WO2022021421A1 - Model management method, system and apparatus, communication device, and storage medium - Google Patents

Model management method, system and apparatus, communication device, and storage medium Download PDF

Info

Publication number
WO2022021421A1
WO2022021421A1 PCT/CN2020/106415 CN2020106415W WO2022021421A1 WO 2022021421 A1 WO2022021421 A1 WO 2022021421A1 CN 2020106415 W CN2020106415 W CN 2020106415W WO 2022021421 A1 WO2022021421 A1 WO 2022021421A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
network element
model management
identification
type
Prior art date
Application number
PCT/CN2020/106415
Other languages
French (fr)
Chinese (zh)
Inventor
许阳
Original Assignee
Oppo广东移动通信有限公司
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 Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Priority to CN202080101791.0A priority Critical patent/CN115699842A/en
Priority to PCT/CN2020/106415 priority patent/WO2022021421A1/en
Publication of WO2022021421A1 publication Critical patent/WO2022021421A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/60—Software deployment
    • G06F8/65—Updates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks

Definitions

  • the present application relates to the field of mobile communications, and in particular, to a model management method, system, apparatus, communication device and storage medium.
  • AI artificial intelligence
  • the third-party application provider of the application corresponding to the AI model needs to store and manage the AI model used by the terminal device.
  • the embodiments of the present application provide a model management method, system, device, communication device, and storage medium, which can manage AI models without occupying the local computer room resources of a third-party application provider, and ensure resource usage of the enterprise.
  • the technical solution is as follows.
  • a model management method is provided, which is applied to a terminal device, where the terminal device includes: an AI model management module, and the method includes:
  • the AI model management module and the AI model management network element execute the first interaction process
  • the AI model management module is a functional module used for AI model management at the terminal device side
  • the AI model management network element is a network element used for AI model management at the data network side
  • the AI model management module supports and The AI model manages network element interactions in order to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  • a model management method is provided, which is applied in a data network, where the data network includes: an AI model management network element, and the method includes:
  • the AI model management network element and the AI model management module execute the first interaction process
  • the AI model management module is a functional module used for AI model management at the terminal device side
  • the AI model management network element is a network element used for AI model management at the data network side
  • the AI model management module supports Interact with the AI model management network element to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  • a model management system comprising: an AI model management module and an AI model management network element;
  • the AI model management module is configured to manage network elements with the AI model and execute a first interaction process
  • the AI model management module is a functional module used for AI model management at the terminal device side
  • the AI model management network element is a network element used for AI model management at the data network side
  • the AI model management module supports Interact with the AI model management network element to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  • a model management apparatus which is applied in a terminal device, and the apparatus includes: an AI model management module;
  • the AI model management module is used to manage network elements with the AI model and execute the first interaction process
  • the AI model management module is a functional module used for AI model management at the terminal device side
  • the AI model management network element is a network element used for AI model management at the data network side
  • the AI model management module supports and The AI model manages network element interactions in order to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  • a model management apparatus applied in a data network, the apparatus includes:
  • AI model manages network element modules
  • the AI model management network element module is used for executing the first interaction process with the AI model management module
  • the AI model management module is a functional module used for AI model management at the terminal device side
  • the AI model management network element module is a network element module used for AI model management at the data network side
  • the AI model management The module supports interaction with the AI model management network element module, so as to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  • a terminal device comprising: a processor; a transceiver connected to the processor; a memory for storing executable instructions of the processor; The processor is configured to load and execute the executable instructions to implement the model management method as described in the above aspects.
  • a data network comprising: a processor; a transceiver connected to the processor; a memory for storing executable instructions of the processor; wherein the The processor is configured to load and execute the executable instructions to implement the model management method as described in the above aspects.
  • a computer-readable storage medium having executable instructions stored in the readable storage medium, the executable instructions being loaded and executed by a processor to implement the model as described in the above aspect management method.
  • a computer program product or computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium, the processor of the computer device being readable from the computer
  • the storage medium reads the computer instructions, and the processor executes the computer instructions, so that the computer device executes the model management method described in the above aspects.
  • the task of AI model management is handed over to the AI model management module and AI model management network element. Since the AI model management module is a functional module used for AI model management on the terminal device side, the AI model management network element is used by the data network side. NEs for AI model management do not need to occupy the local computer room resources of third-party application providers to manage AI models, ensuring enterprise resource usage.
  • FIG. 1 is a schematic diagram of a scenario of performing big data analysis based on an AI model provided by an exemplary embodiment of the present application
  • FIG. 2 is a schematic diagram of a communication system provided by an exemplary embodiment of the present application.
  • FIG. 3 is a flowchart of a model management method provided by an exemplary embodiment of the present application.
  • FIG. 4 is a schematic diagram of a model management method provided by an exemplary embodiment of the present application.
  • FIG. 5 is a schematic diagram of a model management system provided by an exemplary embodiment of the present application.
  • FIG. 6 is a structural block diagram of an apparatus for model management provided by an exemplary embodiment of the present application.
  • FIG. 7 is a structural block diagram of a model management apparatus provided by an exemplary embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of a communication device provided by an exemplary embodiment of the present application.
  • Artificial Intelligence is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
  • artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence.
  • Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.
  • Artificial intelligence technology is a comprehensive discipline, involving a wide range of fields, including both hardware-level technology and software-level technology.
  • the basic technologies of artificial intelligence generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation/interaction systems, and mechatronics.
  • Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning/deep learning.
  • the AI model is a model corresponding to artificial intelligence technology.
  • a multi-level AI model can be considered, that is, the network elements and terminal devices on the network side divide the labor for big data analysis.
  • Figure 1 a) in Figure 1 is a centralized scenario, that is, after all terminal devices report the required data, the big data analysis work is all performed on the server on the network side.
  • b) in Fig. 1 is a completely distributed scenario, that is, different terminal devices analyze the collected data locally.
  • c) in FIG. 1 is a hybrid scenario, that is, after the terminal device analyzes a part of the collected data locally, it sends the result to the server on the network side for further calculation and analysis.
  • data interaction between terminal devices and terminal devices may also be introduced to complete big data analysis or result sharing.
  • the AI model has the following characteristics:
  • AI models There are various types of AI models. Different third-party application providers and under different conditions use different AI models.
  • terminal devices may need to use different AI models in different regions and times.
  • An AI model may require hundreds of megabytes or even larger storage space. It is impossible for terminal devices to store all models locally, so it is necessary to update the AI model in real time and accurately.
  • FIG. 2 shows a block diagram of a communication system provided by an exemplary embodiment of the present application.
  • the communication system may include: a terminal device 12, a (wireless) access network ((R)AN) 14, a core network 16 and a data network ( Data Network, DN) 18.
  • R wireless access network
  • DN Data Network
  • the terminal device 12 may include various handheld devices, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to wireless modems with wireless communication functions, as well as various forms of user equipment, mobile stations (Mobile Station, MS), terminal device, etc.
  • the devices mentioned above are collectively referred to as terminal devices.
  • the access network 14 includes several network devices.
  • the network device may be a base station, which is a device deployed in an access network to provide a wireless communication function for a terminal.
  • the base station may include various forms of macro base station, micro base station, relay station, access point and so on.
  • the names of devices with base station functions may be different.
  • eNodeBs or eNBs In LTE systems, they are called eNodeBs or eNBs; in 5G NR-U systems, they are called gNodeBs or gNBs.
  • the description of "base station” may change.
  • the above-mentioned apparatuses for providing wireless communication functions for terminal equipment are collectively referred to as network equipment.
  • the core network 16 may include: a user plane function (User Plane Function, UPF) and a control plane function.
  • the control plane functions may include: Access and Mobility Management Function (AMF), Session Management Function (SMF), Policy Control Function (PCF) and Unified Data Management (Unified Data) Manager, UDM), application function (Application Function, AF), network slice selection function (Network Slice Selection Function, NSSF), authentication service function (Authentication Server Function, AUSF).
  • AMF Access and Mobility Management Function
  • SMF Session Management Function
  • PCF Policy Control Function
  • UDM Unified Data Management
  • application function Application Function
  • AF Application Function
  • NSSF Network Slice Selection Function
  • AUSF Authentication Server Function
  • the wireless network may include an access network 14 and a core network 16, and different network elements in the wireless network may specifically correspond to base stations of the access network or various functional network elements (such as SMF, PCF, AMF, etc.) of the core network.
  • different network elements in the wireless network may specifically correspond to base stations of the access network or various functional network elements (such as SMF, PCF, AMF, etc.) of the core network.
  • the terminal device 12 and the network devices in the access network 14 communicate with each other through a certain air interface technology, such as a Uu interface.
  • the core network 16 can perform data transmission with the external data network 18 through the N6 interface, and can perform data transmission with the access network 14 through the N3 interface.
  • GSM Global System of Mobile Communication
  • CDMA Code Division Multiple Access
  • CDMA wideband Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • GPRS General Packet Radio Service
  • LTE Long Term Evolution
  • FDD Frequency Division Duplex
  • TDD Time Division Duplex
  • LTE-A Advanced Long Term Evolution
  • NR New Radio
  • evolution systems of NR systems LTE on unlicensed frequency bands (LTE-based access to Unlicensed spectrum, LTE-U) system, NR-U system, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), next-generation communication systems or other communication systems, etc.
  • D2D Device to Device
  • M2M Machine to Machine
  • MTC Machine Type Communication
  • V2V Vehicle to Vehicle
  • V2X Vehicle to Everything
  • FIG. 3 shows a flowchart of a model management method provided by an exemplary embodiment of the present application. This embodiment is exemplarily described by applying the method to the communication system shown in FIG. 2 , and the method includes:
  • Step 310 the AI model management module and the AI model management network element perform a first interaction process.
  • the terminal device includes several functional modules for implementing different functions.
  • the AI model management module is a functional module used for AI model management on the terminal device side.
  • the AI model management module supports interaction with AI model management network elements to download or upload AI models for the application layer and/or wireless protocol layer in the terminal device.
  • the radio protocol layer is a protocol layer that supports processing the 3GPP protocol, and the specific implementation form of the radio protocol layer is not limited in this embodiment of the present application.
  • the AI model management network element is the network element used for AI model management on the data network side.
  • this embodiment of the present application does not limit the specific implementation form of the AI model management network element, and the AI model management network element may be an existing network element or a newly added network element, which is used for AI model management. .
  • the first interaction process is an interaction process between the AI model management module and the AI model management network element.
  • the first interaction process is used to implement downloading or uploading of the AI model.
  • both the AI model management module and the AI model management network element are functional modules or network elements corresponding to the same operator, and the AI model management module and the AI model management network element are part of the operator's network.
  • the AI model management module in addition to the first interaction process between the AI model management module and the AI model management network element, in addition to downloading or uploading the AI model, the AI model management module also supports compression and decompression of the AI model for the transmission of AI model content or storage.
  • the task of AI model management is handed over to the AI model management module and the AI model management network element for execution, because the AI model management module is a functional module used for AI model management on the terminal device side.
  • AI model management network element is the network element used for AI model management on the data network side, so there is no need to occupy the local computer room resources of third-party application providers to manage AI models, ensuring enterprise resource usage.
  • the model management method of the AI model may be used in combination with any one of the embodiments of the present application, or may be used alone, which is not limited in the embodiments of the present application.
  • the following embodiments of the present application are illustrated in combination with the foregoing embodiments.
  • the AI model in the AI model management module and the AI model management network element may include, but not limited to, the first type of AI model and the second type of AI model.
  • the first type of AI model corresponds to an operator
  • the second type of AI model corresponds to a third-party application (eg, from an application or a service provider).
  • An operator is an operator who establishes and operates a network for the purpose of providing land mobile communication services to the public.
  • Third-party applications are applications developed for terminal devices. That is to say, the first type of AI model is the AI model of the operator, and the second type of AI model is the AI model of the third-party application.
  • the AI model corresponds to the AI model logo.
  • the AI model identifiers of the above two types of AI models correspond to the same or different model identifier formats.
  • the model identification format of the first type AI model is the first type model identification format
  • the model identification format of the second type AI model is the second type model identification format.
  • the difference between the first type of model identification format and the second type of model identification format may mean that the identification types contained in the two types of model identification formats are different; or, the positions of different identification types in the formats are different; or , the number of digits for different identification types is different.
  • the first type of model identification format includes: operator identification and model identification.
  • the operator identifier can be recorded as PLMN ID, which is used to distinguish different operators.
  • the model ID can be recorded as Model Id, which is used to identify the model.
  • the model identification format of the second type AI model is the second type model identification format
  • the second type model identification format includes at least one of the following: an operator identification, an application identification and a model identification.
  • the second type of model identification format includes: operator identification, application identification and model identification; in another implementation, the second type of model identification format includes: application identification and model identification.
  • the operator identifier can be recorded as PLMN ID, which is used to distinguish different operators.
  • the application identifier can be recorded as Application Id, which is used to identify third-party applications.
  • the model ID can be recorded as Model Id, which is used to identify the model.
  • the operator identification may be determined by the operator or a third-party application
  • the application identification may be determined by the operator or a third-party application.
  • the model identifiers may include at least one of: model type identifiers (Type Id), model structure parameter identifiers (Structure Id), and model weight parameter identifiers (Weight Id).
  • Type Id model type identifiers
  • Structure Id model structure parameter identifiers
  • Weight Id model weight parameter identifiers
  • the model type identifier is used to identify the type of AI model
  • the types of AI models include but are not limited to: Deep Neural Network (DNN) model, Convolution Neural Networks (CNN) model, Recurrent Neural Network At least one of the (Recurrent Neural Networks, RNN) models.
  • DNN Deep Neural Network
  • CNN Convolution Neural Networks
  • RNN Recurrent Neural Network At least one of the (Recurrent Neural Networks, RNN) models.
  • the model structure parameter identifies the structure used to identify the model.
  • its internal neural network layers can be divided into three categories: input layer, hidden layer and output layer. Generally speaking, the first layer is the input layer, the last layer is the output layer, and the middle layers are all hidden layers.
  • the model weight parameter identifies the weight value used to identify the model.
  • each layer needs to use a specific algorithm, weight value, constant, etc. to calculate the sample parameters of the previous layer to obtain the output result, and the output result is used as the input of the next layer to calculate the next layer. The output of the layer, and finally the result of the output layer.
  • the values or partial values of the model identifiers may include: standardized model identifier values and non-standardized model identifier values.
  • the value of the standardized model identifier is a value agreed upon through standardization, and corresponds to the AI model of the target type or the AI model of the target business or the target AI model.
  • the value or partial value of one or more model identifiers can be agreed as the value of the standardized model identifier.
  • a model identifier with a value of 000010 it means that the AI model is an AI model for processing the target service of the video service; for a model identifier with a value of 000011, it means that the AI model corresponds to CNN.
  • the value of the non-standardized model identifier is the value of the model identifier determined by the operator or a third-party application. In different operators or different third-party applications, the same non-standardized model value can be defined to correspond to different AI models.
  • 100001 is the non-standardized model ID value.
  • the AI model whose mode ID value is 100001 is a CNN model
  • the AI model whose mode ID value is 100001 is an RNN model.
  • the AI model with the value of 100001 of operator A is used for the autonomous driving service
  • the AI model of the operator B with the value of 100001 is suitable for the augmented reality (Artificial Reality, AR)/virtual reality (Virtual Reality, VR) service.
  • the first interface is the interface between the AI model management module and the AI model management network element.
  • the first interface may use an application layer protocol, such as HyperText Transfer Protocol (HTTP).
  • HTTP HyperText Transfer Protocol
  • step 310 in the above embodiment may be alternatively implemented as: the AI model management module and the AI model management network element execute the first interaction process through the first interface.
  • the first interaction process includes but is not limited to at least one of the following:
  • the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element.
  • the AI model notification process is used for the AI model management NE to notify the AI model management module of the target AI model that needs to be uploaded or the target AI model that needs to be sent to the AI model management NE.
  • the capability negotiation process is used for negotiation between the AI model management module and the AI model management network element to support downloading or uploading of the target AI model.
  • the AI model download process is used to implement the AI model management module to download the target AI model from the AI model management network element.
  • the AI model upload process is used to implement the AI model management module uploading the target AI model to the AI model management network element.
  • the first interface includes a first control plane and a first user plane; wherein, the first control plane is used to execute the AI model request process, the AI model notification process and the capability negotiation process, and the first user plane is used to execute the AI model. Download process and AI model upload process.
  • the processes that can be executed by the first interface can be separated, and the first control plane executes the control-related processes (such as the capability negotiation process), and the first user plane executes the bearer-related functions (such as AI model download). Process).
  • the control-related processes such as the capability negotiation process
  • the first user plane executes the bearer-related functions (such as AI model download). Process).
  • the AI model management module and the AI model management network elements can also be correspondingly separated into two planes: the control plane and the user plane, which separate bearer and control.
  • the second interface is an interface between the AI model management module and a third-party application in the terminal device.
  • the AI model management module and the third-party application execute the second interaction process through the second interface.
  • the second interaction process includes: the AI model management module sends the AI model to the third-party application, and the third-party application sends the AI model to the AI model management module.
  • the second interface is used for the application to send the specific AI model to the AI model management module, so that the AI model management module saves or uploads it to the AI model management network element for unified storage/management.
  • the third interface is the interface between the AI model management network element and other servers/network elements in the data network.
  • the AI model management network element and the application server perform a third interaction process through a third interface; or, the AI model management network element and a third-party network element perform a fourth interaction process through the third interface, and the third-party network element NEs other than AI model management NEs.
  • the application server may correspond to a third-party network element.
  • the AI model management network element may also interact with other network elements through the third interface, and the other network elements and the AI model management network element may correspond to the same operator or may correspond to different operators.
  • the third interaction process includes: storing, downloading, and uploading the AI model between the AI model management network element and the application server; the fourth interaction process includes: performing AI between the AI model management network element and a third-party network element Model storage, download, upload.
  • the application server sends the AI model of the third-party application to the AI model management network element for storage.
  • the third-party network element is the AI model selection network element.
  • the AI model selection network element is used to determine the AI model that the terminal device needs to use, and the AI model management network element is triggered through interface 3 to send the corresponding AI model to the terminal device for use. .
  • the fourth interface is the interface between the AI model management network element and the wireless network.
  • the AI model manages the network element and the network element in the wireless network, and executes the fifth interaction process through the fourth interface.
  • the network elements in the wireless network can have the function of the AI model management module, and interact with the AI model management network elements to perform corresponding functions.
  • the purpose of the fifth interaction process can be any one of the following:
  • the fifth interaction process is used to trigger the wireless network to establish a dedicated bearer or a quality of service (Quality of Service, QoS) data flow.
  • QoS Quality of Service
  • the security and efficiency of executing the first interaction process through the first interface are guaranteed.
  • the fifth interaction process is used for the AI model management network element to send the AI model to the wireless network.
  • the wireless network can use the AI model obtained from the AI model management network element.
  • the fifth interaction process is used for the AI model management network element to obtain the AI model from the wireless network, and/or store the AI model.
  • AI model management network elements can also obtain AI models from wireless networks and store them.
  • the fifth interaction process is used for the AI model management network element to receive a request from the network element in the wireless network, and the request is used to request the AI model management network element to send the AI model.
  • the AI model management network element can correspondingly send the AI model to the terminal device according to the request of the network element in the wireless network.
  • the network elements in the wireless network can also perform capability negotiation with the AI model management network element, and negotiate the AI model that can be downloaded or uploaded.
  • the AI model management network element is connected with a capability opening network element in the wireless network or directly connected with a certain network element in the wireless network.
  • the capability opening network element is a network element that provides capability opening services. That is to say, the AI model management network element can interact with the capability opening network element in the wireless network through the fourth interface.
  • Capability exposure network elements include but are not limited to: Network Exposure Function (NEF) network elements, Service Capability Exposure Function (SCEF) network elements, Policy Control Function (Policy Control Function, PCF) network elements at least one of.
  • NEF network elements and SCEF network elements can open service capabilities to third-party service providers through API interfaces, and PCF network elements are responsible for policy control.
  • the AI model can be more accurately identified, which is convenient for the identification of AI models. manage.
  • the operator can open the relevant functions of AI management to other objects (such as third-party applications), which facilitates the transmission of the content of the AI model.
  • the steps performed by the terminal device can be implemented independently as a model management method on the terminal device side
  • the steps performed by the network device can be implemented independently as a model management method on the network device side.
  • the present application provides a model management system
  • the model management system includes: an artificial intelligence AI model management module and an AI model management network element;
  • the AI model management module is used to manage network elements with the AI model and execute the first interaction process
  • the AI model management module is a functional module used for AI model management on the terminal device side
  • the AI model management network element is a network element used for AI model management at the data network side. Interact to download or upload AI models for the application layer and/or wireless protocol layer in the end device.
  • the model management system further includes: a first interface; an AI model management module configured to perform a first interaction process with the AI model management network element through the first interface; wherein the first interaction process includes at least one of the following:
  • AI model request process the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element;
  • the AI model notification process is used for the AI model management network element to notify the AI model management module of the target AI model that needs to be uploaded or the target AI model that needs to be sent to the AI model management network element;
  • the capability negotiation process is used for the AI model management module and the AI model management network element to negotiate the target AI model that supports downloading or uploading;
  • the first interface includes a first control plane and a first user plane; wherein, the first control plane is used to execute the AI model request process, the AI model notification process and the capability negotiation process, and the first user plane is used to execute the AI model. Download process and AI model upload process.
  • the AI model management system further includes: a second interface; the AI model management module is configured to perform a second interaction process with a third-party application through the second interface.
  • the AI model management system further includes: a third interface; an AI model management network element for performing a third interaction process with the application server through the third interface; or an AI model management network element for communicating with a third party.
  • the network element performs the fourth interaction process through the third interface, and the third-party network element is another network element except the AI model management network element.
  • the AI model management system further includes: a fourth interface; the AI model management network element is used to perform the fifth interaction process with the capability opening network element in the wireless network through the fourth interface; wherein, the fifth interaction process uses To trigger wireless network to establish dedicated bearer or QoS data flow;
  • the fifth interaction process is used for the AI model management network element to send the AI model to the network element in the wireless network;
  • the fifth interaction process is used for the AI model management network element to obtain the AI model from the wireless network, and/or store the AI model;
  • the fifth interaction process is used for the AI model management network element to receive the request from the network element in the wireless network, and the request is used to request the AI model management network element to send the AI model.
  • the network elements in the wireless network include: capability exposure network elements, and the capability exposure network elements include: at least one of NEF network elements, SCEF network elements, and PCF network elements.
  • the model identification format of the first type AI model is the first type model identification format, and the first type model identification format includes: operator identification and model identification;
  • the model identification format of the second type AI model is the second type model identification format, and the second type model identification format includes: operator identification, model identification and application identification.
  • the value of the model identifier includes: a standardized model identifier value and a non-standardized model identifier value
  • the standardized model identifier value is a value agreed upon through standardization, and corresponds to the AI model of the target type or the AI of the target business. Model or target AI model.
  • the model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
  • the operator identifier is determined by the operator or a third-party application; the application identifier is determined by the operator or a third-party application.
  • FIG. 5 shows a structural diagram of an AI model management system provided by an embodiment of the present application.
  • the AI model management system includes: an AI model management module 501 and an AI model management network element 502 .
  • the AI model management module 501 is introduced on the terminal device side, and the AI model management network element 502 is introduced on the network side.
  • the AI model management module 501 and the AI model management network element 502 may be part of the operator's network. Interface, API) to provide AI model management services for third-party applications.
  • the AI model management module 501 and the AI model management network element 502 can pass the interface 1 (ie, the first interface) in the user plane of the wireless network.
  • the data transmitted by the interface 1 can be transmitted through a protocol data unit (Protocol Data Unit, PDU) session of the wireless network.
  • PDU Protocol Data Unit
  • the AI model management system further includes an interface 2 (ie a second interface) and an interface 3 (ie a third interface).
  • the AI model management module 501 can open related functions of AI management (including AI model storage, download, upload, etc.) to third-party applications in the terminal device through the interface 2 .
  • the AI model management network element 502 can open related functions of AI management (including AI model storage, download, upload, etc.) to third-party applications or other network elements through the interface 3 .
  • the AI model management system further includes an interface 4 (ie, a fourth interface).
  • the AI model management network element 502 can interact with the capability opening network element of the operator's network through the interface 4 .
  • Capability exposure network elements include but are not limited to: NEF network elements, SCEF network elements, and PCF network elements.
  • the AI model management module 501 is connected to the wireless protocol layer 503, and the wireless protocol layer 503 can process the 3GPP protocol.
  • the AI model management module 501 sends the AI model used by the operator to the wireless protocol layer 503 for use. For example, it is used for wireless channel quality optimization, mobility management optimization, session management optimization, UE policy optimization, etc. in the wireless network.
  • the embodiments of the present application provide a model management system, which can use the operator's own cloud computing resources to implement AI model management services, and third-party application providers do not need to use local computer room resources to manage AI models.
  • FIG. 6 is a block diagram of a model management apparatus provided by an exemplary embodiment of the present application.
  • the apparatus is applied in a terminal device, or the apparatus is implemented as a terminal device or a part of the terminal device.
  • the apparatus includes: an AI model management module 601;
  • the AI model management module 601 is configured to manage network elements with the AI model and execute the first interaction process
  • the AI model management module 601 is a functional module used for AI model management on the terminal device side.
  • the AI model management network element is a network element used for AI model management at the data network side.
  • the AI model management module 601 supports and AI model management network elements. Interact to download or upload AI models for the application layer and/or wireless protocol layer in the end device.
  • the AI model management module 601 is configured to perform a first interaction process with an AI model management network element through a first interface; wherein the first interaction process includes at least one of the following:
  • AI model request process the AI model request process is used for the AI model management module 601 to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element;
  • the AI model notification process is used for the AI model management network element to notify the AI model management module 601 of the target AI model to be uploaded or the target AI model to be sent to the AI model management network element;
  • a capability negotiation process which is used for negotiating between the AI model management module 601 and the AI model management network element to support downloading or uploading of the target AI model;
  • the first interface includes a first control plane and a first user plane; wherein, the first control plane is used to execute an AI model request process, an AI model notification process, and a capability negotiation process, and the first user plane It is used to execute the AI model download process and the AI model upload process.
  • the AI model management module 601 is configured to perform a second interaction process with a third-party application through a second interface.
  • the AI model in the AI model management module 601 includes at least one of the following: a first type of AI model and a second type of AI model; wherein the first type of AI model corresponds to the operator, the second type of AI model Type AI models correspond to third-party applications.
  • the model identification format of the first type AI model is the first type model identification format, and the first type model identification format includes: an operator identification and a model identification; the model identification format of the second type AI model For the second type of model identification format, the second type of model identification format includes at least one of the following: an operator identification, an application identification and a model identification.
  • the value of the model identification includes: a standardized model identification value and a non-standardized model identification value
  • the standardized model identification value is a value agreed through standardization, and corresponds to the AI model of the target type. Or the AI model of the target business or the target AI model.
  • the model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
  • the operator identifier is determined by the operator or a third-party application; the application identifier is determined by the operator or a third-party application.
  • FIG. 7 is a block diagram of a model management apparatus provided by an exemplary embodiment of the present application.
  • the apparatus is applied in a network device, or the apparatus is implemented as a network device or a part of the network device.
  • the apparatus includes: an AI model management network element module 701;
  • the AI model management network element module 701 is configured to execute the first interaction process with the AI model management module
  • the AI model management module is a functional module used for AI model management at the terminal device side
  • the AI model management network element module 701 is a network element module used for AI model management at the data network side.
  • the management network element module 701 interacts to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  • the AI model management network element module 701 is configured to execute a first interaction process with the AI model management module through a first interface; wherein the first interaction process includes at least one of the following:
  • AI model request process the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element module 701 or upload the target AI model to the AI model management network element;
  • the AI model notification process is used for the AI model management network element module 701 to notify the AI model management module of the target AI model that needs to be uploaded or the target AI model that needs to be sent to the AI model management network element;
  • a capability negotiation process is used for negotiating between the AI model management module and the AI model management network element module 701 to support the download or upload of the target AI model;
  • the first interface includes a first control plane and a first user plane; wherein, the first control plane is used to execute an AI model request process, an AI model notification process, and a capability negotiation process, and the first user plane It is used to execute the AI model download process and the AI model upload process.
  • the AI model management network element module 701 is configured to perform a third interaction process with the application server through a third interface; or, the AI model management network element module 701 is configured to communicate with a third-party network element , the fourth interaction process is performed through the third interface, and the third-party network element is other network element except the AI model management network element.
  • the AI model management network element module 701 is configured to perform a fifth interaction process with network elements in the wireless network through a fourth interface; wherein, the fifth interaction process is used to trigger the wireless network to establish a special There is a bearer or QoS data flow; or, the fifth interaction process is used for the AI model management network element module 701 to send the AI model to the network element in the wireless network; or, the fifth interaction process is used for the AI model management network element module 701 from the wireless network Obtaining the AI model in the network, and/or storing the AI model; or, the fifth interaction process is used for the AI model management network element module 701 to receive a request from a network element in the wireless network, and the request is used to request the AI model management network element module 701 Send AI model.
  • the network elements in the wireless network include: a capability opening network element, and the capability opening network element includes: a network opening function NEF network element, a service capability opening function SCEF network element, and a policy control function PCF network element at least one of.
  • the AI model in the AI model management network element module 701 includes at least one of the following: a first type AI model and a second type AI model; wherein the first type AI model corresponds to an operator, The second type of AI model corresponds to third-party applications.
  • the model identification format of the first-type AI model is the first-type model identification format
  • the first-type model identification format includes: an operator identification and a model identification
  • the model identification format of the second type AI model is the second type model identification format, and the second type model identification format includes at least one of the following: an operator identification, a model identification and an application identification.
  • the value of the model identification includes: a standardized model identification value and a non-standardized model identification value
  • the standardized model identification value is a model identification value agreed upon through standardization, and corresponds to the target type.
  • the model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
  • the operator identifier is determined by the operator or a third-party application; the application identifier is determined by the operator or a third-party application.
  • FIG. 8 shows a schematic structural diagram of a communication device provided by an exemplary embodiment of the present application.
  • the communication device includes: a processor 101 , a receiver 102 , a transmitter 103 , a memory 104 , and a bus 105 .
  • the processor 101 includes one or more processing cores, and the processor 101 executes various functional applications and information processing by running software programs and modules.
  • the receiver 102 and the transmitter 103 may be implemented as a communication component, which may be a communication chip.
  • the memory 104 is connected to the processor 101 through the bus 105 .
  • the memory 104 may be configured to store at least one instruction, and the processor 101 may be configured to execute the at least one instruction, so as to implement various steps in the foregoing method embodiments.
  • memory 104 may be implemented by any type or combination of volatile or non-volatile storage devices including, but not limited to, magnetic or optical disks, electrically erasable and programmable Read Only Memory (Electrically-Erasable Programmable Read Only Memory, EEPROM), Erasable Programmable Read Only Memory (EPROM), Static Random Access Memory (SRAM), Read Only Memory (Read-Only Memory, ROM), magnetic memory, flash memory, programmable read-only memory (Programmable Read-Only Memory, PROM).
  • volatile or non-volatile storage devices including, but not limited to, magnetic or optical disks, electrically erasable and programmable Read Only Memory (Electrically-Erasable Programmable Read Only Memory, EEPROM), Erasable Programmable Read Only Memory (EPROM), Static Random Access Memory (SRAM), Read Only Memory (Read-Only Memory, ROM), magnetic memory, flash memory, programmable read-only memory (Programmable Read-Only Memory, PROM).
  • a computer-readable storage medium stores at least one instruction, at least one piece of program, code set or instruction set, the at least one instruction, the At least one section of program, the code set or the instruction set is loaded and executed by the processor to implement the model management method executed by the terminal device or the model management method executed by the data network provided by the above method embodiments.
  • a computer program product or computer program comprising computer instructions stored in a computer readable storage medium from which a processor of a computer device can
  • the computer instructions are read from the storage medium, and the processor executes the computer instructions, so that the computer device executes the model management method described in the above aspects.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Security & Cryptography (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The present application relates to the field of mobile communications. Disclosed are a model management method, system and apparatus, a communication device, and a storage medium. The method is applied to a terminal device. The terminal device comprises: an AI model management module. The method comprises: the AI model management module and an AI model management network element perform a first interaction process; the AI model management module is a functional module used by the terminal device to perform AI model management; the AI model management network element is a network element used by a data network to perform AI model management; the AI model management module supports interaction with the AI model management network element, so as to download or upload an AI model for an application layer and/or a wireless protocol layer in the terminal device.

