WO2023070684A1 - Wireless communication method, and device - Google Patents

Abstract

A wireless communication method, and a device. The method comprises: a first terminal receiving first information that is sent by a core network device, wherein the first information is used for determining an artificial intelligence (AI) learning task group to which the first terminal belongs. Therefore, a terminal device can select, according to the first information, a terminal device of the same AI learning task group as a relay terminal to establish a connection with a network, thereby transmitting training data or a training result, which is beneficial for improving the performance of a model.

Description

Method and device for wireless communication technical field

The embodiments of the present application relate to the communication field, and in particular to a method and device for wireless communication.

Background technique

Federated learning (Federal Learning, FL) is a machine learning architecture. Terminal devices can train the global model based on small sample training data (or a subset of training data) to obtain local training results. For example, terminal devices can use The small sample training data is input to the global model. The federated learning server can complete the training of the global model by aggregating local training results reported by multiple terminals.

In some scenarios, the terminals participating in the federated learning cannot complete all the local training due to problems such as computing power or power consumption, or the terminals participating in the federated learning move out of the coverage of the base station or the federated learning server, resulting in the inability to transmit training data to the federation In this case, how to train the federated learning model is an urgent problem to be solved.

Contents of the invention

This application provides a method and device for wireless communication. The core network device can assign an identification information to the same AI learning task group. Further, the terminal device can select the terminal device of the same AI learning task group as a relay according to the identification information. The terminal establishes a connection with the network to realize the transmission of training data or training results, thereby improving the performance of the model.

In a first aspect, a wireless communication method is provided, including: a first terminal receives first information sent by a core network device, and the first information is used to determine an artificial intelligence AI learning task group to which the first terminal belongs.

In a second aspect, a wireless communication method is provided, including: a second terminal receiving second information sent by a core network device, where the second information is used to determine the AI learning task group to which the second terminal belongs.

In a third aspect, a wireless communication method is provided, including: a first core network device acquires identification information of terminal devices in a first artificial intelligence AI learning task group; the first core network device is the first AI The learning task group assigns first AI learning identification information, wherein the first AI learning identification information is used to identify the first AI learning task group; the first core network device sends the first AI learning task group The terminal device sends the first AI learning identification information.

In a fourth aspect, a wireless communication method is provided, including: a second core network device sending a first relay service code to a first terminal, wherein the first relay service code and the first artificial intelligence AI learning identifier Information correspondence, the first AI learning identification information is used to identify the AI learning task group to which the first terminal belongs.

In a fifth aspect, a terminal device is provided, configured to execute the method in the foregoing first aspect or various implementation manners thereof.

Specifically, the terminal device includes a functional module for executing the method in the above first aspect or its various implementation manners.

In a sixth aspect, a terminal device is provided, configured to execute the method in the foregoing second aspect or various implementation manners thereof.

Specifically, the terminal device includes a functional module for executing the method in the above second aspect or each implementation manner thereof.

In a seventh aspect, a core network device is provided, configured to execute the method in the above third aspect or its various implementation manners.

Specifically, the core network device includes a functional module for executing the method in the above third aspect or each implementation manner thereof.

In an eighth aspect, a core network device is provided, configured to execute the method in the above third aspect or its various implementation manners.

Specifically, the core network device includes a functional module for executing the method in the above fourth aspect or each implementation manner thereof.

A ninth aspect provides a terminal device, including a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the above first aspect or its various implementations.

In a tenth aspect, a terminal device is provided, including a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the above second aspect or its various implementations.

In an eleventh aspect, a core network device is provided, including a processor and a memory. The memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the above third aspect or its various implementations.

In a twelfth aspect, a core network device is provided, including a processor and a memory. The memory is used to store a computer program, and the processor is used to invoke and run the computer program stored in the memory to execute the method in the fourth aspect or its various implementations.

In a thirteenth aspect, a chip is provided for implementing any one of the above first to fourth aspects or the method in each implementation manner thereof.

Specifically, the chip includes: a processor, configured to call and run a computer program from the memory, so that the device installed with the device executes any one of the above-mentioned first to fourth aspects or any of the implementations thereof. method.

In a fourteenth aspect, there is provided a computer-readable storage medium for storing a computer program, and the computer program causes a computer to execute any one of the above-mentioned first to fourth aspects or the method in each implementation manner thereof.

In a fifteenth aspect, a computer program product is provided, including computer program instructions, the computer program instructions causing a computer to execute any one of the above first to fourth aspects or the method in each implementation manner thereof.

A fifteenth aspect provides a computer program that, when running on a computer, causes the computer to execute any one of the above first to fourth aspects or the method in each implementation manner.

Through the above technical solution, the core network device can assign corresponding identification information to the same AI learning task group, and can further send indication information to the terminal device to determine the AI learning task group to which the terminal device belongs. For example, for the first terminal, The core network device may send first information to the first terminal, the first information is used to determine the AI learning task group to which the first terminal belongs, and for the second terminal, the core network device may send second information to the second terminal, The second information is used to determine the AI learning task group to which the second terminal belongs. Thus, the terminal device selects a relay terminal according to the indication information configured on it. Furthermore, training data or training results can be sent to the AI server through the selected relay terminal, which is beneficial to improve the performance of the model.

Description of drawings

FIG. 1 is a schematic diagram of a communication system architecture provided by an embodiment of the present application.

Fig. 2 is a schematic diagram of a federated learning architecture provided by an embodiment of the present application.

Fig. 3 is a schematic diagram of a proximity service architecture provided by an embodiment of the present application.

Fig. 4 is a schematic interaction diagram of a wireless communication method provided according to an embodiment of the present application.

Fig. 5 is a schematic interaction diagram of a wireless communication method according to an embodiment of the present application.

Fig. 6 is a schematic interaction diagram of a wireless communication method according to another embodiment of the present application.

Fig. 7 is a schematic interaction diagram of a wireless communication method according to yet another embodiment of the present application.

Fig. 8 is a schematic interaction diagram of a wireless communication method according to yet another embodiment of the present application.

Fig. 9 is a schematic block diagram of a terminal device provided according to an embodiment of the present application.

Fig. 10 is a schematic block diagram of another terminal device provided according to an embodiment of the present application.

Fig. 11 is a schematic block diagram of a core network device provided according to an embodiment of the present application.

Fig. 12 is a schematic block diagram of a core network device provided according to an embodiment of the present application.

Fig. 13 is a schematic block diagram of a communication device provided according to an embodiment of the present application.

Fig. 14 is a schematic block diagram of a chip provided according to an embodiment of the present application.

Fig. 15 is a schematic block diagram of a communication system provided according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. With regard to the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

The technical solution of the embodiment of the present application can be applied to various communication systems, such as: Global System of Mobile communication (Global System of Mobile communication, GSM) system, code division multiple access (Code Division Multiple Access, CDMA) system, broadband code division multiple access (Wideband Code Division Multiple Access, WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced long term evolution (LTE-A) system , New Radio (NR) system, evolution system of NR system, LTE (LTE-based access to unlicensed spectrum, LTE-U) system on unlicensed spectrum, NR (NR-based access to unlicensed spectrum) on unlicensed spectrum unlicensed spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunications System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (Wireless Fidelity, WiFi), fifth-generation communication (5th-Generation, 5G) system or other communication systems, etc.

Generally speaking, the number of connections supported by traditional communication systems is limited and easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication, but also support, for example, Device to Device (Device to Device, D2D) communication, Machine to Machine (M2M) communication, Machine Type Communication (MTC), Vehicle to Vehicle (V2V) communication, or Vehicle to everything (V2X) communication, etc. , the embodiments of the present application may also be applied to these communication systems.

Optionally, the communication system in the embodiment of the present application may be applied to a carrier aggregation (Carrier Aggregation, CA) scenario, may also be applied to a dual connectivity (Dual Connectivity, DC) scenario, and may also be applied to an independent (Standalone, SA) deployment Web scene.

Optionally, the communication system in the embodiment of the present application may be applied to an unlicensed spectrum, where the unlicensed spectrum may also be considered as a shared spectrum; or, the communication system in the embodiment of the present application may also be applied to a licensed spectrum, where, Licensed spectrum can also be considered as non-shared spectrum.

Fig. 1 is a schematic architecture diagram of a communication system provided by an embodiment of the present application. As shown in Figure 1, the communication system includes: access and mobility management function (Access and mobility management function, AMF) 101, session management function (Session Management Function, SMF) 102, radio access network (Radio Access Network, RAN ) 103, authentication server function (Authentication Server Function, AUSF) 104, unified data management (Unified Data Management, UDM) 105, policy control function (Policy Control function, PCF) 106, data network (Data Network, DN) 107, User Plane Function (UPF) 108, User Equipment (UE) 109.

Among them, UE 109 is connected to AMF 101 through N1 interface, UE 109 is connected to RAN 103 through Radio Resource Control (RRC) protocol; RAN 103 is connected to AMF 101 through N2 interface, and RAN 103 is connected to UPF 108 through N3 interface Multiple UPF 108 are connected through N9 interface, UPF 108 is connected with DN 107 through N6 interface, meanwhile, UPF 108 is connected with SMF 102 through N4 interface; SMF 102 is connected with PCF 106 through N7 interface, SMF 102 is connected with N10 interface UDM 105 is connected, and at the same time, SMF 102 is connected with AMF 101 through N11 interface; multiple AMF 101 are connected through N14 interface, AMF 101 is connected with UDM 105 through N8 interface, AMF 101 is connected with AUSF 104 through N12 interface, at the same time, AMF 101 is connected to PCF 106 through N15 interface; AUSF 104 is connected to UDM 105 through N13 interface. AMF 101 and SMF 102 obtain user subscription data from UDM 105 through N8 and N10 interfaces respectively, and obtain policy data from PCF 106 through N15 and N7 interfaces. The SMF 102 controls the UPF 108 through the N4 interface.

