Information interaction method and apparatus, and network element and first device

Abstract

The present application belongs to the technical field of communications. Disclosed are an information interaction method and apparatus, and a network element and a first device. The information interaction method in the embodiments of the present application comprises: a first network element sending a first request message to a second network element, wherein the first request message is used for requesting registration of first information of the first network element, or requesting an update of the first information of the first network element, and the first information comprises at least one of the following: first capability information of the first network element, or first service information of the first network element, the first capability information being capability information related to proxy federated learning, and the first service information being service information related to the proxy federated learning.

Description

Information interaction method and apparatus, network element, and first device

[0001] Cross-reference to Related Applications

[0002] This application claims priority to Chinese Patent Application No. 202411917423.X, filed on December 24, 2024, the contents of which are incorporated herein by reference in their entirety. TECHNICAL FIELD

[0003] The present application belongs to the field of communication technology, and specifically relates to an information interaction method, device, network element and first device. BACKGROUND

[0004] Federated learning can include vertical federated learning (VFL) and horizontal federated learning (HFL). The essence of vertical federated learning is the joint of features, which is suitable for scenarios with more overlapping users and less overlapping features. For example, the core network (CN) domain and the radio access network (RAN) domain in a communication network serve the same users with different services. By combining the different data features of the common samples of the participating parties, vertical federated learning increases the feature dimension of the training samples, which is conducive to training a better model.

[0005] Currently, in the case of federated learning, there are some inconveniences in the interaction between federated learning devices. For example, it is difficult for external devices participating in federated learning (such as application functions (AF)) to interact with user equipment (UE) or RAN devices participating in federated learning about federated learning process related information, which affects the execution efficiency of the federated learning process. SUMMARY

[0006] Embodiments of the present application provide an information interaction method, device, network element and first device. By registering information related to proxy federated learning of the network element, it is convenient to quickly find a network element supporting proxy federated learning to proxy federated learning devices for federated learning, thereby improving the execution efficiency of the federated learning process.

[0007] In a first aspect, an information interaction method is provided. The method includes:

[0008] The first network element sends a first request message to the second network element;

[0009] The first request message is used to request registration of the first information of the first network element, or is used to request update of the first information of the first network element.

[0010] The first information includes at least one of first capability information of the first network element and first service information of the first network element, wherein the first capability information is capability information related to proxy federated learning, and the first service information is service information related to proxy federated learning.

[0011] In a second aspect, an information interaction apparatus is provided, and the apparatus includes:

[0012] The sending module is configured to send a first request message to a second network element.

[0013] The first request message is used to request registration of the first information of the first network element, or is used to request update of the first information of the first network element.

[0014] The first information includes at least one of first capability information of the first network element and first service information of the first network element, wherein the first capability information is capability information related to proxy federated learning, and the first service information is service information related to proxy federated learning.

[0015] In a third aspect, an information interaction method is provided, and the method includes:

[0016] The second network element receives a first request message from a first network element.

[0017] The first request message is used to request registration of the first information of the first network element, or is used to request update of the first information of the first network element.

[0018] The first information includes at least one of first capability information of the first network element and first service information of the first network element, wherein the first capability information is capability information related to proxy federated learning, and the first service information is service information related to proxy federated learning.

[0019] In a fourth aspect, an information interaction apparatus is provided, and the apparatus includes:

[0020] The receiving module is configured to receive a first request message from a first network element.

[0021] The first request message is used to request registration of the first information of the first network element, or is used to request update of the first information of the first network element.

[0022] The first information includes at least one of the following: first capability information of the first network element, first service information of the first network element, the first capability information being capability information related to proxy federated learning, and the first service information being service information related to proxy federated learning.

[0023] In a fifth aspect, an information interaction method is provided, and the method includes the following steps.

[0024] The first device sends a third request message to the second network element, where the third request message is used to request to find a proxy node that supports proxy federated learning.

[0025] In a sixth aspect, an information interaction apparatus is provided, and the apparatus includes the following components.

[0026] The sending module is configured to send a third request message to the second network element, where the third request message is used to request to find a proxy node that supports proxy federated learning.

[0027] In a seventh aspect, an information interaction apparatus is provided, and the apparatus is configured to perform the steps of the method according to the first aspect, or implement the steps of the method according to the third aspect, or implement the steps of the method according to the fifth aspect.

[0028] In an eighth aspect, a first network element is provided, and the first network element includes a processor and a memory, where the memory stores programs or instructions that can be run on the processor, and the programs or instructions are executed by the processor to implement the steps of the method according to the first aspect.

[0029] In a ninth aspect, a first network element is provided, and the first network element includes a processor and a communication interface, where the communication interface is configured to send a first request message to a second network element, and the first request message is used to request to register first information of the first network element, or is used to request to update the first information of the first network element.

[0030] The first information includes at least one of the following: first capability information of the first network element and first service information of the first network element, the first capability information being capability information related to proxy federation learning, and the first service information being service information related to proxy federation learning.

[0031] In a tenth aspect, a second network element is provided, and the second network element includes a processor and a memory, where the memory stores programs or instructions that can be executed on the processor, and the programs or instructions are executed by the processor to implement the steps of a method according to the third aspect.

[0032] In a eleventh aspect, a second network element is provided, comprising a processor and a communication interface, wherein the communication interface is configured to receive a first request message from a first network element; wherein the first request message is configured to request registration of first information of the first network element, or is configured to request update of the first information of the first network element;

[0033] The first information comprises at least one of: first capability information of the first network element, and first service information of the first network element, wherein the first capability information is capability information related to proxy federated learning, and the first service information is service information related to proxy federated learning.

[0034] In a twelfth aspect, a first device is provided, comprising a processor and a memory, wherein the memory stores programs or instructions executable on the processor, and the programs or instructions are executed by the processor to implement the steps of the method according to the fifth aspect.

[0035] In a thirteenth aspect, a first device is provided, comprising a processor and a communication interface, wherein the communication interface is configured to send a third request message to a second network element, and the third request message is configured to request a proxy node, wherein the proxy node supports proxy federated learning.

[0036] In a fourteenth aspect, a readable storage medium is provided, wherein the readable storage medium stores programs or instructions, and the programs or instructions are executed by a processor to implement the steps of the method according to the first aspect, or to implement the steps of the method according to the third aspect, or to implement the steps of the method according to the fifth aspect.

[0037] In a fifteenth aspect, a wireless communication system is provided, comprising a first network element, a second network element and a first device, wherein the first network element is configured to implement the steps of the information interaction method according to the first aspect, the second network element is configured to implement the steps of the information interaction method according to the third aspect, and the first device is configured to implement the steps of the information interaction method according to the fifth aspect.

[0038] In a sixteenth aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to run programs or instructions to implement the steps of the method according to the first aspect, or to implement the steps of method according to the third aspect.

[0039] In a thirteenth aspect, a computer program / program product is provided, wherein the computer program / program product is stored in a storage medium, and the computer program / program product is executed by at least one processor to implement the steps of the method according to the first aspect, or to implement the steps according to the third aspect.

[0040] In the embodiment of the present application, the first network element sends a first request message to the second network element; wherein the first request message is used to request registration of first information of the first network element, or is used to request update of the first information of the first network element; the first information includes at least one of the following: first capability information of the first network element, first service information of the first network element, the first capability information is capability information related to proxy federated learning, and the first service information is service information related to proxy federated learning. Since the information related to proxy federated learning of the network element is registered, it is convenient to quickly find a network element supporting proxy federated learning to proxy federated learning equipment to perform federated learning, thereby improving the execution efficiency of the federated learning process. BRIEF DESCRIPTION OF DRAWINGS

[0041] FIG. 1 is a block diagram of a wireless communication system to which embodiments of the present application can be applied;

[0042] FIG. 2a is a schematic diagram of vertical federated learning provided by the embodiment of the present application;

[0043] FIG. 2b is a schematic diagram of horizontal federated learning provided by the embodiment of the present application;

[0044] FIG. 3a is a flowchart of network registration to NRF provided by the embodiment of the present application;

[0045] FIG. 3b is a flowchart of querying network element equipment through NRF provided by the embodiment of the present application;

[0046] FIG. 4 is a flowchart of an information interaction method provided by the embodiment of the present application;

[0047] FIG. 5 is a flowchart of another information interaction method provided by the embodiment of the present application;

[0048] FIG. 6 is a flowchart of still another information interaction method provided by the embodiment of the present application;

[0049] FIG. 7 is a flowchart of still another information interaction method provided by the embodiment of the present application;

[0050] FIG. 8 is a structural diagram of an information interaction device provided by the embodiment of the present application;

[0051] FIG. 9 is a structural diagram of another information interaction device provided by the embodiment of the present application;

[0052] FIG. 10 is a structural diagram of still another information interaction device provided by the embodiment of the present application;

[0053] FIG. 11 is a structural diagram of a communication device provided by the embodiment of the present application;

[0054] FIG. 12 is a structural diagram of a network side device provided by the embodiment of the present application;

[0055] FIG. 13 is a structural diagram of a server according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art belong to the scope of protection of the present application.

[0057] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second" are generally a category and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in the present application means at least one of the connected objects. For example, the protection scope of "A or B" at least covers three schemes, namely, scheme one: including A and not including B; scheme two: including B and not including A; scheme three: including A and including B. In addition, the terms "A and / or B", "at least one of A and B", "at least one of A or B" also at least cover the above three schemes, respectively. The character " / " generally represents that the objects before and after are in an "or" relationship.

[0058] The term "indication" in the present application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). Among them, the direct indication can be understood as that the sender explicitly informs the receiver of the specific information, the operation to be performed or the request result, etc. in the indication sent by the sender; the indirect indication can be understood as that the receiver determines the corresponding information according to the indication sent by the sender, or judges and determines the operation to be performed or the request result, etc. according to the judgment result.

