WO2022126563A1 - 网络资源选择方法、终端设备和网络设备 - Google Patents

网络资源选择方法、终端设备和网络设备 Download PDF

Info

Publication number
WO2022126563A1
WO2022126563A1 PCT/CN2020/137414 CN2020137414W WO2022126563A1 WO 2022126563 A1 WO2022126563 A1 WO 2022126563A1 CN 2020137414 W CN2020137414 W CN 2020137414W WO 2022126563 A1 WO2022126563 A1 WO 2022126563A1
Authority
WO
WIPO (PCT)
Prior art keywords
service
network device
network
terminal device
service parameters
Prior art date
Application number
PCT/CN2020/137414
Other languages
English (en)
French (fr)
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 EP20965579.4A priority Critical patent/EP4266756A4/en
Priority to CN202080107755.5A priority patent/CN116569605A/zh
Priority to PCT/CN2020/137414 priority patent/WO2022126563A1/zh
Publication of WO2022126563A1 publication Critical patent/WO2022126563A1/zh
Priority to US18/335,499 priority patent/US20230337065A1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W28/00Network traffic management; Network resource management
    • H04W28/16Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/02Arrangements for optimising operational condition
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W48/00Access restriction; Network selection; Access point selection
    • H04W48/02Access restriction performed under specific conditions
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W48/00Access restriction; Network selection; Access point selection
    • H04W48/08Access restriction or access information delivery, e.g. discovery data delivery
    • H04W48/12Access restriction or access information delivery, e.g. discovery data delivery using downlink control channel
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W48/00Access restriction; Network selection; Access point selection
    • H04W48/18Selecting a network or a communication service
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W76/00Connection management
    • H04W76/10Connection setup
    • H04W76/12Setup of transport tunnels
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W8/00Network data management
    • H04W8/22Processing or transfer of terminal data, e.g. status or physical capabilities
    • H04W8/24Transfer of terminal data
    • H04W8/245Transfer of terminal data from a network towards a terminal

Definitions

  • the present application relates to the field of communications, and more particularly, to a network resource selection method, a terminal device, and a network device.
  • AI Artificial intelligence
  • the embodiments of the present application propose a network resource selection method, terminal equipment, and network equipment, which can divide network resources according to AI services, so as to make full use of the advantages of various network resources to better realize AI service capabilities.
  • the embodiment of the present application proposes a network resource selection method, including:
  • the terminal device sends artificial intelligence AI service parameters to the first network device, where the AI service parameters are used to select corresponding AI domain resources for the terminal device.
  • the embodiment of the present application also proposes a network resource selection method, including:
  • the first network device receives AI service parameters from the terminal device
  • the first network device selects a corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the embodiment of the present application also proposes a network resource selection method, including:
  • the second network device receives the AI service parameter
  • the second network device selects the corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the embodiment of the present application also proposes a network resource selection method, including:
  • the third network device receives AI service parameters
  • the third network device selects the corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the embodiment of the present application also proposes a method for sending subscription information, including:
  • the fourth network device receives the subscription information acquisition request, and the subscription information acquisition request carries the AI service parameter;
  • the fourth network device sends subscription information related to the AI service parameter.
  • the embodiment of the present application also proposes a method for sending policies or rules, including:
  • the fifth network device receives the policy or rule acquisition request, and the policy or rule acquisition request carries AI service parameters;
  • the fifth network device sends policies or rules related to AI service parameters.
  • the embodiment of the present application also proposes a method for dividing network resources, including:
  • the network resources are divided into multiple AI domain resources, and each AI domain resource includes resources used for at least one AI service.
  • the embodiment of the present application also proposes a terminal device, including:
  • the first sending module is configured to send artificial intelligence AI service parameters to the first network device, where the AI service parameters are used to select corresponding AI domain resources for the terminal device.
  • the embodiment of the present application also proposes a network device, including:
  • a second receiving module configured to receive AI service parameters from the terminal device
  • the first selection module is used to select the corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the embodiment of the present application also proposes a network device, including:
  • the third receiving module is used to receive AI service parameters
  • the second selection module is used to select the corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the embodiment of the present application also proposes a network device, including:
  • the fourth receiving module is used to receive AI service parameters
  • the third selection module is used to select the corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the embodiment of the present application also proposes a network device, including:
  • a fifth receiving module configured to receive a contract information acquisition request, where the contract information acquisition request carries AI service parameters
  • the second sending module is configured to send subscription information related to AI service parameters.
  • the embodiment of the present application also proposes a network device, including:
  • the sixth receiving module is used to receive a policy or rule acquisition request, and the policy or rule acquisition request carries AI service parameters;
  • the third sending module is used for sending policies or rules related to AI service parameters.
  • the embodiment of the present application also proposes an apparatus for dividing network resources, including:
  • the dividing module is used to divide the network resources into multiple AI domain resources, and each AI domain resource includes resources used for at least one AI service.
  • network resources are divided into multiple AI domain resources according to AI services, and the terminal device sends AI service parameters to the network device, so that the corresponding AI domain resources can be selected for the terminal device.
  • FIG. 1 is a schematic diagram of an application scenario of an embodiment of the present application.
  • 2A is a schematic diagram of a centralized big data analysis scenario
  • FIG. 2B is a schematic diagram of a fully distributed big data analysis scenario
  • 2C is a schematic diagram of a hybrid big data analysis scenario
  • FIG. 3 is a schematic diagram of a network resource division manner according to an embodiment of the present application. ;
  • FIG. 4 is an implementation flowchart of a network resource selection method 400 according to an embodiment of the present application.
  • Fig. 5 is the realization flow chart of the embodiment 1 of the present application.
  • Fig. 6 is the realization flow chart of Embodiment 2 of the present application.
  • Fig. 7 is the realization flow chart of Embodiment 3 of the present application.
  • FIG. 8 is an implementation flowchart of a network resource selection method 800 according to an embodiment of the present application.
  • FIG. 9 is an implementation flowchart of a network resource selection method 900 according to an embodiment of the present application.
  • FIG. 10 is an implementation flowchart of a network resource selection method 1000 according to an embodiment of the present application.
  • FIG. 11 is an implementation flowchart of a method 1100 for sending subscription information according to an embodiment of the present application
  • FIG. 12 is an implementation flowchart of a method 1200 for sending policies or rules according to an embodiment of the present application
  • FIG. 13 is a schematic structural diagram of a terminal device 1300 according to an embodiment of the present application.
  • FIG. 14 is a schematic structural diagram of a terminal device 1400 according to an embodiment of the present application.
  • FIG. 15 is a schematic structural diagram of a network device 1500 according to an embodiment of the present application.
  • FIG. 16 is a schematic structural diagram of a network device 1600 according to an embodiment of the present application.
  • FIG. 17 is a schematic structural diagram of a network device 1700 according to an embodiment of the present application.
  • FIG. 18 is a schematic structural diagram of a network device 1800 according to an embodiment of the present application.
  • FIG. 19 is a schematic structural diagram of a network device 1900 according to an embodiment of the present application.
  • FIG. 20 is a schematic structural diagram of a network device 2000 according to an embodiment of the present application.
  • FIG. 21 is a schematic structural diagram of a network device 2100 according to an embodiment of the present application.
  • FIG. 22 is a schematic structural diagram of a network device 2200 according to an embodiment of the present application.
  • FIG. 23 is a schematic structural diagram of a communication device 2300 according to an embodiment of the present application.
  • FIG. 24 is a schematic structural diagram of a chip 2400 according to an embodiment of the present application.
  • 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
  • LTE-A Advanced Long Term Evolution
  • NR New Radio
  • LTE LTE-based access to unlicensed spectrum
  • LTE-U Universal Mobile Telecommunication System
  • UMTS Universal Mobile Telecommunication System
  • WLAN Wireless Local Area Networks
  • WiFi Wireless Fidelity
  • the communication system in this embodiment of the present application may be applied to a carrier aggregation (Carrier Aggregation, CA) scenario, a dual connectivity (Dual Connectivity, DC) scenario, or a standalone (Standalone, SA) distribution. web scene.
  • Carrier Aggregation, CA Carrier Aggregation, CA
  • DC Dual Connectivity
  • SA standalone
  • This embodiment of the present application does not limit the applied spectrum.
  • the embodiments of the present application can be applied to licensed spectrum, and can also be applied to unlicensed spectrum.
  • terminal equipment may also be referred to as user equipment (User Equipment, UE), access terminal, subscriber unit, subscriber station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.
  • UE User Equipment
  • access terminal subscriber unit, subscriber station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.
  • the terminal device can be a station (STAION, ST) in the WLAN, can be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a personal digital processing (Personal Digital Assistant, PDA) devices, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, in-vehicle devices, wearable devices, and next-generation communication systems, such as terminal devices in NR networks or Terminal equipment in the future evolved Public Land Mobile Network (Public Land Mobile Network, PLMN) network, etc.
  • STAION, ST in the WLAN
  • SIP Session Initiation Protocol
  • WLL Wireless Local Loop
  • PDA Personal Digital Assistant
  • the terminal device may also be a wearable device.
  • Wearable devices can also be called wearable smart devices, which are the general term for the intelligent design of daily wear and the development of wearable devices using wearable technology, such as glasses, gloves, watches, clothing and shoes.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction.