RAN 103 (or access network device) is the access device that UE 109 accesses to the network architecture through wireless means, and is mainly responsible for wireless resource management, quality of service (QoS) management, and data compression on the air interface side and encryption etc.

In some embodiments of the present application, the access network device may be a device used to communicate with mobile devices, and the access network device may be an access point (Access Point, AP) in WLAN, a base station (Base Station) in GSM or CDMA Transceiver Station, BTS), or a base station (NodeB, NB) in WCDMA, or an evolved base station (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, which can Wearable devices and access network equipment (gNB) in the NR network or access network equipment in the future evolved PLMN network or access network equipment in the NTN network, etc.

As an example but not a limitation, in some embodiments of the present application, the access network device may have a mobility feature, for example: the access network device is a mobile device. Optionally, the access network equipment may be a satellite or a balloon station. For example, the satellite can be a low earth orbit (low earth orbit, LEO) satellite, a medium earth orbit (medium earth orbit, MEO) satellite, a geosynchronous earth orbit (geosynchronous earth orbit, GEO) satellite, a high elliptical orbit (High Elliptical Orbit, HEO) satellite. ) Satellite etc. Optionally, the access network device may also be a base station installed on land, in water, or other locations.

In this embodiment of the application, the access network device can provide services for the cell, and the terminal device communicates with the access network device through the transmission resources (for example, frequency domain resources, or spectrum resources) used by the cell, and the cell can It is a cell corresponding to an access network device (such as a base station). The cell may belong to a macro base station or a base station corresponding to a small cell. The small cell here may include: Metro cell, Micro cell cell), Pico cell, Femto cell, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.

In some embodiments of the present application, AMF 101, SMF 102, AUSF 104, UDM 105, PCF 106, DN 107, and UPF 108 are network elements of the core network (referred to as: core network network elements).

The AMF network element can be used to manage the terminal's access to the core network, such as: terminal location update, network registration, access control, terminal mobility management, terminal attachment and detachment, etc. The AMF network element may also provide storage resources on the control plane for the session of the terminal in the case of providing services for the session, so as to store the session identifier, the SMF network element identifier associated with the session identifier, and the like.

The SMF network element can be used to select a user plane network element for the terminal, redirect the user plane network element for the terminal, assign an Internet protocol (internet protocol, IP) address to the terminal, and establish a bearer between the terminal and the UPF network element (also called session), session modification, release, and QoS control.

The AUSF is used to receive the request from the AMF to authenticate the terminal, request a key from the UDM, and then forward the issued key to the AMF for authentication processing.

UDM includes functions such as generation and storage of user subscription data, management of authentication data, and supports interaction with external third-party servers. PCF network elements are used to provide policies to AMF network elements and SMF network elements, such as QoS policies and slice selection policies.

The DN can provide users with data services such as the IP Multi-media Service (IMS) network and the Internet. In the DN, there can be various application servers (application server, AS), which provide different application services, such as operator services, Internet access or third-party services, etc., and the AS can realize the function of AF.

The UPF network element is mainly responsible for the transmission of user data. Other network elements can be called control plane functional network elements, which are mainly responsible for authentication, authentication, registration management, session management, mobility management, and policy control, etc., to ensure reliable and stable user data. transmission.

The UPF network element can be used to forward and receive terminal data. For example, the UPF network element can receive service data from the data network and transmit it to the terminal through the access network device; the UPF network element can also receive user data from the terminal through the access network device and forward it to the data network. Among them, the transmission resource allocated and scheduled by the UPF network element for the terminal is managed and controlled by the SMF network element. The bearer between the terminal and the UPF network element may include: the user plane connection between the UPF network element and the access network device, and the establishment of a channel between the access network device and the terminal. Wherein, the user plane connection is a quality of service (quality of service, QoS) flow (flow) that can establish data transmission between the UPF network element and the access network device.

The AF network element is used to interact with the core network element to support the routing of application-affected data, access the network exposure function, and interact with the PCF network element for policy control, etc.

In some embodiments of the present application, user equipment (User Equipment, UE) may also be referred to as terminal equipment, access terminal, subscriber unit, subscriber station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal , terminal, wireless communication device, user agent or user device, etc.

The terminal device can be a station (STATION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (Session Initiation Protocol, SIP) phone, a wireless local loop (Wireless Local Loop, WLL) station, a personal digital assistant (Personal Digital Assistant, PDA) devices, handheld devices with wireless communication functions, computing devices or other processing devices connected to wireless modems, vehicle-mounted devices, wearable devices, next-generation communication systems such as terminal devices in NR networks, or future Terminal equipment in the evolved public land mobile network (Public Land Mobile Network, PLMN) network, etc.

In the embodiment of this application, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships, etc.); it can also be deployed in the air (such as aircraft, balloons and satellites) superior).

In this embodiment of the application, the terminal device may be a mobile phone (Mobile Phone), a tablet computer (Pad), a computer with a wireless transceiver function, a virtual reality (Virtual Reality, VR) terminal device, an augmented reality (Augmented Reality, AR) terminal Equipment, wireless terminal equipment in industrial control, wireless terminal equipment in self driving, wireless terminal equipment in remote medical, wireless terminal equipment in smart grid , wireless terminal equipment in transportation safety, wireless terminal equipment in smart city, or wireless terminal equipment in smart home.

As an example but not a limitation, in this embodiment of the present application, the terminal device may also be a wearable device. Wearable devices can also be called wearable smart devices, which is a general term for the application of wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not only a hardware device, but also achieve powerful functions through software support, data interaction, and cloud interaction. Generalized wearable smart devices include full-featured, large-sized, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, etc., and only focus on a certain type of application functions, and need to cooperate with other devices such as smart phones Use, such as various smart bracelets and smart jewelry for physical sign monitoring.

It should be noted that the network architecture of the communication system shown in FIG. 1 does not constitute a limitation on the network architecture of the communication system in this embodiment of the application. During specific implementation, the communication system may also include more or more Fewer network elements, or combine certain network elements, etc. It should be understood that RAN may also be represented by AN in FIG. 1 .

It should be understood that a device with a communication function in the network/system in the embodiment of the present application may be referred to as a communication device. Taking the communication system shown in FIG. 1 as an example, the communication equipment may include access network equipment (such as RAN 103) with communication functions, core network elements (such as PCF 106) and UE 109.

It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and/or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.

It should be understood that the "indication" mentioned in the embodiments of the present application may be a direct indication, may also be an indirect indication, and may also mean that there is an association relationship. For example, A indicates B, which can mean that A directly indicates B, for example, B can be obtained through A; it can also indicate that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also indicate that there is an association between A and B relation.

In the description of the embodiments of the present application, the term "corresponding" may indicate that there is a direct or indirect correspondence between the two, or that there is an association between the two, or that it indicates and is indicated, configuration and is configuration etc.

In the embodiment of this application, "predefinition" can be realized by pre-saving corresponding codes, tables or other methods that can be used to indicate related information in devices (for example, including terminal devices and network devices). The implementation method is not limited. For example, pre-defined may refer to defined in the protocol.

It should be understood that the network devices in this embodiment of the present application may include access network devices and core network devices.

In the embodiment of the present application, the "protocol" may refer to a standard protocol in the communication field, for example, it may include the LTE protocol, the NR protocol, and related protocols applied in future communication systems, which is not limited in the present application.

In order to facilitate the understanding of the technical solutions of the embodiments of the present application, the federated learning related to the present application will be described.

As the performance of cameras and sensors on mobile terminals continues to improve, more and more terminals can collect valuable information that is essential for artificial intelligence (Artifact Intelligence, AI) model or machine learning (Machine Learning, ML) model training. training data. For many AI tasks or ML tasks, the small-sample training data collected by mobile terminals is of great significance for training global models.

Federated learning (Federal Learning, FL) is a machine learning architecture. Terminal devices can train the global model based on small sample training data (or a subset of training data) to obtain local training results. For example, terminal devices can use Small-sample training data is input to a global model (such as Deep Neural Networks (DNN)), and intermediate training results (or local training results), such as gradient information of DNN, are obtained. The FL server can complete the training of the global model by aggregating local training results reported by multiple terminal devices.

Figure 2 is an architecture diagram of federated learning. In each iteration training, the terminal device can use the local training data to perform training on the global model downloaded from the federated learning server, and then report the intermediate training results (for example, the gradient information of DNN) to the federated learning server through the uplink channel. Then the federated learning server aggregates the collected gradient information and updates the global model. The federated learning server distributes the updated global model to the terminal devices participating in the federated learning through the downlink channel, and the terminal devices perform the next iteration training on this updated model.

In order to facilitate the understanding of the technical solutions of the embodiments of the present application, the Proximity-based Services (ProSe) related to the present application will be described.

A terminal device with ProSe capability can directly communicate with another terminal device with ProSe capability through the PC5 interface.

When a terminal device can connect to an external data network through a 5G network and also has ProSe capabilities, this terminal device can act as a relay terminal (Relay UE), and another remote terminal (remote UE) with ProSe capabilities can use the PC5 interface Establish a direct connection with the relay terminal, and interact with the external network through the Protocol Data Unit (Protocol Data Unit, PDU) session established between the relay terminal and the 5G network, as shown in Figure 3.

In order to facilitate understanding of the technical solutions of the embodiments of the present application, the device discovery process related to the present application will be described.

The Remote UE and the Relay UE need to perform a discovery process before establishing a connection. The discovery process can use Model A (Model A) or Model B (Model B).

For mode A, for example, UE1 can act as a Relay UE and send a discovery announcement message (Announcement message), or a discovery notification message, to notify the Remote UE. The UE that has received the discovery announcement message can establish a connection with the UE1 when a relay service is needed, and transmit relay data through the UE1.

For mode B, for example, UE1 can act as a Remote UE and wants to find a Relay UE, then UE1 can send a discovery request message (Solicitation message), or a discovery call message, to notify the Relay UE. The UE receiving the Solicitation message may reply a discovery response message (Response message) to UE1 when it can perform the relay service, and notify UE1 that it can perform the relay service.

