards connection access, the terminal device can select candidate cells from multiple cells based on general cell access information. After the general selection process, the terminal device then selects the target cell that supports the AI ​​service requested by the terminal device from the candidate cells based on the AI ​​capability information of the cell.

[0117] S303, Terminal equipment accesses the target cell.

[0118] In this step, once the terminal device determines the target cell that supports the AI ​​service requested by the terminal device, the terminal device can access the target cell.

[0119] It should be understood that the embodiments of this application do not restrict how the terminal device accesses the target cell. In some embodiments, the terminal device may send an access request to the target cell to the network device. After receiving the access request, the terminal device may access the target cell.

[0120] The aforementioned access request may include a Radio Resource Control (RRC) connection establishment message. Correspondingly, the terminal device's access to the target cell may include the terminal device synchronizing with the target cell or establishing an RRC connection.

[0121] In some embodiments, the access request may include access reason information. Accordingly, the terminal device can identify the access reason information. If the access reason information is identified as indicating that the terminal device's access reason is a request for AI services, the network device can create a target radio bearer (SRBx) associated with the AI ​​service for the terminal device.

[0122] It should be understood that the embodiments of this application do not limit how the network device creates the target radio bearer associated with the AI ​​service for the terminal device. In some embodiments, the network device can create the target radio bearer associated with the AI ​​service for the terminal device based on the access reason information. Subsequently, the network device sends a creation message for the target radio bearer associated with the AI ​​service to the terminal device. After receiving the creation message, the device within the terminal can create the target radio bearer associated with the AI ​​service on the terminal device according to the creation message.

[0123] Among them, the target radio bearer associated with the aforementioned AI service can be used to transmit signaling associated with the AI ​​service.

[0124] The access control of the AI ​​serving cell during the cell reselection process is described below. Figure 4 is a signaling interaction diagram of another AI serving cell access control method provided in this application embodiment. As shown in Figure 4, the AI ​​serving cell access control method includes:

[0125] S401. The network device sends the cell's AI capability information to the terminal device.

[0126] Among them, a cell can be a wireless communication service area covering a specific geographical range. The AI ​​capability information of a cell refers to information related to the AI ​​services that the corresponding cell can provide.

[0127] In some embodiments, the AI ​​capability information of a cell includes at least one of identification information, characteristic information, and service priority information.

[0128] The identification information is used to indicate whether a cell has AI service capabilities. In some embodiments, the identification information may include identification bits corresponding to each AI service, and the values ​​of different identification bits can indicate whether the cell has the corresponding AI service capabilities.

[0129] The characteristic information is used to indicate the capability characteristics of the AI ​​service capabilities possessed by the cell. It should be understood that the embodiments of this application do not limit the type of characteristic information. In some embodiments, the characteristic information includes at least one of the following: the capability type supported by the cell's AI service; the model development framework supported by the cell's AI service; the model structure supported by the cell's AI service; and the pre-built AI models and AI algorithms supported by the cell's AI service.

[0130] Among them, the service priority information is used to indicate the priority of each carrier supported by different capability characteristics.

[0131] For example, if carriers f1 and f2 support AI service feature 1, then the service priority information can be (f1, priority 1)(f2, priority 2), meaning that carrier f1, which supports AI service feature 1, has the first priority, and carrier f2, which supports AI service feature 1, has the second priority. Similarly, if carriers f1 and f3 support AI service feature 2, then the service priority information can be (f1, priority 1)(f3, priority 2), meaning that carrier f1, which supports AI service feature 2, has the first priority, and carrier f3, which supports AI service feature 2, has the second priority.

[0132] It should be understood that the embodiments of this application do not limit how the network device sends the AI ​​capability information of the cell to the terminal device. In some embodiments, the AI ​​capability information is transmitted through unicast messages or broadcast messages of the network device.

[0133] Unicast messages are messages sent by a network device to a terminal device, while broadcast messages are messages sent by a network device to multiple terminal devices.

[0134] In some embodiments, when a network device sends AI capability information to a terminal device via broadcast and the AI ​​capability information includes at least one of identification information, characteristic information, and service priority information, the AI ​​capability information can be carried in an SIB that is also carried in the broadcast message. The SIB may include SIB2 and a newly defined SIBx.

[0135] S402. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the cell's AI capability information and cell reselection information.

[0136] In this step, after the terminal device receives the AI ​​capability information of the cell, it can determine the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell.

[0137] The target cell mentioned above can be the cell that the terminal device can choose to camp on and access. The cell reselection information can include general information related to cell reselection in neighboring cells on the same frequency, different frequencies, and different systems.

[0138] In some embodiments, when the terminal device is powered on, it performs cell reselection if it detects that the signal strength of the access cell has dropped below a signal quality threshold, or if it detects a cell with better signal quality. Subsequently, the terminal device can select a target cell that supports the AI ​​service requested by the terminal device, either during or after the general cell reselection process, based on the cell reselection information and the cell's AI capability information.

[0139] The aforementioned signal quality threshold can be set according to the actual situation, and this application embodiment does not impose any restrictions on it.

[0140] For example, if both cell reselection information and cell AI capability information are carried in SIB2, the terminal device can select the target cell that supports the AI ​​service requested by the terminal device from multiple cells in the general cell reselection process, based on the cell reselection information and the cell AI capability information.

[0141] For example, when cell reselection information and cell AI capability information are both carried in different SIBs, the terminal device can first select candidate cells from multiple cells based on the cell reselection information during the general cell reselection process. Subsequently, after the general cell reselection process, the terminal device selects the target cell that supports the AI ​​service requested by the terminal device from the candidate cells based on the cell's AI capability information.

[0142] S403, Terminal device reselects to target cell.

[0143] In this step, once the terminal device determines the target cell that supports the AI ​​service requested by the terminal device, the terminal device can reselect to the target cell.

[0144] It should be understood that the embodiments of this application do not restrict how the terminal device reselects to the target cell. In some embodiments, the terminal device can send an access request to the target cell to the network device. After receiving the access request, the terminal device can reselect to the target cell.

[0145] The aforementioned access request may include a Radio Resource Control (RRC) connection establishment message. Correspondingly, the terminal device reselecting to the target cell may include the terminal device synchronizing with the target cell or establishing an RRC connection.

[0146] In some embodiments, the access request may include access reason information. Accordingly, the terminal device can identify the access reason information. If the access reason information is identified as indicating that the terminal device's access reason is a request for AI services, the network device can create a target radio bearer (SRBx) associated with the AI ​​service for the terminal device.

[0147] Among them, the target radio bearer associated with the aforementioned AI service can be used to transmit signaling associated with the AI ​​service.

[0148] The following describes how terminal devices interact with network devices to exchange AI resource status information after cell access or reselection. Figure 5 is a signaling interaction diagram of another AI service cell access control method provided in this application embodiment. As shown in Figure 5, the AI ​​service cell access control method includes:

[0149] S501, The network device sends the cell's AI capability information to the terminal device.

[0150] S502. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the cell's AI capability information and the cell's general access information.

[0151] S503, Terminal equipment accesses the target cell.

[0152] S504. The network device sends a semi-static signaling message to the terminal device. The semi-static signaling message includes at least one set of AI resource reporting configuration.

[0153] Semi-static instructions can be signaling that remains unchanged for a period of time. For example, a semi-static instruction can be an L3 signaling message.

[0154] It should be understood that the embodiments of this application do not limit how the network device sends semi-static signaling to the terminal device. In some embodiments, the network device obtains the AI ​​resource reporting capability information of the terminal device. If the AI ​​resource reporting capability information indicates that the terminal device supports the reporting of AI resources, the network device transmits at least one set of AI resource reporting configuration by sending semi-static signaling to the terminal device.

