WO2025035289A1 - 通信方法、终端设备和网络设备 - Google Patents

通信方法、终端设备和网络设备 Download PDF

Info

Publication number
WO2025035289A1
WO2025035289A1 PCT/CN2023/112649 CN2023112649W WO2025035289A1 WO 2025035289 A1 WO2025035289 A1 WO 2025035289A1 CN 2023112649 W CN2023112649 W CN 2023112649W WO 2025035289 A1 WO2025035289 A1 WO 2025035289A1
Authority
WO
WIPO (PCT)
Prior art keywords
use case
network device
feature
identifier
configuration file
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2023/112649
Other languages
English (en)
French (fr)
Inventor
陈景然
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Oppo Mobile Telecommunications Corp Ltd
Original Assignee
Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Oppo Mobile Telecommunications Corp Ltd filed Critical Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority to CN202380098383.8A priority Critical patent/CN121220015A/zh
Priority to PCT/CN2023/112649 priority patent/WO2025035289A1/zh
Publication of WO2025035289A1 publication Critical patent/WO2025035289A1/zh
Anticipated expiration legal-status Critical
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08Configuration management of networks or network elements
    • H04L41/085Retrieval of network configuration; Tracking network configuration history
    • H04L41/0853Retrieval of network configuration; Tracking network configuration history by actively collecting configuration information or by backing up configuration information

