WO2022141295A1 - Procédé et appareil de communication - Google Patents

Procédé et appareil de communication Download PDF

Info

Publication number
WO2022141295A1
WO2022141295A1 PCT/CN2020/141803 CN2020141803W WO2022141295A1 WO 2022141295 A1 WO2022141295 A1 WO 2022141295A1 CN 2020141803 W CN2020141803 W CN 2020141803W WO 2022141295 A1 WO2022141295 A1 WO 2022141295A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
network element
data analysis
information
network
Prior art date
Application number
PCT/CN2020/141803
Other languages
English (en)
Chinese (zh)
Inventor
辛阳
崇卫微
吴晓波
王楚捷
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN202080106205.1A priority Critical patent/CN116325686A/zh
Priority to PCT/CN2020/141803 priority patent/WO2022141295A1/fr
Publication of WO2022141295A1 publication Critical patent/WO2022141295A1/fr

Links

Images

Definitions

  • the embodiments of the present application relate to the field of communication, and more particularly, to a communication method and a communication device.
  • 5G networks need to accurately measure the service experience of services in the network, and adjust the network if the service experience does not meet the requirements.
  • the premise of measuring service experience is to obtain a service experience model through training. Sure.
  • the present application provides a communication method and a communication device, so that the service experience model can still be effectively trained in the scenario of cross-vendor network elements in the core network domain.
  • an embodiment of the present application provides a communication method, the method includes: a first data analysis network element obtains service experience data of a service of a terminal on an application function network element and associated information corresponding to the service experience data, where The service is provided by the core network element of the equipment manufacturer; the first data analysis network element determines the address information of the second data analysis network element corresponding to the equipment manufacturer according to the association information; the first data analysis network element The service experience model of the service is determined in conjunction with the second data analysis network element according to the address information of the second data analysis network element, the service experience data and the associated information.
  • the first data analysis network element includes a data analysis network element of an operator
  • the second data analysis network element includes a data analysis network element of an equipment manufacturer.
  • the service experience model is a service experience model of the device manufacturer.
  • the first data analysis network element acquires the service experience data and associated information on the application function network element, and the first data analysis network element determines the service experience in the service experience data set according to the associated information Data
  • the service experience data is the service experience data generated when the terminal accesses the service provided by the core network element of the equipment manufacturer
  • the associated information is used to
  • the network data generated on the core network element is correlated with the service experience data generated on the application function network element
  • the first data analysis network element determines the address information of the second data analysis network element according to the correlation information.
  • the first data analysis network element determines the service experience model of the service according to the service experience data and the associated information in conjunction with the second data analysis network element.
  • the service experience data of the device vendor is determined through the association information, so as to train the service experience model of the service.
  • the association information includes association information between the UPF and the AF.
  • the AF and the UPF may use a timestamp (Timestamp) and an IP quintuple (IP address 5-tuple). ) to associate the data belonging to the same terminal on the two network elements in pairs.
  • the network storage function network element stores the correspondence between the association information and the address information of the second data analysis network element, and the first data
  • the analysis network element determines the address information of the second data analysis network element according to the association information, including: the first data analysis network element sends a first request to the network storage function network element, and the first request uses When requesting the address information of the second data analysis network element, the first request includes the association information; the first data analysis network element receives a first response from the network element storage function network element, and the first data analysis network element receives the first response from the network element storage function network element.
  • a response includes address information of the second data analysis network element.
  • the second data analysis network element will carry the association information to register with the network storage function network element in advance, and the first data analysis network element can determine the second data analysis network element according to the association information address information of the network element, so that the first data analysis network element can cooperate with the second data analysis network element to complete the training of the service experience model.
  • the association information corresponds to the identification information of the equipment manufacturer
  • the network storage function network element stores the identification information of the equipment manufacturer and the equipment manufacturer's identification information.
  • the corresponding relationship between the address information of the second data analysis network element, and the first data analysis network element determining the address information of the second data analysis network element according to the association information, including: the first data analysis network element.
  • the network element determines the identification information of the equipment manufacturer according to the association information; the first data analysis network element sends a second request to the network storage function network element, and the second request is used to request the second data analysis network element address information of the device, the second request includes the identification information of the device manufacturer; the first data analysis network element receives a second response from the network element storage function network element, and the second response includes the first data analysis network element. 2.
  • the data analyzes the address information of the network element.
  • the second data analysis network element will carry the identification information of the device manufacturer to register with the network storage function network element in advance, and the first data analysis network element will first determine the device according to the association information identification information of the manufacturer, and then determine the address information of the second data analysis network element according to the identification information of the equipment manufacturer, so that the first data analysis network element can cooperate with the second data analysis network element to complete the training of the service experience model.
  • the method further includes: the The first data analysis network element obtains the correspondence between the association information and the identification information of the equipment manufacturer from the core network element of the equipment manufacturer.
  • the first data analysis network element analyzes the address information of the network element and the service experience data according to the second data Determining the service experience model of the service in conjunction with the associated information and the second data analysis network element includes: the first data analysis network element reports to the second data analysis network element according to the address information of the second data analysis network element.
  • the data analysis network element sends the association information and indication information, and the indication information is used to instruct the second data analysis network element to perform distributed machine learning model training according to the association information;
  • the second data analysis network element receives the sub-model corresponding to the association information, and the sub-model is determined by the second data analysis network element according to the first network of the terminal on the equipment manufacturer's core network network element. Data determination; the first data analysis network element determines the service experience model according to the service experience data and the sub-model.
  • the method further includes: receiving, by the first data analysis network element, a network element of the core network of the equipment manufacturer corresponding to the association information
  • the second network data of the first data analysis network element determines the service experience model according to the service experience data, the sub-model and the second network data.
  • the above-mentioned second network data may be implemented in a fourth possible manner, in which the first data analysis network element obtains the association information from the equipment manufacturer's core network element and the equipment manufacturer When the corresponding relationship between the identification information is obtained, the second data network is obtained from the core network element of the equipment manufacturer at the same time, so as to save a certain resource overhead.
  • the first network data includes all information about the terminal on the core network element of the equipment manufacturer. private network data corresponding to the above service.
  • the above sixth possible implementation manner can allow the private network data of the service to participate in the training of the service experience model on the premise of ensuring data privacy, thereby improving the generalization capability of the service experience model and ensuring the service experience.
  • the second network data includes all information about the terminal on the core network element of the equipment manufacturer.
  • the public network data corresponding to the service in addition to the private network data and service experience data corresponding to the service, also participates in the training of the service experience model, which further improves the service experience model. It enables service providers to accurately measure their service experience and effectively monitor service quality, so that service experience requirements and network resources can be precisely matched.
  • the method for training a distributed machine learning model includes one or more of the following methods: vertical federated learning , horizontal federated learning, transfer learning, or sharing learning.
  • the distributed machine learning model training method enables the private network data of the service to be retained in the local data source to participate in the training of the service experience model, which not only ensures the privacy of the data, but also ensures the data experience. The accuracy and validity of the model, thus ensuring the business experience.
  • the determined service experience model is the service experience model corresponding to the device manufacturer.
  • the core network element of the equipment manufacturer includes one or more of the following network elements: Access and Mobility Management Function AMF Network element, session management function SMF network element, policy control PCF network element, user plane function UPF network element or unified data management UDM network element.
  • an embodiment of the present application provides a communication method, the method includes: a first network element obtains service experience data of a service of a terminal on an application function network element and associated information corresponding to the service experience data, and the The service is provided by the equipment manufacturer's core network element; the first network element determines the address information of the equipment manufacturer's data analysis network element according to the association information; the first network element analyzes the equipment manufacturer's data according to the address information The address information of the network element sends the association information and the service experience data to the data analysis network element of the device manufacturer, where the service experience data is used to determine the service experience model of the service.
  • the first network element obtains service experience data and associated information on the application function network element, and the first network element determines the service experience data in the service experience data set according to the associated information, and the The service experience data is the service experience data generated when the terminal accesses the service provided by the core network element of the device manufacturer, and the associated information is used to display the service in the device manufacturer's core network element when the terminal accesses the service.
  • the network data generated on the network element and the service experience data generated on the application function network element are correlated with each other.
  • the first network element After the first network element determines the address information of the data analysis network element of the equipment manufacturer according to the correlation information, the first network element sends the The data analysis network element of the equipment manufacturer sends the association information and the service experience data, so that the data analysis network element of the equipment manufacturer can train a service experience model.
  • the communication method of the embodiment of the present application can determine the service experience data of the equipment manufacturer through the association information in the scenario where the network elements in the core network domain cross equipment manufacturers, so that the data analysis network element of the equipment manufacturer can obtain all the equipment manufacturers.
  • the service experience data corresponding to the equipment manufacturer is obtained, so that the equipment manufacturer can train the service experience model corresponding to the equipment manufacturer.
  • the association information includes association information between the UPF and the AF.
  • the AF and the UPF may use a timestamp (Timestamp) and an IP quintuple (IP address 5-tuple). ) to associate the data belonging to the same terminal on the two network elements in pairs.
  • the network storage function network element stores the correspondence between the association information and the address information of the data analysis network element of the equipment manufacturer, and the first The network element determines the address information of the data analysis network element of the device manufacturer according to the association information, including: the first network element sends a first request to the network storage function network element, where the first request is used to request The address information of the data analysis network element of the equipment manufacturer, the first request includes the association information; the first network element receives a first response from the network storage function network element, and the first response includes all The data analysis network element address information of the equipment manufacturer.
  • the data analysis network element of the device manufacturer will carry the association information to register with the network storage function network element in advance, and the first network element can determine the device manufacturer's data through the association information.
  • the address information of the data analysis network element so that the first network element can deliver the service experience data corresponding to the device manufacturer to the data analysis network element of the device manufacturer, so that the data analysis network element of the device can complete the service experience model training.
  • the association information corresponds to the identification information of the equipment manufacturer
  • the network storage function network element stores the identification information of the equipment manufacturer and the equipment manufacturer's identification information.
  • the correspondence between the address information of the data analysis network element, and the first network element determining the address information of the data analysis network element of the equipment manufacturer according to the association information, including: the first network element according to the association The information determines the identification information of the equipment manufacturer; the first network element sends a second request to the network storage function network element, where the second request is used to request the address information of the data analysis network element of the equipment manufacturer, the The second request includes identification information of the equipment manufacturer; the first network element receives a second response from the network storage function network element, where the second response includes address information of the data analysis network element of the equipment manufacturer.
  • the data analysis network element of the equipment manufacturer will carry the identification information of the equipment manufacturer to register with the network storage function network element in advance, and the first network element first determines the network element according to the association information.
  • the identification information of the equipment manufacturer and then determine the address information of the data analysis network element of the equipment manufacturer according to the identification information of the equipment manufacturer, so that the first network element can deliver the equipment to the data analysis network element of the equipment manufacturer.
  • the service experience data corresponding to the manufacturer enables the data analysis network element of the device to complete the training of the service experience model.
  • the first network element includes a network capability exposure function network element or an operator's data analysis network element.
  • an embodiment of the present application provides a communication method, the method includes: a data analysis network element of an equipment manufacturer obtains associated information and first network data of a service of a terminal on a core network element of the equipment manufacturer, The service is provided by the core network element of the equipment manufacturer; the data analysis network element of the equipment manufacturer determines the service of the service according to the association information and the first network data in conjunction with the data analysis network element of the operator experience the model.
  • the data analysis network element of the equipment manufacturer of the core network element can train the service corresponding to the equipment manufacturer in conjunction with the data analysis network element of the operator experience the model.
