Wireless communication method executed by authorized entity and communication equipment

Abstract

The invention provides a wireless communication method executed by an authorization entity and communication equipment. The method comprises the following steps: acquiring authorization information of terminal equipment; and determining whether to authorize an AI / ML service request related to the terminal device based on the authorization information, the AI / ML service request being used for requesting to transmit information associated with an AI / ML service to the terminal device, and / or the AI / ML service request being used for requesting to acquire the information of the terminal device to perform an AI / ML operation. In the application, the authorization entity determines whether to authorize the AI / ML service request related to the terminal equipment based on the authorization information of the terminal equipment, so that an authorization mechanism related to the AI / ML service request is clarified, and the information related to the AI / ML service is prevented from being acquired by an attacker.

Description

Technical Field

[0001] This application relates to the field of communication technology, and more specifically to a wireless communication method and communication device performed by a licensed entity. Background Technology

[0002] With the development of technology, the introduction of artificial intelligence / machine learning (AI / ML) technologies is a growing trend in communication systems. When applying AI / ML technologies, communication systems may involve the transmission of AI / ML-related information between different communication devices. However, AI / ML-related information is a crucial asset for AI / ML technology providers, therefore, it is essential to ensure the legitimacy of those who acquire it. Therefore, establishing an authorization mechanism for AI / ML-related information is of paramount importance. Summary of the Invention

[0003] This application provides a wireless communication method and communication device performed by an authorized entity. The various aspects covered in this application are described below.

[0004] In a first aspect, a wireless communication method executed by an authorized entity is provided, the method comprising: obtaining authorization information of a terminal device; determining, based on the authorization information, whether to authorize an AI / ML service request related to the terminal device, wherein the AI / ML service request is used to request the transmission of information associated with an AI / ML service to the terminal device, and / or, the AI / ML service request is used to request the acquisition of information from the terminal device for AI / ML operations.

[0005] Secondly, an authorization entity is provided, the authorization entity comprising: an acquisition module for acquiring authorization information of a terminal device; and an authorization module for determining, based on the authorization information, whether to authorize AI / ML service requests related to the terminal device, wherein the AI / ML service requests are used to request the transmission of information associated with AI / ML services to the terminal device, and / or, the AI / ML service requests are used to request the acquisition of information from the terminal device to perform AI / ML operations.

[0006] Thirdly, a wireless communication system is provided, comprising: a first network element, configured to obtain authorization information of the terminal device based on an AI / ML service request related to the terminal device, and determine whether to authorize the AI / ML service request based on the authorization information; wherein the AI / ML service request is used to request the transmission of information associated with the AI / ML service to the terminal device, and / or, the AI / ML service request is used to request the acquisition of information from the terminal device to perform AI / ML operations.

[0007] Fourthly, a communication device is provided, including a memory and a processor, the memory for storing a program, and the processor for calling the program in the memory to cause the communication device to perform the method as described in the first aspect.

[0008] In this application, the authorizing entity determines whether to authorize AI / ML service requests related to the terminal device based on the authorization information of the terminal device, thus clarifying the authorization mechanism related to AI / ML service requests and helping to prevent attackers from obtaining information related to AI / ML services. Attached Figure Description

[0009] Figure 1 This is a schematic diagram of the structure of a wireless communication system to which the embodiments of this application apply.

[0010] Figure 2 This is a schematic flowchart illustrating the transmission of AI / ML models within the same operator's network.

[0011] Figure 3 This is a schematic flowchart illustrating the transmission of AI / ML models across different carrier networks.

[0012] Figure 4 This is a schematic flowchart of a wireless communication method performed by an authorized entity according to an embodiment of this application.

[0013] Figure 5 This is an example diagram of a wireless communication method performed by an authorized entity according to an embodiment of this application.

[0014] Figure 6 This is a schematic flowchart of a wireless communication method performed by an authorized entity, provided in another embodiment of this application.

[0015] Figure 7 This is a schematic flowchart of a wireless communication method performed by an authorized entity, provided in another embodiment of this application.

[0016] Figure 8 This is a schematic flowchart of a wireless communication method performed by an authorized entity, provided in another embodiment of this application.

[0017] Figures 9A-9B This is a schematic flowchart of a wireless communication method performed by an authorized entity, provided in another embodiment of this application.

[0018] Figure 10 This is a schematic flowchart of a wireless communication method performed by an authorized entity, provided in another embodiment of this application.

[0019] Figure 11 This is a schematic diagram of the structure of the authorized entity provided in the embodiments of this application.

[0020] Figure 12 This is a schematic diagram of the wireless communication system provided in the embodiments of this application.

[0021] Figure 13 This is a schematic diagram of the communication device provided in the embodiments of this application. Detailed Implementation

[0022] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0023] Communication system architecture Figure 1 This is a schematic diagram of a communication system architecture applicable to embodiments of this application. The network architecture may include terminal equipment, access network (AN) elements, and core network elements.

[0024] It should be understood that the technical solutions of the embodiments of this application can be applied to various communication systems, such as: 5th generation (5G) systems or new radio (NR), long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, etc. The technical solutions provided in this application can also be applied to future communication systems, such as 6th generation mobile communication systems, satellite communication systems, and so on.

[0025] The terminal device in this application embodiment can also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless core network element, user agent, or user device. The terminal device in this application embodiment can be a device that provides voice and / or data connectivity to a user, and can be used to connect people, objects, and machines, such as handheld devices with wireless connectivity, vehicle-mounted devices, etc. The terminal devices in the embodiments of this application can be mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, self-driving, remote medical surgery, smart grids, transportation safety, smart cities, and smart homes, etc. Optionally, the terminal device can act as a base station. For example, the terminal device can act as a dispatching entity, providing sidelink signals between terminal devices in vehicle-to-everything (V2X) or device-to-device (D2D) communications. For example, cellular phones and cars communicate with each other using sidelink signals. Cellular phones and smart home devices communicate without relaying communication signals through base stations.