Definitions

  • the present application relates to the field of communications, and more specifically, to a communication method, a terminal device, and a network device.
  • AI artificial intelligence
  • model training requires more dimensional data from users.
  • user data is distributed in various nodes such as terminals, base stations, core networks, and third-party OTT application servers.
  • nodes such as terminals, base stations, core networks, and third-party OTT application servers.
  • the effect of the model can be improved.
  • How to collect data for the same use case from different nodes during the training or execution of machine learning models is a problem that needs to be solved.
  • the embodiments of the present application provide a communication method, a terminal device, and a network device, which can accurately collect parameters of different domains and different nodes according to different use cases and successfully perform vertical federated learning.
  • the present application provides a communication method, including:
  • the first network device sends a feature configuration file acquisition request for the first use case to the second network device, where the feature configuration file acquisition request carries a first feature identifier of the first use case;
  • the first network device receives a feature configuration file corresponding to the first feature identifier from the second network device.
  • the present application provides a communication method, including:
  • the second network device receives a feature configuration file acquisition request for the first use case, where the feature configuration file acquisition request carries a first feature identifier of the first use case;
  • the second network device sends a feature configuration file corresponding to the first feature identifier.
  • the present application provides a communication method, including:
  • the third network device receives a feature configuration file of the first use case
  • the third network device determines, based on the feature configuration file, at least one of the network device, the terminal device, and the node required to execute the first use case;
  • the third network device sends the configuration parameters in the feature configuration file to at least one of the network device, the terminal device, and the node required to execute the first use case.
  • the present application provides a communication method, including:
  • the fourth network device sends a first execution request to the first network device, where the first execution request includes a feature identifier of the first use case;
  • the fourth network device receives an execution result of the first use case from the first network device, where the execution result includes a feature identifier of the first use case.
  • the present application provides a communication method, including:
  • the terminal device receives configuration parameters in a feature configuration file of a first use case, model data required by the first use case, and a first feature identifier of the first use case;
  • the terminal device sends an execution result of the first use case, where the execution result includes a first feature identifier of the first use case.
  • the present application provides a communication method, including:
  • the core network element or the access network device receives the configuration parameters in the feature configuration file of the first use case, the model data required by the first use case, and the first feature identifier of the first use case;
  • the core network element or access network device sends the execution result of the first use case, and the execution result includes the first feature identifier of the first use case.
  • An embodiment of the present application provides a first network device, including:
  • the first transceiver unit is used to send a feature configuration file acquisition request for a first use case to a second network device, where the feature configuration file acquisition request carries a first feature identifier of the first use case; and receive a feature configuration file corresponding to the first feature identifier from the second network device.
  • An embodiment of the present application provides a second network device, including:
  • the second transceiver unit is configured to receive a feature configuration file acquisition request for a first use case, where the feature configuration file acquisition request carries a first feature identifier for the first use case; and send a feature configuration file corresponding to the first feature identifier.
  • the embodiment of the present application provides a third network device, including:
  • a third transceiver unit configured to receive a feature configuration file of the first use case
  • a first determining unit configured to determine at least one of a network device, a terminal device, and a node required to execute a first use case according to a feature configuration file;
  • the third transceiver unit is also used to send the configuration parameters in the feature configuration file to at least one of the network device, terminal device and node required to execute the first use case.
  • the embodiment of the present application provides a fourth network device, including:
  • the fourth transceiver unit is used to send a first execution request to the first network device, wherein the first execution request includes a feature identifier of the first use case; and receive an execution result of the first use case from the first network device, wherein the execution result includes the feature identifier of the first use case.
  • the present application provides a terminal device, including:
  • the fifth transceiver unit is used to receive the configuration parameters in the feature configuration file of the first use case, the model data required by the first use case, and the first feature identifier of the first use case; and send the execution result of the first use case, which includes the first feature identifier of the first use case.
  • the embodiment of the present application provides a core network element, including:
  • the sixth transceiver unit is used to receive the configuration parameters in the feature configuration file of the first use case, the model data required by the first use case, and the first feature identifier of the first use case; and send the execution result of the first use case, which includes the first feature identifier of the first use case.
  • the present application provides an access network device, including:
  • the seventh transceiver unit is used for the configuration parameters in the feature configuration file of the first use case, the model data required by the first use case, and the first feature identifier of the first use case; and sends the execution result of the first use case, which includes the first feature identifier of the first use case.
  • the embodiment of the present application also provides a communication device, including a processor, a memory and a transceiver.
  • the memory is used to store a computer program
  • the processor is used to call and run the computer program stored in the memory and control the transceiver so that the device executes the above communication method.
  • An embodiment of the present application provides a chip for implementing the above-mentioned communication method.
  • the chip includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the chip executes the above-mentioned communication method.
  • An embodiment of the present application provides a computer-readable storage medium for storing a computer program.
  • the computer program When the computer program is executed by a device, the device executes the above-mentioned communication method.
  • An embodiment of the present application provides a computer program product, including computer program instructions, which enable a computer to execute the above-mentioned communication method.
  • An embodiment of the present application provides a computer program, which, when executed on a computer, enables the computer to execute the above-mentioned communication method.
  • the first network device obtains a feature configuration file of the first use case from the second network device by utilizing the first feature identifier of the first use case; the feature configuration file can be used to determine which nodes to obtain relevant data of the first use case from, thereby realizing the collection of parameters of different domains or different nodes according to different use cases, thereby meeting the data requirements during machine learning training and/or execution.
  • FIG. 1 is a schematic diagram of an application scenario according to an embodiment of the present application.
  • FIG2 is a schematic diagram of the training process of a vertical federated learning architecture.
  • FIG3 is a schematic diagram of the inference process of a vertical federated learning architecture.
  • FIG4 is a schematic diagram of a 5G network structure.
  • FIG5 is a schematic flowchart of a communication method 500 according to an embodiment of the present application.
  • FIG6 is a schematic flowchart of a communication method 600 according to an embodiment of the present application.
  • FIG. 7 is a schematic flowchart of a communication method 700 according to an embodiment of the present application.
  • FIG8 is a schematic flowchart of a communication method 800 according to an embodiment of the present application.
  • FIG. 9 is a schematic flowchart of a communication method 900 according to an embodiment of the present application.
  • FIG. 10 is a schematic flowchart of a communication method 1000 according to an embodiment of the present application.
  • FIG. 11 is a schematic flowchart of a communication method 1100 according to an embodiment of the present application.
  • FIG. 12 is a schematic flowchart of a communication method 1200 according to an embodiment of the present application.
  • FIG13 is an implementation flow chart of the second embodiment of the present application.
  • FIG14 is an implementation flow chart of the third embodiment of the present application.
  • FIG15 is an implementation flow chart of the fourth embodiment of the present application.
  • FIG. 16 is a schematic block diagram of a first network device 1600 according to an embodiment of the present application.
  • FIG. 17 is a schematic block diagram of a first network device 1700 according to an embodiment of the present application.
  • FIG. 18 is a schematic block diagram of a second network device 1800 according to an embodiment of the present application.
  • FIG. 19 is a schematic block diagram of a second network device 1900 according to an embodiment of the present application.
  • FIG. 20 is a schematic block diagram of a third network device 2000 according to an embodiment of the present application.
  • FIG. 21 is a schematic block diagram of a fourth network device 2100 according to an embodiment of the present application.
  • FIG. 22 is a schematic block diagram of a terminal device 2200 according to an embodiment of the present application.
  • FIG. 23 is a schematic block diagram of a core network element 2300 according to an embodiment of the present application.
  • FIG. 24 is a schematic block diagram of an access network device 2400 according to an embodiment of the present application.
  • Figure 25 is a schematic block diagram of a communication device according to an embodiment of the present application.
  • FIG. 26 is a schematic block diagram of a chip according to an embodiment of the present application.
  • LTE Long Term Evolution
  • LTE-A Advanced long term evolution
  • NR New Radio
  • NR system evolution system LTE on unlicensed spectrum
  • LTE-U LTE on unlicensed spectrum
  • NR-based access to unlicensed spectrum NR-U
  • NTN Non-Terrestrial Networks
  • UMTS Universal Mobile Telecommunication System
  • WLAN Wireless Local Area Networks
  • WiFi fifth-generation communication
  • 5G fifth-generation communication
  • D2D device to device
  • M2M machine to machine
  • MTC machine type communication
  • V2V vehicle to vehicle
  • V2X vehicle to everything
  • the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) networking scenario.
  • CA carrier aggregation
  • DC dual connectivity
  • SA standalone
  • the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, wherein the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, wherein the authorized spectrum can also be considered as an unshared spectrum.
  • the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent or user device, etc.
  • UE user equipment
  • the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in the next generation communication system such as the NR network, or a terminal device in the future evolved Public Land Mobile Network (PLMN) network, etc.
  • STAION, ST in a WLAN
  • a cellular phone a cordless phone
  • Session Initiation Protocol (SIP) phone Session Initiation Protocol
  • WLL Wireless Local Loop
  • PDA Personal Digital Assistant
  • PDA Personal Digital Assistant
  • the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (for example, on airplanes, balloons and satellites, etc.).
  • the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.
  • VR virtual reality
  • AR augmented reality
  • the terminal device may also be a wearable device.
  • Wearable devices may also be referred to as wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction.
  • wearable smart devices include full-featured, large-sized, and fully or partially independent of smartphones, such as smart watches or smart glasses, as well as devices that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart bracelets and smart jewelry for vital sign monitoring.
  • the network device may be a device for communicating with a mobile device
  • the network device may be an access point (AP) in a WLAN, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network, or a network device in an NTN network, etc.
  • the network device may have a mobile feature, for example, the network device may be a mobile device.
  • the network device may be a satellite or a balloon station.
  • the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, or a satellite in a satellite orbit. Satellite, High Elliptical Orbit (HEO) satellite, etc.
  • the network device may also be a base station set up on land, water, etc.
  • a network device can provide services for a cell, and a terminal device communicates with the network device through transmission resources (e.g., frequency domain resources, or spectrum resources) used by the cell.
  • the cell can be a cell corresponding to a network device (e.g., a base station).
  • the cell can belong to a macro base station or a base station corresponding to a small cell.
  • the small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.
  • Fig. 1 exemplarily shows a communication system 100.
  • the communication system includes a network device 110 and two terminal devices 120.
  • the communication system 100 may include multiple network devices 110, and each network device 110 may include other number of terminal devices 120 within its coverage area, which is not limited in the embodiment of the present application.
  • the communication system 100 may also include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), but this is not limited to the embodiments of the present application.
  • MME Mobility Management Entity
  • AMF Access and Mobility Management Function
  • the network equipment may include access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks for communicating with the access network equipment.
  • the access network equipment may be an evolutionary base station (evolutional node B, referred to as eNB or e-NodeB) macro base station, micro base station (also called “small base station”), pico base station, access point (AP), transmission point (TP) or new generation Node B (gNodeB) in a long-term evolution (LTE) system, a next-generation (mobile communication system) (next radio, NR) system or an authorized auxiliary access long-term evolution (LAA-LTE) system.
  • eNB evolutionary base station
  • AP access point
  • TP transmission point
  • gNodeB new generation Node B
  • LTE long-term evolution
  • NR next-generation
  • LAA-LTE authorized auxiliary access long-term evolution
  • the device with communication function in the network/system in the embodiment of the present application can be called a communication device.
  • the communication device may include a network device and a terminal device with communication function, and the network device and the terminal device may be specific devices in the embodiment of the present application, which will not be repeated here; the communication device may also include other devices in the communication system, such as other network entities such as a network controller and a mobile management entity, which is not limited in the embodiment of the present application.
  • the "indication" mentioned in the embodiments of the present application can be a direct indication, an indirect indication, or an indication of an association relationship.
  • a indicates B which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association relationship between A and B.
  • corresponding may indicate a direct or indirect correspondence between two items, or an association relationship between the two items, or a relationship between indication and being indicated, configuration and being configured, and the like.
  • VFL Vertical Federated Learning
  • OTT Over the Top
  • VHL Vertical Federated Learning
  • FIG. 2 is a schematic diagram of the training process of a vertical federated learning architecture. As shown in Figure 2, the training process of the vertical federated learning model is divided into the following steps:
  • the encryption method can be homomorphic encryption, that is, homomorphic encryption of two samples m1 and m2 is equal to the homomorphic encryption of m1 plus the homomorphic encryption of m2.
  • the homomorphic encryption of sample m multiplied by a constant is equal to the homomorphic encryption of the sample multiplied by the constant.
  • the party that owns the sample label is the active party and the demander, such as participant B in the figure.
  • A is the data provider, that is, the passive party. There is no label for the sample.
  • a and B use their own local data to calculate and obtain the intermediate output results of the model.
  • A encrypts the intermediate results and sends them to B.
  • B calculates the overall output error of the model based on its own labels and the model output results of A and B. The output error is encrypted and sent to A.
  • a and B calculate their own encrypted gradients based on the output error, add masks and send them to C.
  • C decrypts the gradients sent by A and B and sends them back to A and B respectively.
  • a and B remove the masks and update their respective models based on the gradients.
  • Figure 3 is a schematic diagram of the inference process of a vertical federated learning architecture. As shown in Figure 3, the inference process of the vertical federated learning model is divided into the following steps.
  • the coordinator sends a model inference request to nodes A and B respectively, including the model ID that A and B need to adopt.
  • Nodes A and B perform calculations based on their own data and locally stored models to obtain intermediate results.
  • C aggregates the intermediate results of nodes A and B, encrypts and calculates the final model inference result, and decrypts it.
  • the inference result can be sent to B.
  • 5G network architecture One of the characteristics of 5G network architecture is service-oriented architecture, that is, core network elements (service providers) can provide specific services and make them available for other network elements (consumers) to call through defined application programming interfaces (APIs).
  • service providers core network elements
  • APIs application programming interfaces
  • FIG 4 is a schematic diagram of a 5G network structure.
  • the UE is connected to the base station at the access stratum (AS), exchanging access stratum messages and wireless data transmission.
  • the UE is connected to the mobile management function AMF at the non-access stratum (NAS), exchanging NAS messages.
  • AMF is responsible for managing the mobility of the UE
  • the session management function (SMF) is responsible for the session management of the UE.
  • SMF session management function
  • AMF is responsible for forwarding session management related messages between the UE and SMF.
  • the Policy Control Function (PCF) is responsible for formulating policies related to the mobility management, session management, and billing of the UE.
  • the User Plane Function (UPF) is connected to the base station and the external data network for data transmission.
  • the 5G network has added network elements such as the Network Data Analytics Function (NWDAF) in the core network, which can collect data from various network elements and network management systems in the core network for big data statistics, analysis or intelligent data analysis, and obtain analysis or prediction data on the network side, thereby assisting each network element to more effectively control UE access based on the data analysis results.
  • NWDAF Network Data Analytics Function
  • the domains described here may include UE, Radio Access Network (RAN), 5G Core (5G Core, 5GC), Operation Administration and Maintenance (OAM) network elements or applications, etc.
  • RAN Radio Access Network
  • 5G Core 5G Core
  • 5GC Operation Administration and Maintenance
  • FIG5 is a schematic flow chart of a communication method 500 according to an embodiment of the present application.
  • the method may optionally be applied to any system shown in FIG1-4, but is not limited thereto.
  • the method includes at least part of the following contents.
  • the first network device sends a feature configuration file acquisition request for a first use case to the second network device, where the feature configuration file acquisition request carries a first feature identifier of the first use case;
  • the first network device receives a feature configuration file corresponding to the first feature identifier from the second network device.
  • the first network device includes a network exposure function (NEF).
  • NEF network exposure function
  • the second network device includes a unified data management function (Unified Data Management, UDM) or a unified data repository function (Unified Data Repository, UDR).
  • UDM Unified Data Management
  • UDR Unified Data Repository
  • the neural network model has a variety of use cases.
  • the types of use cases that VFL has include: statistical prediction and/or prediction of user quality of experience (QoE), statistics and/or prediction of energy efficiency (EE), etc.
  • QoE user quality of experience
  • EE energy efficiency
  • the embodiment of the present application defines an identifier of the first use case, which is called a first feature identifier (feature ID) in the embodiment of the present application.
  • the first feature identifier (feature ID) can be used to distinguish different first use cases.
  • the first feature identifier of the first use case may indicate at least one of the following:
  • the type of the first use case may include at least: statistics and/or prediction of QoE, statistics and/or prediction of EE.
  • the operations used to execute the first use case may include: VFL operations.
  • the second feature identifier can be used.
  • the aforementioned first feature identifier can be considered as an internal feature identifier used within the communication network, and the second feature identifier can be used as a second feature identifier.
  • the identifier can be considered as an external feature identifier used outside the communication network. There is a mapping relationship between the first feature identifier and the second feature identifier.
  • the second feature identifier can be used to obtain the corresponding feature configuration file; after the device inside the communication network receives the second feature identifier, it determines the first feature identifier corresponding to the second feature identifier based on the mapping relationship, and then uses the first feature identifier to obtain the corresponding feature configuration file. Setting different feature identifiers to execute the first use case and using different feature identifiers inside and outside the communication network is conducive to protecting privacy and security.
  • a feature profile may also be referred to as a feature configuration, feature file, etc.
  • a feature profile is associated with a first feature identifier and may be used to describe parameters required for the feature and related operations to be performed.
  • the first network device uses the first feature identifier of the first use case to obtain a feature profile of the first use case; using the feature profile, it is possible to determine from which nodes to obtain relevant data of the first use case, thereby realizing the collection of parameters of different domains or different nodes according to different use cases, and meeting the data requirements during machine learning training and/or execution.
  • the parameters included in the feature configuration file for the first use case include at least one of the following feature parameters:
  • it may include at least one of the following:
  • the parameter type that needs to be collected can be represented by a dataset ID.
  • Model to be adopted refers to the model that nodes in each domain need to adopt in order to execute the same VFL use case.
  • Network elements and nodes that need to be called refers to the network elements involved in executing a VFL use case; for example, performing QoE statistics and/or prediction may require network elements such as SMF, PCF, NWDAF, and may require the participation of nodes such as gNB and UE.
  • the time window and area in which the AI operation is executed Refers to the time window required to execute the VFL use case and the area to which the use case is applicable. It can be represented by an Area of Interest (AOI).
  • AOI Area of Interest
  • (5)UE ID refers to the UE involved in this use case.
  • Application ID refers to the application that initiates the VFL.
  • FIG. 6 is a schematic flow chart of a communication method 600 according to an embodiment of the present application. The method can optionally be applied to any system shown in Figures 1-4, but is not limited to this.
  • the first network device may include NEF
  • the second network device may include UDM or UDR
  • the third network device may include NWDAF
  • the fourth network device may include AF.
  • the method includes at least part of the following contents.