Description

模型管理方法、系统、装置、通信设备及存储介质Model management method, system, device, communication device and storage medium 技术领域technical field
本申请涉及移动通信领域，特别涉及一种模型管理方法、系统、装置、通信设备及存储介质。The present application relates to the field of mobile communications, and in particular, to a model management method, system, apparatus, communication device and storage medium.
背景技术Background technique
随着人工智能(Artificial Intelligence，AI)技术的发展，基于AI模型进行大数据分析已成为一种趋势。With the development of artificial intelligence (AI) technology, big data analysis based on AI model has become a trend.
在终端设备使用AI模型，参与进行大数据分析的情况下，AI模型对应的应用的第三方应用商需要对终端设备使用的AI模型进行存储与管理。When the terminal device uses the AI model and participates in big data analysis, the third-party application provider of the application corresponding to the AI model needs to store and manage the AI model used by the terminal device.
由于单个AI模型对应的存储空间较大，且终端设备使用的AI模型的数量也较多，第三方应用商在进行AI模型管理时，资源开销较大。Because the storage space corresponding to a single AI model is large, and the number of AI models used by terminal devices is also large, third-party application providers have high resource overhead when managing AI models.
发明内容SUMMARY OF THE INVENTION
本申请实施例提供了一种模型管理方法、系统、装置、通信设备及存储介质，可以无需占用第三方应用商本地的机房资源进行AI模型的管理，保障企业的资源使用。所述技术方案如下。The embodiments of the present application provide a model management method, system, device, communication device, and storage medium, which can manage AI models without occupying the local computer room resources of a third-party application provider, and ensure resource usage of the enterprise. The technical solution is as follows.
根据本申请的一个方面，提供了一种模型管理方法，应用于终端设备中，所述终端设备包括：AI模型管理模块，所述方法包括：According to an aspect of the present application, a model management method is provided, which is applied to a terminal device, where the terminal device includes: an AI model management module, and the method includes:
所述AI模型管理模块与AI模型管理网元，执行第一交互流程；The AI model management module and the AI model management network element execute the first interaction process;
所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元是数据网络端用于进行AI模型管理的网元，所述AI模型管理模块支持与所述AI模型管理网元交互，以便为所述终端设备中的应用层和/或无线协议层下载或上传AI模型。The AI model management module is a functional module used for AI model management at the terminal device side, the AI model management network element is a network element used for AI model management at the data network side, and the AI model management module supports and The AI model manages network element interactions in order to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
根据本申请的一个方面，提供了一种模型管理方法，应用于数据网络中，所述数据网络包括：AI模型管理网元，所述方法包括：According to an aspect of the present application, a model management method is provided, which is applied in a data network, where the data network includes: an AI model management network element, and the method includes:
所述AI模型管理网元与AI模型管理模块，执行第一交互流程；The AI model management network element and the AI model management module execute the first interaction process;
其中，所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元是数据网络端用于进行AI模型管理的网元，所述AI模型管理模块支持与所述AI模型管理网元交互，以便为所述终端设备中的应用层和/或无线协议层下载或上传AI模型。Wherein, the AI model management module is a functional module used for AI model management at the terminal device side, the AI model management network element is a network element used for AI model management at the data network side, and the AI model management module supports Interact with the AI model management network element to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
根据本申请的一个方面，提供了一种模型管理系统，所述模型管理系统包括：AI模型管理模块和AI模型管理网元；According to an aspect of the present application, a model management system is provided, the model management system comprising: an AI model management module and an AI model management network element;
所述AI模型管理模块，用于与所述AI模型管理网元，执行第一交互流程；The AI model management module is configured to manage network elements with the AI model and execute a first interaction process;
其中，所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元是数据网络端用于进行AI模型管理的网元，所述AI模型管理模块支持与所述AI模型管理网元交互，以便为所述终端设备中的应用层和/或无线协议层下载或上传AI模型。Wherein, the AI model management module is a functional module used for AI model management at the terminal device side, the AI model management network element is a network element used for AI model management at the data network side, and the AI model management module supports Interact with the AI model management network element to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
根据本申请的一个方面，提供了一种模型管理装置，应用于终端设备中，所述装置包括：AI模型管理模块；According to an aspect of the present application, a model management apparatus is provided, which is applied in a terminal device, and the apparatus includes: an AI model management module;
所述AI模型管理模块，用于与AI模型管理网元，执行第一交互流程；The AI model management module is used to manage network elements with the AI model and execute the first interaction process;
所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元是数据网络端用于进行AI模型管理的网元，所述AI模型管理模块支持与所述AI模型管理网元交互，以便为所述终端设备中的应用层和/或无线协议层下载或上传AI模型。The AI model management module is a functional module used for AI model management at the terminal device side, the AI model management network element is a network element used for AI model management at the data network side, and the AI model management module supports and The AI model manages network element interactions in order to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
根据本申请的一个方面，提供了一种模型管理装置，应用于数据网络中，所述装置包括：According to an aspect of the present application, a model management apparatus is provided, applied in a data network, the apparatus includes:
AI模型管理网元模块；AI model manages network element modules;
所述AI模型管理网元模块，用于与AI模型管理模块，执行第一交互流程；The AI model management network element module is used for executing the first interaction process with the AI model management module;
其中，所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元模块是数据网络端用于进行AI模型管理的网元模块，所述AI模型管理模块支持与所述AI模型管理网元模块交互，以便为所述终端设备中的应用层和/或无线协议层下载或上传AI模型。Wherein, the AI model management module is a functional module used for AI model management at the terminal device side, the AI model management network element module is a network element module used for AI model management at the data network side, and the AI model management The module supports interaction with the AI model management network element module, so as to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
根据本申请的一个方面，提供了一种终端设备，所述终端设备包括：处理器；与所述处理器相连的收发器；用于存储所述处理器的可执行指令的存储器；其中，所述处理器被配置为加载并执行所述可执行指令以实现如上述方面所述的模型管理方法。According to an aspect of the present application, a terminal device is provided, the terminal device comprising: a processor; a transceiver connected to the processor; a memory for storing executable instructions of the processor; The processor is configured to load and execute the executable instructions to implement the model management method as described in the above aspects.
根据本申请的一个方面，提供了一种数据网络，所述数据网络包括：处理器；与所述处理器相连的收发器；用于存储所述处理器的可执行指令的存储器；其中，所述处理器被配置为加载并执行所述可执行指令以实现如上述方面所述的模型管理方法。According to one aspect of the present application, a data network is provided, the data network comprising: a processor; a transceiver connected to the processor; a memory for storing executable instructions of the processor; wherein the The processor is configured to load and execute the executable instructions to implement the model management method as described in the above aspects.
根据本申请的一个方面，提供了一种计算机可读存储介质，所述可读存储介质中存储有可执行指令，所述可执行指令由处理器加载并执行以实现如上述方面所述的模型管理方法。According to one aspect of the present application, there is provided a computer-readable storage medium having executable instructions stored in the readable storage medium, the executable instructions being loaded and executed by a processor to implement the model as described in the above aspect management method.
根据本申请的一个方面，提供了一种计算机程序产品或计算机程序，该计算机程序产品或计算机程序包括计算机指令，该计算机指令存储在计算机可读存储介质中，计算机设备的处理器从计算机可读存储介质读取该计算机指令，处理器执行该计算机指令，使得该计算机设备执行上述方面所述的模型管理方法。According to one aspect of the present application, there is provided a computer program product or computer program, the computer program product or computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium, the processor of the computer device being readable from the computer The storage medium reads the computer instructions, and the processor executes the computer instructions, so that the computer device executes the model management method described in the above aspects.
本申请实施例提供的技术方案至少包括如下有益效果：The technical solutions provided by the embodiments of the present application include at least the following beneficial effects:
将AI模型管理的任务交由AI模型管理模块与AI模型管理网元执行，由于AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，AI模型管理网元是数据网络端用于进行AI模型管理的网元，则无需占用第三方应用商本地的机房资源进行AI模型的管理，保障企业的资源使用。The task of AI model management is handed over to the AI model management module and AI model management network element. Since the AI model management module is a functional module used for AI model management on the terminal device side, the AI model management network element is used by the data network side. NEs for AI model management do not need to occupy the local computer room resources of third-party application providers to manage AI models, ensuring enterprise resource usage.
附图说明Description of drawings
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort.
图1是本申请一个示例性实施例提供的基于AI模型进行大数据分析的场景示意图；1 is a schematic diagram of a scenario of performing big data analysis based on an AI model provided by an exemplary embodiment of the present application;
图2是本申请一个示例性实施例提供的通信系统的示意图；FIG. 2 is a schematic diagram of a communication system provided by an exemplary embodiment of the present application;
图3是本申请一个示例性实施例提供的模型管理方法的流程图；3 is a flowchart of a model management method provided by an exemplary embodiment of the present application;
图4是本申请一个示例性实施例提供的模型管理方法的示意图；4 is a schematic diagram of a model management method provided by an exemplary embodiment of the present application;
图5是本申请一个示例性实施例提供的模型管理系统的示意图；5 is a schematic diagram of a model management system provided by an exemplary embodiment of the present application;
图6是本申请一个示例性实施例提供的模型管理装置的结构框图；6 is a structural block diagram of an apparatus for model management provided by an exemplary embodiment of the present application;
图7是本申请一个示例性实施例提供的模型管理装置的结构框图；FIG. 7 is a structural block diagram of a model management apparatus provided by an exemplary embodiment of the present application;
图8是本申请一个示例性实施例提供的通信设备的结构示意图。FIG. 8 is a schematic structural diagram of a communication device provided by an exemplary embodiment of the present application.
具体实施方式detailed description
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。In order to make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.
首先，对本申请实施例中涉及的名词进行简单介绍：First, briefly introduce the terms involved in the embodiments of the present application:
人工智能(Artificial Intelligence,AI)是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能，感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。换句话说，人工智能是计算机科学的一个综合技术，它企图了解智能的实质，并生产出一种新的能以人类智能相似的方式做出反应的智能机器。人工智能也就是研究各种智能机器的设计原理与实现方法，使机器具有感知、推理与决策的功能。Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.
人工智能技术是一门综合学科，涉及领域广泛，既有硬件层面的技术也有软件层面的技术。人工智能基础技术一般包括如传感器、专用人工智能芯片、云计算、分布式存储、大数据处理技术、操作/交互系统、机电一体化等技术。人工智能软件技术主要包括计算机视觉技术、语音处理技术、自然语言处理技术以及机器学习/深度学习等几大方向。Artificial intelligence technology is a comprehensive discipline, involving a wide range of fields, including both hardware-level technology and software-level technology. The basic technologies of artificial intelligence generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation/interaction systems, and mechatronics. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning/deep learning.
其中，AI模型是与人工智能技术对应的模型。Among them, the AI model is a model corresponding to artificial intelligence technology.
在基于AI模型进行大数据分析的场景下，为了能够提升大数据分析的效果和用户体验，可以考虑采用多级AI模型的方式，即网络侧的网元和终端设备分工进行大数据分析。In the scenario of big data analysis based on the AI model, in order to improve the effect of big data analysis and user experience, a multi-level AI model can be considered, that is, the network elements and terminal devices on the network side divide the labor for big data analysis.
图1中的a)为集中式场景，即所有终端设备将需要的数据上报后，大数据分析工作全都在网络侧的服务器进行。图1中的b)为完全分布式场景，即不同的终端设备对于采集的数据本地进行分析。图1中的c)为混合式场景，即终端设备对于采集的数据在本地进行一部分的分析后，将结果发送给网络侧的服务器，进行进一步的计算分析。此外，在b)和c)的方式下，还可能引入终端设备和终端设备之间的数据交互以完成大数据分析或结果共享。a) in Figure 1 is a centralized scenario, that is, after all terminal devices report the required data, the big data analysis work is all performed on the server on the network side. b) in Fig. 1 is a completely distributed scenario, that is, different terminal devices analyze the collected data locally. c) in FIG. 1 is a hybrid scenario, that is, after the terminal device analyzes a part of the collected data locally, it sends the result to the server on the network side for further calculation and analysis. In addition, in the manners of b) and c), data interaction between terminal devices and terminal devices may also be introduced to complete big data analysis or result sharing.
在上述场景中，AI模型具有如下特点：In the above scenario, the AI model has the following characteristics:
1)AI模型的种类繁杂，不同的第三方应用商以及不同的条件下，使用的AI模型不同。1) There are various types of AI models. Different third-party application providers and under different conditions use different AI models.
2)由于很多AI业务具有按地域和时间划分的特殊性，终端设备在不同的地域和时间可能需要使用不同的AI模型。2) Due to the particularity of many AI services divided by region and time, terminal devices may need to use different AI models in different regions and times.
3)对于机器学习、分布式AI计算等业务，AI模型需要进行频繁更新。3) For businesses such as machine learning and distributed AI computing, the AI model needs to be updated frequently.
4)一个AI模型可能需要上百兆甚至更大的存储空间，终端设备不可能将所有的模型都存储在本地，因此需要能够实时、准确的更新AI模型。4) An AI model may require hundreds of megabytes or even larger storage space. It is impossible for terminal devices to store all models locally, so it is necessary to update the AI model in real time and accurately.
由上述对AI模型的特点的描述可知，AI模型的种类很多，数量庞大，更新频繁，若由企业利用本地的机房资源对AI模型进行管理，需要的资源开销较大。From the above description of the characteristics of AI models, it can be seen that there are many types of AI models, a large number, and frequent updates. If the enterprise uses the local computer room resources to manage the AI model, the resource overhead required is relatively large.
图2示出了本申请一个示例性实施例提供的通信系统的框图，该通信系统可以包括：终端设备12、(无线)接入网络((R)AN)14、核心网16和数据网络(Data Network，DN)18。FIG. 2 shows a block diagram of a communication system provided by an exemplary embodiment of the present application. The communication system may include: a terminal device 12, a (wireless) access network ((R)AN) 14, a core network 16 and a data network ( Data Network, DN) 18.
其中，终端设备12可以包括各种具有无线通信功能的手持设备、车载设备、可穿戴设备、 计算设备或连接到无线调制解调器的其他处理设备，以及各种形式的用户设备，移动台(Mobile Station，MS)，终端(terminal device)等等。为方便描述，上面提到的设备统称为终端设备。Wherein, the terminal device 12 may include various handheld devices, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to wireless modems with wireless communication functions, as well as various forms of user equipment, mobile stations (Mobile Station, MS), terminal device, etc. For the convenience of description, the devices mentioned above are collectively referred to as terminal devices.
接入网络14中包括若干个网络设备。网络设备可以是基站，所述基站是一种部署在接入网中用以为终端提供无线通信功能的装置。基站可以包括各种形式的宏基站，微基站，中继站，接入点等等。在采用不同的无线接入技术的系统中，具备基站功能的设备的名称可能会有所不同，例如在LTE系统中，称为eNodeB或者eNB；在5G NR-U系统中，称为gNodeB或者gNB。随着通信技术的演进，“基站”这一描述可能会变化。为方便本申请实施例中，上述为终端设备提供无线通信功能的装置统称为网络设备。The access network 14 includes several network devices. The network device may be a base station, which is a device deployed in an access network to provide a wireless communication function for a terminal. The base station may include various forms of macro base station, micro base station, relay station, access point and so on. In systems using different radio access technologies, the names of devices with base station functions may be different. For example, in LTE systems, they are called eNodeBs or eNBs; in 5G NR-U systems, they are called gNodeBs or gNBs. . As communication technology evolves, the description of "base station" may change. For convenience, in the embodiments of the present application, the above-mentioned apparatuses for providing wireless communication functions for terminal equipment are collectively referred to as network equipment.
核心网16可以包括：用户平面功能(User Plane Function，UPF)和控制平面功能。控制平面功能可以包括：接入和移动管理功能(Access and Mobility Management Function，AMF)、会话管理功能(Session Management Function，SMF)、控制策略功能(Policy Control Function，PCF)和统一数据管理(Unified Data Manager，UDM)、应用功能(Application Function，AF)、网络切片选择功能(Network Slice Selection Function，NSSF)、认证服务功能(Authentication Server Function，AUSF)。The core network 16 may include: a user plane function (User Plane Function, UPF) and a control plane function. The control plane functions may include: Access and Mobility Management Function (AMF), Session Management Function (SMF), Policy Control Function (PCF) and Unified Data Management (Unified Data) Manager, UDM), application function (Application Function, AF), network slice selection function (Network Slice Selection Function, NSSF), authentication service function (Authentication Server Function, AUSF).
无线网络可以包括接入网络14和核心网16，无线网络中的不同网元可以具体对应于接入网的基站或核心网的各种功能网元(如SMF、PCF、AMF等)。The wireless network may include an access network 14 and a core network 16, and different network elements in the wireless network may specifically correspond to base stations of the access network or various functional network elements (such as SMF, PCF, AMF, etc.) of the core network.