[0059] It is worth noting that the technology described in the embodiments of the present application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as in other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems. th

[0060] ​FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a terminal-side device such as a mobile phone, a Tablet Personal Computer, a Laptop Computer, a notebook computer, a Personal Digital Assistant (PDA), a palmtop computer, a netbook, an Ultra-mobile Personal Computer (UMPC), a Mobile Internet Device (MID), an Augmented Reality (AR) device, a Virtual Reality (VR) device, a robot, a wearable device, a flight vehicle, a Vehicle User Equipment (VUE), a shipboard device, a Pedestrian User Equipment (PUE), a smart home (a home device with a wireless communication function such as a refrigerator, a television, a washing machine, or furniture), a game console, a Personal Computer (PC), a kiosk, or a self-service machine. The wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, etc.), a smart wristband, smart clothes, etc. The vehicle-mounted device can also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. The access network device can also be referred to as a Radio Access Network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a Wireless Local Area Network (WLAN) Access Point (AP), or a Wireless Fidelity (WiFi) node, etc.The base station can be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a relay station (RBS), a serving base station (SBS), a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home Node B (HNB), a home evolved Node B, a transmit / receive point (TRP), or some other suitable terminology in the art, and is not limited to a particular technical terminology, provided that the same technical effect is achieved. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0061] The core network device can also be referred to as a core network node, a core network function, or a core network network element, etc., which includes but is not limited to at least one of the following: a mobility management entity (MME), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a policy control function (PCF), a policy and charging rules function (PCRF), an edge application server discovery function (EASDF), a unified data management (UDM), a unified data repository (UDR), a home subscriber server (HSS), a centralized network configuration (CNC), a network repository function (NRF), a network exposure function (NEF), a local NEF (L-NEF), a binding support function (BSF), an application function (AF), a location management function (LMF), a gateway mobile location center (GMLC), a network data analytics function (NWDAF), etc. It should be noted that only the core network device in the NR system is taken as an example for introduction in the embodiments of the present application, and the specific type of the core network device is not limited. If the name of the core network device mentioned in the embodiments of the present application changes in the subsequent protocol version (for example, 6G), it is also within the protection scope of the present application.

[0062] Optionally, the core network device can be implemented by one or more function modules in one device, or can be implemented by multiple devices together, and the embodiments of the present application do not make a specific limitation in this regard. It can be understood that the above function modules can be network elements in a hardware device, can be software function modules running on a dedicated hardware, or can be virtualized function modules instantiated on a platform (for example, a cloud platform).

[0063] For the convenience of understanding, some contents related to the embodiments of the present application are described as follows:

[0064] I. VFL

[0065] The essence of vertical federated learning is the joint of features, which is suitable for a scenario with more overlapping users and less overlapping features, for example, the CN domain and the RAN domain in a communication network serving different services (for example, Mobility Management (MM) service, Session Management (SM) service) of the same user (for example, UE), where the same user means the same sample, and the different services mean different features. By jointly participating in the different data features of the common samples of the parties, vertical federated learning increases the feature dimension of the training samples and obtains a better model. Wherein, FIG. 2a is a schematic diagram of vertical federated learning, and FIG. 2b is a schematic diagram of horizontal federated learning (Horizontal Federated Learning).

[0066] One of the features of VFL is a scenario with overlapping users and different features, therefore, the two parties or multiple parties performing VFL training / inference need to have overlapping users, that is, the same sample data.

[0067] II. Registration process in network

[0068] The NRF is mainly responsible for service discovery function, and maintains the profile of network function (NF) (or network element), where the profile of the network element records the identification and capability information of the network element. For example, the profile of the network element can include the following information:

[0069] NF instance ID;

[0070] NF type;

[0071] PLMN ID in a Public Land Mobile Network (PLMN), PLMN ID and Network ID (NID) in a Stand-alone Non-Public Network (SNPN);

[0072] Fully Qualified Domain Name (FQDN) or Internet Protocol (IP) address of the NF, etc.

[0073] The registration and deregistration of the NF use the services related to Nnrf_NFManagement, and the discovery of the NF can be through the services related to Nnrf_NFDiscovery.

[0074] 1) Network registration to NRF.

[0075] Please refer to FIG. 3a, the network registration to NRF includes the following processes:

[0076] 1. The network element (such as a service consumer (NF service consumer)) sends a message to the NRF through a registration request message (Nnrf_NFManagement_NFRegister Request message) to request network element registration;

[0077] 2. The NRF stores the network element profile of the service consumer and marks the service consumer available (The NRF stores the NF profile of NF service consumer and marks the NF service consumer available);

[0078] 3. The NRF sends a response message to the service consumer through a registration response message (Nnrf_NFManagement_NFRegister response) to confirm that the registration request of the service consumer is accepted (The NRF acknowledge NF Registration is accepted via Nnrf_NFManagement_NFRegister response).

[0079] 2) Network lookup.

[0080] Please refer to FIG. 3b, the network element device can be queried through the NRF, which can include the following steps:

[0081] 1. A network element (e.g., an NF service consumer) sends a message to the NRF via a lookup request (Nnrf_NFDiscovery_Request), which can carry the following information: expected network element type information, expected service name, etc.

[0082] 2. The NRF determines whether to allow the service consumer to discover and find the required NF entity according to the network element type of the service consumer and the expected network element or service.

[0083] 3. If allowed, the NRF determines a set of NF entities that match the lookup request and sends a message to the service consumer via a lookup request response (Nnrf_NFDiscovery_Request Response), carrying the determined matching network element information.

[0084] The information interaction method provided by the embodiments of the present application will be described in detail below in combination with the accompanying drawings and some embodiments and application scenarios thereof.

[0085] Please refer to FIG. 4, which is a flowchart of an information interaction method provided by an embodiment of the present application. The method can be executed by a first network element, as shown in FIG. 4, and includes the following steps:

[0086] Step 401: The first network element sends a first request message to a second network element.

[0087] The first request message is used to request registration of first information of the first network element, or is used to request update of the first information of the first network element.

[0088] The first information includes at least one of the following: first capability information of the first network element, and first service information of the first network element. The first capability information is capability information related to proxy federated learning, and the first service information is service information related to proxy federated learning.

[0089] In this embodiment, the first network element can be any network element supporting proxy federated learning, which can proxy federated learning devices to perform federated learning. For example, the first network element can relay messages of the federated learning device, or can replace the federated learning device to perform federated learning, etc. In some optional embodiments, the above-mentioned first network element can also have federated learning related capabilities, for example, at least one of the following: federated learning preparation capability, federated learning training capability, federated learning inference capability, etc. Illustratively, the above-mentioned federated learning can include vertical federated learning.

[0090] The network element supporting the proxy federated learning can also be referred to as an agent node. Exemplarily, the first network element can be a newly added network element, or can be obtained by enhancing the function of an existing network element, for example, an enhanced NEF or NWDAF, etc.

[0091] The federated learning device can be understood as a device with federated learning capability. The federated learning device can include at least one of a federated learning server and a federated learning client. The federated learning server can include a vertical federated learning server or a horizontal federated learning server, and the federated learning client can include a vertical federated learning client or a horizontal federated learning client.

[0092] The second network element can be any network element capable of storing the registration information of the network element, for example, the second network element can be an NRF or a UDM, etc.

[0093] The capability information related to the proxy federated learning can be used to indicate the capability related to the proxy federated learning, for example, at least one of an indication of the capability of the proxy federated learning, a type of the proxy federated learning (for example, relaying the message of the federated learning device or performing federated learning instead of the federated learning device, etc.), a type of the federated learning device that can be proxied, an identifier of the federated learning device that can be proxied, etc.

[0094] The first service information is used to indicate the service supported by the first network element. The service information related to the proxy federated learning can be used to indicate the service related to the proxy federated learning, for example, a federated learning preparation service, a federated learning training service, a federated learning inference service, etc.

[0095] In some optional embodiments, the first request message can further include at least one of the identifier information of the first network element, the network element type of the first network element, etc. The identifier information of the first network element can include but is not limited to a network element instance identifier, an FQDN, an IP address of the NF, etc.

[0096] Exemplarily, the first request message can be a registration request message, for example, an Nnrf_NFManagement_NFRegister Request message.

[0097] In actual application, the first network element sends a first request message to the second network element, the second network element can store the first information carried in the first request message, or the first network element can update the stored first information of the first network element according to the first information carried in the first request message. In some optional embodiments, the second network element can send a response message to the first network element, for indicating that the first information of the first network element is stored successfully or registered successfully or updated successfully, etc. For example, the second network element can send an Nnrf_NFManagement_NFRegister response message to the first network element to inform the first network element that the registration is successful.

[0098] In the embodiments of the present application, the first network element sends a first request message to the second network element; wherein the first request message is used to request registration of first information of the first network element, or is used to request update of the first information of the first network element; the first information includes at least one of the following: first capability information of the first network element, first service information of the first network element, the first capability information is capability information related to proxy federated learning, and the first service information is service information related to proxy federated learning. Since the information related to proxy federated learning of the network element is registered, it is convenient to quickly find a network element supporting proxy federated learning to proxy federated learning devices to perform federated learning, thereby improving the execution efficiency of the federated learning process.

[0099] Optionally, the proxy federated learning includes at least one of the following:

[0100] Relaying messages of the federated learning devices;

[0101] Substituting the federated learning devices to perform federated learning.

[0102] In the embodiments, the above-mentioned relaying messages of the federated learning devices can also be referred to as forwarding or relaying or bridging messages of the federated learning devices, etc. For example, the proxy node can send messages from the first federated learning device to the second federated learning device, and send messages from the second federated learning device to the first federated learning device, so as to realize convenient interaction between the first federated learning device and the second federated learning device. It can be understood that the proxy node can interact with the second federated learning device, for example, the proxy node can determine the second federated learning device and send messages to the second federated learning device or receive messages from the second federated learning device. The messages can be messages related to federated learning, etc. It should be noted that the above-mentioned relaying messages of the federated learning devices can also be understood as that the proxy node participates in the related process of federated learning as an intermediate node or a sub-node.

[0103] The federated learning performed by the replaced federated learning device can be understood as participating in a federated learning process based on the obtained federated learning device related data, for example, participating in at least one of federated learning preparation, federated learning training, federated learning inference and other federated learning processes based on federated learning device related data. It should be noted that the message relayed by the federated learning device can also be understood as the proxy node participating in the relevant process of federated learning as a leaf node. In this case, the replaced federated learning device can not participate in the corresponding federated learning process, which can reduce the load and computing power of the replaced federated learning device.