  • the fourth network device sends a first execution request to the first network device, wherein the first execution request includes a feature identifier of the first use case.
  • the feature identifier may be a first feature identifier or a second feature identifier; if it is the first feature identifier, it means that the same identifier is used both inside and outside the communication network without distinguishing between internal and external identifiers; if it is the second feature identifier, it means that different identifiers are used both inside and outside the communication network.
  • the first execution request may include a machine learning execution request, such as a VFL execution request.
  • the first execution request also includes at least one of the following: an identifier of a terminal device involved in the first use case, an identifier of an application executing the first use case, and model data required to execute the first use case.
  • the first network device receives a first execution request, and if the first execution request includes a second feature identifier of the first use case, the first network device determines a first feature identifier corresponding to the second feature identifier. For example, the first network device determines the first feature identifier corresponding to the second feature identifier according to a pre-set mapping rule or mapping relationship.
  • the first network device sends a feature configuration file acquisition request for a first use case to the second network device, where the feature configuration file acquisition request carries a first feature identifier of the first use case.
  • the second network device internally stores a correspondence between the first feature identifier and the feature configuration file. Based on the correspondence, the second network device can determine the feature configuration file corresponding to the first feature identifier. The second network device sends the feature configuration file corresponding to the first feature identifier to the first network device.
  • the relevant contents of the feature identifier and the feature configuration file have been introduced in the above content and will not be repeated here.
  • the first network device determines at least one of a network device, a terminal device, and a node required to execute the first use case according to the feature configuration file.
  • the network device required to execute the first use case may include a core network element, such as LMF, MDAF, NWDAF, etc.
  • the first network device sends configuration parameters in the feature configuration file to at least one of the network device, the terminal device, and the node required to execute the first use case.
  • the first network device receives an execution result of the first use case from at least one of the network devices, terminal devices, and nodes required to execute the first use case, and the execution result includes a first feature identifier of the first use case.
  • the execution result may also include at least one of the following: the type of parameters that need to be collected by the first use case, the time window and/or area required by the first use case.
  • the first network device aggregates the received multiple execution results according to the first feature identifier included in each execution result. For example, the first network device can aggregate the execution results with the same first feature identifier, thereby implementing data for the same first use case.
  • the first network device sends the aggregated execution result to the fourth network device.
  • the aggregated execution result includes the first feature identifier or the second feature identifier of the first use case; the second feature identifier is determined by the first network device according to the first feature identifier. For example, the first network device determines the second feature identifier corresponding to the first feature identifier received in step S650 according to a pre-set mapping rule or mapping relationship.
  • the aggregated execution result may also include at least one of the following: the type of parameters that need to be collected by the first use case, and the time window and/or area required by the first use case.
  • FIG7 is a schematic flow chart of a communication method 700 according to an embodiment of the present application.
  • the method can optionally be applied to any system shown in FIG1-4, but is not limited thereto.
  • the method includes the following contents:
  • the second network device receives a feature configuration file acquisition request for a first use case, where the feature configuration file acquisition request carries a first feature identifier of the first use case.
  • the second network device sends a feature configuration file corresponding to the first feature identifier.
  • the second network device may receive a feature profile acquisition request from the first network device, and send the feature profile to the first network device.
  • the first network device may include an NEF.
  • the second network device When the second network device receives a request carrying the first feature identifier of the first use case from the first network device, the second network device returns the feature configuration file of the first use case to the first network device; the first network device can use the feature configuration file to determine which nodes to obtain relevant data of the first use case from, thereby realizing the collection of parameters of different domains or different nodes according to different use cases, and meeting the data requirements during machine learning training and/or execution.
  • the feature configuration file for the first use case includes at least one of the following feature parameters:
  • the identifier of the application that initiated the first use case is the identifier of the application that initiated the first use case.
  • the type of parameter is represented by a dataset ID.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following:
  • the type of the first use case may include at least one of the following: statistics and/or prediction of QoE; statistics and/or prediction of EE.
  • the operation adopted in executing the first use case may include: VFL operation.
  • the second network device saves a feature configuration file corresponding to the first feature identifier. Based on the pre-saved information, after receiving the feature configuration file acquisition request, the second network device can search for the feature configuration file corresponding to the first feature identifier based on the first feature identifier of the first use case carried in the feature configuration file acquisition request, and feed back the feature configuration file.
  • execution steps of the second network device may refer to the relevant contents of the second network device in the example of FIG. 6 , which will not be described in detail here.
  • FIG8 is a schematic flow chart of a communication method 800 according to an embodiment of the present application.
  • the method can optionally be applied to any system shown in FIG1-4, but is not limited thereto.
  • the method includes the following contents:
  • the fourth network device sends a first execution request to the first network device, where the first execution request includes a feature identifier of the first use case;
  • the fourth network device receives an execution result of the first use case from the first network device, where the execution result includes a feature identifier of the first use case.
  • the fourth network device By setting a feature identifier for the first use case, and the fourth network device obtaining the execution result of the first use case based on the feature identifier of the first use case, the parameters of the first use case in different domains or different nodes can be obtained to meet the data requirements during machine learning training and/or execution.
  • the first network device may include a NEF.
  • the first execution request further includes at least one of the following:
  • the parameter type is represented by the dataset ID.
  • the first use case may include a VFL use case.
  • the feature identifier of the first use case may be a first feature identifier or a second feature identifier.
  • the specific content of the first feature identifier or the second feature identifier may refer to the aforementioned related content, which will not be repeated here.
  • the feature identifier indicates at least one of the following:
  • the type of the first use case may include at least one of the following: statistics and/or prediction of user experience quality QoE; statistics and/or prediction of energy efficiency EE.
  • the operation adopted in executing the first use case may include: VFL operation.
  • FIG. 9 is a schematic flow chart of a communication method 900 according to an embodiment of the present application. The method can optionally be applied to any system shown in Figures 1-4, but is not limited to this.
  • the first network device may include NEF
  • the second network device may include UDM or UDR
  • the third network device may include NWDAF
  • the fourth network device may include AF
  • the fifth network device may include ADRF.
  • the method includes at least part of the following contents.
  • the third network device receives a feature configuration file of the first use case.
  • the third network device can receive the feature profile of the first use case or the configuration parameters contained in the feature profile from the first network device; specifically, the first network device can send the feature profile or the configuration parameters contained in the feature profile to the third network device after receiving the first execution request.
  • the third network device may send a feature profile acquisition request for the first use case to the second network device, wherein the feature profile acquisition request carries the first feature identifier of the first use case; the third network device receives the feature profile of the first use case (that is, the feature profile corresponding to the first feature identifier) from the second network device.
  • the third network device determines the required model data according to the feature configuration file, and sends a model acquisition request to the fifth network device, wherein the model acquisition request carries the model ID.
  • the fifth network device may store model data of multiple models in advance.
  • the third network device receives model data of the model from the fifth network device.
  • the third network device determines the network devices, terminal devices and/or nodes required to execute the first use case based on the feature configuration file, and sends the configuration parameters, model parameters and other information in the feature configuration file to the network devices, terminal devices and/or nodes required to execute the first use case.
  • the network device, terminal device and/or node required to execute the first use case executes the first use case based on the received configuration parameters and model parameters and other information, and feeds back the execution result of the first use case to the third network device, respectively.
  • the execution result may also include the first feature identifier of the first use case.
  • the execution result may also include at least one of the following: the type of parameters required to be collected by the first use case; the time window and/or area required by the first use case.
  • the third network device aggregates the received multiple execution results according to the first feature identifier included in the execution result. If the data aggregation is initiated by the third network device, the current process ends. If the data aggregation is initiated by the first network device, step S970 is continued.
  • the third network device sends the aggregated execution result to the first network device.
  • FIG10 is a schematic flow chart of a communication method 1000 according to an embodiment of the present application.
  • the method can optionally be applied to any system shown in FIG1-4, but is not limited thereto.
  • the method includes the following contents:
  • the third network device receives a feature configuration file of the first use case
  • the third network device determines, according to the feature configuration file, at least one of the network device, the terminal device, and the node required to execute the first use case;
  • the third network device sends configuration parameters in the feature configuration file to at least one of the network device, the terminal device, and the node required to execute the first use case.
  • the third network device determines each node executing the first use case, so as to obtain relevant data of the first use case from each node, realize the collection of parameters of the first use case in different domains or different nodes, and meet the requirements of machine learning training and and/or the need for data during execution.
  • the third network device further includes acquiring model data required for the first use case from the fifth network device according to the feature configuration file of the first use case;
  • the third network device sends the model data required by the first use case to at least one of the network device, the terminal device, and the node required to execute the first use case.
  • the fifth network device may include ADRF.
  • the third network device receives an execution result of the first use case from at least one of a network device, a terminal device, and a node required to execute the first use case, wherein the execution result includes a first feature identifier of the first use case;
  • the third network device aggregates the received multiple execution results according to the first feature identifier included in the execution result.
  • the execution result may also include at least one of the following:
  • the time window and/or region required by the first use case are the time window and/or region required by the first use case.
  • the third network device may send the aggregated execution result to the first network device.
  • the first network device may include an NEF.
  • the feature configuration file for the first use case includes at least one of the following feature parameters:
  • the identifier of the application that initiated the first use case is the identifier of the application that initiated the first use case.
  • the type of parameter can be represented by the dataset ID.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following: a type of the first use case; an operation adopted to execute the first use case.
  • the type of the first use case includes at least one of: statistics and/or prediction of QoE; statistics and/or prediction of EE.
  • the operation adopted in executing the first use case may include: VFL operation.
  • execution steps of the second network device may refer to the relevant contents of the third network device in the examples of FIG. 6 and FIG. 9 , which will not be described in detail here.
  • FIG. 11 is a schematic flow chart of a communication method 1100 according to an embodiment of the present application.
  • the method can optionally be applied to any system shown in Figures 1-4, but is not limited thereto.
  • the method includes the following contents:
  • the terminal device receives configuration parameters in a feature configuration file of a first use case, model data required by the first use case, and a first feature identifier of the first use case;
  • the terminal device sends an execution result of the first use case, where the execution result includes a first feature identifier of the first use case.
  • the terminal device executes the first use case, by including the first feature identifier of the first use case in the execution result of the first use case, the execution result of the first use case can be marked with a corresponding identifier, so that the device receiving the execution result can collect parameters belonging to the same first use case according to the first feature identifier, thereby meeting the data requirements during machine learning training and/or execution.
  • the execution result further includes at least one of the following:
  • the time window and/or region required by the first use case are the time window and/or region required by the first use case.
  • the type of the parameter is represented by a data set identifier.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following: a type of the first use case; an operation adopted to execute the first use case.
  • the type of the first use case includes at least one of: statistics and/or prediction of QoE; statistics and/or prediction of EE.
  • the operations employed to perform the first use case include: VFL operations.
  • FIG. 12 is a schematic flow chart of a communication method 1200 according to an embodiment of the present application.
  • the method can optionally be applied to any system shown in Figures 1-4, but is not limited thereto.
  • the method includes the following contents:
  • a core network element or an access network device receives configuration parameters in a feature configuration file of a first use case, model data required by the first use case, and a first feature identifier of the first use case;
  • the core network element or access network device sends an execution result of the first use case, where the execution result includes a first feature identifier of the first use case.
  • the core network network element or access network device can mark the execution result of the first use case with a corresponding identifier by including the first feature identifier of the first use case in the execution result of the first use case, so that the device receiving the execution result can collect parameters belonging to the same first use case according to the first feature identifier, thereby meeting the data requirements during machine learning training and/or execution.
  • the execution result further includes at least one of the following:
  • the time window and/or region required by the first use case are the time window and/or region required by the first use case.
  • the type of the parameter is represented by a data set identifier.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following: a type of the first use case; an operation adopted to execute the first use case.
  • the type of the first use case includes at least one of: statistics and/or prediction of QoE; statistics and/or prediction of EE.
  • the operations employed to perform the first use case include: VFL operations.
  • the other execution steps of the terminal device can refer to the relevant content of the network equipment or nodes required to execute the first use case in the examples of Figures 6 and 9, which will not be repeated here.
  • the first network device is specifically NEF
  • the second network device is specifically UDM or UDR
  • the third network device is specifically NWDAF
  • the fourth network device AF is specifically ADRF.
  • the aforementioned network devices may also be other functional network elements.
  • the first use case is specifically a VFL use case for example. In other embodiments of the present application, the first use case may also be other use cases.
  • Embodiment 1 is a diagrammatic representation of Embodiment 1:
  • VFL has various use cases, such as QoE statistics and/or prediction, EE statistics and/or prediction, etc.
  • this embodiment defines a new ID, namely feature ID, to distinguish different use cases.
  • the information that feature ID can reflect is as follows:
  • Execution use cases such as QoE prediction statistics, energy efficiency statistics, etc.
  • a third party When a third party requests the communication network to perform related operations through a feature ID, there may also be a mapping relationship between the external feature ID and the internal feature ID.
  • the embodiment of the present application also defines a feature profile associated with the feature ID to describe the parameters required for the feature and the related operations to be performed.
  • the parameters included in the feature profile are as follows:
  • the parameter type that needs to be collected can be represented by the dataset ID.
  • Model to be adopted refers to the model that nodes in each domain need to adopt in order to execute the same VFL use case.
  • Network elements and nodes that need to be called In order to execute a VFL use case, the network elements involved, such as QoE, may require SMF, PCF, NWDAF and other network elements. And the participation of nodes such as gNB and UE may be required.
  • the time window and area for executing the AI operation Refers to the time window required to execute the VFL use case and the area to which the use case applies. It can be represented by AOI.
  • Embodiment 2 is a diagrammatic representation of Embodiment 1:
  • the VFL execution request is initiated by the AF, and the model required for executing the VFL is directly sent by the AF.
  • FIG13 is a flowchart of the implementation of the second embodiment of the present application, including the following steps:
  • Step 1 When a third-party AF requests to execute a VFL use case, the AF sends a VFL execution request to the NEF.
  • the VFL execution request contains a second feature identifier (or external feature ID), which indicates the VFL use case that the AF requests to execute.
  • the second feature identifier indicates that the type of the VFL use case is statistics and/or prediction of QoE.
  • the VFL execution request may also include a UE identifier (UE ID), an application identifier (Application ID), and model data required to execute the VFL use case; wherein the UE identifier indicates the UE involved in executing the VFL use case, and the application identifier indicates the application corresponding to the execution of the VFL use case.
  • Step 2 NEF maps the second feature identifier to the first feature identifier (or internal feature ID) used within the communication network based on the UE identifier, application identifier and other information.
  • Step 3 After receiving the request, NEF sends a request to obtain a feature profile to the Unified Data Repository (UDR) according to the first feature identifier.
  • UDR Unified Data Repository
  • Step 4 The UDR returns a pre-stored feature profile corresponding to the first feature identifier. For details of the parameters included in the configuration file, see Example 1.
  • Step 5 The NEF determines at least one of the network element, RAN and UE that needs to interact according to the received feature configuration file.
  • Step 6 NEF sends the configuration parameters in the feature configuration file to at least one of the determined network element, RAN and UE, mainly including the first feature identifier, the model data required to execute the VFL use case, the parameter type that needs to be collected as the model input, the time window for executing the AI operation (including training and/or reasoning), the area information where the UE and/or RAN executes the VFL use case, and the service area information of each network element when executing the VFL use case.
  • the configuration parameters in the feature configuration file to at least one of the determined network element, RAN and UE, mainly including the first feature identifier, the model data required to execute the VFL use case, the parameter type that needs to be collected as the model input, the time window for executing the AI operation (including training and/or reasoning), the area information where the UE and/or RAN executes the VFL use case, and the service area information of each network element when executing the VFL use case.
  • Step 7 Each node (including at least one of the network element, RAN, and UE) sends the result of the AI operation to the NEF.
  • the result includes the first feature identifier, result information, parameter type (represented by dataset ID), time of executing the AI operation, regional information, etc.
  • dataset ID is used to indicate the form of the data set used by each node when performing AI operations locally, such as distribution characteristics, sampling characteristics, or sample dimensions, etc.
  • Step 8 NEF determines that the results returned by each node belong to the same VFL operation based on the first feature identifier in the information collected by each node. NEF can aggregate information with the same first feature identifier. In addition, NEF maps the first feature identifier to the second feature identifier.
  • Step 9 replies the result of the AI operation to AF.
  • the message includes the result information or aggregated result information, parameter type (indicated by dataset ID), time of executing the AI operation, area information, second feature identifier, etc.
  • VFL execution request is initiated by AF, and the model required to execute VFL is pre-stored in the Analytic Data Repository Function (ADRF).
  • ADRF Analytic Data Repository Function
  • the AF does not directly provide model data, but the model is stored in the ADRF of the core network in advance.
  • the relevant VFL has been executed before, or the AF and the core network element have negotiated before requesting to execute the operation, and the model is pre-stored in the ADRF.
  • FIG. 14 is a flowchart of the implementation of the third embodiment of the present application, including the following steps:
  • Step 1 When a third-party AF requests to execute a VFL use case, the AF sends a VFL execution request to the NEF.
  • the VFL execution request contains a second feature identifier (or external feature ID), which indicates the VFL use case that the AF requests to execute.
  • the second feature identifier indicates that the type of the VFL use case is statistics and/or prediction of QoE.
  • the VFL execution request may also include a UE identifier (UE ID) and an application identifier (Application ID); wherein the UE identifier indicates the UE involved in executing the VFL use case, and the application identifier indicates the application corresponding to the execution of the VFL use case.
  • Step 2 NEF maps the second feature identifier to the first feature identifier (or internal feature ID) used within the communication network based on the UE identifier, application identifier and other information.
  • Step 3 After receiving the request, NEF sends a request to obtain a feature profile to the Unified Data Repository (UDR) according to the first feature identifier.
  • UDR Unified Data Repository
  • Step 4 The UDR returns the pre-stored feature profile corresponding to the first feature identifier.
  • the parameters included in the feature profile are detailed in Example 1.
  • Step 5 NEF determines the NWDAF that can interact with ADRF based on the received feature profile.
  • Step 6 NEF sends the first feature identifier and the corresponding feature configuration file to NWDAF.