In some scenarios, the terminals participating in the federated learning cannot complete all the local training due to problems such as computing power or power consumption, or the terminals participating in the federated learning move out of the coverage of the base station or the federated learning server, resulting in the inability to transfer the training data or training results In this case, how to train the federated learning task model is an urgent problem to be solved.

In order to facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific examples. As optional solutions, the above related technologies may be combined with the technical solutions of the embodiments of the present application in any combination, and all of them belong to the protection scope of the embodiments of the present application. The embodiment of the present application includes at least part of the following contents.

FIG. 4 is a schematic interaction diagram of a wireless communication method 200 according to an embodiment of the present application. As shown in FIG. 4, the method 200 includes at least part of the following content:

S210. The core network device sends first information to the first terminal, where the first information is used to determine the AI learning task group to which the first terminal belongs;

S220. The core network device sends second information to the second terminal, where the second information is used to determine the AI learning task group to which the second terminal belongs.

In some embodiments of the present application, the core network device may be a core network element in the communication system shown in FIG. 1 .

In some embodiments of the present application, the first terminal may be a UE in the communication system shown in FIG. 1 , and the first terminal may be the specific device described in FIG. 1 , which will not be repeated here.

In some embodiments of the present application, the second terminal may be a UE in the communication system shown in FIG. 1 , and the first terminal may be the specific device described in FIG. 1 , which will not be repeated here.

It should be understood that the AI learning task group in the embodiment of the present application can be replaced by a terminal group, and the terminal group can be divided based on the tasks performed by the terminal devices (for example, AI learning tasks), or can also be based on the capabilities, or may also be divided according to the location of the terminal equipment, and this application does not limit the specific grouping manner.

Optionally, a terminal device in the same terminal group may serve as a relay terminal for another terminal device. Hereinafter, the terminal group is an AI learning task group as an example for illustration, but the present application is not limited thereto.

In this embodiment of the application, the AI learning task group is also called AI task group, AI group, or ML learning task group, ML task group, ML group, etc., and the above expressions can be replaced with each other.

In some embodiments, the AI learning task group may include, but not limited to, a federated learning task group, a cluster learning task group, and the like.

In the embodiment of the application, the AI learning task group includes multiple terminal devices, and the multiple terminal devices are used to execute the same AI learning task, such as a federated learning task.

In the embodiment of the application, terminal devices in the same AI learning task group have the same AI model, such as a DNN model.

In this embodiment of the application, each AI learning task may correspond to a corresponding server, and the server may be called an AI server, an AI learning server, an AI learning task server, and the like.

Optionally, the AI server can be a federated learning server, and the federated learning server can aggregate the training results of the terminal devices in the federated learning task group to complete the training of the global model.

In some embodiments, the first terminal supports the execution of AI learning tasks, or, the first terminal supports the execution of ML learning tasks, and the first terminal supports AI operations.

In some embodiments, the second terminal supports the execution of AI learning tasks, or, the second terminal supports the execution of ML learning tasks, and the second terminal supports AI operations.

In some embodiments, the AI learning tasks supported by the first terminal and the second terminal may be the same, or may also be different.

In some embodiments of the application, each AI learning task group corresponds to identification information, and the identification information can be used to uniquely identify the AI learning task group.

For example, each federated learning task group corresponds to identification information, and the identification information is used to uniquely identify the federated learning task group, or used to uniquely identify a federation.

In some embodiments of the present application, the first information directly indicates the AI learning task group to which the first terminal belongs.

That is, the first information may be direct indication information of the AI learning task group to which the first terminal belongs.

For example, the first information is first identification information, and the first identification information is used to identify the AI learning task group to which the first terminal belongs.

In other words, the first information may be identification information of the AI learning task group to which the first terminal belongs.

In other embodiments of the present application, the first information indirectly indicates the AI learning task group to which the first terminal belongs.

That is, the first information may be indirect indication information of the AI learning task group to which the first terminal belongs.

For example, the first information may be first configuration information, and the first configuration information is in one-to-one correspondence with first identification information, and the first identification information is used to identify the AI learning task group to which the first terminal belongs.

As an example, the first configuration information may be a first relay service code (Relay Service Code, RSC), and the first relay service code corresponds to the first identification information one by one, or the first configuration information may also be other parameters , the application is not limited to this.

Optionally, the first identification information or the first AI learning identification information, the first AI identification information, and the above expressions may be replaced with each other.

In some embodiments of the present application, the first information is called the first AI operation configuration. According to the first AI operation configuration, the AI learning task group to which the first terminal belongs, or the executed AI learning task, or the executed AI operation may be determined.

In some embodiments of the present application, the second information directly indicates the AI learning task group to which the second terminal belongs.

That is, the second information may be direct indication information of the AI learning task group to which the second terminal belongs.

For example, the second information is second identification information, and the second identification information is used to identify the AI learning task group to which the second terminal belongs.

In other words, the second information may be identification information of the AI learning task group to which the second terminal belongs.

In other embodiments of the present application, the second information indirectly indicates the AI learning task group to which the second terminal belongs.

That is, the second information may be indirect indication information of the AI learning task group to which the second terminal belongs.

For example, the second information may be second configuration information, and the second configuration information is in one-to-one correspondence with second identification information, and the second identification information is used to identify the AI learning task group to which the second terminal belongs.

As an example, the second configuration information may be the second RSC, and the second relay service code is in one-to-one correspondence with the second identification information, or the second configuration information may also be other parameters, and the present application is not limited thereto.

Optionally, the second identification information is also called the second AI learning identification information, the second AI identification information, and the above expressions can be replaced with each other.

In some embodiments of the present application, the second information is called the second AI operation configuration. According to the second AI operation configuration, the AI learning task group to which the second terminal belongs, or the executed AI learning task, or the executed AI operation can be determined.

In some embodiments of the present application, the core network device may be an existing core network element, for example, a network data analysis function (Network Data Analytics Function, NWDAF) entity, or may also be a newly added core network element, For example, a new network element connected to a third-party application server is added to support third-party AI-related requirements in the core network.

In some embodiments, the core network device may be a first core network device, and the first core network device may be a NWDAF entity or an AI functional entity, and is used to support AI-related functions. The AI functional entity is a newly added network element.

For example, the AI functional entity may send the first information to the first terminal for determining the AI learning task group to which the first terminal belongs.

As a specific example, the AI functional entity may send the first identification information to the first terminal, which is used to indicate the AI learning task group to which the first terminal belongs.

For another example, the AI functional entity may send the second information to the second terminal, which is used to determine the AI learning task group to which the second terminal belongs.

As a specific example, the AI functional entity may send the second identification information to the second terminal, which is used to indicate the AI learning task group to which the second terminal belongs.

In some other embodiments, the core network device is a second core network device, for example, the second core network device is a Policy Control Function (Policy Control Function, PCF) entity.

For example, the second core network device may send the first information to the first terminal, which is used to determine the AI learning task group to which the first terminal belongs.

As a specific example, the second core network device may send first identification information to the first terminal, where the first identification information is used to identify the AI learning task group to which the first terminal belongs.

As a specific example, the second core network device may send the first RSC to the first terminal, where the first RSC corresponds to first identification information, and the first identification information is used to identify the AI learning task group to which the first terminal belongs.

For example, the second core network device may determine the RSC corresponding to the first identification information, that is, the first RSC according to the first identification information and the correspondence between the AI learning task group and the RSC, and further send the first RSC to the first terminal.

For another example, the second core network device may send second information to the second terminal, which is used to determine the AI learning task group to which the second terminal belongs.

As a specific example, the second core network device may send second identification information to the second terminal, where the second identification information is used to identify the AI learning task group to which the second terminal belongs.

As a specific example, the second core network device may send a second RSC to the second terminal, where the second RSC corresponds to second identification information, and the second identification information is used to identify the AI learning task group to which the second terminal belongs.

For example, the second core network device may determine the RSC corresponding to the second identification information, that is, the second RSC according to the second identification information and the correspondence between the AI learning task group and the RSC, and further send the second RSC to the second terminal.

That is to say, the second core network device may send the target RSC to the terminal device, where the target RSC corresponds to target identification information, and the target identification information is used to identify the AI learning task group to which the terminal device belongs.

In some embodiments, the correspondence between AI learning task groups and RSCs may be preconfigured.

In other words, different RSCs correspond to different AI learning task groups.

For example, different values of some or all bits of the RSC are used to indicate different AI learning task groups.

As an example, use M bits in RSC (such as bit 0 and bit 1) to indicate different types of AI learning tasks, such as federated learning tasks, transfer learning tasks, etc., use N bits in the remaining bits in RSC (such as bit 2 and bit 3) different values indicate different AI learning task groups. For example, if the M bit indicates a federated learning task, the N bit takes a value of 0 to indicate federated learning task group 0, a value of 1 indicates federated learning task group 1, and so on.

It should be understood that, in the embodiment of the present application, the information sent by the core network device to the terminal device is forwarded by the access network device.

In some embodiments, the core network device sending the first information to the first terminal may refer to:

The core network device sends the first information to the first terminal through the access network device.

For example, the core network device first sends the first information to the access network device, and the access network device further forwards the first information to the first terminal.

Similarly, the core network device sending the second information to the second terminal may refer to:

The core network device sends the second information to the second terminal through the access network device.

For example, the core network device first sends the second information to the access network device, and the access network device further forwards the second information to the second terminal.

In some embodiments of the present application, the first terminal may select a relay terminal according to the first information.

Hereinafter, description will be made by taking an example in which the first information includes the first identification information and/or the first RSC, and the second information includes the second identification information and/or the second RSC, but the present application is not limited thereto.

In some embodiments, the method 200 further includes: the first terminal sends the first identification information and/or the first RSC.