[0104] In some optional embodiments, the replaced federated learning device can be a federated learning client, for example, a UE or a RAN, etc.

[0105] Optionally, the first capability information of the first network element includes at least one of:

[0106] The first indication indicates that the first network element is a proxy node;

[0107] The first capability indication indicates that the first network element has the capability of relaying the message of the federated learning device;

[0108] The first type is the type of the federated learning device that the first network element can relay;

[0109] The first identifier is the identifier of the federated learning device that the first network element can relay;

[0110] The second capability indication indicates that the first network element has the capability of performing federated learning by replacing the federated learning device;

[0111] The second type is the type of the federated learning device that the first network element can replace;

[0112] The second identifier is the identifier of the federated learning device that the first network element can replace;

[0113] The third capability indication indicates that the first network element has the capability of proxying federated learning;

[0114] The third type is the type of the federated learning device that the first network element can proxy;

[0115] The third identifier is the identifier of the federated learning device that the first network element can proxy;

[0116] The first aggregation capability information indicates the capability of the first network element for message aggregation;

[0117] The first data collection capability information is used to indicate that the first network element has the capability of collecting relevant data of the federated learning device.

[0118] The first area information is used to indicate a service area of the first network element as a proxy node.

[0119] The first time information is used to indicate a service time of the first network element as a proxy node.

[0120] The proxy node supports proxy federated learning.

[0121] The first indication is used to indicate that the first network element is a proxy node. For example, 1 bit can be used to indicate whether the first network element is a proxy node. Alternatively, the proxy node can be regarded as a type of network element, so that whether the first network element is a proxy node can be determined by the type of network element, that is, the first indication can be the type of network element, and the type of network element is the type of proxy node. Alternatively, whether the first network element is a proxy node can be indicated by whether the first network element has the relevant capability of the proxy node, that is, the first indication can be the capability indication of the first network element related to the proxy federated learning.

[0122] The first capability indication is used to indicate that the first network element has the capability of relaying the message of the federated learning device. It can be understood that the first network element can forward the federated learning related message from the federated learning server to the UE and / or RAN as the federated learning client as an intermediate device or intermediate node. Alternatively, the first network element can forward the federated learning related message from the UE and / or RAN as the federated learning client to the federated learning server as an intermediate device or intermediate node.

[0123] The first type is the type of federated learning device that can be relayed by the first network element, for example, RAN and / or UE, etc. It can be understood that the federated learning device that can be relayed by the first network element means that the first network element can relay the message of the federated learning device.

[0124] The second capability indication is used to indicate that the first network element has the capability of replacing the federated learning device to perform federated learning. It can be understood that the first network element can replace the federated learning device (for example, RAN and / or UE, etc.) to participate in the federated learning process, for example, the first network element can obtain the data of the UE or RAN, and participate in the VFL process as a VFL Client based on the data, that is, the first network element can replace the UE or RAN to participate in the federated learning process by obtaining the data of the UE or RAN.

[0125] The first aggregation capability information is used to indicate the capability of the first network element to aggregate messages. For example, the capability of message aggregation can be understood as the capability of aggregating multiple messages from the federated learning device into one message. For example, multiple VFL preparation messages fed back by multiple VFL clients can be combined into one message. For example, sample identification information can be aggregated. For example, multiple intermediate results fed back by multiple VFL clients can be combined into one aggregated intermediate result. It should be noted that the capability of message aggregation can also be used to indicate the capability of the first network element to relay the messages of the federated learning device.

[0126] Optionally, the first capability information can further include splitting capability information, which is used to indicate the capability of the first network element to split messages. For example, one intermediate message can be divided into multiple intermediate messages. It should be noted that the capability of message splitting can also be used to indicate the capability of the first network element to relay the messages of the federated learning device.

[0127] The second type is the type of federated learning device that can be replaced by the first network element. For example, RAN and / or UE, etc. The federated learning device that can be replaced by the first network element can be understood as that the first network element can replace the federated learning device to perform federated learning.

[0128] The third capability indication is used to indicate the capability of the first network element to proxy federated learning, i.e. the capability of the first network element to proxy / help other devices to perform federated learning. For example, when other devices cannot directly participate in federated learning, the first network element can proxy / help other devices to perform federated learning. For example, when the federated learning client and the federated learning server cannot directly interact, the first network element can relay the messages related to federated learning. For example, the capability of the first network element to relay the messages of the federated learning device or the capability of the first network element to replace the federated learning device to perform federated learning.

[0129] The third type is the type of federated learning device that can be proxied by the first network element. For example, RAN and / or UE, etc. The federated learning device that can be proxied by the first network element can be understood as that the first network element can proxy the federated learning device to perform federated learning.

[0130] The first data collection capability information is used to indicate the capability of the first network element to collect the related data of the federated learning device. For example, the first network element can collect the related data of the federated learning device to replace the federated learning device to perform federated learning. It should be noted that the capability of data collection can also be used to indicate the capability of the first network element to replace the federated learning device to perform federated learning.

[0131] The first area information is used to indicate a service area of the first network element as a proxy node, which can be understood as that the first network element can proxy the federal learning devices in the service area indicated by the first area information to perform federal learning when the first network element is a proxy node. It should be noted that the first area information can also be used to indicate a service area of the first network element having the capability of relaying messages of federal learning devices or the capability of performing federal learning instead of federal learning devices or the capability of message aggregation or the capability of data collection, and the like. It can be understood that the first network element can have the capability of relaying messages of federal learning devices in the service area.

[0132] The first time information is used to indicate a service time of the first network element as a proxy node, which can be understood as that the first network element can proxy federal learning devices to perform federal learning as a proxy node in the service time indicated by the first time information. It should be noted that the first area information can also be used to indicate a service time of the first network element having the capability of relaying messages of federal learning devices or the capability of performing federal learning instead of federal learning devices or the capability of message aggregation or the capability of data collection, and the like. It can be understood that the first network element can have the capability of relaying messages of federal learning devices in the service time.

[0133] It should be noted that the identifier of the federal learning device can include identification information such as a UE ID and / or a RAN ID, or the identifier of the federal learning device can also include identification information such as an IP address and / or a port number.

[0134] It should be noted that the first indication and the second indication can also be referred to as Agent indication. The first type and the second type can include UE agent indication or RAN agent indication.

[0135] In some optional embodiments, the first capability information of the first network element further includes at least one of the following:

[0136] A first federal learning task identifier (task ID) used to indicate a federal learning task supported by the first network element;

[0137] First federal learning capability information used to indicate a capability related to federal learning supported by the first network element;

[0138] Third time information used to indicate a time in which the first network element supports the capability related to federal learning;

[0139] A federal learning type that can be relayed;

[0140] A federal learning type that can be replaced.

[0141] The aforementioned relayable federated learning types include, for example, horizontal federated learning and vertical federated learning. For instance, a proxy node can relay messages from the federated learning device as a proxy node in horizontal federated learning, or as a proxy node in vertical federated learning.

[0142] The aforementioned alternative types of federated learning include, for example, horizontal federated learning and vertical federated learning. For instance, a proxy node can replace other federated learning devices in horizontal federated learning or in vertical federated learning.

[0143] For example, the aforementioned first federated learning task identifier can also be a federated learning task type, used to indicate the type of federated learning task supported by the first network element. It should be noted that the aforementioned federated learning task identifier can also be a VFL task ID, or an analytics ID, etc., where the analytics ID is used to indicate a type of data analysis task. It should also be noted that a task can refer to an event, analytics, data analysis, or a data analysis task, etc., all expressing the same meaning. For example, a VFL task can be a VFL-related event, a VFL-related data analysis, etc.

[0144] For example, the above-mentioned capabilities related to federated learning may include at least one of the following: federated learning client capability, that is, the ability to participate in the federated learning process as a federated learning client; proxy federated learning client capability, that is, the ability to participate in the federated learning process on behalf of a federated learning client; and substitute federated learning client capability, that is, the ability to participate in VFL-related processes on behalf of a federated learning client.

[0145] The aforementioned third time information is used to indicate the time during which the first network element supports capabilities related to federated learning. This can be understood as the first network element supporting the aforementioned capabilities related to federated learning within the time period indicated by the third time information. For example, the aforementioned third time information can indicate a time period.

[0146] In this embodiment, the first network element registers the aforementioned capability information related to proxy federated learning, which helps to more accurately find suitable network elements to proxy federated learning devices for federated learning.

[0147] Optionally, the first service information of the first network element includes at least one of the following:

[0148] Federated learning preparation service information, used to instruct the first network element to support services related to federated learning preparation;

[0149] Federated learning and training service information is used to instruct the first network element to support services related to federated learning and training.

[0150] Federated learning inference service information is used to instruct the first network element to support services related to federated learning inference.

[0151] It is understood that the services supported by the first network element mentioned above can also refer to interactions between other devices (e.g., the second network element) and the first network element through the services supported by the first network element. In some embodiments, the aforementioned services can also be referred to as business operations.

[0152] In this embodiment, the aforementioned federated learning preparation may include sample alignment and / or feature alignment, etc. Optionally, the aforementioned federated learning preparation service information may also include federated learning training services and / or corresponding preparation stage indication information, etc. The first network element supports services related to federated learning preparation, which can be understood as the first network element acting as an agent for the federated learning device in performing the federated learning preparation process. For example, the first network element may relay service messages related to federated learning preparation from the federated learning device, or the first network element may perform federated learning preparation on behalf of the federated learning device, for example, by performing sample alignment and / or feature alignment on behalf of the federated learning device.

[0153] The aforementioned first network element supports services related to federated learning training. This can be understood as the first network element acting as an agent for the federated learning device to perform the federated learning training process. For example, the first network element can relay service messages related to federated learning training from the federated learning device, such as transmitting service messages for at least one of the following used in federated learning training: sample identifiers, intermediate results, intermediate information, model update data, differences, gradient values, etc. Alternatively, the first network element can perform federated learning training on behalf of the federated learning device.

[0154] The aforementioned first network element supports services related to federated learning inference. This can be understood as the first network element acting as an agent for the federated learning device to perform the federated learning inference process. For example, the first network element can relay service messages related to federated learning inference from the federated learning device, such as service messages for data and / or intermediate results used in federated learning inference. Alternatively, the first network element can perform federated learning inference on behalf of the federated learning device.