  • Step 7 NWDAF interacts with ADRF according to the instructions of the required model in the feature configuration file to obtain the required model. Specifically, NWDAF can send a model acquisition message to ADRF, and the message includes the model ID to be obtained.
  • Step 8 ADRF returns the data of the model that meets the requirements to NWDAF.
  • NWDAF sends the configuration parameters in the feature configuration file to at least one of the corresponding network element, RAN and UE, mainly including the first feature identifier, the model data required to execute the VFL use case, the parameter type that needs to be collected as the model input, the time window for executing the AI operation (including training and/or reasoning), the area information where the UE and/or RAN executes the VFL use case, and the service area information of each network element when executing the VFL use case.
  • Step 10 Each node (including at least one of the network element, RAN, and UE) sends the result of the AI operation to the NWDAF.
  • the result includes the first feature identifier, result information, parameter type (indicated by dataset ID), time of executing the AI operation, regional information, etc.
  • the dataset ID is used to indicate the form of the data set used by each node when performing the AI operation locally, such as distribution characteristics, sampling characteristics, or sample dimensions, etc.
  • Step 11 NWDAF determines, based on the first feature identifier in the information collected by each node, that the results returned by each node belong to the same VFL operation. NWDAF can aggregate information with the same first feature identifier.
  • Step 12 NWDAF sends the aggregated result to NEF.
  • Step 13 NEF maps the first feature identifier to a second feature identifier.
  • Step 14 NEF replies the result of the AI operation to AF.
  • the message includes the result information or the aggregated result information, parameter type (indicated by dataset ID), the time when the AI operation was executed, area information, the second feature identifier, etc.
  • Embodiment 4 is a diagrammatic representation of Embodiment 4:
  • the VFL process is initiated by NWDAF.
  • the VFL operation is initiated by a network element of the core network, such as NWDAF, so the participation of NEF and the mapping of feature identifiers are not required.
  • NWDAF network element of the core network
  • FIG. 15 is a flowchart of an implementation of the fourth embodiment of the present application, comprising the following steps:
  • Step 1 When NWDAF requests to execute VFL, NWDAF sends a request to obtain a feature configuration file to UDR, where the feature configuration file includes a first feature identifier.
  • Step 2 The UDR returns a pre-stored feature profile corresponding to the first feature identifier to the NWDAF. For details of the parameters included in the feature profile, see Example 1.
  • Step 3 NWDAF determines the model to be adopted according to the indication of the required model contained in the feature configuration file.
  • Step 4 NWDAF interacts with ADRF to obtain the required model. Specifically, NWDAF may send a model acquisition message to ADRF, where the message includes the model ID to be obtained.
  • Step 5 ADRF returns the data of the model that meets the requirements to NWDAF.
  • Step 6 NWDAF sends the configuration parameters in the feature configuration file to at least one of the corresponding network element, RAN and UE, mainly including the first feature identifier, the model data required to execute the VFL use case, the parameter type that needs to be collected as the model input, the time window for executing the AI operation (including training and/or reasoning), the area information where the UE and/or RAN executes the VFL use case, and the service area information when each network element executes the VFL use case.
  • the AI operation including training and/or reasoning
  • Step 7 Each node (including at least one of the network element, RAN, and UE) sends the result of the AI operation to the NWDAF.
  • the result includes the first feature identifier, result information, parameter type (indicated by dataset ID), time of executing the AI operation, regional information, etc.
  • dataset ID is used to indicate the form of the data set used by each node when performing AI operations locally, such as distribution characteristics, sampling characteristics, or sample dimensions, etc.
  • Step 8 NWDAF determines, based on the first feature identifier in the information collected by each node, that the results returned by each node belong to the same VFL operation. NWDAF can aggregate information with the same first feature identifier.
  • This technical solution introduces how to use feature representation and call related feature configuration files when executing multi-domain VFL, so that the execution node can know which network elements, RAN, UE and other information to obtain to successfully perform VFL operations.
  • This solution provides specific execution processes in two different scenarios: third-party initiated VFL and core network element initiated NWDAF, and realizes the support of VFL by the communication system, which can meet the needs of use cases such as QoE statistics and/or prediction, EE statistics and/or prediction, etc.
  • FIG16 is a schematic block diagram of a first network device 1600 according to an embodiment of the present application.
  • the first network device 1600 may include:
  • the first transceiver unit 1610 is configured to send a feature configuration file acquisition request for a first use case to a second network device, where the feature configuration file acquisition request carries a first feature identifier for the first use case; and receive a feature configuration file corresponding to the first feature identifier from the second network device.
  • the feature configuration file for the first use case includes at least one of the following feature parameters:
  • the identifier of the application that initiated the first use case is the identifier of the application that initiated the first use case.
  • the type of the parameter is represented by a data set identifier.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following:
  • the type of the first use case includes at least one of the following:
  • the operations adopted by the first use case include: VFL operations.
  • the first transceiver unit 1610 is further configured to receive a first execution request from a fourth network device, where the first execution request includes a feature identifier of the first use case.
  • the first execution request further includes at least one of the following:
  • the feature identifier of the first use case includes a first feature identifier of the first use case.
  • the feature identifier of the first use case includes a second feature identifier of the first use case.
  • FIG17 is a schematic block diagram of a first network device 1700 according to an embodiment of the present application.
  • the first network device 1700 may further include:
  • the first processing unit 1720 is configured to determine the first feature identifier corresponding to the second feature identifier.
  • the first processing unit 1720 is further configured to determine, based on the feature configuration file, at least one of a network device, a terminal device, and a node required to perform the first use case;
  • the first transceiver unit 1610 is further used to send configuration parameters in the feature configuration file to at least one of the network device, terminal device and node required to execute the first use case.
  • the first transceiver unit 1610 is further used to receive an execution result of the first use case from at least one of a network device, a terminal device, and a node required to execute the first use case, wherein the execution result includes a first feature identifier of the first use case.
  • the execution result further includes at least one of the following:
  • the time window and/or region required by the first use case are the time window and/or region required by the first use case.
  • the first processing unit 1720 is further configured to aggregate the received multiple execution results according to the first feature identifier included in the execution results.
  • the first transceiver unit 1610 is further configured to send the aggregated execution result to a fourth network device.
  • the aggregated execution result includes the first feature identifier or the second feature identifier of the first use case
  • the second characteristic identifier is determined by the first network device according to the first characteristic identifier.
  • the aggregated execution result further includes at least one of the following:
  • the time window and/or region required by the first use case are the time window and/or region required by the first use case.
  • the first network device includes a NEF.
  • the second network device includes a UDM or a UDR.
  • the fourth network device includes an AF.
  • the network equipment required to perform the first use case includes a core network element.
  • the core network element includes LMF, MDAF or NWDAF.
  • the first network devices 1600 and 1700 of the embodiment of the present application can implement the corresponding functions of the first network devices in the aforementioned method embodiment.
  • the processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the first network devices 1600 and 1700 can be found in the corresponding descriptions in the above method embodiments, which will not be repeated here.
  • the functions described by the various modules (sub-modules, units or components, etc.) in the first network devices 1600 and 1700 of the embodiment of the application can be implemented by different modules (sub-modules, units or components, etc.), or by the same module (sub-module, unit or component, etc.).
  • FIG18 is a schematic block diagram of a second network device 1800 according to an embodiment of the present application.
  • the second network device 1800 may include:
  • the second transceiver unit 1810 is configured to receive a feature configuration file acquisition request for a first use case, where the feature configuration file acquisition request carries a first feature identifier for the first use case; and send a feature configuration file corresponding to the first feature identifier.
  • the feature configuration file for the first use case includes at least one of the following feature parameters:
  • the identifier of the application that initiated the first use case is the identifier of the application that initiated the first use case.
  • the type of the parameter is represented by a data set identifier.
  • FIG19 is a schematic block diagram of a second network device 1900 according to an embodiment of the present application.
  • the second network device 1900 may include:
  • the second processing unit 1920 is configured to save a feature configuration file corresponding to the first feature identifier.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following:
  • the type of the first use case includes at least one of the following:
  • the operations employed to perform the first use case include: VFL operations.
  • the second network device includes a UDM or a UDR.
  • the second network devices 1800 and 1900 of the embodiment of the present application can implement the corresponding functions of the second network devices in the aforementioned method embodiment.
  • the processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the second network devices 1800 and 1900 can be found in the corresponding descriptions in the above method embodiments, which will not be repeated here.
  • the functions described by the various modules (sub-modules, units or components, etc.) in the second network devices 1800 and 1900 of the embodiment of the application can be implemented by different modules (sub-modules, units or components, etc.), or by the same module (sub-module, unit or component, etc.).
  • FIG20 is a schematic block diagram of a third network device 2000 according to an embodiment of the present application.
  • the third network device 2000 may include:
  • the third transceiver unit 2010 is used to receive a feature configuration file of the first use case
  • the third processing unit 220 is used to determine at least one of the network device, the terminal device and the node required to perform the first use case according to the feature configuration file;
  • the third transceiver unit 2010 is also used to send the configuration parameters in the feature configuration file to at least one of the network device, terminal device and node required to execute the first use case.
  • the second processing unit 220 is further configured to obtain model data required for the first use case from the fifth network device according to the feature configuration file of the first use case;
  • the third transceiver unit 2010 is also used to send the model data required for the first use case to at least one of the network device, terminal device and node required to execute the first use case.
  • the third transceiver unit 2010 is further configured to receive an execution result of the first use case from at least one of a network device, a terminal device, and a node required to execute the first use case, wherein the execution result includes a first feature identifier of the first use case;
  • the third processing unit 2020 is further configured to aggregate the received multiple execution results according to the first feature identifier included in the execution results.
  • the execution result further includes at least one of the following:
  • the time window and/or region required by the first use case are the time window and/or region required by the first use case.
  • the third transceiver unit 2010 is further configured to send the aggregated execution result to the first network device.
  • the feature configuration file for the first use case includes at least one of the following feature parameters:
  • the identifier of the application that initiated the first use case is the identifier of the application that initiated the first use case.
  • the type of the parameter is represented by a data set identifier.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following:
  • the type of the first use case includes at least one of the following:
  • the operations employed to perform the first use case include: VFL operations.
  • the third network device includes a NWDAF.
  • the fifth network device includes an ADRF.
  • the first network device includes a NEF.
  • the third network device 2000 of the embodiment of the present application can implement the corresponding functions of the third network device in the aforementioned method embodiment.
  • the processes, functions, implementation methods and beneficial effects corresponding to each module (sub-module, unit or component, etc.) in the third network device 2000 can be found in the corresponding description in the above method embodiment, which will not be repeated here.
  • the functions described by each module (sub-module, unit or component, etc.) in the third network device 2000 of the embodiment of the application can be implemented by different modules (sub-module, unit or component, etc.), or by the same module (sub-module, unit or component, etc.).
  • FIG21 is a schematic block diagram of a fourth network device 2100 according to an embodiment of the present application.
  • the fourth network device 2100 may include:
  • the fourth transceiver unit 2110 is used to send a first execution request to the first network device, wherein the first execution request includes a feature identifier of the first use case; and receive an execution result of the first use case from the first network device, wherein the execution result includes the feature identifier of the first use case.
  • the first execution request further includes at least one of the following:
  • the type of the parameter is represented by a data set identifier.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following:
  • the type of the first use case includes at least one of the following:
  • the operations employed to perform the first use case include: VFL operations.
  • the fourth network device 2100 of the embodiment of the present application can implement the corresponding functions of the fourth network device in the aforementioned method embodiment.
  • the processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the fourth network device 2100 can be found in the corresponding descriptions in the above method embodiments, which will not be repeated here.
  • the functions described by the various modules (sub-modules, units or components, etc.) in the fourth network device 2100 of the application embodiment can be implemented by different modules (sub-modules, units or components, etc.), or by the same module (sub-module, unit or component, etc.).
  • FIG22 is a schematic block diagram of a terminal device 2200 according to an embodiment of the present application.
  • the terminal device 2200 may include:
  • the fifth transceiver unit 2210 is used to receive the configuration parameters in the feature configuration file of the first use case, the model data required by the first use case, and the first feature identifier of the first use case; and send the execution result of the first use case, which includes the first feature identifier of the first use case.
  • the execution result further includes at least one of the following:
  • the time window and/or region required by the first use case are the time window and/or region required by the first use case.
  • the type of the parameter is represented by a data set identifier.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following:
  • the type of the first use case includes at least one of the following:
  • the operations employed to perform the first use case include: VFL operations.
  • the terminal device 2200 of the embodiment of the present application can implement the corresponding functions of the terminal device in the aforementioned method embodiment.
  • the processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the terminal device 2200 can be found in the corresponding descriptions in the above method embodiments, which will not be repeated here.
  • the functions described by the various modules (sub-modules, units or components, etc.) in the terminal device 2200 of the embodiment of the application can be implemented by different modules (sub-modules, units or components, etc.), or by the same module (sub-module, unit or component, etc.).
  • FIG23 is a schematic block diagram of a core network element 2300 according to an embodiment of the present application.
  • the core network element 2300 may include:
  • the sixth transceiver unit 2310 is used to receive the configuration parameters in the feature configuration file of the first use case, the model data required by the first use case, and the first feature identifier of the first use case; and send the execution result of the first use case, which includes the first feature identifier of the first use case.
  • the execution result further includes at least one of the following:
  • the time window and/or region required by the first use case are the time window and/or region required by the first use case.
  • the type of the parameter is represented by a data set identifier.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following:
  • the type of the first use case includes at least one of the following:
  • the operations employed to perform the first use case include: VFL operations.
  • the core network element 2300 of the embodiment of the present application can implement the corresponding functions of the core network element in the aforementioned method embodiment.
  • the processes, functions, implementation methods and beneficial effects corresponding to each module (sub-module, unit or component, etc.) in the core network element 2300 can be found in the corresponding description in the above method embodiment, which will not be repeated here.
  • the functions described by each module (sub-module, unit or component, etc.) in the core network element 2300 of the embodiment of the application can be implemented by different modules (sub-module, unit or component, etc.), or by the same module (sub-module, unit or component, etc.).
  • FIG24 is a schematic block diagram of an access network device 2400 according to an embodiment of the present application.
  • the access network device 2400 may include:
  • the seventh transceiver unit 2410 is used to receive the configuration parameters in the feature configuration file of the first use case, the model data required by the first use case, and the first feature identifier of the first use case; and send the execution result of the first use case, which includes the first feature identifier of the first use case.
  • the execution result further includes at least one of the following:
  • the time window and/or region required by the first use case are the time window and/or region required by the first use case.
  • the type of the parameter is represented by a data set identifier.
  • the first use case includes a VFL use case.
  • the first feature identifier indicates at least one of the following:
  • the type of the first use case includes at least one of the following:
  • the operations employed to perform the first use case include: VFL operations.
  • Fig. 25 is a schematic structural diagram of a communication device 2500 according to an embodiment of the present application.
  • the communication device 2500 includes a processor 2510, and the processor 2510 can call and run a computer program from a memory to enable the communication device 2500 to implement the method in the embodiment of the present application.
  • the communication device 2500 may further include a memory 2520.
  • the processor 2510 may call and run a computer program from the memory 2520 to enable the communication device 2500 to implement the method in the embodiment of the present application.
  • the memory 2520 may be a separate device independent of the processor 2510 , or may be integrated into the processor 2510 .
  • the communication device 2500 may further include a transceiver 2530, and the processor 2510 may control the transceiver 2530 to communicate with other devices, specifically, may send information or data to other devices, or receive information or data sent by other devices.
  • the transceiver 2530 may include a transmitter and a receiver.
  • the transceiver 2530 may further include an antenna, and the number of antennas may be one or more.
  • the communication device 2500 may be a network device of an embodiment of the present application, and the communication device 2500 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.
  • the communication device 2500 may be a terminal device of an embodiment of the present application, and the communication device 2500 may implement the corresponding processes implemented by the terminal device in each method of the embodiment of the present application, which will not be described again for the sake of brevity.
  • the communication device 2500 may be a core network network element of an embodiment of the present application, and the communication device 2500 may implement the corresponding processes implemented by the core network network element in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.
  • the communication device 2500 may be an access network device of an embodiment of the present application, and the communication device 2500 may implement the corresponding processes implemented by the access network device in each method of the embodiment of the present application, which will not be described again here for the sake of brevity.
  • Fig. 26 is a schematic structural diagram of a chip 2600 according to an embodiment of the present application.
  • the chip 2600 includes a processor 2610, and the processor 2610 can call and run a computer program from a memory to implement the method in the embodiment of the present application.
  • the chip 2600 may further include a memory 2620.
  • the processor 2610 may call and run a computer program from the memory 2620 to implement the method executed by the terminal device or the network device or the core network element or the access network device in the embodiment of the present application.
  • the memory 2620 may be a separate device independent of the processor 2610 , or may be integrated into the processor 2610 .
  • the chip 2600 may further include an input interface 2630.
  • the processor 2610 may control the input
  • the interface 2630 communicates with other devices or chips, and specifically, can obtain information or data sent by other devices or chips.
  • the chip 2600 may further include an output interface 2640.
  • the processor 2610 may control the output interface 2640 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.
  • the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application, which will not be described in detail here for the sake of brevity.
  • the chip can be applied to the terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
  • the chips used in network equipment, terminal equipment, core network elements and access network equipment can be the same chip or different chips.
  • the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
  • the processor mentioned above may be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC) or other programmable logic devices, transistor logic devices, discrete hardware components, etc.
  • DSP digital signal processor
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • the general-purpose processor mentioned above may be a microprocessor or any conventional processor, etc.
  • the memory mentioned above may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories.
  • the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM) or a flash memory.
  • the volatile memory may be a random access memory (RAM).
  • the memory in the embodiment of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is to say, the memory in the embodiment of the present application is intended to include but not limited to these and any other suitable types of memory.
  • the computer program product includes one or more computer instructions.
  • the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
  • the computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.
  • the computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated.
  • the available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.
  • the size of the serial numbers of the above-mentioned processes does not mean the order of execution.
  • the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请涉及一种通信方法、终端设备和网络设备,其中,通信方法包括:第一网络设备向第二网络设备发送第一用例的特征配置文件获取请求,特征配置文件获取请求中携带第一用例的第一特征标识;第一网络设备从第二网络设备接收第一特征标识对应的特征配置文件。在本申请实施例中,可以准确的根据不同的用例收集不同域或不同节点的参数。