[0026] Access network elements can be access network devices. Access network devices are devices that terminals use to wirelessly access the network architecture. They are primarily responsible for air interface-side radio resource management, Quality of Service (QoS) management, data compression, and encryption. Access network devices can also be called radio access network (RAN) devices, such as base stations. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master eNB (MeNB), secondary eNB (SeNB), multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, base band unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, a device that performs base station functions in D2D, V2X, and machine-to-machine (M2M) communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. Base stations can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or device forms used in the access network equipment.

[0027] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0028] In some deployments, the access network device in this application embodiment may refer to a CU or a DU, or the access network device may include both a CU and a DU. The gNB may also include an AAU.

[0029] The types of core network elements can include user plane function (UPF) elements, access and mobility management function (AMF) elements, session management function (SMF) elements, policy control function (PCF) elements, application function (AF) elements, data network (DN), network slice selection function (NSSF), authentication server function (AUSF), unified data management (UDM), network exposure function (NEF), network repository function (NRF), and network slice-specific authentication and authorization function (NSSAAF). In addition, some networks (such as 5G networks) have added a network data analytics function (NWDAF) to the core network. NWDAF can be further divided into analytics logical function (AnLF) and model training logical function (MTLF). In some communication systems (such as 5G systems), core network elements can also be called network functions (NFs).

[0030] Figure 1Each network element can be a network component in a hardware device, a software function running on dedicated hardware, or a virtualized function implemented on a platform (e.g., a cloud platform). It should be noted that the network architecture shown in the above figures is merely an illustrative representation of the network elements included in the overall network architecture. The embodiments of this application do not limit the network elements included in the entire network architecture.

[0031] Those skilled in the art will understand that Figure 1 The network architecture shown does not constitute a limitation on the network architecture. In actual implementation, the network architecture may include more or fewer network elements than shown, or combine certain network elements, etc. It should be understood that... Figure 1 In this context, AN or RAN is represented by (R)AN.

[0032] In some scenarios, network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenarios in which the network devices and terminal devices are located.

[0033] AI / ML services in communication systems In communication systems, AI / ML services can include AI / ML services that enhance the application layer and AI / ML services that enhance communication capabilities (also known as "AI enhancements"). Communication systems provide auxiliary capabilities to support application-layer AI / ML operations, such as AI / ML operation separation between AI / ML endpoints, AI / ML model / data distribution and sharing, and distributed / federated learning. To enhance application-layer AI / ML services, considerations include how to design QoS to satisfy transmission and how to select UEs to participate in federated learning. Key application cases for AI enhancements include channel state information (CSI) feedback enhancement, beam management enhancement, and positioning accuracy enhancement.

[0034] CSI feedback enhancement primarily refers to using AI / ML models on both sides to perform CSI compression in the spatial frequency domain. These AI / ML models can be jointly trained on one side (either the terminal device side or the network side). Joint training involves training the generative and reconstructed models through forward and backward propagation within the same loop. Joint training can be performed on a single node or across multiple nodes through gradient exchange between nodes. Joint training can include: the network side and the terminal device side jointly training the two models respectively; or the network side and the terminal device side training separately, with the terminal device side training the CSI generation part and the network side training the CSI reconstruction part.

[0035] Beam management enhancement mainly refers to using AI / ML models for spatial domain beamprediction or temporal domain beam prediction. The training and derivation of the AI / ML models can be performed on the network side or on the terminal device side.

[0036] Enhancing positioning accuracy can include using AI / ML models for direct positioning and assisted positioning.

[0037] Transmission of AI / ML models in communication systems The aforementioned AI / ML services may involve the transmission of AI / ML model-related information (including the AI / ML model itself and its associated information) between different devices. Typically, AI / ML model-related information can be transmitted over the carrier's network. For example... Figure 2As shown, model-related information can be transmitted within the same operator's network. In step S210, the NWDAF service consumer can subscribe to / unsubscribe from an ML model to another NWDAF (an NWDAF containing the MTLF) through relevant service requests, such as the NWDAF_MLModelProvision_Subscribe request and the NWDAF_MLModelProvision_Unsubscribe request. In step S220, the NWDAF can respond to the above requests with relevant messages, such as the NWDAF_MLModelProvision_Notify message. The NWDAF service consumer can carry an analytics identifier (ID) in the service request, and the NWDAF can notify the NWDAF service consumer of ML model information (e.g., a unique ML model identifier) ​​in the service request response. For example... Figure 3 As shown, model-related information can also be transmitted across different operator networks. In step S310, the NWDAF service consumer can also subscribe to / unsubscribe from an ML model to another NWDAF (an NWDAF containing the MTLF) via the Nnwdaf_MLModelProvision_Subscribe request and the Nnwdaf_MLModelProvision_Unsubscribe request. In step S320, the NWDAF can respond to the above requests via the Nnwdaf_MLModelProvision_Notify message. The NWDAF service consumer can carry ML model interoperability information in the service request to support model transmission across multiple operators. This information can be operator-specific information (e.g., the requested model format, model execution environment, etc.).

[0038] With the development of AI / ML services, terminal devices may also participate in AI / ML model training. Therefore, AI / ML model-related information may be transmitted between the network and terminal devices. For example, in CSI feedback enhancement or beam management enhancement, AI / ML model-related information may be transmitted between the terminal device and gNB, the terminal device and the network side, or the terminal device and server-applicable applications. Similarly, in positioning accuracy enhancement, AI / ML model-related information may be transmitted between the terminal device and the location management function (LMF) of the network-side positioning elements, or between the terminal device and server-applicable applications.

[0039] Furthermore, whether it's AI / ML services that enhance the application layer or AI / ML services that enhance communication capabilities, the network may also transmit auxiliary information related to AI / ML services to the terminal devices to assist them in performing AI / ML operations. For example, the network may provide the AF (Application Analyzer) and the terminal device's client with the network status of each terminal device (such as bit rate, latency, reliability, network performance analysis, etc.) to assist in AI / ML operations.