  • the method further includes: the data analysis network element of the equipment manufacturer sends a network element registration request to the network storage function network element, where the network element registration request includes the association information and/or the identification information of the equipment manufacturer.
  • the data analysis network element of the equipment manufacturer of the core network element will carry the associated information corresponding to the equipment manufacturer and/or the identification information of the equipment manufacturer to register with the network storage function network element in advance, so that The first network element can query the network storage function network element through the association information and/or the identification information of the equipment manufacturer to determine the service experience data corresponding to the equipment manufacturer, so that the service experience data of the equipment manufacturer can participate in the equipment manufacturer. Training of the corresponding business experience model.
  • the data analysis network element of the equipment manufacturer may jointly analyze the data of the operator according to the association information and the first network data.
  • the network element determining the service experience model of the service includes: the data analysis network element of the equipment manufacturer receives the association information and indication information from the data analysis network element of the operator, where the indication information is used to indicate the The data analysis network element of the equipment manufacturer performs distributed machine learning model training according to the associated information; the data analysis network element of the equipment manufacturer is determined according to the first network data of the terminal on the core network element of the equipment manufacturer A sub-model; the data analysis network element of the device manufacturer sends the sub-model to the data analysis network element of the operator, where the sub-model is used to determine the service experience model.
  • the first network data of the terminal on the core network element of the equipment manufacturer participates in the equipment manufacturer's data analysis network element on the equipment manufacturer's data analysis network element.
  • the training of the service experience model corresponding to the equipment manufacturer, the service experience data of the terminal on the application function network element participates in the training on the data analysis network element of the operator, through the distributed machine learning method, the data analysis network element of the equipment manufacturer only
  • the sub-model needs to be sent to the data analysis network element of the operator, and the first network data on the core network network element of the equipment manufacturer is avoided to be directly sent.
  • the communication method can ensure the data privacy of all parties under the premise of ensuring
  • the first network data and service experience data corresponding to the equipment manufacturer are allowed to participate in the training of the service experience model corresponding to the equipment manufacturer, thereby improving the generalization capability of the service experience model and ensuring the service experience.
  • the method for training the distributed machine learning model includes one or more of the following methods: vertical federated learning, horizontal federated learning Learning (horizontal federated learning), transfer learning (transferring learning) or shared learning (sharing learning).
  • the distributed machine learning model training method enables the private network data of the service to be retained in the local data source to participate in the training of the service experience model, which not only ensures the privacy of the data, but also ensures the data experience. The accuracy and validity of the model, thus ensuring the business experience.
  • the data analysis network element of the equipment manufacturer cooperates with the data analysis of the operator according to the association information and the first network data
  • the network element determining the service experience model of the service includes: the data analysis network element of the equipment manufacturer receives the association information and the service experience data from a first network element, where the first network element includes a network capability opening function A network element or a data analysis network element of an operator, where the service experience data is used to determine a service experience model of the service;
  • the data analysis network element of the equipment manufacturer receives the association information and the indication information from the data analysis network element of the operator, and the indication information is used to instruct the data analysis network element of the equipment manufacturer to perform a data analysis according to the association information.
  • Service experience model training; the data analysis network element of the device manufacturer determines the service experience model according to the first network data and the service experience data.
  • the data analysis network element of the equipment manufacturer can directly obtain the first network data and service experience data corresponding to the equipment manufacturer, without using a distributed machine learning method, and can be based on the first network data and service experience data.
  • the network data and the service experience data complete the training of the service experience model corresponding to the equipment manufacturer on the data analysis network element of the equipment manufacturer, which not only ensures the generalization capability of the service experience model corresponding to the equipment manufacturer, but also The training efficiency of the business experience model is improved.
  • the data analysis network element of the equipment manufacturer operates jointly according to the association information, the first network data and the second network data.
  • the data analysis network element of the manufacturer determines the service experience model of the service, and the second network data includes public network data of the service of the terminal on the core network element of the equipment manufacturer.
  • the public network data corresponding to the service also participates in the training of the service experience model, which further improves the service
  • the accuracy of the experience model enables service providers to accurately measure their service experience and effectively monitor service quality, so that service experience requirements and network resources can be accurately matched.
  • the first network data includes the private network of the service of the terminal on the core network element of the equipment manufacturer data.
  • the above sixth possible implementation manner can allow the private network data of the service to participate in the training of the service experience model on the premise of ensuring data privacy, thereby improving the generalization capability of the service experience model and ensuring the service experience.
  • the core network elements of the equipment manufacturer include one or more of the following network elements: Access and Mobility Management Function AMF Network element, session management function SMF network element, policy control PCF network element, user plane function UPF network element or unified data management UDM network element.
  • a communication apparatus in a fourth aspect, can be used to perform the operations of the communication device in the first aspect and any possible implementation manner of the first aspect.
  • the communication apparatus includes means for performing the steps or functions described in the first aspect.
  • the corresponding means may be the first communication device of the first aspect.
  • the steps or functions can be implemented by software, or by hardware, or by a combination of hardware and software.
  • a communication apparatus in a fifth aspect, can be used to perform the operation of the communication device in the second aspect and any possible implementation manner of the second aspect.
  • the apparatus may include means for performing the steps or functions described in the second aspect above.
  • the steps or functions can be implemented by software, or by hardware, or by a combination of hardware and software.
  • a communication apparatus in a sixth aspect, can be used to perform the operation of the communication device in the third aspect and any possible implementation manner of the third aspect.
  • the communication apparatus includes means for performing the steps or functions described in the third aspect.
  • the corresponding means may be the first communication device of the third aspect.
  • the steps or functions can be implemented by software, or by hardware, or by a combination of hardware and software.
  • a computer-readable medium stores a computer program (also referred to as code, or instruction), when it runs on a computer, causing the computer to execute the above-mentioned first to sixth aspects.
  • a computer program also referred to as code, or instruction
  • the method in any of the three possible implementations.
  • a chip system including a memory and a processor, the memory is used for storing a computer program, and the processor is used for calling and running the computer program from the memory, so that the communication device installed with the chip system executes the above-mentioned The method in any one possible implementation manner of the first aspect to the third aspect.
  • a chip in a ninth aspect, includes a processor and a communication interface, the communication interface is used to communicate with an external device or an internal device, and the processor is used to implement any one of the above-mentioned first to third aspects. method in the implementation.
  • the chip may further include a memory in which instructions are stored, and the processor is configured to execute the instructions stored in the memory or derived from other instructions. When the instruction is executed, the processor is configured to implement the method in any possible implementation manner of the first aspect to the third aspect.
  • the chip may be integrated on an access network device.
  • a computer program product comprising: a computer program (also referred to as code, or instructions), which, when the computer program is executed, causes a computer to execute the above-mentioned first to sixth aspects The method in any of the three possible implementations.
  • a communication device comprising: a processor and a memory, the memory is used for storing a computer program, the processor is used for calling and running the computer program from the memory, so that the communication device executes the first to the first
  • the communication method in any one possible implementation manner of the three aspects.
  • the processor is one or more, and the memory is one or more.
  • the memory may be integrated with the processor, or the memory may be provided separately from the processor.
  • a communication device in one possible design, includes a communication interface, a processor and a memory.
  • the processor is used to control the communication interface to send and receive signals
  • the memory is used to store a computer program
  • the processor is used to call and run the computer program from the memory, so that the communication device executes the first to fourth aspects or the first to third aspects method in any of the possible implementations.
  • a twelfth aspect provides a system including the above communication device.
  • the communication method and the communication apparatus can determine the equipment manufacturer information corresponding to the service experience data provided by the application function network element, so that in the scenario where the core network element crosses equipment manufacturers, the service experience of each equipment manufacturer can also be realized.
  • the training of the model also improves the accuracy of the service experience model, so that the network device can accurately measure the service experience of the service in the network, and make adaptive adjustments to the network if the service experience does not meet the requirements, so as to ensure the user's service experience. .
  • FIG. 1 is a schematic diagram of an application scenario to which the method according to the embodiment of the present application is applicable.
  • FIG. 2 is a schematic diagram of the framework of the federated learning system involved in the embodiment of the present application.
  • FIG. 3 is a schematic diagram of a manner of associating data of a terminal on each network element in an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of a service experience model training method provided by an embodiment of the present application.
  • FIG. 5 is a schematic flowchart of a service experience model training method provided by another embodiment of the present application.
  • FIG. 6 is a schematic flowchart of a service experience model training method provided by another embodiment of the present application.
  • FIG. 7 is a schematic flowchart of a service experience model training method provided by another embodiment of the present application.
  • FIG. 8 is a schematic flowchart of a service experience model training method provided by another embodiment of the present application.
  • FIG. 9 is a schematic block diagram of a communication apparatus provided by an embodiment of the present application.
  • FIG. 10 is a schematic block diagram of another communication apparatus provided by an embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • LTE long term evolution
  • FDD frequency division duplex
  • TDD time division duplex
  • UMTS universal mobile telecommunication system
  • 5th generation, 5G future fifth generation
  • 5.5th generation, 5.5G sixth generation
  • 6th generation new wireless
  • new radio new radio
  • NWDAF network data analysis function
  • the communication system includes but is not limited to the following network elements:
  • the terminal equipment in the embodiments of the present application may also be referred to as: user equipment (user equipment, UE), mobile station (mobile station, MS), mobile terminal (mobile terminal, MT), access terminal, subscriber unit, subscriber station, Mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user equipment, etc.
  • user equipment user equipment
  • MS mobile station
  • MT mobile terminal
  • access terminal subscriber unit, subscriber station, Mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user equipment, etc.
  • the terminal device may be a device that provides voice/data connectivity to the user, such as a handheld device with a wireless connection function, a vehicle-mounted device, and the like.
  • some examples of terminals are: mobile phone (mobile phone), tablet computer, notebook computer, PDA, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented Augmented reality (AR) equipment, wireless terminals in industrial control, wireless terminals in self-driving or autopilot, wireless terminals in remote medical surgery, smart grid ( Wireless terminal in smart grid), wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol Session initiation protocol (SIP) telephones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices, or other devices connected to wireless modems Processing equipment, vehicle-mounted equipment, wearable equipment, terminal equipment in the future 5G network or terminal equipment in the future evolved public land mobile network (public land mobile network, PLMN), etc.,
  • the terminal device may also be a wearable device.
  • Wearable devices can also be called wearable smart devices, which are the general term for the intelligent design of daily wear and the development of wearable devices using wearable technology, such as glasses, gloves, watches, clothing and shoes.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction.
  • wearable smart devices include full-featured, large-scale, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, and only focus on a certain type of application function, which needs to cooperate with other devices such as smart phones.
  • the terminal device may also be a terminal device in an internet of things (internet of things, IoT) system.
  • IoT internet of things
  • the terminal device may also communicate with terminal devices of other communication systems, for example, inter-device communication.
  • the terminal device may also transmit (eg, send and/or receive) time synchronization messages with terminal devices of other communication systems.
  • Radio access network (RAN)
  • a wireless access network is an access network that realizes the function of an access network based on a wireless communication technology.
  • the wireless access network can manage wireless resources, provide wireless access or air interface access services for the terminal, and then complete the forwarding of control signals and user data between the terminal and the core network.
  • the radio access network may be an evolved NodeB (evolved NodeB, eNB or eNodeB) in the LTE system, or may be a wireless controller in a cloud radio access network (cloud radio access network, CRAN) scenario , or the access device can be a relay station, an access point, a vehicle-mounted device, a wearable device, an access device in a 5G network or an access device in a future evolved PLMN network, etc., and can be an access point in a WLAN ( access point, AP), which may be a gNB in the NR system, which is not limited in this embodiment of the present application.
  • a WLAN access point, AP
  • NWDAF network data analytics function
  • the network element NWDAF has at least one of the following functions: a data collection function, a model training function, an analysis result inference function, and an analysis result feedback function.
  • the data collection function refers to the collection of data from network elements, third-party service servers, terminal equipment or network management systems
  • the model training function refers to the analysis and training based on the relevant input data to obtain a model
  • the analysis result inference function is based on the training
  • the good model and inference data are used for inference to determine the data analysis result.
  • the analysis result feedback function can provide the data analysis result to the network element, third-party service server, terminal equipment or network management system. QoS parameters, or assist the network to perform traffic routing, or assist the network to select background traffic transmission policies, etc. This application mainly involves the data collection function and model training function of NWDAF.
  • the NWDAF may be an independent network element, or may be co-located with other core network network elements.
  • the NWDAF network element may be co-located with the access and mobility management function (AMF) network element or with the session management function (session management function, SMF) network element.
  • AMF access and mobility management function
  • SMF session management function
  • NWDAF uses reliable analysis and prediction models to evaluate and analyze different types of users by collecting information such as user connection management, mobility management, session management, and accessed services. , build user portraits, determine the user's movement trajectory and service usage habits, and predict user behavior.
  • 5G networks optimize user mobility management parameters and wireless resource management parameters based on analysis and prediction data; service (path) optimization, that is, NWDAF collects information such as network performance, service load in a specific area, and user service experience, and uses reliable network performance analysis and prediction models to evaluate and analyze different types of services, build service profiles, and determine the quality of experience (QoE) of services.