[0155] In this embodiment, the first network element registers the aforementioned service information related to proxy federated learning, which helps to more accurately find suitable network elements to proxy federated learning devices for federated learning.

[0156] Optionally, if the first network element is the target network element determined through network element lookup, the method further includes:

[0157] The first network element receives a second request message from the first device, the second request message being used to request information on federated learning devices that the first network element can proxies;

[0158] The first network element sends a first response message to the first device, the first response message being used to indicate information about federated learning devices that the first network element can proxies.

[0159] For example, the second request message can be used to request information about the federated learning devices covered by the first network element, or it can be used to request information about the federated learning devices that can be covered by the first network element among at least one federated learning device indicated by the first device.

[0160] The first device mentioned above can be a Federated Learning Server (e.g., AF) or a NEF device.

[0161] In this embodiment, the first device interacts with the first network element to determine information about the federated learning devices that the first network element can proxy, thereby more accurately determining whether the first network element can be used to proxy the federated learning devices for federated learning.

[0162] In some optional embodiments, even if the first network element has not registered information about the federated learning devices it can proxies, the first network element may receive a second request message from the first device and send a first response message to the first device. It should be noted that the second request message may be sent from the first device to the first network element through a fourth device, which may include NEF, etc.

[0163] Optionally, the second request message includes information about the target federated learning device, which is used by the first network element to determine whether it can proxy the target federated learning device for federated learning.

[0164] The first response message includes at least one of the following:

[0165] The second instruction is used to indicate whether the first network element can act as an agent for the target federated learning device to perform federated learning.

[0166] Information about the second device, which includes at least one of the target federated learning devices that the first network element can proxies;

[0167] Information about the third device, wherein the third device is a federated learning device that the first network element can proxy, and the third device is different from the target federated learning device.

[0168] In this embodiment, the target federated learning device can be any federated learning device indicated by the first device, and the number of the target federated learning devices can be at least one.

[0169] The second device mentioned above includes at least one of the target federated learning devices that the first network element can proxies. For example, if the target federated learning devices include UE1, UE2 and UE3, and the target federated learning devices that the first network element can proxies are UE1 and UE2, then the second device mentioned above may include at least one of UE1 and UE2.

[0170] The aforementioned third device is a federated learning device other than the target federated learning device. For example, if the target federated learning device includes UE1, UE2 and UE3, and the federated learning devices that the first network element can proxy are UE1, UE2 and UE4, then the third device can be UE4.

[0171] In this embodiment, by carrying the information of the target federated learning device in the second request message, the first network element determines whether the target federated learning device can be proxied. This makes it easier to more accurately determine whether the first network element can be used to proximate the target federated learning device for federated learning.

[0172] Optionally, the information of the target federated learning device includes at least one of the following: the device type of the target federated learning device, and the identifier of the target federated learning device.

[0173] For example, the device type of the aforementioned target federated learning device may include UE, RAN, etc. The identifier of the aforementioned target federated learning device may include UE ID or RAN ID, etc.

[0174] Optionally, the second request message includes a third instruction, which is used to request information on the federated learning devices that the first network element can proxies;

[0175] The first response message includes information about the federated learning devices that the first network element can proxies.

[0176] The federated learning devices that the aforementioned first network element can represent can also be referred to as the federated learning devices covered by the first network element. The information of the federated learning devices that the aforementioned first network element can represent may include, but is not limited to, the device type and identifier of the federated learning devices.

[0177] In this embodiment, the first network element interacts with the first device to exchange information about the federated learning devices covered by the first network element. This makes it easier to determine more accurately whether the first network element can be used to proxy the target federated learning device for federated learning.

[0178] Please refer to Figure 5, which is a flowchart of an information interaction method provided in an embodiment of this application. This method can be executed by a second network element, and as shown in Figure 5, it includes the following steps:

[0179] Step 501: The second network element receives the first request message from the first network element;

[0180] The first request message is used to request the registration of the first information of the first network element, or to request the updating of the first information of the first network element.

[0181] The first information includes at least one of the following: first capability information of the first network element, first service information of the first network element, the first capability information being capability information related to agent federated learning, and the first service information being service information related to agent federated learning.

[0182] Optionally, the agent federated learning includes at least one of the following:

[0183] Relay message from the federated learning device;

[0184] Used as an alternative to federal learning devices for federal learning.

[0185] Optionally, the first capability information of the first network element includes at least one of the following:

[0186] The first indication is used to indicate that the first network element is a proxy node;

[0187] The first capability indicator is used to indicate that the first network element has the ability to relay messages from the federated learning device.

[0188] The first type is the type of federated learning device that the first network element can relay;

[0189] The first identifier is the identifier of the federated learning device that the first network element can relay;

[0190] The second capability indicator is used to indicate that the first network element has the capability to perform federated learning in place of the federated learning device.

[0191] The second type is the type of federated learning device that the first network element can replace;

[0192] The second identifier is the identifier of the federated learning device that the first network element can replace;

[0193] The third capability indicator is used to indicate that the first network element has the capability of proxy federated learning;

[0194] The third type is the type of federated learning device that the first network element can proxies;

[0195] The third identifier is the identifier of the federated learning device that the first network element can proxies;

[0196] First data collection capability information is used to indicate that the first network element has the ability to collect relevant data from the federated learning device;

[0197] The first aggregation capability information is used to indicate the first network element's ability to aggregate messages;

[0198] The first area information is used to indicate the service area of ​​the first network element as a proxy node;

[0199] First-time information is used to indicate the service time of the first network element as a proxy node;

[0200] The agent node supports agent federated learning.

[0201] Optionally, the first service information of the first network element includes at least one of the following:

[0202] First Federated Learning Preparation Service Information, used to instruct the first network element to support services related to federated learning preparation;

[0203] First Federated Learning and Training Service Information, used to instruct the first network element to support services related to federated learning and training;

[0204] First federated learning inference service information is used to instruct the first network element to support services related to federated learning inference.

[0205] Optionally, the method further includes:

[0206] The second network element receives a third request message from the first device, the third request message being used to request the search of a proxy node, the proxy node supporting proxy federated learning.

[0207] The first device mentioned above can be a federated learning server or an AF, etc. In some optional embodiments, the first device can send a third request message to the first network element through NEF.

[0208] The aforementioned third request message is used to request the search for agent nodes that meet the conditions. For example, it can be a message such as Nnrf_NFDiscovery_Request service. The third request message can include at least one of the following: network element type (used to indicate the type of network element being searched, such as Agent), area information (used to indicate the service range of the network element being searched, etc.).

[0209] It should be noted that the agent node can also be a network element in the enhancement-related technology, so the network element type can also be a device type in other networks, such as NWDAF, NEF, etc.

[0210] In this embodiment, the first device can request the second network element to find a proxy node to perform federated learning on behalf of the federated learning device, which helps to ensure the execution of the federated learning process.

[0211] Optionally, the third request message includes at least one of the following:

[0212] The fourth instruction is used to indicate that the network element to be searched is a proxy node;

[0213] The second capability information that the network element to be searched must possess;

[0214] The network element to be searched must support the second service information;

[0215] The second capability information is capability information related to agent federated learning, and the second service information is service information related to agent federated learning.

[0216] The fourth indication mentioned above is used to indicate that the network element to be searched is a proxy node. For example, it can be indicated by 1 bit that the network element to be searched is a proxy node; or, a proxy node can be a network element type, so that the network element to be searched can be indicated by the network element type being proxy node; or it can be indicated by indicating that the network element to be searched must have the relevant capabilities of a proxy node.

[0217] Optionally, the second capability information includes at least one of the following:

[0218] The fourth capability indicator is used to indicate that the network element to be searched must have the ability to relay messages from the federated learning device;

[0219] The fourth type is the type of federated learning device that the network element to be searched can relay;

[0220] The fourth identifier is the identifier of the federated learning device that the network element to be searched can relay;

[0221] The fifth capability indicator is used to indicate that the network element to be searched must have the ability to perform federated learning in place of the federated learning device;

[0222] The fifth type is the type of federated learning device that can replace the network element to be searched;

[0223] The fifth identifier is the identifier of the federated learning device that the network element to be searched can replace;

[0224] The sixth capability indicator is used to indicate that the network element to be searched must have the ability to perform federated learning on behalf of the federated learning device;

[0225] The sixth type is the type of federated learning device that the network element to be searched can proxies;

[0226] The sixth identifier is the identifier of the federated learning device that the network element to be searched can proxies;

[0227] The second data collection capability information is used to indicate that the network element to be searched must have the ability to collect relevant data from the federated learning device;

[0228] The second aggregation capability information is used to indicate that the network element to be searched must have the ability to perform message aggregation;

[0229] The second area information is used to indicate the service area that the network element to be searched needs to cover;

[0230] The second time information is used to indicate the service time that the network element to be searched needs to support.

[0231] The aforementioned fourth capability indication is used to indicate that the network element to be searched must have the ability to relay messages from the federated learning device. This can be understood as the network element to be searched needing to be able to act as an intermediate device or intermediate node to forward federated learning-related messages from the federated learning server to the UE and / or RAN devices acting as the federated learning client; or the network element to be searched needing to be able to act as an intermediate device or intermediate node to forward federated learning-related messages from the UE, RAN devices acting as the federated learning client to the federated learning server.

[0232] The fourth type mentioned above refers to the type of federated learning device that the network element to be searched can relay, such as RAN and / or UE. Here, "the network element to be searched can relay the federated learning device" can be understood as the network element to be searched being able to relay messages from that federated learning device.

[0233] The aforementioned fifth capability indication is used to indicate that the network element to be searched must have the ability to perform federated learning in place of the federated learning device. This can be understood as the network element to be searched must be able to participate in the federated learning process in place of the federated learning device (e.g., RAN and / or UE). For example, the network element to be searched can obtain data from the UE and / or RAN and participate in the VFL process as a VFL Client based on this data. That is, the network element to be searched can participate in the federated learning process in place of the UE and / or RAN by obtaining data from the UE and / or RAN.