[0040] However, AI / ML model-related information and network-aided information are crucial assets for model providers (such as operators). Therefore, ensuring the legitimacy of the terminal devices acquiring this information is paramount. Otherwise, attackers could potentially steal AI / ML models and related information, or network-aided information, from the network side.

[0041] Based on the above problems, the embodiments of this application will be described in detail below.

[0042] like Figure 4 As shown, this application provides a wireless communication method executed by an authorized entity. The authorized entity is a network-side entity, which can be a network element in the core network as described above, such as NWDAF, gateway mobile location center (GMLC), LMF, AMF, etc. Alternatively, the authorized entity can be a network element in the access network as described above, such as a base station. Or, the authorized entity can also be an operation administration and maintenance (OAM) network element.

[0043] Figure 4 The method shown may include steps S410 to S420.

[0044] In step S410, the authorizing entity obtains the authorization information of the terminal device. The authorization information can be stored locally on the authorizing entity, allowing the entity to retrieve it locally. Alternatively, the authorization information can be stored on an entity other than the authorizing entity (hereinafter referred to as the "authorizing information storage entity"), in which case the authorizing entity can request the authorization information from the authorization information storage entity. As an example, the authorization information can be stored in the core network's UDM or unified data repository (UDR).

[0045] In step S420, the authorizing entity determines whether to authorize the AI / ML service request related to the terminal device based on the authorization information. The AI / ML service request is used to request the transmission of information associated with the AI / ML service to the terminal device, and / or, the AI / ML service request is used to request the acquisition of information from the terminal device to perform AI / ML operations. AI / ML operations may refer to operations related to AI / ML models, such as training AI / ML models. The authorization information may be determined based on the terminal device's subscription data, and / or, the authorization information may also be determined based on the terminal device's instructions.

[0046] AI / ML services can refer to services or operations involving AI / ML models, and may include AI / ML services that enhance the application layer or AI / ML services that enhance communication capabilities, as mentioned above. AI / ML services that enhance communication capabilities may include AI / ML model-based positioning services, AI / ML model-based CSI feedback services, and AI / ML model-based beam management services, etc.

[0047] Information associated with AI / ML services may include AI / ML model-related information and / or network-aided information. AI / ML model-related information may include the AI / ML model and related information. Network-aided information can be used to assist AI / ML services and may include network status of terminal devices, network performance analysis, and information assisting in AI / ML model training. For example, network-aided information may include communication link quality, QoS analysis, and NWDAF prediction information. Information associated with AI / ML services may be stored in an authorized entity or in other entities (hereinafter referred to as the "AI / ML service information storage entity"). For example, the AI / ML service information storage entity may be network elements such as NWDAF, LMF, and OAM. If the authorized entity does not store information associated with the AI / ML service, the authorized entity may request the AI / ML service information storage entity to obtain such information. It is worth noting that, based on the request from the authorized entity, the AI / ML service information storage entity may also determine whether to authorize the AI / ML service request based on the authorization information.

[0048] AI / ML service requests can be triggered by authorized entities, which can initiate AI / ML service requests within the AI / ML service itself. For example, in a location service based on an AI / ML model, an authorized entity can trigger an AI / ML service request to obtain information from the terminal device for AI / ML operations. Alternatively, AI / ML service requests can also be triggered by entities other than authorized entities (hereinafter referred to as "AI / ML service request entities"). AI / ML service request entities can be network elements in the core network, terminal devices, external servers, external clients, etc. For example, a terminal device can trigger an AI / ML service request through registration. Again, in a location service based on an AI / ML model, a terminal device can initiate an AI / ML service request to an authorized entity to obtain an AI / ML model for location services. Alternatively, in a location service based on an AI / ML model, a location client or core network elements such as NWDAF can also initiate an AI / ML service request to an authorized entity to request the transmission of the AI / ML model to the terminal device to obtain the terminal device's location information. For example, in AI / ML model-based CSI feedback services or AI / ML model-based beam management services, terminal devices can trigger AI / ML service requests by reporting AI / ML capability information to authorized entities to request AI / ML model-related information and network auxiliary information. Similarly, network elements storing AI / ML models (such as gNB, OAM, or NWDAF) can also initiate AI / ML service requests to authorized entities to obtain terminal device information (such as QoS, terminal mobility information, and terminal IP address) for AI / ML model training.

[0049] In this application, the authorizing entity determines whether to authorize AI / ML service requests related to the terminal device based on the authorization information of the terminal device, thus clarifying the authorization mechanism related to AI / ML service requests and helping to prevent attackers from obtaining information related to AI / ML services.

[0050] The following provides a detailed description of the authorization information. Authorization information may include AI / ML subscription data from the terminal device and / or AI / ML configuration information from the terminal device.

[0051] AI / ML subscription data of a terminal device can refer to the terminal device's subscription data for AI / ML services. AI / ML subscription data may include information related to the public land mobile network (PLMN) that allows the terminal device to use AI / ML services, and / or information related to the AI / ML services that allow the terminal device to use.

[0052] A PLMN that allows end devices to use AI / ML services can refer to a PLMN in which the end device is authorized to use AI / ML services, or a PLMN in which the end device is authorized to use a specific AI / ML service. Information related to PLMNs that allow end devices to use can be represented by a set of PLMNs or a list of PLMNs.

[0053] Information related to AI / ML services permitted for use by terminal devices may include at least one of the following: information indicating permission for terminal devices to use AI / ML services; AI / ML model information; and the types of services to which the AI / ML model applies. The information indicating permission for terminal devices to use AI / ML services may be information indicating that the terminal device is authorized to access AI / ML models. AI / ML model information may include the storage location of the AI / ML model, the model ID of the AI / ML model, the type of the AI / ML model, and the version of the AI / ML model. The types of services to which the AI / ML model applies may include location services based on AI / ML models, CSI services based on AI / ML models, beam management services based on AI / ML models, energy-saving services based on AI / ML models, and mobility optimization services based on AI / ML models.