终端设备12与接入网络14中的网络设备之间通过某种空口技术互相通信，例如Uu接口。核心网16可以通过N6接口与外部数据网络18进行数据传输，通过N3接口与接入网络14进行数据传输。The terminal device 12 and the network devices in the access network 14 communicate with each other through a certain air interface technology, such as a Uu interface. The core network 16 can perform data transmission with the external data network 18 through the N6 interface, and can perform data transmission with the access network 14 through the N3 interface.
本申请实施例的技术方案可以应用于各种通信系统，例如：全球移动通讯(Global System of Mobile Communication，GSM)系统、码分多址(Code Division Multiple Access，CDMA)系统、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)系统、通用分组无线业务(General Packet Radio Service，GPRS)、长期演进(Long Term Evolution，LTE)系统、LTE频分双工(Frequency Division Duplex，FDD)系统、LTE时分双工(Time Division Duplex，TDD)系统、先进的长期演进(Advanced Long Term Evolution，LTE-A)系统、新无线(New Radio，NR)系统、NR系统的演进系统、非授权频段上的LTE(LTE-based access to Unlicensed spectrum，LTE-U)系统、NR-U系统、通用移动通信系统(Universal Mobile Telecommunication System，UMTS)、全球互联微波接入(Worldwide Interoperability for Microwave Access，WiMAX)通信系统、无线局域网(Wireless Local Area Networks，WLAN)、无线保真(Wireless Fidelity，WiFi)、下一代通信系统或其他通信系统等。The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile Communication (GSM) system, Code Division Multiple Access (CDMA) system, wideband Code Division Multiple Access (CDMA) system (Wideband Code Division Multiple Access, WCDMA) system, General Packet Radio Service (General Packet Radio Service, GPRS), Long Term Evolution (Long Term Evolution, LTE) system, LTE Frequency Division Duplex (Frequency Division Duplex, FDD) system, LTE Time Division Duplex (TDD) systems, Advanced Long Term Evolution (LTE-A) systems, New Radio (NR) systems, evolution systems of NR systems, LTE on unlicensed frequency bands (LTE-based access to Unlicensed spectrum, LTE-U) system, NR-U system, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) communication system, Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), next-generation communication systems or other communication systems, etc.
通常来说，传统的通信系统支持的连接数有限，也易于实现，然而，随着通信技术的发展，移动通信系统将不仅支持传统的通信，还将支持例如，设备到设备(Device to Device，D2D)通信，机器到机器(Machine to Machine，M2M)通信，机器类型通信(Machine Type Communication，MTC)，车辆间(Vehicle to Vehicle，V2V)通信以及车联网(Vehicle to Everything，V2X)系统等。本申请实施例也可以应用于这些通信系统。Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication, but also support, for example, Device to Device (Device to Device, D2D) communication, Machine to Machine (M2M) communication, Machine Type Communication (MTC), Vehicle to Vehicle (V2V) communication and Vehicle to Everything (V2X) system, etc. The embodiments of the present application can also be applied to these communication systems.
图3示出了本申请的一个示例性实施例提供的模型管理方法的流程图。本实施例以该方法应用于图2所示的通信系统中进行示例性的说明，该方法包括：FIG. 3 shows a flowchart of a model management method provided by an exemplary embodiment of the present application. This embodiment is exemplarily described by applying the method to the communication system shown in FIG. 2 , and the method includes:
步骤310，AI模型管理模块与AI模型管理网元，执行第一交互流程。Step 310, the AI model management module and the AI model management network element perform a first interaction process.
终端设备包括若干个功能模块，用于实现不同的功能。其中，AI模型管理模块是终端设备端用于进行AI模型管理的功能模块。The terminal device includes several functional modules for implementing different functions. Among them, the AI model management module is a functional module used for AI model management on the terminal device side.
终端设备安装有若干个应用，这些应用需要利用AI模型执行相应的AI业务。AI模型管理模块支持与AI模型管理网元交互，以便为终端设备中的应用层和/或无线协议层下载或上传AI模型。无线协议层是支持处理3GPP协议的协议层，本申请实施例对无线协议层的具体实现形式不进行限定。Several applications are installed on the terminal device, and these applications need to use the AI model to perform corresponding AI services. The AI model management module supports interaction with AI model management network elements to download or upload AI models for the application layer and/or wireless protocol layer in the terminal device. The radio protocol layer is a protocol layer that supports processing the 3GPP protocol, and the specific implementation form of the radio protocol layer is not limited in this embodiment of the present application.
AI模型管理网元是数据网络端用于进行AI模型管理的网元。可选地，本申请实施例对AI模型管理网元的具体实现形式不进行限定，AI模型管理网元可以是现有的网元，也可以是新增的网元，用于进行AI模型管理。The AI model management network element is the network element used for AI model management on the data network side. Optionally, this embodiment of the present application does not limit the specific implementation form of the AI model management network element, and the AI model management network element may be an existing network element or a newly added network element, which is used for AI model management. .
第一交互流程是AI模型管理模块与AI模型管理网元之间的交互流程。第一交互流程用于实现AI模型的下载或上传。The first interaction process is an interaction process between the AI model management module and the AI model management network element. The first interaction process is used to implement downloading or uploading of the AI model.
可选地，AI模型管理模块与AI模型管理网元均是对应于同一运营商的功能模块或网元，AI模型管理模块与AI模型管理网元是运营商网络中的一部分。Optionally, both the AI model management module and the AI model management network element are functional modules or network elements corresponding to the same operator, and the AI model management module and the AI model management network element are part of the operator's network.
可选地，AI模型管理模块与AI模型管理网元除了进行第一交互流程，实现AI模型的下载或上传之外，还支持对AI模型进行压缩和解压缩，以用于AI模型内容的传输或存储。Optionally, in addition to the first interaction process between the AI model management module and the AI model management network element, in addition to downloading or uploading the AI model, the AI model management module also supports compression and decompression of the AI model for the transmission of AI model content or storage.
综上所述，本实施例提供的方法，将AI模型管理的任务交由AI模型管理模块与AI模型管理网元执行，由于AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，AI模型管理网元是数据网络端用于进行AI模型管理的网元，则无需占用第三方应用商本地的机房资源进行AI模型的管理，保障企业的资源使用。To sum up, in the method provided in this embodiment, the task of AI model management is handed over to the AI model management module and the AI model management network element for execution, because the AI model management module is a functional module used for AI model management on the terminal device side. , AI model management network element is the network element used for AI model management on the data network side, so there is no need to occupy the local computer room resources of third-party application providers to manage AI models, ensuring enterprise resource usage.
在本申请的所有实施例中，AI模型的模型管理方法可以结合本申请的任意一个实施例一起使用，也可以单独使用，本申请实施例并不对此做出限定。但是为了使得技术方案更容易被理解，本申请的以下实施例结合前述的实施例进行举例说明。In all the embodiments of the present application, the model management method of the AI model may be used in combination with any one of the embodiments of the present application, or may be used alone, which is not limited in the embodiments of the present application. However, in order to make the technical solution easier to understand, the following embodiments of the present application are illustrated in combination with the foregoing embodiments.
在基于图3的可选实施例中，AI模型管理模块与AI模型管理网元中的AI模型可以包括但不限于：第一类型AI模型和第二类型AI模型。In an optional embodiment based on FIG. 3 , the AI model in the AI model management module and the AI model management network element may include, but not limited to, the first type of AI model and the second type of AI model.
其中，第一类型AI模型对应于运营商，第二类型AI模型对应于第三方应用(如来自于应用或服务提供商)。运营商是为公众提供陆地移动通信业务目的而建立和经营网络的经营者。第三方应用是针对终端设备而开发的应用。也就是说，第一类型AI模型是运营商的AI模型，第二类型AI模型是第三方应用的AI模型。The first type of AI model corresponds to an operator, and the second type of AI model corresponds to a third-party application (eg, from an application or a service provider). An operator is an operator who establishes and operates a network for the purpose of providing land mobile communication services to the public. Third-party applications are applications developed for terminal devices. That is to say, the first type of AI model is the AI model of the operator, and the second type of AI model is the AI model of the third-party application.
AI模型对应有AI模型标识。可选地，上述两种类型的AI模型的AI模型标识对应于相同或不同的模型标识格式。其中，第一类型AI模型的模型标识格式为第一类型模型标识格式，第二类型AI模型的模型标识格式为第二类型模型标识格式。The AI model corresponds to the AI model logo. Optionally, the AI model identifiers of the above two types of AI models correspond to the same or different model identifier formats. The model identification format of the first type AI model is the first type model identification format, and the model identification format of the second type AI model is the second type model identification format.
可选地，第一类型模型标识格式和第二类型模型标识格式不同，可以指的是两种类型的模型标识格式所包含的标识类型不同；或，不同标识类型在格式中的位置不同；或，不同标识类型的位数不同。Optionally, the difference between the first type of model identification format and the second type of model identification format may mean that the identification types contained in the two types of model identification formats are different; or, the positions of different identification types in the formats are different; or , the number of digits for different identification types is different.
示例性的，第一类型模型标识格式包括：运营商标识和模型标识。Exemplarily, the first type of model identification format includes: operator identification and model identification.
其中，运营商标识可以记为PLMN ID，用于区分不同运营商。模型标识可以记为Model Id，用于标识模型。Among them, the operator identifier can be recorded as PLMN ID, which is used to distinguish different operators. The model ID can be recorded as Model Id, which is used to identify the model.
示例性的，第二类型AI模型的模型标识格式为第二类型模型标识格式，第二类型模型标识格式包括如下至少之一：运营商标识、应用标识和模型标识。Exemplarily, the model identification format of the second type AI model is the second type model identification format, and the second type model identification format includes at least one of the following: an operator identification, an application identification and a model identification.
在一种实现方式中，第二类型模型标识格式包括：运营商标识、应用标识和模型标识；在另一种实现方式中，第二类型模型标识格式包括：应用标识和模型标识。In one implementation, the second type of model identification format includes: operator identification, application identification and model identification; in another implementation, the second type of model identification format includes: application identification and model identification.
其中，运营商标识可以记为PLMN ID，用于区分不同运营商。应用标识可以记为Application Id，用于标识第三方应用。模型标识可以记为Model Id，用于标识模型。Among them, the operator identifier can be recorded as PLMN ID, which is used to distinguish different operators. The application identifier can be recorded as Application Id, which is used to identify third-party applications. The model ID can be recorded as Model Id, which is used to identify the model.
针对上述两种类型的模型标识格式中的运营商标识和应用标识，运营商标识可以由运营商或第三方应用确定，应用标识可以由运营商或第三方应用确定。For the operator identification and application identification in the above two types of model identification formats, the operator identification may be determined by the operator or a third-party application, and the application identification may be determined by the operator or a third-party application.
针对上述两种类型的模型标识格式中的模型标识，模型标识可以包括：模型类型标识(Type Id)、模型结构参数标识(Structure Id)和模型权重参数标识(Weight Id)中的至少一种。For the model identifiers in the above two types of model identifier formats, the model identifiers may include at least one of: model type identifiers (Type Id), model structure parameter identifiers (Structure Id), and model weight parameter identifiers (Weight Id).
其中，模型类型标识用于标识AI模型的类型，AI模型的类型包括但不限于：深度神经网络(Deep Neural Network，DNN)模型、卷积神经网络(Convolution Neural Networks，CNN)模型、循环神经网络(Recurrent Neural Networks，RNN)模型中的至少一种。Among them, the model type identifier is used to identify the type of AI model, and the types of AI models include but are not limited to: Deep Neural Network (DNN) model, Convolution Neural Networks (CNN) model, Recurrent Neural Network At least one of the (Recurrent Neural Networks, RNN) models.
模型结构参数标识用于标识模型的结构。示例性的，针对DNN模型，其内部的神经网络层可以分为三类：输入层，隐藏层和输出层。一般来说第一层是输入层，最后一层是输出层，而中间的层数都是隐藏层。The model structure parameter identifies the structure used to identify the model. Exemplarily, for the DNN model, its internal neural network layers can be divided into three categories: input layer, hidden layer and output layer. Generally speaking, the first layer is the input layer, the last layer is the output layer, and the middle layers are all hidden layers.
模型权重参数标识用于标识模型使用的权重值。示例性的，针对DNN模型，每一层都需要使用特定的算法、权重值、常量等将上一层的样本参数进行计算得到输出结果，该输出结果作为下一层的输入以便计算下下一层的输出，最终得到输出层(output layer)的结果。The model weight parameter identifies the weight value used to identify the model. Exemplarily, for the DNN model, each layer needs to use a specific algorithm, weight value, constant, etc. to calculate the sample parameters of the previous layer to obtain the output result, and the output result is used as the input of the next layer to calculate the next layer. The output of the layer, and finally the result of the output layer.
针对上述两种类型的模型标识格式中的模型标识，模型标识的取值或部分取值可以包括：标准化模型标识取值和非标准化模型标识取值。For the model identifiers in the above two types of model identifier formats, the values or partial values of the model identifiers may include: standardized model identifier values and non-standardized model identifier values.
其中，标准化模型标识取值是通过标准化约定好的取值，对应于目标类型的AI模型或目标业务的AI模型或目标AI模型。The value of the standardized model identifier is a value agreed upon through standardization, and corresponds to the AI model of the target type or the AI model of the target business or the target AI model.
通过标准化，可以约定一个或多个模型标识的取值或部分取值作为标准化模型标识取值。示例性的，对于取值为000010的模型标识，意味着该AI模型是用于处理视频业务这一目标业务的AI模型；对于取值为000011的模型标识，意味着该AI模型是对应于CNN这一目标类型的AI模型；对于取值为000012的模型标识，意味着该AI模型是用于自动驾驶这一目标业务的目标AI模型。Through standardization, the value or partial value of one or more model identifiers can be agreed as the value of the standardized model identifier. Exemplarily, for a model identifier with a value of 000010, it means that the AI model is an AI model for processing the target service of the video service; for a model identifier with a value of 000011, it means that the AI model corresponds to CNN. The AI model of this target type; for the model identifier whose value is 000012, it means that the AI model is the target AI model for the target business of autonomous driving.
其中，非标准化模型标识取值是由运营商或第三方应用确定的模型标识取值。在不同运营商或不同第三方应用中，可以定义同一非标准化模型取值对应于不同的AI模型。如：100001是非标准化模型标识取值，在运营商A中，模式标识取值是100001的AI模型是CNN模型，而运营商B中，模式标识取值是100001的AI模型是RNN模型。或者，运营商A的100001取值的AI模型是用于自动驾驶业务，运营商B的100001取值的AI模型适用于增强现实(Artificial Reality，AR)/虚拟现实(Virtual Reality，VR)业务。The value of the non-standardized model identifier is the value of the model identifier determined by the operator or a third-party application. In different operators or different third-party applications, the same non-standardized model value can be defined to correspond to different AI models. For example, 100001 is the non-standardized model ID value. In operator A, the AI model whose mode ID value is 100001 is a CNN model, while in operator B, the AI model whose mode ID value is 100001 is an RNN model. Alternatively, the AI model with the value of 100001 of operator A is used for the autonomous driving service, and the AI model of the operator B with the value of 100001 is suitable for the augmented reality (Artificial Reality, AR)/virtual reality (Virtual Reality, VR) service.
同时，在基于图3的可选实施例中，还存在如下接口，用于实现AI模型管理。可以理解的是，通过上述实施例所述的AI模型标识来进行交互。Meanwhile, in the optional embodiment based on FIG. 3 , there are also the following interfaces for implementing AI model management. It can be understood that the interaction is performed through the AI model identifiers described in the above embodiments.
一、第一接口。1. The first interface.
第一接口是AI模型管理模块与AI模型管理网元之间的接口。第一接口可以使用应用层协议，如超文本传输协议(HyperText Transfer Protocol，HTTP)。The first interface is the interface between the AI model management module and the AI model management network element. The first interface may use an application layer protocol, such as HyperText Transfer Protocol (HTTP).
可选地，上述实施例中的步骤310可以替换实现为：AI模型管理模块与AI模型管理网 元，通过第一接口执行第一交互流程。Optionally, step 310 in the above embodiment may be alternatively implemented as: the AI model management module and the AI model management network element execute the first interaction process through the first interface.
其中，第一交互流程包括但不限于如下至少一种：Wherein, the first interaction process includes but is not limited to at least one of the following:
1)AI模型请求流程。1) AI model request process.
AI模型请求流程用于供AI模型管理模块请求从AI模型管理网元下载目标AI模型或向AI模型管理网元上传目标AI模型。The AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element.
2)AI模型通知流程。2) AI model notification process.
AI模型通知流程用于供AI模型管理网元通知AI模型管理模块需要上传的目标AI模型或需要向AI模型管理网元发送的目标AI模型。The AI model notification process is used for the AI model management NE to notify the AI model management module of the target AI model that needs to be uploaded or the target AI model that needs to be sent to the AI model management NE.
3)能力协商流程。3) Capability negotiation process.
能力协商流程用于供AI模型管理模块和AI模型管理网元之间协商支持下载或上传的目标AI模型。The capability negotiation process is used for negotiation between the AI model management module and the AI model management network element to support downloading or uploading of the target AI model.
4)AI模型下载流程。4) AI model download process.
AI模型下载流程用于实现AI模型管理模块从AI模型管理网元处下载目标AI模型。The AI model download process is used to implement the AI model management module to download the target AI model from the AI model management network element.
5)AI模型上传流程。5) AI model upload process.
AI模型上传流程用于实现AI模型管理模块向AI模型管理网元上传目标AI模型。The AI model upload process is used to implement the AI model management module uploading the target AI model to the AI model management network element.
可选地，第一接口包括第一控制面和第一用户面；其中，第一控制面用于执行AI模型请求流程、AI模型通知流程和能力协商流程，第一用户面用于执行AI模型下载流程和AI模型上传流程。Optionally, the first interface includes a first control plane and a first user plane; wherein, the first control plane is used to execute the AI model request process, the AI model notification process and the capability negotiation process, and the first user plane is used to execute the AI model. Download process and AI model upload process.