[0155] For example, a network device can obtain the AI ​​resource reporting capability information of a terminal device by sending capability query information to the terminal device. After receiving the capability query information, the terminal device can send its own AI resource reporting capability information to the terminal device.

[0156] The AI ​​resource reporting configuration can be the configuration information used during the AI ​​resource status information reporting process. There can be one or multiple AI resource reporting configurations; this embodiment does not impose any restrictions on this.

[0157] It should be understood that the embodiments of this application do not limit the information included in the AI ​​resource reporting configuration. In some embodiments, the AI ​​resource reporting configuration includes at least one of the following: configuration index information; AI resource reporting content indication information; air interface resource acquisition method for AI resource status reporting; air interface resource location for AI resource status reporting; and AI resource reporting method information.

[0158] The configuration index information can be the number of each AI resource reporting configuration. For example, the configuration index information can include multiple AI resource reporting configurations such as AI resource reporting configuration 1, AI resource reporting configuration 2, and AI resource reporting configuration N, where N is an integer greater than or equal to 1.

[0159] The AI ​​resource reporting content indication information can indicate the content included in the AI ​​resource status information. For example, the AI ​​resource reporting content indication information can indicate at least one of the following: the available computing power of the reporting terminal device, the available storage of the terminal device, and the remaining power of the terminal device.

[0160] The air interface resource acquisition method for AI resource status reporting can include semi-static configuration and dynamic configuration. For example, when the air interface resource acquisition method is semi-static configuration, the terminal device can use the air interface resource location for AI resource status reporting in the AI ​​resource reporting configuration to report AI resource status information.

[0161] For example, if the air interface resource acquisition method is dynamic configuration, the network device can dynamically allocate the reported resource location by sending an indication of the reported resource location to the terminal device. The terminal device then sends AI resource status information to the network device at the reported resource location.

[0162] The AI ​​resource reporting method information can be used to indicate the time interval at which the terminal device reports AI resource status information. For example, the AI ​​resource reporting method information can indicate that the terminal device reports AI resource status information periodically, semi-continuously, or non-periodically.

[0163] It should be noted that some information in the reporting configurations of multiple AI resources may be the same, or all information in the reporting configurations of multiple AI resources may be different. This application embodiment does not impose any restrictions.

[0164] It should be understood that the embodiments of this application do not limit how the network device sends semi-static signaling to the terminal device. In some embodiments, when the network device generates a target radio bearer associated with the AI ​​service for the terminal device, the semi-static signaling can be carried on the target radio bearer associated with the AI ​​service. Accordingly, after receiving the semi-static signaling, the terminal device can send a reconfiguration completion message to the network device on the target radio bearer associated with the AI ​​service.

[0165] In some embodiments, where the semi-static signaling sent by the network device includes multiple AI resource reporting configurations, the network device can also send configuration activation indication information to the terminal device to activate the target AI resource reporting configuration in at least one set of AI resource reporting configurations. Subsequently, the terminal device sends AI resource status information to the network device according to the target AI resource reporting configuration. The configuration activation indication information includes configuration index information of the target AI resource reporting configuration and is carried in semi-static or dynamic signaling.

[0166] For example, the aforementioned semi-static signaling can be the semi-static signaling corresponding to the AI ​​resource reporting configuration, or it can be the semi-static signaling sent for subsequent reselection.

[0167] It should be understood that the target AI resource reporting configuration can be any set of AI resource reporting configurations that the network device indicates to be activated.

[0168] S505: The terminal device sends AI resource status information to the network device based on at least one set of AI resource reporting configurations.

[0169] In some implementations, when the air interface resource acquisition method in the target AI resource reporting configuration is semi-static, the terminal device can use the air interface resource location of the AI ​​resource status reporting in the target AI resource reporting configuration to report AI resource status information.

[0170] In some implementations, when the air interface resource acquisition method is dynamic configuration (i.e., dynamically allocating reported resource locations), the network device can dynamically allocate reported resource locations by sending indication information of the reported resource locations to the terminal device. Subsequently, the terminal device sends AI resource status information to the network device at the reported resource locations according to the target AI resource reporting configuration.

[0171] In other embodiments, the network device may also send AI resource status information to the terminal device. This AI resource status information is carried in a unicast message.

[0172] In this embodiment, network devices and terminal devices can interact with each other to exchange AI resource status information, thereby enabling more refined scheduling and performance assurance for AI services provided over the air interface.

[0173] The following explains how to control the reporting of AI resource status information through semi-static instructions. Figure 6 is a signaling interaction diagram of another AI serving cell access control method provided in this application embodiment. As shown in Figure 6, the AI ​​serving cell access control method includes:

[0174] S601. The network device sends the cell's AI capability information to the terminal device.

[0175] S602. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the cell's AI capability information and the cell's general access information.

[0176] S603, Terminal equipment accesses the target cell.

[0177] S604. The network device sends a first semi-static signaling message to the terminal device. The first semi-static signaling message includes at least one set of AI resource reporting configuration.

[0178] After S604, execute S605a, or after S604, execute S605b1-S605b2.

[0179] S605a: The terminal device activates at least one set of target AI resource reporting configurations in the AI ​​resource reporting configuration according to the first semi-static signaling.

[0180] In some embodiments, the first semi-static signaling may include a configuration activation indication message, thereby instructing the activation of the target AI resource reporting configuration.

[0181] In other embodiments, the first semi-static signaling may not include a configuration activation indication message, and the terminal device can directly activate the AI ​​resource reporting configuration upon receiving the AI ​​resource reporting configuration.

[0182] S605b1, The network device sends a second semi-static signaling message to the terminal device, which includes configuration activation indication information.

[0183] S605b2, The terminal device activates at least one set of target AI resource reporting configurations in the AI ​​resource reporting configuration according to the configuration activation instruction information in the second semi-static signaling.

[0184] S606. The terminal device sends AI resource status information to the network device according to the target AI resource reporting configuration.

[0185] S607. The network device sends an AI service configuration adjustment message to the terminal device. The AI ​​service configuration adjustment message is used to adjust the configuration corresponding to the AI ​​service.

[0186] The configuration corresponding to the AI ​​service includes at least one of the following: the split point of the distributed model or federated learning model corresponding to the AI ​​service; the data transmission cycle of the model corresponding to the AI ​​service; the data transmission bandwidth of the model corresponding to the AI ​​service; the data transmission power of the model corresponding to the AI ​​service; and the data transmission bit width of the model corresponding to the AI ​​service.

[0187] In some embodiments, after receiving AI resource status information, the network device can determine whether to adjust the configuration corresponding to the AI ​​service in which the terminal device participates, based on the AI ​​resource status information. If it is necessary to adjust the configuration corresponding to the AI ​​service in which the terminal device participates, the network device sends an AI service configuration adjustment message to the terminal device.

[0188] It should be understood that the embodiments of this application do not limit how the network device sends the configuration adjustment message of the AI ​​service to the terminal device. In some embodiments, the network device can send the configuration adjustment message of the AI ​​service to the terminal device through semi-static signaling, which can be L3 signaling.

[0189] S608: The terminal device adjusts the configuration corresponding to the AI ​​service based on the configuration adjustment message of the AI ​​service.

[0190] In some embodiments, after receiving a configuration adjustment message for an AI service, the device within the terminal can adjust the configuration of one or more AI services according to the items to be adjusted indicated in the configuration adjustment message.

[0191] For example, the items to be adjusted indicated in the configuration adjustment message may include the collaborative set of distributed AI training or inference, the collaborative method of distributed AI training or inference, the split point of the distributed or federated learning model between network devices and terminal devices, and the reporting cycle of AI-related measurement data.

[0192] For example, Figure 7 is a schematic diagram of the adjustment of the split points of a distributed model or federated learning model provided in an embodiment of this application. As shown in Figure 7, the configuration adjustment message can instruct the split points of the distributed model or federated learning model to be partially adjusted from the network side to the terminal 1 and terminal y side.