[0054] AI / ML subscription data can be determined based on the subscription data of the terminal device. For example, AI / ML subscription data can be generated and maintained by the operator based on the subscription data of the subscribers. Therefore, the terminal device or application function AF cannot directly change the AI / ML subscription data, but it can be changed by updating the subscription data. For example, the terminal device can change the AI / ML subscription data by changing the operator's plan.

[0055] The AI / ML configuration information of a terminal device, also known as an AI / ML profile, can include information indicating whether the terminal device allows AI / ML model transmission and / or training. Typically, the types of models a terminal device can support are related to its capabilities, computing power, and storage. However, the state of a terminal device can change, so the models it can support are not static. Furthermore, due to the mobility of terminal devices, the applicable areas for training models may also change. Alternatively, in some cases, the terminal device may not be able to support high-precision models. Therefore, when determining whether to transmit information associated with AI / ML services to a terminal device, the authorizing entity can also determine whether the terminal device supports training and / or transmitting AI / ML models based on the terminal device's state information. However, since certain state information of the terminal device (such as battery level, computing power, and storage size) is considered private information and cannot be accessed by the network side, the network side cannot determine whether the terminal device is available for model transmission and / or model training at a given time. Therefore, AI / ML configuration information allows the network side to clearly define whether a terminal device is available for model transmission and / or model training, helping to protect the privacy of the terminal device.

[0056] AI / ML configuration information can be determined based on instructions from the terminal device. For example, the terminal device can trigger the update of AI / ML configuration information via a non-access stratum (NAS) message. Alternatively, an authorized AF can update the AI / ML configuration information for the terminal device via NEF. Furthermore, when the terminal device prohibits model transmission or model training, it can report this instruction to the network side, updating its authorization information by updating its AI / ML configuration information.

[0057] It is worth noting that in some implementations, AI / ML configuration information can also be determined based on location service (LCS) privacy configuration information. For example, when the AI / ML service described above is a location service based on an AI / ML model, the authorized entity can determine the AI / ML configuration information of the terminal device based on the terminal device's LCS privacy configuration information. The terminal device's LCS privacy configuration information can be obtained through the terminal device's LCS privacy profile. Furthermore, the AI / ML configuration information may include a location privacy indication (LPI) from the LCS privacy configuration information. The LPI can be used to indicate whether the terminal device is allowed to perform location operations based on the AI / ML model. The LPI can be an AI-based location privacy indication (AILPI) specifically for AI / ML services, or it can be an existing LPI in the LCS privacy profile.

[0058] The following is combined with Figure 5 The following describes an example of a wireless communication method performed by an authorized entity according to an embodiment of this application. Exemplarily, Figure 5 In the method shown, authorization information and information associated with the AI / ML service are stored in an entity other than the authorization entity, and the AI / ML service request is initiated by the entity other than the authorization entity. Specifically, the authorization information is stored in an authorization information storage entity, the information associated with the AI / ML service is stored in an AI / ML service information storage entity, and the AI / ML service request is initiated by an AI / ML service request entity. Of course, the authorization information and information associated with the AI / ML service can also be stored in the authorization entity, and the AI / ML service request can also be initiated by the authorization entity; this application does not limit this. Figure 5 As shown, the method may include steps S510 to S580.

[0059] In step S510, the AI / ML service requesting entity initiates an AI / ML service request to the authorized entity. The AI / ML service request can be used to request the transmission of information associated with the AI / ML service to the terminal device. Alternatively, the AI / ML service request can also be used to request information from the terminal device to perform AI / ML operations. The AI / ML service request may carry the terminal device's ID, such as a subscription permanent identifier (SUPI), a subscription concealed identifier (SUCI), or a generic public subscription identifier (GPSI), to indicate the terminal device to which the AI / ML service request is targeted.

[0060] In step S520, the authorizing entity sends an authorization information request message to the authorization information storage entity. The authorization information request message may carry the ID of the terminal device to indicate the terminal device to which the request message is addressed.

[0061] In step S530, the authorization information storage entity retrieves the authorization information of the terminal device.

[0062] In step S540, the authorization information storage entity sends the authorization information of the terminal device to the authorization entity.

[0063] In step S550, the authorizing entity checks the authorization information to determine whether to authorize the AI / ML service request. If the authorizing entity determines to authorize the AI / ML service request, proceed to step S560.

[0064] In step S560, the authorizing entity sends a request message to the AI / ML service information storage entity for information / terminal device information associated with the AI / ML service. The request message may carry the terminal device ID to indicate the terminal device to which the request is directed.

[0065] In step S570, the AI / ML service information storage entity sends information / terminal device information associated with the AI / ML service to the authorized entity.

[0066] In step S580, the authorizing entity sends information associated with the AI / ML service / terminal device to the AI / ML service requesting entity. It is worth noting that the AI / ML service information storage entity can also directly transmit information associated with the AI / ML service to the terminal device (not shown in the figure).

[0067] based on Figure 5The method shown allows the authorizing entity to determine an authorization mechanism for transmitting information associated with AI / ML services to the terminal device or for requesting the AI / ML service entity to transmit information from the terminal device based on the authorization information of the terminal device. This helps ensure the security of information associated with AI / ML services and information from the terminal device.

[0068] The following examples, using Embodiments 1 to 4, illustrate how to apply the methods of this application in different scenarios. In these different scenarios, the AI / ML service information storage entity differs. In Embodiments 1 to 3, the AI / ML service information storage entity is a network element in the core network. In Embodiment 4, the AI / ML service information storage entity is an entity (e.g., a base station) or OAM in the access network. For ease of understanding, in the following description, the authorized entity may also be referred to as an "authorized node".

[0069] Example 1 Example 1 applies to scenarios where the UE, as a consumer of network-side models (the model itself, model information), data used to assist the UE in training the model, or network auxiliary information (such as communication link quality, QoS analysis, NWDAF prediction information, etc.), needs to obtain relevant information from the NWDAF. For example, in Example 1, the AI / ML service information storage entity is the NWDAF, the authorizing node is the NF in the core network, such as AMF, PCF, LMF, NWDAF, or UDM, the authorizing information storage entity is the UDM, and the AI / ML service request entity is the UE. Figure 6 As shown, the method in Embodiment 1 may include steps S610 to S680.