  • wearable smart devices include full-featured, large-scale, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, and only focus on a certain type of application function, which needs to cooperate with other devices such as smart phones.
  • a network device can be a device used to communicate with a mobile device.
  • the network device can be an access point (Access Point, AP) in WLAN, a base station (Base Transceiver Station, BTS) in GSM or CDMA, or a WCDMA
  • a base station NodeB, NB
  • it can also be an evolved base station (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, wearable device, and network equipment (gNB) in NR networks Or network equipment in the PLMN network that evolves in the future.
  • AP Access Point
  • BTS Base Transceiver Station
  • gNB network equipment
  • a network device provides services for a cell
  • a terminal device communicates with the network device through transmission resources (for example, frequency domain resources, or spectrum resources) used by the cell
  • the cell may be a network device (for example, a frequency domain resource).
  • the cell corresponding to the base station), the cell can belong to the macro base station, or it can belong to the base station corresponding to the small cell (Small cell), where the small cell can include: Metro cell, Micro cell, Pico cell cell), Femto cell, etc.
  • These small cells have the characteristics of small coverage and low transmit power, and are suitable for providing high-speed data transmission services.
  • FIG. 1 exemplarily shows one network device 110 and two terminal devices 120.
  • the wireless communication system 100 may include a plurality of network devices 110, and the coverage of each network device 110 may include other numbers
  • the terminal device 120 is not limited in this embodiment of the present application.
  • the embodiments of the present application may be applied to one terminal device 120 and one network device 110 , and may also be applied to one terminal device 120 and another terminal device 120 .
  • the wireless communication system 100 may further include other network entities such as a mobility management entity (Mobility Management Entity, MME), an access and mobility management function (Access and Mobility Management Function, AMF). This is not limited.
  • MME Mobility Management Entity
  • AMF Access and Mobility Management Function
  • the "instruction" mentioned in the embodiments of the present application may be a direct instruction, an indirect instruction, or an associated relationship.
  • a indicates B it can indicate that A directly indicates B, for example, B can be obtained through A; it can also indicate that A indicates B indirectly, such as A indicates C, and B can be obtained through C; it can also indicate that there is an association between A and B relation.
  • corresponding may indicate that there is a direct or indirect corresponding relationship between the two, or may indicate that there is an associated relationship between the two, or indicate and be instructed, configure and be instructed configuration, etc.
  • AI/Machine Learning (ML, Machine Learning) (which can also become big data analysis) is the future direction of network development and can be used for optimization of communication systems, such as optimization of terminal configuration parameters, policy control and billing (PCC, Policy Control and Charging)/Quality of Service (QoS, Quantity of Service) parameter optimization, etc.
  • network elements and functions related to big data analysis need to be introduced into communication networks (such as mobile communication networks), such as network data analysis function (NWDAF, Network Data Analytics Function) network elements for collecting, analyzing and forming valuable data.
  • NWDAF Network Data Analytics Function
  • a multi-level AI/ML approach can be considered, that is, network elements and terminals on the network side divide the labor for big data analysis.
  • FIG. 2A is a schematic diagram of a centralized big data analysis scenario, that is, after all terminals report the required data, the big data analysis work is all performed on the network server.
  • FIG. 2B is a schematic diagram of a fully distributed big data analysis scenario, that is, different terminals perform local analysis on the collected data.
  • Figure 2C is a schematic diagram of a hybrid big data analysis scenario, that is, after the terminal performs a part of the analysis on the collected data locally, the result is sent to the network server, and the network server performs further calculation and analysis.
  • data interaction between terminal devices and terminal devices may also be introduced to complete big data analysis or result sharing.
  • terminal devices may allocate different AI/ML models and computing workloads according to their needs, and complete the calculations within the required time and successfully send them to the network server.
  • the embodiment of the present application proposes a method for dividing network resources, which can divide network resources according to AI services.
  • network resources may be divided into multiple AI domain resources, and each AI domain resource includes resources used for at least one AI service.
  • the AI service can be a business or service provided based on a specific condition, or a specific business or service provided by one or some companies.
  • different AI technology processing solutions are provided based on different users, scenarios, locations, time and other factors, and each AI technology processing solution can correspond to one AI service.
  • FIG. 3 is a schematic diagram of a network resource division manner according to an embodiment of the present application.
  • the AI domain proposed in this embodiment of the present application may refer to a network resource used for a specific AI service in the network, and the network resource may refer to a specific one or more servers (or network elements), or a server specific resources in .
  • corresponding resources may be divided on different network elements, and the resources divided on each network element may be combined to support an AI domain.
  • the corresponding network resources are divided in the UE, RAN and core network respectively, and the terminal, edge data center (DC, Data Center) and local data are divided into corresponding network resources.
  • a part of computing resources and data resources are divided into equipment such as the center (Local DC), and these divided resources together form the "wireless resource optimization" AI domain in Figure 3.
  • the AI domain proposed in the embodiments of the present application has multiple resources that a single network does not have, and can provide optimal strategies for accurate AI model allocation, network resource scheduling, data sharing, and the like.
  • each node does its best to provide data, AI model management, computing power, communication capabilities, etc.
  • the AI domain resources in an AI domain may include at least one of an AI model, network computing power, communication resources, communication resources, and data. As shown in Figure 3, these resources can all be pooled resources that can be shared within an AI domain.
  • the communication resources may include network resources, such as access network resources, core network resources, such as base stations, access mobility/management network elements (AMF, Access and Mobility Management Function), session management network elements (SMF, Session Management Function) ), User Plane Function (UPF, User Plane Function) and other network devices.
  • AMF access mobility/management network elements
  • SMF Session Management Function
  • UPF User Plane Function
  • the AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device, and the application server.
  • the network elements participating in the AI domain include one or more of terminals, base stations, core network elements, and application servers, and the AI domain can be planned across multiple network slices.
  • the AI domain may be divided according to at least one of business, location, user, and third-party customization.
  • AI domains can be divided according to business, and can be further subdivided according to dimensions such as location, user, and third-party customization.
  • the decision point in the AI domain can determine the most Appropriate AI model, and call the corresponding storage module to send the AI model to the terminal.
  • the decision point for the terminal to decide the most suitable AI model may be determined by the characteristics of the terminal, such as the location of the terminal, user preferences, terminal power, computing power, service requirements, and so on. That is to say, the decision point of the AI domain can be matched with the most suitable AI model according to the historical data and training results, combined with the characteristics of the terminal.
  • the mobile network can select appropriate network resources for the UE according to the AI services requested, selected or allowed by the UE.
  • FIG. 4 is an implementation flowchart of a network resource selection method 400 according to an embodiment of the present application, including:
  • the terminal device sends an AI service parameter to the first network device, where the AI service parameter is used to select a corresponding AI domain resource for the terminal device.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • AI service parameters may also be referred to as AI domain parameters, AI service parameters, AI parameters, or other similar names.
  • AI service parameters correspond to AI domains, and AI domain resources in each AI domain include resources used for at least one AI service.
  • the above-mentioned AI domain resources include at least one of AI models, network computing power, communication resources, and data, and these resources can be pooled resources and can be shared in an AI domain.
  • the AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device and the application server.
  • the above-mentioned first network device includes a base station, the base station broadcasts the AI domain or AI service allowed or supported by the network to which the base station belongs, and the terminal device determines whether to reside in the base station according to the message broadcasted by the base station and the AI service selected by itself.
  • the cell where the base station is located and/or an RRC connection is initiated to the base station.
  • step S410 includes:
  • the terminal device receives AI service parameters allowed or supported by the first network, where the AI service parameters allowed or supported by the first network correspond to the AI services allowed or supported by the first network;
  • the terminal device sends AI service parameters to the first network device according to the AI service allowed or supported by the first network and the AI service required by the terminal device.
  • the above-mentioned first network may include at least one of a terminal, a base station, a core network, and an application server.
  • the above-mentioned first network device may be a base station in the first network.
  • the above-mentioned terminal device sending AI service parameters to the first network device may refer to the terminal device establishing a data connection with the first network using AI service parameters allowed or supported in the first network.
  • the above method may also include:
  • the terminal device receives allowed AI service parameters, where the allowed AI service parameters correspond to AI domain resources provided for the terminal device.
  • the allowed AI service parameters may be sent by the AMF to the terminal device.
  • the AMF can determine whether the terminal device is allowed to register and/or which AI services are allowed according to the AI service parameters, and feed back the allowed AI service parameters to the terminal device.
  • the terminal device may carry the above AI service parameters when initiating an AS layer RRC connection establishment and/or a NAS layer registration request.
  • the terminal device in the above step S410 sends AI service parameters to the first network device, including:
  • the terminal device sends a registration request message to the first network device, where the registration request message carries AI service parameters, such as AI service parameters requested by the terminal device; or,
  • the terminal device sends a session establishment/modification request message to the first network device, where the session establishment/modification request message carries AI service parameters, such as AI service parameters allowed by the terminal device, for establishing a PDU session; or,
  • the terminal device sends an AS layer message to the first network device, where the AS layer message carries AI service parameters, such as AI service parameters requested or allowed by the terminal device.
  • AI service parameters such as AI service parameters requested or allowed by the terminal device.