也就是说，可以对第一接口能够执行的流程进行分离，由第一控制面执行与控制相关的流程(如能力协商流程)，由第一用户面执行与承载相关的功能(如AI模型下载流程)。That is to say, the processes that can be executed by the first interface can be separated, and the first control plane executes the control-related processes (such as the capability negotiation process), and the first user plane executes the bearer-related functions (such as AI model download). Process).
可以理解的是，如图4所示，AI模型管理模块与AI模型管理网元也可以相应地分离为：控制面和用户面两个平面，将承载和控制进行分离。It can be understood that, as shown in Figure 4, the AI model management module and the AI model management network elements can also be correspondingly separated into two planes: the control plane and the user plane, which separate bearer and control.
二、第二接口。Second, the second interface.
第二接口是AI模型管理模块与终端设备中的第三方应用之间的接口。The second interface is an interface between the AI model management module and a third-party application in the terminal device.
可选地，AI模型管理模块与第三方应用，通过第二接口执行第二交互流程。可选地，第二交互流程包括：AI模型管理模块向第三方应用发送AI模型，第三方应用向AI模型管理模块发送AI模型。Optionally, the AI model management module and the third-party application execute the second interaction process through the second interface. Optionally, the second interaction process includes: the AI model management module sends the AI model to the third-party application, and the third-party application sends the AI model to the AI model management module.
示例性的，AI模型管理模块从AI模型管理网元处下载了AI模型，该AI模型的AI模型标识中的应用标识Application ID＝1，则AI模型管理模块将下载的AI模型发送给应用-1。Exemplarily, the AI model management module downloads the AI model from the AI model management network element, and the application ID Application ID=1 in the AI model ID of the AI model, then the AI model management module sends the downloaded AI model to the application- 1.
示例性的，第二接口用于应用将特定的AI模型发送给AI模型管理模块，以便AI模型管理模块保存或上传给AI模型管理网元进行统一保存/管理。Exemplarily, the second interface is used for the application to send the specific AI model to the AI model management module, so that the AI model management module saves or uploads it to the AI model management network element for unified storage/management.
三、第三接口。Third, the third interface.
第三接口是AI模型管理网元与数据网络中的其他服务器/网元之间的接口。The third interface is the interface between the AI model management network element and other servers/network elements in the data network.
可选地，AI模型管理网元与应用服务器，通过第三接口执行第三交互流程；或，AI模型管理网元与第三方网元，通过第三接口执行第四交互流程，第三方网元是除AI模型管理网元之外的其他网元。Optionally, the AI model management network element and the application server perform a third interaction process through a third interface; or, the AI model management network element and a third-party network element perform a fourth interaction process through the third interface, and the third-party network element NEs other than AI model management NEs.
其中，应用服务器可以对应于第三方网元。The application server may correspond to a third-party network element.
可选地，AI模型管理网元通过第三接口，也可以与其他网元进行交互，其他网元与AI模型管理网元可以对应于同一运营商，也可以对应于不同运营商。Optionally, the AI model management network element may also interact with other network elements through the third interface, and the other network elements and the AI model management network element may correspond to the same operator or may correspond to different operators.
可选地，第三交互流程包括：AI模型管理网元与应用服务器之间进行AI模型的存储、 下载、上传；第四交互流程包括：AI模型管理网元与第三方网元之间进行AI模型的存储、下载、上传。Optionally, the third interaction process includes: storing, downloading, and uploading the AI model between the AI model management network element and the application server; the fourth interaction process includes: performing AI between the AI model management network element and a third-party network element Model storage, download, upload.
示例性的，应用服务器将第三方应用的AI模型发送给AI模型管理网元进行保管。Exemplarily, the application server sends the AI model of the third-party application to the AI model management network element for storage.
示例性的，第三方网元是AI模型选择网元，AI模型选择网元用于确定终端设备需要使用的AI模型，通过接口3触发AI模型管理网元将相应的AI模型发送给终端设备使用。Exemplarily, the third-party network element is the AI model selection network element. The AI model selection network element is used to determine the AI model that the terminal device needs to use, and the AI model management network element is triggered through interface 3 to send the corresponding AI model to the terminal device for use. .
四、第四接口。Fourth, the fourth interface.
第四接口是AI模型管理网元与无线网络的接口。The fourth interface is the interface between the AI model management network element and the wireless network.
AI模型管理网元与无线网络中的网元，通过第四接口执行第五交互流程。无线网络中的网元可以具备AI模型管理模块的功能，与AI模型管理网元交互执行相应的功能。The AI model manages the network element and the network element in the wireless network, and executes the fifth interaction process through the fourth interface. The network elements in the wireless network can have the function of the AI model management module, and interact with the AI model management network elements to perform corresponding functions.
可选地，第五交互流程的目的可以是如下中的任意一种：Optionally, the purpose of the fifth interaction process can be any one of the following:
1)第五交互流程用于触发无线网络建立专有承载或服务质量(Quality of Service,QoS)数据流。1) The fifth interaction process is used to trigger the wireless network to establish a dedicated bearer or a quality of service (Quality of Service, QoS) data flow.
通过触发无线网络建立专有承载或QoS数据流，保障通过第一接口执行第一交互流程时的安全性和高效性。By triggering the wireless network to establish a dedicated bearer or a QoS data flow, the security and efficiency of executing the first interaction process through the first interface are guaranteed.
2)第五交互流程用于供AI模型管理网元向无线网络发送AI模型。2) The fifth interaction process is used for the AI model management network element to send the AI model to the wireless network.
无线网络可以使用从AI模型管理网元处获得的AI模型。The wireless network can use the AI model obtained from the AI model management network element.
3)第五交互流程用于AI模型管理网元从无线网络中获得AI模型，和/或存储AI模型。3) The fifth interaction process is used for the AI model management network element to obtain the AI model from the wireless network, and/or store the AI model.
AI模型管理网元也可以从无线网络中获得AI模型，并进行存储。AI model management network elements can also obtain AI models from wireless networks and store them.
4)第五交互流程用于供AI模型管理网元接收来自无线网络中的网元的请求，请求用于请求AI模型管理网元发送AI模型。4) The fifth interaction process is used for the AI model management network element to receive a request from the network element in the wireless network, and the request is used to request the AI model management network element to send the AI model.
AI模型管理网元可以根据无线网络中的网元的请求，相应地向终端设备发送AI模型。The AI model management network element can correspondingly send the AI model to the terminal device according to the request of the network element in the wireless network.
可选地，无线网络中的网元除了具有上述功能之外，无线网络中的网元还可以与AI模型管理网元进行能力协商，协商可以下载或者上传的AI模型。Optionally, in addition to the above functions, the network elements in the wireless network can also perform capability negotiation with the AI model management network element, and negotiate the AI model that can be downloaded or uploaded.
可选地，AI模型管理网元与无线网络中的能力开放网元对接或直接与无线网络中的某一个网元对接。其中，能力开放网元是提供能力开放服务的网元。也就是说，AI模型管理网元可以与无线网络中的能力开放网元通过第四接口进行交互。能力开放网元包括但不限于：网络开放功能(Network Exposure Function，NEF)网元、业务能力开放功能(Service Capability Exposure Function，SCEF)网元、策略控制功能(Policy Control Function，PCF)网元中的至少一种。NEF网元和SCEF网元可以通过API接口将业务能力开放给第三方服务商，PCF网元负责进行策略控制。Optionally, the AI model management network element is connected with a capability opening network element in the wireless network or directly connected with a certain network element in the wireless network. The capability opening network element is a network element that provides capability opening services. That is to say, the AI model management network element can interact with the capability opening network element in the wireless network through the fourth interface. Capability exposure network elements include but are not limited to: Network Exposure Function (NEF) network elements, Service Capability Exposure Function (SCEF) network elements, Policy Control Function (Policy Control Function, PCF) network elements at least one of. NEF network elements and SCEF network elements can open service capabilities to third-party service providers through API interfaces, and PCF network elements are responsible for policy control.
综上所述，本实施例提供的方法，通过定义第一类型AI模型和第二类型AI模型，并给出不同种类AI模型的模型标识格式，从而更准确地标识AI模型，便于AI模型的管理。To sum up, in the method provided in this embodiment, by defining the first type of AI model and the second type of AI model, and giving the model identification formats of different types of AI models, the AI model can be more accurately identified, which is convenient for the identification of AI models. manage.
本实施例提供的方法，通过定义不同的接口，运营商可以向其他对象(如第三方应用)开放AI管理的相关功能，便于AI模型的内容的传输。In the method provided in this embodiment, by defining different interfaces, the operator can open the relevant functions of AI management to other objects (such as third-party applications), which facilitates the transmission of the content of the AI model.
需要说明的是，上述方法实施例可以分别单独实施，也可以组合实施，本申请对此不进行限制。It should be noted that, the foregoing method embodiments may be implemented separately, or may be implemented in combination, which is not limited in this application.
在上述各个实施例中，由终端设备执行的步骤可以单独实现成为终端设备一侧的模型管理方法，由网络设备执行的步骤可以单独实现成为网络设备一侧的模型管理方法。In each of the above embodiments, the steps performed by the terminal device can be implemented independently as a model management method on the terminal device side, and the steps performed by the network device can be implemented independently as a model management method on the network device side.
对应于上述方法实施例，本申请提供了一种模型管理系统，模型管理系统包括：人工智能AI模型管理模块和AI模型管理网元；Corresponding to the above method embodiments, the present application provides a model management system, the model management system includes: an artificial intelligence AI model management module and an AI model management network element;
AI模型管理模块，用于与AI模型管理网元，执行第一交互流程；The AI model management module is used to manage network elements with the AI model and execute the first interaction process;
其中，AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，AI模型管理网元是数据网络端用于进行AI模型管理的网元，AI模型管理模块支持与AI模型管理网元交互，以便为终端设备中的应用层和/或无线协议层下载或上传AI模型。Among them, the AI model management module is a functional module used for AI model management on the terminal device side, and the AI model management network element is a network element used for AI model management at the data network side. Interact to download or upload AI models for the application layer and/or wireless protocol layer in the end device.
可选地，模型管理系统还包括：第一接口；AI模型管理模块，用于与AI模型管理网元，通过第一接口执行第一交互流程；其中，第一交互流程包括如下至少一种：Optionally, the model management system further includes: a first interface; an AI model management module configured to perform a first interaction process with the AI model management network element through the first interface; wherein the first interaction process includes at least one of the following:
AI模型请求流程，AI模型请求流程用于供AI模型管理模块请求从AI模型管理网元下载目标AI模型或向AI模型管理网元上传目标AI模型；AI model request process, the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element;
AI模型通知流程，AI模型通知流程用于供AI模型管理网元通知AI模型管理模块需要上传的目标AI模型或需要向AI模型管理网元发送的目标AI模型；AI model notification process, the AI model notification process is used for the AI model management network element to notify the AI model management module of the target AI model that needs to be uploaded or the target AI model that needs to be sent to the AI model management network element;
能力协商流程，能力协商流程用于供AI模型管理模块和AI模型管理网元之间协商支持下载或上传的目标AI模型；The capability negotiation process is used for the AI model management module and the AI model management network element to negotiate the target AI model that supports downloading or uploading;
AI模型下载流程；AI model download process;
AI模型上传流程。AI model upload process.
可选地，第一接口包括第一控制面和第一用户面；其中，第一控制面用于执行AI模型请求流程、AI模型通知流程和能力协商流程，第一用户面用于执行AI模型下载流程和AI模型上传流程。Optionally, the first interface includes a first control plane and a first user plane; wherein, the first control plane is used to execute the AI model request process, the AI model notification process and the capability negotiation process, and the first user plane is used to execute the AI model. Download process and AI model upload process.
可选地，AI模型管理系统还包括：第二接口；AI模型管理模块用于与第三方应用，通过第二接口执行第二交互流程。Optionally, the AI model management system further includes: a second interface; the AI model management module is configured to perform a second interaction process with a third-party application through the second interface.
可选地，AI模型管理系统还包括：第三接口；AI模型管理网元，用于与应用服务器，通过第三接口执行第三交互流程；或，AI模型管理网元，用于与第三方网元，通过第三接口执行第四交互流程，第三方网元是除AI模型管理网元之外的其他网元。Optionally, the AI model management system further includes: a third interface; an AI model management network element for performing a third interaction process with the application server through the third interface; or an AI model management network element for communicating with a third party. The network element performs the fourth interaction process through the third interface, and the third-party network element is another network element except the AI model management network element.
可选地，AI模型管理系统还包括：第四接口；AI模型管理网元，用于与无线网络中的能力开放网元，通过第四接口执行第五交互流程；其中，第五交互流程用于触发无线网络建立专有承载或QoS数据流；Optionally, the AI model management system further includes: a fourth interface; the AI model management network element is used to perform the fifth interaction process with the capability opening network element in the wireless network through the fourth interface; wherein, the fifth interaction process uses To trigger wireless network to establish dedicated bearer or QoS data flow;
或，第五交互流程用于AI模型管理网元向无线网络中的网元发送AI模型；Or, the fifth interaction process is used for the AI model management network element to send the AI model to the network element in the wireless network;
或，第五交互流程用于AI模型管理网元从无线网络中获得AI模型，和/或存储AI模型；Or, the fifth interaction process is used for the AI model management network element to obtain the AI model from the wireless network, and/or store the AI model;
或，第五交互流程用于供AI模型管理网元接收来自无线网络中的网元的请求，请求用于请求AI模型管理网元发送AI模型。Or, the fifth interaction process is used for the AI model management network element to receive the request from the network element in the wireless network, and the request is used to request the AI model management network element to send the AI model.
可选地，无线网络中的网元包括：能力开放网元，能力开放网元包括：NEF网元、SCEF网元和PCF网元中的至少一种。Optionally, the network elements in the wireless network include: capability exposure network elements, and the capability exposure network elements include: at least one of NEF network elements, SCEF network elements, and PCF network elements.
可选地，第一类型AI模型的模型标识格式为第一类型模型标识格式，第一类型模型标识格式包括：运营商标识和模型标识；Optionally, the model identification format of the first type AI model is the first type model identification format, and the first type model identification format includes: operator identification and model identification;
第二类型AI模型的模型标识格式为第二类型模型标识格式，第二类型模型标识格式包括：运营商标识、模型标识和应用标识。The model identification format of the second type AI model is the second type model identification format, and the second type model identification format includes: operator identification, model identification and application identification.
可选地，模型标识的取值包括：标准化模型标识取值和非标准化模型标识取值，标准化模型标识取值是通过标准化约定好的取值，对应于目标类型的AI模型或目标业务的AI模型或目标AI模型。Optionally, the value of the model identifier includes: a standardized model identifier value and a non-standardized model identifier value, the standardized model identifier value is a value agreed upon through standardization, and corresponds to the AI model of the target type or the AI of the target business. Model or target AI model.
可选地，模型标识包括：模型类型标识、模型结构参数标识和模型权重参数标识中的至少一种。Optionally, the model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
可选地，运营商标识由运营商或第三方应用确定；应用标识由运营商或第三方应用确定。Optionally, the operator identifier is determined by the operator or a third-party application; the application identifier is determined by the operator or a third-party application.
结合参考图5，其示出了本申请一个实施例提供的一个AI模型管理系统的构成图。With reference to FIG. 5 , it shows a structural diagram of an AI model management system provided by an embodiment of the present application.
如图5中的(a)所示，该AI模型管理系统包括：AI模型管理模块501、和AI模型管理网元502。As shown in (a) of FIG. 5 , the AI model management system includes: an AI model management module 501 and an AI model management network element 502 .
在终端设备侧引入AI模型管理模块501，在网络侧引入AI模型管理网元502，AI模型管理模块501和AI模型管理网元502可以是运营商网络中的一部分，通过应用程序接口(Application Program Interface,API)为第三方应用提供AI模型管理服务。The AI model management module 501 is introduced on the terminal device side, and the AI model management network element 502 is introduced on the network side. The AI model management module 501 and the AI model management network element 502 may be part of the operator's network. Interface, API) to provide AI model management services for third-party applications.
终端设备和数据网络之间是运营商的无线网络(包括基站和核心网)，AI模型管理模块501和AI模型管理网元502可以通过无线网络的用户面中的接口1(即第一接口)进行通信，接口1传递的数据可以通过无线网络的协议数据单元(Protocol Data Unit，PDU)会话进行传输。Between the terminal device and the data network is the operator's wireless network (including the base station and the core network), the AI model management module 501 and the AI model management network element 502 can pass the interface 1 (ie, the first interface) in the user plane of the wireless network. For communication, the data transmitted by the interface 1 can be transmitted through a protocol data unit (Protocol Data Unit, PDU) session of the wireless network.