[0193] For example, Figure 8 is a schematic diagram of adjusting the collaborative set for AI training or inference provided in an embodiment of this application. As shown in Figure 8, the configuration adjustment message can indicate that the collaborative set for AI training or inference, which was provided by terminal 1 and terminal x, is adjusted to be provided by terminal 1 and terminal y.

[0194] S609. The terminal device sends a configuration adjustment confirmation message to the network device.

[0195] The following explains how to control the AI ​​resource status information to stop being reported using semi-static instructions. Figure 9 is a signaling interaction diagram of another AI serving cell access control method provided in this application embodiment. As shown in Figure 9, the AI ​​serving cell access control method includes:

[0196] S701, The network device sends the cell's AI capability information to the terminal device.

[0197] S702. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the cell's AI capability information and the cell's general access information.

[0198] S703, Terminal equipment accesses the target cell.

[0199] S704. The network device sends a semi-static signaling message to the terminal device. The semi-static signaling message includes at least one set of AI resource reporting configuration.

[0200] S705: The terminal device sends AI resource status information to the network device based on at least one set of AI resource reporting configurations.

[0201] S706. When the terminal device meets the conditions for stopping the reporting of AI resource status information or receives a stop reporting instruction, it shall stop sending AI resource status information to the network device.

[0202] The stop reporting condition and the stop reporting indication information are both carried in the semi-static signaling. For example, the semi-static signaling can be L3 signaling.

[0203] For example, the above-mentioned conditions for stopping reporting can be the reporting duration, the amount of data reported, etc., and this application embodiment does not limit this.

[0204] In some embodiments, the stop reporting instruction information also includes configuration index information, thereby instructing the deactivation of the AI ​​resource reporting configuration corresponding to the configuration index information.

[0205] In some embodiments, the aforementioned stop-reporting instruction information further includes a feedback confirmation identifier, which instructs the terminal device to confirm the cessation of reporting AI resource status information. Correspondingly, the network device can allocate target resources for the terminal device to send a confirmation feedback message for stopping the reporting of AI resource status information. The terminal device then sends a confirmation feedback message for stopping the reporting of AI resource status information to the network device based on the feedback confirmation identifier.

[0206] In some embodiments, the signaling bearers corresponding to the aforementioned confirmation feedback message and the stop reporting instruction are the same.

[0207] The following explains how to control the reporting of AI resource status information and the adjustment of AI service configurations through dynamic commands. Figure 10 is a signaling interaction diagram of another AI service cell access control method provided in this application embodiment. As shown in Figure 10, the AI ​​service cell access control method includes:

[0208] S801, The network device sends the cell's AI capability information to the terminal device.

[0209] S802. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the cell's AI capability information and the cell's general access information.

[0210] S803, Terminal equipment accesses the target cell.

[0211] S804. The network device sends a semi-static signaling message to the terminal device. The semi-static signaling message includes at least one set of AI resource reporting configuration.

[0212] S805: The network device sends dynamic signaling to the terminal device, which includes configuration activation instruction information.

[0213] The configuration activation instruction information includes the configuration index information of the target AI resource reporting configuration.

[0214] It should be understood that the embodiments of this application do not limit dynamic signaling. In some embodiments, dynamic signaling may include context control information (DCI), media access control element (MAC CE), etc.

[0215] S806. The terminal device activates at least one set of target AI resource reporting configurations in the AI ​​resource reporting configuration according to the configuration activation instruction information in the dynamic signaling.

[0216] S807: The terminal device sends AI resource status information to the network device according to the target AI resource reporting configuration.

[0217] In some embodiments, if the air interface resource acquisition method corresponding to the target AI resource reporting configuration is dynamic allocation of the reported resource location, the network device can send indication information of the reported resource location to the terminal device. The terminal device can then send AI resource status information to the network device at the reported resource location according to the target AI resource reporting configuration.

[0218] S808: The network device sends an AI service configuration adjustment message to the terminal device. The AI ​​service configuration adjustment message is used to adjust the configuration corresponding to the AI ​​service.

[0219] The configuration corresponding to the AI ​​service includes at least one of the following: the split point of the distributed model or federated learning model corresponding to the AI ​​service; the data transmission cycle of the model corresponding to the AI ​​service; the data transmission bandwidth of the model corresponding to the AI ​​service; the data transmission power of the model corresponding to the AI ​​service; and the data transmission bit width of the model corresponding to the AI ​​service.

[0220] In some embodiments, after receiving AI resource status information, the network device can determine whether to adjust the configuration corresponding to the AI ​​service in which the terminal device participates, based on the AI ​​resource status information. If it is necessary to adjust the configuration corresponding to the AI ​​service in which the terminal device participates, the network device sends an AI service configuration adjustment message to the terminal device.

[0221] It should be understood that the embodiments of this application do not limit how the network device sends the configuration adjustment message of the AI ​​service to the terminal device. In some embodiments, the network device can send the configuration adjustment message of the AI ​​service to the terminal device through semi-static signaling, which can be L3 signaling.

[0222] S809: The terminal device adjusts the configuration corresponding to the AI ​​service based on the configuration adjustment message of the AI ​​service.

[0223] In some embodiments, after receiving a configuration adjustment message for an AI service, the device within the terminal can adjust the configuration of one or more AI services according to the items to be adjusted indicated in the configuration adjustment message.

[0224] For example, the items to be adjusted indicated in the configuration adjustment message may include the split point of the distributed or federated learning model between the network device and the terminal device, the data transmission cycle of the model corresponding to the AI ​​service, the data transmission bandwidth of the model corresponding to the AI ​​service, the data transmission power of the model corresponding to the AI ​​service, and the data transmission bit width of the model corresponding to the AI ​​service.

[0225] For example, continuing to refer to Figure 7, the configuration adjustment message can instruct the splitting points of the distributed model or federated learning model to be partially adjusted from the network side to the terminal 1 and terminal y sides.

[0226] For example, Figure 11 is a schematic diagram of adjusting the data transmission bit width of a model corresponding to an AI service provided in an embodiment of this application. As shown in Figure 11, the configuration adjustment message can indicate that the intermediate result bit width of the model corresponding to the AI ​​service is adjusted from m bits to n bits.

[0227] S819. The terminal device sends a configuration adjustment confirmation message to the network device.

[0228] The following explains how to control the AI ​​resource status information to stop being reported using dynamic commands. Figure 12 is a signaling interaction diagram of another AI serving cell access control method provided in this application embodiment. As shown in Figure 12, the AI ​​serving cell access control method includes:

[0229] S901, The network device sends the cell's AI capability information to the terminal device.

[0230] S902. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell.

[0231] S903, the terminal device accesses or reselects to the target cell.

[0232] S904. The network device sends a semi-static signaling message to the terminal device. The semi-static signaling message includes at least one set of AI resource reporting configuration.

[0233] S905: The terminal device sends AI resource status information to the network device based on at least one set of AI resource reporting configurations.

[0234] S906. The network device sends a stop reporting instruction to the terminal device. The stop reporting instruction is carried in dynamic signaling.

[0235] Dynamic signaling can include DCI, MAC CE, etc.

[0236] In some embodiments, the stop reporting instruction information also includes configuration index information, thereby instructing the deactivation of the AI ​​resource reporting configuration corresponding to the configuration index information.

[0237] In some embodiments, the aforementioned stop-reporting instruction information further includes a feedback confirmation identifier, which instructs the terminal device to confirm the cessation of reporting AI resource status information. Correspondingly, the network device can allocate target resources for the terminal device to send a confirmation feedback message for stopping the reporting of AI resource status information. The terminal device then sends a confirmation feedback message for stopping the reporting of AI resource status information to the network device based on the feedback confirmation identifier.