Description

通信方法、终端设备和网络设备 技术领域
本申请涉及通信领域,更具体地,涉及一种通信方法、终端设备和网络设备。
背景技术
为了生成更符合用户需求的人工智能(artificial intelligence,AI)模型,模型的训练需要用户更多维度的数据。而用户的数据分布在终端、基站、核心网和第三方OTT应用服务器等各个节点。通过从各节点收集针对同一用例的参数,并采用收集的参数进行模型训练,能够提升模型的效果。如何实现机器学习模型在训练或执行过程中,从不同节点收集同一用例的数据,是需要解决的问题。
发明内容
本申请实施例提供一种通信方法、终端设备和网络设备,可以准确的根据不同的用例,收集不同域,不同节点的参数,成功的执行纵向联邦学习。
本申请实施例提供一种通信方法,包括:
第一网络设备向第二网络设备发送第一用例的特征配置文件获取请求,特征配置文件获取请求中携带第一用例的第一特征标识;
第一网络设备从第二网络设备接收第一特征标识对应的特征配置文件。
本申请实施例提供一种通信方法,包括:
第二网络设备接收第一用例的特征配置文件获取请求,特征配置文件获取请求中携带第一用例的第一特征标识;
第二网络设备发送第一特征标识对应的特征配置文件。
本申请实施例提供一种通信方法,包括:
第三网络设备接收第一用例的特征配置文件;
第三网络设备根据特征配置文件,确定执行第一用例所需的网络设备、终端设备和节点中的至少之一;
第三网络设备向执行第一用例所需的网络设备、终端设备和节点中的至少之一发送特征配置文件中的配置参数。
本申请实施例提供一种通信方法,包括:
第四网络设备向第一网络设备发送第一执行请求,第一执行请求中包含第一用例的特征标识;
第四网络设备从第一网络设备接收第一用例的执行结果,执行结果中包含第一用例的特征标识。
本申请实施例提供一种通信方法,包括:
终端设备接收第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;
终端设备发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
本申请实施例提供一种通信方法,包括:
核心网网元或接入网设备接收第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;
核心网网元或接入网设备发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
本申请实施例提供一种第一网络设备,包括:
第一收发单元,用于向第二网络设备发送第一用例的特征配置文件获取请求,特征配置文件获取请求中携带第一用例的第一特征标识;从第二网络设备接收第一特征标识对应的特征配置文件。
本申请实施例提供一种第二网络设备,包括:
第二收发单元,用于接收第一用例的特征配置文件获取请求,特征配置文件获取请求中携带第一用例的第一特征标识;发送第一特征标识对应的特征配置文件。
本申请实施例提供一种第三网络设备,包括:
第三收发单元,用于接收第一用例的特征配置文件;
第一确定单元,用于根据特征配置文件,确定执行第一用例所需的网络设备、终端设备和节点中的至少之一;
第三收发单元还用于向执行第一用例所需的网络设备、终端设备和节点中的至少之一发送特征配置文件中的配置参数。
本申请实施例提供一种第四网络设备,包括:
第四收发单元,用于向第一网络设备发送第一执行请求,第一执行请求中包含第一用例的特征标识;从第一网络设备接收第一用例的执行结果,执行结果中包含第一用例的特征标识。
本申请实施例提供一种终端设备,包括:
第五收发单元,用于接收第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
本申请实施例提供一种核心网网元,包括:
第六收发单元,用于接收第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
本申请实施例提供一种接入网设备,包括:
第七收发单元,用于第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
本申请实施例还提供一种通信设备,包括处理器、存储器和收发器。该存储器用于存储计算机程序,该处理器用于调用并运行该存储器中存储的计算机程序、并控制该收发器,以使该设备执行上述的通信方法。
本申请实施例提供一种芯片,用于实现上述的通信方法。
具体地,芯片包括:处理器,用于从存储器中调用并运行计算机程序,使得安装有芯片的设备执行上述的通信方法。
本申请实施例提供一种计算机可读存储介质,用于存储计算机程序,当计算机程序被设备运行时使得设备执行上述的通信方法。
本申请实施例提供一种计算机程序产品,包括计算机程序指令,计算机程序指令使得计算机执行上述的通信方法。
本申请实施例提供一种计算机程序,当其在计算机上运行时,使得计算机执行上述的通信方法。
本申请实施例中,第一网络设备通过利用第一用例的第一特征标识,从第二网络设备获取第一用例的特征配置文件;利用该特征配置文件能够确定从哪些节点获取第一用例的相关数据,从而实现了根据不同的用例收集不同域或不同节点的参数,满足机器学习训练和/或执行过程中对数据的需求。
附图说明
图1是根据本申请实施例的应用场景的示意图。
图2是一种纵向联邦学习的架构的训练过程示意图。
图3是一种纵向联邦学习的架构的推断过程示意图。
图4是一种5G网络结构示意图。
图5是根据本申请一实施例的通信方法500的示意性流程图。
图6是根据本申请一实施例的通信方法600的示意性流程图。
图7是根据本申请一实施例的通信方法700的示意性流程图。
图8是根据本申请一实施例的通信方法800的示意性流程图。
图9是根据本申请一实施例的通信方法900的示意性流程图。
图10是根据本申请一实施例的通信方法1000的示意性流程图。
图11是根据本申请一实施例的通信方法1100的示意性流程图。
图12是根据本申请一实施例的通信方法1200的示意性流程图。
图13是本申请实施例二的实现流程图。
图14是本申请实施例三的实现流程图。
图15是本申请实施例四的实现流程图。
图16是根据本申请一实施例的第一网络设备1600的示意性框图。
图17是根据本申请一实施例的第一网络设备1700的示意性框图。
图18是根据本申请一实施例的第二网络设备1800的示意性框图。
图19是根据本申请一实施例的第二网络设备1900的示意性框图。
图20是根据本申请一实施例的第三网络设备2000的示意性框图。
图21是根据本申请一实施例的第四网络设备2100的示意性框图。
图22是根据本申请一实施例的终端设备2200的示意性框图。
图23是根据本申请一实施例的核心网网元2300的示意性框图。
图24是根据本申请一实施例的接入网设备2400的示意性框图。
图25是根据本申请实施例的通信设备示意性框图。
图26是根据本申请实施例的芯片的示意性框图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行描述。
本申请实施例的技术方案可以应用于各种通信系统,例如:长期演进(Long Term Evolution,LTE)系统、先进的长期演进(Advanced long term evolution,LTE-A)系统、新无线(New Radio,NR)系统、NR系统的演进系统、非授权频谱上的LTE(LTE-based access to unlicensed spectrum,LTE-U)系统、非授权频谱上的NR(NR-based access to unlicensed spectrum,NR-U)系统、非地面通信网络(Non-Terrestrial Networks,NTN)系统、通用移动通信系统(Universal Mobile Telecommunication System,UMTS)、无线局域网(Wireless Local Area Networks,WLAN)、无线保真(Wireless Fidelity,WiFi)、第五代通信(5th-Generation,5G)系统或其他通信系统等。
通常来说,传统的通信系统支持的连接数有限,也易于实现,然而,随着通信技术的发展,移动通信系统将不仅支持传统的通信,还将支持例如,设备到设备(Device to Device,D2D)通信,机器到机器(Machine to Machine,M2M)通信,机器类型通信(Machine Type Communication,MTC),车辆间(Vehicle to Vehicle,V2V)通信,或车联网(Vehicle to everything,V2X)通信等,本申请实施例也可以应用于这些通信系统。
在一种实施方式中,本申请实施例中的通信系统可以应用于载波聚合(Carrier Aggregation,CA)场景,也可以应用于双连接(Dual Connectivity,DC)场景,还可以应用于独立(Standalone,SA)布网场景。
在一种实施方式中,本申请实施例中的通信系统可以应用于非授权频谱,其中,非授权频谱也可以认为是共享频谱;或者,本申请实施例中的通信系统也可以应用于授权频谱,其中,授权频谱也可以认为是非共享频谱。
本申请实施例结合网络设备和终端设备描述了各个实施例,其中,终端设备也可以称为用户设备(User Equipment,UE)、接入终端、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、终端、无线通信设备、用户代理或用户装置等。
终端设备可以是WLAN中的站点(STAION,ST),可以是蜂窝电话、无绳电话、会话启动协议(Session Initiation Protocol,SIP)电话、无线本地环路(Wireless Local Loop,WLL)站、个人数字处理(Personal Digital Assistant,PDA)设备、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、可穿戴设备、下一代通信系统例如NR网络中的终端设备,或者未来演进的公共陆地移动网络(Public Land Mobile Network,PLMN)网络中的终端设备等。
在本申请实施例中,终端设备可以部署在陆地上,包括室内或室外、手持、穿戴或车载;也可以部署在水面上(如轮船等);还可以部署在空中(例如飞机、气球和卫星上等)。
在本申请实施例中,终端设备可以是手机(Mobile Phone)、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(Virtual Reality,VR)终端设备、增强现实(Augmented Reality,AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self driving)中的无线终端设备、远程医疗(remote medical)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全(transportation safety)中的无线终端设备、智慧城市(smart city)中的无线终端设备或智慧家庭(smart home)中的无线终端设备等。
作为示例而非限定,在本申请实施例中,该终端设备还可以是可穿戴设备。可穿戴设备也可以称为穿戴式智能设备,是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称,如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上,或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备,更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能,例如:智能手表或智能眼镜等,以及只专注于某一类应用功能,需要和其它设备如智能手机配合使用,如各类进行体征监测的智能手环、智能首饰等。
在本申请实施例中,网络设备可以是用于与移动设备通信的设备,网络设备可以是WLAN中的接入点(Access Point,AP),可以是LTE中的演进型基站(Evolutional Node B,eNB或eNodeB),或者中继站或接入点,或者车载设备、可穿戴设备以及NR网络中的网络设备(gNB)或者未来演进的PLMN网络中的网络设备或者NTN网络中的网络设备等。
作为示例而非限定,在本申请实施例中,网络设备可以具有移动特性,例如网络设备可以为移动的设备。可选地,网络设备可以为卫星、气球站。例如,卫星可以为低地球轨道(low earth orbit,LEO)卫星、中地球轨道(medium earth orbit,MEO)卫星、地球同步轨道(geostationary earth orbit,GEO) 卫星、高椭圆轨道(High Elliptical Orbit,HEO)卫星等。可选地,网络设备还可以为设置在陆地、水域等位置的基站。
在本申请实施例中,网络设备可以为小区提供服务,终端设备通过该小区使用的传输资源(例如,频域资源,或者说,频谱资源)与网络设备进行通信,该小区可以是网络设备(例如基站)对应的小区,小区可以属于宏基站,也可以属于小小区(Small cell)对应的基站,这里的小小区可以包括:城市小区(Metro cell)、微小区(Micro cell)、微微小区(Pico cell)、毫微微小区(Femto cell)等,这些小小区具有覆盖范围小、发射功率低的特点,适用于提供高速率的数据传输服务。
图1示例性地示出了一种通信系统100。该通信系统包括一个网络设备110和两个终端设备120。在一种实施方式中,该通信系统100可以包括多个网络设备110,并且每个网络设备110的覆盖范围内可以包括其它数量的终端设备120,本申请实施例对此不做限定。
在一种实施方式中,该通信系统100还可以包括移动性管理实体(Mobility Management Entity,MME)、接入与移动性管理功能(Access and Mobility Management Function,AMF)等其他网络实体,本申请实施例对此不作限定。
其中,网络设备又可以包括接入网设备和核心网设备。即无线通信系统还包括用于与接入网设备进行通信的多个核心网。接入网设备可以是长期演进(long-term evolution,LTE)系统、下一代(移动通信系统)(next radio,NR)系统或者授权辅助接入长期演进(authorized auxiliary access long-term evolution,LAA-LTE)系统中的演进型基站(evolutional node B,简称可以为eNB或e-NodeB)宏基站、微基站(也称为“小基站”)、微微基站、接入站点(access point,AP)、传输站点(transmission point,TP)或新一代基站(new generation Node B,gNodeB)等。
应理解,本申请实施例中网络/系统中具有通信功能的设备可称为通信设备。以图1示出的通信系统为例,通信设备可包括具有通信功能的网络设备和终端设备,网络设备和终端设备可以为本申请实施例中的具体设备,此处不再赘述;通信设备还可包括通信系统中的其他设备,例如网络控制器、移动管理实体等其他网络实体,本申请实施例中对此不做限定。
应理解,本文中术语“系统”和“网络”在本文中常被可互换使用。本文中术语“和/或”,仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。
应理解,在本申请的实施例中提到的“指示”可以是直接指示,也可以是间接指示,还可以是表示具有关联关系。举例说明,A指示B,可以表示A直接指示B,例如B可以通过A获取;也可以表示A间接指示B,例如A指示C,B可以通过C获取;还可以表示A和B之间具有关联关系。
在本申请实施例的描述中,术语“对应”可表示两者之间具有直接对应或间接对应的关系,也可以表示两者之间具有关联关系,也可以是指示与被指示、配置与被配置等关系。
为便于理解本申请实施例的技术方案,以下对本申请实施例的相关技术进行说明,以下相关技术作为可选方案与本申请实施例的技术方案可以进行任意结合,其均属于本申请实施例的保护范围。
一、纵向联邦学习(Vertical Federated Learning,VFL):
为了生成更符合用户需求的AI模型,模型的训练需要用户更多维度的数据。而用户的数据分布在终端、基站、核心网和第三方(Over the Top,OTT)应用服务器等各个节点,OTT(Over the Top)是指利用运营商的网络、而服务由运营商之外的第三方提供的服务业务。如果可以通过联合各节点上针对同一机器学习用例的不同参数,并采用该参数进行模型训练,将会极大的提升模型的效果,对模型的训练有着重要的意义。但是,多节点的多域数据共享,将会对数据隐私带来极大的挑战。纵向联邦学习(VHL,Vertical Federated Learning)就是在满足数据隐私、安全和监管需求的前提下,使人工智能系统可以高效、准确地使用多节点的本地数据,在保证隐私安全的前提下,打破数据孤岛,实现跨域的多节点数据共享技术。
图2是一种纵向联邦学习的架构的训练过程示意图。如图2所示,纵向联邦学习模型的训练过程分为以下几步:
1、加密样本对齐。纵向联邦学习适用于参与者训练样本标识(identification,ID)重叠较多,而数据特征重叠较少的情况,例如,某个区域UE在通信系统的不同节点产生的不同特征数据。因此,需要对参与者的样本进行对齐,在不增加样本ID的情况下,增加每个样本的特征维度。
2、对齐的样本进行模型加密训练。其步骤如下。
2.1、如右侧图所示,由第三方协调者C向A和B发送公钥,用来加密需要传输的数据。加密方式可以采用同态加密,即对两个样本m1、m2进行同态加密,等于m1的同态加密加上m2的同态加密。样本m和一个常数相乘的同态加密,等于对这个样本同态加密再乘以常数。
2.2、拥有样本标签的一方为主动方和需求方,如图中的参与方B。A为数据提供方,即被动方, 不具有样本的标签。A和B分别利用自己本地数据进行计算,得到模型的中间输出结果,A将中间结果加密后发送给B,B根据自身标签,和A,B的模型输出结果,计算得到模型整体的输出误差。将输出误差加密发送给A。
2.3、A和B分别根据输出误差,计算各自加密后的梯度并添加掩码发送给C。
2.4、C解密A和B发送的梯度后分别回传给A和B,A和B去除掩码后根据梯度更新各自的模型。
图3是一种纵向联邦学习的架构的推断过程示意图。如图3所示,纵向联邦学习模型的推断过程分为以下几步。
1.协调者分别向节点A和B发送模型推断请求,包括指示A和B需要采用的模型ID。
2.节点A和B根据自身数据和本地存储的模型,进行计算,得出中间结果。
3.A和B对中间结果加密,传输给协调者C。
4.C聚合A,B节点的中间结果,加密计算得到最后的模型推断结果,并解密。推理结果可以发送给B。
二、第五代移动通信技术(5th Generation Mobile Communication Technology,5G)网络架构:
5G网络架构中的一个特征是服务化架构,即核心网网元(服务提供者)可以提供特定的服务,并通过定义好的应用程序编程接口(Application Programming Interface,API)供其他网元(消费者)调用。
图4是一种5G网络结构示意图。如图4所示,UE与基站进行接入层(access stratum,AS)连接,交互接入层消息及无线数据传输,UE与移动管理功能AMF进行非接入层(Non-access stratum,NAS)连接,交互NAS消息。AMF负责对UE移动性的管理,会话管理功能(Session Management Function,SMF)负责对UE的会话管理,AMF在对移动终端进行移动性管理之外,还负责将从会话管理相关消息在UE和SMF之间的转发。策略控制功能(Policy Control Function,PCF)负责制定对UE的移动性管理、会话管理、计费等相关的策略。用户面功能(User Plane Function,UPF)与基站及外部数据网络相连进行数据传输。
此外,5G网络还在核心网中增加了网络数据分析功能(Network Data Analytics Function,NWDAF)等网元,可以从核心网各个网元、网管系统等处收集数据进行大数据统计、分析或者智能化的数据分析,得出网络侧的分析或者预测数据,从而辅助各个网元根据数据分析结果对UE接入进行更有效的控制。
相关技术中,网络架构支持跨域的纵向联邦学习中存在多个使用场景,例如通过收集不同域的参数来统计、预测或确定更精确的用户体验质量(Quality of Experience,QoE)。或者通过收集不同域的参数来分析、统计或预测整个通信系统的能量效率(Energy Efficiency,EE),从而实现能效的提升。这些机器学习用例均需要收集多个域内的不同数据,因此,如何保证神经网络模型(如纵向联邦学习)在训练或推测的过程中,可以准确地收集对应同一机器学习用例、并且分布在不同域或不同节点的数据,从而成功地执行神经网络模块的训练或推测,如执行纵向联邦学习,是需要解决的问题。此处所述的域可以包括UE,无线接入网(Radio Access Network,RAN),5G核心网(5G Core,5GC)、操作管理维护(Operation Administration and Maintenance,OAM)网元或应用(Application)等。
图5是根据本申请一实施例的通信方法500的示意性流程图。该方法可选地可以应用于图1-4中任一所示的系统,但并不仅限于此。该方法包括以下内容的至少部分内容。
S510、第一网络设备向第二网络设备发送第一用例的特征配置文件获取请求,该特征配置文件获取请求中携带该第一用例的第一特征标识;
S520、第一网络设备从该第二网络设备接收该第一特征标识对应的特征配置文件。
在一些实施方式中,第一网络设备包括网络开放功能(Network Exposure Function,NEF)。
在一些实施方式中,第二网络设备包括统一数据管理功能(Unified Data Management,UDM)或统一数据仓库功能(Unified Data Repository,UDR)。
神经网络模型具有多样化的用例,以VFL为例,VFL具有的用例的类型包括:用户体验质量(QoE)的统计预测和/或预测,能量效率(EE)的统计和/或预测等等。为了能使通信网络可以准确地识别出不同的第一用例,从而进行不同的操作,本申请实施例定义一个第一用例的标识,在本申请实施例中称为第一特征标识(feature ID),第一特征标识(feature ID)可以用来区分不同的第一用例。
第一用例的第一特征标识可以指示以下至少之一:
(1)该第一用例的类型;
(2)执行该第一用例采用的操作。
其中,第一用例的类型可以至少包括:QoE的统计和/或预测、EE的统计和/或预测。
执行该第一用例采用的操作可以包括:VFL操作。
当第三方设备,如应用功能(Application Function,AF)网元通过请求通信网络执行相关的操作时,可以采用第二特征标识。前述的第一特征标识可以认为是通信网络内部使用的内部特征标识,第二特征 标识可以认为是通信网络外部使用的外部特征标识。第一特征标识和第二特征标识之间存在映射关系。当通信网络外部的设备,如AF请求通信网络执行相关操作时,可以采第二特征标识获取对应的特征配置文件;通信网络内部的设备接收到该第二特征标识之后,根据该映射关系,确定与该第二特征标识对应的第一特征标识,再采用第一特征标识获取对应的特征配置文件。为执行该第一用例设置不同的特征标识,并且通信网络内部和外部使用不同的特征标识,有利于保护隐私安全。