[0070] In step S610, the UE initiates a registration request or an AI / ML service request to the NF to request AI / ML model-related information, data to assist the UE in training the model, or network-assisted information. The UE may include its ID and capability information in the request.

[0071] In step S620, the NF sends an Authorization Request message or a Nudm_SDM_Request message to the UDM to request the UE's authorization information. The NF may include the UE's ID in the request.

[0072] In step S630, UDM retrieves the UE's authorization information.

[0073] In step S640, UDM sends an Authorization Response message or a UDM_SDM_Response message to NF. The response message may carry the UE's authorization information.

[0074] In step S650, the NF checks the UE's authorization information to determine whether to authorize the UE to obtain AI / ML model-related information, data used to assist the UE in training the model, or network-aided information. If the NF determines to authorize the UE's AI / ML service request based on the authorization information, then proceed to step S660.

[0075] In step S660, NF sends an NWDAF_model (Nnwdaf_model) message or an analytics_Request (analytics_Request) message to NWDAF to request the transmission of AI / ML model-related information, data used to assist UE in training the model, or network-assisted information to the terminal device.

[0076] In step S670, the NWDAF sends an Nnwdaf_model message or an analytics_Response message to the NF. The NWDAF transmits AI / ML model-related information, data to assist the UE in model training, or network-aided information (not shown in the figure) to the UE. The NWDAF can transmit AI / ML model-related information, data to assist the UE in model training, or network-aided information to the UE via control plane signaling, for example, via NWDAF-AMF-UE. Alternatively, considering the size of the AI / ML model, the NWDAF can also transmit AI / ML model-related information, data to assist the UE in model training, or network-aided information to the UE via user plane data, for example, by establishing a specific protocol data unit (PDU) session through the UPF.

[0077] In step S680, the NF sends an AI / ML service response message or a registration response message to the UE.

[0078] Based on the method in Embodiment 1, when the network transmits AI / ML model-related information, data used to assist the UE in training the model, or network-assisted information in NWDAF to the UE, it can determine the legitimacy of the UE based on the UE's authorization information, which helps to ensure the security of AI / ML model-related information, data used to assist the UE in training the model, and network-assisted information.

[0079] Example 2 Example 2 is applicable to scenarios where the UE, as a consumer of network-side models (the model itself, model information) and network auxiliary information (such as communication link quality, QoS analysis, NWDAF prediction information, etc.), needs to obtain relevant information from the LMF. For example, Example 2 can be applied to the sidelink (SL)-mobile originating-location request ((SL)-MO-LR) process in location services. For AI / ML-based location services, the AI / ML model may be stored in the LMF, in which case the authorized node on the network side can determine whether it can transmit relevant information to the UE. Alternatively, the LMF can obtain the model through NWDAF, in which case the LMF can act as an authorized node to determine whether it can transmit relevant information to the UE. The following is combined with... Figure 7 Taking the AI / ML service information storage entity as LMF, the authorized node as NF in the core network (such as AMF, LMF, LMF, or UDM), the authorized information storage node as UDM, and the AI / ML service request entity as UE as an example, the method of Embodiment 2 will be described. Figure 7 As shown, the method in Embodiment 2 of this application may include steps S710 to S780.

[0080] In step S710, the UE initiates a registration request or AIML service request to the NF to request AI / ML model-related information, data to assist the UE in training the model, or network-assisted information. The UE may include its ID and capability information in the request.

[0081] In step S720, the NF sends an Authorization Request message or a Nudm_SDM_Request message to the UDM to request the UE's authorization information. The NF may include the UE's ID in the request to specify the terminal device to which the request is directed.

[0082] In step S730, UDM retrieves the UE's authorization information.

[0083] In step S740, the UDM sends an Authorization Response message or a Nudm_SDM_Response message to the NF. The response message may carry the UE's authorization information.

[0084] In step S750, the NF checks the UE's authorization information to determine whether to authorize the UE to obtain AI / ML model-related information, data used to assist the UE in training the model, or network-aided information. If the NF determines to authorize the UE's AI / ML service request based on the authorization information, then proceed to step S760.

[0085] In step S760, the NF sends an LMF_model_request (Nlmf_model_Request) message to the LMF. The NF may also include the UE's ID in the request to specify the terminal device to which the request is directed.

[0086] In step S770, the LMF sends an LMF_model_response (Nlmf_model_Response) message to the NF. The LMF sends AI / ML model-related information, data to assist the UE in training the model, or network-aided information (not shown in the figure) to the UE.

[0087] In step S780, the NF sends an AIML service Response message or a registration response message to the UE.

[0088] Based on the method in Embodiment 2, when the network transmits AI / ML model-related information in the LMF, data used to assist the UE in training the model, or network auxiliary information to the UE, it can determine the legitimacy of the UE based on the UE's authorization information, which helps to ensure the security of AI / ML model-related information, data used to assist the UE in training the model, and network auxiliary information.

[0089] Example 3 Example 3 applies to scenarios where an external client or core network element initiates a service exposure request to the network to request the transmission of network-side AI / ML related information to the UE. For example, during a mobile termination-location request (MT-LR) process, an LCS client, AF, or NF (such as NWDAF) can initiate a service exposure request to the network to obtain the target UE's location information. In this scenario, the network can transmit AI / ML model-related information to the target UE to improve positioning accuracy, data to assist the UE in training the model, or network-aided information, enabling the target UE to calculate its own location information based on the AI / ML model. Furthermore, the network-side GMLC can determine the legitimacy of the target UE based on its authorization information. The following section combines... Figure 8 Taking the AI / ML service information storage entity as LMF, the authorized node as GMLC in the core network, the authorized information storage node as UDM, and the AI / ML service request entity as LCS client / AF / NF as an example, the method of Embodiment 3 will be introduced. Figure 8 As shown, the method in Embodiment 3 may include steps S810 to S880.