[0238] In some embodiments, the signaling bearers corresponding to the aforementioned confirmation feedback message and the stop reporting instruction are the same.

[0239] S907. Terminal devices stop sending AI resource status information to network devices.

[0240] The following describes the access control of the AI ​​serving cell during cell handover. Figure 13 is a signaling interaction diagram of another AI serving cell access control method provided in this application embodiment. As shown in Figure 13, the AI ​​serving cell access control method includes:

[0241] S1001, The network device sends the cell's AI capability information to the terminal device.

[0242] S1002. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell.

[0243] S1003, The terminal device is reselected or connected to the target cell.

[0244] S1004. The terminal equipment measures the neighboring cells and determines the measurement results.

[0245] The above measurement results are used to indicate the signal quality of neighboring cells.

[0246] S1005. The terminal device sends the measurement results to the network device.

[0247] S1006. The network equipment determines whether the cell handover conditions are met based on the measurement results.

[0248] In some embodiments, if the signal quality of a neighboring cell is better than the signal quality of the currently accessed cell, and the signal quality of the currently accessed cell is lower than a quality threshold, the network device can determine that the cell handover conditions are met.

[0249] The quality threshold can be set according to the actual situation, and this application embodiment does not impose any restrictions on it.

[0250] S1007. The network device determines the cell to be switched to by the terminal device based on the air interface information, AI resource information, and AI capability information of the neighboring cell network.

[0251] Among them, the AI ​​resource information and AI capability information of the neighboring cell network are used to filter out the cells to be handed over that support the AI ​​services requested by the terminal devices.

[0252] S1008. The network device sends a cell handover instruction message to the terminal device. The cell handover instruction message is used to instruct the terminal device to switch access to the cell to be handed over. The cell handover instruction message contains at least one of the AI ​​capability information and AI resource status information of the cell to be handed over.

[0253] S1009. The terminal device switches to the cell to be switched.

[0254] The AI ​​service cell access control method provided in this application embodiment involves a terminal device first receiving AI capability information of the cell from a network device. Then, based on the cell's AI capability information, the terminal device determines the target cell that supports the AI ​​service requested by the terminal device. Finally, the terminal device accesses or reselects the target cell. Because the network device sends the cell's AI capability information to the terminal device, the terminal device can refer to this information when accessing or reselecting the cell to select a target cell, thus enabling it to choose a suitable cell providing AI services. Furthermore, the network device and the terminal device can exchange AI resource status information, thereby supporting more refined scheduling and performance guarantees for AI services provided over the air interface.

[0255] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0256] Based on the same concept, this application also provides an access control device for an AI serving cell to implement the access control method for the AI ​​serving cell described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more AI serving cell access control device embodiments provided below can be found in the limitations on the communication method above, and will not be repeated here.

[0257] In one embodiment, as shown in FIG14, an access control device 1100 for an AI serving cell is provided and applied to a terminal device. The access control device 1100 for the AI ​​serving cell includes a first receiving module 1101 and a first processing module 1102.

[0258] The first receiving module 1101 is used to receive the artificial intelligence (AI) capability information of the cell sent by the network device;

[0259] The first processing module 1102 is used for the terminal device to determine the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell; and to access or reselect the target cell.

[0260] In some embodiments, the AI ​​capability information of a cell includes at least one of identification information, characteristic information, and service priority information;

[0261] Identification information is used to indicate whether a cell has AI service capabilities, characteristic information is used to indicate the capability characteristics of the AI ​​service capabilities that the cell possesses, and priority information is used to indicate the priorities of the carriers supported by different capability characteristics.

[0262] In some embodiments, the characteristic information includes at least one of the following:

[0263] The types of capabilities supported by the community's AI services;

[0264] The AI ​​service support model development framework for the community;

[0265] The model structure supported by the community's AI services;

[0266] The community's AI services support pre-built AI models and AI algorithms.

[0267] In some embodiments, AI capability information is transmitted via unicast or broadcast messages from network devices.

[0268] In some embodiments, identification information is carried in the main information block (MIB) of the broadcast message, and characteristic information is carried in the system information block (SIB1) of the broadcast message; or...

[0269] Identification and characteristic information are both carried in the SIB of the broadcast message.

[0270] In some embodiments, the access control device 1100 for the AI ​​serving cell further includes:

[0271] The second sending module is used to send an access request for the target cell to the network device. The access request includes access reason information, which indicates that the access reason of the terminal device is to request AI services.

[0272] In some embodiments, the first receiving module 1101 is further configured to receive a creation message of the target radio bearer associated with the AI ​​service sent by the network device;

[0273] The first processing module 1102 is further configured to create a target wireless bearer associated with the AI ​​service on the terminal device according to the creation message.

[0274] In some embodiments, the first receiving module 1101 is further configured to receive semi-static signaling sent by the network device, wherein the semi-static signaling includes at least one set of AI resource reporting configuration.

[0275] The second sending module is also used to send AI resource status information to network devices based on at least one set of AI resource reporting configurations.

[0276] In some embodiments, the AI ​​resource reporting configuration includes at least one of the following:

[0277] Configure index information;

[0278] AI resource reporting content instructions;

[0279] AI resource status reporting method for obtaining air interface resources;

[0280] The location of air interface resources reported by AI resource status;

[0281] Information on AI resource reporting methods.

[0282] In some embodiments, semi-static signaling is carried on the target radio bearer associated with the AI ​​service.

[0283] In some embodiments, the first processing module 1102 is further configured to activate at least one set of target AI resource reporting configurations in the terminal device according to the configuration activation instruction information;

[0284] The second sending module is also used to send AI resource status information to network devices according to the target AI resource reporting configuration;

[0285] The configuration activation indication information includes the configuration index information of the target AI resource reported configuration, and the configuration activation indication information is carried in semi-static signaling or dynamic signaling.

[0286] In some embodiments, when the air interface resource acquisition method corresponding to the target AI resource reporting configuration is to dynamically allocate the reported resource location, the first receiving module 1101 is further configured to receive the indication information of the reported resource location sent by the network device.

[0287] The second sending module is also used to send AI resource status information to the network device at the reported resource location according to the target AI resource reporting configuration.

[0288] In some embodiments, the first processing module 1102 is further configured to stop sending AI resource status information to the network device when the conditions for stopping reporting AI resource status information are met or when a stop reporting instruction is received;

[0289] Among them, the conditions for stopping reporting are carried in semi-static signaling, and the instructions for stopping reporting are carried in semi-static signaling or dynamic signaling.

[0290] In some embodiments, the stop reporting instruction information also includes a feedback confirmation identifier, which is used to instruct the terminal device to provide confirmation feedback on stopping the reporting of AI resource status information;

[0291] The second sending module is also used to send a confirmation feedback message to the network device to stop reporting AI resource status information based on the feedback confirmation identifier.

[0292] In some embodiments, the first receiving module 1101 is further configured to receive a configuration adjustment message for an AI service sent by a network device;

[0293] The first processing module 1102 is also used to adjust the configuration of the AI ​​service according to the configuration adjustment message of the AI ​​service;

[0294] The second sending module is also used to send configuration adjustment confirmation messages to network devices.

[0295] In some embodiments, the configuration corresponding to the AI ​​service includes at least one of the following:

[0296] The splitting points of the distributed or federated learning model corresponding to the AI ​​service;

[0297] Data transmission cycle of the model corresponding to the AI ​​service;

[0298] Data transmission bandwidth of the model corresponding to the AI ​​service;

[0299] Data transmission power of the model corresponding to the AI ​​service;

[0300] The data transmission bit width of the model corresponding to the AI ​​service.

[0301] In some embodiments, the first receiving module 1101 is further configured to receive AI resource status information sent by the network device.

[0302] In some embodiments, when the terminal device performs cell reselection, the first processing module 1102 is further configured to determine the target cell based on the cell reselection information and AI capability information.