特征配置文件(feature Profile)也可以称为特征配置、特征文件等。特征配置文件(feature Profile)与第一特征标识相关联的,可以用来描述该特征所需要的参数和需要执行的相关操作等。第一网络设备利用第一用例的第一特征标识,获取该第一用例的特征配置文件;利用该特征配置文件能够确定从哪些节点获取第一用例的相关数据,从而实现了根据不同的用例收集不同域或不同节点的参数,满足机器学习训练和/或执行过程中对数据的需求。
在一些实施方式中,第一用例的特征配置文件中包括的参数包括以下特征参数中的至少之一:
(1)该第一用例需要收集的参数的类型;
(2)该第一用例需要采用的模型;
(3)该第一用例需要调用的网元和/或节点;
(4)该第一用例需要的时间窗和/或区域;
(5)该第一用例所涉及的终端设备的标识;
(6)发起该第一用例的应用的标识。
具体地,可以包括以下至少之一:
(1)执行该用例,需要收集的参数类型,该参数的类型可以用数据集标识(dataset ID)表示。
(2)需要采用的模型:指各个域的节点为了执行同一个VFL用例,需要采用的模型。
(3)需要调用的网元、节点:指为了执行一个VFL用例,所涉及的网元;例如执行QoE的统计和/或预测可能需要SMF,PCF,NWDAF等网元,以及可能需要gNB和UE等节点的参加。
(4)该AI操作执行的时间窗、区域等。指执行该VFL用例所需的时间窗,以及该用例所适用的区域。可以采用感兴趣区域(Area of Interest,AOI)表示。
(5)UE ID:指该用例所涉及的UE。
(6)Application ID;指发起该VFL的应用。
本申请实施例涉及的通信方法涉及多个设备,以下介绍多个设备的功能及设备间的交互过程。图6是根据本申请一实施例的通信方法600的示意性流程图。该方法可选地可以应用于图1-4中任一所示的系统,但并不仅限于此。在图6所示的示例中,第一网络设备可以包括NEF、第二网络设备可以包括UDM或UDR、第三网络设备可以包括NWDAF、第四网络设备可以包括AF。
如图6所示,该方法包括以下内容的至少部分内容。
S610、第四网络设备向第一网络设备发送第一执行请求,该第一执行请求中包含第一用例的特征标识。其中,特征标识可以为第一特征标识或第二特征标识;如果是第一特征标识,则说明通信网络内部和外部均使用同样的标识,而不划分内部标识和外部标识;如果是第二特征标识,则说明通信网络内部和外部均使用不同的标识。
该第一执行请求可以包括机器学习执行请求,如VFL执行请求。
该第一执行请求中还包含以下至少之一:该第一用例所涉及的终端设备的标识、执行该第一用例的应用的标识、执行该第一用例所需的模型数据。
S620、第一网络设备接收第一执行请求,如果该第一执行请求中包含第一用例的第二特征标识,则第一网络设备确定该第二特征标识对应的第一特征标识。例如,第一网络设备根据预先设定的映射规则或映射关系,确定该第二特征标识对应的第一特征标识。
第一网络设备向第二网络设备发送第一用例的特征配置文件获取请求,该特征配置文件获取请求中携带第一用例的第一特征标识。
S630、第二网络设备内部预先保存与第一特征标识与特征配置文件的对应关系。根据该对应关系,第二网络设备可以确定该第一特征标识对应的特征配置文件。第二网络设备向第一网络设备发送该第一特征标识对应的特征配置文件。特征标识和特征配置文件的相关内容在上述内容中已有介绍,在此不再赘述。
S640、第一网络设备根据该特征配置文件,确定执行该第一用例所需的网络设备、终端设备和节点中的至少之一。执行该第一用例所需的网络设备可以包括核心网网元,如LMF、MDAF、NWDAF等。
第一网络设备向执行该第一用例所需的网络设备、终端设备和节点中的至少之一发送特征配置文件中的配置参数。
S650、第一网络设备从执行该第一用例所需的网络设备、终端设备和节点中的至少之一接收该第一用例的执行结果,该执行结果中包含该第一用例的第一特征标识。执行结果中还可以包含以下至少之一:该第一用例需要收集的参数的类型、该第一用例需要的时间窗和/或区域。第一网络设备根据各个执行结果中包含的第一特征标识,将接收的多个执行结果进行聚合。例如,第一网络设备可以将具有相同第一特征标识的执行结果聚合在一起,从而实现对同一第一用例的数据的。
S660、第一网络设备将聚合后的执行结果发送至第四网络设备。
其中,聚合后的执行结果中包含第一用例的第一特征标识或第二特征标识;该第二特征标识由第一网络设备根据第一特征标识确定。例如,第一网络设备根据预先设定的映射规则或映射关系,确定步骤S650中接收到的第一特征标识所对应的第二特征标识。
聚合后的执行结果中还可以包含以下至少之一:该第一用例需要收集的参数的类型、该第一用例需要的时间窗和/或区域。
本申请还提出一种通信方法,该通信方法可以由第二网络设备执行,该第二网络设备可以包括UDM或UDR。图7是根据本申请一实施例的通信方法700的示意性流程图。该方法可选地可以应用于图1-4中任一所示的系统,但并不仅限于此。该方法包括以下内容:
S710、第二网络设备接收第一用例的特征配置文件获取请求,特征配置文件获取请求中携带第一用例的第一特征标识;
S720、第二网络设备发送第一特征标识对应的特征配置文件。
在一些实施方式中,第二网络设备可以从第一网络设备接收特征配置文件获取请求,并向第一网络设备发送特征配置文件。第一网络设备可以包括NEF。
第二网络设备在从第一网络设备接收到携带第一用例的第一特征标识的请求时,将该第一用例的特征配置文件返回至第一网络设备;第一网络设备可以利用该特征配置文件确定从哪些节点获取第一用例的相关数据,从而实现了根据不同的用例收集不同域或不同节点的参数,满足机器学习训练和/或执行过程中对数据的需求。
在一些实施方式中,第一用例的特征配置文件中包含以下特征参数中的至少之一:
第一用例需要收集的参数的类型;
第一用例需要采用的模型;
第一用例需要调用的网元和/或节点;
第一用例需要的时间窗和/或区域;
第一用例所涉及的终端设备的标识;
发起第一用例的应用的标识。
在一些实施方式中,参数的类型采用数据集标识(dataset ID)表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:
第一用例的类型;
执行第一用例采用的操作。
其中,第一用例的类型可以包括以下至少之一:QoE的统计和/或预测;EE的统计和/或预测。
其中,执行第一用例采用的操作可以包括:VFL操作。
在一些实施方式中,第二网络设备保存第一特征标识对应的特征配置文件。根据预先保存的前述信息,第二网络设备接收到特征配置文件获取请求后,可以基于该特征配置文件获取请求中携带的第一用例的第一特征标识,查找该第一特征标识对应的特征配置文件,并反馈该特征配置文件。
第二网络设备的其它执行步骤可以参照图6示例中第二网络设备的相关内容,在此不再赘述。
本申请还提出一种通信方法,该通信方法可以由第四网络设备执行,该第四网络设备可以包括AF。图8是根据本申请一实施例的通信方法800的示意性流程图。该方法可选地可以应用于图1-4中任一所示的系统,但并不仅限于此。该方法包括以下内容:
S810、第四网络设备向第一网络设备发送第一执行请求,第一执行请求中包含第一用例的特征标识;
S820、第四网络设备从第一网络设备接收第一用例的执行结果,执行结果中包含第一用例的特征标识。
通过为第一用例设置特征标识,并且第四网络设备基于第一用例的特征标识获取第一用例的执行结果,能够获取第一用例在不同域或不同节点的参数,满足机器学习训练和/或执行过程中对数据的需求。
其中,第一网络设备可以包括NEF。
在一些实施方式中,第一执行请求中还包含以下至少之一:
第一用例所涉及的终端设备的标识;
执行第一用例的应用的标识;
执行第一用例所需的模型数据。
其中,参数的类型采用数据集标识(dataset ID)表示。
在一些实施方式中,第一用例可以包括VFL用例。
在一些实施方式中,第一用例的特征标识可以为第一特征标识或第二特征标识。第一特征标识或第二特征标识的具体内容可以参见前述相关内容,在此不再赘述。
在一些实施方式中,特征标识指示以下至少之一:
第一用例的类型;
执行第一用例采用的操作。
其中,第一用例的类型可以包括以下至少之一:用户体验质量QoE的统计和/或预测;能量效率EE的统计和/或预测。
其中,执行第一用例采用的操作可以包括:VFL操作。
第四网络设备的其它执行步骤可以参照图6示例中第四网络设备的相关内容,在此不再赘述。
本申请实施例还提出另一种通信方法,该通信方法涉及多个设备,以下介绍多个设备的功能及设备间的交互过程。图9是根据本申请一实施例的通信方法900的示意性流程图。该方法可选地可以应用于图1-4中任一所示的系统,但并不仅限于此。在图9所示的示例中,第一网络设备可以包括NEF、第二网络设备可以包括UDM或UDR、第三网络设备可以包括NWDAF、第四网络设备可以包括AF、第五网络设备可以包括ADRF。
如图9所示,该方法包括以下内容的至少部分内容。
S910、第三网络设备接收第一用例的特征配置文件。
例如,如果数据聚合是由第一网络设备发起的,则第三网络设备可以从第一网络设备接收第一用例的特征配置文件或特征配置文件中包含的配置参数;具体地,第一网络设备可以在接收到第一执行请求后,向该第三网络设备发送特征配置文件或特征配置文件中包含的配置参数。
又如,如果数据聚合是由第三网络设备发起的,则第三网络设备可以向第二网络设备发送第一用例的特征配置文件获取请求,该特征配置文件获取请求中携带第一用例的第一特征标识;第三网络设备从第二网络设备接收该第一用例的特征配置文件(也就是该第一特征标识对应的特征配置文件)。
第一特征标识和特征配置文件的相关内容在前述内容中已有介绍,在此不再赘述。
S920、第三网络设备根据该特征配置文件确定需要的模型数据,向第五网络设备发送模型获取请求,该模型获取请求中携带该模型ID。第五网络设备中可以预先保存多个模型的模型数据。
S930、第三网络设备从第五网络设备接收该模型的模型数据。
S940、第三网络设备根据特征配置文件,确定执行该第一用例所需的网络设备、终端设备和/或节点,并向执行该第一用例所需的网络设备、终端设备和/或节点发送特征配置文件中的配置参数、模型参数等信息。
S950、执行该第一用例所需的网络设备、终端设备和/或节点基于接收到的配置参数和模型参数等信息,执行该第一用例,并将该第一用例的执行结果分别反馈至第三网络设备,该执行结果中还可以包含该第一用例的第一特征标识。该执行结果中还可以包含以下至少之一:第一用例需要收集的参数的类型;第一用例需要的时间窗和/或区域。
S960、第三网络设备根据执行结果中包含的第一特征标识,将接收的多个执行结果进行聚合。如果数据聚合是由第三网络设备发起的,则结束当前流程。如果数据聚合是由第一网络设备发起的,则继续执行步骤S970。
S970、第三网络设备将聚合后的执行结果发送至第一网络设备。
本申请还提出一种通信方法,该通信方法可以由第三网络设备执行,该第三网络设备可以包括NWDAF。图10是根据本申请一实施例的通信方法1000的示意性流程图。该方法可选地可以应用于图1-4中任一所示的系统,但并不仅限于此。该方法包括以下内容:
S1010、第三网络设备接收第一用例的特征配置文件;
S1020、第三网络设备根据特征配置文件,确定执行该第一用例所需的网络设备、终端设备和节点中的至少之一;
S1030、第三网络设备向执行该第一用例所需的网络设备、终端设备和节点中的至少之一发送特征配置文件中的配置参数。
根据第一用例的特征配置文件,第三网络设备确定出执行该第一用例的各个节点,从而能够从各个节点获取到第一用例的相关数据,实现收集第一用例在不同域或不同节点的参数,满足机器学习训练和 /或执行过程中对数据的需求。
在一些实施方式中,还包括,第三网络设备根据第一用例的特征配置文件,从第五网络设备获取第一用例需要的模型数据;
第三网络设备向执行第一用例所需的网络设备、终端设备和节点中的至少之一发送第一用例需要的模型数据。
其中,第五网络设备可以包括ADRF。
在一些实施方式中,还包括,第三网络设备从执行第一用例所需的网络设备、终端设备和节点中的至少之一接收第一用例的执行结果,该执行结果中包含第一用例的第一特征标识;
第三网络设备根据执行结果中包含的第一特征标识,将接收的多个执行结果进行聚合。
其中,该执行结果中还可以包含以下至少之一:
第一用例需要收集的参数的类型;
第一用例需要的时间窗和/或区域。
在一些实施方式中,还包括,第三网络设备将聚合后的执行结果发送至第一网络设备。第一网络设备可以包括NEF。
在一些实施方式中,第一用例的特征配置文件中包含以下特征参数中的至少之一:
第一用例需要收集的参数的类型;
第一用例需要采用的模型;
第一用例需要调用的网元和/或节点;
第一用例需要的时间窗和/或区域;
第一用例所涉及的终端设备的标识;
发起第一用例的应用的标识。
其中,参数的类型可以采用数据集标识(dataset ID)表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:第一用例的类型;执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:QoE的统计和/或预测;EE的统计和/或预测。
其中,执行第一用例采用的操作可以包括:VFL操作。
第二网络设备的其它执行步骤可以参照图6和图9示例中第三网络设备的相关内容,在此不再赘述。
本申请实施例还提出一种通信方法,该通信方法可以由终端备执行。图11是根据本申请一实施例的通信方法1100的示意性流程图。该方法可选地可以应用于图1-4中任一所示的系统,但并不仅限于此。该方法包括以下内容:
S1110、终端设备接收第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;
S1120、终端设备发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
终端设备执行第一用例之后,通过在该第一用例的执行结果中包含该第一用例的第一特征标识,能够为第一用例的执行结果标注相应的标识,以便接收到该执行结果的设备根据该第一特征标识收集属于同一第一用例的参数,从而满足机器学习训练和/或执行过程中对数据的需求。
在一些实施方式中,执行结果中还包含以下至少之一:
第一用例需要收集的参数的类型;
第一用例需要的时间窗和/或区域。
在一些实施方式中,参数的类型采用数据集标识表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:第一用例的类型;执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:QoE的统计和/或预测;EE的统计和/或预测。
在一些实施方式中,执行第一用例采用的操作包括:VFL操作。
终端设备的其它执行步骤可以参照图6和图9示例中终端设备的相关内容,在此不再赘述。
本申请实施例还提出一种通信方法,该通信方法可以由核心网网元或接入网设备执行。图12是根据本申请一实施例的通信方法1200的示意性流程图。该方法可选地可以应用于图1-4中任一所示的系统,但并不仅限于此。该方法包括以下内容:
S1210、核心网网元或接入网设备接收第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;
S1220、该核心网网元或接入网设备发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
核心网网元或接入网设备在执行第一用例之后,通过在该第一用例的执行结果中包含该第一用例的第一特征标识,能够为第一用例的执行结果标注相应的标识,以便接收到该执行结果的设备根据该第一特征标识收集属于同一第一用例的参数,从而满足机器学习训练和/或执行过程中对数据的需求。
在一些实施方式中,执行结果中还包含以下至少之一:
第一用例需要收集的参数的类型;
第一用例需要的时间窗和/或区域。
在一些实施方式中,参数的类型采用数据集标识表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:第一用例的类型;执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:QoE的统计和/或预测;EE的统计和/或预测。
在一些实施方式中,执行第一用例采用的操作包括:VFL操作。
终端设备的其它执行步骤可以参照图6和图9示例中执行第一用例所需的网络设备或节点的相关内容,在此不再赘述。
以下参照附图,举具体的实施例详细介绍。
在以下实施例中,将第一网络设备具体为NEF、第二网络设备具体为UDM或UDR、第三网络设备具体为NWDAF、第四网络设备AF、第五网络设备具体为ADRF为例进行介绍。在本申请其他实施例中,前述各网络设备还可以是其他功能网元。并且,在以下实施例中,将第一用例具体为VFL用例进行举例,在本申请其他实施例中,第一用例也可以是其他用例。
实施例一:
VFL具有多样化的用例,例如QoE的统计和/预测,EE的统计和/或预测等等。为了能使通信网络可以准确地识别出不同的用例,从而进行不同的操作,本实施例定义一个新的ID,即特征ID(feature ID),用来区分不同的用例。特征ID可以体现的信息如下所示:
(1)执行的用例:例如QoE的预测统计,能量效率的统计等。
(2)执行该用例采用的AI操作:VFL。
当第三方通过特征ID来请求通信网络执行相关的操作时,还可以存在外部feature ID和内部feature ID的映射关系。
本申请实施例还定义与特征ID相关联的特征配置文件(特征profile),用来描述该特征所需要的参数和需要执行的相关操作。特征Profile中包括的参数如下所示:
(1)执行该用例,需要收集的参数类型,可以用dataset ID表示。
(2)需要采用的模型:指各个域的节点为了执行同一个VFL用例,需要采用的模型。
(3)需要调用的网元,节点:为了执行一个VFL用例,所涉及的网元,例如执行QoE,可能需要SMF,PCF,NWDAF等网元。以及可能需要gNB和UE等节点的参加。
(4)该AI操作执行的时间窗,区域等。指执行该VFL用例所需的时间窗,以及该用例所适用的区域。可以以AOI表示。
(5)UE ID。该用例所涉及的UE。
(6)Application ID。发起该VFL的应用。
实施例二:
在本实施例中,由AF发起VFL执行请求,执行VFL所需的模型通过AF直接发送。
图13是本申请实施例二的实现流程图,包括以下步骤:
步骤1、当一个第三方的AF请求执行VFL用例时,AF向NEF发送VFL执行请求。VFL执行请求中包含第二特征标识(或称为外部feature ID),该第二特征标识表示AF请求执行的VFL用例。例如,该第二特征标识指示该VFL用例的类型是QoE的统计和/或预测。VFL执行请求中还可以包含UE标识(UE ID)、应用标识(Application ID)以及执行该VFL用例需要的模型数据;其中,UE标识指示执行该VFL用例所涉及的UE,应用标识指示执行该VFL用例对应的应用。
步骤2、NEF根据UE标识、应用标识等信息,将第二特征标识映射为通信网络内部使用的第一特征标识(或称为内部feature ID)。
步骤3、NEF收到请求后,根据第一特征标识向统一数据仓库功能(Unified Data Repository,UDR)发送特征配置文件(feature profile)获取请求。
步骤4、UDR返回提前存储的与该第一特征标识相对应的特征配置文件(feature profile),特征配 置文件中包括的参数详见实施例一。
步骤5、NEF根据接收的特征配置文件,确定需要进行交互的网元、RAN和UE中的至少之一。
步骤6、NEF向确定出的网元、RAN和UE中的至少之一发送特征配置文件中的配置参数,主要包括第一特征标识、执行VFL用例需要的模型数据、需要收集用作模型输入的参数类型、执行该AI操作的时间窗(包括训练和/或推理)、UE和/或RAN执行该VFL用例时所在的区域信息、以及各个网元执行该VFL用例时的服务区域信息。
步骤7、各个节点(包括网元、RAN、UE中的至少之一)将完成AI操作后的结果发送给NEF。该结果中包含第一特征标识、结果信息、参数类型(用dataset ID表示)、执行该AI操作的时间、区域信息等。其中,dataset ID用来指示各节点在本地进行AI操作时所采用的数据集的形式,例如分布特征、采样特征、或者样本维度等等。
步骤8、NEF根据各个节点收集到的信息中的第一特征标识,确定各节点返回的结果属于同一个VFL操作。NEF可以将具有相同第一特征标识的信息进行聚合。并且,NEF将第一特征标识映射为第二特征标识。
步骤9、NEF将AI操作的结果回复给AF,消息中包括结果信息或者聚合后的结果信息、参数类型(用dataset ID表示)、执行该AI操作的时间、区域信息、第二特征标识等。
实施例三:
本实施例中,由AF发起VFL执行请求,执行VFL所需的模型预先存储在分析数据存储功能(Analytic Data Repository Function,ADRF)中。
与实施例二相比,本实施例中不是AF直接提供模型数据,而是模型提前存储在了核心网的ADRF中,例如之前执行过相关的VFL,或者AF和核心网网元在请求执行操作前进行了协商,将模型预先存储在了ADRF中。
图14是本申请实施例三的实现流程图,包括以下步骤:
步骤1、当一个第三方的AF请求执行VFL用例时,AF向NEF发送VFL执行请求。VFL执行请求中包含第二特征标识(或称为外部feature ID),该第二特征标识表示AF请求执行的VFL用例。例如,该第二特征标识指示该VFL用例的类型是QoE的统计和/或预测。VFL执行请求中还可以包含UE标识(UE ID)和应用标识(Application ID);其中,UE标识指示执行该VFL用例所涉及的UE,应用标识指示执行该VFL用例对应的应用。
步骤2、NEF根据UE标识、应用标识等信息,将第二特征标识映射为通信网络内部使用的第一特征标识(或称为内部feature ID)。
步骤3、NEF收到请求后,根据第一特征标识向统一数据仓库功能(Unified Data Repository,UDR)发送特征配置文件(feature profile)获取请求。
步骤4、UDR返回提前存储的与该第一特征标识相对应的特征配置文件(feature profile),特征配置文件中包括的参数详见实施例一。
步骤5、NEF根据接收的特征配置文件,确定可以与ADRF进行交互的NWDAF。
步骤6、NEF将第一特征标识和对应的特征配置文件发送给NWDAF。
步骤7、NWDAF根据特征配置文件中所需要的模型的指示,与ADRF进行交互,获取需要的模型,具体地,NWDAF可以ADRF发送模型获取消息,该消息中包括需要获取的模型ID。
步骤8、ADRF向NWDAF返回满足要求的模型的数据。
步骤9、NWDAF向对应的网元、RAN和UE中的至少之一发送特征配置文件中的配置参数,主要包括第一特征标识、执行VFL用例需要的模型数据、需要收集用作模型输入的参数类型、执行该AI操作的时间窗(包括训练和/或推理)、UE和/或RAN执行该VFL用例时所在的区域信息、以及各个网元执行该VFL用例时的服务区域信息。