  • the above AI service parameters are used to select the corresponding AI domain resources for the terminal device. For example, when the base station receives the AI service parameter, it can select the corresponding core network element for the terminal device according to the parameter; when the AMF receives the AI service parameter, it can select a suitable SMF for the terminal device according to the parameter; when the SMF receives When the AI service parameter is reached, the appropriate UPF or mobile gateway can be selected for the terminal device according to the parameter.
  • the above-mentioned process of selecting network elements based on AI service parameters may occur in a registration management process and/or a session management process.
  • the AI service parameters may refer to AI service parameters corresponding to one or more AI services (such as an AR service, a VR service in a certain scenario, and a company's autonomous driving service) requested, selected or permitted by the terminal device.
  • AI services such as an AR service, a VR service in a certain scenario, and a company's autonomous driving service
  • FIG. 5 is a flowchart of the implementation of Embodiment 1 of the present application. As shown in FIG. 5 , this embodiment includes the following steps:
  • the terminal device sends a registration request to the AMF through the access network, where the registration request carries AI service parameters used by the terminal device, such as AI service parameters requested by the terminal device.
  • the AMF determines, according to the AI service parameters requested by the terminal device, whether to allow the terminal device to register, and/or which AI services (or AI services provided for the terminal device) are allowed. Specifically, the AMF can be determined according to the preconfigured information about the correspondence between the terminal device and the AI service; or, the AMF can interact with other network elements (such as network element A in FIG. 5 ), according to the terminal equipment stored in the other network elements. Correspondence information with the AI service is determined. The other network elements may be existing network elements in the communication system, or may be newly added network elements.
  • the AMF sends a subscription information acquisition request to a unified data management (UDM, Unified Data Manager) platform, and the subscription information acquisition request may carry the AI service parameters requested by the terminal device, or carry the allowed AI service parameters, the allowed AI service parameters
  • the parameter corresponds to the allowed AI service (or AI service provided for the terminal device) determined by the AMF in step S502.
  • the UDM generates subscription information corresponding to the AI service parameters, and returns the subscription information to the AMF.
  • the AMF sends a policy or rule acquisition request to a policy control function (PCF, Policy Control Function), and the policy or rule acquisition request may carry the AI service parameters requested by the terminal device, or carry the allowed AI service parameters.
  • the service parameter corresponds to the allowed AI service (or AI service provided for the terminal device) determined by the AMF in step S502.
  • the PCF generates a policy or rule corresponding to the AI service parameter, and returns the policy or rule to the AMF.
  • the AMF sends a registration reply message to the terminal device, where the registration reply message may carry AI service parameters corresponding to the permitted AI service (or AI service provided for the terminal device) determined in step S502.
  • the AI service parameters requested by the terminal device in the above step S501 and the allowed AI service parameters fed back in the step S505 may have a relationship of inclusion and inclusion, or may not have an inclusion relationship.
  • the allowed AI service parameters are one or more of the AI service parameters requested by the terminal device, or the allowed AI service parameters do not belong to the AI service parameters requested by the terminal device.
  • This embodiment relates to an implementation manner of using AI service parameters to allocate network resources in a session management process. Since the application server may also participate in the AI domain, the selection of the mobile gateway (such as SMF and/or UPF) is very important, and it is necessary to select a gateway closest to the application server in the AI domain, which is also the purpose of this embodiment. Highlighted content.
  • the mobile gateway such as SMF and/or UPF
  • FIG. 6 is a flow chart of the implementation of Embodiment 2 of the present application. As shown in FIG. 6 , this embodiment includes the following steps:
  • the terminal device sends a registration request to the AMF through the access network, where the registration request carries AI service parameters used by the terminal device, such as AI service parameters allowed by the terminal device.
  • the AMF selects a corresponding SMF according to the AI service parameter used by the terminal device, and initiates a session establishment request to the SMF.
  • the session establishment request sent to the SMF may carry the AI service parameters used by the terminal device.
  • the SMF sends a subscription information acquisition request to the UDM, where the subscription information acquisition request may carry AI service parameters used by the terminal device.
  • the UDM generates subscription information corresponding to the AI service parameters, and returns the subscription information to the SMF.
  • the SMF sends a policy or rule acquisition request to the PCF, where the policy or rule acquisition request may carry AI service parameters used by the terminal device.
  • the PCF generates a policy or rule corresponding to the AI service parameters used by the terminal device, and returns the policy or rule to the SMF.
  • the SMF selects a corresponding UPF according to the AI service parameter used by the terminal device, and initiates a session establishment request to the UPF to establish a session with the UPF.
  • the SMF returns a session establishment reply message to the AMF, and the AMF returns a session establishment reply message to the terminal device. Afterwards, the terminal device establishes a user plane session with the application server for transmitting data with the application server.
  • This embodiment relates to an example in which the terminal device carries AI service parameters at the AS layer.
  • the base station may carry supported or allowed AI service parameters in the broadcast message, and the terminal device selects the AI service parameters used by itself according to the AI service parameters sent by the base station.
  • FIG. 7 is a flowchart of the implementation of Embodiment 3 of the present application. As shown in FIG. 7 , this embodiment includes the following steps:
  • the base station sends a broadcast message, where the broadcast message includes AI service parameters supported or allowed by the network to which the base station belongs, and the AI service parameters correspond to AI services allowed or supported by the network to which the base station belongs.
  • the terminal device determines, according to the broadcast of the base station and the AI service selected by itself, whether to camp in the cell where the base station is located, and/or initiates a connection establishment request (eg, an RRC connection establishment request) to the base station.
  • a connection establishment request eg, an RRC connection establishment request
  • the terminal equipment If it is selected to initiate a connection establishment request to the base station, the terminal equipment carries the AI service parameters used by the terminal equipment in the AS layer message (such as the RRC establishment complete message) sent to the base station, such as the terminal equipment request or allowed AI service parameters .
  • the AI service parameter requested or permitted by the terminal device corresponds to the AI service requested or permitted by the terminal device.
  • the base station selects a core network element (eg, AMF, SMF) corresponding to the AI service parameter according to the AI service parameter in the AS layer message.
  • a core network element eg, AMF, SMF
  • the base station forwards the NAS message of the terminal device to the selected core network element, where the NAS message carries AI service parameters used by the terminal device, such as AI service parameters requested or allowed by the terminal device.
  • FIG. 8 is an implementation flowchart of a method 800 for selecting network resources according to an embodiment of the present application, including:
  • the first network device receives AI service parameters from the terminal device;
  • the first network device selects a corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the above-mentioned first network device may include a base station.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • the above-mentioned AI domain resources include resources used for at least one AI service.
  • the above-mentioned AI domain resources include at least one of AI models, network computing power, communication resources, and data. These resources can all be pooled resources that can be shared within an AI domain.
  • the above-mentioned AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device and the application server.
  • the above-mentioned first network device selects corresponding AI domain resources for the terminal device according to the AI service parameters, including:
  • the first network device selects a corresponding core network device for the terminal device according to the AI service parameter.
  • the above method further includes:
  • the first network device broadcasts AI service parameters allowed or supported by the first network, and the AI service parameters allowed or supported by the first network correspond to the AI services allowed or supported by the first network; wherein, the first network includes terminals, base stations, core at least one of a web and an application server.
  • the first network device may be a base station device in the first network.
  • FIG. 9 is an implementation flowchart of a method 900 for selecting network resources according to an embodiment of the present application, including:
  • the second network device receives the AI service parameter
  • the second network device selects a corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the above-mentioned second network device may include AMF.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • the above-mentioned AI domain resources include resources used for at least one AI service.
  • the above-mentioned AI domain resources include at least one of AI models, network computing power, communication resources, and data.
  • the above-mentioned AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device and the application server.
  • the above-mentioned second network device selects corresponding AI domain resources for the terminal device according to the AI service parameter, including:
  • the second network device determines the AI service provided for the terminal device according to the AI service parameter and the correspondence information between the terminal device and the AI service;
  • the second network device sends the allowed AI service parameter to the terminal device, where the allowed AI service parameter corresponds to the AI service that should be provided for the terminal device.
  • the above-mentioned second network device preconfigures the corresponding relationship information; and/or, the second network device acquires the corresponding relationship information from other network devices.
  • the above-mentioned second network device selects a corresponding SMF for the terminal device according to the AI service parameter.
  • the above method further includes: the second network device sends a session establishment request to the corresponding SMF, where the session establishment request carries the AI service parameter.
  • the above method further includes that the second network device sends a subscription information acquisition request, where the subscription information acquisition request carries the AI service parameter, so as to acquire subscription information related to the AI service parameter.
  • the above method further includes that the second network device sends a policy or rule acquisition request, where the policy or rule acquisition request carries the AI service parameter to acquire the policy or rule related to the AI service parameter.
  • FIG. 10 is an implementation flowchart of a method 1000 for selecting network resources according to an embodiment of the present application, including:
  • the third network device receives the AI service parameter
  • the third network device selects a corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the above-mentioned third network device may include SMF.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • the above-mentioned AI domain resources include resources used for at least one AI service.
  • the above-mentioned AI domain resources include at least one of AI models, network computing power, communication resources, and data. These resources can all be pooled resources that can be shared within an AI domain.
  • the above-mentioned AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device and the application server.
  • the above-mentioned third network device selects a corresponding UPF for the terminal device according to the AI service parameter.
  • receiving the AI service parameter by the third network device includes: the third network device receiving a session establishment request, where the session establishment request carries the AI service parameter.