可选地，AI模型管理系统还包括接口2(即第二接口)和接口3(即第三接口)。AI模型管理模块501可以通过接口2向终端设备中的第三方应用开放AI管理的相关功能(包括AI模型存储、下载、上传等)。AI模型管理网元502可以通过接口3向第三方应用或者其他网元开放AI管理的相关功能(包括AI模型存储、下载、上传等)。Optionally, the AI model management system further includes an interface 2 (ie a second interface) and an interface 3 (ie a third interface). The AI model management module 501 can open related functions of AI management (including AI model storage, download, upload, etc.) to third-party applications in the terminal device through the interface 2 . The AI model management network element 502 can open related functions of AI management (including AI model storage, download, upload, etc.) to third-party applications or other network elements through the interface 3 .
可选地，AI模型管理系统还包括接口4(即第四接口)。AI模型管理网元502可以通过接口4与运营商网络的能力开放网元进行交互。能力开放网元包括但不限于：NEF网元、SCEF网元、PCF网元。Optionally, the AI model management system further includes an interface 4 (ie, a fourth interface). The AI model management network element 502 can interact with the capability opening network element of the operator's network through the interface 4 . Capability exposure network elements include but are not limited to: NEF network elements, SCEF network elements, and PCF network elements.
可选地，如图5中的(b)所示，AI模型管理模块501对接无线协议层503，无线协议层503可以处理3GPP协议。示例性的，AI模型管理模块501将运营商使用的AI模型发送给无线协议层503使用。比如，用于对无线网络的无线信道质量优化、移动性管理优化、会话管理优化、UE策略优化等。Optionally, as shown in (b) of FIG. 5 , the AI model management module 501 is connected to the wireless protocol layer 503, and the wireless protocol layer 503 can process the 3GPP protocol. Exemplarily, the AI model management module 501 sends the AI model used by the operator to the wireless protocol layer 503 for use. For example, it is used for wireless channel quality optimization, mobility management optimization, session management optimization, UE policy optimization, etc. in the wireless network.
综上所述，本申请实施例提供了一种模型管理系统，可以利用运营商自身的云计算资源实现AI模型管理服务，第三方应用商无需利用本地的机房资源对AI模型进行管理。To sum up, the embodiments of the present application provide a model management system, which can use the operator's own cloud computing resources to implement AI model management services, and third-party application providers do not need to use local computer room resources to manage AI models.
图6是本申请一个示例性实施例提供的模型管理装置的框图。所述装置应用在终端设备中，或者，所述装置实现成为终端设备或终端设备的一部分。所述装置包括：AI模型管理模块601；FIG. 6 is a block diagram of a model management apparatus provided by an exemplary embodiment of the present application. The apparatus is applied in a terminal device, or the apparatus is implemented as a terminal device or a part of the terminal device. The apparatus includes: an AI model management module 601;
AI模型管理模块601，用于与AI模型管理网元，执行第一交互流程；The AI model management module 601 is configured to manage network elements with the AI model and execute the first interaction process;
AI模型管理模块601是终端设备端用于进行AI模型管理的功能模块，AI模型管理网元是数据网络端用于进行AI模型管理的网元，AI模型管理模块601支持与AI模型管理网元交互，以便为终端设备中的应用层和/或无线协议层下载或上传AI模型。The AI model management module 601 is a functional module used for AI model management on the terminal device side. The AI model management network element is a network element used for AI model management at the data network side. The AI model management module 601 supports and AI model management network elements. Interact to download or upload AI models for the application layer and/or wireless protocol layer in the end device.
在一个可选的实施例中，AI模型管理模块601，用于与AI模型管理网元，通过第一接口执行第一交互流程；其中，第一交互流程包括如下至少一种：In an optional embodiment, the AI model management module 601 is configured to perform a first interaction process with an AI model management network element through a first interface; wherein the first interaction process includes at least one of the following:
AI模型请求流程，AI模型请求流程用于供AI模型管理模块601请求从AI模型管理网元下载目标AI模型或向AI模型管理网元上传目标AI模型；AI model request process, the AI model request process is used for the AI model management module 601 to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element;
AI模型通知流程，AI模型通知流程用于供AI模型管理网元通知AI模型管理模块601需要上传的目标AI模型或需要向AI模型管理网元发送的目标AI模型；AI model notification process, the AI model notification process is used for the AI model management network element to notify the AI model management module 601 of the target AI model to be uploaded or the target AI model to be sent to the AI model management network element;
能力协商流程，能力协商流程用于供AI模型管理模块601和AI模型管理网元之间协商支持下载或上传的目标AI模型；A capability negotiation process, which is used for negotiating between the AI model management module 601 and the AI model management network element to support downloading or uploading of the target AI model;
AI模型下载流程；AI model download process;
AI模型上传流程。AI model upload process.
在一个可选的实施例中，第一接口包括第一控制面和第一用户面；其中，第一控制面用于执行AI模型请求流程、AI模型通知流程和能力协商流程，第一用户面用于执行AI模型下载流程和AI模型上传流程。In an optional embodiment, the first interface includes a first control plane and a first user plane; wherein, the first control plane is used to execute an AI model request process, an AI model notification process, and a capability negotiation process, and the first user plane It is used to execute the AI model download process and the AI model upload process.
在一个可选的实施例中，AI模型管理模块601，用于与第三方应用，通过第二接口执行第二交互流程。In an optional embodiment, the AI model management module 601 is configured to perform a second interaction process with a third-party application through a second interface.
在一个可选的实施例中，AI模型管理模块601中的AI模型包括如下至少之一：第一类型AI模型和第二类型AI模型；其中，第一类型AI模型对应于运营商，第二类型AI模型对应于第三方应用。In an optional embodiment, the AI model in the AI model management module 601 includes at least one of the following: a first type of AI model and a second type of AI model; wherein the first type of AI model corresponds to the operator, the second type of AI model Type AI models correspond to third-party applications.
在一个可选的实施例中，第一类型AI模型的模型标识格式为第一类型模型标识格式，第一类型模型标识格式包括：运营商标识和模型标识；第二类型AI模型的模型标识格式为第二类型模型标识格式，第二类型模型标识格式包括如下至少之一：运营商标识、应用标识和模型标识。In an optional embodiment, the model identification format of the first type AI model is the first type model identification format, and the first type model identification format includes: an operator identification and a model identification; the model identification format of the second type AI model For the second type of model identification format, the second type of model identification format includes at least one of the following: an operator identification, an application identification and a model identification.
在一个可选的实施例中，模型标识的取值包括：标准化模型标识取值和非标准化模型标识取值，标准化模型标识取值是通过标准化约定好的取值，对应于目标类型的AI模型或目标业务的AI模型或目标AI模型。In an optional embodiment, the value of the model identification includes: a standardized model identification value and a non-standardized model identification value, the standardized model identification value is a value agreed through standardization, and corresponds to the AI model of the target type. Or the AI model of the target business or the target AI model.
在一个可选的实施例中，模型标识包括：模型类型标识、模型结构参数标识和模型权重参数标识中的至少一种。In an optional embodiment, the model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
在一个可选的实施例中，运营商标识由运营商或第三方应用确定；应用标识由运营商或第三方应用确定。In an optional embodiment, the operator identifier is determined by the operator or a third-party application; the application identifier is determined by the operator or a third-party application.
图7是本申请一个示例性实施例提供的模型管理装置的框图。所述装置应用在网络设备中，或者，所述装置实现成为网络设备或网络设备的一部分。所述装置包括：AI模型管理网元模块701；FIG. 7 is a block diagram of a model management apparatus provided by an exemplary embodiment of the present application. The apparatus is applied in a network device, or the apparatus is implemented as a network device or a part of the network device. The apparatus includes: an AI model management network element module 701;
AI模型管理网元模块701，用于与AI模型管理模块，执行第一交互流程；The AI model management network element module 701 is configured to execute the first interaction process with the AI model management module;
其中，AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，AI模型管理网元模块701是数据网络端用于进行AI模型管理的网元模块，AI模型管理模块支持与AI模型管理网元模块701交互，以便为终端设备中的应用层和/或无线协议层下载或上传AI模型。Among them, the AI model management module is a functional module used for AI model management at the terminal device side, and the AI model management network element module 701 is a network element module used for AI model management at the data network side. The management network element module 701 interacts to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
在一个可选的实施例中，AI模型管理网元模块701，用于与AI模型管理模块，通过第一接口执行第一交互流程；其中，第一交互流程包括如下至少一种：In an optional embodiment, the AI model management network element module 701 is configured to execute a first interaction process with the AI model management module through a first interface; wherein the first interaction process includes at least one of the following:
AI模型请求流程，AI模型请求流程用于供AI模型管理模块请求从AI模型管理网元模块701下载目标AI模型或向AI模型管理网元上传目标AI模型；AI model request process, the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element module 701 or upload the target AI model to the AI model management network element;
AI模型通知流程，AI模型通知流程用于供AI模型管理网元模块701通知AI模型管理模块需要上传的目标AI模型或需要向AI模型管理网元发送的目标AI模型；AI model notification process, the AI model notification process is used for the AI model management network element module 701 to notify the AI model management module of the target AI model that needs to be uploaded or the target AI model that needs to be sent to the AI model management network element;
能力协商流程，能力协商流程用于供AI模型管理模块和AI模型管理网元模块701之间协商支持下载或上传的目标AI模型；A capability negotiation process, the capability negotiation process is used for negotiating between the AI model management module and the AI model management network element module 701 to support the download or upload of the target AI model;
AI模型下载流程；AI model download process;
AI模型上传流程。AI model upload process.
在一个可选的实施例中，第一接口包括第一控制面和第一用户面；其中，第一控制面用于执行AI模型请求流程、AI模型通知流程和能力协商流程，第一用户面用于执行AI模型下载流程和AI模型上传流程。In an optional embodiment, the first interface includes a first control plane and a first user plane; wherein, the first control plane is used to execute an AI model request process, an AI model notification process, and a capability negotiation process, and the first user plane It is used to execute the AI model download process and the AI model upload process.
在一个可选的实施例中，AI模型管理网元模块701，用于与应用服务器，通过第三接口执行第三交互流程；或，AI模型管理网元模块701，用于与第三方网元，通过第三接口执行第四交互流程，第三方网元是除AI模型管理网元之外的其他网元。In an optional embodiment, the AI model management network element module 701 is configured to perform a third interaction process with the application server through a third interface; or, the AI model management network element module 701 is configured to communicate with a third-party network element , the fourth interaction process is performed through the third interface, and the third-party network element is other network element except the AI model management network element.
在一个可选的实施例中，AI模型管理网元模块701，用于与无线网络中的网元，通过第四接口执行第五交互流程；其中，第五交互流程用于触发无线网络建立专有承载或QoS数据流；或，第五交互流程用于AI模型管理网元模块701向无线网络中的网元发送AI模型；或，第五交互流程用于AI模型管理网元模块701从无线网络中获得AI模型，和/或存储AI模型；或，第五交互流程用于供AI模型管理网元模块701接收来自无线网络中的网元的请求，请求用于请求AI模型管理网元模块701发送AI模型。In an optional embodiment, the AI model management network element module 701 is configured to perform a fifth interaction process with network elements in the wireless network through a fourth interface; wherein, the fifth interaction process is used to trigger the wireless network to establish a special There is a bearer or QoS data flow; or, the fifth interaction process is used for the AI model management network element module 701 to send the AI model to the network element in the wireless network; or, the fifth interaction process is used for the AI model management network element module 701 from the wireless network Obtaining the AI model in the network, and/or storing the AI model; or, the fifth interaction process is used for the AI model management network element module 701 to receive a request from a network element in the wireless network, and the request is used to request the AI model management network element module 701 Send AI model.
在一个可选的实施例中，无线网络中的网元包括：能力开放网元，能力开放网元包括：网络开放功能NEF网元、业务能力开放功能SCEF网元和策略控制功能PCF网元中的至少一种。In an optional embodiment, the network elements in the wireless network include: a capability opening network element, and the capability opening network element includes: a network opening function NEF network element, a service capability opening function SCEF network element, and a policy control function PCF network element at least one of.
在一个可选的实施例中，AI模型管理网元模块701中的AI模型包括如下至少之一：第一类型AI模型和第二类型AI模型；其中，第一类型AI模型对应于运营商，第二类型AI模型对应于第三方应用。In an optional embodiment, the AI model in the AI model management network element module 701 includes at least one of the following: a first type AI model and a second type AI model; wherein the first type AI model corresponds to an operator, The second type of AI model corresponds to third-party applications.
在一个可选的实施例中，第一类型AI模型的模型标识格式为第一类型模型标识格式，第一类型模型标识格式包括：运营商标识和模型标识；In an optional embodiment, the model identification format of the first-type AI model is the first-type model identification format, and the first-type model identification format includes: an operator identification and a model identification;
第二类型AI模型的模型标识格式为第二类型模型标识格式，第二类型模型标识格式包括如下至少之一：运营商标识、模型标识和应用标识。The model identification format of the second type AI model is the second type model identification format, and the second type model identification format includes at least one of the following: an operator identification, a model identification and an application identification.
在一个可选的实施例中，模型标识的取值包括：标准化模型标识取值和非标准化模型标识取值，标准化模型标识取值是通过标准化约定好的模型标识取值，对应于目标类型的AI模型或目标业务的AI模型或目标AI模型。In an optional embodiment, the value of the model identification includes: a standardized model identification value and a non-standardized model identification value, the standardized model identification value is a model identification value agreed upon through standardization, and corresponds to the target type. AI model or AI model of target business or target AI model.
在一个可选的实施例中，模型标识包括：模型类型标识、模型结构参数标识和模型权重参数标识中的至少一种。In an optional embodiment, the model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
在一个可选的实施例中，运营商标识由运营商或第三方应用确定；应用标识由运营商或第三方应用确定。In an optional embodiment, the operator identifier is determined by the operator or a third-party application; the application identifier is determined by the operator or a third-party application.
图8示出了本申请一个示例性实施例提供的通信设备的结构示意图，该通信设备包括：处理器101、接收器102、发射器103、存储器104和总线105。FIG. 8 shows a schematic structural diagram of a communication device provided by an exemplary embodiment of the present application. The communication device includes: a processor 101 , a receiver 102 , a transmitter 103 , a memory 104 , and a bus 105 .
处理器101包括一个或者一个以上处理核心，处理器101通过运行软件程序以及模块，从而执行各种功能应用以及信息处理。The processor 101 includes one or more processing cores, and the processor 101 executes various functional applications and information processing by running software programs and modules.
接收器102和发射器103可以实现为一个通信组件，该通信组件可以是一块通信芯片。The receiver 102 and the transmitter 103 may be implemented as a communication component, which may be a communication chip.
存储器104通过总线105与处理器101相连。The memory 104 is connected to the processor 101 through the bus 105 .
存储器104可用于存储至少一个指令，处理器101用于执行该至少一个指令，以实现上述方法实施例中的各个步骤。The memory 104 may be configured to store at least one instruction, and the processor 101 may be configured to execute the at least one instruction, so as to implement various steps in the foregoing method embodiments.
此外，存储器104可以由任何类型的易失性或非易失性存储设备或者它们的组合实现， 易失性或非易失性存储设备包括但不限于：磁盘或光盘，电可擦除可编程只读存储器(Electrically-Erasable Programmable Read Only Memory，EEPROM)，可擦除可编程只读存储器(Erasable Programmable Read Only Memory，EPROM)，静态随时存取存储器(Static Random Access Memory，SRAM)，只读存储器(Read-Only Memory，ROM)，磁存储器，快闪存储器，可编程只读存储器(Programmable Read-Only Memory，PROM)。Additionally, memory 104 may be implemented by any type or combination of volatile or non-volatile storage devices including, but not limited to, magnetic or optical disks, electrically erasable and programmable Read Only Memory (Electrically-Erasable Programmable Read Only Memory, EEPROM), Erasable Programmable Read Only Memory (EPROM), Static Random Access Memory (SRAM), Read Only Memory (Read-Only Memory, ROM), magnetic memory, flash memory, programmable read-only memory (Programmable Read-Only Memory, PROM).
在示例性实施例中，还提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由处理器加载并执行以实现上述各个方法实施例提供的由终端设备执行的模型管理方法，或数据网络执行的模型管理方法。In an exemplary embodiment, a computer-readable storage medium is also provided, wherein the computer-readable storage medium stores at least one instruction, at least one piece of program, code set or instruction set, the at least one instruction, the At least one section of program, the code set or the instruction set is loaded and executed by the processor to implement the model management method executed by the terminal device or the model management method executed by the data network provided by the above method embodiments.
在示例性实施例中，还提供了一种计算机程序产品或计算机程序，该计算机程序产品或计算机程序包括计算机指令，该计算机指令存储在计算机可读存储介质中，计算机设备的处理器从计算机可读存储介质读取该计算机指令，处理器执行该计算机指令，使得该计算机设备执行上述方面所述的模型管理方法。In an exemplary embodiment, there is also provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium from which a processor of a computer device can The computer instructions are read from the storage medium, and the processor executes the computer instructions, so that the computer device executes the model management method described in the above aspects.
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。Those of ordinary skill in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The storage medium mentioned may be a read-only memory, a magnetic disk or an optical disk, etc.
以上所述仅为本申请的可选实施例，并不用以限制本申请，凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。The above descriptions are only optional embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection of the present application. within the range.