步骤10、各个节点(包括网元、RAN、UE中的至少之一)将完成AI操作后的结果发送给NWDAF。该结果中包含第一特征标识、结果信息、参数类型(用dataset ID表示)、执行该AI操作的时间、区域信息等。其中,dataset ID用来指示各节点在本地进行AI操作时所采用的数据集的形式,例如分布特征、采样特征、或者样本维度等等。
步骤11、NWDAF根据各个节点收集到的信息中的第一特征标识,确定各节点返回的结果属于同一个VFL操作。NWDAF可以将具有相同第一特征标识的信息进行聚合。
步骤12、NWDAF将聚合后的结果发送给NEF。
步骤13、NEF将第一特征标识映射为第二特征标识。
步骤14、NEF将AI操作的结果回复给AF,消息中包括结果信息或者聚合后的结果信息、参数类型(用dataset ID表示)、执行该AI操作的时间、区域信息、第二特征标识等。
实施例四:
本实施例中,由NWDAF发起VFL流程。
与实施例二和实施例三的不同之处在于,本实施例下,是由核心网的网元,例如NWDAF来发起VFL的操作。因此,不需要NEF的参与,不需要特征标识的映射。
图15是本申请实施例四的实现流程图,包括以下步骤:
步骤1、当NWDAF请求执行VFL时,NWDAF向UDR发送特征配置文件获取请求,该特征配置文件中包含第一特征标识。
步骤2、UDR向NWDAF返回提前存储的与该第一特征标识相对应的特征配置文件(feature profile),特征配置文件中包括的参数详见实施例一。
步骤3、NWDAF根据特征配置文件中包含的所需要模型的指示,确定需要采用的模型。
步骤4、NWDAF与ADRF进行交互,获取需要的模型,具体地,NWDAF可以ADRF发送模型获取消息,该消息中包括需要获取的模型ID。
步骤5、ADRF向NWDAF返回满足要求的模型的数据。
步骤6、NWDAF向对应的网元、RAN和UE中的至少之一发送特征配置文件中的配置参数,主要包括第一特征标识、执行VFL用例需要的模型数据、需要收集用作模型输入的参数类型、执行该AI操作的时间窗(包括训练和/或推理)、UE和/或RAN执行该VFL用例时所在的区域信息、以及各个网元执行该VFL用例时的服务区域信息。
步骤7、各个节点(包括网元、RAN、UE中的至少之一)将完成AI操作后的结果发送给NWDAF。该结果中包含第一特征标识、结果信息、参数类型(用dataset ID表示)、执行该AI操作的时间、区域信息等。其中,dataset ID用来指示各节点在本地进行AI操作时所采用的数据集的形式,例如分布特征、采样特征、或者样本维度等等。
步骤8、NWDAF根据各个节点收集到的信息中的第一特征标识,确定各节点返回的结果属于同一个VFL操作。NWDAF可以将具有相同第一特征标识的信息进行聚合。
本技术方案介绍了在执行多域的VFL时,如何通过特征表示和调用相关的特征配置文件的方式,使得执行节点可以知道联合哪些网元、RAN、UE获取的等信息来成功进行VFL的操作。本方案给出了第三方发起VFL和核心网网元发起NWDAF两种不同场景下具体的执行流程,实现了通信系统对VFL的支持,能够满足QoE的统计和/或预测、EE的统计和/或预测等用例的需求。
本申请实施例还提出一种第一网络设备,图16是根据本申请一实施例的第一网络设备1600的示意性框图。该第一网络设备1600可以包括:
第一收发单元1610,用于向第二网络设备发送第一用例的特征配置文件获取请求,特征配置文件获取请求中携带第一用例的第一特征标识;从第二网络设备接收第一特征标识对应的特征配置文件。
在一些实施方式中,第一用例的特征配置文件中包含以下特征参数中的至少之一:
第一用例需要收集的参数的类型;
第一用例需要采用的模型;
第一用例需要调用的网元和/或节点;
第一用例需要的时间窗和/或区域;
第一用例所涉及的终端设备的标识;
发起第一用例的应用的标识。
在一些实施方式中,参数的类型采用数据集标识表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:
第一用例的类型;
执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:
用户QoE的统计和/或预测;
能量效率EE的统计和/或预测。
在一些实施方式中,第一用例采用的操作包括:VFL操作。
在一些实施方式中,第一收发单元1610还用于,从第四网络设备接收第一执行请求,第一执行请求中包含第一用例的特征标识。
在一些实施方式中,第一执行请求中还包含以下至少之一:
第一用例所涉及的终端设备的标识;
执行第一用例的应用的标识;
执行第一用例所需的模型数据。
在一些实施方式中,第一用例的特征标识包括第一用例的第一特征标识。
在一些实施方式中,第一用例的特征标识包括第一用例的第二特征标识。
本申请实施例还提出一种第一网络设备,图17是根据本申请一实施例的第一网络设备1700的示意性框图。该第一网络设备1700还可以包括:
第一处理单元1720,用于确定第二特征标识对应的第一特征标识。
在一些实施方式中,第一处理单元1720还用于根据特征配置文件,确定执行第一用例所需的网络设备、终端设备和节点中的至少之一;
第一收发单元1610还用于,向执行第一用例所需的网络设备、终端设备和节点中的至少之一发送特征配置文件中的配置参数。
在一些实施方式中,第一收发单元1610还用于,从执行第一用例所需的网络设备、终端设备和节点中的至少之一接收第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
在一些实施方式中,执行结果中还包含以下至少之一:
第一用例需要收集的参数的类型;
第一用例需要的时间窗和/或区域。
在一些实施方式中,第一处理单元1720还用于根据执行结果中包含的第一特征标识,将接收的多个执行结果进行聚合。
在一些实施方式中,第一收发单元1610还用于,将聚合后的执行结果发送至第四网络设备。
在一些实施方式中,聚合后的执行结果中包含第一用例的第一特征标识或第二特征标识;
第二特征标识由第一网络设备根据第一特征标识确定。
在一些实施方式中,聚合后的执行结果中还包含以下至少之一:
第一用例需要收集的参数的类型;
第一用例需要的时间窗和/或区域。
在一些实施方式中,第一网络设备包括NEF。
在一些实施方式中,第二网络设备包括UDM或UDR。
在一些实施方式中,第四网络设备包括AF。
在一些实施方式中,执行第一用例所需的网络设备包括核心网网元。
在一些实施方式中,核心网网元包括LMF、MDAF或NWDAF。
本申请实施例的第一网络设备1600、1700能够实现前述的方法实施例中的第一网络设备的对应功能。该第一网络设备1600、1700中的各个模块(子模块、单元或组件等)对应的流程、功能、实现方式以及有益效果,可参见上述方法实施例中的对应描述,在此不再赘述。需要说明,关于申请实施例的第一网络设备1600、1700中的各个模块(子模块、单元或组件等)所描述的功能,可以由不同的模块(子模块、单元或组件等)实现,也可以由同一个模块(子模块、单元或组件等)实现。
本申请实施例还提出一种第二网络设备,图18是根据本申请一实施例的第二网络设备1800的示意性框图。该第二网络设备1800可以包括:
第二收发单元1810,用于接收第一用例的特征配置文件获取请求,特征配置文件获取请求中携带第一用例的第一特征标识;发送第一特征标识对应的特征配置文件。
在一些实施方式中,第一用例的特征配置文件中包含以下特征参数中的至少之一:
第一用例需要收集的参数的类型;
第一用例需要采用的模型;
第一用例需要调用的网元和/或节点;
第一用例需要的时间窗和/或区域;
第一用例所涉及的终端设备的标识;
发起第一用例的应用的标识。
在一些实施方式中,参数的类型采用数据集标识表示。
本申请实施例还提出一种第二网络设备,图19是根据本申请一实施例的第二网络设备1900的示意性框图。该第二网络设备1900可以包括:
第二处理单元1920,用于保存第一特征标识对应的特征配置文件。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:
第一用例的类型;
执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:
用户QoE的统计和/或预测;
EE的统计和/或预测。
在一些实施方式中,执行第一用例采用的操作包括:VFL操作。
在一些实施方式中,第二网络设备包括UDM或UDR。
本申请实施例的第二网络设备1800、1900能够实现前述的方法实施例中的第二网络设备的对应功能。该第二网络设备1800、1900中的各个模块(子模块、单元或组件等)对应的流程、功能、实现方式以及有益效果,可参见上述方法实施例中的对应描述,在此不再赘述。需要说明,关于申请实施例的第二网络设备1800、1900中的各个模块(子模块、单元或组件等)所描述的功能,可以由不同的模块(子模块、单元或组件等)实现,也可以由同一个模块(子模块、单元或组件等)实现。
本申请实施例还提出一种第三网络设备,图20是根据本申请一实施例的第三网络设备2000的示意性框图。该第三网络设备2000可以包括:
第三收发单元2010,用于接收第一用例的特征配置文件;
第三处理单元2020,用于根据特征配置文件,确定执行第一用例所需的网络设备、终端设备和节点中的至少之一;
第三收发单元2010还用于向执行第一用例所需的网络设备、终端设备和节点中的至少之一发送特征配置文件中的配置参数。
在一些实施方式中,第二处理单元2020还用于根据第一用例的特征配置文件,从第五网络设备获取第一用例需要的模型数据;
第三收发单元2010还用于向执行第一用例所需的网络设备、终端设备和节点中的至少之一发送第一用例需要的模型数据。
在一些实施方式中,第三收发单元2010还用于从执行第一用例所需的网络设备、终端设备和节点中的至少之一接收第一用例的执行结果,执行结果中包含第一用例的第一特征标识;
第三处理单元2020还用于根据执行结果中包含的第一特征标识,将接收的多个执行结果进行聚合。
在一些实施方式中,执行结果中还包含以下至少之一:
第一用例需要收集的参数的类型;
第一用例需要的时间窗和/或区域。
在一些实施方式中,第三收发单元2010还用于将聚合后的执行结果发送至第一网络设备。
在一些实施方式中,第一用例的特征配置文件中包含以下特征参数中的至少之一:
第一用例需要收集的参数的类型;
第一用例需要采用的模型;
第一用例需要调用的网元和/或节点;
第一用例需要的时间窗和/或区域;
第一用例所涉及的终端设备的标识;
发起第一用例的应用的标识。
在一些实施方式中,参数的类型采用数据集标识表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:
第一用例的类型;
执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:
用户QoE的统计和/或预测;
EE的统计和/或预测。
在一些实施方式中,执行第一用例采用的操作包括:VFL操作。
在一些实施方式中,第三网络设备包括NWDAF。
在一些实施方式中,第五网络设备包括ADRF。
在一些实施方式中,第一网络设备包括NEF。
本申请实施例的第三网络设备2000能够实现前述的方法实施例中的第三网络设备的对应功能。该第三网络设备2000中的各个模块(子模块、单元或组件等)对应的流程、功能、实现方式以及有益效果,可参见上述方法实施例中的对应描述,在此不再赘述。需要说明,关于申请实施例的第三网络设备2000中的各个模块(子模块、单元或组件等)所描述的功能,可以由不同的模块(子模块、单元或组件等)实现,也可以由同一个模块(子模块、单元或组件等)实现。
本申请实施例还提出一种第四网络设备,图21是根据本申请一实施例的第四网络设备2100的示意性框图。该第四网络设备2100可以包括:
第四收发单元2110,用于向第一网络设备发送第一执行请求,第一执行请求中包含第一用例的特征标识;从第一网络设备接收第一用例的执行结果,执行结果中包含第一用例的特征标识。
在一些实施方式中,第一执行请求中还包含以下至少之一:
第一用例所涉及的终端设备的标识;
执行第一用例的应用的标识;
执行第一用例所需的模型数据。
在一些实施方式中,参数的类型采用数据集标识表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:
第一用例的类型;
执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:
用户QoE的统计和/或预测;
EE的统计和/或预测。
在一些实施方式中,执行第一用例采用的操作包括:VFL操作。
本申请实施例的第四网络设备2100能够实现前述的方法实施例中的第四网络设备的对应功能。该第四网络设备2100中的各个模块(子模块、单元或组件等)对应的流程、功能、实现方式以及有益效果,可参见上述方法实施例中的对应描述,在此不再赘述。需要说明,关于申请实施例的第四网络设备2100中的各个模块(子模块、单元或组件等)所描述的功能,可以由不同的模块(子模块、单元或组件等)实现,也可以由同一个模块(子模块、单元或组件等)实现。
本申请实施例还提出一种终端设备,图22是根据本申请一实施例的终端设备2200的示意性框图。该终端设备2200可以包括:
第五收发单元2210,用于接收第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
在一些实施方式中,执行结果中还包含以下至少之一:
第一用例需要收集的参数的类型;
第一用例需要的时间窗和/或区域。
在一些实施方式中,参数的类型采用数据集标识表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:
第一用例的类型;
执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:
用户QoE的统计和/或预测;
EE的统计和/或预测。
在一些实施方式中,执行第一用例采用的操作包括:VFL操作。
本申请实施例的终端设备2200能够实现前述的方法实施例中的终端设备的对应功能。该终端设备2200中的各个模块(子模块、单元或组件等)对应的流程、功能、实现方式以及有益效果,可参见上述方法实施例中的对应描述,在此不再赘述。需要说明,关于申请实施例的终端设备2200中的各个模块(子模块、单元或组件等)所描述的功能,可以由不同的模块(子模块、单元或组件等)实现,也可以由同一个模块(子模块、单元或组件等)实现。
本申请实施例还提出一种核心网网元,图23是根据本申请一实施例的核心网网元2300的示意性框图。该核心网网元2300可以包括:
第六收发单元2310,用于接收第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
在一些实施方式中,执行结果中还包含以下至少之一:
第一用例需要收集的参数的类型;
第一用例需要的时间窗和/或区域。
在一些实施方式中,参数的类型采用数据集标识表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:
第一用例的类型;
执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:
用户QoE的统计和/或预测;
EE的统计和/或预测。
在一些实施方式中,执行第一用例采用的操作包括:VFL操作。
本申请实施例的核心网网元2300能够实现前述的方法实施例中的核心网网元的对应功能。该核心网网元2300中的各个模块(子模块、单元或组件等)对应的流程、功能、实现方式以及有益效果,可参见上述方法实施例中的对应描述,在此不再赘述。需要说明,关于申请实施例的核心网网元2300中的各个模块(子模块、单元或组件等)所描述的功能,可以由不同的模块(子模块、单元或组件等)实现,也可以由同一个模块(子模块、单元或组件等)实现。
本申请实施例还提出一种接入网设备,图24是根据本申请一实施例的接入网设备2400的示意性框图。该接入网设备2400可以包括:
第七收发单元2410,用于接收第一用例的特征配置文件中的配置参数、第一用例需要的模型数据、以及第一用例的第一特征标识;发送第一用例的执行结果,执行结果中包含第一用例的第一特征标识。
在一些实施方式中,执行结果中还包含以下至少之一:
第一用例需要收集的参数的类型;
第一用例需要的时间窗和/或区域。
在一些实施方式中中,参数的类型采用数据集标识表示。
在一些实施方式中,第一用例包括VFL用例。
在一些实施方式中,第一特征标识指示以下至少之一:
第一用例的类型;
执行第一用例采用的操作。
在一些实施方式中,第一用例的类型包括以下至少之一:
用户QoE的统计和/或预测;
EE的统计和/或预测。
在一些实施方式中,执行第一用例采用的操作包括:VFL操作。
图25是根据本申请实施例的通信设备2500示意性结构图。该通信设备2500包括处理器2510,处理器2510可以从存储器中调用并运行计算机程序,以使通信设备2500实现本申请实施例中的方法。
在一种实施方式中,通信设备2500还可以包括存储器2520。其中,处理器2510可以从存储器2520中调用并运行计算机程序,以使通信设备2500实现本申请实施例中的方法。
其中,存储器2520可以是独立于处理器2510的一个单独的器件,也可以集成在处理器2510中。
在一种实施方式中,通信设备2500还可以包括收发器2530,处理器2510可以控制该收发器2530与其他设备进行通信,具体地,可以向其他设备发送信息或数据,或接收其他设备发送的信息或数据。
其中,收发器2530可以包括发射机和接收机。收发器2530还可以进一步包括天线,天线的数量可以为一个或多个。
在一种实施方式中,该通信设备2500可为本申请实施例的网络设备,并且该通信设备2500可以实现本申请实施例的各个方法中由网络设备实现的相应流程,为了简洁,在此不再赘述。
在一种实施方式中,该通信设备2500可为本申请实施例的终端设备,并且该通信设备2500可以实现本申请实施例的各个方法中由终端设备实现的相应流程,为了简洁,在此不再赘述。
在一种实施方式中,该通信设备2500可为本申请实施例的核心网网元,并且该通信设备2500可以实现本申请实施例的各个方法中由核心网网元实现的相应流程,为了简洁,在此不再赘述。
在一种实施方式中,该通信设备2500可为本申请实施例的接入网设备,并且该通信设备2500可以实现本申请实施例的各个方法中由接入网设备实现的相应流程,为了简洁,在此不再赘述。
图26是根据本申请实施例的芯片2600的示意性结构图。该芯片2600包括处理器2610,处理器2610可以从存储器中调用并运行计算机程序,以实现本申请实施例中的方法。
在一种实施方式中,芯片2600还可以包括存储器2620。其中,处理器2610可以从存储器2620中调用并运行计算机程序,以实现本申请实施例中由终端设备或者网络设备或者核心网网元或者接入网设备执行的方法。
其中,存储器2620可以是独立于处理器2610的一个单独的器件,也可以集成在处理器2610中。
在一种实施方式中,该芯片2600还可以包括输入接口2630。其中,处理器2610可以控制该输入 接口2630与其他设备或芯片进行通信,具体地,可以获取其他设备或芯片发送的信息或数据。
在一种实施方式中,该芯片2600还可以包括输出接口2640。其中,处理器2610可以控制该输出接口2640与其他设备或芯片进行通信,具体地,可以向其他设备或芯片输出信息或数据。
在一种实施方式中,该芯片可应用于本申请实施例中的网络设备,并且该芯片可以实现本申请实施例的各个方法中由网络设备实现的相应流程,为了简洁,在此不再赘述。
在一种实施方式中,该芯片可应用于本申请实施例中的终端设备,并且该芯片可以实现本申请实施例的各个方法中由终端设备实现的相应流程,为了简洁,在此不再赘述。
应用于网络设备、终端设备、核心网网元和接入网设备的芯片可以是相同的芯片或不同的芯片。
应理解,本申请实施例提到的芯片还可以称为系统级芯片,系统芯片,芯片系统或片上系统芯片等。
上述提及的处理器可以是通用处理器、数字信号处理器(digital signal processor,DSP)、现成可编程门阵列(field programmable gate array,FPGA)、专用集成电路(application specific integrated circuit,ASIC)或者其他可编程逻辑器件、晶体管逻辑器件、分立硬件组件等。其中,上述提到的通用处理器可以是微处理器或者也可以是任何常规的处理器等。
上述提及的存储器可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(read-only memory,ROM)、可编程只读存储器(programmable ROM,PROM)、可擦除可编程只读存储器(erasable PROM,EPROM)、电可擦除可编程只读存储器(electrically EPROM,EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory,RAM)。
应理解,上述存储器为示例性但不是限制性说明,例如,本申请实施例中的存储器还可以是静态随机存取存储器(static RAM,SRAM)、动态随机存取存储器(dynamic RAM,DRAM)、同步动态随机存取存储器(synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(synch link DRAM,SLDRAM)以及直接内存总线随机存取存储器(Direct Rambus RAM,DR RAM)等等。也就是说,本申请实施例中的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。该计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行该计算机程序指令时,全部或部分地产生按照本申请实施例中的流程或功能。该计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。该计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,该计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(Digital Subscriber Line,DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。该计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。该可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质(例如固态硬盘(Solid State Disk,SSD))等。
应理解,在本申请的各种实施例中,上述各过程的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请实施例的实施过程构成任何限定。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
以上所述仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以该权利要求的保护范围为准。