  • path that is, NWDAF collects information such as network performance, service load in a specific area, and user service experience, and uses reliable network performance analysis and prediction models to evaluate and analyze different types of services, build service profiles, and determine the quality of experience (QoE) of services.
  • QoE quality of experience
  • the Internet of Vehicles is an important technology of the 5G network.
  • the prediction of the network performance (such as QoS information, business load) of the base stations that the vehicle will pass through plays an important role in improving the service quality of the Internet of Vehicles.
  • the Internet of Vehicles server can determine whether to continue to maintain the driverless mode based on the predicted information of the network performance. NWDAF collects information such as network performance and service load in a specific area, and uses reliable network performance analysis and prediction models to achieve statistics and predictions on network performance and assist AF in optimizing parameters.
  • each equipment manufacturer has its corresponding network element of the equipment manufacturer's network data analysis function.
  • Session management function network element (session management function, SMF)
  • the session management function network element is mainly used for session management, Internet Protocol (IP) address allocation and management of terminal equipment, selection of manageable user plane function (UPF) network elements, policy control and charging functions
  • IP Internet Protocol
  • UPF manageable user plane function
  • policy control and charging functions The endpoint of the interface and the downlink data notification, etc.
  • it can be used to implement the function of the session management network element.
  • Access and mobility management function network element access and mobility management function, AMF
  • the access and mobility management function network elements are mainly used for mobility management and access management, etc., and can be used to implement other functions other than session management in the mobility management entity (mobility management entity, MME) function, for example, legal Monitoring, or access authorization (or authentication) and other functions.
  • MME mobility management entity
  • the functions of the access and mobility management network elements can be implemented.
  • PCF Policy control function
  • the policy control network element is used to guide the unified policy framework of network behavior, and provides policy rule information and the like for the control plane functional network elements (such as AMF, SMF network elements, etc.).
  • Application function network element (application function, AF)
  • the application function network element is used to provide services, or to perform data routing affected by the application, to access the network open function network element, or to exchange service data with the NWDAF network element for policy control, etc.
  • User plane functional network elements can be used for packet routing and forwarding, or QoS parameter processing of user plane data.
  • User data can be accessed to a data network (DN) through this network element.
  • DN data network
  • it can be used to implement the function of the user plane network element.
  • Network storage function network element (network repository function, NRF)
  • the network storage function network element can be used to support network element services or network element discovery functions, receive NF discovery requests from network function (network function, NF) instances, and provide information about the discovered NF instances to the NF instances. and NF configuration files to support maintaining available NF instances and the services they support. In this embodiment of the present application, it can be used to support a network element service or a network element discovery function.
  • network function network function
  • Network capability exposure function Network element (network exposure function, NEF): used to open services and network capability information (such as terminal location, session reachability) provided by the 3GPP network function to the outside.
  • the N2 interface is the interface between the RAN and the AMF network element, which is used for sending radio parameters, non-access stratum (NAS) signaling, etc.
  • the N3 interface is the interface between the RAN and the UPF network element.
  • the N4 interface is the interface between the SMF network element and the UPF network element, which is used to transmit service policies, tunnel identification information of N3 connection, data buffer indication information, and downlink data notification. messages, etc.
  • the N6 interface is the interface between the DN network element and the UPF network element. It is used to transmit data on the user plane.
  • Naf is the service interface provided by AF
  • Nnrf is the service interface provided by NRF
  • Nnwdaf is the service interface provided by NWDAF.
  • the service interface provided by Nnef for NEF is the service interface provided by NEF.
  • the above-mentioned network architecture applied to the embodiments of the present application is only a network architecture described from the perspective of a traditional point-to-point architecture and a service-oriented architecture, and the network architecture applicable to the embodiments of the present application is not limited thereto. Any network architecture capable of implementing the functions of the foregoing network elements is applicable to the embodiments of the present application.
  • the name of the interface between each network element in FIG. 1 is just an example, and the name of the interface in the specific implementation may be other names, which are not specifically limited in this application.
  • the names of the messages (or signaling) transmitted between the above network elements are only an example, and do not constitute any limitation on the functions of the messages themselves.
  • network elements may also be referred to as entities, devices, devices, or modules, etc., which are not particularly limited in this application.
  • the description of network elements is omitted in some descriptions.
  • NWDAF the NWDAF network element
  • NWDAF should be understood as the NWDAF network element. The following , and the description of the same or similar situations is omitted.
  • the above-mentioned functional network elements may be network elements in hardware devices, software functions running on dedicated hardware, or virtualized functions instantiated on a platform (eg, a cloud platform).
  • each component network element is only exemplary, and not all functions of each component network element are required when applied to the embodiments of the present application.
  • the core network network elements in the above network elements are from at least two different equipment manufacturers.
  • federated learning is divided into horizontal federated learning, vertical federated learning and federated transfer learning.
  • Longitudinal federated learning is suitable for the situation where the training sample IDs of the participants overlap more and the data features overlap less.
  • longitudinal federated learning the training data of each participant is divided vertically and combined with different data features of the common samples of multiple participants for federated learning.
  • Vertical federation increases the feature dimension of training samples.
  • Horizontal federated learning is suitable for the situation where the data features of the participants overlap a lot, but the sample IDs overlap less.
  • Horizontal federated learning divides the training data of each participant horizontally and combines multiple rows with the same characteristics of multiple participants. sample for federated learning.
  • horizontal federated learning increases the total number of training samples.
  • Figure 2 is a schematic diagram of the federated learning system framework.
  • the system framework consists of two parts: encrypted sample alignment and encrypted model training. Once the shared user group is identified, the data can be used to train a machine learning model. In order to ensure the confidentiality of the data during the training process, it is necessary to use a third-party collaborator C for encrypted training. Taking the linear regression model as an example, the training process can be divided into the following four steps:
  • Step 1 the collaborator C distributes the initialized model parameters ⁇ A and ⁇ B to A and B to encrypt the data that needs to be exchanged during the training process.
  • step 2 A and B interact in encrypted form to calculate the intermediate result of the gradient.
  • the specific process is as follows:
  • ClientA has the dataset There is a dataset on ClientB, Where y i is the label data, then the model to be trained is as follows:
  • L is the loss function
  • the training method based on vertical federation is as follows:
  • model parameters are updated as follows:
  • Client A and Client B determine initialization model parameters ⁇ A and ⁇ B ;
  • Client A is calculated based on ⁇ A and L A , which is then sent to Client B;
  • Client B is calculated based on ⁇ B further based on And yi calculates di , L AB , and L B , and finally calculates L based on L A , L AB , and L B .
  • Client B sends di to Client A.
  • Step 3 A and B are calculated based on the encrypted gradient values respectively, while B calculates the loss according to its label data, and summarizes these results to C, C calculates the total gradient by summarizing the results and decrypts it.
  • Step 4 sends the decrypted gradient back to A and B respectively, and A and B update the parameters of their respective models according to the gradient.
  • the vertical federated learning method is only one of the possible training methods for realizing the training of the service experience model in the embodiment of the present application, and should not constitute any limitation to the present application.
  • This application does not exclude the definition of other models in the future or the use of other methods to achieve the ability to concentrate complete data to train a business experience model without violating data privacy regulations. As long as the methods that can achieve the same or similar functions as described above are included in this application within the scope of protection.
  • training a service experience model requires training with private network data and service experience data of the same manufacturer, and the trained service experience model is used to determine the location of the core network elements belonging to the manufacturer. Provide a business experience for the business.
  • the data participating in the training of the service experience model may also include public network data belonging to the core network element of the manufacturer.
  • the data used in the training of the above-mentioned service experience model can be for a specific service of the terminal (such as Tencent video service), or can be used for multiple services in a class of services of the terminal (such as Tencent video in the video service). , YouTube, etc.), this application does not make any restrictions on the training data used in the training process of the service experience model.
  • the training of the service experience model in the embodiment of the present application only focuses on the data in the CN domain and the data on the AF related to the core of the solution of the present application, but the data actually participating in the training of the service experience model includes UE, RAN, CN and AF.
  • the process of data in domains such as UE and RAN participating in the training of the service experience model is similar to that in the prior art.
  • the embodiments of this application omit data in domains such as UE and RAN participating in the service experience model. A specific description of the training.
  • the private network data in this embodiment of the present application includes data that cannot be reported on each network element or non-standardized data, wherein the network element may determine which data cannot be reported according to data privacy or data volume or the device manufacturer's policy described by the network element.
  • NWDAF National Air Traffic Analysis Function
  • base station equipment manufacturers may be unwilling to report private parameters of the RAN, such as energy saving parameters, positioning parameters, and radio resource management parameters, due to the protection of product interests.
  • the public network data in this embodiment of the present application includes data or standardized data that each network element can report to the NWDAF, wherein the network element can determine which data can be used according to data privacy or data volume, or the device manufacturer's policy described by the network element. Report to NWDAF.
  • the public network data reported by each network element may include the wireless signal quality reported by the RAN: reference signal received power (RSRP), reference signal received quality (RSRQ), signal and interference plus Noise ratio (signal to interference plus noise ratio, SINR); QoS-related parameters reported by UPF: flow rate (QoS flow bit rate), flow delay (QoS flow packet delay), flow packet error rate (QoS flow packet error rate) ; Service flow related parameters reported by AF: application layer cache size (buffer size) corresponding to the service flow, service experience (service experience) of the service flow.
  • RSRP reference signal received power
  • RSRQ reference signal received quality
  • SINR interference plus Noise ratio
  • QoS-related parameters reported by UPF flow rate (QoS flow bit rate), flow delay (QoS flow packet delay), flow packet error rate (QoS flow packet error rate)
  • Service flow related parameters reported by AF application layer cache size (buffer size) corresponding to the service flow, service experience (service experience) of the service flow.
  • the NWDAF needs to analyze the data on the RAN, CN and AF, it needs to logically associate the data generated on different network elements when the terminal accesses the service.
  • FIG. 3 and Table 1 show a possible way of correlating data of terminals on different network elements with each other. Specifically, the data belonging to the same terminal on every two network elements may be sequentially correlated pair by pair through different types of correlation information.
  • Table 1 Association information used to associate terminal data on two different network elements
  • the association method may be that the AF and the UPF associate the data belonging to the same terminal on the two network elements through the association information of timestamp (Timestamp) and IP address 5-tuple (IP address 5-tuple). Perform pairwise association.
  • UPF and SMF associate data belonging to the same terminal on two network elements through association information of timestamp (Timestamp) and UE IP.
  • SMF and PCF use association information as timestamp (Timestamp) and user
  • the permanent identifier (SUPI, subscription permanent identifier) associates the data belonging to the same terminal on the two network elements.
  • the data of the same terminal on the two network elements are associated with each other, and the AMF and RAN will belong to the same terminal on the two network elements through the association information such as Timestamp, RAN UE NGAP ID and RAN Global Unique ID (Global RAN Node ID).
  • the data of the terminal is associated in pairs, and the RAN and UPF associate the data belonging to the same terminal on the two network elements through the association information of timestamp (Timestamp) and AN Tunnel Info.
  • the action of correlating the data of the terminal on different network elements can be performed by the equipment manufacturer NWDAF after the equipment manufacturer NWDAF collects the data set and the corresponding association information on the core network elements of the equipment manufacturer, or can be performed by the equipment manufacturer NWDAF.
  • the operator NWDAF obtains the data set and the corresponding association information list or set on the core network element of the device manufacturer, it is executed by the operator NWDAF, and it can also be executed by other network elements with the same or similar functions.
  • This application is here. Not limited.
  • the data generated by the terminal on different network elements when accessing the service can also be logically associated in other ways, such as the association of per UE data between AMF and RAN.
  • the associated information is in addition to the above [RAN UE NGAP ID, Global RAN In addition to Node ID, Timestamp], it can also be [AMF UE NGAP ID, Global RAN Node ID, Timestamp], the association information and association sequence in the above association methods are only examples, and this application does not limit this.
  • the current 5G network lacks the establishment of the corresponding service experience model.
  • Terminal-specific private network data and public network data that can be used to train service experience models are stored locally on NEs in the core network domain.
  • NEs in the core network domain can learn their own device manufacturer information and can only report their own private network data Give the NWDAF of your own device manufacturer.
  • the service experience data used to train the model is provided by the AF, but because the AF cannot perceive the manufacturer information of the terminal's service flow through the network equipment in the network, the service experience data does not include the equipment manufacturer information corresponding to the network side. Therefore, it is necessary to consider first. How to segment the service experience data provided by AF according to the equipment manufacturer, so that the network data and service experience data belonging to the same equipment manufacturer can be collected and trained to obtain the service experience model required by the equipment manufacturer.
  • the embodiments of the present application provide a training method for a service experience model, so that the training of the service experience model can still be completed when the network elements within the core network domain are cross-vendor.
  • the embodiment of the present application first determines the equipment manufacturer information of the service experience data provided by the AF.
  • the NWDAF of each equipment manufacturer can directly obtain the service experience data corresponding to its own manufacturer, it can directly obtain the service experience data corresponding to the equipment manufacturer.
  • a third-party collaborator can be introduced to complete the training of the service experience model.
  • the private data of the core network elements of the device manufacturer is leaked.
  • machine learning methods can be used to ensure the privacy of network element data in the core network domain and the establishment of a service experience model.
  • the private network data on the core network element is only trained by the NWDAF of the local equipment manufacturer, while the service experience data can be trained by the operator.
  • the operator can participate in the training on the NWDAF of the operator. It can also be obtained by the NEF or the NWDAF of the operator and sent to the NWDAF of the equipment manufacturer to participate in the training.
  • the public network data on the core network element participates in the training, it can be The NWDAF of the local equipment manufacturer participates in the training, and the NWDAF of the equipment manufacturer can also send it to the NWDAF of the operator to participate in the training.