[0090] In step S810, the LCS client / AF / NF initiates a service exposure request to the GMLC to request the location information of the target UE. The request may include the ID of the target UE.

[0091] In step S820, the GMLC sends an Authorization Request message or a Nudm_SDM_Request message to the UDM to request authorization information from the target UE. The GMLC may include the target UE's ID in the request to clearly identify the terminal device to which the request is directed.

[0092] In step S830, UDM retrieves the authorization information of the target UE.

[0093] In step S840, the UDM sends an Authorization Response message or a Nudm_SDM_Response message to the GMLC. The response message may carry the authorization information of the target UE.

[0094] In step S850, the GMLC checks the authorization information of the target UE to determine whether it authorizes the target UE to obtain AI / ML model-related information, data used to assist the UE in training the model, or network-assisted information for positioning operations. If the GMLC determines that it authorizes the target UE to obtain AI / ML model-related information, data used to assist the UE in training the model, or network-assisted information, then proceed to step S860.

[0095] In step S860, the GMLC sends an Nlmf_model_Request message to the LMF to request the transmission of AI / ML model-related information, data used to assist the UE in training the model, or network-aided information to the target UE. The GMLC may also include the target UE's ID in the request to specify the terminal device to which the request is directed.

[0096] In step S870, the LMF sends an Nlmf_model_Response message to the GMLC. The LMF sends AI / ML model-related information, data to assist the UE in training the model, or network-aided information (not shown in the figure) to the target UE.

[0097] In step S880, GMLC sends a service request response message to the LCS client / AF / NF.

[0098] It is worth noting that during the (SL)-MT-LR process, the above-mentioned process of GMLC checking the target UE's authorization information can be carried out together with the process of GMLC checking the target UE's subscription data.

[0099] Furthermore, in sidelink positioning, the LMF can determine whether the serving UE should calculate the positioning result. Therefore, in AI-based positioning enhancement, the network can also transmit AI / ML model-related information to the serving UE to improve positioning accuracy, data to assist the UE in training the model, or network-aided information, enabling the serving UE to calculate the target UE's location information based on the AI / ML model. Thus, in the method of Embodiment 3, the network-side GMLC can also determine the legitimacy of the serving UE based on its authorization information.

[0100] Based on the method in Embodiment 3, during the 5GC-MT-LR process, when the network transmits AI / ML model-related information, data used to assist the UE in training the model, or network auxiliary information to the UE, it can determine the legitimacy of the UE based on the UE's authorization information, which helps to ensure the security of AI / ML model-related information, data used to assist the UE in training the model, and network auxiliary information.

[0101] Example 4 Example 4 applies to scenarios where AI / ML model-related information is stored in the access network or OAM. For example, the RAN side already has AI / ML functionality for beam management or CSI feedback processes. That is, the RAN side already has the relevant model, and can transmit AI / ML model-related information, data used to assist the UE in model training, or network auxiliary information to the UE. Alternatively, the AI / ML model may also be stored in the OAM. The AI / ML model-related information, data used to assist the UE in model training, or network auxiliary information can then be transmitted to the RAN side via the OAM, and then from the RAN side to the UE. Therefore, the RAN-side gNB or OAM can act as an authorized node, determining whether to authorize the transmission of AI / ML model-related information, data used to assist the UE in model training, or network auxiliary information to the UE based on UE authorization information stored locally or obtained through the core network's UDM or AMF. Alternatively, if the gNB or OAM is not an authorized node, it can send an authorization request to the network side. After authorization, the network element (NF) on the network side (e.g., AMF, LMF) returns the authorization result to the gNB or OAM. The gNB or OAM then determines whether the AI / ML model, data used to assist the UE in model training, or network-assisted information can be transmitted to the UE based on the authorization result. Alternatively, the gNB can also determine whether the AI / ML model, data used to assist the UE in model training, or network-assisted information can be transmitted to the UE based on the OAM's authorization result.

[0102] The following is combined Figure 9A , Figure 9B and Figure 10 The method of Embodiment 4 will be described in detail. Exemplarily, in Embodiment 4, the AI / ML service information storage entity is the OAM, the authorizing node is the gNB in ​​the access network or the NF in the core network or the OAM, the authorizing information storage node is the UDM, and the AI / ML service request entity is the UE.

[0103] The interaction process of each entity in Example 4 can be as follows: Figure 9A As shown, it includes steps S910 to S970.

[0104] In step S910, the UE initiates an AI / ML service request to the RAN side to request an AI / ML model.

[0105] In step S920, the RAN sends an authorization information request to the UDM of the core network.

[0106] In step S930, the core network's UDM returns UE authorization information to the RAN.

[0107] In step S940, the RAN checks the UE authorization information to determine whether to authorize the UE's AI / ML service request. If the RAN determines to authorize the UE's AI / ML service request, then proceed to step S950.

[0108] In step S950, RAN sends an AI / ML model request to OAM.

[0109] In step S960, OAM returns the AI / ML model to RAN.

[0110] In step S970, the RAN returns the AI / ML model to the UE.

[0111] The interaction process of the entities in Example 4 can also be as follows: Figure 9B As shown, it includes steps S910 to S970.

[0112] In step S910, the UE initiates an AI / ML service request to the RAN side to request an AI / ML model.

[0113] In step S920, the RAN sends an authorization check request to the NF (e.g., AMF, LMF) of the core network.

[0114] In step S930, the NF (e.g., AMF, LMF) checks the UE authorization information.

[0115] In step S940, the NF of the core network returns an authorization check response to the RAN.

[0116] In step S950, RAN sends an AI / ML model request to OAM.

[0117] In step S960, OAM returns the AI / ML model to RAN.

[0118] In step S970, the RAN returns the AI / ML model to the UE.

[0119] It is worth noting that, Figure 9A , Figure 9B In the method shown, RAN can also be replaced with OAM, and the corresponding method may not include steps S950 and S960.