  • the above method further includes that the third network device sends a subscription information acquisition request, where the subscription information acquisition request carries the AI service parameter, so as to acquire subscription information related to the AI service parameter.
  • the above method further includes that the third network device sends a policy or rule acquisition request, where the policy or rule acquisition request carries the AI service parameter to acquire the policy or rule related to the AI service parameter.
  • FIG. 11 is an implementation flowchart of a method 1100 for sending contract information according to an embodiment of the present application, including:
  • the fourth network device receives a subscription information acquisition request, where the subscription information acquisition request carries AI service parameters;
  • S1120 The fourth network device sends subscription information related to the AI service parameter.
  • the above-mentioned fourth network device may include UDM.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • FIG. 12 is an implementation flowchart of a method 1200 for sending policies or rules according to an embodiment of the present application, including:
  • the fifth network device receives a policy or rule acquisition request, where the policy or rule acquisition request carries AI service parameters;
  • the fifth network device sends a policy or rule related to the AI service parameter.
  • the above-mentioned fifth network device may include a PCF.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • FIG. 13 is a schematic structural diagram of a terminal device 1300 according to an embodiment of the present application, including:
  • the first sending module 1310 is configured to send artificial intelligence AI service parameters to the first network device, where the AI service parameters are used to select corresponding AI domain resources for the terminal device.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • the above-mentioned AI domain resources include resources used for at least one AI service.
  • the above-mentioned AI domain resources include at least one of AI models, network computing power, communication resources, and data.
  • the above-mentioned AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device and the application server.
  • the above-mentioned first sending module 1310 is used for:
  • Receive and receive AI service parameters allowed or supported in the first network where the AI service parameters allowed or supported in the first network correspond to the AI services allowed or supported in the first network; wherein the first network includes terminals, base stations, At least one of the core network and the application server; according to the AI service allowed or supported by the first network and the AI service required by the terminal device, send AI service parameters to the first network device.
  • the above-mentioned first sending module is configured to: establish a data connection with the first network by using the AI service parameters allowed or supported in the first network.
  • FIG. 14 is a schematic structural diagram of a terminal device 1400 according to an embodiment of the present application. As shown in FIG. 14 , optionally, the above-mentioned terminal device may further include:
  • the first receiving module 1420 is configured to receive allowed AI service parameters, where the allowed AI service parameters correspond to AI domain resources provided for the terminal device.
  • the above-mentioned first sending module 1310 is used for:
  • FIG. 15 is a schematic structural diagram of a network device 1500 according to an embodiment of the present application, including:
  • the second receiving module 1510 is configured to receive AI service parameters from the terminal device
  • the first selection module 1520 is configured to select the corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the network equipment may include a base station.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • the above-mentioned AI domain resources include resources used for at least one AI service.
  • the above-mentioned AI domain resources include at least one of AI models, network computing power, communication resources, and data.
  • the above-mentioned AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device and the application server.
  • the above-mentioned first selection module 1520 is configured to select a corresponding core network device for the terminal device according to the AI service parameter.
  • FIG. 16 is a schematic structural diagram of a network device 1600 according to an embodiment of the present application. As shown in FIG. 16 , optionally, the above-mentioned network device may further include:
  • the broadcasting module 1630 is configured to broadcast AI service parameters allowed or supported by the first network to which the network device belongs, and AI service parameters allowed or supported by the first network and AI services allowed or supported by the first network.
  • FIG. 17 is a schematic structural diagram of a network device 1700 according to an embodiment of the present application, including:
  • a third receiving module 1710 configured to receive AI service parameters
  • the second selection module 1720 is configured to select the corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • the above-mentioned AI domain resources include resources used for at least one AI service.
  • the above-mentioned AI domain resources include at least one of AI models, network computing power, communication resources, and data.
  • the above-mentioned AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device and the application server.
  • the above-mentioned second selection module 1720 is used to determine the AI service provided for the terminal device according to the AI service parameters and the corresponding relationship information between the terminal device and the AI service; AI service parameters correspond to AI services provided for terminal devices.
  • the above-mentioned network device preconfigures the corresponding relationship information; and/or, the above-mentioned network device obtains the corresponding relationship information from other network devices.
  • the above-mentioned second selection module 1720 is configured to select the corresponding SMF for the terminal device according to the AI service parameter.
  • FIG. 18 is a schematic structural diagram of a network device 1800 according to an embodiment of the present application. As shown in FIG. 18 , optionally, the above-mentioned network device may further include:
  • the session establishment request module 1830 is configured to send a session establishment request to the corresponding SMF, where the session establishment request carries AI service parameters.
  • the network device may include AMF.
  • the above network device may also include:
  • the first subscription information acquisition module 1840 is configured to send a subscription information acquisition request, where the subscription information acquisition request carries AI service parameters, and is used to acquire subscription information related to the AI service parameters.
  • the above network device may also include:
  • the first policy or rule acquisition module 1850 is configured to send a policy or rule acquisition request, where the policy or rule acquisition request carries AI service parameters to acquire policies or rules related to the AI service parameters.
  • FIG. 19 is a schematic structural diagram of a network device 1900 according to an embodiment of the present application, including:
  • a fourth receiving module 1910 configured to receive AI service parameters
  • the third selection module is used to select the corresponding AI domain resource for the terminal device according to the AI service parameter.
  • the above-mentioned network device may include SMF.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • the above-mentioned AI domain resources include resources used for at least one AI service.
  • the above-mentioned AI domain resources include at least one of AI models, network computing power, communication resources, and data.
  • the above-mentioned AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device and the application server.
  • the above-mentioned third selection module 1920 selects the corresponding user plane function UPF for the terminal device according to the AI service parameter.
  • the above-mentioned fourth receiving module 1910 receives a session establishment request, where the session establishment request carries AI service parameters.
  • FIG. 20 is a schematic structural diagram of a network device 2000 according to an embodiment of the present application. As shown in FIG. 20 , optionally, the above-mentioned network device may further include:
  • the second subscription information acquisition module 2030 is configured to send a subscription information acquisition request, where the subscription information acquisition request carries AI service parameters, and is used to acquire subscription information related to the AI service parameters.
  • the above network device may further include:
  • the second policy or rule acquisition module 2040 is configured to send a policy or rule acquisition request, where the policy or rule acquisition request carries AI service parameters, and is used to acquire policies or rules related to the AI service parameters.
  • FIG. 21 is a schematic structural diagram of a network device 2100 according to an embodiment of the present application, including:
  • a fifth receiving module 2110 configured to receive a contract information acquisition request, where the contract information acquisition request carries AI service parameters;
  • the second sending module 2120 is configured to send subscription information related to AI service parameters.
  • the above-mentioned network device may include UDM.
  • the above AI service parameters include:
  • AI service parameters corresponding to the AI service requested, selected or permitted by the terminal device are included in the AI service requested, selected or permitted by the terminal device.
  • FIG. 22 is a schematic structural diagram of a network device 2200 according to an embodiment of the present application, including:
  • the sixth receiving module 2210 is used to receive a policy or rule acquisition request, where the policy or rule acquisition request carries AI service parameters;
  • the third sending module 2220 is configured to send policies or rules related to AI service parameters.
  • the above-mentioned network device may include a PCF.
  • the above AI service parameters include: AI service parameters corresponding to AI services requested, selected or permitted by the terminal device.
  • the embodiment of the present application also proposes an apparatus for dividing network resources, including:
  • the dividing module is used to divide the network resources into multiple AI domain resources, and each AI domain resource includes resources used for at least one AI service.
  • the above-mentioned AI domain resources include at least one of AI models, network computing power, communication resources, and data.
  • the above-mentioned AI domain resources are distributed in at least one of the terminal device, the access network device, the core network device and the application server.
  • the above AI domain resources are divided by at least one of services, locations, users, and third-party customization.
  • FIG. 23 is a schematic structural diagram of a communication device 2300 according to an embodiment of the present application.
  • the communication device 2300 shown in FIG. 23 includes a processor 2310, and the processor 2310 can call and run a computer program from a memory to implement the method in the embodiment of the present application.
  • the communication device 2300 may further include a memory 2320 .
  • the processor 2310 may call and run a computer program from the memory 2320 to implement the methods in the embodiments of the present application.
  • the memory 2320 may be a separate device independent of the processor 2310, or may be integrated in the processor 2310.
  • the communication device 2300 may further include a transceiver 2330, and the processor 2310 may control the transceiver 2330 to communicate with other devices, specifically, may send information or data to other devices, or receive other devices Information or data sent by a device.
  • the transceiver 2330 may include a transmitter and a receiver.
  • the transceiver 2330 may further include an antenna, and the number of the antenna may be one or more.
  • the communication device 2300 may be a terminal device of this embodiment of the present application, and the communication device 2300 may implement the corresponding processes implemented by the terminal device in each method of this embodiment of the present application, which is not repeated here for brevity.
  • the communication device 2300 may be a network device of this embodiment of the present application, and the communication device 2300 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application, which is not repeated here for brevity.
  • FIG. 24 is a schematic structural diagram of a chip 2400 according to an embodiment of the present application.
  • the chip 2400 shown in FIG. 24 includes a processor 2410, and the processor 2410 can call and run a computer program from a memory to implement the method in the embodiment of the present application.
  • the chip 2400 may further include a memory 2420 .