[0234] The fifth type mentioned above refers to the type of federated learning device that can replace the network element to be searched, such as RAN and / or UE. Here, "the network element to be searched that can replace the federated learning device" can be understood as the network element to be searched that can replace the federated learning device for federated learning.

[0235] The sixth capability indicator mentioned above is used to indicate that the network element to be searched must have the capability to act as a proxy for federated learning, such as the ability to relay messages from federated learning devices or the ability to perform federated learning on behalf of federated learning devices.

[0236] The sixth type mentioned above refers to the type of federated learning device that the network element to be searched can proxy, such as RAN and / or UE. Here, "the network element to be searched can proxy the federated learning device" can be understood as the network element to be searched being able to proxy that federated learning device for federated learning.

[0237] The aforementioned second aggregation capability information is used to indicate that the network element to be searched must have the ability to aggregate messages. For example, the aforementioned message aggregation capability can be understood as the ability to aggregate multiple messages received from federated learning devices into a single message.

[0238] The aforementioned second data collection capability information is used to indicate that the network element to be searched must have the ability to collect relevant data from the federated learning device. For example, the network element to be searched can collect relevant data from the federated learning device to perform federated learning on behalf of the federated learning device.

[0239] The aforementioned second area information is used to indicate the service area that the network element to be searched needs to cover. It can be understood that the network element to be searched needs to be able to proxy federated learning devices within the service area indicated by the second area information to perform federated learning.

[0240] The aforementioned second time information is used to indicate the service time that the network element to be searched needs to support. It can be understood that the network element to be searched needs to support the federated learning device to perform federated learning within the service time indicated by the second time information.

[0241] In some optional embodiments, the second capability information further includes at least one of the following:

[0242] The second federated learning task ID is used to indicate the federated learning task that the network element to be searched must support;

[0243] The second federated learning capability information is used to indicate the federated learning-related capabilities that the network element to be searched must support;

[0244] The fourth time information is used to indicate the time when the network element to be searched must support capabilities related to federated learning.

[0245] For example, the second federated learning task identifier mentioned above can also be a federated learning task type, which indicates the type of federated learning task that the network element to be searched needs to support.

[0246] For example, the above-mentioned capabilities related to federated learning may include at least one of the following: federated learning client capability, that is, the ability to participate in the federated learning process as a federated learning client; proxy federated learning client capability, that is, the ability to participate in the federated learning process on behalf of a federated learning client; and substitute federated learning client capability, that is, the ability to participate in VFL-related processes on behalf of a federated learning client.

[0247] The aforementioned fourth time information is used to indicate the time during which the network element to be searched must support the capabilities related to federated learning. This can be understood as the network element to be searched must support the aforementioned capabilities related to federated learning within the time indicated by the fourth time information.

[0248] In this embodiment, the first device carries the aforementioned capability information related to proxy federated learning in the third request message, which helps to more accurately find a suitable proxy node to proxy the federated learning device for federated learning.

[0249] Optionally, the second service information includes at least one of the following:

[0250] The second federated learning preparation service information is used to indicate that the network element to be searched must support services related to federated learning preparation;

[0251] The second federated learning and training service information is used to indicate that the network element to be searched must support services related to federated learning and training.

[0252] The second federated learning inference service information is used to indicate that the network element to be searched must support services related to federated learning inference.

[0253] In this embodiment, the aforementioned federated learning preparation may include sample alignment, feature alignment, etc. The network element to be searched must support services related to federated learning preparation. This can be understood as the network element to be searched needing to be able to proxy the federated learning device in performing the federated learning preparation process. For example, the network element to be searched needing to be able to relay service messages related to federated learning preparation from the federated learning device, or the first network element can perform federated learning preparation on behalf of the federated learning device.

[0254] The network element to be searched must support services related to federated learning training. This can be understood as the network element to be searched needing to be able to act as an agent for the federated learning device in the federated learning training process. For example, the network element to be searched needs to be able to relay service messages related to federated learning training from the federated learning device, such as transmitting service messages for sample identifiers, intermediate results, intermediate information, model update data, differences, gradient values, etc. used in federated learning training. Alternatively, the network element to be searched needs to be able to perform federated learning training on behalf of the federated learning device.

[0255] The network element to be searched must support services related to federated learning inference. This can be understood as the network element to be searched needing to be able to act as an agent for the federated learning device in the federated learning inference process. For example, the network element to be searched needs to be able to relay service messages related to federated learning inference from the federated learning device, such as service messages for data and intermediate results used in federated learning inference. Alternatively, the network element to be searched needs to be able to perform federated learning inference on behalf of the federated learning device.

[0256] In this embodiment, the first device carries the aforementioned service information related to proxy federated learning in the third request message, which helps to more accurately find a suitable proxy node to proxy the federated learning device for federated learning.

[0257] Optionally, the method further includes:

[0258] The second network element sends a second response message to the first device;

[0259] The second response message includes at least one of the following:

[0260] At least one of the identification information and address information of the target network element;

[0261] The first capability information of the target network element;

[0262] The first service information of the target network element.

[0263] The target network element mentioned above is a network element that satisfies the conditions indicated in the third request message. It is understood that the number of the target network elements can be one or more.

[0264] The identification information of the target network element may include at least one of the following: Network Element Instance ID (NF instance ID), FQDN, etc. The address information of the target network element may include the network element IP address.

[0265] The aforementioned first capability information and first service information can be found in the relevant descriptions of the foregoing embodiments, and will not be repeated here.

[0266] For example, the second response message mentioned above can be a message such as Nnrf_NFDiscovery_Request response.

[0267] Specifically, upon receiving a third request message, the second network element can determine the target network element based on the third request message. For example, the second network element can compare the information in the third request message with the network element registration information to determine at least one target network element that meets the conditions. For instance, the second network element can compare the information in the third request message indicating the need to find a proxy node with the information of the proxy node in the registration message to determine at least one target network element, and then feed back the information of the at least one target network element to the first device.

[0268] It should be noted that when the second network element fails to find a matching agent node, it can send a response message indicating that the search failed to the first device.

[0269] It should be noted that the implementation method of this method can be found in the relevant description of the embodiment shown in Figure 4, and will not be repeated here.

[0270] Please refer to Figure 6, which is a flowchart of an information interaction method provided in an embodiment of this application. The method can be executed by a first device, and as shown in Figure 6, it includes the following steps:

[0271] Step 601: The first device sends a third request message to the second network element. The third request message is used to request the search for a proxy node, and the proxy node supports proxy federated learning.

[0272] Optionally, the agent federated learning includes at least one of the following:

[0273] Relay message from the federated learning device;

[0274] Used as an alternative to federal learning equipment for federal learning.

[0275] Optionally, the third request message includes at least one of the following:

[0276] The fourth instruction is used to indicate that the network element to be searched is a proxy node;

[0277] The second capability information that the network element to be searched must possess;

[0278] The network element to be searched must support the second service information;

[0279] The second capability information is capability information related to agent federated learning, and the second service information is service information related to agent federated learning.

[0280] Optionally, the second capability information includes at least one of the following:

[0281] The fourth capability indicator is used to indicate that the network element to be searched must have the ability to relay messages from the federated learning device;

[0282] The fourth type is the type of federated learning device that the network element to be searched can relay;

[0283] The fourth identifier is the identifier of the federated learning device that the network element to be searched can relay;

[0284] The fifth capability indicator is used to indicate that the network element to be searched must have the ability to perform federated learning in place of the federated learning device;

[0285] The fifth type is the type of federated learning device that can replace the network element to be searched;

[0286] The fifth identifier is the identifier of the federated learning device that the network element to be searched can replace;

[0287] The sixth capability indicator is used to indicate that the network element to be searched must have the ability to perform federated learning on behalf of the federated learning device;

[0288] The sixth type is the type of federated learning device that the network element to be searched can proxies;

[0289] The sixth identifier is the identifier of the federated learning device that the network element to be searched can proxies;

[0290] The second data collection capability information is used to indicate that the network element to be searched must have the ability to collect relevant data from the federated learning device;

[0291] The second aggregation capability information is used to indicate that the network element to be searched must have the ability to perform message aggregation;

[0292] The second area information is used to indicate the service area that the network element to be searched needs to cover;

[0293] The second time information is used to indicate the service time that the network element to be searched needs to support.

[0294] Optionally, the second service information includes at least one of the following:

[0295] The second federated learning preparation service information is used to indicate that the network element to be searched must support services related to federated learning preparation;

[0296] The second federated learning and training service information is used to indicate that the network element to be searched must support services related to federated learning and training.

[0297] The second federated learning inference service information is used to indicate that the network element to be searched must support services related to federated learning inference.

[0298] Optionally, the method further includes:

[0299] The first device receives a second response message from the second network element;

[0300] The second response message includes at least one of the following:

[0301] At least one of the identification information and address information of the target network element;

[0302] The first capability information of the target network element;

[0303] The first service information of the target network element.

[0304] Optionally, the method further includes:

[0305] The first device sends a second request message to the target network element, the second request message being used to request information on federated learning devices that the target network element can proxies;

[0306] The first device receives a first response message from the target network element, the first response message being used to indicate a federated learning device that the target network element can proxy.

[0307] Optionally, the second request message includes information about the target federated learning device;

[0308] The first response message includes at least one of the following:

[0309] The second instruction is used to indicate whether the target network element can act as an agent for the target federated learning device to perform federated learning.

[0310] Information about the second device, wherein the second device includes at least one of the target federated learning devices that the target network element can proxies;

[0311] Information about the third device, wherein the third device is a federated learning device that the target network element can proxy, and the third device is different from the target federated learning device.

[0312] Optionally, the information of the target federated learning device includes at least one of the following: the device type of the target federated learning device, and the identifier of the target federated learning device.

[0313] Optionally, the second request message includes a third instruction, which is used to request information on each federated learning device that the target network element can proxies;

[0314] The first response message includes information about the various federated learning devices that the target network element can proxies.

[0315] It should be noted that the implementation method of this method can be found in the relevant descriptions of the embodiments shown in Figures 4 and 5, and will not be repeated here.