[0303] In some embodiments, the first receiving module 1101 is further configured to receive a cell handover indication message sent by the network device. The cell handover indication message is used to indicate that the terminal device is switched to the cell to be switched. The cell handover indication message includes at least one of the AI ​​capability information and AI resource status information of the cell to be switched.

[0304] The first processing module 1102 is also used for terminal devices to switch access to the cell to be switched.

[0305] It should be noted that the access control device for the AI ​​service cell provided in this application embodiment can implement all the method steps implemented in the access control method embodiment for the AI ​​service cell on the terminal device side, and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0306] Based on the same concept, this application also provides an access control device for an AI serving cell to implement the access control method for the AI ​​serving cell described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more AI serving cell access control device embodiments provided below can be found in the limitations on the communication method above, and will not be repeated here.

[0307] In one embodiment, as shown in FIG15, an access control device 1200 for an AI serving cell is provided and applied to a network device. The access control device 1200 for the AI ​​serving cell includes: a first sending module 1201, a second receiving module 1202, and a second processing module 1203.

[0308] The first sending module 1201 is used to send the AI ​​capability information of the cell to the terminal device;

[0309] The second receiving module 1202 is used to receive the access request of the target cell sent by the terminal device. The target cell is a cell that supports the AI ​​service requested by the terminal device. The target cell is determined based on the AI ​​capability information of the cell.

[0310] The second processing module 1203 is used to connect or reselect the terminal device to the target cell.

[0311] In some embodiments, the AI ​​capability information of a cell includes at least one of identification information, characteristic information, and service priority information;

[0312] Identification information is used to indicate whether a cell has AI service capabilities, characteristic information is used to indicate the capability characteristics of the AI ​​service capabilities that the cell possesses, and priority information is used to indicate the priorities of the carriers supported by different capability characteristics.

[0313] In some embodiments, the characteristic information includes at least one of the following:

[0314] The types of capabilities supported by the community's AI services;

[0315] The AI ​​service support model development framework for the community;

[0316] The model structure supported by the community's AI services;

[0317] The community's AI services support pre-built AI models and AI algorithms.

[0318] In some embodiments, AI capability information is transmitted via unicast or broadcast messages from network devices.

[0319] In some embodiments, identification information is carried in the main information block (MIB) of the broadcast message, and characteristic information is carried in the system information block (SIB1) of the broadcast message; or...

[0320] Identification and characteristic information are both carried in the SIB of the broadcast message.

[0321] In some embodiments, the access request includes access reason information, which is used to indicate that the access reason of the terminal device is to request AI services.

[0322] The second processing module 1203 is also used to create a target wireless bearer associated with AI services for the terminal device based on the access reason information.

[0323] The first sending module 1201 is also used to send a creation message of the target radio bearer associated with the AI ​​service to the terminal device.

[0324] In some embodiments, the second processing module 1203 is further configured to allow the network device to obtain AI resource reporting capability information of the terminal device;

[0325] The first sending module 1201 is also used to send semi-static signaling to the terminal device when the AI ​​resource reporting capability information indicates that the terminal device supports the reporting of AI resources. The semi-static signaling includes at least one set of AI resource reporting configuration.

[0326] The second receiving module 1202 is also used to receive AI resource status information sent by the terminal device according to at least one set of AI resource reporting configuration.

[0327] In some embodiments, the AI ​​resource reporting configuration includes at least one of the following:

[0328] Configure index information;

[0329] AI resource reporting content instructions;

[0330] AI resource status reporting and air interface resource acquisition methods;

[0331] The location of air interface resources reported by AI resource status;

[0332] Information on AI resource reporting methods.

[0333] In some embodiments, semi-static signaling is carried on the target radio bearer associated with the AI ​​service.

[0334] In some embodiments, the semi-static signaling includes configuration activation indication information, which is used to instruct the terminal device to activate the target AI resource reporting configuration from at least one set of AI resource reporting configurations.

[0335] In some embodiments, the first sending module 1201 is further configured to send configuration activation indication information to the terminal device, wherein the configuration activation indication information is carried in semi-static signaling or dynamic signaling.

[0336] In some embodiments, when the air interface resource acquisition method corresponding to the target AI resource reporting configuration is to dynamically allocate the reported resource location, the first sending module 1201 is further used to send the indication information of the reported resource location to the terminal device via the network device.

[0337] In some embodiments, the first sending module 1201 is further configured to send a stop reporting instruction to the terminal device. The stop reporting instruction is used to instruct the terminal device to stop sending AI resource status information to the network device. The stop reporting instruction is carried in semi-static signaling or dynamic signaling.

[0338] In some embodiments, the stop reporting instruction information also includes a feedback confirmation identifier, which is used to instruct the terminal device to provide confirmation feedback on stopping the reporting of AI resource status information;

[0339] The second processing module 1203 is also used to allocate target resources for the terminal device to receive confirmation feedback messages to stop reporting AI resource status information;

[0340] The second receiving module 1202 is also used to receive confirmation feedback messages sent by the terminal device through the target resource.

[0341] In some embodiments, the first sending module 1201 is further configured to send a configuration adjustment message for the AI ​​service to the terminal device, wherein the configuration adjustment message for the AI ​​service is used to adjust the configuration corresponding to the AI ​​service.

[0342] The second receiving module 1202 is also used to receive a configuration adjustment confirmation message sent by the terminal device.

[0343] In some embodiments, the configuration corresponding to the AI ​​service includes at least one of the following:

[0344] The splitting points of the distributed or federated learning model corresponding to the AI ​​service;

[0345] Data transmission cycle of the model corresponding to the AI ​​service;

[0346] Data transmission bandwidth of the model corresponding to the AI ​​service;

[0347] Data transmission power of the model corresponding to the AI ​​service;

[0348] The data transmission bit width of the model corresponding to the AI ​​service.

[0349] In some embodiments, the first sending module 1201 is further configured to send AI resource status information from the network device to the terminal device.

[0350] In some embodiments, the second processing module 1203 is further configured to determine the cell to be switched to by the terminal device based on the air interface information of the neighboring cell network, the AI ​​resource information of the neighboring cell network, and the AI ​​capability information of the neighboring cell network.

[0351] The first sending module 1201 is also used to send a cell handover indication message to the terminal device. The cell handover indication message contains at least one of the AI ​​capability information and AI resource status information of the cell to be handed over.

[0352] It should be noted that the apparatus provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0353] It should be noted that the module division in the embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0354] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application.

[0355] It should be noted that the apparatus provided in this application embodiment can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.

[0356] As shown in Figure 16, this application embodiment also provides an access control device for an AI serving cell to implement the above-mentioned access control method for the AI ​​serving cell on the terminal device side. The access control device for the AI ​​serving cell includes a processor 1301, a memory 1302, and a transceiver 1303.

[0357] Memory 1302 is used to store computer programs; transceiver 1303 is used to receive and send data under the control of processor 1301. Processor 1301 is used to read the computer program from memory and perform the following operations:

[0358] The transceiver receives information about the cell's artificial intelligence (AI) capabilities from network devices.

[0359] Based on the AI ​​capability information of the community, determine the target community that supports the AI ​​services requested by the terminal device;

[0360] Access or reselect to the target cell.

[0361] In some embodiments, the AI ​​capability information of a cell includes at least one of identification information, characteristic information, and service priority information;

[0362] Identification information is used to indicate whether a cell has AI service capabilities, characteristic information is used to indicate the capability characteristics of the AI ​​service capabilities that the cell possesses, and priority information is used to indicate the priorities of the carriers supported by different capability characteristics.

[0363] In some embodiments, the characteristic information includes at least one of the following:

[0364] The types of capabilities supported by the community's AI services;

[0365] The AI ​​service support model development framework for the community;

[0366] The model structure supported by the community's AI services;

[0367] The community's AI services support pre-built AI models and AI algorithms.