Correspondingly, other terminals receive the first identification information and/or the first RSC. For example, the second terminal receives the first identification information and/or the first RSC.

In some implementation manners, the first terminal sending the first identification information and/or the first RSC may include: the first terminal sending the first identification information and/or the first RSC during device discovery.

That is, the first terminal may carry the indication information of the AI learning task group that the relay terminal needs to satisfy in device discovery.

For example, the first terminal sends a discovery request message (solicitation message), where the discovery request message includes the first identification information and/or the first RSC.

That is, the first terminal may carry the first identification information and/or the first RSC in the solicitation message in mode B.

Further, the terminal device that has received the first identification information and/or the first RSC may combine the indication information of the AI learning task group configured on the terminal device (such as , the identification information of the AI learning task group, or, RSC), determine whether the terminal device and the first terminal belong to the same AI learning task group.

For example, the second terminal may determine whether the first terminal and the second terminal belong to the same AI according to the combination of the first identification information and/or the first RSC, the second identification information and/or the second RSC configured on the second terminal. learning task force.

For example, the second terminal may determine that the first terminal and the second terminal belong to the same AI learning task group when at least one of the following conditions is met:

The first identification information is the same as the second identification information;

The first RSC and the second RSC are the same.

Further, a terminal device belonging to the same AI learning task group as the first terminal may send a discovery response message to the first terminal.

For example, when it is determined that the second terminal and the first terminal belong to the same AI learning task group, the second terminal sends a discovery response message to the first terminal.

According to the discovery response message, the first terminal may determine that the second terminal and the first terminal belong to the same AI learning task group, and further, may select the second terminal as a relay terminal.

In some other embodiments, the method 200 further includes: the second terminal sends the second identification information and/or the second RSC.

Correspondingly, the first terminal receives the second identification information and/or the second RSC sent by the second terminal.

In some implementation manners, the second terminal sending the second identification information and/or the second RSC may include: the second terminal sending the second identification information and/or the second RSC during device discovery.

That is, the second terminal may carry the indication information of the AI learning task group to which the second terminal belongs in the device discovery.

For example, the second terminal sends a discovery announcement message (Announcement message), and the discovery announcement message includes the second identification information and/or the second RSC. That is, the second terminal may send the second information by using mode A of Prose Direct Discovery.

For another example, the second terminal sends a discovery response message to the first terminal, and the discovery response message includes the second identification information and/or the second RSC.

That is, the second terminal may carry the second identification information and/or the second RSC in the discovery response message in mode B.

Further, the first terminal may determine the second terminal according to the first identification information and/or the first RSC configured on the first terminal in combination with the second identification information and/or the second RSC sent by the second terminal. Whether it belongs to the same AI learning task group as the first terminal. In the case that the second terminal and the first terminal belong to the same AI learning task group, the first terminal may select the second terminal as the relay terminal.

For example, the first terminal may determine that the second terminal and the first terminal belong to the same AI learning task group when at least one of the following conditions is met:

The second identification information is the same as the first identification information;

The second RSC is the same as the first RSC.

To sum up, whether the first terminal and the second terminal belong to the same AI learning task group may be determined by the first terminal, or may also be determined by the second terminal. For example, the second terminal may obtain the first identification information and/or the first RSC of the first terminal, and then determine whether the first identification information and/or the first RSC and the second information configured on the second terminal belong to the same AI Learning Task Force. For another example, the first terminal may acquire the second identification information and/or the second RSC of the second terminal, and then determine whether it belongs to the The same AI learning task group.

In some embodiments of the present application, the first terminal can establish a connection with the network through the selected relay terminal, and further send training data or intermediate training results to the AI server through the selected relay terminal, which is beneficial to ensure the smooth progress of the AI learning task , to improve the performance of the AI model.

That is, as a remote terminal, the first terminal may send training data or training results to the AI server through the relay terminal in a Prose manner.

For example, due to computing power or power problems, the first terminal cannot complete all the local training. In this case, the first terminal can send the intermediate training results of a certain step or a certain layer to the relay terminal. The relay terminal and the first terminal have the same AI model, and the relay terminal can train subsequent layers based on the intermediate training result, and further send the training result to the server corresponding to the AI learning task.

For another example, due to mobility reasons, the first terminal moves out of the coverage of the base station or the AI server during the local training process. In this case, the first terminal may calculate up to a certain step, or The intermediate training result is sent to the relay terminal, and the relay terminal sends the training result to the AI server.

In some embodiments of the present application, the identification information corresponding to each AI learning task group may be assigned by the core network device.

Optionally, the core network device may be a first core network device, and the first core network device is configured to assign corresponding identification information to each AI learning task group.

Optionally, the first core network device may be an existing core network element, such as an NWDAF entity. That is to say, for existing core network elements, add support for third-party AI-related functions.

Optionally, the first core network device may also be a newly added core network element, such as a newly added AI functional entity, for supporting third-party AI-related functions in the core network.

It should be understood that in this embodiment of the application, the core network device that distributes the identification information corresponding to the AI learning task group and the core network device that sends the identification information corresponding to the AI learning task group to the terminal device may be the same core network device, or, It may be different core network devices.

For example, after the first core network device assigns corresponding identification information to the AI learning task group, it may further send the identification information to the terminal devices in the AI learning task group.

For another example, after the first core network device assigns corresponding identification information to the AI learning task group, it may send the identification information to the second core network device, and the second core network device further sends the terminal device in the AI learning task group Send the identification information.

In some embodiments of the present application, the terminal devices (for example, the first terminal and the second terminal) may report to the AI server the AI operation capabilities they support, for example, whether they support federated learning. Further, the AI server may determine the target terminals forming the AI learning task group according to the AI operation capabilities of the terminal devices, or in other words, the target terminals performing the same AI learning task.

In some embodiments, the first core network device may acquire a set of terminals performing the same AI learning task from the AI server.

For example, the first core network device may acquire a set of terminals performing the same federated learning task from the federated learning server.

Further, the first core network device may send the identification information assigned to the AI learning task group to the terminal devices in the AI learning task group.

In the following, in conjunction with Fig. 5 to Fig. 8, taking the AI learning task as the federated learning task, the AI learning identification information as the FL ID, and the AI functional entity assigning the FL ID as an example, the specific implementation of the wireless communication method according to the embodiment of the present application will be described. But the present application is not limited thereto.

It should be noted that, in FIG. 5 to FIG. 8 , the remote terminal may correspond to the first terminal in the foregoing, and the relay terminal may correspond to the second terminal in the foregoing. FIG. 5 is a schematic interaction diagram of a generation and configuration process of an AI operation configuration, and FIGS. 6 to 8 are schematic interaction diagrams of a terminal device selecting a relay terminal according to an AI operation configuration.

As shown in Figure 5, at least some of the following steps may be included:

S301. The relay terminal reports to the FL server information about its supported AI operation capabilities, such as whether it supports federated learning tasks.

S302. The remote terminal reports to the FL server information about its supported AI operation capabilities, such as whether it supports federated learning tasks.

It should be understood that this embodiment of the present application does not limit the order in which the relay terminal and the remote terminal report the AI operation capability information. For example, they may report at the same time, or the relay terminal may report first, or the remote terminal may report The terminal reports first.

Optionally, the FL server may also receive AI operation capability information reported by more terminals.

S303. The FL server selects a target terminal for performing a federated learning task according to the AI operation capability information reported by the terminal device, or in other words, forms a federated target terminal. The target terminal can be regarded as forming a federated learning task group.

S304. The FL server sends identification information (for example, terminal IDs) of target terminals forming a federation to the AI functional entity.

The AI functional entity assigns a FL ID to the federated learning task group.

S305. The AI functional entity sends the FL ID corresponding to the federated learning task group to the PCF entity.

Optionally, the AI functional entity may also send the terminal ID included in the federated learning task group to the PCF entity.

Further, the PCF entity sends the AI operation configuration to all terminals in the federated learning task group.

In some embodiments, the AI operational configuration may include a FL ID.

In some other embodiments, the AI operation configuration may include an RSC, and the RSC corresponds to the FL ID.

For example, in S306, the PCF entity sends the AI operation configuration to the relay terminal, and the AI operation configuration may include the FL ID assigned by the AI functional entity to the federated learning task group to which the relay terminal belongs, or, RSC, the RSC and the AI The functional entity corresponds to the FL ID assigned by the federated learning task group to which the relay terminal belongs.

In some implementation manners, the PCF entity first sends the AI operation configuration of the relay terminal to the access network device, and the access network device further sends the AI operation configuration of the relay terminal to the relay terminal.

For example, in S307, the PCF entity sends the AI operation configuration to the remote terminal, and the AI operation configuration may include the FL ID assigned by the AI functional entity to the federated learning task group to which the remote terminal belongs, or, RSC, the RSC and the AI The functional entity corresponds to the FL ID assigned by the federated learning task group to which the remote terminal belongs.

In some implementation manners, the PCF entity first sends the AI operation configuration of the remote terminal to the access network device, and the access network device further sends the AI operation configuration of the remote terminal to the remote terminal.

Alternatively, in some implementation manners, in S305, the AI functional entity may also send the FL ID allocated for the federated learning task group to all terminals in the federated learning task group. For example, the AI functional entity sends the FL ID to the access network device, and the access network device further sends the FL ID to the corresponding terminal device.

In some embodiments of the present application, the remote terminal and the relay terminal may determine whether they are in the same federation according to the AI operation configuration. That is, the remote terminal can select a relay terminal according to the AI operation configuration. For example, only when the AI operation configuration of the relay terminal is the same as that of the remote terminal, the remote terminal selects the relay terminal to establish a connection with the network.

As shown in Figure 6, at least some of the following steps may be included:

S311. The relay terminal sends the AI operation configuration of the relay terminal.

The AI operation configuration here may be configured in the manner shown in the embodiment shown in FIG. 5 .