[0316] The embodiments of this application are illustrated below with reference to Figure 7:

[0317] It should be noted that in Figure 7, NRF represents a network storage function network element, but it can also be other network elements or devices with storage functions. NEF represents a network element exposed to the network, that is, a communication device that provides exposed core network internal services to (external) communication devices; it can also be other network elements with similar functions. VFL Server is a device with VFL Server capabilities (e.g., it can find and discover VFL Clients, trigger VFL training and inference, generate intermediate results for updating the model, determine the final inference result, etc.), such as AF. AF represents a communication device outside the core network, such as a third-party server. Agent represents a node in the core network with proxy capabilities (i.e., a proxy node), that is, a device that can directly interact with UE and RAN, and can also be a communication device with VFL-related capabilities, such as a communication device with VFL training capabilities and VFL participant capabilities.

[0318] As shown in Figure 7, the information interaction method provided in this application embodiment includes the following steps:

[0319] Step 1: The agent node sends a registration request message to the NRF. The content of the registration request message can be found in the relevant content of the first request message mentioned above, and will not be repeated here.

[0320] Step 2: NRF receives the registration request message from the agent node and saves the agent node's capability information.

[0321] Step 3: The NRF sends a response message indicating that the agent node has successfully stored its capability information.

[0322] Step 4: The VFL Server (such as AF) sends a network element lookup request message to the NRF, requesting the search for a proxy node that meets the conditions. The content of this network element lookup request message can be found in the relevant content of the aforementioned third request message, and will not be repeated here. The selection criteria mentioned above are the content carried in the aforementioned third request message.

[0323] In some optional embodiments, the VFL Server (such as AF) can send a network element lookup request message to the NRF via the NEF, see step 5.

[0324] Step 5: NEF sends a Discovery message to NRF.

[0325] Step 6: The NRF determines the information of the agent node (i.e. the target network element) that meets the feedback conditions, and sends a response message to the NEF carrying the information of the target network element being searched. The content of the response message can be found in the relevant content of the second response message mentioned above, and will not be repeated here.

[0326] Step 7: The VFL Server can send a request message or negotiation message to the agent node, or the VFL Server can send a request message or negotiation message to the agent node through NEF to request information on the federated learning devices that it can proxy. The relevant content of the request message or negotiation message can be found in the relevant content of the second request message mentioned above, and will not be repeated here.

[0327] Specifically, when a proxy node has not registered information about the federated learning devices it proxies, the VFL Server / NEF can interact with the proxy node after obtaining a qualified proxy node, that is, determine the information about the federated learning devices that the proxy node can proxies, thereby determining whether it can participate in the relevant VFL processes.

[0328] For example, after receiving the information about the proxy node from the NRF, the VFL Server / NEF can determine whether it needs to obtain information about the federated learning devices that the proxy node can proxies based on the proxy node's capability information. If so, it sends a request message to the proxy node based on the information about the proxy node from the NRF, requesting to obtain information about the federated learning devices that the proxy node can proxies.

[0329] It should be noted that steps 7-8 can occur either before NEF sends the agent node information to the VFL Server or after NEF sends the agent node information to the VFL Server.

[0330] Step 8: The proxy node sends out a response message. The content of this response message can be found in the relevant content of the first response message mentioned above, and will not be repeated here.

[0331] Step 9: NEF reports the information of the found proxy nodes to the VFL Server. The information of the proxy nodes can be anonymized device information, such as temporary network element identifiers.

[0332] The information interaction method provided in this application introduces a proxy node that helps external devices indirectly communicate with the UE and RAN for VFL procedures, enabling external devices to find the proxy node more efficiently and complete VFL training and other related processes.

[0333] It should be noted that the information interaction method provided in this application embodiment can be executed by an information interaction device. This application embodiment uses an information interaction device executing the information interaction method as an example to illustrate the information interaction device provided in this application embodiment.

[0334] This application provides an information interaction device. As an example, the information interaction device may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0335] The information interaction device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0336] Specifically, referring to Figure 8, when the information interaction device is a network-side device or a component in a network-side device, the information interaction device 800 includes a sending module 801, used to send a first request message to the second network element;

[0337] The first request message is used to request the registration of the first information of the first network element, or to request the updating of the first information of the first network element.

[0338] The first information includes at least one of the following: first capability information of the first network element, first service information of the first network element, the first capability information being capability information related to agent federated learning, and the first service information being service information related to agent federated learning.

[0339] Optionally, the agent federated learning includes at least one of the following:

[0340] Relay message from the federated learning device;

[0341] Used as an alternative to federal learning equipment for federal learning.

[0342] Optionally, the first capability information of the first network element includes at least one of the following:

[0343] The first indication is used to indicate that the first network element is a proxy node;

[0344] The first capability indicator is used to indicate that the first network element has the ability to relay messages from the federated learning device.

[0345] The first type is the type of federated learning device that the first network element can relay;

[0346] The first identifier is the identifier of the federated learning device that the first network element can relay;

[0347] The second capability indicator is used to indicate that the first network element has the capability to perform federated learning in place of the federated learning device.

[0348] The second type is the type of federated learning device that the first network element can replace;

[0349] The second identifier is the identifier of the federated learning device that the first network element can replace;

[0350] The third capability indicator is used to indicate that the first network element has the capability of proxy federated learning;

[0351] The third type is the type of federated learning device that the first network element can proxies;

[0352] The third identifier is the identifier of the federated learning device that the first network element can proxies;

[0353] The first aggregation capability information is used to indicate the first network element's ability to aggregate messages;

[0354] First data collection capability information is used to indicate that the first network element has the ability to collect relevant data from the federated learning device;

[0355] The first area information is used to indicate the service area of ​​the first network element as a proxy node;

[0356] First-time information is used to indicate the service time of the first network element as a proxy node;

[0357] The agent node supports agent federated learning.

[0358] Optionally, the first service information of the first network element includes at least one of the following:

[0359] Federated learning preparation service information, used to instruct the first network element to support services related to federated learning preparation;

[0360] Federated learning and training service information is used to instruct the first network element to support services related to federated learning and training.

[0361] Federated learning inference service information is used to instruct the first network element to support services related to federated learning inference.

[0362] Optionally, if the first network element is a target network element determined through network element lookup, the device further includes:

[0363] The receiving module is configured to receive a second request message from the first device, the second request message being used to request information on the federated learning devices that the first network element can proxies;

[0364] The sending module is further configured to send a first response message to the first device, the first response message being used to indicate information about federated learning devices that the first network element can proxies.

[0365] Optionally, the second request message includes information about the target federated learning device, which is used by the first network element to determine whether it can proxy the target federated learning device for federated learning.

[0366] The first response message includes at least one of the following:

[0367] The second instruction is used to indicate whether the first network element can act as an agent for the target federated learning device to perform federated learning.

[0368] Information about the second device, which includes at least one of the target federated learning devices that the first network element can proxies;

[0369] Information about the third device, wherein the third device is a federated learning device that the first network element can proxy, and the third device is different from the target federated learning device.

[0370] Optionally, the information of the target federated learning device includes at least one of the following: the device type of the target federated learning device, and the identifier of the target federated learning device.

[0371] Optionally, the second request message includes a third instruction, which is used to request information on the federated learning devices that the first network element can proxies;

[0372] The first response message includes information about the federated learning devices that the first network element can proxies.

[0373] The information interaction device provided in this application embodiment can implement the various processes implemented in the method embodiment of FIG4 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0374] Referring to Figure 9, when the information interaction device is a network-side device or a component in a network-side device, the information interaction device 900 includes a receiving module 901, which is used to receive a first request message from the first network element.

[0375] The first request message is used to request the registration of the first information of the first network element, or to request the updating of the first information of the first network element.

[0376] The first information includes at least one of the following: first capability information of the first network element, first service information of the first network element, the first capability information being capability information related to agent federated learning, and the first service information being service information related to agent federated learning.

[0377] Optionally, the agent federated learning includes at least one of the following:

[0378] Relay message from the federated learning device;

[0379] Used as an alternative to federal learning devices for federal learning.

[0380] Optionally, the first capability information of the first network element includes at least one of the following:

[0381] The first indication is used to indicate that the first network element is a proxy node;

[0382] The first capability indicator is used to indicate that the first network element has the ability to relay messages from the federated learning device.

[0383] The first type is the type of federated learning device that the first network element can relay;

[0384] The first identifier is the identifier of the federated learning device that the first network element can relay;

[0385] The second capability indicator is used to indicate that the first network element has the capability to perform federated learning in place of the federated learning device.

[0386] The second type is the type of federated learning device that the first network element can replace;

[0387] The second identifier is the identifier of the federated learning device that the first network element can replace;

[0388] The third capability indicator is used to indicate that the first network element has the capability of proxy federated learning;

[0389] The third type is the type of federated learning device that the first network element can proxies;

[0390] The third identifier is the identifier of the federated learning device that the first network element can proxies;

[0391] First data collection capability information is used to indicate that the first network element has the ability to collect relevant data from the federated learning device;

[0392] The first aggregation capability information is used to indicate the first network element's ability to aggregate messages;

[0393] The first area information is used to indicate the service area of ​​the first network element as a proxy node;

[0394] First-time information is used to indicate the service time of the first network element as a proxy node;

[0395] The agent node supports agent federated learning.

[0396] Optionally, the first service information of the first network element includes at least one of the following:

[0397] First Federated Learning Preparation Service Information, used to instruct the first network element to support services related to federated learning preparation;

[0398] First Federated Learning and Training Service Information, used to instruct the first network element to support services related to federated learning and training;

[0399] First federated learning inference service information is used to instruct the first network element to support services related to federated learning inference.

[0400] Optionally, the receiving module is further configured to receive a third request message from the first device, the third request message being used to request the search of a proxy node, the proxy node supporting proxy federated learning.

[0401] Optionally, the third request message includes at least one of the following:

[0402] The fourth instruction is used to indicate that the network element to be searched is a proxy node;

[0403] The second capability information that the network element to be searched must possess;

[0404] The network element to be searched must support the second service information;

[0405] The second capability information is capability information related to agent federated learning, and the second service information is service information related to agent federated learning.