[0120] Furthermore, the detailed process of the method in Example 4 can be described as follows: Figure 10 As shown, it may include steps S1010 to S1070.

[0121] In step S1010, the UE initiates a UE capability report to the gNB. The UE capability report can trigger an AI / ML service request to obtain an AI / ML model. The network-side authorization process for the UE-triggered AI / ML service request can include the following three scenarios.

[0122] If the gNB is an authorized node, and if the gNB locally stores the UE's authorization information, then proceed to step S1020, where the gNB checks the UE's authorization information. In step S1060, based on the authorization result, the gNB decides whether to transmit the AI / ML model to the UE. In step S1070, the gNB transmits the AI / ML model to the UE. If the gNB is an authorized node, and it does not store the UE's authorization information locally, then proceed to step S1030, where the gNB sends an authorization information request to the UDM in the core network. In step S1040, the UDM retrieves the UE's authorization information. Then, proceed to step S1050, where the UDM sends an authorization information response to the gNB. Subsequently, the gNB checks the UE's authorization information again, and in step S1070, the gNB transmits the AI / ML model to the UE. If the gNB is not an authorized node, proceed to step S1030, where the gNB sends an authorization check request to the NF or OAM of the core network. In step S1040, the NF or OAM of the core network checks the UE's authorization information. Proceed to step S1050, the NF or OAM of the core network returns an authorization check response to the gNB. In step S1060, based on the authorization result, the gNB decides whether to transmit the AI / ML model to the UE. In step S1070, the gNB transmits the AI / ML model to the UE.

[0123] It is worth noting that, Figure 10 In the method shown, gNB can also be replaced by OAM. In the case that OAM is not an authorized node, OAM sends an authorization check request to NF in step S1030.

[0124] Based on the method in Embodiment 4, when the gNB or OAM transmits the AI / ML model to the UE, it can determine the legitimacy of the UE based on the UE's authorization information, which helps to ensure the security of the AI / ML model.

[0125] The above text combined Figures 1 to 10 The method embodiments of this application are described in detail below, in conjunction with... Figures 11 to 13 The present application provides a detailed description of the apparatus embodiments. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments; therefore, any parts not described in detail can be found in the foregoing method embodiments.

[0126] Figure 11 This is a schematic diagram of the structure of the authorized entity provided in the embodiments of this application. Figure 11 The authorized entity 1100 includes an acquisition module 1110 and an authorization module 1120. The acquisition module 1110 is used to acquire authorization information of the terminal device, and the authorization module 1120 is used to determine whether to authorize AI / ML service requests related to the terminal device based on the authorization information. The AI / ML service request is used to request the transmission of information associated with the AI / ML service to the terminal device, and / or, the AI / ML service request is used to request the acquisition of information from the terminal device to perform AI / ML operations.

[0127] In some implementations, the authorization information includes AI / ML subscription data of the terminal device and / or AI / ML configuration information of the terminal device.

[0128] In some implementations, AI / ML subscription data includes at least one of the following: information indicating permission for terminal devices to use AI / ML services; a set of public terrestrial mobile networks (PLMNs) that allow terminal devices to use AI / ML services; AI / ML model information; and the type of service to which the AI / ML model is applicable.

[0129] In some implementations, the AI / ML configuration information includes at least one of the following: information indicating whether the terminal device allows the transmission of AI / ML models; information indicating whether the terminal device allows the training of AI / ML models.

[0130] In some implementations, AI / ML configuration information is determined based on location service (LCS) privacy configuration information.

[0131] In some implementations, the AI / ML configuration information includes the Location Privacy Indicator (LPI) in the LCS privacy configuration information. The LPI is used to indicate whether the terminal device is allowed to perform location operations based on the AI / ML model.

[0132] In some implementations, the information associated with AI / ML services includes at least one of the following: AI / ML model-related information; network-assisted information used to support AI / ML services.

[0133] In some implementations, the authorization information is determined based on the terminal device's subscription data, and / or, the authorization information is determined based on the terminal device's instructions.

[0134] Figure 12 The figure shown is a schematic diagram of the wireless communication system provided in an embodiment of this application. Figure 12 The wireless communication system 1200 includes a first network element 1210. The first network element 1210 is used to obtain authorization information from the terminal device based on an AI / ML service request related to the terminal device, and to determine whether to authorize the AI / ML service request based on the authorization information. The AI / ML service request is used to request the transmission of information associated with the AI / ML service to the terminal device, and / or, the AI / ML service request is used to request information from the terminal device to perform AI / ML operations.

[0135] In some implementations, the system also includes a second network element 1220, which is used to initiate AI / ML service requests to the first network element 1210.

[0136] In some implementations, the system also includes a third network element 1230, which stores information associated with the AI / ML service and transmits the information associated with the AI / ML service to the terminal device based on the authorization of the AI / ML service request by the first network element 1210.

[0137] In some implementations, the system also includes a fourth network element 1240, which stores authorization information and transmits authorization information to the first network element 1210 based on the request of the first network element 1210.

[0138] In some implementations, the authorization information includes AI / ML subscription data of the terminal device and / or AI / ML configuration information of the terminal device.

[0139] In some implementations, AI / ML subscription data includes at least one of the following: information indicating permission for terminal devices to use AI / ML services; a set of public terrestrial mobile networks (PLMNs) that allow terminal devices to use AI / ML services; AI / ML model information; and the type of service to which the AI / ML model is applicable.

[0140] In some implementations, the AI / ML configuration information includes at least one of the following: information indicating whether the terminal device allows the transmission of AI / ML models; information indicating whether the terminal device allows the training of AI / ML models.

[0141] In some implementations, AI / ML configuration information is determined based on location service (LCS) privacy configuration information.

[0142] In some implementations, the AI / ML configuration information includes the Location Privacy Indicator (LPI) in the LCS privacy configuration information. The LPI is used to indicate whether the terminal device is allowed to perform location operations based on the AI / ML model.

[0143] In some implementations, the information associated with AI / ML services includes at least one of the following: AI / ML model-related information; network-assisted information used to support AI / ML services.