For example, the relay terminal sends a second FL ID, where the second FL ID is used to identify the federated learning task group to which the relay terminal belongs.

For another example, the relay terminal sends a second RSC, and the second RSC corresponds to the second FL ID.

Optionally, the relay terminal may broadcast the AI operation configuration of the relay terminal. For example, the relay terminal can adopt the mode A of Prose Direct Discovery, and indicate the AI operation configuration of the relay terminal in the broadcasted discovery announcement message.

S312. The remote terminal determines whether to select the relay terminal to establish a connection with the network according to the AI operation configuration of the remote terminal and the AI operation configuration of the relay terminal.

Optionally, the AI operation configuration of the remote terminal includes a first FL ID and/or a first RSC, the first RSC corresponds to the first FL ID, and the first FL ID is used to identify the federated learning to which the remote terminal belongs task group.

For example, if the first FL ID is the same as the second FL ID, it is determined to choose to establish a connection with the network through the relay terminal.

For another example, if the first RSC is the same as the second RSC, it is determined to choose to establish a connection with the network through the relay terminal.

S313. The remote terminal initiates corresponding connection establishment according to the judgment result.

For example, when the first FL ID and the second FL ID are the same, choose to establish a connection with the network through the relay terminal.

For another example, when the first RSC and the second RSC are the same, the relay terminal is selected to establish a connection with the network.

As shown in Figure 7, at least some of the following steps may be included:

S321. The remote terminal sends the AI operation configuration of the remote terminal.

The AI operation configuration here may be configured in the manner shown in the embodiment shown in FIG. 5 .

For example, the remote terminal sends a first FL ID, where the first FL ID is used to identify the federated learning task group to which the remote terminal belongs.

For another example, the remote terminal sends a first RSC, and the first RSC corresponds to the first FL ID.

Optionally, the remote terminal may carry the AI operation configuration of the remote terminal in the discovery request message.

For example, the remote terminal may indicate the AI operation configuration of the remote terminal in the solicitation message in mode B, or in other words, the AI operation configuration that the relay terminal needs to meet.

S322. The relay terminal determines whether the two are in the same federation according to the AI operation configuration of the remote terminal and the AI operation configuration of the relay terminal.

Optionally, the AI operation configuration of the relay terminal includes a second FL ID and/or a second RSC, the second RSC corresponds to the second FL ID, and the second FL ID is used to identify the federated learning to which the relay terminal belongs task group.

For example, if the first FL ID is the same as the second FL ID, it is determined that the remote terminal and the relay terminal are in the same federation.

For another example, if the first RSC is the same as the second RSC, it is determined that the remote terminal and the relay terminal are in the same federation.

S323. The relay terminal determines whether to send a discovery response message according to the decision result.

For example, in the case that the first FL ID and the second FL ID are the same, the relay terminal sends a discovery response message.

For another example, when the first FL ID is different from the second FL ID, the relay terminal does not send a discovery response message.

For example, in the case that the first RSC and the second RSC are the same, the relay terminal sends a discovery response message.

For another example, when the first RSC is different from the second RSC, the relay terminal does not send the discovery response message.

S324. The remote terminal initiates corresponding connection establishment according to the discovery response message.

For example, the remote terminal establishes a connection with the network through the relay terminal that sends the discovery response message.

As shown in Figure 8, at least some of the following steps may be included:

S331. The remote terminal sends a discovery request message.

In this embodiment, the discovery request message does not carry the AI operation configuration of the remote terminal.

S332. The relay terminal sends the AI operation configuration of the relay terminal in the discovery response message.

The AI operation configuration here may be configured in the manner shown in the embodiment shown in FIG. 5 .

For example, the relay terminal sends a second FL ID, where the second FL ID is used to identify the federated learning task group to which the relay terminal belongs.

For another example, the relay terminal sends a second RSC, and the second RSC corresponds to the second FL ID.

S333. The remote terminal determines whether the relay terminal and the remote terminal are in the same federation according to the AI operation configuration of the remote terminal and the AI operation configuration of the relay terminal.

Optionally, the AI operation configuration of the remote terminal includes a first FL ID and/or a first RSC, the first RSC corresponds to the first FL ID, and the first FL ID is used to identify the federated learning to which the remote terminal belongs task group.

For example, if the first FL ID is the same as the second FL ID, it is determined that the relay terminal and the remote terminal are in the same federation.

For another example, if the first RSC is the same as the second RSC, it is determined that the relay terminal and the remote terminal are in the same federation.

S334, the remote terminal initiates corresponding connection establishment according to the judgment result.

For example, when the first FL ID and the second FL ID are the same, the remote terminal chooses to establish a connection with the network through the relay terminal.

For another example, when the first RSC and the second RSC are the same, the remote terminal chooses to establish a connection with the network through the relay terminal.

To sum up, in the embodiment of this application, the core network equipment assigns corresponding identification information to the AI learning task group, so that the remote terminal can determine and select the relay terminal belonging to the same AI learning task group to establish a connection with the network according to the identification information . In this way, when the remote terminal is out of coverage, or has poor computing power and low power, the remote terminal can send the training result or training data to the AI server through the relay terminal to ensure the smooth progress of the AI learning task. In addition, by assigning corresponding identification information to the AI learning task group, it is only necessary to find terminals belonging to the same AI learning task group through the identification information, without providing specific model information, which can effectively protect the training data owned by the terminal device. model information.

The method embodiment of the present application is described in detail above in conjunction with FIG. 4 to FIG. 8 , and the device embodiment of the present application is described in detail below in conjunction with FIG. 9 to FIG. 14 . It should be understood that the device embodiment and the method embodiment correspond to each other, similar to The description can refer to the method embodiment.

Fig. 9 shows a schematic block diagram of a terminal device 400 according to an embodiment of the present application. As shown in FIG. 9, the terminal device 400 includes:

The communication unit 410 is configured to receive first information sent by the core network device, where the first information is used to determine the artificial intelligence AI learning task group to which the terminal device belongs.

In some embodiments of the present application, the first information includes at least one of the following:

The first AI learning identification information, the first relay service code, wherein the first AI learning identification information is used to identify the AI learning task group to which the terminal device belongs, the first relay service code and the first relay service code A corresponding AI learning identification information.

In some embodiments of the present application, the communication unit 410 is also used to:

Sending the first AI learning identification information and/or the first relay service code.

In some embodiments of the present application, the communication unit 410 is also used to:

Sending a discovery request message, where the discovery request message includes the first AI learning identification information and/or the first relay service code.

In some embodiments of the present application, the communication unit 410 is also used to:

Receive a discovery response message sent by a second terminal, where the second terminal and the terminal device belong to the same AI learning task group.

In some embodiments of the present application, the terminal device further includes:

A processing unit, configured to select the second terminal as a relay terminal.

In some embodiments of the present application, the communication unit 410 is also used to:

receiving second information sent by the second terminal, where the second information is used to determine the AI learning task group to which the second terminal belongs.

In some embodiments of the present application, the second information includes at least one of the following:

The second AI learning identification information and the second relay service code, wherein the second AI learning identification information is used to identify the AI learning task group to which the second terminal belongs, and the second relay service code and the The second AI learns to correspond to the identification information.

In some embodiments of the present application, the communication unit 410 is also used to:

receiving a discovery announcement message sent by the second terminal, where the discovery announcement message includes the second information.

In some embodiments of the present application, the communication unit 410 is also used to:

Receive a discovery response message sent by the second terminal, where the discovery response message includes the second information.

In some embodiments of the present application, the terminal device further includes:

A processing unit, configured to determine whether to select the second terminal as a relay terminal according to the second information and the first information.

In some embodiments of the present application, the processing unit is also used for:

determining whether the second terminal and the terminal device belong to the same AI learning task group according to the second information and the first information;

If the second terminal and the terminal device belong to the same AI learning task group, select the second terminal as a relay terminal.

In some embodiments of the present application, the processing unit is also used for:

When at least one of the following conditions is met, it is determined that the second terminal and the terminal device belong to the same AI learning task group:

The AI learning identification information included in the second information is the same as the AI learning identification information included in the first information;

The relay service code included in the second information is the same as the relay service code included in the first information.

In some embodiments of the present application, the core network device includes a first core network device, and the first core network device is an artificial intelligence (AI) functional entity.

In some embodiments of the present application, the core network device includes a second core network device, and the second core network device is a policy control function (PCF) entity.

In some embodiments of the present application, the communication unit 410 is also used to:

Send the training data of the AI model to the server corresponding to the first AI learning task through the second terminal, wherein both the terminal device and the second terminal belong to the AI learning task group corresponding to the first AI learning task.

In some embodiments of the present application, the first information includes first AI learning identification information, and the first AI learning identification information is allocated by the AI functional entity to the AI learning task group to which the terminal device belongs.

In some embodiments of the present application, the AI learning task group is a federated learning task group, the first information includes first AI learning identification information, and the first AI learning identification information is federated learning identification information.

Optionally, in some embodiments, the above-mentioned communication unit may be a communication interface or a transceiver, or an input-output interface of a communication chip or a system-on-chip. The aforementioned processing unit may be one or more processors.

It should be understood that the terminal device 400 according to the embodiment of the present application may correspond to the first terminal in the method embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the terminal device 400 are to realize the The corresponding process of the first terminal in the method shown in 8 is not repeated here for the sake of brevity.

Fig. 10 shows a schematic block diagram of a terminal device 500 according to an embodiment of the present application. As shown in Figure 10, the terminal device 500 includes:

The communication unit 510 is configured to receive second information sent by the core network device, where the second information is used to determine the AI learning task group to which the terminal device belongs.

In some embodiments of the present application, the second information includes at least one of the following:

The second AI learning identification information, the second relay service code, wherein the second AI learning identification information is used to identify the AI learning task group to which the terminal device belongs, the second relay service code and the first Two AI learning identification information correspondence.