Claims (55)

  1. 一种模型管理方法，其特征在于，应用于终端设备中，所述终端设备包括：人工智能AI模型管理模块，所述方法包括：A model management method, characterized in that it is applied to a terminal device, the terminal device includes: an artificial intelligence AI model management module, and the method includes:
    所述AI模型管理模块与AI模型管理网元，执行第一交互流程；The AI model management module and the AI model management network element execute the first interaction process;
    所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元是数据网络端用于进行AI模型管理的网元，所述AI模型管理模块支持与所述AI模型管理网元交互，以便为所述终端设备中的应用层和/或无线协议层下载或上传AI模型。The AI model management module is a functional module used for AI model management at the terminal device side, the AI model management network element is a network element used for AI model management at the data network side, and the AI model management module supports and The AI model manages network element interactions in order to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  2. 根据权利要求1所述的方法，其特征在于，所述AI模型管理模块与AI模型管理网元，执行第一交互流程，包括：The method according to claim 1, wherein the AI model management module and the AI model management network element perform a first interaction process, comprising:
    所述AI模型管理模块与所述AI模型管理网元，通过第一接口执行所述第一交互流程；The AI model management module and the AI model management network element execute the first interaction process through a first interface;
    其中，所述第一交互流程包括如下至少一种：Wherein, the first interaction process includes at least one of the following:
    AI模型请求流程，所述AI模型请求流程用于供所述AI模型管理模块请求从所述AI模型管理网元下载目标AI模型或向所述AI模型管理网元上传所述目标AI模型；AI model request process, the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element;
    AI模型通知流程，所述AI模型通知流程用于供所述AI模型管理网元通知所述AI模型管理模块需要上传的所述目标AI模型或需要向所述AI模型管理网元发送的所述目标AI模型；AI model notification process, the AI model notification process is used for the AI model management network element to notify the AI model management module of the target AI model that needs to be uploaded or the AI model management network element that needs to be sent to the AI model management network element. target AI model;
    能力协商流程，所述能力协商流程用于供所述AI模型管理模块和所述AI模型管理网元之间协商支持下载或上传的所述目标AI模型；a capability negotiation process, where the capability negotiation process is used for negotiating the target AI model that supports downloading or uploading between the AI model management module and the AI model management network element;
    AI模型下载流程；AI model download process;
    AI模型上传流程。AI model upload process.
  3. 根据权利要求2所述的方法，其特征在于，所述第一接口包括第一控制面和第一用户面；The method according to claim 2, wherein the first interface comprises a first control plane and a first user plane;
    其中，所述第一控制面用于执行所述AI模型请求流程、所述AI模型通知流程和所述能力协商流程，所述第一用户面用于执行所述AI模型下载流程和所述AI模型上传流程。The first control plane is used to execute the AI model request process, the AI model notification process and the capability negotiation process, and the first user plane is used to execute the AI model download process and the AI Model upload process.
  4. 根据权利要求1所述的方法，其特征在于，所述方法还包括：The method according to claim 1, wherein the method further comprises:
    所述AI模型管理模块与第三方应用，通过第二接口执行第二交互流程。The AI model management module and the third-party application execute the second interaction process through the second interface.
  5. 根据权利要求1至4任一所述的方法，其特征在于，The method according to any one of claims 1 to 4, wherein,
    所述AI模型管理模块中的AI模型包括如下至少之一：第一类型AI模型和第二类型AI模型；The AI model in the AI model management module includes at least one of the following: a first-type AI model and a second-type AI model;
    其中，所述第一类型AI模型对应于运营商，所述第二类型AI模型对应于第三方应用。The first type of AI model corresponds to an operator, and the second type of AI model corresponds to a third-party application.
  6. 根据权利要求5所述的方法，其特征在于，The method of claim 5, wherein:
    所述第一类型AI模型的模型标识格式为第一类型模型标识格式，所述第一类型模型标识格式包括：运营商标识和模型标识；The model identification format of the first type AI model is the first type model identification format, and the first type model identification format includes: operator identification and model identification;
    所述第二类型AI模型的模型标识格式为第二类型模型标识格式，所述第二类型模型标识格式包括如下至少之一：所述运营商标识、应用标识和所述模型标识。The model identification format of the second-type AI model is a second-type model identification format, and the second-type model identification format includes at least one of the following: the operator identification, the application identification, and the model identification.
  7. 根据权利要求6所述的方法，其特征在于，The method of claim 6, wherein:
    所述模型标识的取值包括：标准化模型标识取值和非标准化模型标识取值，所述标准化模型标识取值是通过标准化约定好的取值，对应于目标类型的AI模型或目标业务的AI模型 或目标AI模型。The value of the model identifier includes: a standardized model identifier value and a non-standardized model identifier value, the standardized model identifier value is a value agreed upon through standardization, and corresponds to the AI model of the target type or the AI of the target business. Model or target AI model.
  8. 根据权利要求6所述的方法，其特征在于，The method of claim 6, wherein:
    所述模型标识包括：模型类型标识、模型结构参数标识和模型权重参数标识中的至少一种。The model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
  9. 根据权利要求6所述的方法，其特征在于，The method of claim 6, wherein:
    所述运营商标识由所述运营商或所述第三方应用确定；the operator identification is determined by the operator or the third-party application;
    所述应用标识由所述运营商或所述第三方应用确定。The application identification is determined by the operator or the third-party application.
  10. 一种模型管理方法，其特征在于，应用于数据网络中，所述数据网络包括：人工智能AI模型管理网元，所述方法包括：A model management method, characterized in that it is applied to a data network, wherein the data network includes: artificial intelligence AI model management network elements, and the method includes:
    所述AI模型管理网元与AI模型管理模块，执行第一交互流程；The AI model management network element and the AI model management module execute the first interaction process;
    其中，所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元是数据网络端用于进行AI模型管理的网元，所述AI模型管理模块支持与所述AI模型管理网元交互，以便为终端设备中的应用层和/或无线协议层下载或上传AI模型。The AI model management module is a functional module used for AI model management on the terminal device side, the AI model management network element is a network element used for AI model management on the data network side, and the AI model management module supports Interact with the AI model management network element to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  11. 根据权利要求10所述的方法，其特征在于，所述AI模型管理网元与AI模型管理模块，执行第一交互流程，包括：The method according to claim 10, wherein the AI model management network element and the AI model management module execute a first interaction process, comprising:
    所述AI模型管理网元与AI模型管理模块，通过第一接口执行第一交互流程；The AI model management network element and the AI model management module execute the first interaction process through the first interface;
    其中，所述第一交互流程包括如下至少一种：Wherein, the first interaction process includes at least one of the following:
    AI模型请求流程，所述AI模型请求流程用于供所述AI模型管理模块请求从所述AI模型管理网元下载目标AI模型或向所述AI模型管理网元上传所述目标AI模型；AI model request process, the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element;
    AI模型通知流程，所述AI模型通知流程用于供所述AI模型管理网元通知所述AI模型管理模块需要上传的所述目标AI模型或需要向所述AI模型管理网元发送的所述目标AI模型；AI model notification process, the AI model notification process is used for the AI model management network element to notify the AI model management module of the target AI model that needs to be uploaded or the AI model management network element that needs to be sent to the AI model management network element. target AI model;
    能力协商流程，所述能力协商流程用于供所述AI模型管理模块和所述AI模型管理网元之间协商支持下载或上传的所述目标AI模型；a capability negotiation process, where the capability negotiation process is used for negotiating the target AI model that supports downloading or uploading between the AI model management module and the AI model management network element;
    AI模型下载流程；AI model download process;
    AI模型上传流程。AI model upload process.
  12. 根据权利要求11所述的方法，其特征在于，所述第一接口包括第一控制面和第一用户面；The method according to claim 11, wherein the first interface comprises a first control plane and a first user plane;
    其中，所述第一控制面用于执行所述AI模型请求流程、所述AI模型通知流程和所述能力协商流程，所述第一用户面用于执行所述AI模型下载流程和所述AI模型上传流程。The first control plane is used to execute the AI model request process, the AI model notification process and the capability negotiation process, and the first user plane is used to execute the AI model download process and the AI Model upload process.
  13. 根据权利要求10所述的方法，其特征在于，所述方法还包括：The method of claim 10, wherein the method further comprises:
    所述AI模型管理网元与应用服务器，通过第三接口执行第三交互流程；The AI model manages the network element and the application server, and executes a third interaction process through a third interface;
    或，or,
    所述AI模型管理网元与第三方网元，通过所述第三接口执行第四交互流程，所述第三方网元是除所述AI模型管理网元之外的其他网元。The AI model management network element and a third-party network element perform a fourth interaction process through the third interface, and the third-party network element is another network element except the AI model management network element.
  14. 根据权利要求10所述的方法，其特征在于，所述方法还包括：The method of claim 10, wherein the method further comprises:
    所述AI模型管理网元与无线网络中的网元，通过第四接口执行第五交互流程；The AI model manages network elements and network elements in the wireless network, and executes a fifth interaction process through a fourth interface;
    其中，所述第五交互流程用于触发所述无线网络建立专有承载或服务质量QoS数据流；Wherein, the fifth interaction process is used to trigger the wireless network to establish a dedicated bearer or a quality of service QoS data flow;
    或，所述第五交互流程用于所述AI模型管理网元向所述无线网络中的网元发送AI模型；Or, the fifth interaction process is for the AI model management network element to send the AI model to the network element in the wireless network;
    或，所述第五交互流程用于所述AI模型管理网元从所述无线网络中获得AI模型，和/或存储所述AI模型；Or, the fifth interaction process is for the AI model management network element to obtain the AI model from the wireless network, and/or store the AI model;
    或，所述第五交互流程用于供所述AI模型管理网元接收来自所述无线网络中的网元的请求，所述请求用于请求所述AI模型管理网元发送AI模型。Or, the fifth interaction process is used for the AI model management network element to receive a request from a network element in the wireless network, where the request is used to request the AI model management network element to send the AI model.
  15. 根据权利要求14所述的方法，其特征在于，The method of claim 14, wherein:
    所述无线网络中的网元包括：能力开放网元，所述能力开放网元包括：网络开放功能NEF网元、业务能力开放功能SCEF网元和策略控制功能PCF网元中的至少一种。The network elements in the wireless network include: a capability exposure network element, and the capability exposure network element includes at least one of a network exposure function NEF network element, a service capability exposure function SCEF network element, and a policy control function PCF network element.
  16. 根据权利要求10至15任一所述的方法，其特征在于，The method according to any one of claims 10 to 15, wherein,
    所述AI模型管理网元中的AI模型包括如下至少之一：第一类型AI模型和第二类型AI模型；The AI model in the AI model management network element includes at least one of the following: a first type AI model and a second type AI model;
    其中，所述第一类型AI模型对应于所述运营商，所述第二类型AI模型对应于第三方应用。The first type of AI model corresponds to the operator, and the second type of AI model corresponds to a third-party application.
  17. 根据权利要求16所述的方法，其特征在于，The method of claim 16, wherein:
    所述第一类型AI模型的模型标识格式为第一类型模型标识格式，所述第一类型模型标识格式包括：运营商标识和模型标识；The model identification format of the first type AI model is the first type model identification format, and the first type model identification format includes: operator identification and model identification;
    所述第二类型AI模型的模型标识格式为第二类型模型标识格式，所述第二类型模型标识格式包括如下至少之一：所述运营商标识、所述模型标识和应用标识。The model identification format of the second type AI model is the second type model identification format, and the second type model identification format includes at least one of the following: the operator identification, the model identification and the application identification.
  18. 根据权利要求17所述的方法，其特征在于，The method of claim 17, wherein:
    所述模型标识的取值包括：标准化模型标识取值和非标准化模型标识取值，所述标准化模型标识取值是通过标准化约定好的模型标识取值，对应于目标类型的AI模型或目标业务的AI模型或目标AI模型。The value of the model identification includes: a standardized model identification value and a non-standardized model identification value, the standardized model identification value is a model identification value agreed by standardization, and corresponds to the AI model of the target type or the target business. AI model or target AI model.
  19. 根据权利要求17所述的方法，其特征在于，The method of claim 17, wherein:
    所述模型标识包括：模型类型标识、模型结构参数标识和模型权重参数标识中的至少一种。The model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
  20. 根据权利要求17所述的方法，其特征在于，The method of claim 17, wherein:
    所述运营商标识由所述运营商或所述第三方应用确定；the operator identification is determined by the operator or the third-party application;
    所述应用标识由所述运营商或所述第三方应用确定。The application identification is determined by the operator or the third-party application.
  21. 一种模型管理系统，其特征在于，所述模型管理系统包括：人工智能AI模型管理模块和AI模型管理网元；A model management system, characterized in that the model management system comprises: an artificial intelligence AI model management module and an AI model management network element;
    所述AI模型管理模块，用于与所述AI模型管理网元，执行第一交互流程；The AI model management module is configured to manage network elements with the AI model and execute a first interaction process;
    其中，所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元是数据网络端用于进行AI模型管理的网元，所述AI模型管理模块支持与所述AI模型管理网元交互，以便为终端设备中的应用层和/或无线协议层下载或上传AI模型。Wherein, the AI model management module is a functional module used for AI model management at the terminal device side, the AI model management network element is a network element used for AI model management at the data network side, and the AI model management module supports Interact with the AI model management network element to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  22. 根据权利要求21所述的系统，其特征在于，所述模型管理系统还包括：第一接口；The system of claim 21, wherein the model management system further comprises: a first interface;
    所述AI模型管理模块，用于与所述AI模型管理网元，执行第一交互流程，包括：The AI model management module is configured to manage network elements with the AI model and execute the first interaction process, including:
    所述AI模型管理模块，用于与所述AI模型管理网元，通过所述第一接口执行所述第一交互流程；The AI model management module is configured to manage network elements with the AI model, and execute the first interaction process through the first interface;
    其中，所述第一交互流程包括如下至少一种：Wherein, the first interaction process includes at least one of the following:
    AI模型请求流程，所述AI模型请求流程用于供所述AI模型管理模块请求从所述AI模 型管理网元下载目标AI模型或向所述AI模型管理网元上传所述目标AI模型；AI model request process, the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element;
    AI模型通知流程，所述AI模型通知流程用于供所述AI模型管理网元通知所述AI模型管理模块需要上传的所述目标AI模型或需要向所述AI模型管理网元发送的所述目标AI模型；AI model notification process, the AI model notification process is used for the AI model management network element to notify the AI model management module of the target AI model that needs to be uploaded or the AI model management network element that needs to be sent to the AI model management network element. target AI model;
    能力协商流程，所述能力协商流程用于供所述AI模型管理模块和所述AI模型管理网元之间协商支持下载或上传的所述目标AI模型；a capability negotiation process, where the capability negotiation process is used for negotiating the target AI model that supports downloading or uploading between the AI model management module and the AI model management network element;
    AI模型下载流程；AI model download process;
    AI模型上传流程。AI model upload process.
  23. 根据权利要求22所述的系统，所述第一接口包括第一控制面和第一用户面；The system of claim 22, the first interface comprising a first control plane and a first user plane;
    其中，所述第一控制面用于执行所述AI模型请求流程、所述AI模型通知流程和所述能力协商流程，所述第一用户面用于执行所述AI模型下载流程和所述AI模型上传流程。The first control plane is used to execute the AI model request process, the AI model notification process and the capability negotiation process, and the first user plane is used to execute the AI model download process and the AI Model upload process.
  24. 根据权利要求21所述的系统，其特征在于，所述AI模型管理系统还包括：第二接口；The system according to claim 21, wherein the AI model management system further comprises: a second interface;
    所述AI模型管理模块用于与第三方应用，通过所述第二接口执行第二交互流程。The AI model management module is configured to perform a second interaction process with a third-party application through the second interface.
  25. 根据权利要求21所述的系统，其特征在于，所述AI模型管理系统还包括：第三接口；The system according to claim 21, wherein the AI model management system further comprises: a third interface;
    所述AI模型管理网元，用于与应用服务器，通过所述第三接口执行第三交互流程；The AI model management network element is configured to perform a third interaction process with the application server through the third interface;
    或，or,
    所述AI模型管理网元，用于与第三方网元，通过所述第三接口执行第四交互流程，所述第三方网元是除所述AI模型管理网元之外的其他网元。The AI model management network element is configured to perform a fourth interaction process with a third-party network element through the third interface, where the third-party network element is another network element other than the AI model management network element.
  26. 根据权利要求21所述的系统，其特征在于，所述AI模型管理系统还包括：第四接口；The system according to claim 21, wherein the AI model management system further comprises: a fourth interface;
    所述AI模型管理网元，用于与无线网络中的网元，通过所述第四接口执行第五交互流程；The AI model management network element is configured to perform a fifth interaction process with the network element in the wireless network through the fourth interface;
    其中，所述第五交互流程用于触发所述无线网络建立专有承载或服务质量QoS数据流；Wherein, the fifth interaction process is used to trigger the wireless network to establish a dedicated bearer or a quality of service QoS data flow;
    或，所述第五交互流程用于所述AI模型管理网元向所述无线网络中的网元发送AI模型；Or, the fifth interaction process is for the AI model management network element to send the AI model to the network element in the wireless network;
    或，所述第五交互流程用于所述AI模型管理网元从所述无线网络中获得AI模型，和/或存储所述AI模型；Or, the fifth interaction process is for the AI model management network element to obtain the AI model from the wireless network, and/or store the AI model;