[0368] In some embodiments, AI capability information is transmitted via unicast or broadcast messages from network devices.

[0369] In some embodiments, identification information is carried in the main information block (MIB) of the broadcast message, and characteristic information is carried in the system information block (SIB1) of the broadcast message; or...

[0370] Identification and characteristic information are both carried in the SIB of the broadcast message.

[0371] In some embodiments, accessing or reselecting to a target cell includes:

[0372] The terminal device sends an access request for the target cell to the network device via a transceiver. The access request includes access reason information, which indicates that the access reason of the terminal device is to request AI services.

[0373] In some embodiments, the processor also performs the following operations:

[0374] The transceiver receives the creation message of the target wireless bearer associated with the AI ​​service sent by the network device.

[0375] Based on the creation message, create a target wireless bearer associated with the AI ​​service on the terminal device.

[0376] In some embodiments, the processor also performs the following operations:

[0377] The transceiver receives semi-static signaling sent by network devices, and the semi-static signaling includes at least one set of AI resource reporting configuration.

[0378] Based on at least one set of AI resource reporting configurations, send AI resource status information to network devices.

[0379] In some embodiments, the AI ​​resource reporting configuration includes at least one of the following:

[0380] Configure index information;

[0381] AI resource reporting content instructions;

[0382] AI resource status reporting and air interface resource acquisition methods;

[0383] The location of air interface resources reported by AI resource status;

[0384] Information on AI resource reporting methods.

[0385] In some embodiments, semi-static signaling is carried on the target radio bearer associated with the AI ​​service.

[0386] In some embodiments, AI resource status information is sent to the network device according to at least one set of AI resource reporting configurations, including:

[0387] According to the configuration activation instruction information, activate at least one set of target AI resource reporting configurations in the AI ​​resource reporting configuration;

[0388] Based on the target AI resource reporting configuration, send AI resource status information to the network device;

[0389] The configuration activation indication information includes the configuration index information of the target AI resource reported configuration, and the configuration activation indication information is carried in semi-static signaling or dynamic signaling.

[0390] In some embodiments, when the air interface resource acquisition method corresponding to the target AI resource reporting configuration is dynamic allocation of the reported resource location, the processor also performs the following operations:

[0391] The transceiver receives resource location indication information reported by network devices.

[0392] Based on the target AI resource reporting configuration, send AI resource status information to the network device, including: based on the target AI resource reporting configuration, send AI resource status information to the network device at the reported resource location.

[0393] In some embodiments, the method further includes:

[0394] When the terminal device meets the conditions for stopping the reporting of AI resource status information or receives a stop reporting instruction, it stops sending AI resource status information to the network device.

[0395] Among them, the conditions for stopping reporting are carried in semi-static signaling, and the instructions for stopping reporting are carried in semi-static signaling or dynamic signaling.

[0396] In some embodiments, the stop reporting instruction information further includes a feedback confirmation identifier, which is used to instruct the terminal device to provide confirmation feedback on stopping the reporting of AI resource status information; the processor also performs the following operations:

[0397] Based on the feedback confirmation identifier, a confirmation feedback message is sent to the network device to stop reporting AI resource status information.

[0398] In some embodiments, the processor also performs the following operations:

[0399] Receive configuration adjustment messages for AI services from network devices via transceiver;

[0400] Adjust the configuration of the AI ​​service according to the configuration adjustment message.

[0401] Send configuration adjustment confirmation messages to network devices via transceiver.

[0402] In some embodiments, the configuration corresponding to the AI ​​service includes at least one of the following:

[0403] The splitting points of the distributed or federated learning model corresponding to the AI ​​service;

[0404] Data transmission cycle of the model corresponding to the AI ​​service;

[0405] Data transmission bandwidth of the model corresponding to the AI ​​service;

[0406] Data transmission power of the model corresponding to the AI ​​service;

[0407] The data transmission bit width of the model corresponding to the AI ​​service.

[0408] In some embodiments, the processor also performs the following operations:

[0409] The transceiver receives AI resource status information sent by network devices.

[0410] In some embodiments, when the terminal device performs cell reselection, the target cell supporting the AI ​​service requested by the terminal device is determined based on the AI ​​capability information of the cell, including:

[0411] The target community is determined based on community reselection information and AI capability information.

[0412] In some embodiments, the processor also performs the following operations:

[0413] The transceiver receives a cell handover instruction message sent by a network device. The cell handover instruction message is used to instruct the terminal device to switch access to the cell to be handed over. The cell handover instruction message contains at least one of the AI ​​capability information and AI resource status information of the cell to be handed over.

[0414] Switch access to the cell to be switched.

[0415] In Figure 16, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors 1301 represented by processor 1301 and memory 1302 represented by memory 1302. The bus architecture may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 1303 may be multiple components, including transmitters and receivers, providing a unit for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, etc. For different user equipment, the user interface 1304 may also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc.

[0416] The processor 1301 is responsible for managing the bus architecture and general processing, while the memory 1302 can store the data used by the processor 1301 when performing operations.

[0417] Optionally, the processor 1301 can be a CPU (Central Processing Unit 1301), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a CPLD (Complex Programmable Logic Device). The processor 1301 can also adopt a multi-core architecture.

[0418] The processor 1301 executes any of the methods provided in the embodiments of this application according to the obtained executable instructions by calling the program stored in the memory 1302. The processor 1301 and the memory 1302 may also be physically separated.

[0419] As shown in Figure 17, this application embodiment also provides an access control device for an AI serving cell to implement the above-mentioned access control method for an AI serving cell on the network device side. The access control device for the AI ​​serving cell includes a processor 1401, a memory 1402, and a transceiver 1403.

[0420] Memory 1402 is used to store computer programs; transceiver 1403 is used to receive and send data under the control of processor 1401. Processor 1401 is used to read the computer program from memory and perform the following operations:

[0421] The transceiver sends the cell's AI capability information to the terminal device.

[0422] The transceiver receives the access request for the target cell sent by the terminal device. The target cell is a cell that supports the AI ​​service requested by the terminal device. The target cell is determined based on the AI ​​capability information of the cell.

[0423] Connect or reselect the terminal device to the target cell.

[0424] In some embodiments, the AI ​​capability information of a cell includes at least one of identification information, characteristic information, and service priority information;

[0425] Identification information is used to indicate whether a cell has AI service capabilities, characteristic information is used to indicate the capability characteristics of the AI ​​service capabilities that the cell possesses, and priority information is used to indicate the priorities of the carriers supported by different capability characteristics.

[0426] In some embodiments, the characteristic information includes at least one of the following:

[0427] The types of capabilities supported by the community's AI services;

[0428] The AI ​​service support model development framework for the community;

[0429] The model structure supported by the community's AI services;

[0430] The community's AI services support pre-built AI models and AI algorithms.

[0431] In some embodiments, AI capability information is transmitted via unicast or broadcast messages from network devices.

[0432] In some embodiments, identification information is carried in the main information block (MIB) of the broadcast message, and characteristic information is carried in the system information block (SIB1) of the broadcast message; or...

[0433] Identification and characteristic information are both carried in the SIB of the broadcast message.

[0434] In some embodiments, the access request includes access reason information, which indicates that the access reason of the terminal device is to request AI services; the processor also performs the following operations:

[0435] Based on the access reason information, create a target wireless bearer associated with the AI ​​service for the terminal device;

[0436] The transceiver sends a creation message for the target radio bearer associated with the AI ​​service to the terminal device.

[0437] In some embodiments, the processor also performs the following operations:

[0438] Obtain information on the AI ​​resource reporting capabilities of terminal devices;

[0439] When the AI ​​resource reporting capability information indicates that the terminal device supports the reporting of AI resources, a semi-static signaling is sent to the terminal device through the transceiver. The semi-static signaling includes at least one set of AI resource reporting configuration.