In some embodiments of the present application, the communication unit 510 is also used to:

The first information sent by the first terminal is received, where the first information is used to determine the AI learning task group to which the first terminal belongs.

In some embodiments of the present application, the communication unit 510 is also used to:

Receive a discovery request message sent by the first terminal, where the discovery request message includes the first information.

In some embodiments of the present application, the terminal device further includes:

a processing unit, configured to determine whether the first terminal and the terminal device belong to the same AI learning task group according to the first information and the second information;

The communication unit 510 is further configured to: send a discovery response message to the first terminal when the first terminal and the terminal device belong to the same AI learning task group.

In some embodiments of the present application, the processing unit is also used for:

When at least one of the following conditions is met, it is determined that the first terminal and the terminal device belong to the same AI learning task group:

The AI learning identification information included in the first information is the same as the AI learning identification information included in the second information;

The relay service code included in the first information is the same as the relay service code included in the second information.

In some embodiments of the present application, the communication unit 510 is further configured to: send the second AI learning identification information and/or the second relay service code.

In some embodiments of the present application, the communication unit 510 is also used to:

Sending a discovery announcement message, where the discovery announcement message includes the second AI learning identification information and/or the second relay service code.

In some embodiments of the present application, the communication unit 510 is also used to:

Sending a discovery response message to the first terminal, where the discovery response message includes the second AI learning identification information and/or the second relay service code.

In some embodiments of the present application, the core network device includes a first core network device, and the first core network device is an artificial intelligence (AI) functional entity.

In some embodiments of the present application, the core network device includes a second core network device, and the second core network device is a policy control function (PCF) entity.

In some embodiments of the present application, the second information includes second AI learning identification information, where the second AI learning identification information is allocated by the AI functional entity to the AI learning task group to which the terminal device belongs.

In some embodiments of the present application, the AI learning task group is a federated learning task group, the second information includes second AI learning identification information, and the second AI learning identification information is federated learning identification information.

Optionally, in some embodiments, the above-mentioned communication unit may be a communication interface or a transceiver, or an input-output interface of a communication chip or a system-on-chip. The aforementioned processing unit may be one or more processors.

It should be understood that the terminal device 500 according to the embodiment of the present application may correspond to the second terminal in the method embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the terminal device 500 are to realize the The corresponding process of the second terminal in the method shown in 8 is not repeated here for the sake of brevity.

Fig. 11 is a schematic block diagram of a core network device according to an embodiment of the present application. The core network device 800 in FIG. 11 includes:

A communication unit 810, configured to acquire identification information of terminal devices in the first artificial intelligence AI learning task group;

A processing unit 820, configured to assign first AI learning identification information to the first AI learning task group, where the first AI learning identification information is used to identify the first AI learning task group;

The communication unit 810 is further configured to: send the first AI learning identification information to terminal devices in the first AI learning task group.

In some embodiments of the present application, the communication unit 810 is also used to:

Sending the first AI learning identification information to the terminal devices in the first AI learning task group through the second core network device.

In some embodiments of the present application, the second core network device is a policy control function (PCF) entity.

In some embodiments of the present application, the core network device is an artificial intelligence AI functional entity.

In some embodiments of the present application, the communication unit 810 is also used to:

Obtain the identification information of the terminal devices in the first AI learning task group from the server corresponding to the first AI learning task.

Optionally, in some embodiments, the above-mentioned communication unit may be a communication interface or a transceiver, or an input-output interface of a communication chip or a system-on-chip. The aforementioned processing unit may be one or more processors.

It should be understood that the core network device 800 according to the embodiment of the present application may correspond to the core network device in the method embodiment of the present application, such as the first core network device, and the above and other operations and/or operations of each unit in the core network device 800 or functions are respectively to realize the corresponding processes of the core network device in the methods shown in FIG. 4 to FIG.

Fig. 12 is a schematic block diagram of a core network device according to an embodiment of the present application. The core network device 1000 in FIG. 12 includes:

The communication unit 1010 is configured to send a first relay service code to the first terminal, where the first relay service code corresponds to first artificial intelligence AI learning identification information, and the first AI learning identification information is used to identify The AI learning task group to which the first terminal belongs.

In some embodiments of the present application, the core network equipment further includes:

A processing unit, configured to determine the first relay service code according to the first AI learning identification information and the corresponding relationship between the AI learning identification information and the relay service code.

In some embodiments of the present application, the correspondence between the AI learning identification information and the relay service code is pre-configured.

In some embodiments of the present application, the core network device is a policy control function (PCF) entity.

Optionally, in some embodiments, the above-mentioned communication unit may be a communication interface or a transceiver, or an input-output interface of a communication chip or a system-on-chip. The aforementioned processing unit may be one or more processors.

It should be understood that the core network device 1000 according to the embodiment of the present application may correspond to the core network device in the method embodiment of the present application, such as the second core network device, and the above and other operations and/or operations of each unit in the core network device 1000 or functions are respectively to realize the corresponding processes of the core network device in the methods shown in FIG. 4 to FIG.

Fig. 13 is a schematic structural diagram of a communication device 600 provided by an embodiment of the present application. The communication device 600 shown in FIG. 13 includes a processor 610, and the processor 610 can call and run a computer program from a memory, so as to implement the method in the embodiment of the present application.

Optionally, as shown in FIG. 13 , the communication device 600 may further include a memory 620 . Wherein, the processor 610 can invoke and run a computer program from the memory 620, so as to implement the method in the embodiment of the present application.

Wherein, the memory 620 may be an independent device independent of the processor 610 , or may be integrated in the processor 610 .

Optionally, as shown in FIG. 13 , the communication device 600 may further include a transceiver 630, and the processor 610 may control the transceiver 630 to communicate with other devices, specifically, to send information or data to other devices, or receive other Information or data sent by the device.

Wherein, the transceiver 630 may include a transmitter and a receiver. The transceiver 630 may further include antennas, and the number of antennas may be one or more.

Optionally, the communication device 600 may specifically be the core network device of the embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the core network device in each method of the embodiment of the present application. Let me repeat.

Optionally, the communication device 600 may specifically be the first terminal in the embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the first terminal in each method of the embodiment of the present application. For the sake of brevity, the Let me repeat.

Optionally, the communication device 600 may specifically be the second terminal in the embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the second terminal in each method of the embodiment of the present application. For the sake of brevity, the Let me repeat.

FIG. 14 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 700 shown in FIG. 14 includes a processor 710, and the processor 710 can call and run a computer program from a memory, so as to implement the method in the embodiment of the present application.

Optionally, as shown in FIG. 14 , the chip 700 may further include a memory 720 . Wherein, the processor 710 can invoke and run a computer program from the memory 720, so as to implement the method in the embodiment of the present application.

Wherein, the memory 720 may be an independent device independent of the processor 710 , or may be integrated in the processor 710 .

Optionally, the chip 700 may also include an input interface 730 . Wherein, the processor 710 can control the input interface 730 to communicate with other devices or chips, specifically, can obtain information or data sent by other devices or chips.

Optionally, the chip 700 may also include an output interface 740 . Wherein, the processor 710 can control the output interface 740 to communicate with other devices or chips, specifically, can output information or data to other devices or chips.

Optionally, the chip can be applied to the core network device in the embodiment of the present application, and the chip can implement the corresponding process implemented by the core network device in each method of the embodiment of the present application. For the sake of brevity, details are not repeated here.

Optionally, the chip can be applied to the first terminal in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the first terminal in the methods of the embodiments of the present application. For the sake of brevity, details are not repeated here.

Optionally, the chip can be applied to the second terminal in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the second terminal in the methods of the embodiments of the present application. For the sake of brevity, details are not repeated here.

It should be understood that the chip mentioned in the embodiment of the present application may also be called a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip.

FIG. 15 is a schematic block diagram of a communication system 1100 provided by an embodiment of the present application. As shown in FIG. 15 , the communication system 1100 includes a remote terminal 1110 , a relay terminal 1120 and a core network device 1130 .

Wherein, the remote terminal 1110 can be used to implement the corresponding functions implemented by the first terminal in the above method, the relay terminal 1120 can be used to implement the corresponding functions implemented by the second terminal in the above method, and the core network The device 1130 may be used to implement the corresponding functions implemented by the core network device (for example, the first core network device and/or the second core network device) in the above method. For the sake of brevity, details are not repeated here.

It should be understood that the processor in the embodiment of the present application may be an integrated circuit chip, which has a signal processing capability. In the implementation process, each step of the above-mentioned method embodiments may be completed by an integrated logic circuit of hardware in a processor or instructions in the form of software. The above-mentioned processor can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other available Program logic devices, discrete gate or transistor logic devices, discrete hardware components. Various methods, steps, and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.

It can be understood that the memory in the embodiments of the present application may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. Among them, the non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electronically programmable Erase Programmable Read-Only Memory (Electrically EPROM, EEPROM) or Flash. The volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (Static RAM, SRAM), Dynamic Random Access Memory (Dynamic RAM, DRAM), Synchronous Dynamic Random Access Memory (Synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory (Synchlink DRAM, SLDRAM ) and Direct Memory Bus Random Access Memory (Direct Rambus RAM, DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but not be limited to, these and any other suitable types of memory.

It should be understood that the above-mentioned memory is illustrative but not restrictive. For example, the memory in the embodiment of the present application may also be a static random access memory (static RAM, SRAM), a dynamic random access memory (dynamic RAM, DRAM), Synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous connection Dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is, the memory in the embodiments of the present application is intended to include, but not be limited to, these and any other suitable types of memory.

The embodiment of the present application also provides a computer-readable storage medium for storing computer programs.

Optionally, the computer-readable storage medium can be applied to the core network device in the embodiment of the present application, such as the first core network device and the second core network device, and the computer program enables the computer to execute each method in the embodiment of the present application For the sake of brevity, the corresponding process implemented by the core network equipment will not be repeated here.