  • the drawings are only schematic diagrams for ease of understanding, and should not constitute any limitation to the present application.
  • the Vendor NWDAF can correspond to the data analysis function network element of the equipment manufacturer
  • the 5GC NF corresponds to the internal network element of the 5G core network domain, such as AMF, SMF, UPF, PCF, etc.
  • the NRF can correspond to the network storage function network element.
  • AF represents the application function network element
  • the operator NWDAF represents the operator's data analysis network element.
  • the names of each network element are only defined to distinguish different functions, and should not constitute any limitation to this application. This application does not exclude the possibility of defining other network elements to implement the same or similar functions.
  • FIG. 4 shows a schematic flowchart of the training method 100 of the service experience model of the present application.
  • the specific method for determining the service experience model of each equipment manufacturer includes S110 to S120, and each step is described in detail below.
  • S110 Determine device manufacturer information corresponding to the service experience data generated when the terminal uses the service.
  • the methods for determining the device manufacturer information corresponding to the service experience data include but are not limited to the following:
  • the operator NWDAF obtains the association information corresponding to the service experience data of the terminal on the AF, and the association information is used to associate the network data generated by the terminal on the core network element and the service experience data generated on the AF;
  • the operator NWDAF obtains the equipment manufacturer identification (such as Vendor ID) corresponding to the core network element and the associated information corresponding to the network data generated by the terminal on the core network element of the equipment manufacturer;
  • equipment manufacturer identification such as Vendor ID
  • the operator NWDAF associates the service experience data with the device manufacturer identifier according to the association information, so as to determine the device manufacturer information corresponding to the service experience data.
  • the NWDAF of the equipment manufacturer When the NWDAF of the equipment manufacturer registers with the NRF, it carries the associated information corresponding to the network data generated by the terminal on the core network element of the equipment manufacturer and the information of the equipment manufacturer (such as the address information of the equipment manufacturer, the manufacturer ID of the equipment manufacturer). information, etc.);
  • the operator NWDAF obtains the association information corresponding to the service experience data of the terminal on the AF, and the association information is used to associate the network data generated by the terminal on the core network element and the service experience data generated on the AF;
  • the operator NWDAF carries the association information to query the NRF for the equipment manufacturer information corresponding to the association information, so as to determine the equipment manufacturer information corresponding to the service experience data through the association information.
  • operator NWDAF may carry one or multiple pieces of associated information to query the NRF, which is not limited in this application.
  • the NWDAF of the equipment manufacturer can also communicate with other network elements with similar functions (such as the data collection coordination function (DCCF) and the data repository function, DRF), etc.) when registering, carry the associated information corresponding to the network data generated on the core network element of the equipment manufacturer when the terminal uses the service, correspondingly, the operator NWDAF carries the associated information to the network element with similar functions (such as The data collection coordination function network element DCCF and the data storage function network element DRF, etc.) query the equipment manufacturer information corresponding to the associated information, which is not limited in this application.
  • DCCF data collection coordination function
  • DRF data repository function
  • the DCCF is responsible for coordinating the NWDAF to collect data of the terminal on the core network element corresponding to the equipment manufacturer, and the DRF is used to store the data of the terminal on the core network element corresponding to the equipment manufacturer.
  • the DCCF or DRF can be deployed in the NWDAF as an internal logical function of the NWDAF.
  • the NWDAF of the equipment manufacturer When the NWDAF of the equipment manufacturer registers with the NRF, it carries the associated information corresponding to the network data of the terminal on the core network element of the equipment manufacturer;
  • the NEF obtains the association information corresponding to the service experience data of the terminal on the AF, and the association information is used to associate the data of the terminal on the core network element and the service experience data;
  • the NEF carries the association information to query the NRF for the device manufacturer information corresponding to the association information.
  • the NEF may query the NRF with one or multiple pieces of associated information, which is not limited in this application.
  • the NWDAF of the equipment manufacturer can also communicate with other network elements with similar functions (such as the data collection coordination function (DCCF) and the data repository function, DRF), etc.) when registering, carry the association information corresponding to the network data generated on the core network element of the equipment manufacturer when the terminal uses the service.
  • the NEF can carry the association information to the network element with similar functions (such as data Collect and coordinate function network element DCCF and data storage function network element DRF, etc.) to query the equipment manufacturer information corresponding to the associated information, which is not limited in this application.
  • the DCCF is responsible for coordinating the NWDAF to collect data of the terminal on the core network element corresponding to the equipment manufacturer, and the DRF is used to store the data of the terminal on the core network element corresponding to the equipment manufacturer.
  • the DCCF or DRF can be deployed in the NWDAF as an internal logical function of the NWDAF.
  • other network elements with similar functions can also obtain the service experience data set of the service of the terminal on the AF and determine the equipment manufacturer information corresponding to each service experience data in the service experience data set, This application is not limited here.
  • network data of the equipment manufacturer or “the network data on the core network element of the equipment manufacturer” in the following description can be understood as being generated on the core network element of the equipment manufacturer when the terminal uses the service.
  • the network data wherein the network data includes private network data and/or public network data.
  • service experience data corresponding to the equipment manufacturer in the description below can be understood as the service experience data corresponding to the manufacturer's equipment on the application function network element when the core network element of the manufacturer's equipment provides services for the terminal. .
  • service experience model of the equipment manufacturer in the following description can be understood as the service experience model corresponding to the equipment manufacturer when the core network element of the manufacturer's equipment provides services for the terminal.
  • terminal used in this application may refer to a same terminal or a plurality of different terminals, which is not limited in this application.
  • the methods for training the service experience model of the equipment manufacturer by combining the network data of the core network elements of the equipment manufacturer and the service experience data corresponding to the equipment manufacturer include but are not limited to the following:
  • the equipment manufacturer's NWDAF collects the private network data of the equipment manufacturer's core network elements
  • the operator NWDAF obtains the service experience data of the device manufacturer from the AF;
  • the operator NWDAF determines the address information of the device manufacturer's NWDAF
  • the operator NWDAF and the NWDAF of the equipment manufacturer determine the service experience model of the equipment manufacturer through training based on the private network data of the core network elements of the equipment manufacturer and the service experience data corresponding to the equipment manufacturer.
  • the operator NWDAF may also cooperate with the NWDAF of the equipment manufacturer to determine the service experience model of the equipment manufacturer based on the private network data, public network data and service experience data of the core network elements of the equipment manufacturer.
  • the public network data of the equipment manufacturer's core network element can be sent by the equipment manufacturer's core network element to the operator NWDAF, and the operator can participate in training on the operator NWDAF; it can also be sent by the equipment manufacturer's core network element.
  • the NWDAF of the equipment manufacturer will then send it to the NWDAF of the operator, and participate in the training on the NWDAF of the operator; it can also be sent by the core network element of the equipment manufacturer to the NWDAF of the equipment manufacturer, and the NWDAF of the equipment manufacturer can be sent to the NWDAF of the equipment manufacturer.
  • the manufacturer's NWDAF participates locally in the training.
  • the public network data of the core network element of the equipment manufacturer can be displayed in the method A of S110.
  • the operator NWDAF obtains the equipment vendor ID Vendor ID of each equipment manufacturer's core network element and the associated information corresponding to the network data of each equipment manufacturer's core network element, and obtains it at the same time to save a certain amount of resource overhead.
  • the equipment manufacturer's NWDAF collects the private network data of the equipment manufacturer's core network elements
  • the NWDAF of the equipment manufacturer obtains the service experience data corresponding to the equipment manufacturer
  • the NWDAF of the equipment manufacturer determines the service experience model of the equipment manufacturer according to the private network data of the core network elements of the equipment manufacturer and the service experience data corresponding to the equipment manufacturer.
  • the manner in which the device manufacturer's NWDAF obtains the service experience data corresponding to the device manufacturer includes, but is not limited to, the NEF sending the device manufacturer's service experience data to the device manufacturer's NWDAF (wherein the device manufacturer on the NEF The service experience data of the device manufacturer comes from the AF), or the operator NWDAF sends the service experience data of the device manufacturer to the NWDAF of the device manufacturer.
  • the NWDAF of the equipment manufacturer may also train and determine the service of the equipment manufacturer according to the private network data and public network data of the core network elements of the equipment manufacturer and the service experience data corresponding to the equipment manufacturer experience the model.
  • the method 2 should also include that the NWDAF of the equipment manufacturer collects the public network data of the core network elements of the equipment manufacturer.
  • the data analysis network element NWDAF includes the data analysis network element NWDAF of the operator and the data analysis network element NWDAF of the core network element equipment manufacturer.
  • the cross-manufacturers of the internal network elements in the core network domain may cross two equipment manufacturers, or may cross multiple equipment manufacturers. This is an example and not a limitation.
  • the core network network elements belong to two equipment manufacturers as an example. ,Be explained.
  • the NWDAF of a device manufacturer cannot directly obtain the service experience data corresponding to the manufacturer, a third-party collaborator can be introduced to cooperate with the training of the service experience model.
  • the third-party collaborator can be the operator NWDAF. .
  • the following will take the operator NWDAF as an example for detailed description.
  • FIG. 5 shows a schematic flowchart of a method 200 for acquiring a service experience model according to the first specific embodiment of the present application.
  • the specific determination method includes S201a to S204, and then combine the network data of the core network elements of the equipment manufacturer and the corresponding service experience data to train the equipment.
  • the specific training steps include S205a to S207, and each step is described in detail below.
  • the operator NWDAF sends request information #a to the AF, and subscribes the service experience data of the terminal to the AF and associated information corresponding to the service experience data.
  • Event ID Service Experience (Service Experience)
  • Event Filter application
  • the identifier or service identifier is used to subscribe the service experience data of the service identified by the Application ID to the AF, and subscribe to the service experience data of the terminal and the associated information corresponding to the service experience data to the AF.
  • the operator NWDAF can subscribe to the AF for one terminal service experience data and the associated information corresponding to the service experience data, and can also subscribe to the AF for multiple terminal service experience data and the associated information corresponding to the service experience data set at the same time. This application is not limited here.
  • the above-mentioned service experience data may specifically include one or more service experience data, wherein one service experience data corresponds to one associated information, where one service experience data may correspond to a service generated by a terminal accessing a certain service.
  • the experience data may also correspond to service experience data generated in a type of service (including multiple services) accessed by a terminal, which is not limited in this application.
  • the service experience data may include the service experience and/or the location of the terminal when the terminal uses the service at a specific timestamp (timestamp), where the service experience may be one or more of the following types: Mean Opinion Score (mean opinion score, MOS), loopback delay (round trip time, RTT), bandwidth (bandwidth), jitter (jitter), etc.
  • Mean Opinion Score mean opinion score, MOS
  • loopback delay round trip time, RTT
  • bandwidth bandwidth
  • jitter jitter
  • the AF sends reply information #a to the operator NWDAF, where the reply information #a includes service experience data subscribed by the operator NWDAF and associated information corresponding to the service experience data set.
  • the AF triggers the event opening notification (Naf_EventExposure_Notify) service operation on the Naf interface of the operator NWDAF, and sends the service experience data of the terminal and the association corresponding to the service experience data to the operator NWDAF information.
  • Naf_EventExposure_Notify the event opening notification
  • association information is used to associate the service experience data generated on the AF by a certain terminal when accessing the service and the network data on the core network element, and the service experience data and the network data correspond to the same device.
  • the association information can first associate the service experience data generated on the AF by a certain terminal when accessing the service with the network data generated on the UPF.
  • the association information can include: Timestamp (Timestamp) and IP quintuple (IP address 5-tuple), and then associate the data on SMF, AMF or AN according to the method described above.
  • the operator NWDAF sends the request information #b1 to the 5GC NF#1 of the equipment manufacturer #1, and subscribes to the 5GC NF#1 of the equipment manufacturer #1 for the public network data #1 on the network element of the equipment manufacturer and the public network
  • the operator NWDAF triggers the event open subscription (Nnf_EventExposure_Subscribe) service operation on the Nnf interface of 5GC NF#1, and subscribes to the 5GC NF#1 of equipment manufacturer #1 to belong to the equipment manufacturer.
  • 5GC NF#1 sends reply message #b1 to operator NWDAF, and reply message #b1 includes public network data #1 subscribed by operator NWDAF, associated information #1 of terminal information corresponding to public network data #1, and 5GC NF Device Vendor ID #1 for #1.
  • the 5GC NF#1 triggers the event open notification (Nnf_EventExposure_Notify) service operation on the Nnf interface of the operator NWDAF, and sends the public network data subscribed by the operator NWDAF in step S202a to the operator NWDAF #1.
  • the associated information #1 corresponding to the public network data #1 and the equipment manufacturer ID #1 of the 5GC NF#1.
  • the NWDAF of device manufacturer #1 collects private network data on each network element from 5GC NF#1.
  • Vendor NWDAF#1 triggers the event open subscription (Nnf_EventExposure_Subscribe) service operation on the Nnf interface of 5GC NF#1, and subscribes to 5GC NF1 for private network data on the core network element of equipment manufacturer #1 and the corresponding associated information.
  • 5GC NF#1 triggers the event open notification (Nnf_EventExposure_Notify) service operation on the Nnf interface of Vendor NWDAF#1, and sends the public network data and private network data of each terminal and the corresponding associated information to Vendor NWDAF#1.
  • Vendor NWDAF#1 can subscribe to 5GC NF#1 for private network data and corresponding associated information of a terminal, and can also subscribe to 5GC NF#1 for private network data and corresponding associated information of multiple terminals at the same time. It is not limited in the application examples.
  • association information corresponding to the data of different network elements in 5GC NF may be different.
  • Figure 3 or Table 1 shows a possible correspondence between the network element data and the association information.
  • the associated information may include: timestamp Timestamp and IP quintuple IP address 5-tuple.
  • the NWDAF of the equipment manufacturer #1 may also collect private network data on the core network elements of the equipment manufacturer #1 through other methods (such as hardware probes).
  • the device manufacturer NWDAF#1 carries the vendor ID Vendor ID to which it belongs to register with the NRF.
  • the device manufacturer NWDAF#1 registers with the NRF, and the device manufacturer NWDAF#1 carries the registration information to trigger the network element registration request (Nnrf_NFManagement_NFRegister_request) service operation in the network element management of the Nnrf interface, and initiates a registration request to the NRF, and the registration information Including the Vendor ID of the device manufacturer NWDAF.
  • the NRF stores the registration information of the device manufacturer NWDAF.
  • the NRF triggers the service operation of the network element registration response (Nnrf_NFManagement_NFRegister_response) in the network element management of the Nnrf interface to send a reply to the equipment manufacturer NWDAF#1 message, the registration was successful.