[0406] Optionally, the second capability information includes at least one of the following:

[0407] The fourth capability indicator is used to indicate that the network element to be searched must have the ability to relay messages from the federated learning device;

[0408] The fourth type is the type of federated learning device that the network element to be searched can relay;

[0409] The fourth identifier is the identifier of the federated learning device that the network element to be searched can relay;

[0410] The fifth capability indicator is used to indicate that the network element to be searched must have the ability to perform federated learning in place of the federated learning device;

[0411] The fifth type is the type of federated learning device that can replace the network element to be searched;

[0412] The fifth identifier is the identifier of the federated learning device that the network element to be searched can replace;

[0413] The sixth capability indicator is used to indicate that the network element to be searched must have the ability to perform federated learning on behalf of the federated learning device;

[0414] The sixth type is the type of federated learning device that the network element to be searched can proxies;

[0415] The sixth identifier is the identifier of the federated learning device that the network element to be searched can proxies;

[0416] The second data collection capability information is used to indicate that the network element to be searched must have the ability to collect relevant data from the federated learning device;

[0417] The second aggregation capability information is used to indicate that the network element to be searched must have the ability to perform message aggregation;

[0418] The second area information is used to indicate the service area that the network element to be searched needs to cover;

[0419] The second time information is used to indicate the service time that the network element to be searched needs to support.

[0420] Optionally, the second service information includes at least one of the following:

[0421] The second federated learning preparation service information is used to indicate that the network element to be searched must support services related to federated learning preparation;

[0422] The second federated learning and training service information is used to indicate that the network element to be searched must support services related to federated learning and training.

[0423] The second federated learning inference service information is used to indicate that the network element to be searched must support services related to federated learning inference.

[0424] Optionally, the device further includes:

[0425] The sending module is used to send a second response message to the first device;

[0426] The second response message includes at least one of the following:

[0427] At least one of the identification information and address information of the target network element;

[0428] The first capability information of the target network element;

[0429] The first service information of the target network element.

[0430] The information interaction device provided in this application embodiment can implement the various processes implemented in the method embodiment of FIG5 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0431] Referring to Figure 10, when the information interaction device is a network-side device or a component of a network-side device, or a server or a component of a server, the information interaction device 1000 includes a sending module 1001, which is used to send a third request message to the second network element. The third request message is used to request the search of a proxy node, and the proxy node supports proxy federated learning.

[0432] Optionally, the agent federated learning includes at least one of the following:

[0433] Relay message from the federated learning device;

[0434] Used as an alternative to federal learning equipment for federal learning.

[0435] Optionally, the third request message includes at least one of the following:

[0436] The fourth instruction is used to indicate that the network element to be searched is a proxy node;

[0437] The second capability information that the network element to be searched must possess;

[0438] The network element to be searched must support the second service information;

[0439] The second capability information is capability information related to agent federated learning, and the second service information is service information related to agent federated learning.

[0440] Optionally, the second capability information includes at least one of the following:

[0441] The fourth capability indicator is used to indicate that the network element to be searched must have the ability to relay messages from the federated learning device;

[0442] The fourth type is the type of federated learning device that the network element to be searched can relay;

[0443] The fourth identifier is the identifier of the federated learning device that the network element to be searched can relay;

[0444] The fifth capability indicator is used to indicate that the network element to be searched must have the ability to perform federated learning in place of the federated learning device;

[0445] The fifth type is the type of federated learning device that can replace the network element to be searched;

[0446] The fifth identifier is the identifier of the federated learning device that the network element to be searched can replace;

[0447] The sixth capability indicator is used to indicate that the network element to be searched must have the ability to perform federated learning on behalf of the federated learning device;

[0448] The sixth type is the type of federated learning device that the network element to be searched can proxies;

[0449] The sixth identifier is the identifier of the federated learning device that the network element to be searched can proxies;

[0450] The second data collection capability information is used to indicate that the network element to be searched must have the ability to collect relevant data from the federated learning device;

[0451] The second aggregation capability information is used to indicate that the network element to be searched must have the ability to perform message aggregation;

[0452] The second area information is used to indicate the service area that the network element to be searched needs to cover;

[0453] The second time information is used to indicate the service time that the network element to be searched needs to support.

[0454] Optionally, the second service information includes at least one of the following:

[0455] The second federated learning preparation service information is used to indicate that the network element to be searched must support services related to federated learning preparation;

[0456] The second federated learning and training service information is used to indicate that the network element to be searched must support services related to federated learning and training.

[0457] The second federated learning inference service information is used to indicate that the network element to be searched must support services related to federated learning inference.

[0458] Optionally, the device further includes:

[0459] The receiving module is used to receive a second response message from the second network element;

[0460] The second response message includes at least one of the following:

[0461] At least one of the identification information and address information of the target network element;

[0462] The first capability information of the target network element;

[0463] The first service information of the target network element.

[0464] Optionally, the sending module is further configured to send a second request message to the target network element, the second request message being used to request information on federated learning devices that the target network element can proxies;

[0465] The device further includes a receiving module for receiving a first response message from the target network element, the first response message being a message indicating a federated learning device that the target network element can proxies.

[0466] Optionally, the second request message includes information about the target federated learning device;

[0467] The first response message includes at least one of the following:

[0468] The second instruction is used to indicate whether the target network element can act as an agent for the target federated learning device to perform federated learning.

[0469] Information about the second device, wherein the second device includes at least one of the target federated learning devices that the target network element can proxies;

[0470] Information about the third device, wherein the third device is a federated learning device that the target network element can proxy, and the third device is different from the target federated learning device.

[0471] Optionally, the information of the target federated learning device includes at least one of the following: the device type of the target federated learning device, and the identifier of the target federated learning device.

[0472] Optionally, the second request message includes a third instruction, which is used to request information on each federated learning device that the target network element can proxies;

[0473] The first response message includes information about the various federated learning devices that the target network element can proxies.

[0474] The information interaction device provided in this application embodiment can implement the various processes implemented in the method embodiment of FIG6 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0475] As shown in Figure 11, this application embodiment also provides a communication device 1100, including a processor 1101 and a memory 1102. The memory 1102 stores programs or instructions that can run on the processor 1101. For example, when the communication device 1100 is a first network element, when the program or instructions are executed by the processor 1101, they implement the various steps of the information interaction method embodiment on the first network element side described above, and achieve the same technical effect. When the communication device 1100 is a second network element, when the program or instructions are executed by the processor 1101, they implement the various steps of the information interaction method embodiment on the second network element side described above, and achieve the same technical effect. To avoid repetition, this will not be repeated here. When the communication device 1100 is a first device, when the program or instructions are executed by the processor 1101, they implement the various steps of the information interaction method embodiment on the first device side described above, and achieve the same technical effect. To avoid repetition, this will not be repeated here.

[0476] This application also provides a network-side device, including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method embodiment shown in FIG4, FIG5, or FIG6. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0477] Specifically, this application embodiment also provides a network-side device. As shown in FIG12, the network-side device 1200 includes: a processor 1201, a network interface 1202, and a memory 1203. The network-side device may be the information interaction device shown in FIG8, FIG9, or FIG10. The network interface 1202 is, for example, a Common Public Radio Interface (CPRI).

[0478] Specifically, the network-side device 1200 in this application embodiment further includes: instructions or programs stored in memory 1203 and executable on processor 1201. Processor 1201 calls the instructions or programs in memory 1203 to execute the methods executed by the modules shown in FIG8, FIG9 or FIG10 and achieve the same technical effect. To avoid repetition, it will not be described in detail here.

[0479] This application embodiment also provides a server. As shown in FIG13, the server 1300 includes a processor 1301 and a memory 1302. The memory 1302 stores a program or instructions that can run on the processor 1301. When the program or instructions are executed by the processor 1301, they perform the following steps:

[0480] A third request message is sent to the second network element. The third request message is used to request the search of a proxy node, and the proxy node supports proxy federated learning.

[0481] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of method embodiment 6 and achieve the same or corresponding technical effects. To avoid repetition, it will not be described again here.

[0482] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described information interaction method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0483] The processor mentioned above is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0484] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described information interaction method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0485] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0486] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described information interaction method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0487] This application also provides a wireless communication system, including a terminal and a network-side device. The terminal can be used to execute the steps of the information interaction method described above, and the network-side device can be used to execute the steps of the information interaction method described above.

[0488] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0489] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of computer software products plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0490] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. An information interaction method, comprising: a first network element sending a first request message to a second network element; wherein the first request message is used to request registration of first information of the first network element, or is used to request update of the first information of the first network element; the first information comprising at least one of: first capability information of the first network element, first service information of the first network element, the first capability information being capability information related to proxy federated learning, and the first service information being service information related to proxy federated learning.

2. The method of claim 1, wherein, the proxy federated learning comprising at least one of: relaying messages of a federated learning device; performing federated learning instead of the federated learning device.

3. The method of claim 1 or 2, wherein, the first capability information of the first network element comprising at least one of: a first indication indicating that the first network element is a proxy node; a first capability indication indicating that the first network element has a capability of relaying messages of a federated learning device; a first type, the first type being a type of federated learning device that can be relayed by the first network element; a first identifier, the first identifier being an identifier of a federated learning device that can be relayed by the first network element; a second capability indication indicating that the first network element has a capability of performing federated learning instead of a federated learning device; a second type, the second type being a type of federated learning device that can be replaced by the first network element; a second identifier, the second identifier being an identifier of a federated learning device that can be replaced by the first network element; a third capability indication indicating that the first network element has a capability of proxy federated learning; a third type, the third type being a type of federated learning device that can be proxied by the first network element; a third identifier, the third identifier being an identifier of a federated learning device that can be proxied by the first network element; first aggregation capability information indicating a capability of the first network element of message aggregation; first data collection capability information indicating that the first network element has a capability of collecting related data of a federated learning device; first area information indicating a service area of the first network element as a proxy node; first time information indicating a service time of the first network element as a proxy node; wherein the proxy node supports proxy federated learning.

4. The method of any one of claims 1 to 3, wherein, the first service information of the first network element comprising at least one of: federated learning preparation service information indicating that the first network element supports a service related to federated learning preparation; federated learning training service information indicating that the first network element supports a service related to federated learning training; federated learning inference service information indicating that the first network element supports a service related to federated learning inference.

5. The method of any one of claims 1 to 4, wherein, in a case where the first network element is a target network element determined through network element lookup, the method further comprising: the first network element receiving a second request message from a first device, the second request message being used to request information of a federated learning device that can be proxied by the first network element; the first network element sending a first response message to the first device, the first response message being used to indicate the information of the federated learning device that can be proxied by the first network element.