  • the processor 2410 may call and run a computer program from the memory 2420 to implement the methods in the embodiments of the present application.
  • the memory 2420 may be a separate device independent of the processor 2410, or may be integrated in the processor 2410.
  • the chip 2400 may further include an input interface 2430 .
  • the processor 2410 may control the input interface 2430 to communicate with other devices or chips, and specifically, may acquire information or data sent by other devices or chips.
  • the chip 2400 may further include an output interface 2440 .
  • the processor 2410 can control the output interface 2440 to communicate with other devices or chips, and specifically, can output information or data to other devices or chips.
  • the chip can be applied to the terminal device in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the terminal device in each method of the embodiment of the present application, which is not repeated here for brevity.
  • the chip can be applied to the network device in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiment of the present application, which is not repeated here for brevity.
  • the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a system-on-chip, or a system-on-a-chip, or the like.
  • the above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an off-the-shelf programmable gate array (field programmable gate array, FPGA), an application specific integrated circuit (ASIC) or Other programmable logic devices, transistor logic devices, discrete hardware components, etc.
  • DSP digital signal processor
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • the general-purpose processor mentioned above may be a microprocessor or any conventional processor or the like.
  • the memory mentioned above may be either volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM).
  • the memory in the embodiment of the present application may also be a static random access memory (static RAM, SRAM), a dynamic random access memory (dynamic RAM, DRAM), Synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous connection Dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM) and so on. That is, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.
  • the above-mentioned embodiments it may be implemented in whole or in part by software, hardware, firmware or any combination thereof.
  • software it can be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions.
  • the computer program instructions When the computer program instructions are loaded and executed on a computer, the procedures or functions according to the embodiments of the present application are generated in whole or in part.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
  • the computer instructions may be stored on or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted over a wire from a website site, computer, server or data center (eg coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (eg infrared, wireless, microwave, etc.) means to another website site, computer, server or data center.
  • the computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, or the like that includes an integration of one or more available media.
  • the available media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVD), or semiconductor media (eg, Solid State Disk (SSD)), and the like.
  • the size of the sequence numbers of the above-mentioned processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not be dealt with in the embodiments of the present application. implementation constitutes any limitation.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请实施例涉及网络资源选择方法、终端设备和网络设备,其中方法包括,终端设备向第一网络设备发送人工智能(AI)服务参数,AI服务参数用于为终端设备选择对应的AI域资源。本申请实施例可以对网络资源按照AI业务进行划分,并为终端设备分配对应的AI域资源。

Description

网络资源选择方法、终端设备和网络设备 技术领域
本申请涉及通信领域,并且更具体地,涉及网络资源选择方法、终端设备和网络设备。
背景技术
人工智能(Artifact Intelligence,AI)是未来网络发展的方向,由于人工智能的到来,未来的网络需要能够支持甚至参与到AI中。但是,目前的网络资源无法按照AI业务进行划分,移动网络不感知也不能参与到AI业务中,不能充分使用通信层和应用层各自的优势实现更好的AI服务能力。
发明内容
本申请实施例提出网络资源选择方法、终端设备和网络设备,可以对网络资源按照AI业务进行划分,从而充分利用各种网络资源的优势以更好地实现AI服务能力。
本申请实施例提出一种网络资源选择方法,包括:
终端设备向第一网络设备发送人工智能AI服务参数,AI服务参数用于为终端设备选择对应的AI域资源。
本申请实施例还提出一种网络资源选择方法,包括:
第一网络设备从终端设备接收AI服务参数;
第一网络设备根据AI服务参数为终端设备选择对应的AI域资源。
本申请实施例还提出一种网络资源选择方法,包括:
第二网络设备接收AI服务参数;
第二网络设备根据AI服务参数为终端设备选择对应的AI域资源。
本申请实施例还提出一种网络资源选择方法,包括:
第三网络设备接收AI服务参数;
第三网络设备根据AI服务参数为终端设备选择对应的AI域资源。
本申请实施例还提出一种签约信息发送方法,包括:
第四网络设备接收签约信息获取请求,签约信息获取请求中携带AI服务参数;
第四网络设备发送与AI服务参数相关的签约信息。
本申请实施例还提出一种策略或规则发送方法,包括:
第五网络设备接收策略或规则获取请求,策略或规则获取请求中携带AI服务参数;
第五网络设备发送与AI服务参数相关的策略或规则。
本申请实施例还提出一种网络资源划分方法,包括:
将网络资源划分为多个AI域资源,各个AI域资源包括用于供至少一种AI服务使用的资源。
本申请实施例还提出一种终端设备,包括:
第一发送模块,用于向第一网络设备发送人工智能AI服务参数,AI服务参数用于为终端设备选择对应的AI域资源。
本申请实施例还提出一种网络设备,包括:
第二接收模块,用于从终端设备接收AI服务参数;
第一选择模块,用于根据AI服务参数为终端设备选择对应的AI域资源。
本申请实施例还提出一种网络设备,包括:
第三接收模块,用于接收AI服务参数;
第二选择模块,用于根据AI服务参数为终端设备选择对应的AI域资源。
本申请实施例还提出一种网络设备,包括:
第四接收模块,用于接收AI服务参数;
第三选择模块,用于根据AI服务参数为终端设备选择对应的AI域资源。
本申请实施例还提出一种网络设备,包括:
第五接收模块,用于接收签约信息获取请求,签约信息获取请求中携带AI服务参数;
第二发送模块,用于发送与AI服务参数相关的签约信息。
本申请实施例还提出一种网络设备,包括:
第六接收模块,用于接收策略或规则获取请求,策略或规则获取请求中携带AI服务参数;
第三发送模块,用于发送与AI服务参数相关的策略或规则。
本申请实施例还提出一种网络资源划分装置,包括:
划分模块,用于将网络资源划分为多个AI域资源,各个AI域资源包括用于供至少一种AI服务使用的资源。