  • the registration service operation Nnrf interface network element management in the network element registration request includes the equipment manufacturer's NWD AF NF network element information (NFProfile), that is, the NWDAF network element Information (NWDAF Profile), in which the NF Profile needs to carry other basic information in addition to the vendor ID to which it belongs, such as one or more of the following information corresponding to the device manufacturer NWDAF: network element type, address information, service Areas, analysis identifiers, Analytics ID, etc., are similar to those in the prior art, and will not be repeated here.
  • NFProfile equipment manufacturer's NWD AF NF network element information
  • NWDAF Network element Information NWDAF network element Information
  • NWDAF Profile NWDAF network element Information
  • the NF Profile needs to carry other basic information in addition to the vendor ID to which it belongs, such as one or more of the following information corresponding to the device manufacturer NWDAF: network element type, address information, service Areas, analysis identifiers, Analytics ID, etc.
  • Steps S203a to S203d are actions related to the device manufacturer NWDAF#2. For specific steps, reference may be made to the descriptions in steps S202a to S202d, which will not be repeated here.
  • the operator NWDAF associates the service experience data corresponding to the association information with the device manufacturer identification, thereby determining the device manufacturer identification of each service experience data, and associates the service experience data corresponding to the association information with the public network data, thereby Determine the data set belonging to equipment manufacturer #1, the data set includes service experience data #1, public network data #1, associated information #1 corresponding to public network data #1, equipment manufacturer ID Vendor ID #1, and equipment manufacturer # 2, the data set includes service experience data #2, public network data #2, associated information #2 corresponding to public network data #2, and equipment manufacturer ID Vendor ID #2.
  • FIG. 3 a possible way to correlate service experience data and public network data belonging to the same equipment manufacturer and the same terminal is shown in Figure 3 and Table 1. It may be that the operator NWDAF obtains the public network data on the 5GC NF and the corresponding After the association information, the operator NWDAF first associates the service experience data from AF with the public network data from UPF according to the association information of Timestamp, IP address 5-tuple, and then according to Timestamp, the association information of UE IP will be from UPF.
  • the public network data is associated with the public network data from SMF, and then according to the association information of Timestamp and SUPI, the public network data from SMF is associated with the public network data from AMF, and the public network data from SMF is associated with the public network data from PCF.
  • the public network data is associated, and then the public network data from the AMF is associated with the public network data from the RAN according to the association information of Timestamp, RAN UE NGAP ID and RAN global unique identifier Global RAN Node ID. According to Timestamp, AN Tunnel Info The association information associates public network data from the RAN with public network data from the UPF.
  • the operator NWDAF directly trains the service experience model based on the public network data of the core network elements of each equipment manufacturer and the service experience data corresponding to the equipment manufacturer, the generalization ability of the obtained service experience model is poor.
  • the private network data of each equipment manufacturer is required to participate in the training of the model.
  • the operator NWDAF cannot directly obtain the private network data of each equipment manufacturer, but the NWDAF of the equipment manufacturer can.
  • the embodiment of this application adopts the vertical federation method to let the operator NWDAF cooperate with the NWDAF of the equipment manufacturer, so that the private network data of the equipment manufacturer is kept locally in the NWDAF of the equipment manufacturer Participate in model training to improve the generalization ability or model performance of the business experience model.
  • the vertical federation method is only an example training method in the embodiment of the present application, and the training method used in the embodiment of the present application may also be named by other names, as long as it is possible to combine all parties on the premise of protecting the privacy of all parties
  • the data training service experience model is within the scope of protection of this application.
  • the operator NWDAF sends request information #c to the NRF, and queries the NRF for the address of the equipment manufacturer NWDAF, where the request information #c includes the vendor ID of the equipment manufacturer.
  • the operator NWDAF triggers the Nnrf interface network element discovery request (Nnrf_NFDiscovery_Request) service operation, and sends request information #c to the NRF, where the request information #c includes the vendor ID of the equipment manufacturer. , and query the NRF for the address of the device manufacturer NWDAF corresponding to the vendor ID Vendor ID.
  • Nnrf_NFDiscovery_Request Nnrf interface network element discovery request
  • the request information #c may include the Vendor ID of one equipment manufacturer, and may also include the Vendor IDs of multiple equipment manufacturers at the same time (used to request the equipment manufacturer NWDAF corresponding to the Vendor ID of each manufacturer). address), which is not limited in this embodiment of the present application.
  • the NRF sends reply information #c to the operator NWDAF, where the reply information #c includes the address of the equipment manufacturer NWDAF corresponding to the manufacturer identifier Vendor ID of the equipment manufacturer.
  • the NRF triggers the Nnrf interface surfing element discovery request response (Nnrf_NFDiscovery_RequestResponse) service operation, and sends reply information #c to the operator NWDAF, where the reply information #c includes the equipment manufacturer identifier Vendor ID corresponding to the The address of the device manufacturer NWDAF Vendor NWDAF ID.
  • Nnrf_NFDiscovery_RequestResponse the Nnrf interface surfing element discovery request response
  • the manner in which the operator NWDAF obtains the address information of the equipment manufacturer NWDAF may also be, in steps S202b and S203b, when the core network element of the equipment manufacturer sends data to the operator NWDAF, it also carries the The address of the device manufacturer's NWDAF.
  • LiR linear regression
  • the operator NWDAF sends an initial federated learning parameter distribution (Initial Federated Learning parameters provisioning) message to the device manufacturer NWDAF#1 to the Vendor NWDAF to trigger the vertical federated learning training process.
  • initial federated learning parameter distribution Initial Federated Learning parameters provisioning
  • the Initial Federated Learning parameters provisioning message includes algorithm identification information and a list of association information.
  • the association information list is used to determine the data set participating in model training.
  • the association information can be association information between AF and UPF, that is, IP Quintuple and timestamp.
  • the message also includes the longitudinal federation training dataset
  • the equipment manufacturer NWDAF receives the above message sent by the operator NWDAF, and initializes the model parameters according to the calculate And send it to the operator NWDAF through the machine learning model update notification (Nnwdaf_MLModelUpdate_Notify) service operation on the Nnwdaf interface and an association information list, which is used to associate With the training data belonging to equipment manufacturer #1 on the operator NWDAF;
  • Nnwdaf_MLModelUpdate_Notify machine learning model update notification
  • the training data belonging to equipment manufacturer #1 on the operator NWDAF includes service experience data and public network data corresponding to equipment manufacturer #1.
  • x i represents the ith sample data, where is the public network data distributed on CN in the sample data, is the private network data distributed on CN in the sample data, ⁇ A and ⁇ B are respectively and the corresponding model parameters.
  • h(x) is based on data And the model parameters ⁇ A and ⁇ B calculation results.
  • the operator NWDAF updates the model parameters ⁇ A according to the residual d i , and the specific update process is as follows:
  • the operator NWDAF sends the residuals di and Corresponding association information to assist the update of local model parameters ⁇ B , this association information is used to associate the residual d i with the data set on the equipment manufacturer NWDAF#1
  • the specific update process is as follows:
  • the device manufacturer NWDAF receives and updates the model parameter ⁇ B according to the residual d i , and sends the updated intermediate result to the operator NWDAF with the association information list, which is used to associate the updated intermediate results With the training data belonging to equipment manufacturer #1 on the operator NWDAF;
  • the operator NWDAF receives the updated intermediate result and the associated information list, and determine whether the training end condition of the service experience model is met. If the training end condition is met, the operator NWDAF determines the final service experience model and ends the training process; if the training end condition is not met, repeat the above training steps until training. Finish.
  • model parameters ⁇ A and ⁇ B are model parameter vectors.
  • each model parameter vector may include one or more model parameters.
  • condition for ending the training of the service experience model may be set in advance by the operator NWDAF.
  • the number of model parameter iterations reaches a certain threshold, for example, the number of model parameter iterations reaches 10,000, or it may be a loss.
  • the function L(eg based on the updated intermediate result as well as ) is less than a certain threshold, for example, the value of the loss function is less than 0.001.
  • the model training termination can be set by the equipment manufacturer NWDAF, and the equipment manufacturer NWDAF does not need to send the updated intermediate results to the operator NWDAF. With the list of related information, you can judge whether the model training is terminated or not.
  • step S207 may also be performed, the operator NWDAF will The model parameters of the public network data or the model parameter gradients of the public network data in the service experience model trained by the manufacturer are trained horizontally, so that the model parameters of different equipment manufacturers for the public network data are unified, and the model parameters of the public network data are further improved.
  • the NWDAF of each equipment manufacturer carries the equipment manufacturer identification to register with the NRF in advance; the operator NWDAF associates the service experience data provided by the AF with the Vendor ID provided by the core network element according to the same association information , so as to determine the equipment manufacturer information of each service experience data; the operator NWDAF then inquires the NRF for the Vendor NWDAF ID corresponding to the equipment manufacturer identification according to the equipment manufacturer identification sent by the core network element, and then combines the NWDAF of different equipment manufacturers respectively. , perform vertical federation training based on the network side data and service experience data of each equipment manufacturer, and train the service experience models of different equipment manufacturers respectively.
  • the model parameters of the public network data in the service experience model are calculated and updated on the operator NWDAF by the operator NWDAF after it obtains the public network data from the equipment manufacturer's core network network element, and in another In this possible implementation manner, the model parameters of the public network data can also be calculated and updated on the equipment manufacturer NWDAF after the public network data is collected by the equipment manufacturer's own NWDAF from the equipment manufacturer's core network element.
  • the specific determination methods include S301a to S305, and then combine the network data of each equipment manufacturer's core network elements and the corresponding service experience data for training
  • the specific training steps for the service experience model of each equipment manufacturer include S306 to S308, and each step is described in detail below.
  • Steps S301a-S301b are the same as steps S201a-S201b in the first embodiment, and are not repeated here.
  • the NWDAF of the equipment manufacturer #1 sends the request information #b1 to the 5GC NF#1 of the equipment manufacturer #1, and subscribes the public network data and private network data of the equipment manufacturer #1 and the corresponding association information to the 5GC NF#1.
  • the information is used to identify the public network data and the private network data.
  • Vendor NWDAF#1 triggers an event open subscription (Nnf_EventExposure_Subscribe) service operation on the Nnf interface of 5GC NF#1, and subscribes to 5GC NF#1 for the public network data and data corresponding to each terminal. Private network data and corresponding associated information.
  • Nnf_EventExposure_Subscribe an event open subscription
  • Vendor NWDAF#1 can subscribe to 5GC NF#1 for public network data and private network data corresponding to one terminal and corresponding associated information, and can also subscribe to 5GC NF#1 for public network data and private network data corresponding to multiple terminals at the same time.
  • the network data and the corresponding associated information are not limited in the embodiments of the present application.
  • the 5GC NF#1 of equipment manufacturer #1 sends reply information #b1 to the NWDAF of equipment manufacturer #1, and the reply information #b1 includes the public network data and private network data of equipment manufacturer #1 and the corresponding association information.
  • the information is used to identify the terminal information of the public network data and the private network data.
  • 5GC NF#1 triggers the event open notification (Nnf_EventExposure_Notify) service operation on the Nnf interface of Vendor NWDAF#1, and sends the public network data and private data of each terminal to Vendor NWDAF#1 Network data and corresponding associated information.
  • Nnf_EventExposure_Notify the event open notification
  • association information corresponding to the data of different network elements in 5GC NF may be different.
  • Figure 3 and Table 1 show a possible correspondence between the network element data and the association information.
  • the associated information may include: timestamp Timestamp and IP quintuple IP address 5-tuple.
  • the NWDAF of the equipment manufacturer #1 may also collect private network data on the core network elements of the equipment manufacturer #1 through other methods (such as hardware probes).
  • the NWDAF of the equipment manufacturer #1 carries the association information corresponding to the data on the core network element of the equipment manufacturer #1 to register with the NRF.
  • the device manufacturer NWDAF can register with the NRF in a manner that the device manufacturer NWDAF carries the registration information to trigger the network element registration request (Nnrf_NFManagement_NFRegister_request) service operation in the Internet element management of the Nnrf interface, and initiates a registration request to the NRF, and the registration information includes the equipment manufacturer
  • the NRF stores the registration information of the equipment manufacturer NWDAF after receiving the registration request, and the NRF triggers the service operation of the network element registration response (Nnrf_NFManagement_NFRegister_response) in the network element management of the Nnrf interface to the equipment manufacturer NWDAF
  • a reply message is sent, and the registration is successful.
  • NFProfile network element information, such as equipment manufacturer NWDAF). address
  • S303a-S303c is the process in which the NWDAF of the equipment manufacturer #2 collects the public network data and private network data and the corresponding associated information corresponding to the terminal from the 5GC NF#2 of the equipment manufacturer #2, and registers with the NRF, please refer to steps S302a- S302c, I won't go into details here
  • the operator NWDAF sends request information #c to the NRF, and queries the NRF for the Vendor NWDAF ID (Vendor NWDAF identifier, or the address information of the Vendor NWDAF) corresponding to the associated information, and the request information #c includes the services collected by the operator NWDAF The associated information corresponding to the experience data.
  • Vendor NWDAF ID Vendor NWDAF identifier, or the address information of the Vendor NWDAF
  • the request information #c includes the services collected by the operator NWDAF The associated information corresponding to the experience data.
  • one service experience data corresponds to one associated information
  • the operator NWDAF can request the NRF to query the Vendor NWDAF ID corresponding to one associated information, and can also request to query the Vendor NWDAF ID corresponding to multiple associated information at the same time.
  • This application is here. Not limited.
  • the operator NWDAF triggers the Nnrf interface network element discovery request (Nnrf_NFDiscovery_Request) service operation, sends the request information #c to the NRF, and requests the NRF to query the Vendor NWDAF ID corresponding to each associated information,
  • the request information #c includes the associated information of the service experience data collected by the operator NWDAF, namely Timestamp and IP address 5-tuple.
  • the NRF sends reply information #c to the operator NWDAF, where the reply information #c includes the Vendor NWDAF ID corresponding to the associated information.
  • the NRF triggers the Nnrf interface surfing element discovery response (Nnrf_NFD discovery_RequestResponse) service operation, and sends reply information #c to the operator NWDAF, where the reply information #c includes the corresponding information corresponding to each associated information. Vendor NWDAF ID.
  • the operator NWDAF determines the device manufacturer information of the service experience data according to the association information, thereby determining the service experience data of the device manufacturer #1 and the service experience data of the device manufacturer #2.
  • the operator NWDAF currently obtains the service experience data of equipment manufacturer #1 and equipment manufacturer #2, and the Vendor NWDAF currently obtains the private network data and public network data of its corresponding equipment manufacturer.
  • the device manufacturer's private network data, public network data and service experience data can be combined to participate in the training of the service experience model corresponding to the device manufacturer.
  • the operator NWDAF cannot directly Obtain the private network data corresponding to the device manufacturer.