[0440] The transceiver receives AI resource status information reported by terminal devices based on at least one set of AI resource configurations.

[0441] In some embodiments, the AI ​​resource reporting configuration includes at least one of the following:

[0442] Configure index information;

[0443] AI resource reporting content instructions;

[0444] AI resource status reporting method for obtaining air interface resources;

[0445] The location of air interface resources reported by AI resource status;

[0446] Information on AI resource reporting methods.

[0447] In some embodiments, semi-static signaling is carried on the target radio bearer associated with the AI ​​service.

[0448] In some embodiments, the semi-static signaling includes configuration activation indication information, which is used to instruct the terminal device to activate the target AI resource reporting configuration from at least one set of AI resource reporting configurations.

[0449] In some embodiments, the processor also performs the following operations:

[0450] The transceiver sends a configuration activation instruction to the terminal device, which is carried in semi-static or dynamic signaling.

[0451] In some embodiments, when the air interface resource acquisition method corresponding to the target AI resource reporting configuration is dynamic allocation of the reported resource location, the processor also performs the following operations:

[0452] The transceiver sends the reported resource location indication information to the terminal device.

[0453] In some embodiments, the processor also performs the following operations:

[0454] The transceiver sends a stop reporting instruction to the terminal device. The stop reporting instruction is used to instruct the terminal device to stop sending AI resource status information to the network device. The stop reporting instruction is carried in semi-static signaling or dynamic signaling.

[0455] In some embodiments, the stop reporting instruction information further includes a feedback confirmation identifier, which is used to instruct the terminal device to provide confirmation feedback on stopping the reporting of AI resource status information; the processor also performs the following operations:

[0456] Assign target resources to terminal devices that will stop reporting AI resource status information;

[0457] The transceiver receives confirmation feedback messages sent by the terminal device through the target resource.

[0458] In some embodiments, the processor also performs the following operations:

[0459] The AI ​​service configuration adjustment message is sent to the terminal device through the transceiver. The AI ​​service configuration adjustment message is used to adjust the configuration of the AI ​​service.

[0460] The transceiver receives configuration adjustment confirmation messages sent by the terminal device.

[0461] In some embodiments, the configuration corresponding to the AI ​​service includes at least one of the following:

[0462] The splitting points of the distributed or federated learning model corresponding to the AI ​​service;

[0463] Data transmission cycle of the model corresponding to the AI ​​service;

[0464] Data transmission bandwidth of the model corresponding to the AI ​​service;

[0465] Data transmission power of the model corresponding to the AI ​​service;

[0466] The data transmission bit width of the model corresponding to the AI ​​service.

[0467] In some embodiments, the processor also performs the following operations:

[0468] AI resource status information is sent to the terminal device via a transceiver.

[0469] In some embodiments, the processor also performs the following operations:

[0470] Based on the air interface information, AI resource information, and AI capability information of the neighboring cell network, determine the cell to be switched to for the terminal device.

[0471] The transceiver sends a cell handover instruction message to the terminal device. The cell handover instruction message contains at least one of the AI ​​capability information and AI resource status information of the cell to be handed over.

[0472] In Figure 17, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors 1401 (represented by the processor) and memory 1402 (represented by the memory). The bus architecture can also link various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides the interface. The transceiver can be multiple components, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, etc. The processor is responsible for managing the bus architecture and general processing, and the memory can store data used by the processor 1401 during operation.

[0473] The processor 1401 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor can also adopt a multi-core architecture.

[0474] This application also provides a processor-readable storage medium, which can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0475] In one embodiment, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described AI service cell access control method.

[0476] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0477] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0478] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0479] These processor-executable instructions may also be stored in a processor-readable memory that can instruct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0480] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0481] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

[0482] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no structural conflict, the various technical features mentioned in the embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. An access control method for an AI-serving cell, comprising: The terminal device receives information about the cell's artificial intelligence (AI) capabilities from the network device. The terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell. The terminal device accesses or reselects to the target cell.

2. The method of claim 1, wherein, The AI ​​capability information of the community includes at least one of the following: identification information, characteristic information, and service priority information; The identification information is used to indicate whether the cell has AI service capabilities, the characteristic information is used to indicate the capability characteristics of the AI ​​service capabilities of the cell, and the priority information is used to indicate the priorities of the carriers supported by different capability characteristics; the AI ​​capability information is transmitted through unicast messages or broadcast messages of the network device. The characteristic information includes at least one of the following: The types of capabilities supported by the community's AI services; The AI ​​service support model development framework for the community; The model structure supported by the community's AI services; The community's AI services support pre-built AI models and AI algorithms.

3. The method of claim 2, wherein, The identification information is carried in the main information block (MIB) of the broadcast message, and the characteristic information is carried in the system information block (SIB1) of the broadcast message; or, the identification information and the characteristic information are both carried in the SIB of the broadcast message.

4. The method of claim 1, wherein, The terminal device accessing or reselecting to the target cell includes: The terminal device sends an access request to the target cell to the network device. The access request includes access reason information, which indicates that the access reason of the terminal device is to request AI services.

5. The method of claim 4, wherein, The method further includes: The terminal device receives the creation message of the target radio bearer associated with the AI ​​service sent by the network device; The terminal device creates the target wireless bearer associated with the AI ​​service on the terminal device according to the creation message.

6. The method according to any one of claims 1 to 5, wherein, The method further includes: The terminal device receives semi-static signaling sent by the network device. The semi-static signaling includes at least one set of AI resource reporting configurations and is carried on the target radio bearer associated with the AI ​​service. The terminal device sends AI resource status information to the network device according to the at least one set of AI resource reporting configurations.

7. The method of claim 6, wherein, The AI ​​resource reporting configuration takes effect through immediate activation and activation via a configuration activation instruction message; the AI ​​resource reporting configuration includes at least one of the following: Configure index information; AI resource reporting content instructions; AI resource status reporting and air interface resource acquisition methods; The location of air interface resources reported by AI resource status; Information on AI resource reporting methods.

8. The method of claim 6, wherein, The terminal device sends AI resource status information to the network device according to the at least one set of AI resource reporting configurations, including: The terminal device activates the target AI resource reporting configuration in the at least one set of AI resource reporting configurations according to the configuration activation instruction information; The terminal device sends AI resource status information to the network device according to the target AI resource reporting configuration; The configuration activation indication information includes configuration index information of the target AI resource reporting configuration, and the configuration activation indication information is carried in the semi-static signaling or dynamic signaling.

9. The method according to claim 8, wherein, If the air interface resource acquisition method corresponding to the target AI resource reporting configuration is dynamically allocated and reported resource locations, then the method further includes: The terminal device receives the indication information of the reported resource location sent by the network device; The terminal device sends AI resource status information to the network device according to the target AI resource reporting configuration, including: the terminal device sends AI resource status information to the network device at the reported resource location according to the target AI resource reporting configuration.

10. The method of claim 6, wherein, The method further includes: When the terminal device meets the conditions for stopping the reporting of the AI ​​resource status information or receives a stop reporting instruction, it stops sending the AI ​​resource status information to the network device. The stop reporting condition is carried in the semi-static signaling, and the stop reporting indication information is carried in the semi-static signaling or dynamic signaling.

11. The method of claim 10, wherein, The stop reporting instruction information also includes a feedback confirmation identifier, which is used to instruct the terminal device to confirm the cessation of reporting the AI ​​resource status information.