本申请实施例将网络资源按照AI业务划分为多个AI域资源,终端设备向网络设备发送AI服务参数,可以实现为终端设备选择对应的AI域资源。
附图说明
图1是本申请实施例的应用场景的示意图。
图2A是集中式大数据分析场景示意图;
图2B是完全分布式大数据分析场景示意图;
图2C是混合式大数据分析场景示意图;
图3是根据本申请实施例的一种网络资源划分方式示意图。;
图4是根据本申请实施例的一种网络资源选择方法400的实现流程图;
图5是本申请实施例1的实现流程图;
图6是本申请实施例2的实现流程图;
图7是本申请实施例3的实现流程图;
图8是根据本申请实施例的一种网络资源选择方法800的实现流程图;
图9是根据本申请实施例的一种网络资源选择方法900的实现流程图;
图10是根据本申请实施例的一种网络资源选择方法1000的实现流程图;
图11是根据本申请实施例的一种签约信息发送方法1100的实现流程图;
图12是根据本申请实施例的一种策略或规则发送方法1200的实现流程图;
图13是根据本申请实施例的终端设备1300结构示意图;
图14是根据本申请实施例的终端设备1400结构示意图;
图15是根据本申请实施例的网络设备1500结构示意图;
图16是根据本申请实施例的网络设备1600结构示意图;
图17是根据本申请实施例的网络设备1700结构示意图;
图18是根据本申请实施例的网络设备1800结构示意图;
图19是根据本申请实施例的网络设备1900结构示意图;
图20是根据本申请实施例的网络设备2000结构示意图;
图21是根据本申请实施例的网络设备2100结构示意图;
图22是根据本申请实施例的网络设备2200结构示意图;
图23是根据本申请实施例的通信设备2300示意性结构图;
图24是根据本申请实施例的芯片2400的示意性结构图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行描述。
需要说明的是,本申请实施例的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。同时描述的“第一”、“第二”描述的对象可以相同,也可以不同。
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、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、免授权频谱上的LTE(LTE-based access to unlicensed spectrum,LTE-U)系统、免授权频谱上的NR(NR-based access to unlicensed spectrum,NR-U)系统、通用移动通信系统(Universal Mobile Telecommunication System,UMTS)、无线局域网(Wireless Local Area Networks,WLAN)、无线保真(Wireless Fidelity,WiFi)、下一代通信(5th-Generation,5G)系统或其他通信系统等。
通常来说,传统的通信系统支持的连接数有限,也易于实现,然而,随着通信技术的发展,移动通信系统将不仅支持传统的通信,还将支持例如,设备到设备(Device to Device,D2D)通信,机器到机器(Machine to Machine,M2M)通信,机器类型通信(Machine Type Communication,MTC),以及车辆间(Vehicle to Vehicle,V2V)通信等,本申请实施例也可以应用于这些通信系统。
可选地,本申请实施例中的通信系统可以应用于载波聚合(Carrier Aggregation,CA)场景,也可以应用于双连接(Dual Connectivity,DC)场景,还可以应用于独立(Standalone,SA)布网场景。
本申请实施例对应用的频谱并不限定。例如,本申请实施例可以应用于授权频谱,也可以应用于免 授权频谱。
本申请实施例结合网络设备和终端设备描述了各个实施例,其中:终端设备也可以称为用户设备(User Equipment,UE)、接入终端、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、终端、无线通信设备、用户代理或用户装置等。终端设备可以是WLAN中的站点(STAION,ST),可以是蜂窝电话、无绳电话、会话启动协议(Session Initiation Protocol,SIP)电话、无线本地环路(Wireless Local Loop,WLL)站、个人数字处理(Personal Digital Assistant,PDA)设备、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、可穿戴设备以及下一代通信系统,例如,NR网络中的终端设备或者未来演进的公共陆地移动网络(Public Land Mobile Network,PLMN)网络中的终端设备等。
作为示例而非限定,在本申请实施例中,该终端设备还可以是可穿戴设备。可穿戴设备也可以称为穿戴式智能设备,是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称,如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上,或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备,更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能,例如:智能手表或智能眼镜等,以及只专注于某一类应用功能,需要和其它设备如智能手机配合使用,如各类进行体征监测的智能手环、智能首饰等。
网络设备可以是用于与移动设备通信的设备,网络设备可以是WLAN中的接入点(Access Point,AP),GSM或CDMA中的基站(Base Transceiver Station,BTS),也可以是WCDMA中的基站(NodeB,NB),还可以是LTE中的演进型基站(Evolutional Node B,eNB或eNodeB),或者中继站或接入点,或者车载设备、可穿戴设备以及NR网络中的网络设备(gNB)或者未来演进的PLMN网络中的网络设备等。
在本申请实施例中,网络设备为小区提供服务,终端设备通过该小区使用的传输资源(例如,频域资源,或者说,频谱资源)与网络设备进行通信,该小区可以是网络设备(例如基站)对应的小区,小区可以属于宏基站,也可以属于小小区(Small cell)对应的基站,这里的小小区可以包括:城市小区(Metro cell)、微小区(Micro cell)、微微小区(Pico cell)、毫微微小区(Femto cell)等,这些小小区具有覆盖范围小、发射功率低的特点,适用于提供高速率的数据传输服务。
图1示例性地示出了一个网络设备110和两个终端设备120,可选地,该无线通信系统100可以包括多个网络设备110,并且每个网络设备110的覆盖范围内可以包括其它数量的终端设备120,本申请实施例对此不做限定。本申请实施例可以应用于一个终端设备120与一个网络设备110,也可以应用于一个终端设备120与另一个终端设备120。
可选地,该无线通信系统100还可以包括移动性管理实体(Mobility Management Entity,MME)、接入与移动性管理功能(Access and Mobility Management Function,AMF)等其他网络实体,本申请实施例对此不作限定。
应理解,本文中术语“系统”和“网络”在本文中常被可互换使用。本文中术语“和/或”,仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。
应理解,在本申请的实施例中提到的“指示”可以是直接指示,也可以是间接指示,还可以是表示具有关联关系。举例说明,A指示B,可以表示A直接指示B,例如B可以通过A获取;也可以表示A间接指示B,例如A指示C,B可以通过C获取;还可以表示A和B之间具有关联关系。
在本申请实施例的描述中,术语“对应”可表示两者之间具有直接对应或间接对应的关系,也可以表示两者之间具有关联关系,也可以是指示与被指示、配置与被配置等关系。
为便于理解本申请实施例的技术方案,以下对本申请实施例的相关技术进行说明,以下相关技术作为可选方案与本申请实施例的技术方案可以进行任意结合,其均属于本申请实施例的保护范围。
AI/机器学习(ML,Machine Learning)(也可以成为大数据分析)是未来网络发展的方向,可以用于通信系统的优化,比如终端配置参数的优化、策略控制和计费(PCC,Policy Control and Charging)/服务质量(QoS,Quantity of Service)参数的优化等。为了实现该目的,通信网络(如移动通信网络)中需要引入大数据分析相关网元和功能,比如网络数据分析功能(NWDAF,Network Data Analytics Function)网元用于采集、分析和形成有价值的参数优化方法。
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/ML的方式,即网络侧的网元和终端分工进行大数据分析。
图2A是集中式大数据分析场景示意图,即所有终端将需要的数据上报后,大数据分析工作全都在网络服务器进行。图2B是完全分布式大数据分析场景示意图,即不同的终端对于采集的数据本地进行分析。图2C是混合式大数据分析场景示意图,即终端对于采集的数据在本地进行一部分的分析后,将 结果发送给网络服务器,网络服务器进行进一步的计算分析。此外,如图2B和图2C所示,完全分布式和混合式的大数据分析场景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。
举例来说,大数据分析工作可以在终端设备、边缘服务器、云端服务器三者上分摊进行,也可以只在一个或两个上面进行。因此,终端设备可能会根据需要分摊不同的AI/ML模型和计算工作量,并在要求的时间内计算完成并成功发送给网络服务器。
目前的网络资源无法按照AI业务进行划分,包括通信资源、计算资源、存储资源等。移动网络既不感知也不能参与到AI业务中,不能充分使用通信层和应用层各自的优势实现更好的AI服务能力。
本申请实施例提出一种网络资源划分方法,能够将网络资源按照AI业务进行划分。具体地,本申请实施例可以将网络资源划分为多个AI域资源,各个AI域资源包括用于供至少一种AI服务使用的资源。其中,AI服务可以是基于某个特定条件提供的业务或服务,或者是某个或某些公司提供的特定业务或服务。例如,基于不同的用户、场景、位置、时间等因素提供不同的AI技术的处理方案,每种AI技术的处理方案可以对应一种AI服务。
图3是根据本申请实施例的一种网络资源划分方式示意图。如图3所示,本申请实施例提出的AI域可以指网络中用于供特定AI业务使用的网络资源,该网络资源可以指特定的一台或多台服务器(或网元)、或者服务器中的特定资源。
如图3所示,本申请实施例可以在不同的网元上划分出相应的资源,各个网元上划分出的资源组合起来支撑一个AI域。例如图3中的“无线资源优化”AI域,在图3中,分别在UE、RAN和核心网中划分出相应的网络资源,并在终端、边缘数据中心(DC,Data Center)和本地数据中心(Local DC)等设备中划分出一部分算力资源和数据资源,这些划分出的资源共同组成图3中的“无线资源优化”AI域。
可见,本申请实施例提出的AI域具备单一网络所没有的多重资源,对于精准的AI模型分配、网络资源调度、数据共享等能够提供最优化策略。在AI域中,各节点尽其所能提供数据、AI模型管理、计算能力、通信能力等。
本申请实施例中,一个AI域中的AI域资源可以包括AI模型、网络算力、通信资源、通信资源和数据中的至少一个。如图3所示,这些资源都可以是池化的资源,可以在一个AI域中共享。其中,该通信资源可以包括网络资源,如接入网资源、核心网资源,例如基站、接入移动/管理网元(AMF,Access and Mobility Management Function)、会话管理网元(SMF,Session Management Function)、用户面功能(UPF,User Plane Function)等网络设备。