  • the embodiment of this application adopts the vertical federation method to let the operator NWDAF cooperate with the NWDAF of the device manufacturer, so that the private network data of the device manufacturer is retained in the device manufacturer NWDAF to participate in the device locally. Training of the business experience model corresponding to the manufacturer to improve the generalization ability of the business experience model.
  • the vertical federation method is only an example training method in the embodiment of the present application, and the training method used in the embodiment of the present application may also be named by other names, as long as it is possible to combine all parties on the premise of protecting the privacy of all parties
  • the data training service experience model is within the scope of protection of this application.
  • the public network data of equipment manufacturer #1 is used. 1 is the dataset Take the private network data #1 of device manufacturer #1 as the data set Taking the service experience data #1 of equipment manufacturer #1 as the data yi and the service experience model as the linear regression model as an example, the training process is introduced:
  • the business experience models that need to be trained are as follows:
  • x i represents the ith sample data, where is the public network data distributed on CN in the sample data, is the private network data distributed on CN in the sample data, ⁇ A and ⁇ B are respectively and the corresponding model parameters.
  • the operator NWDAF sends an initial federated learning parameter provisioning (Initial Federated Learning parameters provisioning) message to the device manufacturer NWDAF#1 to the Vendor NWDAF to trigger the vertical federated learning training process.
  • initial federated learning parameter provisioning Initial Federated Learning parameters provisioning
  • the Initial Federated Learning parameters provisioning message includes algorithm identification information and an association information list, and the association information list is used to determine the data set participating in the model training, that is, specifically, the association information can be the association information between AF and UPF, Namely IP quintuple and timestamp.
  • the algorithm identifier is used to determine the algorithm used in longitudinal federated learning, such as linear regression, neural network, etc.
  • the algorithm information also includes a data set and dataset
  • the equipment manufacturer NWDAF receives the above message sent by the operator NWDAF, and initializes the model parameters according to the and calculate and And send it to the operator NWDAF through the machine learning model update notification (Nnwdaf_MLModelUpdate_Notify) service operation on the Nnwdaf interface and an association information list, which is used to associate Business experience data with equipment manufacturer #1;
  • Nnwdaf_MLModelUpdate_Notify machine learning model update notification
  • the operator NWDAF sends the residual d i and the associated information list to the equipment manufacturer NWDAF through the machine learning model update notification (Nnwdaf_MLModelUpdate_Notify) service operation on the Nnwdaf interface.
  • the associated information list is used to associate the residual d i with the network side of the equipment manufacturer #1 data;
  • the equipment manufacturer NWDAF receives and updates the model parameters of ⁇ A and ⁇ B according to the residual d i .
  • the specific update process is as follows:
  • the device manufacturer NWDAF sends the updated intermediate result to the operator NWDAF through the machine learning model update notification (Nnwdaf_MLModelUpdate_Notify) service operation on the Nnwdaf interface with the association information list, which is used to associate the updated intermediate results With the training data belonging to equipment manufacturer #1 on the operator NWDAF
  • the device manufacturer NWDAF may also send the model parameter gradient corresponding to the model parameter ⁇ A , the number of samples and the corresponding association information list to the operator NWDAF, so that the operator NWDAF can correlate public network data with the operator NWDAF.
  • the association information list is used to associate the model parameter gradient, number of samples and equipment manufacturer #1 corresponding to ⁇ A ;
  • the operator NWDAF receives the updated intermediate result and intermediate results computed locally And judge whether the end condition of business experience model training is reached. If the training end condition is met, the operator NWDAF determines the final service experience model and ends the training process; if the training end condition is not met, repeat the above training steps until the training is completed;
  • model parameters ⁇ A and ⁇ B are model parameter vectors.
  • each model parameter vector may include one or more model parameters.
  • condition for ending the training of the service experience model may be set in advance by the operator NWDAF.
  • the number of model parameter iterations reaches a certain threshold, for example, the number of model parameter iterations reaches 10,000, or it may be a loss.
  • the function L(eg based on the updated intermediate result as well as ) is less than a certain threshold, for example, the value of the loss function is less than 0.001.
  • the model training termination can be set by the equipment manufacturer NWDAF, and the equipment manufacturer NWDAF does not need to send the updated intermediate results to the operator NWDAF. With the list of related information, you can judge whether the model training is terminated or not.
  • the above specific steps are only examples of the first iteration process.
  • the data sent by the operator NWDAF to the equipment manufacturer NWDAF in S306a is updated after the last iteration.
  • the model parameters are determined.
  • steps S307 to S308 may also be performed, the operator NWDAF performs the model parameters or model parameters of the public network data in the service experience model trained by each equipment manufacturer.
  • the model parameter gradient of the public network data is horizontally federated, so that the model parameters of different equipment manufacturers for the public network data are unified, and the generalization ability of the model parameters of the public network data is further improved.
  • the operator NWDAF performs horizontal federation training on the model parameters of the public network data or the model parameter gradients of the public network data in the service experience models trained by different device manufacturers.
  • horizontal federation training for model parameter gradients of public network data is an optional step. The purpose is to unify the model parameters of different equipment manufacturers for public network data and further improve the generalization ability of model parameters of public network data. .
  • the operator NWDAF sends a processing parameter #d to the NWDAF of each device manufacturer, where the processing parameter #d is a parameter obtained by the operator NWDAF performing horizontal federation of model parameters of public network data or model parameter gradients of public network data.
  • the Vendor NWDAF carries the association information corresponding to the network side data of each device manufacturer to register with the NRF in advance, so the operator NWDAF can query the NRF for the association according to the association information corresponding to the service experience data sent by the AF
  • the Vendor NWDAF ID corresponding to the information, so as to determine the equipment manufacturer information of each service experience data, and then the operator NWDAF will combine the NWDAF of different equipment manufacturers respectively, and conduct vertical federation training based on the network side data and service experience data of each equipment manufacturer.
  • the service experience models of different equipment manufacturers are trained separately.
  • the operator NWDAF after the operator NWDAF determines the device manufacturer information of the service experience data, it will be retained in the operator NWDAF to participate in the training of the service experience model locally, as an example and not a limitation.
  • the operator NWDAF after determining the equipment manufacturer information of the service experience data, the operator NWDAF can also directly send the service experience data corresponding to the equipment manufacturer to the Vendor NWDAF, and the equipment manufacturer can also send the public network data corresponding to the equipment manufacturer. and private network data, and directly train the service experience model in the device manufacturer's Vendor NWDAF.
  • FIG. 7 shows a schematic flowchart of a method 400 for acquiring a service experience model according to another specific embodiment of the present application.
  • the specific determination methods include S401a to S405, and then combine the network data of each equipment manufacturer's core network element and the corresponding service experience data for training
  • the specific training steps for the service experience model of each equipment manufacturer include S406a to S410, and each step is described in detail below.
  • the method for determining the device manufacturer information of the service experience data may also refer to the determination method in the first embodiment, or other methods for associating the service experience data with the device manufacturer information may be implemented.
  • the application is not limited here.
  • the operator NWDAF sends a training parameter #d1 to the Vendor NWDAF#1, where the training parameter #d1 includes service experience data #1 corresponding to the device manufacturer #1 and associated information #1 corresponding to the service experience data #1.
  • the operator NWDAF sends a training parameter #d2 to the Vendor NWDAF#2, where the training parameter #d2 includes service experience data #2 corresponding to the equipment manufacturer #2 and associated information #2 corresponding to the service experience data #2.
  • the operator NWDAF determines the equipment manufacturer information of the service experience data and sends each service experience data to the corresponding equipment manufacturer's NWDAF, and participates in the service experience model training on the equipment manufacturer's NWDAF.
  • each equipment manufacturer NWDAF has obtained the network data on its own core network elements and the service experience data corresponding to its own equipment manufacturer, so it is not necessary to introduce the vertical federation training method.
  • the equipment manufacturer NWDAF is based on the core network corresponding to the equipment manufacturer.
  • the network data on the network element and the corresponding service experience data are used to train the service experience model.
  • the service experience model training processes S407a and S407b are similar to those in the prior art, and are not repeated here.
  • the operator NWDAF may also perform steps S408a to S410 to perform horizontal federation training on the model parameters of the public network data or the model parameter gradients of the public network data in the service experience models of each device manufacturer, so that different Equipment manufacturers unify the model parameters of public network data to further improve the generalization ability of model parameters of public network data.
  • steps S406a and S406b further include that the operator NWDAF sends an initial federated learning parameter distribution (Initial Federated Learning parameters provisioning) message to Vendor NWDAF#1 and Vendor NWDAF#2 to trigger the horizontal federated learning training process.
  • the message includes the identification of the algorithm and the data type list information of the public data participating in the training.
  • steps S407a and S407b further include the local public data corresponding to the data type list based on the public data of each Vendor NWDAF Perform model training, determine the size of the local training dataset n I and the gradient value of the local model training
  • each Vendor NWDAF sends the local training data set size n I and the gradient value of the local model training through the machine learning model update notification (Nnwdaf_MLModelUpdate_Notify) service on the Nnwdaf interface to the operator NWDAF.
  • Nnwdaf_MLModelUpdate_Notify machine learning model update notification
  • the operator NWDAF performs weighted aggregation on the local model gradient values reported by each Vendor NWDAF, as follows:
  • the operator NWDAF sends the processing parameter #f to the NWDAF of each equipment manufacturer to assist each Vendor NWDAF to update the model parameters locally
  • the processing parameter #f is the gradient result after weighted aggregation
  • the local model parameter update process is as follows
  • the model termination condition of the horizontal federated learning can be the maximum number of iterations (such as 10,000 times), and the termination condition can be set and judged in advance by the operator NWDAF, or it can be set and judged in advance by the equipment manufacturer NWDAF.
  • the operator NWDAF first determines the vendor information of the service experience data provided by the AF, and then distributes the service experience data to the Vendor NWDAF of the corresponding device manufacturer to assist in the training of the service experience model within the manufacturer.
  • the Vendor NWDAF of the equipment manufacturer directly completes the training of the service experience model on the internal NWDAF of the equipment manufacturer after receiving the service experience data corresponding to the equipment manufacturer.
  • Vertical federated learning does not need to be introduced in this embodiment.
  • the operator NWDAF after determining the equipment manufacturer information of the service experience data, the operator NWDAF directly sends the service experience data corresponding to the equipment manufacturer to the Vendor NWDAF, and the equipment manufacturer then combines the public network data and private network data corresponding to the equipment manufacturer.
  • Network data, the training of the service experience model is directly performed in the Vendor NWDAF of the equipment manufacturer, as an example and not a limitation
  • the equipment manufacturer information of the service experience data sent by the AF can also be determined by the NEF, Then, it sends its corresponding service experience data to each Vendor NWDAF, and the operator NWDAF assists the vendor's internal service experience model training.
  • the Vendor NWDAF of the equipment manufacturer directly trains the service experience model on the Vendor NWDAF within the equipment manufacturer after receiving the service experience data corresponding to the equipment manufacturer, without introducing vertical federated learning.
  • FIG. 8 shows a schematic flowchart of a method 500 for acquiring a service experience model according to another specific embodiment of the present application.
  • the specific determination methods include S501a to S505, and then combine the network data of the core network elements of each equipment manufacturer and the corresponding service experience data for training
  • the specific training steps for the service experience model of each equipment manufacturer include S506a to S510, and each step is described in detail below.
  • the NEF sends the request information #a to the AF, and subscribes the service experience data of the terminal and the associated information corresponding to the service experience data set to the AF.
  • the NEF triggers an event open subscription (Naf_EventExposure_Subscribe) service operation on the Naf interface of the AF, and subscribes the service experience data of the terminal and the associated information corresponding to the service experience data to the AF.
  • Naf_EventExposure_Subscribe an event open subscription
  • the NEF can subscribe to the AF for one terminal service experience data and the associated information corresponding to the service experience data, and can also subscribe to the AF for multiple terminal service experience data and the associated information corresponding to the service experience data at the same time. This is not limited.
  • a piece of service experience data corresponds to a piece of associated information, where a piece of service experience data can be directed to a specific service of the terminal (such as Tencent video service), or can be directed to multiple services in a type of service of the terminal (such as Tencent Video, YouTube, etc. in the video business), which is not limited in this application.
  • the AF sends reply information #a to the NEF, where the reply information #a includes service experience data subscribed by the operator NWDAF and associated information corresponding to the service experience data.
  • the AF triggers an event exposure notification (Naf_EventExposure_Notify) service operation on the Naf interface of the NEF, and sends the service experience data of the terminal and the associated information corresponding to the service experience data to the NEF.
  • Naf_EventExposure_Notify an event exposure notification
  • steps S502a to S503c reference may be made to steps S402a to S403c in the third embodiment, which will not be repeated here.
  • the NEF sends the request information #c to the NRF, and queries the NRF for the Vendor NWDAF ID corresponding to each association information, and the request information #c includes the association information corresponding to the service experience data.
  • one piece of association information corresponds to one piece of service experience data.
  • the NEF triggers the Nnrf interface surfing element discovery request (Nnrf_NFDiscovery_Request) service operation, sends the request information #c to the NRF, and requests the NRF to query the Vendor NWDAF ID corresponding to the associated information.
  • the request information # c includes the associated information Timestamp and IP address 5-tuple corresponding to the service experience data.
  • the NRF sends reply information #c to the NEF, where the reply information #c includes the Vendor NWDAF ID corresponding to the associated information.
  • the NRF triggers the Nnrf interface surfing element discovery request response (Nnrf_NFDiscovery_RequestResponse) service operation, and sends a reply message #c to the NEF, where the reply message #c includes the Vendor NWDAF ID corresponding to the associated information.
  • Nnrf_NFDiscovery_RequestResponse the Nnrf interface surfing element discovery request response
  • the NEF determines the device manufacturer information of the service experience data according to the association information, thereby determining the service experience data of the device manufacturer #1 and the service experience data of the device manufacturer #2.
  • NEF sends training parameter #d1 to Vendor NWDAF#1, where training parameter #d1 includes service experience data #1 corresponding to equipment manufacturer #1 and association information #1 corresponding to service experience data #1.
  • NEF sends training parameter #d2 to Vendor NWDAF#2, where training parameter #d2 includes service experience data #2 corresponding to equipment manufacturer #2 and association information #2 corresponding to service experience data #2.
  • the NEF determines the equipment manufacturer information of the service experience data and sends the service experience data to the NWDAF of the equipment manufacturer to participate in the training on the NWDAF of the equipment manufacturer.
  • the equipment manufacturer NWDAF has obtained the network data on the core network elements corresponding to the equipment manufacturer, as well as the service experience data corresponding to the equipment manufacturer. Therefore, it is not necessary to introduce the federal training method, and the equipment manufacturer NWDAF can directly use the equipment manufacturer based on the equipment manufacturer.