[0144] In some implementations, the authorization information is determined based on the terminal device's subscription data, and / or, the authorization information is determined based on the terminal device's instructions.

[0145] Figure 13 This is a schematic diagram of the communication device provided in the embodiments of this application. Figure 13 The communication device 1300 can be used to implement the methods described in the above method embodiments. The device 1300 can be a chip, a terminal device, or a base station.

[0146] The communication device 1300 may include one or more processors 1310. The processor 1310 may support the device 1300 in implementing the methods described in the preceding method embodiments. The processor 1310 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0147] The communication device 1300 may further include one or more memories 1320. The memories 1320 store a program that can be executed by the processor 1310, causing the processor 1310 to perform the methods described in the preceding method embodiments. The memories 1320 may be independent of the processor 1310 or integrated into the processor 1310.

[0148] The communication device 1300 may also include a transceiver 1330. The processor 1310 can communicate with other devices or chips via the transceiver 1330. For example, the processor 1310 can send and receive data with other devices or chips via the transceiver 1330.

[0149] It should be understood that in the embodiments of this application, the processor 1310 may be a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0150] The memory 1320 may include read-only memory and random access memory, and provides instructions and data to the processor 1310. A portion of the processor 1310 may also include non-volatile random access memory. For example, the processor 1310 may also store device type information.

[0151] In implementation, each step of the above method can be completed by the integrated logic circuitry of the hardware in the processor 1310 or by instructions in software form. The method for requesting uplink transmission resources disclosed in the embodiments of this application can be directly implemented by the hardware processor, or by a combination of hardware and software modules in the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 1320, and the processor 1310 reads the information in memory 1320 and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are not provided here.

[0152] It should be understood that in the embodiments of this application, the processor 1310 can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0153] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to a terminal device or network device provided in this application, and the program causes a computer to execute the wireless communication methods performed by the authorized entity in various embodiments of this application.

[0154] This application also provides a computer program product. The computer program product includes a program. This computer program product can be applied to a terminal device or network device provided in this application embodiment, and the program causes a computer to execute the wireless communication methods performed by the authorized entity in various embodiments of this application.

[0155] This application also provides a computer program. This computer program can be applied to the terminal device or network device provided in this application, and the computer program causes the computer to execute the wireless communication methods performed by the authorized entity in various embodiments of this application.

[0156] It should be understood that all or part of the functions of the communication device in this application can also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform (such as a cloud platform).

[0157] It should be understood that the terms "system" and "network" in this application can be used interchangeably. Furthermore, the terminology used in this application is only for explaining specific embodiments of the application and is not intended to limit the application. The terms "first," "second," "third," and "fourth," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. In addition, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0158] In the embodiments of this application, the term "instruction" can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0159] In the embodiments of this application, "comprising" can refer to direct inclusion or indirect inclusion. Optionally, "comprising" mentioned in the embodiments of this application can be replaced with "indicating" or "used to determine". For example, "A includes B" can be replaced with "A indicates B" or "A is used to determine B".

[0160] In the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0161] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0162] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0163] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0164] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can read or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0165] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A wireless communication method performed by an authorized entity, the method comprising: Obtain authorization information from the terminal device; Based on the authorization information, it is determined whether to authorize the terminal device to make AI / ML service requests. The AI / ML service requests are used to request the transmission of information associated with AI / ML services to the terminal device, and / or, the AI / ML service requests are used to request the acquisition of information from the terminal device to perform AI / ML operations.

2. The method according to claim 1, wherein the authorization information includes the AI / ML subscription data of the terminal device and / or the AI / ML configuration information of the terminal device.

3. The method according to claim 2, wherein the AI / ML subscription data includes at least one of the following: Information used to indicate permission for the terminal device to use AI / ML services; The terminal device is allowed to use a set of public terrestrial mobile networks (PLMNs) that provide AI / ML services; AI / ML model information; The types of services to which AI / ML models are applicable.

4. The method according to claim 2, wherein the AI / ML subscription data is determined based on the subscription data of the terminal device.

5. The method of claim 1, wherein the information associated with the AI / ML service includes at least one of the following: AI / ML model related information; Network-assisted information, used to support AI / ML services.

6. The method according to claim 1, wherein the authorization information is determined based on the subscription data of the terminal device, and / or, the authorization information is determined based on the instruction of the terminal device.

7. An authorizing entity, the authorizing entity comprising: The acquisition module is used to acquire authorization information from the terminal device; An authorization module is used to determine whether to authorize AI / ML service requests related to the terminal device based on the authorization information. The AI / ML service requests are used to request the transmission of information associated with AI / ML services to the terminal device, and / or, the AI / ML service requests are used to request the acquisition of information from the terminal device to perform AI / ML operations.

8. The authorization entity according to claim 7, wherein the authorization information includes the AI / ML subscription data of the terminal device and / or the AI / ML configuration information of the terminal device.

9. The authorizing entity according to claim 7, wherein the authorization information is determined based on the contract data of the terminal device, and / or, the authorization information is determined based on the instruction of the terminal device.

10. A wireless communication system, comprising: The first network element is used to obtain the authorization information of the terminal device based on the artificial intelligence (AI) / machine learning (ML) service request related to the terminal device, and determine whether to authorize the AI / ML service request based on the authorization information. The AI / ML service request is used to request the transmission of information associated with the AI / ML service to the terminal device, and / or the AI / ML service request is used to request the acquisition of information from the terminal device to perform AI / ML operations.

11. The wireless communication system according to claim 10, further comprising: The third network element is used to store the information associated with the AI / ML service, and to transmit the information associated with the AI / ML service to the terminal device based on the authorization of the AI / ML service request by the first network element.

12. The wireless communication system according to claim 10, further comprising: The fourth network element is used to store the authorization information and, based on the request of the first network element, transmit the authorization information to the first network element.

13. The wireless communication system according to claim 10, wherein the authorization information is determined based on the subscription data of the terminal device, and / or, the authorization information is determined based on the instruction of the terminal device.

Images