6. The method of claim 5, wherein, The second request message includes information of a target federated learning device, and the information of the target federated learning device is used by the first network element to determine whether the target federated learning device can be proxied for federated learning; The first response message includes at least one of the following: A second indication indicating whether the first network element can proxy the target federated learning device for federated learning; Information of a second device including at least one of the target federated learning devices that can be proxied by the first network element; Information of a third device, which is a federated learning device that can be proxied by the first network element and is different from the target federated learning device.

7. The method of claim 6, wherein, The information of the target federated learning device includes at least one of the following: a device type of the target federated learning device, and an identifier of the target federated learning device.

8. The method of claim 5, wherein, The second request message includes a third indication used to request information of the federated learning devices that can be proxied by the first network element; The first response message includes information of the federated learning devices that can be proxied by the first network element.

9. An information interaction method, comprising: A second network element receives a first request message from a first network element; The first request message is used to request registration of first information of the first network element, or is used to request update of the first information of the first network element; The first information includes at least one of the following: first capability information of the first network element, and first service information of the first network element, wherein the first capability information is capability information related to proxying federated learning, and the first service information is service information related to proxying federated learning.

10. The method of claim 9, wherein, The proxying federated learning includes at least one of the following: Relaying messages of federated learning devices; Substituting federated learning devices for federated learning.

11. The method of claim 9 or 10, wherein, The first capability information of the first network element includes at least one of the following: A first indication indicating that the first network element is a proxy node; A first capability indication indicating that the first network element has the capability of relaying messages of federated learning devices; A first type, which is a type of federated learning devices that can be relayed by the first network element; A first identifier, which is an identifier of federated learning devices that can be relayed by the first network element; A second capability indication indicating that the first network element has the capability of substituting federated learning devices for federated learning; A second type, which is a type of federated learning devices that can be substituted by the first network element; A second identifier, which is an identifier of federated learning devices that can be substituted by the first network element; A third capability indication indicating that the first network element has the capability of proxying federated learning; A third type, which is a type of federated learning devices that can be proxied by the first network element; A third identifier, which is an identifier of federated learning devices that can be proxied by the first network element; First data collection capability information indicating that the first network element has the capability of collecting related data of federated learning devices; First aggregation capability information indicating the capability of the first network element for message aggregation; First area information indicating a service area of the first network element as a proxy node; The first time information is used to indicate a service time of the first network element as a proxy node. The proxy node supports proxy federated learning.

12. The method of any one of claims 9-11, wherein, The first service information of the first network element includes at least one of the following: First federated learning preparation service information, used to indicate that the first network element supports a service related to federated learning preparation; First federated learning training service information, used to indicate that the first network element supports a service related to federated learning training; First federated learning inference service information, used to indicate that the first network element supports a service related to federated learning inference.

13. The method of any one of claims 9 to 12, further comprising: The second network element receives a third request message from a first device, the third request message being used to request a proxy node supporting proxy federated learning.

14. The method of claim 13, wherein, The third request message includes at least one of the following: Fourth indication, used to indicate that a required search network element is a proxy node; Second capability information required by the required search network element; Second service information required by the required search network element; The second capability information is capability information related to proxy federated learning, and the second service information is service information related to proxy federated learning.

15. The method of claim 14, wherein, The second capability information includes at least one of the following: Fourth capability indication, used to indicate that the required search network element needs to have the capability of relaying messages of federated learning devices; Fourth type, which is a type of federated learning device that can be relayed by the required search network element; Fourth identification, which is an identification of a federated learning device that can be relayed by the required search network element; Fifth capability indication, used to indicate that the required search network element needs to have the capability of replacing federated learning devices for federated learning; Fifth type, which is a type of federated learning device that can be replaced by the required search network element; Fifth identification, which is an identification of a federated learning device that can be replaced by the required search network element; Sixth capability indication, used to indicate that the required search network element needs to have the capability of proxying federated learning devices for federated learning; Sixth type, which is a type of federated learning device that can be proxied by the required search network element; Sixth identification, which is an identification of a federated learning device that can be proxied by the required search network element; Second data collection capability information, used to indicate that the required search network element needs to have the capability of collecting relevant data of federated learning devices; Second aggregation capability information, used to indicate that the required search network element needs to have the capability of message aggregation; Second area information, used to indicate a service area that needs to be covered by the required search network element; Second time information, used to indicate a service time that needs to be supported by the required search network element.

16. The method of claim 14 or 15, wherein, The second service information includes at least one of the following: Second federated learning preparation service information, used to indicate that the required search network element needs to support a service related to federated learning preparation; Second federated learning training service information, used to indicate that the required search network element needs to support a service related to federated learning training; Second federated learning inference service information, used to indicate that the required search network element needs to support a service related to federated learning inference.

17. The method of any of claims 13-16, further comprising: sending, by the second network element, a second response message to the first device; wherein the second response message comprises at least one of: at least one of identification information and address information of the target network element; first capability information of the target network element; first service information of the target network element.

18. An information interaction method, comprising: sending, by a first device, a third request message to a second network element, the third request message being used to request a proxy node, the proxy node supporting proxy federated learning.

19. The method of claim 18, wherein, The proxy federated learning comprises at least one of: relaying messages of a federated learning device; performing federated learning instead of a federated learning device.

20. The method of claim 18 or 19, wherein, The third request message comprises at least one of: a fourth indication, used to indicate that a required search network element is a proxy node; second capability information required by the required search network element; second service information required by the required search network element; wherein the second capability information is capability information related to proxy federated learning, and the second service information is service information related to proxy federated learning.

21. The method of claim 20, wherein, The second capability information comprises at least one of: a fourth capability indication, used to indicate that the required search network element needs to have the capability of relaying messages of a federated learning device; a fourth type, the fourth type being a type of a federated learning device that can be relayed by the required search network element; a fourth identification, the fourth identification being an identification of a federated learning device that can be relayed by the required search network element; a fifth capability indication, used to indicate that the required search network element needs to have the capability of performing federated learning instead of a federated learning device; a fifth type, the fifth type being a type of a federated learning device that can be replaced by the required search network element; a fifth identification, the fifth identification being an identification of a federated learning device that can be replaced by the required search network element; a sixth capability indication, used to indicate that the required search network element needs to have the capability of performing proxy federated learning; a sixth type, the sixth type being a type of a federated learning device that can be proxied by the required search network element; a sixth identification, the sixth identification being an identification of a federated learning device that can be proxied by the required search network element; second data collection capability information, used to indicate that the required search network element needs to have the capability of collecting related data of a federated learning device; second aggregation capability information, used to indicate that the required search network element needs to have the capability of message aggregation; second area information, used to indicate a service area that needs to be covered by the required search network element; second time information, used to indicate a service time that needs to be supported by the required search network element.

22. The method of claim 20 or 21, wherein, The second service information comprises at least one of: second federated learning preparation service information, used to indicate that the required search network element needs to support services related to federated learning preparation; second federated learning training service information, used to indicate that the required search network element needs to support services related to federate learning training; second federated learning inference service information, used to indicate that the required search network element needs to support services related to federat learning inference.

23. The method of any of claims 18-22, further comprising: The first device receives a second response message from the second network element; The second response message includes at least one of the following: at least one of identification information and address information of the target network element; first capability information of the target network element; first service information of the target network element.

24. The method of claim 23, further comprising: The first device sends a second request message to the target network element, the second request message being used to request information of a federated learning device that the target network element can proxy; The first device receives a first response message from the target network element, the first response message being used to indicate information of a federated learning device that the target network element can proxy.

25. The method of claim 24, wherein, The second request message includes information of a target federated learning device; The first response message includes at least one of the following: a second indication indicating whether the target network element can proxy the target federated learning device for federated learning; information of a second device, the second device including at least one of the target federated learning devices that the target network element can proxy; information of a third device, the third device being a federated learning device that the target network element can proxy, and the third device being different from the target federated learning device.

26. The method of claim 25, wherein, The information of the target federated learning device includes at least one of the following: a device type of the target federated learning device, and identification of the target federated learning device.

27. The method of claim 24, wherein, The second request message includes a third indication requesting information of each federated learning device that the target network element can proxy; The first response message includes information of each federated learning device that the target network element can proxy.

28. An information interaction apparatus, comprising: a sending module configured to send a first request message to a second network element; The first request message is used to request registration of first information of a first network element to the second network element, or is used to request update of the first information of the first network element; The first information includes at least one of the following: first capability information of the first network element, and first service information of the first network element, the first capability information being capability information related to proxying federated learning, and the first service information being service information related to proxying federated learning.

29. An information interaction apparatus, comprising: a receiving module configured to receive a first request message from a first network element; The first request message is used to request registration of first information of the first network element to a second network element, or is used to request update of the first information of the first network element. The first information includes at least one of the following: first capability information of the first network element and first service information of the first network element, the first capability information being capability information related to federated learning, and the first service information being service information related to federated learning.

30. An information interaction apparatus, comprising: a sending module configured to send a third request message to a second network element, the third request message being used to request a proxy node that supports proxying federated learning.

31. A first network element comprising a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the information interaction method according to any one of claims 1 to 8.

32. A second network element comprising a processor and a memory, the memory storing a program or instructions executable on the processer, the program or instructions, when executed by the processor, implementing the steps of the information interaction according to any one of claims 9 to 17.

33. A first device comprising a processor and a memory, the memory storing a program or instructions executable on the processor, and the program or instructions, when executed by the processor, implementing the steps of the information interaction method of any one of claims 18 to 27.

34. A readable storage medium, the readable storage medium storing a program or instructions, the program or instructions, when executed by a processor, implementing the steps of the information interaction method according to any one of claims 1 to8, or implementing the steps of the information interaction method according to any one of claims 9 to 17, or implementing the steps of the information interaction method according to any one of claims 18 to 27.

35. A computer program product, the computer program product being executed by at least one processor to implement the steps of the information interaction method according to any one of claims 1 to 8, or to implement the steps of the information interaction method according to any one of claims 9 to 17,or to implement the steps of the information interaction method according to any one of claims 18 to 27.

Images