Optionally, the computer-readable storage medium may be applied to the first terminal in the embodiment of the present application, and the computer program causes the computer to execute the corresponding process implemented by the first terminal in each method of the embodiment of the present application. For brevity, I won't repeat them here.

Optionally, the computer-readable storage medium can be applied to the second terminal in the embodiment of the present application, and the computer program causes the computer to execute the corresponding process implemented by the second terminal in each method of the embodiment of the present application. For the sake of brevity, I won't repeat them here.

The embodiment of the present application also provides a computer program product, including computer program instructions.

Optionally, the computer program product can be applied to the core network device in the embodiment of the present application, such as the first core network device and the second core network device, and the computer program instructions cause the computer to execute each method in the embodiment of the present application For the sake of brevity, the corresponding processes implemented by the core network equipment will not be repeated here.

Optionally, the computer program product may be applied to the first terminal in the embodiment of the present application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the first terminal in each method of the embodiment of the present application. For brevity, the This will not be repeated here.

Optionally, the computer program product can be applied to the second terminal in the embodiment of the present application, and the computer program instructions cause the computer to execute the corresponding process implemented by the second terminal in each method of the embodiment of the present application. For brevity, the This will not be repeated here.

The embodiment of the present application also provides a computer program.

Optionally, the computer program can be applied to the core network device in the embodiment of the present application, such as the first core network device and the second core network device, and when the computer program is run on the computer, the computer executes the embodiment of the present application For the sake of brevity, the corresponding processes implemented by the core network device in each of the methods will not be repeated here.

Optionally, the computer program can be applied to the first terminal in the embodiment of the present application, and when the computer program is run on the computer, the computer executes the corresponding process implemented by the first terminal in each method of the embodiment of the present application, For the sake of brevity, details are not repeated here.

Optionally, the computer program can be applied to the second terminal in the embodiment of the present application, and when the computer program is run on the computer, the computer executes the corresponding process implemented by the second terminal in each method of the embodiment of the present application, For the sake of brevity, details are not repeated here.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

If the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

The above is only a specific implementation of the application, but the scope of protection of the application is not limited thereto. Anyone familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the application. Should be covered within the protection scope of this application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims (100)