    或，所述第五交互流程用于供所述AI模型管理网元接收来自所述无线网络中的网元的请求，所述请求用于请求所述AI模型管理网元发送AI模型。Or, the fifth interaction process is used for the AI model management network element to receive a request from a network element in the wireless network, where the request is used to request the AI model management network element to send the AI model.
  27. 根据权利要求26所述的系统，其特征在于，The system of claim 26, wherein:
    所述无线网络中的网元包括：能力开放网元，所述能力开放网元包括：网络开放功能NEF网元、业务能力开放功能SCEF网元和策略控制功能PCF网元中的至少一种。The network elements in the wireless network include: a capability exposure network element, and the capability exposure network element includes at least one of a network exposure function NEF network element, a service capability exposure function SCEF network element, and a policy control function PCF network element.
  28. 根据权利要求21至27任一所述的系统，其特征在于，The system according to any one of claims 21 to 27, wherein,
    所述AI模型管理系统中的AI模型包括如下至少之一：第一类型AI模型和第二类型AI模型；The AI model in the AI model management system includes at least one of the following: a first-type AI model and a second-type AI model;
    其中，所述第一类型AI模型对应于所述运营商，所述第二类型AI模型对应于第三方应用。The first type of AI model corresponds to the operator, and the second type of AI model corresponds to a third-party application.
  29. 根据权利要求28所述的系统，其特征在于，The system of claim 28, wherein:
    所述第一类型AI模型的模型标识格式为第一类型模型标识格式，所述第一类型模型标识 格式包括：运营商标识和模型标识；The model identification format of the first type AI model is the first type model identification format, and the first type model identification format includes: operator identification and model identification;
    所述第二类型AI模型的模型标识格式为第二类型模型标识格式，所述第二类型模型标识格式包括：所述运营商标识、所述模型标识和应用标识。The model identification format of the second type AI model is the second type model identification format, and the second type model identification format includes: the operator identification, the model identification and the application identification.
  30. 根据权利要求29所述的系统，其特征在于，The system of claim 29, wherein:
    所述模型标识的取值包括：标准化模型标识取值和非标准化模型标识取值，所述标准化模型标识取值是通过标准化约定好的取值，对应于目标类型的AI模型或目标业务的AI模型或目标AI模型。The value of the model identifier includes: a standardized model identifier value and a non-standardized model identifier value, the standardized model identifier value is a value agreed upon through standardization, and corresponds to the AI model of the target type or the AI of the target business. Model or target AI model.
  31. 根据权利要求29所述的系统，其特征在于，The system of claim 29, wherein:
    所述模型标识包括：模型类型标识、模型结构参数标识和模型权重参数标识中的至少一种。The model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
  32. 根据权利要求29所述的系统，其特征在于，The system of claim 29, wherein:
    所述运营商标识由所述运营商或所述第三方应用确定；the operator identification is determined by the operator or the third-party application;
    所述应用标识由所述运营商或所述第三方应用确定。The application identification is determined by the operator or the third-party application.
  33. 一种模型管理装置，其特征在于，应用于终端设备中，所述装置包括：人工智能AI模型管理模块；A model management device, characterized in that, when applied to terminal equipment, the device comprises: an artificial intelligence AI model management module;
    所述AI模型管理模块，用于与AI模型管理网元，执行第一交互流程；The AI model management module is used to manage network elements with the AI model and execute the first interaction process;
    所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元是数据网络端用于进行AI模型管理的网元，所述AI模型管理模块支持与所述AI模型管理网元交互，以便为所述终端设备中的应用层和/或无线协议层下载或上传AI模型。The AI model management module is a functional module used for AI model management at the terminal device side, the AI model management network element is a network element used for AI model management at the data network side, and the AI model management module supports and The AI model manages network element interactions in order to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  34. 根据权利要求33所述的装置，其特征在于，The apparatus of claim 33, wherein
    所述AI模型管理模块，用于与所述AI模型管理网元，通过第一接口执行所述第一交互流程；the AI model management module, configured to manage network elements with the AI model, and execute the first interaction process through a first interface;
    其中，所述第一交互流程包括如下至少一种：Wherein, the first interaction process includes at least one of the following:
    AI模型请求流程，所述AI模型请求流程用于供所述AI模型管理模块请求从所述AI模型管理网元下载目标AI模型或向所述AI模型管理网元上传所述目标AI模型；AI model request process, the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element or upload the target AI model to the AI model management network element;
    AI模型通知流程，所述AI模型通知流程用于供所述AI模型管理网元通知所述AI模型管理模块需要上传的所述目标AI模型或需要向所述AI模型管理网元发送的所述目标AI模型；AI model notification process, the AI model notification process is used for the AI model management network element to notify the AI model management module of the target AI model that needs to be uploaded or the AI model management network element that needs to be sent to the AI model management network element. target AI model;
    能力协商流程，所述能力协商流程用于供所述AI模型管理模块和所述AI模型管理网元之间协商支持下载或上传的所述目标AI模型；a capability negotiation process, where the capability negotiation process is used for negotiating the target AI model that supports downloading or uploading between the AI model management module and the AI model management network element;
    AI模型下载流程；AI model download process;
    AI模型上传流程。AI model upload process.
  35. 根据权利要求34所述的装置，其特征在于，所述第一接口包括第一控制面和第一用户面；The apparatus of claim 34, wherein the first interface comprises a first control plane and a first user plane;
    其中，所述第一控制面用于执行所述AI模型请求流程、所述AI模型通知流程和所述能力协商流程，所述第一用户面用于执行所述AI模型下载流程和所述AI模型上传流程。The first control plane is used to execute the AI model request process, the AI model notification process and the capability negotiation process, and the first user plane is used to execute the AI model download process and the AI Model upload process.
  36. 根据权利要求33所述的装置，其特征在于，The apparatus of claim 33, wherein
    所述AI模型管理模块，用于与第三方应用，通过第二接口执行第二交互流程。The AI model management module is used for executing a second interaction process with a third-party application through a second interface.
  37. 根据权利要求33至36任一所述的装置，其特征在于，The device according to any one of claims 33 to 36, characterized in that,
    所述AI模型管理模块中的AI模型包括如下至少之一：第一类型AI模型和第二类型AI模型；The AI model in the AI model management module includes at least one of the following: a first-type AI model and a second-type AI model;
    其中，所述第一类型AI模型对应于运营商，所述第二类型AI模型对应于第三方应用。The first type of AI model corresponds to an operator, and the second type of AI model corresponds to a third-party application.
  38. 根据权利要求37所述的装置，其特征在于，The apparatus of claim 37, wherein:
    所述第一类型AI模型的模型标识格式为第一类型模型标识格式，所述第一类型模型标识格式包括：运营商标识和模型标识；The model identification format of the first type AI model is the first type model identification format, and the first type model identification format includes: operator identification and model identification;
    所述第二类型AI模型的模型标识格式为第二类型模型标识格式，所述第二类型模型标识格式包括如下至少之一：所述运营商标识、应用标识和所述模型标识。The model identification format of the second-type AI model is a second-type model identification format, and the second-type model identification format includes at least one of the following: the operator identification, the application identification, and the model identification.
  39. 根据权利要求38所述的装置，其特征在于，The apparatus of claim 38, wherein:
    所述模型标识的取值包括：标准化模型标识取值和非标准化模型标识取值，所述标准化模型标识取值是通过标准化约定好的取值，对应于目标类型的AI模型或目标业务的AI模型或目标AI模型。The value of the model identifier includes: a standardized model identifier value and a non-standardized model identifier value, the standardized model identifier value is a value agreed upon through standardization, and corresponds to the AI model of the target type or the AI of the target business. Model or target AI model.
  40. 根据权利要求38所述的装置，其特征在于，The apparatus of claim 38, wherein:
    所述模型标识包括：模型类型标识、模型结构参数标识和模型权重参数标识中的至少一种。The model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
  41. 根据权利要求38所述的装置，其特征在于，The apparatus of claim 38, wherein:
    所述运营商标识由所述运营商或所述第三方应用确定；the operator identification is determined by the operator or the third-party application;
    所述应用标识由所述运营商或所述第三方应用确定。The application identification is determined by the operator or the third-party application.
  42. 一种模型管理装置，其特征在于，应用于数据网络中，所述装置包括：人工智能AI模型管理网元模块；A model management device, characterized in that, when applied to a data network, the device comprises: an artificial intelligence AI model management network element module;
    所述AI模型管理网元模块，用于与AI模型管理模块，执行第一交互流程；The AI model management network element module is used for executing the first interaction process with the AI model management module;
    其中，所述AI模型管理模块是终端设备端用于进行AI模型管理的功能模块，所述AI模型管理网元模块是数据网络端用于进行AI模型管理的网元模块，所述AI模型管理模块支持与所述AI模型管理网元模块交互，以便为终端设备中的应用层和/或无线协议层下载或上传AI模型。Wherein, the AI model management module is a functional module used for AI model management at the terminal device side, the AI model management network element module is a network element module used for AI model management at the data network side, and the AI model management The module supports interaction with the AI model management network element module, so as to download or upload the AI model for the application layer and/or the wireless protocol layer in the terminal device.
  43. 根据权利要求42所述的装置，其特征在于，The apparatus of claim 42, wherein
    所述AI模型管理网元模块，用于与AI模型管理模块，通过第一接口执行第一交互流程；The AI model management network element module is used to execute the first interaction process with the AI model management module through the first interface;
    其中，所述第一交互流程包括如下至少一种：Wherein, the first interaction process includes at least one of the following:
    AI模型请求流程，所述AI模型请求流程用于供所述AI模型管理模块请求从所述AI模型管理网元模块下载目标AI模型或向所述AI模型管理网元上传所述目标AI模型；AI model request process, the AI model request process is used for the AI model management module to request to download the target AI model from the AI model management network element module or upload the target AI model to the AI model management network element;
    AI模型通知流程，所述AI模型通知流程用于供所述AI模型管理网元模块通知所述AI模型管理模块需要上传的所述目标AI模型或需要向所述AI模型管理网元发送的所述目标AI模型；AI model notification process, the AI model notification process is used for the AI model management network element module to notify the AI model management module of the target AI model that needs to be uploaded or the target AI model that needs to be sent to the AI model management network element. Describe the target AI model;
    能力协商流程，所述能力协商流程用于供所述AI模型管理模块和所述AI模型管理网元模块之间协商支持下载或上传的所述目标AI模型；a capability negotiation process, where the capability negotiation process is used for negotiating the target AI model that supports downloading or uploading between the AI model management module and the AI model management network element module;
    AI模型下载流程；AI model download process;
    AI模型上传流程。AI model upload process.
  44. 根据权利要求43所述的装置，其特征在于，所述第一接口包括第一控制面和第一用户面；The apparatus of claim 43, wherein the first interface comprises a first control plane and a first user plane;
    其中，所述第一控制面用于执行所述AI模型请求流程、所述AI模型通知流程和所述能力协商流程，所述第一用户面用于执行所述AI模型下载流程和所述AI模型上传流程。The first control plane is used to execute the AI model request process, the AI model notification process and the capability negotiation process, and the first user plane is used to execute the AI model download process and the AI Model upload process.
  45. 根据权利要求42所述的装置，其特征在于，The apparatus of claim 42, wherein
    所述AI模型管理网元模块，用于与应用服务器，通过第三接口执行第三交互流程；The AI model management network element module is used to perform a third interaction process with the application server through a third interface;
    或，or,
    所述AI模型管理网元模块，用于与第三方网元，通过所述第三接口执行第四交互流程，所述第三方网元是除所述AI模型管理网元之外的其他网元。The AI model management network element module is used to perform a fourth interaction process with a third-party network element through the third interface, and the third-party network element is other network elements except the AI model management network element .
  46. 根据权利要求42所述的装置，其特征在于，The apparatus of claim 42, wherein
    所述AI模型管理网元模块，用于与无线网络中的网元，通过第四接口执行第五交互流程；The AI model management network element module is configured to perform a fifth interaction process with a network element in a wireless network through a fourth interface;
    其中，所述第五交互流程用于触发所述无线网络建立专有承载或服务质量QoS数据流；Wherein, the fifth interaction process is used to trigger the wireless network to establish a dedicated bearer or a quality of service QoS data flow;
    或，所述第五交互流程用于所述AI模型管理网元模块向所述无线网络中的网元发送AI模型；Or, the fifth interaction process is for the AI model management network element module to send the AI model to the network element in the wireless network;
    或，所述第五交互流程用于所述AI模型管理网元模块从所述无线网络中获得AI模型，和/或存储所述AI模型；Or, the fifth interaction process is for the AI model management network element module to obtain the AI model from the wireless network, and/or store the AI model;
    或，所述第五交互流程用于供所述AI模型管理网元模块接收来自所述无线网络中的网元的请求，所述请求用于请求所述AI模型管理网元模块发送AI模型。Or, the fifth interaction process is used for the AI model management network element module to receive a request from a network element in the wireless network, where the request is used to request the AI model management network element module to send the AI model.
  47. 根据权利要求46所述的装置，其特征在于，The apparatus of claim 46, wherein:
    所述无线网络中的网元包括：能力开放网元，所述能力开放网元包括：网络开放功能NEF网元、业务能力开放功能SCEF网元和策略控制功能PCF网元中的至少一种。The network elements in the wireless network include: a capability exposure network element, and the capability exposure network element includes at least one of a network exposure function NEF network element, a service capability exposure function SCEF network element, and a policy control function PCF network element.
  48. 根据权利要求42至47任一所述的装置，其特征在于，The device according to any one of claims 42 to 47, characterized in that:
    所述AI模型管理网元模块中的AI模型包括如下至少之一：第一类型AI模型和第二类型AI模型；The AI model in the AI model management network element module includes at least one of the following: a first type AI model and a second type AI model;
    其中，所述第一类型AI模型对应于所述运营商，所述第二类型AI模型对应于第三方应用。The first type of AI model corresponds to the operator, and the second type of AI model corresponds to a third-party application.
  49. 根据权利要求48所述的装置，其特征在于，The apparatus of claim 48, wherein
    所述第一类型AI模型的模型标识格式为第一类型模型标识格式，所述第一类型模型标识格式包括：运营商标识和模型标识；The model identification format of the first type AI model is the first type model identification format, and the first type model identification format includes: operator identification and model identification;
    所述第二类型AI模型的模型标识格式为第二类型模型标识格式，所述第二类型模型标识格式包括如下至少之一：所述运营商标识、所述模型标识和应用标识。The model identification format of the second type AI model is the second type model identification format, and the second type model identification format includes at least one of the following: the operator identification, the model identification and the application identification.
  50. 根据权利要求49所述的装置，其特征在于，The apparatus of claim 49, wherein
    所述模型标识的取值包括：标准化模型标识取值和非标准化模型标识取值，所述标准化模型标识取值是通过标准化约定好的模型标识取值，对应于目标类型的AI模型或目标业务的AI模型或目标AI模型。The value of the model identification includes: a standardized model identification value and a non-standardized model identification value, the standardized model identification value is a model identification value agreed by standardization, and corresponds to the AI model of the target type or the target business. AI model or target AI model.
  51. 根据权利要求49所述的装置，其特征在于，The apparatus of claim 49, wherein
    所述模型标识包括：模型类型标识、模型结构参数标识和模型权重参数标识中的至少一种。The model identifier includes at least one of a model type identifier, a model structure parameter identifier, and a model weight parameter identifier.
  52. 根据权利要求49所述的装置，其特征在于，The apparatus of claim 49, wherein
    所述运营商标识由所述运营商或所述第三方应用确定；the operator identification is determined by the operator or the third-party application;
    所述应用标识由所述运营商或所述第三方应用确定。The application identification is determined by the operator or the third-party application.
  53. 一种终端设备，其特征在于，所述终端设备包括：A terminal device, characterized in that the terminal device includes:
    处理器；processor;
    与所述处理器相连的收发器；a transceiver connected to the processor;
    用于存储所述处理器的可执行指令的存储器；memory for storing executable instructions for the processor;
    其中，所述处理器被配置为加载并执行所述可执行指令以实现如权利要求1至9中任一所述的模型管理方法。Wherein, the processor is configured to load and execute the executable instructions to implement the model management method of any one of claims 1 to 9.
  54. 一种数据网络，其特征在于，所述数据网络包括：A data network, characterized in that the data network includes:
    处理器；processor;
    与所述处理器相连的收发器；a transceiver connected to the processor;
    用于存储所述处理器的可执行指令的存储器；memory for storing executable instructions for the processor;
    其中，所述处理器被配置为加载并执行所述可执行指令以实现如权利要求10至20中任一所述的模型管理方法。Wherein, the processor is configured to load and execute the executable instructions to implement the model management method of any one of claims 10-20.
  55. 一种计算机可读存储介质，其特征在于，所述可读存储介质中存储有可执行指令，所述可执行指令由处理器加载并执行以实现如权利要求1至20中任一所述的模型管理方法。A computer-readable storage medium, wherein executable instructions are stored in the readable storage medium, and the executable instructions are loaded and executed by a processor to implement the method according to any one of claims 1 to 20. Model management methods.
PCT/CN2020/106415 2020-07-31 2020-07-31 Model management method, system and apparatus, communication device, and storage medium WO2022021421A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202080101791.0A CN115699842A (en) 2020-07-31 2020-07-31 Model management method, system, device, communication equipment and storage medium
PCT/CN2020/106415 WO2022021421A1 (en) 2020-07-31 2020-07-31 Model management method, system and apparatus, communication device, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/106415 WO2022021421A1 (en) 2020-07-31 2020-07-31 Model management method, system and apparatus, communication device, and storage medium