  • the network data on the corresponding core network element and the corresponding service experience data are used to train the service experience model.
  • the service experience model training processes S508a and S508b are similar to those in the prior art, and are not repeated here.
  • the operator NWDAF may also perform steps S509a to S511 to perform horizontal federation training on the model parameters of the public network data or the model parameter gradients of the public network data in the service experience models of each device manufacturer, so that different Equipment manufacturers unify the model parameters of public network data to further improve the generalization ability of model parameters of public network data.
  • steps S509a to S511 to perform horizontal federation training on the model parameters of the public network data or the model parameter gradients of the public network data in the service experience models of each device manufacturer, so that different Equipment manufacturers unify the model parameters of public network data to further improve the generalization ability of model parameters of public network data.
  • the Vendor NWDAF carries the association information corresponding to the network side data of the equipment manufacturer to register with the NRF in advance, and after obtaining the service experience data and the corresponding association information from the AF, the NEF queries the NRF through the association information to determine the service experience data Vendor NWDAF, and then distribute the service experience data to the Vendor NWDAF of equipment manufacturers.
  • the Vendor NWDAF receives the service experience data corresponding to the equipment manufacturer, it does not need to introduce vertical federated learning, and directly trains the service experience model on the equipment manufacturer's Vendor NWDAF.
  • the operator NWDAF assists the Vendor NWDAF in carrying out the business corresponding to the equipment manufacturer. Experience model training.
  • pre-set may be pre-saved in a device (for example, a network device) by a corresponding code, a table, or other methods that can be used to indicate relevant information
  • a device for example, a network device
  • a corresponding code for example, a table
  • present application does not limit the specific implementation manner, such as the preset rules and preset constants in the embodiments of the present application.
  • the method implemented by the communication device may also be implemented by a component (for example, a chip or a circuit) that can be configured inside the communication device.
  • each network element includes corresponding hardware structures and/or software modules for performing each function.
  • each network element includes corresponding hardware structures and/or software modules for performing each function.
  • the present application can be implemented in hardware or a combination of hardware and computer software with the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of this application.
  • the transmitting-end device or the receiving-end device may be divided into functional modules according to the foregoing method examples.
  • each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. middle.
  • the above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. It should be noted that, the division of modules in the embodiments of the present application is schematic, and is only a logical function division, and there may be other division manners in actual implementation. The following description will be given by taking as an example that each function module is divided corresponding to each function.
  • FIG. 9 is a schematic structural diagram of a communication apparatus 600 .
  • the communication apparatus includes a receiving unit 610, a processing unit 620, and a sending unit 630.
  • the communication apparatus 600 may be the data analysis device or the network capability opening device in the above method embodiments, or may be used to implement the above method embodiments.
  • the communication apparatus 600 may correspond to the data analysis device in the method 200 to the method 500 or the network capability opening device in the method 500 according to the embodiments of the present application, and the communication apparatus 600 may include a device for executing FIG. 5 to FIG. 8 .
  • each unit in the communication device 600 and the above-mentioned other operations and/or functions respectively implement the corresponding processes of the method 200 to the method 500 in FIG. 5 to FIG. 8 .
  • the communication apparatus 600 may implement any function possessed by the operator data analysis device NWDAF in the embodiment shown in any one of FIG. 4 to FIG. 8 .
  • the receiving unit 610 is configured to receive first information, where the first information includes service experience data of the terminal on the application function device and corresponding associated information;
  • the receiving unit 610 is further configured to receive second information, where the second information includes information related to network data of the terminal on the core network device;
  • the second information may further include the device manufacturer identifier of the core network device and/or the network data of the terminal on the core network device;
  • the receiving unit 610 is further configured to receive third information, where the second information includes address information of the device manufacturer data analysis device NWDAF;
  • a processing unit 620 configured to determine the device manufacturer information of the service experience data according to the association information and/or the device manufacturer identifier, further configured to determine the address of the device manufacturer data analysis device NWDAF according to the third information, and for the joint equipment manufacturer data analysis equipment NWDAF to determine the service experience model of the equipment manufacturer about the terminal according to the first information and the second information;
  • a sending unit 630 configured to send request information, where the request information can be used to request the first information and/or the second information and/or the third information;
  • the sending unit 630 is further configured to send training parameters in the process of determining the service experience model, such as training algorithm information of the service experience model, residual values in model training, and the like.
  • the receiving unit 610 is configured to receive first information, where the first information includes service experience data of the terminal on the application function device and corresponding associated information;
  • the receiving unit 610 is further configured to receive third information, where the second information includes address information of the device manufacturer data analysis device NWDAF;
  • the processing unit 620 is configured to determine the device manufacturer information of the service experience data and the address of the device manufacturer data analysis device NWDAF according to the first information and the third information, and is also configured to cooperate with the device manufacturer data analysis device NWDAF according to the data analysis device NWDAF.
  • the first information and the third information determine the device manufacturer's service experience model for the terminal;
  • a sending unit 630 configured to send request information, where the request information can be used to request the first information and/or the third information;
  • the sending unit 630 is further configured to send the service experience data corresponding to the equipment manufacturer to the equipment manufacturer data analysis equipment NWDAF;
  • the sending unit 630 is further configured to send training parameters in the process of determining the service experience model, such as training algorithm information of the service experience model.
  • the communication apparatus 600 can implement any function of the device manufacturer data analysis device NWDAF in the embodiment shown in any one of FIGS. 4 to 8 .
  • the receiving unit 610 is configured to receive fourth information, where the fourth information includes network data of the terminal on the core network device and corresponding associated information;
  • the receiving unit 610 is further configured to receive fifth information, where the fifth information includes service experience data of the terminal on the application function device and corresponding associated information;
  • the processing unit 620 is used for the joint operator NWDAF to determine the service experience model of the device manufacturer on the terminal according to the fourth information, or for joint equipment manufacturer data analysis equipment NWDAF according to the fourth information and the The fifth information determines the service experience model of the device manufacturer about the terminal;
  • the sending unit 630 is used to send the training parameters in the process of determining the service experience model, such as the model parameter gradient of the public network data in the service experience model, the product of the initial model parameters and the original network data, the updated model parameters, etc.
  • the communication apparatus 600 may implement any function possessed by the network capability opening device in the embodiment shown in FIG. 8 .
  • the receiving unit 610 is configured to receive first information, where the first information includes service experience data of the terminal on the application function device and corresponding associated information;
  • the receiving unit 610 is further configured to receive third information, where the second information includes address information of the device manufacturer data analysis device NWDAF;
  • a processing unit 620 configured to determine the device manufacturer information of the service experience data according to the first information and the third information, and also configured to determine the address of the device manufacturer data analysis device NWDAF according to the third information;
  • a sending unit 630 configured to send request information, where the request information can be used to request the first information and/or the third information;
  • the sending unit 630 is further configured to send the service experience data corresponding to the equipment manufacturer to the equipment manufacturer data analysis equipment NWDAF.
  • FIG. 10 is a schematic structural diagram of a communication device 700 .
  • the communication apparatus includes a receiving unit 710 and a sending unit 720, and the communication apparatus 700 may be an application function device, a core network device, or a network storage function device in the above method embodiments. It may also be a chip for implementing the functions of the application function device, the core network device, or the network storage device in the above method embodiments.
  • the communication apparatus 700 may implement any function possessed by the application function device in any one of the embodiments shown in FIG. 4 to FIG. 8 .
  • the receiving unit 710 is configured to receive request information, where the request information is used to request service experience data of the terminal on the application function device;
  • the sending unit 720 is configured to send the service experience data of the terminal on the application function device.
  • the communication apparatus 700 may implement any function possessed by the core network device in the embodiment shown in any one of FIG. 4 to FIG. 8 .
  • the receiving unit 710 is configured to receive request information, where the request information is used to request network data of the terminal on the core network device;
  • the sending unit 720 is configured to send the network data of the terminal on the core network device.
  • the communication apparatus 700 can implement any function of the network storage device in the embodiment shown in any one of FIG. 4 to FIG. 8 .
  • the receiving unit 710 is configured to receive request information, where the request information is used to request the address information of the device manufacturer's network analysis device NWDAF, and the request information includes the manufacturer's identifier of the device manufacturer and/or the corresponding device manufacturer's related information;
  • the sending unit 720 is configured to send the address information of the network analysis equipment NWDAF of the equipment manufacturer according to the manufacturer identification of the equipment manufacturer and/or the associated information corresponding to the equipment manufacturer.
  • FIG. 11 is a structural block diagram of a communication device 800 provided according to an embodiment of the present application.
  • the communication device 800 shown in FIG. 11 includes: a processor 810 , a memory 820 and a communication interface 830 .
  • the processor 810 is coupled to the memory for executing instructions stored in the memory to control the communication interface 830 to send and/or receive signals.
  • processor 810 and the memory 820 may be combined into a processing device, and the processor 810 is configured to execute the program codes stored in the memory 820 to realize the above-mentioned functions.
  • the memory 820 may also be integrated in the processor 810 or independent of the processor 810 .
  • the communication device 800 may be the data analysis device or the network capability opening device in the above method embodiments, or may be used to implement the data analysis device or the network capability opening device in the above method embodiments The functional chip of the device.
  • the communication device 800 may correspond to the operator data analysis device manufacturer data analysis device in the methods 200 to 500 according to the embodiments of the present application, and the network capability opening device in the method 500, and the communication device 800 may include a device for A unit for executing the method performed by the operator and device manufacturer data analysis device in FIG. 4 to FIG. 8 , and a unit for performing the method performed by the network capability opening device in FIG. 8 .
  • each unit in the communication device 800 and the above-mentioned other operations and/or functions are to implement the corresponding processes of the method 200 to the method 500, respectively. It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above-mentioned method embodiments, and for the sake of brevity, it will not be repeated here.
  • the chip When the communication device 800 is a chip, the chip includes a transceiver unit and a processing unit.
  • the transceiver unit may be an input/output circuit or a communication interface;
  • the processing unit may be a processor, a microprocessor or an integrated circuit integrated on the chip.
  • the embodiment of the present application also provides a processing apparatus, including a processor and an interface.
  • the processor may be used to execute the methods in the above method embodiments.
  • the above processing device may be a chip.
  • the processing device may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), or a It is a central processing unit (CPU), a network processor (NP), a digital signal processing circuit (DSP), or a microcontroller (microcontroller unit). , MCU), it can also be a programmable logic device (PLD) or other integrated chips.
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • SoC system on chip
  • MCU microcontroller unit
  • MCU programmable logic device
  • PLD programmable logic device
  • each step of the above-mentioned method can be completed by a hardware integrated logic circuit in a processor or an instruction in the form of software.
  • the steps of the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware. To avoid repetition, detailed description is omitted here.
  • the processor in this embodiment of the present application may be an integrated circuit chip, which has a signal processing capability.
  • each step of the above method embodiments may be completed by a hardware integrated logic circuit in a processor or an instruction in the form of software.
  • the aforementioned processors may be general purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components .
  • DSPs digital signal processors
  • ASICs application specific integrated circuits
  • FPGAs field programmable gate arrays
  • the methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the method disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.
  • the memory in this embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous DRAM
  • SDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • direct ram-bus RAM direct ram-bus RAM
  • the present application also provides a computer program product, the computer program product includes: computer program code, when the computer program code is run on a computer, the computer is made to execute the steps shown in FIG. 4 and FIG. 8 .
  • the present application further provides a computer-readable medium, where the computer-readable medium stores program codes, and when the program codes are executed on a computer, the computer is made to execute the programs shown in FIG. 4 and FIG. 8 .
  • the present application further provides a system, which includes the foregoing apparatus or equipment.
  • the above-mentioned embodiments it may be implemented in whole or in part by software, hardware, firmware or any combination thereof.
  • software it can be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated.
  • the computer may be a general purpose computer, special purpose computer, computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server or data center Transmission to another website site, computer, server, or data center by wire (eg, coaxial cable, optical fiber, digital subscriber line, DSL) or wireless (eg, infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes an integration of one or more available media.
  • the available media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, high-density digital video discs (DVDs)), or semiconductor media (eg, solid state discs, SSD)) etc.
  • the network-side equipment in each of the above apparatus embodiments corresponds to the terminal equipment and the network-side equipment or terminal equipment in the method embodiments, and corresponding steps are performed by corresponding modules or units, for example, the communication unit (communication interface) performs the receiving in the method embodiments. Or the step of sending, other steps except sending and receiving may be performed by a processing unit (processor). For functions of specific units, reference may be made to corresponding method embodiments.
  • the number of processors may be one or more.
  • a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer.
  • an application running on a computing device and the computing device may be components.
  • One or more components may reside in a process and/or thread of execution, and a component may be localized on one computer and/or distributed between two or more computers.
  • these components can execute from various computer readable media having various data structures stored thereon.
  • a component may, for example, be based on a signal having one or more data packets (eg, data from two components interacting with another component between a local system, a distributed system, and/or a network, such as the Internet interacting with other systems via signals) Communicate through local and/or remote processes.
  • data packets eg, data from two components interacting with another component between a local system, a distributed system, and/or a network, such as the Internet interacting with other systems via signals
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium.
  • the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .

Landscapes

  • Mobile Radio Communication Systems (AREA)

Abstract

La présente invention concerne un procédé de communication et un appareil de communication. Le procédé de communication comprend les étapes suivantes : un élément de réseau d'analyse de données d'un opérateur détermine des informations de fabricant de dispositif de données d'expérience de service de terminal au moyen d'informations d'association ; l'élément de réseau d'analyse de données de l'opérateur obtient des informations d'adresse d'un élément de réseau d'analyse de données du fabricant de dispositif ; et l'élément de réseau d'analyse de données de l'opérateur, conjointement à l'élément de réseau d'analyse de données du fabricant de dispositif, détermine un modèle d'expérience de service correspondant au fabricant de dispositif sur la base des données d'expérience de service et de données côté réseau correspondant au fabricant de dispositif. Le présent procédé dans le mode de réalisation de la présente demande peut établir de manière efficace des modèles d'expérience de service correspondant à des fabricants de dispositif dans un scénario dans lequel des éléments de réseau central proviennent de multiples fabricants de dispositifs.
PCT/CN2020/141803 2020-12-30 2020-12-30 Procédé et appareil de communication WO2022141295A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202080106205.1A CN116325686A (zh) 2020-12-30 2020-12-30 一种通信方法和装置
PCT/CN2020/141803 WO2022141295A1 (fr) 2020-12-30 2020-12-30 Procédé et appareil de communication

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/141803 WO2022141295A1 (fr) 2020-12-30 2020-12-30 Procédé et appareil de communication

Publications (1)

Publication Number Publication Date
WO2022141295A1 true WO2022141295A1 (fr) 2022-07-07

Family

ID=82260072

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/141803 WO2022141295A1 (fr) 2020-12-30 2020-12-30 Procédé et appareil de communication

Country Status (2)

Country Link
CN (1) CN116325686A (fr)
WO (1) WO2022141295A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115499477A (zh) * 2022-11-16 2022-12-20 无锡锐泰节能系统科学有限公司 一种智能化用能设备控制系统及控制方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117289669B (zh) * 2023-11-27 2024-02-02 青岛创新奇智科技集团股份有限公司 一种基于工业大模型的自动调整式生产线控制系统及方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108768702A (zh) * 2018-05-15 2018-11-06 华为技术有限公司 网络分析方法及设备
WO2019080799A1 (fr) * 2017-10-23 2019-05-02 华为技术有限公司 Procédé de traitement de trafic, appareil de plan utilisateur, et dispositif terminal
WO2019137195A1 (fr) * 2018-01-15 2019-07-18 华为技术有限公司 Procédé et appareil pour obtenir des données de service
CN110519802A (zh) * 2018-05-21 2019-11-29 华为技术有限公司 一种数据处理方法、发送方法及装置
CN111770587A (zh) * 2019-04-02 2020-10-13 华为技术有限公司 一种数据处理方法、装置及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019080799A1 (fr) * 2017-10-23 2019-05-02 华为技术有限公司 Procédé de traitement de trafic, appareil de plan utilisateur, et dispositif terminal
WO2019137195A1 (fr) * 2018-01-15 2019-07-18 华为技术有限公司 Procédé et appareil pour obtenir des données de service
CN108768702A (zh) * 2018-05-15 2018-11-06 华为技术有限公司 网络分析方法及设备
CN110519802A (zh) * 2018-05-21 2019-11-29 华为技术有限公司 一种数据处理方法、发送方法及装置
CN111770587A (zh) * 2019-04-02 2020-10-13 华为技术有限公司 一种数据处理方法、装置及系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115499477A (zh) * 2022-11-16 2022-12-20 无锡锐泰节能系统科学有限公司 一种智能化用能设备控制系统及控制方法

Also Published As

Publication number Publication date
CN116325686A (zh) 2023-06-23

Similar Documents

Publication Publication Date Title
EP4160995A1 (fr) Procédé et dispositif de traitement de données
US20210014739A1 (en) Data processing method and apparatus, and data sending method and apparatus
WO2020073855A1 (fr) Procédé et dispositif d'établissement de session, et, procédé et dispositif de transmission de paquet
CN111901135B (zh) 一种数据分析方法及装置
EP4132066A1 (fr) Procédé, appareil et système de communication
WO2021017550A1 (fr) Procédé, dispositif et système d'envoi de rapports d'événement
WO2022141295A1 (fr) Procédé et appareil de communication
WO2022226713A1 (fr) Procédé et appareil de détermination de politique
WO2021212939A1 (fr) Procédé, appareil et système de communication
KR20240060722A (ko) 논리적 tsn 브리지를 위한 방법 및 장치
WO2019076308A1 (fr) Procédé, appareil et dispositif de détermination d'état de dispositif terminal
US20230308930A1 (en) Communication method and apparatus
WO2022007847A1 (fr) Procédé et dispositif de communication
US20230289615A1 (en) Training a machine learning model
US20240015534A1 (en) Model processing method, communication apparatus, and system
WO2022222745A1 (fr) Procédé et appareil de communication
WO2021218244A1 (fr) Procédé, appareil et système de communication
WO2022141279A1 (fr) Procédé de détermination de modèle d'expérience de service, et appareil de communication
WO2024027381A1 (fr) Procédé de détection d'anomalie et appareil de communication
WO2023078183A1 (fr) Procédé de collecte de données et appareil de communication
WO2024032270A1 (fr) Procédé et appareil de détermination de stratégie, et support de stockage
WO2023185452A1 (fr) Procédé de communication et appareil de communication
WO2023213226A1 (fr) Procédé et appareil d'autorisation
WO2023185807A1 (fr) Procédé et appareil de communication
WO2023179262A1 (fr) Procédé et appareil de configuration d'informations de cellule, support de stockage lisible et système de puce

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20967634

Country of ref document: EP

Kind code of ref document: A1