在一些实施方式中,AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。从图3中可以看出,参与AI域的网元包括终端、基站、核心网网元、应用服务器中的一个或多个,并且AI域是可以跨多个网络切片进行规划的。
在一些实施方式中,AI域可以根据业务、地点、用户和第三方定制中的至少一项划分。例如,AI域可以根据业务划分,并可以进一步根据地点、用户、第三方定制等维度进行细分。
举例来讲,当一个终端到一个特定的位置时,其需要增强现实(AR,Augmented Reality)/虚拟现实(VR,Virtual Reality)业务的支持,那么该AI域中的决策点可以为其确定最合适的AI模型,并调用对应的存储模块将AI模型发送给该终端。可选地,决策点为终端决定最适合的AI模型可以是通过该终端的特点来决定的,比如终端的位置、用户喜好、终端电量、计算能力、业务要求等。也就是说,该AI域的决策点可以根据历史数据和训练结果,结合该终端的特征为其匹配最合适的AI模型。
如图3所示,在将网络资源根据AI业务划分多个AI域的情况下,当终端设备(UE)加入不同的AI域时,其对应的网元可能不同。因此,移动网络可以根据UE请求、选择或允许的AI服务来为其选择合适的网络资源。
图4是根据本申请实施例的一种网络资源选择方法400的实现流程图,包括:
S410:终端设备向第一网络设备发送AI服务参数,该AI服务参数用于为该终端设备选择对应的AI域资源。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
在本申请实施例中,上述AI服务参数也可以称为AI域参数、AI业务参数、AI参数或其他类似的名称。AI服务参数与AI域对应,各个AI域中的AI域资源包括用于供至少一种AI服务使用的资源。可选地,上述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个,这些资源都可以是池化的资源,可以在一个AI域中共享。可选地,AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
在一些实施方式中,上述第一网络设备包括基站,基站广播基站所属的网络允许或支持的AI域或AI服务,终端设备根据基站广播的消息以及自身选择的AI服务,确定是否驻留在该基站所在的小区和 /或向该基站发起RRC连接。
相应的,在一些实施方式中,上述步骤S410包括:
终端设备接收第一网络允许或支持的AI服务参数,该第一网络允许或支持的AI服务参数对应该第一网络允许或支持的AI服务;
终端设备根据该第一网络允许或支持的AI服务以及终端设备所需的AI服务,向第一网络设备发送AI服务参数。
其中,上述第一网络可以包括终端、基站、核心网和应用服务器中的至少一个。上述第一网络设备可以为该第一网络中的基站。
在一些实施方式中,上述终端设备向第一网络设备发送AI服务参数,可以指终端设备使用第一网络中允许或支持的AI服务参数,与第一网络建立数据连接。
可选地,上述方法还可以包括:
终端设备接收允许的AI服务参数,该允许的AI服务参数对应为该终端设备提供的AI域资源。例如,该允许的AI服务参数可以由AMF发送至终端设备。具体地,AMF可以在收到AI服务参数后,根据该AI服务参数判断是否允许该终端设备进行注册,和/或允许的AI服务有哪些,并向终端设备反馈允许的AI服务参数。
终端设备可以在发起AS层RRC连接建立和/或NAS层注册请求的情况下,携带上述AI服务参数。
例如,上述步骤S410中的终端设备向第一网络设备发送AI服务参数,包括:
终端设备向第一网络设备发送注册请求消息,该注册请求消息中携带AI服务参数,如终端设备请求的AI服务参数;或者,
终端设备向第一网络设备发送会话建立/修改请求消息,该会话建立/修改请求消息中携带AI服务参数,如终端设备允许的AI服务参数,用于建立PDU会话;或者,
终端设备向第一网络设备发送AS层消息,该AS层消息中携带AI服务参数,如终端设备请求或允许的AI服务参数。
上述AI服务参数用于为终端设备选择对应的AI域资源。例如,当基站接收到AI服务参数时,可以根据该参数为终端设备选择对应的核心网网元;当AMF接收到AI服务参数时,可以根据该参数为终端设备选择适合的SMF;当SMF接收到AI服务参数时,可以根据该参数为终端设备选择适合的UPF或移动网关。上述基于AI服务参数对网元进行选择的过程可以发生在注册管理过程和/或会话管理过程中。
以下参照附图,分别介绍在注册管理过程和会话管理过程中根据AI服务参数进行网络资源选择的实施方式示例。
实施例1:
本实施例涉及在终端设备注册过程中,利用AI服务参数进行网络资源分配的实现方式。其中,AI服务参数可以指终端设备请求、选择或允许的一个或多个AI服务(比如某AR业务、某场景下的VR业务、某公司的自动驾驶业务)对应的AI服务参数。
图5是本申请实施例1的实现流程图,如图5所示,本实施例包括以下步骤:
S501:终端设备通过接入网向AMF发送注册请求,该注册请求中携带终端设备使用的AI服务参数,例如终端设备请求的AI服务参数。
S502:AMF根据终端设备请求的AI服务参数判断是否允许该终端设备进行注册,和/或允许的AI服务(或者为终端设备提供的AI服务)有哪些。具体地,AMF可以根据预配置的终端设备与AI服务的对应关系信息进行确定;或者,AMF可以与其他网元(如图5中的网元A)交互,根据其他网元中保存的终端设备与AI服务的对应关系信息进行确定。其中,该其他网元可以是通信系统中已有的网元,也可以是新增网元。
S503:AMF向统一数据管理(UDM,Unified Data Manager)平台发送签约信息获取请求,该签约信息获取请求中可以携带终端设备请求的AI服务参数,或者携带允许的AI服务参数,该允许的AI服务参数对应步骤S502中AMF确定出的允许的AI服务(或者为终端设备提供的AI服务)。UDM生成对应该AI服务参数的签约信息,将该签约信息返回至AMF。
S504:AMF向策略控制功能(PCF,Policy Control Function)发送策略或规则获取请求,该策略或规则获取请求中可以携带终端设备请求的AI服务参数,或者携带允许的AI服务参数,该允许的AI服务参数对应步骤S502中AMF确定出的允许的AI服务(或者为终端设备提供的AI服务)。PCF生成对应该AI服务参数的策略或规则,将该策略或规则返回至AMF。
S505:AMF向终端设备发送注册回复消息,该注册回复消息中可以携带步骤S502中确定出的允许的AI服务(或者为终端设备提供的AI服务)所对应的AI服务参数。
需要说明的是,上述步骤S501中终端设备请求的AI服务参数与步骤S505中反馈的允许的AI服务参数可以是包含与被包含的关系,也可以没有包含关系。例如,允许的AI服务参数是终端设备请求的AI服务参数中的一个或多个,或者,允许的AI服务参数不属于终端设备请求的AI服务参数。
实施例2:
本实施例涉及在会话管理过程中,利用AI服务参数进行网络资源分配的实现方式。由于应用服务器也可能会参与到AI域中,因此移动网关的选择(如SMF和/或UPF)是非常重要的,需要选择到一个最靠近该AI域应用服务器的网关,这也是本实施例将要重点介绍的内容。
图6是本申请实施例2的实现流程图,如图6所示,本实施例包括以下步骤:
S601:终端设备通过接入网向AMF发送注册请求,该注册请求中携带终端设备使用的AI服务参数,例如终端设备允许的AI服务参数。
S602:AMF根据终端设备使用的AI服务参数选择对应的SMF,并向该SMF发起会话建立请求。在向SMF发送的会话建立请求中,可以携带该终端设备使用的AI服务参数。
S603:SMF向UDM发送签约信息获取请求,该签约信息获取请求中可以携带终端设备使用的AI服务参数。UDM生成对应该AI服务参数的签约信息,将该签约信息返回至SMF。
S604:SMF向PCF发送策略或规则获取请求,该策略或规则获取请求中可以携带终端设备使用的AI服务参数。PCF生成对应该终端设备使用的AI服务参数的策略或规则,将该策略或规则返回至SMF。
S605:SMF根据终端设备使用的AI服务参数选择对应的UPF,并向该UPF发起会话建立请求,与该UPF建立会话。
S606:SMF向AMF返回会话建立回复消息,AMF向终端设备返回会话建立回复消息。之后,终端设备与应用服务器建立用户面会话,用于与应用服务器传输数据。
实施例3:
本实施例涉及终端设备在AS层携带AI服务参数的示例。在本实施例中,基站在广播消息中可以携带支持或允许的AI服务参数,终端设备根据基站发送的AI服务参数来选择自身使用的AI服务参数。
图7是本申请实施例3的实现流程图,如图7所示,本实施例包括以下步骤:
S701:基站发送广播消息,该广播消息中包含基站所属的网络支持或允许的AI服务参数,该AI服务参数对应基站所属的网络允许或支持的AI服务。
S702:终端设备根据基站的广播以及自身选择的AI服务,确定是否驻留在该基站所在的小区,和/或向该基站发起连接建立请求(如RRC连接建立请求)。
S703:如果选择向该基站发起连接建立请求,终端设备在向基站发送的AS层消息(如RRC建立完成消息)中,携带终端设备使用的AI服务参数,例如终端设备请求或允许的AI服务参数。该终端设备请求或允许的AI服务参数对应终端设备请求或允许的AI服务。
S704:基站根据AS层消息中的AI服务参数,选择与该AI服务参数对应的核心网网元(如AMF、SMF)。
S705:基站向选择的核心网网元转发终端设备的NAS消息,该NAS消息中携带终端设备使用的AI服务参数,例如终端设备请求或允许的AI服务参数。
本申请实施例还提出一种网络资源选择方法,图8是根据本申请实施例的一种网络资源选择方法800的实现流程图,包括:
S810:第一网络设备从终端设备接收AI服务参数;
S820:第一网络设备根据该AI服务参数为该终端设备选择对应的AI域资源。
其中,上述第一网络设备可以包括基站。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
可选地,上述AI域资源包括用于供至少一种AI服务使用的资源。
可选地,上述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。这些资源都可以是池化的资源,可以在一个AI域中共享。
可选地,上述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
可选地,上述第一网络设备根据AI服务参数为终端设备选择对应的AI域资源,包括:
第一网络设备根据AI服务参数为终端设备选择对应的核心网设备。
可选地,上述方法还包括:
第一网络设备广播第一网络允许或支持的AI服务参数,该第一网络允许或支持的AI服务参数对应第一网络允许或支持的AI服务;其中,该第一网络包括终端、基站、核心网和应用服务器中的至少一个。
第一网络设备可以为该第一网络中的基站设备。
本申请实施例还提出一种网络资源选择方法,图9是根据本申请实施例的一种网络资源选择方法900的实现流程图,包括:
S910:第二网络设备接收AI服务参数;
S920:第二网络设备根据该AI服务参数为该终端设备选择对应的AI域资源。
其中,上述第二网络设备可以包括AMF。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
可选地,上述AI域资源包括用于供至少一种AI服务使用的资源。
可选地,上述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
可选地,上述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
可选地,上述第二网络设备根据该AI服务参数为该终端设备选择对应的AI域资源,包括:
第二网络设备根据该AI服务参数、以及终端设备与AI服务的对应关系信息,确定为该终端设备提供的AI服务;