12. The method of claim 6, wherein, The method further includes: The terminal device receives the configuration adjustment message for the AI ​​service sent by the network device; The terminal device adjusts the configuration corresponding to the AI ​​service according to the configuration adjustment message of the AI ​​service; The terminal device sends a configuration adjustment confirmation message to the network device; The configuration corresponding to the AI ​​service includes at least one of the following: The splitting points of the distributed or federated learning model corresponding to the AI ​​service; Data transmission cycle of the model corresponding to the AI ​​service; Data transmission bandwidth of the model corresponding to the AI ​​service; Data transmission power of the model corresponding to the AI ​​service; The data transmission bit width of the model corresponding to the AI ​​service.

13. The method of any one of claims 1-5, wherein, The method further includes: The terminal device receives AI resource status information sent by the network device.

14. The method of any one of claims 1-5, wherein, When the terminal device performs cell reselection, the terminal device determines the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell, including: The terminal device determines the target cell based on the cell reselection information and the AI ​​capability information.

15. The method of any one of claims 1-5, wherein, The method further includes: The terminal device receives a cell handover instruction message sent by the network device. The cell handover instruction message is used to instruct the terminal device to switch access to the cell to be handed over. The cell handover instruction message contains at least one of the AI ​​capability information and AI resource status information of the cell to be handed over. The terminal device switches access to the cell to be switched.

16. An access control method of an Al serving cell, wherein, Applied to network devices, including: The network device sends the cell's AI capability information to the terminal device; The network device receives an access request for a target cell sent by the terminal device. The target cell is a cell that supports the AI ​​service requested by the terminal device, and the target cell is determined based on the AI ​​capability information of the cell. The network device connects or reselects the terminal device to the target cell.

17. The method of claim 16, wherein, The AI ​​capability information of the community includes at least one of the following: identification information, characteristic information, and service priority information; The identification information is used to indicate whether the cell has AI service capabilities, the characteristic information is used to indicate the capability characteristics of the AI ​​service capabilities of the cell, the priority information is used to indicate the priority of the carriers supported by different capability characteristics, and the AI ​​capability information is transmitted through unicast messages or broadcast messages of the network device. The characteristic information includes at least one of the following: The types of capabilities supported by the community's AI services; The AI ​​service support model development framework for the community; The model structure supported by the community's AI services; The community's AI services support pre-built AI models and AI algorithms.

18. The method of claim 17, wherein, The identification information is carried in the main information block (MIB) of the broadcast message, and the characteristic information is carried in the system information block (SIB1) of the broadcast message; or, the identification information and the characteristic information are both carried in the SIB of the broadcast message.

19. The method of claim 16, wherein, The access request includes access reason information, which indicates that the access reason of the terminal device is a request for AI services; the method further includes: The network device creates a target wireless bearer for the AI ​​service association for the terminal device based on the access reason information. The network device sends a creation message for the target radio bearer associated with the AI ​​service to the terminal device.

20. The method of any one of claims 16-19, wherein, The method further includes: The network device acquires the AI ​​resource reporting capability information of the terminal device; When the AI ​​resource reporting capability information indicates that the terminal device supports AI resource reporting, the network device sends semi-static signaling to the terminal device. The semi-static signaling includes at least one set of AI resource reporting configurations and is carried on the target radio bearer associated with the AI ​​service. The network device receives AI resource status information sent by the terminal device according to the at least one set of AI resource reporting configurations.

21. The method according to claim 20, wherein the activation method of the AI ​​resource reporting configuration includes immediate activation and activation via a configuration activation indication message; the AI ​​resource reporting configuration includes at least one of the following: Configure index information; AI resource reporting content instructions; AI resource status reporting and air interface resource acquisition methods; The location of air interface resources reported by AI resource status; Information on AI resource reporting methods.

22. The method of claim 20, wherein, The semi-static signaling includes configuration activation indication information, which is used to instruct the terminal device to activate the target AI resource reporting configuration from the at least one set of AI resource reporting configurations.

23. The method of claim 20, wherein, The method further includes: The network device sends a configuration activation instruction to the terminal device, and the configuration activation instruction is carried in semi-static signaling or dynamic signaling.

24. The method of claim 22 or 23, wherein, If the target AI resource reporting configuration corresponds to the air interface resource acquisition method of dynamically allocating the reported resource location, then the method further includes: The network device sends the reported resource location indication information to the terminal device.

25. The method of claim 20, wherein, The method further includes: The network device sends a stop reporting instruction to the terminal device. The stop reporting instruction is used to instruct the terminal device to stop sending the AI ​​resource status information to the network device. The stop reporting instruction is carried in semi-static signaling or dynamic signaling.

26. The method of claim 25, wherein, The stop reporting instruction information also includes a feedback confirmation identifier, which is used to instruct the terminal device to confirm the cessation of reporting the AI ​​resource status information; the method further includes: The network device allocates a target resource to the terminal device to receive a confirmation feedback message to stop reporting the AI ​​resource status information; The network device receives the confirmation feedback message sent by the terminal device through the target resource.

27. The method of claim 20, wherein, The method further includes: The network device sends an AI service configuration adjustment message to the terminal device, the AI ​​service configuration adjustment message being used to adjust the configuration corresponding to the AI ​​service; The network device receives a configuration adjustment confirmation message sent by the terminal device; The configuration corresponding to the AI ​​service includes at least one of the following: The splitting points of the distributed or federated learning model corresponding to the AI ​​service; Data transmission cycle of the model corresponding to the AI ​​service; Data transmission bandwidth of the model corresponding to the AI ​​service; Data transmission power of the model corresponding to the AI ​​service; The data transmission bit width of the model corresponding to the AI ​​service.

28. The method of any one of claims 16-19, wherein, The method further includes: The network device sends AI resource status information to the terminal device.

29. The method of any one of claims 18-19, wherein, The method further includes: The network device determines the cell to be switched to by the terminal device based on the air interface information of the neighboring cell network, the AI ​​resource information of the neighboring cell network, and the AI ​​capability information of the neighboring cell network. The network device sends the cell handover instruction message to the terminal device. The cell handover instruction message contains at least one of the AI ​​capability information and AI resource status information of the cell to be handed over.

30. An access control apparatus of an Al serving cell, wherein, Applications in terminal devices, including memory, transceivers, and processors: A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: The transceiver receives information about the cell's artificial intelligence (AI) capabilities from network devices. Based on the AI ​​capability information of the cell, determine the target cell that supports the AI ​​service requested by the terminal device; Access or reselect to the target cell.

31. An access control apparatus of an Al serving cell, wherein, Applications in network devices, including memory, transceivers, and processors: A memory for storing computer programs; a transceiver for sending and receiving data under the control of the processor; and a processor for reading the computer programs from the memory and performing the following operations: The transceiver sends the cell's AI capability information to the terminal device. The transceiver receives an access request from the target cell sent by the terminal device. The target cell is a cell that supports the AI ​​service requested by the terminal device, and the target cell is determined based on the AI ​​capability information of the cell. The terminal device is connected to or reselected to the target cell.

32. An access control device for an AI-serving cell, wherein the terminal equipment includes: The first receiving module is used to receive the artificial intelligence (AI) capability information of the cell sent by the network device; The first processing module is used for the terminal device to determine the target cell that supports the AI ​​service requested by the terminal device based on the AI ​​capability information of the cell; and to access or reselect the target cell.

33. An access control apparatus of an Al serving cell, wherein, Applied to network devices, including: The first sending module is used to send the cell's AI capability information to the terminal device; The second receiving module is used to receive the access request of the target cell sent by the terminal device. The target cell is a cell that supports the AI ​​service requested by the terminal device. The target cell is determined based on the AI ​​capability information of the cell. The second processing module is used to connect or reselect the terminal device to the target cell.

34. A processor-readable storage medium, wherein, The processor-readable storage medium stores a program for causing the processor to perform the method according to any one of claims 1 to 37.

35. A computer program product, wherein, When the computer program product is invoked by a computer, it causes the computer to perform the method as described in any one of claims 1-37.

Images