Publications (1)

Publication Number Publication Date
WO2022021421A1 true WO2022021421A1 (en) 2022-02-03

Family

ID=80037376

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/106415 WO2022021421A1 (en) 2020-07-31 2020-07-31 Model management method, system and apparatus, communication device, and storage medium

Country Status (2)

Country Link
CN (1) CN115699842A (en)
WO (1) WO2022021421A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023039905A1 (en) * 2021-09-18 2023-03-23 Oppo广东移动通信有限公司 Ai data transmission method and apparatus, device, and storage medium
WO2024082261A1 (en) * 2022-10-21 2024-04-25 北京小米移动软件有限公司 Model management method and apparatus, and device and medium
WO2024092852A1 (en) * 2022-11-06 2024-05-10 北京小米移动软件有限公司 Communication method and apparatus, and storage medium
WO2024120285A1 (en) * 2022-12-07 2024-06-13 维沃移动通信有限公司 Information transmission method and apparatus, and terminal and network-side device

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024103544A1 (en) * 2023-02-10 2024-05-23 Zte Corporation Transfer of artificial intelligence network management models in wireless communication systems

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109155012A (en) * 2016-12-30 2019-01-04 谷歌有限责任公司 Assess the accuracy of machine learning model
CN109698822A (en) * 2018-11-28 2019-04-30 众安信息技术服务有限公司 Combination learning method and system based on publicly-owned block chain and encryption neural network
US20190286989A1 (en) * 2018-03-15 2019-09-19 Polarr, Inc. Distributed neural network model utilization system
CN110866588A (en) * 2019-11-08 2020-03-06 中国科学院软件研究所 Training learning method and system for realizing individuation of learnable ability model of intelligent virtual digital animal
CN111295863A (en) * 2017-10-30 2020-06-16 苹果公司 Extended implementation of enhanced broadcast multicast services for broadcast multicast content selection and services
CN111435926A (en) * 2019-01-11 2020-07-21 中国移动通信有限公司研究院 MIMO system channel prediction method, device, medium and equipment

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109155012A (en) * 2016-12-30 2019-01-04 谷歌有限责任公司 Assess the accuracy of machine learning model
CN111295863A (en) * 2017-10-30 2020-06-16 苹果公司 Extended implementation of enhanced broadcast multicast services for broadcast multicast content selection and services
US20190286989A1 (en) * 2018-03-15 2019-09-19 Polarr, Inc. Distributed neural network model utilization system
CN109698822A (en) * 2018-11-28 2019-04-30 众安信息技术服务有限公司 Combination learning method and system based on publicly-owned block chain and encryption neural network
CN111435926A (en) * 2019-01-11 2020-07-21 中国移动通信有限公司研究院 MIMO system channel prediction method, device, medium and equipment
CN110866588A (en) * 2019-11-08 2020-03-06 中国科学院软件研究所 Training learning method and system for realizing individuation of learnable ability model of intelligent virtual digital animal

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023039905A1 (en) * 2021-09-18 2023-03-23 Oppo广东移动通信有限公司 Ai data transmission method and apparatus, device, and storage medium
WO2024082261A1 (en) * 2022-10-21 2024-04-25 北京小米移动软件有限公司 Model management method and apparatus, and device and medium
WO2024092852A1 (en) * 2022-11-06 2024-05-10 北京小米移动软件有限公司 Communication method and apparatus, and storage medium
WO2024120285A1 (en) * 2022-12-07 2024-06-13 维沃移动通信有限公司 Information transmission method and apparatus, and terminal and network-side device

Also Published As

Publication number Publication date
CN115699842A (en) 2023-02-03

Similar Documents

Publication Publication Date Title
WO2022021421A1 (en) Model management method, system and apparatus, communication device, and storage medium
Bonati et al. Open, programmable, and virtualized 5G networks: State-of-the-art and the road ahead
US11736942B2 (en) Multi-domain trust establishment in edge cloud architectures
EP4099635A1 (en) Method and device for selecting service in wireless communication system
CN109818868B (en) Method, device, equipment and storage medium for realizing edge network capability opening
US20230209390A1 (en) Intelligent Radio Access Network
WO2022011862A1 (en) Method and system for communication between o-ran and mec
CN115119331A (en) Reinforcement learning for multi-access traffic management
JP2022093339A (en) QoS control method and device
EP2949136B1 (en) Communication between machine-to-machine service layers and transport network
Upadhyaya et al. Prototyping next-generation O-RAN research testbeds with SDRs
US20240193021A1 (en) Platform independent application programming interface configuration
US9769742B2 (en) Devices, methods, and computer readable storage devices for providing application services
EP4304238A1 (en) Model processing method, communication device, and system
WO2019199311A1 (en) Qos and home routed roaming
WO2022218347A1 (en) Communication system and method, first functional entity, and storage medium
CN117716674A (en) Network resource model-based solution for AI-ML model training
KR20230139297A (en) Communication related to federated learning
da Silva et al. Demonstration of open radio access network intelligent controllers
CN107211479B (en) Method and device for selecting access network
US20240114332A1 (en) Method and apparatus for managing user consent for roaming ue in wireless communication system
WO2023030077A1 (en) Communication method, communication apparatus, and communication system
CN114143832B (en) Service processing method, device and storage medium
EP4369678A1 (en) Conflict management of functions and services
WO2024000166A1 (en) Sensing data providing methods and apparatuses, device, storage medium and program product

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: 20946662

Country of ref document: EP

Kind code of ref document: A1