Claims (80)

  1. 一种通信方法,包括:
    第一网络设备向第二网络设备发送第一用例的特征配置文件获取请求,所述特征配置文件获取请求中携带所述第一用例的第一特征标识;
    所述第一网络设备从所述第二网络设备接收所述第一特征标识对应的特征配置文件。
  2. 根据权利要求1所述的方法,其中,所述第一用例的特征配置文件中包含以下特征参数中的至少之一:
    所述第一用例需要收集的参数的类型;
    所述第一用例需要采用的模型;
    所述第一用例需要调用的网元和/或节点;
    所述第一用例需要的时间窗和/或区域;
    所述第一用例所涉及的终端设备的标识;
    发起所述第一用例的应用的标识。
  3. 根据权利要求2所述的方法,其中,所述参数的类型采用数据集标识表示。
  4. 根据权利要求1-3中任一所述的方法,其中,所述第一用例包括纵向联邦学习VFL用例。
  5. 根据权利要求1-4中任一所述的方法,其中,所述第一特征标识指示以下至少之一:
    所述第一用例的类型;
    执行所述第一用例采用的操作。
  6. 根据权利要求5所述的方法,其中,所述第一用例的类型包括以下至少之一:
    用户体验质量QoE的统计和/或预测;
    能量效率EE的统计和/或预测。
  7. 根据权利要求5所述的方法,其中,所述执行所述第一用例采用的操作包括:VFL操作。
  8. 根据权利要求1-7中任一所述的方法,所述第一网络设备向第二网络设备发送第一用例的特征配置文件获取请求之前,还包括:
    所述第一网络设备从第四网络设备接收第一执行请求,所述第一执行请求中包含第一用例的特征标识。
  9. 根据权利要求8所述的方法,其中,所述第一执行请求中还包含以下至少之一:
    所述第一用例所涉及的终端设备的标识;
    执行所述第一用例的应用的标识;
    执行所述第一用例所需的模型数据。
  10. 根据权利要求8或9所述的方法,其中,所述第一用例的特征标识包括所述第一用例的第一特征标识。
  11. 根据权利要求8或9所述的方法,其中,所述第一用例的特征标识包括所述第一用例的第二特征标识。
  12. 根据权利要求11所述的方法,还包括,所述第一网络设备确定所述第二特征标识对应的第一特征标识。
  13. 根据权利要求1-12中任一所述的方法,还包括,
    所述第一网络设备根据所述特征配置文件,确定执行所述第一用例所需的网络设备、终端设备和节点中的至少之一;
    所述第一网络设备向所述执行所述第一用例所需的网络设备、终端设备和节点中的至少之一发送所述特征配置文件中的配置参数。
  14. 根据权利要求13所述的方法,还包括,
    所述第一网络设备从所述执行所述第一用例所需的网络设备、终端设备和节点中的至少之一接收所述第一用例的执行结果,所述执行结果中包含所述第一用例的第一特征标识。
  15. 根据权利要求14所述的方法,其中,所述执行结果中还包含以下至少之一:
    所述第一用例需要收集的参数的类型;
    所述第一用例需要的时间窗和/或区域。
  16. 根据权利要求14或15所述的方法,还包括,
    所述第一网络设备根据执行结果中包含的所述第一特征标识,将接收的多个执行结果进行聚合。
  17. 根据权利要求16所述的方法,还包括,
    所述第一网络设备将聚合后的执行结果发送至所述第四网络设备。
  18. 根据权利要求17所述的方法,其中,所述聚合后的执行结果中包含所述第一用例的第一特征 标识或第二特征标识;
    所述第二特征标识由所述第一网络设备根据所述第一特征标识确定。
  19. 根据权利要求18所述的方法,其中,所述聚合后的执行结果中还包含以下至少之一:
    所述第一用例需要收集的参数的类型;
    所述第一用例需要的时间窗和/或区域。
  20. 根据权利要求1-19中任一所述的方法,其中,所述第一网络设备包括网元功能NEF。
  21. 根据权利要求1-19中任一所述的方法,其中,所述第二网络设备包括统一数据管理功能UDM或统一数据仓库功能UDR。
  22. 根据权利要求8-12中任一所述的方法,其中,所述第四网络设备包括应用功能AF。
  23. 根据权利要求14-19中任一所述的方法,其中,所述执行所述第一用例所需的网络设备包括核心网网元。
  24. 根据权利要求23所述的方法,其中,所述核心网网元包括本地管理功能LMF、管理数据分析功能MDAF或网络数据分析功能NWDAF。
  25. 一种通信方法,包括:
    第二网络设备接收第一用例的特征配置文件获取请求,所述特征配置文件获取请求中携带所述第一用例的第一特征标识;
    所述第二网络设备发送所述第一特征标识对应的特征配置文件。
  26. 根据权利要求25所述的方法,其中,所述第一用例的特征配置文件中包含以下特征参数中的至少之一:
    所述第一用例需要收集的参数的类型;
    所述第一用例需要采用的模型;
    所述第一用例需要调用的网元和/或节点;
    所述第一用例需要的时间窗和/或区域;
    所述第一用例所涉及的终端设备的标识;
    发起所述第一用例的应用的标识。
  27. 根据权利要求26所述的方法,其中,所述参数的类型采用数据集标识表示。
  28. 根据权利要求25-27中任一所述的方法,还包括,所述第二网络设备保存第一特征标识对应的特征配置文件。
  29. 根据权利要求25-28中任一所述的方法,其中,所述第一用例包括VFL用例。
  30. 根据权利要求25-29中任一所述的方法,其中,所述第一特征标识指示以下至少之一:
    所述第一用例的类型;
    执行所述第一用例采用的操作。
  31. 根据权利要求30所述的方法,其中,所述第一用例的类型包括以下至少之一:
    QoE的统计和/或预测;
    EE的统计和/或预测。
  32. 根据权利要求30所述的方法,其中,所述执行所述第一用例采用的操作包括:VFL操作。
  33. 根据权利要求25-32中任一所述的方法,其中,所述第二网络设备包括UDM或UDR。
  34. 一种通信方法,包括:
    第三网络设备接收第一用例的特征配置文件;
    所述第三网络设备根据所述特征配置文件,确定执行所述第一用例所需的网络设备、终端设备和节点中的至少之一;
    所述第三网络设备向所述执行所述第一用例所需的网络设备、终端设备和节点中的至少之一发送所述特征配置文件中的配置参数。
  35. 根据权利要求34所述的方法,还包括,
    所述第三网络设备根据所述第一用例的特征配置文件,从第五网络设备获取所述第一用例需要的模型数据;
    所述第三网络设备向所述执行所述第一用例所需的网络设备、终端设备和节点中的至少之一发送所述第一用例需要的模型数据。
  36. 根据权利要求34或35所述的方法,还包括,
    所述第三网络设备从所述执行所述第一用例所需的网络设备、终端设备和节点中的至少之一接收所述第一用例的执行结果,所述执行结果中包含所述第一用例的第一特征标识;
    所述第三网络设备根据执行结果中包含的所述第一特征标识,将接收的多个执行结果进行聚合。
  37. 根据权利要求36所述的方法,其中,所述执行结果中还包含以下至少之一:
    所述第一用例需要收集的参数的类型;
    所述第一用例需要的时间窗和/或区域。
  38. 根据权利要求37所述的方法,还包括,
    所述第三网络设备将聚合后的执行结果发送至所述第一网络设备。
  39. 根据权利要求34-38中任一所述的方法,其中,所述第一用例的特征配置文件中包含以下特征参数中的至少之一:
    所述第一用例需要收集的参数的类型;
    所述第一用例需要采用的模型;
    所述第一用例需要调用的网元和/或节点;
    所述第一用例需要的时间窗和/或区域;
    所述第一用例所涉及的终端设备的标识;
    发起所述第一用例的应用的标识。
  40. 根据权利要求39所述的方法,其中,所述参数的类型采用数据集标识表示。
  41. 根据权利要求34-40中任一所述的方法,其中,所述第一用例包括VFL用例。
  42. 根据权利要求36-40中任一所述的方法,其中,所述第一特征标识指示以下至少之一:
    所述第一用例的类型;
    执行所述第一用例采用的操作。
  43. 根据权利要求42所述的方法,其中,所述第一用例的类型包括以下至少之一:
    QoE的统计和/或预测;
    EE的统计和/或预测。
  44. 根据权利要求42所述的方法,其中,所述执行所述第一用例采用的操作包括:VFL操作。
  45. 根据权利要求34-44中任一所述的方法,其中,所述第三网络设备包括NWDAF。
  46. 根据权利要求35所述的方法,其中,所述第五网络设备包括分析数据存储功能ADRF。
  47. 根据权利要求38所述的方法,其中,所述第一网络设备包括NEF。
  48. 一种通信方法,包括:
    第四网络设备向第一网络设备发送第一执行请求,所述第一执行请求中包含第一用例的特征标识;
    所述第四网络设备从所述第一网络设备接收所述第一用例的执行结果,所述执行结果中包含所述第一用例的特征标识。
  49. 根据权利要求48所述的方法,其中,所述第一执行请求中还包含以下至少之一:
    所述第一用例所涉及的终端设备的标识;
    执行所述第一用例的应用的标识;
    执行所述第一用例所需的模型数据。
  50. 根据权利要求49所述的方法,其中,所述参数的类型采用数据集标识表示。
  51. 根据权利要求48-50中任一所述的方法,其中,所述第一用例包括VFL用例。
  52. 根据权利要求48-51中任一所述的方法,其中,所述第一特征标识指示以下至少之一:
    所述第一用例的类型;
    执行所述第一用例采用的操作。
  53. 根据权利要求52所述的方法,其中,所述第一用例的类型包括以下至少之一:
    QoE的统计和/或预测;
    EE的统计和/或预测。
  54. 根据权利要求52所述的方法,其中,所述执行所述第一用例采用的操作包括:VFL操作。
  55. 一种通信方法,包括:
    终端设备接收第一用例的特征配置文件中的配置参数、所述第一用例需要的模型数据、以及所述第一用例的第一特征标识;
    所述终端设备发送所述第一用例的执行结果,所述执行结果中包含所述第一用例的第一特征标识。
  56. 根据权利要求55所述的方法,其中,所述执行结果中还包含以下至少之一:
    所述第一用例需要收集的参数的类型;
    所述第一用例需要的时间窗和/或区域。
  57. 根据权利要求56所述的方法,其中,所述参数的类型采用数据集标识表示。
  58. 根据权利要求55-57中任一所述的方法,其中,所述第一用例包括VFL用例。
  59. 根据权利要求55-58中任一所述的方法,其中,所述第一特征标识指示以下至少之一:
    所述第一用例的类型;
    执行所述第一用例采用的操作。
  60. 根据权利要求59所述的方法,其中,所述第一用例的类型包括以下至少之一:
    QoE的统计和/或预测;
    EE的统计和/或预测。
  61. 根据权利要求59所述的方法,其中,所述执行所述第一用例采用的操作包括:VFL操作。
  62. 一种通信方法,包括:
    核心网网元或接入网设备接收第一用例的特征配置文件中的配置参数、所述第一用例需要的模型数据、以及所述第一用例的第一特征标识;
    所述核心网网元或接入网设备发送所述第一用例的执行结果,所述执行结果中包含所述第一用例的第一特征标识。
  63. 根据权利要求62所述的方法,其中,所述执行结果中还包含以下至少之一:
    所述第一用例需要收集的参数的类型;
    所述第一用例需要的时间窗和/或区域。
  64. 根据权利要求63所述的方法,其中,所述参数的类型采用数据集标识表示。
  65. 根据权利要求62-64中任一所述的方法,其中,所述第一用例包括VFL用例。
  66. 根据权利要求62-65中任一所述的方法,其中,所述第一特征标识指示以下至少之一:
    所述第一用例的类型;
    执行所述第一用例采用的操作。
  67. 根据权利要求66所述的方法,其中,所述第一用例的类型包括以下至少之一:
    QoE的统计和/或预测;
    EE的统计和/或预测。
  68. 根据权利要求66所述的方法,其中,所述执行所述第一用例采用的操作包括:VFL操作。
  69. 一种第一网络设备,包括:
    第一收发单元,用于向第二网络设备发送第一用例的特征配置文件获取请求,所述特征配置文件获取请求中携带所述第一用例的第一特征标识;从所述第二网络设备接收所述第一特征标识对应的特征配置文件。
  70. 一种第二网络设备,包括:
    第二收发单元,用于接收第一用例的特征配置文件获取请求,所述特征配置文件获取请求中携带所述第一用例的第一特征标识;发送所述第一特征标识对应的特征配置文件。
  71. 一种第三网络设备,包括:
    第三收发单元,用于接收第一用例的特征配置文件;
    第一确定单元,用于根据所述特征配置文件,确定执行所述第一用例所需的网络设备、终端设备和节点中的至少之一;
    第三收发单元还用于向所述执行所述第一用例所需的网络设备、终端设备和节点中的至少之一发送所述特征配置文件中的配置参数。
  72. 一种第四网络设备,包括:
    第四收发单元,用于向第一网络设备发送第一执行请求,所述第一执行请求中包含第一用例的特征标识;从所述第一网络设备接收所述第一用例的执行结果,所述执行结果中包含所述第一用例的特征标识。
  73. 一种终端设备,包括:
    第五收发单元,用于接收第一用例的特征配置文件中的配置参数、所述第一用例需要的模型数据、以及所述第一用例的第一特征标识;发送所述第一用例的执行结果,所述执行结果中包含所述第一用例的第一特征标识。
  74. 一种核心网网元,包括:
    第六收发单元,用于接收第一用例的特征配置文件中的配置参数、所述第一用例需要的模型数据、以及所述第一用例的第一特征标识;发送所述第一用例的执行结果,所述执行结果中包含所述第一用例的第一特征标识。
  75. 一种接入网设备,包括:
    第七收发单元,用于第一用例的特征配置文件中的配置参数、所述第一用例需要的模型数据、以及所述第一用例的第一特征标识;发送所述第一用例的执行结果,所述执行结果中包含所述第一用例的第一特征标识。
  76. 一种通信设备,包括:处理器、存储器和收发器,该存储器用于存储计算机程序,所述处理器用于调用并运行所述存储器中存储的计算机程序,并控制所述收发器,执行如权利要求1至68中任一项所述的方法。
  77. 一种芯片,包括:处理器,用于从存储器中调用并运行计算机程序,使得安装有所述芯片的设备执行如权利要求1至68中任一项所述的方法。
  78. 一种计算机可读存储介质,用于存储计算机程序,当所述计算机程序被设备运行时使得所述设备执行如权利要求1至68中任一项所述的方法。
  79. 一种计算机程序产品,包括计算机程序指令,该计算机程序指令使得计算机执行如权利要求1至68中任一项所述的方法。
  80. 一种计算机程序,所述计算机程序使得计算机执行如权利要求1至68中任一项所述的方法。
PCT/CN2023/112649 2023-08-11 2023-08-11 通信方法、终端设备和网络设备 Pending WO2025035289A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202380098383.8A CN121220015A (zh) 2023-08-11 2023-08-11 通信方法、终端设备和网络设备
PCT/CN2023/112649 WO2025035289A1 (zh) 2023-08-11 2023-08-11 通信方法、终端设备和网络设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2023/112649 WO2025035289A1 (zh) 2023-08-11 2023-08-11 通信方法、终端设备和网络设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US19/439,706 Continuation US20260128963A1 (en) 2026-01-05 Communication method, terminal device, and network device

Publications (1)

Publication Number Publication Date
WO2025035289A1 true WO2025035289A1 (zh) 2025-02-20

Family

ID=94632055

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/112649 Pending WO2025035289A1 (zh) 2023-08-11 2023-08-11 通信方法、终端设备和网络设备

Country Status (2)

Country Link
CN (1) CN121220015A (zh)
WO (1) WO2025035289A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113988319A (zh) * 2021-10-27 2022-01-28 深圳前海微众银行股份有限公司 联邦学习模型的训练方法、装置、电子设备、介质及产品
WO2023040429A1 (zh) * 2021-09-15 2023-03-23 京东科技信息技术有限公司 用于联邦特征工程的数据处理方法、装置、设备以及介质
CN116419209A (zh) * 2021-12-30 2023-07-11 维沃移动通信有限公司 数据处理的方法、装置及通信设备
CN116567608A (zh) * 2022-01-28 2023-08-08 华为技术有限公司 一种通信方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023040429A1 (zh) * 2021-09-15 2023-03-23 京东科技信息技术有限公司 用于联邦特征工程的数据处理方法、装置、设备以及介质
CN113988319A (zh) * 2021-10-27 2022-01-28 深圳前海微众银行股份有限公司 联邦学习模型的训练方法、装置、电子设备、介质及产品
CN116419209A (zh) * 2021-12-30 2023-07-11 维沃移动通信有限公司 数据处理的方法、装置及通信设备
CN116567608A (zh) * 2022-01-28 2023-08-08 华为技术有限公司 一种通信方法及装置

Also Published As

Publication number Publication date
CN121220015A (zh) 2025-12-26

Similar Documents

Publication Publication Date Title
US20250132901A1 (en) Federated learning method, first device, and third device
WO2020073855A1 (zh) 建立会话的方法和装置以及发送报文的方法和装置
WO2022126563A1 (zh) 网络资源选择方法、终端设备和网络设备
EP3849228A1 (en) Core network device, access network device, communication terminal, communication system, and communication method
US20240236655A1 (en) Information indication method, first access network device, and core network element
EP4243481A1 (en) Communication method and apparatus
US12101838B2 (en) Communications method, apparatus, and system
US12279111B2 (en) Wireless communication method, terminal device and network element
US20250274759A1 (en) Authorization method and device
CN116686265A (zh) 用于获取数据的方法和装置
CN120092427A (zh) 通信方法和设备
US20250358200A1 (en) Communication methods and apparatuses, device, chip and storage medium
CN113453311B (zh) 封闭接入组信息处理方法及装置
WO2025035289A1 (zh) 通信方法、终端设备和网络设备
US20260128963A1 (en) Communication method, terminal device, and network device
CN115499470B (zh) 一种智能电表数据的存储管理方法及装置
US20250132807A1 (en) First node, second node, method by first node, and method by second node
WO2025059850A1 (zh) 一种网络设备会话管理的通信方法、设备和介质
US20260081752A1 (en) Domain-based key management method and apparatus
US20260128856A1 (en) Homomorphic Task Management Method, Key Management Method, Ciphertext Storage Management Method, and Apparatus
WO2025098294A1 (en) Task-level homomorphic encryption management method and apparatus
US20260128857A1 (en) User-level homomorphic encryption management method and apparatus
WO2024229713A1 (zh) 通信方法和设备
WO2025103209A1 (zh) 通信方法及装置
WO2025019999A1 (zh) 感知上报确定方法、终端设备和网络设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23948725

Country of ref document: EP

Kind code of ref document: A1

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112026000099

Country of ref document: BR

NENP Non-entry into the national phase

Ref country code: DE