A method for wireless communication, comprising: The first terminal receives the first information sent by the core network device, and the first information is used to determine the artificial intelligence AI learning task group to which the first terminal belongs. The method according to claim 1, wherein the first information includes at least one of the following: The first AI learning identification information and the first relay service code, wherein the first AI learning identification information is used to identify the AI learning task group to which the first terminal belongs, the first relay service code and the The first AI learns to correspond to the identification information. The method according to claim 2, further comprising: The first terminal sends the first AI learning identification information and/or the first relay service code. The method according to claim 3, wherein the sending of the first AI learning identification information and/or the first relay service code by the first terminal includes: The first terminal sends a discovery request message, where the discovery request message includes the first AI learning identification information and/or the first relay service code. The method according to claim 3 or 4, wherein the method further comprises: The first terminal receives the discovery response message sent by the second terminal, and the second terminal and the first terminal belong to the same AI learning task group. The method according to claim 5, wherein the method further comprises: The first terminal selects the second terminal as a relay terminal. The method according to claim 1 or 2, characterized in that the method further comprises: The first terminal receives the second information sent by the second terminal, and the second information is used to determine the AI learning task group to which the second terminal belongs. The method according to claim 7, wherein the second information includes at least one of the following: The second AI learning identification information and the second relay service code, wherein the second AI learning identification information is used to identify the AI learning task group to which the second terminal belongs, and the second relay service code and the The second AI learns to correspond to the identification information. The method according to claim 8, wherein the first terminal receiving the second information sent by the second terminal comprises: The first terminal receives the discovery announcement message sent by the second terminal, where the discovery announcement message includes the second information. The method according to claim 8, wherein the first terminal receiving the second information sent by the second terminal comprises: The first terminal receives the discovery response message sent by the second terminal, where the discovery response message includes the second information. The method according to any one of claims 7-10, further comprising: The first terminal determines whether to select the second terminal as a relay terminal according to the second information and the first information. The method according to claim 11, wherein the first terminal determines whether to select the second terminal as a relay terminal according to the second information and the first information, comprising: The first terminal determines whether the second terminal and the first terminal belong to the same AI learning task group according to the second information and the first information; If the second terminal and the first terminal belong to the same AI learning task group, select the second terminal as a relay terminal. The method according to claim 12, wherein the first terminal determines whether the second terminal and the first terminal belong to the same AI learning task group according to the second information or the first information ,include: When at least one of the following conditions is met, it is determined that the second terminal and the first terminal belong to the same AI learning task group: The AI learning identification information included in the second information is the same as the AI learning identification information included in the first information; The relay service code included in the second information is the same as the relay service code included in the first information. The method according to any one of claims 1-13, wherein the core network device includes a first core network device, and the first core network device is a network data analysis function NWDAF entity or an artificial intelligence AI function entity. The method according to any one of claims 1-13, wherein the core network device includes a second core network device, and the second core network device is a Policy Control Function (PCF) entity. The method according to any one of claims 1-15, further comprising: The first terminal sends the training data of the AI model to the server corresponding to the first AI learning task through the second terminal, wherein both the first terminal and the second terminal belong to the server corresponding to the first AI learning task. AI Learning Task Force. The method according to any one of claims 1-16, wherein the first information includes first AI learning identification information, and the first AI learning identification information is that the AI functional entity is the first terminal Assigned by the AI learning task group to which it belongs. The method according to any one of claims 1-17, wherein the AI learning task group is a federated learning task group, the first information includes first AI learning identification information, and the first AI learning task group The identification information is federated learning identification information. A method for wireless communication, comprising: The second terminal receives the second information sent by the core network device, where the second information is used to determine the AI learning task group to which the second terminal belongs. The method according to claim 19, wherein the second information includes at least one of the following: The second AI learning identification information and the second relay service code, wherein the second AI learning identification information is used to identify the AI learning task group to which the second terminal belongs, and the second relay service code and the The second AI learns to correspond to the identification information. The method according to claim 19 or 20, wherein the method further comprises: The second terminal receives the first information sent by the first terminal, where the first information is used to determine the AI learning task group to which the first terminal belongs. The method according to claim 21, wherein the second terminal receiving the first information sent by the first terminal comprises: The second terminal receives the discovery request message sent by the first terminal, where the discovery request message includes the first information. The method according to claim 21 or 22, further comprising: The second terminal determines whether the first terminal and the second terminal belong to the same AI learning task group according to the first information and the second information; If the first terminal and the second terminal belong to the same AI learning task group, sending a discovery response message to the first terminal. The method according to claim 23, wherein the second terminal determines whether the first terminal and the second terminal belong to the same AI learning task group according to the first information and the second information ,include: When at least one of the following conditions is met, the second terminal determines that the first terminal and the second terminal belong to the same AI learning task group: The AI learning identification information included in the first information is the same as the AI learning identification information included in the second information; The relay service code included in the first information is the same as the relay service code included in the second information. The method according to claim 20, further comprising: The second terminal sends the second AI learning identification information and/or the second relay service code. The method according to claim 25, wherein the sending of the second information by the second terminal includes: The second terminal sends a discovery announcement message, where the discovery announcement message includes the second AI learning identification information and/or the second relay service code. The method according to claim 25, wherein the second terminal sends the second AI learning identification information and/or the second relay service code, comprising: The second terminal sends a discovery response message to the first terminal, where the discovery response message includes the second AI learning identification information and/or the second relay service code. The method according to any one of claims 19-27, wherein the core network device includes a first core network device, and the first core network device is a network data analysis function NWDAF entity or an artificial intelligence AI function entity. The method according to any one of claims 19-27, wherein the core network device includes a second core network device, and the second core network device is a Policy Control Function (PCF) entity. The method according to any one of claims 19-29, wherein the second information includes second AI learning identification information, wherein the second AI learning identification information is the NWDAF entity or the AI functional entity is Assigned by the AI learning task group to which the second terminal belongs. The method according to any one of claims 19-30, wherein the AI learning task group is a federated learning task group, the second information includes second AI learning identification information, and the second AI learning task group The identification information is federated learning identification information. A method for wireless communication, comprising: The first core network device obtains the identification information of the terminal devices in the first artificial intelligence AI learning task group; The first core network device assigns first AI learning identification information to the first AI learning task group, where the first AI learning identification information is used to identify the first AI learning task group; The first core network device sends the first AI learning identification information to terminal devices in the first AI learning task group. The method of claim 32, further comprising: The first core network device sends the first AI learning identification information to the terminal devices in the first AI learning task group through the second core network device. The method according to claim 33, wherein the second core network device is a Policy Control Function (PCF) entity. The method according to any one of claims 32-34, wherein the first core network device is a network data analysis function NWDAF entity or an artificial intelligence AI function entity. The method according to any one of claims 32-35, wherein the first core network device acquires identification information of terminal devices in the first AI learning task group, including: The first core network device acquires identification information of terminal devices in the first AI learning task group from a server corresponding to the first AI learning task. A method for wireless communication, comprising: The second core network device sends the first relay service code to the first terminal, where the first relay service code corresponds to the first artificial intelligence AI learning identification information, and the first AI learning identification information is used to identify the The AI learning task group to which the first terminal belongs. The method according to claim 37, characterized in that the method further comprises: the second core network device determines according to the first AI learning identification information combined with the corresponding relationship between the AI learning identification information and the relay service code The first relay service code. The method according to claim 38, wherein the correspondence between the AI learning identification information and the relay service code is pre-configured. The method according to any one of claims 37-39, wherein the second core network device is a Policy Control Function (PCF) entity. A terminal device, characterized in that it includes: The communication unit is configured to receive the first information sent by the core network device, the first information is used to determine the artificial intelligence AI learning task group to which the terminal device belongs. The terminal device according to claim 41, wherein the first information includes at least one of the following: The first AI learning identification information, the first relay service code, wherein the first AI learning identification information is used to identify the AI learning task group to which the terminal device belongs, the first relay service code and the first relay service code A corresponding AI learning identification information. The terminal device according to claim 42, wherein the communication unit is also used for: Sending the first AI learning identification information and/or the first relay service code. The terminal device according to claim 43, wherein the communication unit is further used for: Sending a discovery request message, where the discovery request message includes the first AI learning identification information and/or the first relay service code. The terminal device according to claim 43 or 44, wherein the communication unit is further used for: Receive a discovery response message sent by a second terminal, where the second terminal and the terminal device belong to the same AI learning task group. The terminal device according to claim 45, wherein the terminal device further comprises: A processing unit, configured to select the second terminal as a relay terminal. The terminal device according to claim 41 or 42, wherein the communication unit is further used for: receiving second information sent by the second terminal, where the second information is used to determine the AI learning task group to which the second terminal belongs. The terminal device according to claim 47, wherein the second information includes at least one of the following: The second AI learning identification information and the second relay service code, wherein the second AI learning identification information is used to identify the AI learning task group to which the second terminal belongs, and the second relay service code and the The second AI learns to correspond to the identification information. The terminal device according to claim 48, wherein the communication unit is further used for: receiving a discovery announcement message sent by the second terminal, where the discovery announcement message includes the second information. The terminal device according to claim 49, wherein the communication unit is further used for: Receive a discovery response message sent by the second terminal, where the discovery response message includes the second information. The terminal device according to any one of claims 47-50, wherein the terminal device further comprises: A processing unit, configured to determine whether to select the second terminal as a relay terminal according to the second information and the first information. The terminal device according to claim 51, wherein the processing unit is further used for: determining whether the second terminal and the terminal device belong to the same AI learning task group according to the second information and the first information; If the second terminal and the terminal device belong to the same AI learning task group, select the second terminal as a relay terminal. The terminal device according to claim 52, wherein the processing unit is further used for: When at least one of the following conditions is met, it is determined that the second terminal and the terminal device belong to the same AI learning task group: The AI learning identification information included in the second information is the same as the AI learning identification information included in the first information; The relay service code included in the second information is the same as the relay service code included in the first information. The terminal device according to any one of claims 41-53, wherein the core network device includes a first core network device, and the first core network device is a network data analysis function NWDAF entity or artificial intelligence AI functional entities. The terminal device according to any one of claims 41-54, wherein the core network device includes a second core network device, and the second core network device is a Policy Control Function (PCF) entity. The terminal device according to any one of claims 41-55, wherein the communication unit is further used for: Send the training data of the AI model to the server corresponding to the first AI learning task through the second terminal, wherein both the terminal device and the second terminal belong to the AI learning task group corresponding to the first AI learning task. The terminal device according to any one of claims 41-56, wherein the first information includes first AI learning identification information, and the first AI learning identification information is that the NWDAF entity or the AI functional entity is the assigned by the AI learning task group to which the above-mentioned terminal device belongs. The terminal device according to any one of claims 41-57, wherein the AI learning task group is a federated learning task group, the first information includes first AI learning identification information, and the first AI The learning identification information is federated learning identification information. A terminal device, characterized in that it includes: The communication unit is configured to receive the second information sent by the core network device, where the second information is used to determine the AI learning task group to which the terminal device belongs. The terminal device according to claim 59, wherein the second information includes at least one of the following: The second AI learning identification information, the second relay service code, wherein the second AI learning identification information is used to identify the AI learning task group to which the terminal device belongs, the second relay service code and the first Two AI learning identification information correspondence. The terminal device according to claim 59 or 60, wherein the communication unit is further used for: The first information sent by the first terminal is received, where the first information is used to determine the AI learning task group to which the first terminal belongs. The terminal device according to claim 61, wherein the communication unit is further used for: Receive a discovery request message sent by the first terminal, where the discovery request message includes the first information. The terminal device according to claim 61 or 62, wherein the terminal device further comprises: a processing unit, configured to determine whether the first terminal and the terminal device belong to the same AI learning task group according to the first information and the second information; The communication unit is further configured to: send a discovery response message to the first terminal when the first terminal and the terminal device belong to the same AI learning task group. The terminal device according to claim 63, wherein the processing unit is further used for: When at least one of the following conditions is met, it is determined that the first terminal and the terminal device belong to the same AI learning task group: The AI learning identification information included in the first information is the same as the AI learning identification information included in the second information; The relay service code included in the first information is the same as the relay service code included in the second information. The terminal device according to claim 60, wherein the communication unit is further used for: Sending the second AI learning identification information and/or the second relay service code. The terminal device according to claim 65, wherein the communication unit is further used for: Sending a discovery announcement message, where the discovery announcement message includes the second AI learning identification information and/or the second relay service code. The terminal device according to claim 65, wherein the communication unit is further used for: Sending a discovery response message to the first terminal, where the discovery response message includes the second AI learning identification information and/or the second relay service code. The terminal device according to any one of claims 59-67, wherein the core network device includes a first core network device, and the first core network device is a network data analysis function NWDAF entity or an artificial intelligence AI functional entities. The terminal device according to any one of claims 59-67, wherein the core network device includes a second core network device, and the second core network device is a Policy Control Function (PCF) entity. The terminal device according to any one of claims 59-69, wherein the second information includes second AI learning identification information, wherein the second AI learning identification information is a NWDAF entity or an AI functional entity Assigned to the AI learning task group to which the terminal device belongs. The terminal device according to any one of claims 59-70, wherein the AI learning task group is a federated learning task group, the second information includes second AI learning identification information, and the second AI The learning identification information is federated learning identification information. A core network device, characterized in that it includes: A communication unit, configured to obtain identification information of terminal devices in the first artificial intelligence AI learning task group; A processing unit, configured to assign first AI learning identification information to the first AI learning task group, wherein the first AI learning identification information is used to identify the first AI learning task group; The communication unit is further configured to: send the first AI learning identification information to terminal devices in the first AI learning task group. The core network device according to claim 72, wherein the communication unit is further used for: Sending the first AI learning identification information to the terminal devices in the first AI learning task group through the second core network device. The core network device according to claim 73, wherein the second core network device is a Policy Control Function (PCF) entity. The core network device according to any one of claims 72-74, wherein the core network device is a network data analysis function NWDAF entity or an artificial intelligence AI function entity. The core network device according to any one of claims 72-75, wherein the communication unit is further used for: Obtain the identification information of the terminal devices in the first AI learning task group from the server corresponding to the first AI learning task. A core network device, characterized in that it includes: A communication unit, configured to send a first relay service code to the first terminal, where the first relay service code corresponds to first artificial intelligence AI learning identification information, and the first AI learning identification information is used to identify the The AI learning task group to which the first terminal belongs. The core network device according to claim 77, wherein the core network device further comprises: A processing unit, configured to determine the first relay service code according to the first AI learning identification information and the corresponding relationship between the AI learning identification information and the relay service code. The core network device according to claim 78, wherein the correspondence between the AI learning identification information and the relay service code is pre-configured. The core network device according to any one of claims 77-79, wherein the core network device is a Policy Control Function (PCF) entity. A terminal device, characterized by comprising: a processor and a memory, the memory is used to store a computer program, the processor is used to call and run the computer program stored in the memory, and execute any of the following claims 1 to 18 one of the methods described. A chip, characterized by comprising: a processor, configured to invoke and run a computer program from a memory, so that a device installed with the chip executes the method according to any one of claims 1 to 18. A computer-readable storage medium, characterized by being used for storing a computer program, the computer program causes a computer to execute the method according to any one of claims 1 to 18. A computer program product, characterized by comprising computer program instructions, the computer program instructions cause a computer to execute the method according to any one of claims 1 to 18. A computer program, characterized in that the computer program causes a computer to execute the method according to any one of claims 1-18. A terminal device, characterized by comprising: a processor and a memory, the memory is used to store a computer program, the processor is used to invoke and run the computer program stored in the memory, and execute any of the following claims 19 to 31 one of the methods described. A chip, characterized by comprising: a processor, configured to invoke and run a computer program from a memory, so that a device installed with the chip executes the method according to any one of claims 19 to 31. A computer-readable storage medium, characterized by being used for storing a computer program, the computer program causes a computer to execute the method according to any one of claims 19 to 31. A computer program product, characterized by comprising computer program instructions, the computer program instructions cause a computer to execute the method according to any one of claims 19 to 31. A computer program, characterized in that the computer program causes a computer to execute the method according to any one of claims 19-31. A core network device, characterized by comprising: a processor and a memory, the memory is used to store a computer program, the processor is used to call and run the computer program stored in the memory, and execute the method described in claims 32 to 36 any one of the methods described. A chip, characterized by comprising: a processor, configured to invoke and run a computer program from a memory, so that a device installed with the chip executes the method according to any one of claims 32 to 36. A computer-readable storage medium, characterized in that it is used to store a computer program, the computer program causes a computer to perform the method according to any one of claims 32 to 36. A computer program product, characterized by comprising computer program instructions, the computer program instructions cause a computer to execute the method as claimed in any one of claims 32 to 36. A computer program, characterized in that the computer program causes a computer to execute the method according to any one of claims 32 to 36. A core network device, characterized by comprising: a processor and a memory, the memory is used to store a computer program, the processor is used to call and run the computer program stored in the memory, and execute the computer program as claimed in claims 37 to 40 any one of the methods described. A chip, characterized by comprising: a processor, configured to call and run a computer program from a memory, so that a device installed with the chip executes the method according to any one of claims 37 to 40. A computer-readable storage medium, characterized by being used to store a computer program, the computer program causing a computer to execute the method according to any one of claims 37 to 40. A computer program product, characterized by comprising computer program instructions, the computer program instructions cause a computer to execute the method according to any one of claims 37 to 40. A computer program, characterized in that the computer program causes a computer to execute the method according to any one of claims 37-40.

Images