第二网络设备向该终端设备发送允许的AI服务参数,该允许的AI服务参数对应该为终端设备提供的AI服务。
可选地,上述第二网络设备预配置该对应关系信息;和/或,第二网络设备从其他网络设备获取该对应关系信息。
可选地,上述第二网络设备根据该AI服务参数为该终端设备选择对应的SMF。
可选地,上述方法还包括:第二网络设备向该对应的SMF发送会话建立请求,该会话建立请求中携带该AI服务参数。
可选地,上述方法还包括,第二网络设备发送签约信息获取请求,该签约信息获取请求中携带该AI服务参数,用以获取与该AI服务参数相关的签约信息。
可选地,上述方法还包括,第二网络设备发送策略或规则获取请求,该策略或规则获取请求中携带该AI服务参数,用以获取与该AI服务参数相关的策略或规则。
本申请实施例还提出一种网络资源选择方法,图10是根据本申请实施例的一种网络资源选择方法1000的实现流程图,包括:
S1010:第三网络设备接收AI服务参数;
S1020:第三网络设备根据该AI服务参数为该终端设备选择对应的AI域资源。
其中,上述第三网络设备可以包括SMF。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
可选地,上述AI域资源包括用于供至少一种AI服务使用的资源。
可选地,上述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。这些资源都可以是池化的资源,可以在一个AI域中共享。
可选地,上述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
可选地,上述第三网络设备根据该AI服务参数为该终端设备选择对应的UPF。
可选地,上述第三网络设备接收AI服务参数,包括:第三网络设备接收会话建立请求,该会话建立请求中携带该AI服务参数。
可选地,上述方法还包括,第三网络设备发送签约信息获取请求,该签约信息获取请求中携带该AI服务参数,用以获取与该AI服务参数相关的签约信息。
可选地,上述方法还包括,第三网络设备发送策略或规则获取请求,该策略或规则获取请求中携带该AI服务参数,用以获取与该AI服务参数相关的策略或规则。
本申请实施例还提出一种签约信息发送方法,图11是根据本申请实施例的一种签约信息发送方法1100的实现流程图,包括:
S1110:第四网络设备接收签约信息获取请求,该签约信息获取请求中携带AI服务参数;
S1120:第四网络设备发送与该AI服务参数相关的签约信息。
其中,上述第四网络设备可以包括UDM。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
本申请实施例还提出一种策略或规则发送方法,图12是根据本申请实施例的一种策略或规则发送方法1200的实现流程图,包括:
S1210:第五网络设备接收策略或规则获取请求,该策略或规则获取请求中携带AI服务参数;
S1220:第五网络设备发送与该AI服务参数相关的策略或规则。
其中,上述第五网络设备可以包括PCF。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
本申请实施例还提出一种终端设备,图13是根据本申请实施例的终端设备1300结构示意图,包括:
第一发送模块1310,用于向第一网络设备发送人工智能AI服务参数,AI服务参数用于为终端设备选择对应的AI域资源。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
可选地,上述AI域资源包括用于供至少一种AI服务使用的资源。
可选地,上述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
可选地,上述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
可选地,上述第一发送模块1310用于:
接收接收第一网络中允许或支持的AI服务参数,该第一网络中允许或支持的AI服务参数对应该第一网络中允许或支持的AI服务;其中,该第一网络包括终端、基站、核心网和应用服务器中的至少一个;根据该第一网络允许或支持的AI服务及终端设备所需的AI服务,向第一网络设备发送AI服务参数。
可选地,上述第一发送模块用于:使用该第一网络中允许或支持的AI服务参数,与第一网络建立数据连接。
图14是根据本申请实施例的终端设备1400结构示意图,如图14所示,可选地,上述终端设备还可以包括:
第一接收模块1420,用于接收允许的AI服务参数,允许的AI服务参数对应为终端设备提供的AI域资源。
可选地,上述第一发送模块1310用于:
向第一网络设备发送注册请求消息,注册请求消息中携带AI服务参数;或者,
向第一网络设备发送会话建立/修改请求消息,会话建立/修改请求消息中携带AI服务参数;或者,
向第一网络设备发送AS层消息,AS层消息中携带AI服务参数。
应理解,根据本申请实施例的终端设备中的模块的上述及其他操作和/或功能分别为了实现图4的方法400中的终端设备的相应流程,为了简洁,在此不再赘述。
本申请实施例还提出一种网络设备,图15是根据本申请实施例的网络设备1500结构示意图,包括:
第二接收模块1510,用于从终端设备接收AI服务参数;
第一选择模块1520,用于根据AI服务参数为终端设备选择对应的AI域资源。
可选地,该网络设备可以包括基站。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
可选地,上述AI域资源包括用于供至少一种AI服务使用的资源。
可选地,上述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
可选地,上述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
可选地,上述第一选择模块1520用于,根据AI服务参数为终端设备选择对应的核心网设备。
图16是根据本申请实施例的网络设备1600结构示意图,如图16所示,可选地,上述网络设备还可以包括:
广播模块1630,用于广播网络设备所属的第一网络允许或支持的AI服务参数,网该第一网络允许或支持的AI服务参数该第一网络允许或支持的AI服务。
应理解,根据本申请实施例的网络设备中的模块的上述及其他操作和/或功能分别为了实现图8的方法800中的网络设备的相应流程,为了简洁,在此不再赘述。
本申请实施例还提出一种网络设备,图17是根据本申请实施例的网络设备1700结构示意图,包括:
第三接收模块1710,用于接收AI服务参数;
第二选择模块1720,用于根据AI服务参数为终端设备选择对应的AI域资源。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
可选地,上述AI域资源包括用于供至少一种AI服务使用的资源。
可选地,上述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
可选地,上述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
可选地,上述第二选择模块1720用于,根据AI服务参数、以及终端设备与AI服务的对应关系信息,确定为终端设备提供的AI服务;向终端设备发送允许的AI服务参数,允许的AI服务参数对应为终端设备提供的AI服务。
可选地,上述网络设备预配置对应关系信息;和/或,上述网络设备从其他网络设备获取对应关系信息。
可选地,上述第二选择模块1720,用于根据AI服务参数为终端设备选择对应的SMF。
图18是根据本申请实施例的网络设备1800结构示意图,如图18所示,可选地,上述网络设备还可以包括:
会话建立请求模块1830,用于向该对应的SMF发送会话建立请求,会话建立请求中携带AI服务参数。
可选地,该网络设备可以包括AMF。
可选地,上述网络设备还可以包括:
第一签约信息获取模块1840,用于发送签约信息获取请求,签约信息获取请求中携带AI服务参数,用以获取与AI服务参数相关的签约信息。
可选地,上述网络设备还可以包括:
第一策略或规则获取模块1850,用于发送策略或规则获取请求,策略或规则获取请求中携带AI服务参数,用以获取与AI服务参数相关的策略或规则。
应理解,根据本申请实施例的网络设备中的模块的上述及其他操作和/或功能分别为了实现图9的方法900中的网络设备的相应流程,为了简洁,在此不再赘述。
本申请实施例还提出一种网络设备,图19是根据本申请实施例的网络设备1900结构示意图,包括:
第四接收模块1910,用于接收AI服务参数;
第三选择模块,用于根据AI服务参数为终端设备选择对应的AI域资源。
上述网络设备可以包括SMF。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
可选地,上述AI域资源包括用于供至少一种AI服务使用的资源。
可选地,上述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
可选地,上述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
可选地,上述第三选择模块1920根据AI服务参数为终端设备选择对应的用户面功能UPF。
可选地,上述第四接收模块1910接收会话建立请求,会话建立请求中携带AI服务参数。
图20是根据本申请实施例的网络设备2000结构示意图,如图20所示,可选地,上述网络设备还可以包括:
第二签约信息获取模块2030,用于发送签约信息获取请求,签约信息获取请求中携带AI服务参数,用以获取与AI服务参数相关的签约信息。
可选地,上述网络设备还可以包括:
第二策略或规则获取模块2040,用于发送策略或规则获取请求,策略或规则获取请求中携带AI服务参数,用以获取与AI服务参数相关的策略或规则。
应理解,根据本申请实施例的网络设备中的模块的上述及其他操作和/或功能分别为了实现图10的方法1000中的网络设备的相应流程,为了简洁,在此不再赘述。
本申请实施例还提出一种网络设备,图21是根据本申请实施例的网络设备2100结构示意图,包括:
第五接收模块2110,用于接收签约信息获取请求,签约信息获取请求中携带AI服务参数;
第二发送模块2120,用于发送与AI服务参数相关的签约信息。
上述网络设备可以包括UDM。
可选地,上述AI服务参数包括:
终端设备请求、选择或允许的AI服务对应的AI服务参数。
应理解,根据本申请实施例的网络设备中的模块的上述及其他操作和/或功能分别为了实现图11的方法1100中的网络设备的相应流程,为了简洁,在此不再赘述。
本申请实施例还提出一种网络设备,图22是根据本申请实施例的网络设备2200结构示意图,包括:
第六接收模块2210,用于接收策略或规则获取请求,策略或规则获取请求中携带AI服务参数;
第三发送模块2220,用于发送与AI服务参数相关的策略或规则。
上述网络设备可以包括PCF。
可选地,上述AI服务参数包括:终端设备请求、选择或允许的AI服务对应的AI服务参数。
应理解,根据本申请实施例的网络设备中的模块的上述及其他操作和/或功能分别为了实现图12的方法1200中的网络设备的相应流程,为了简洁,在此不再赘述。
本申请实施例还提出一种网络资源划分装置,包括:
划分模块,用于将网络资源划分为多个AI域资源,各个AI域资源包括用于供至少一种AI服务使用的资源。
可选地,上述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
可选地,上述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
可选地,上述AI域资源通过业务、地点、用户和第三方定制中的至少一项划分。
图23是根据本申请实施例的通信设备2300示意性结构图。图23所示的通信设备2300包括处理器2310,处理器2310可以从存储器中调用并运行计算机程序,以实现本申请实施例中的方法。
可选地,如图23所示,通信设备2300还可以包括存储器2320。其中,处理器2310可以从存储器2320中调用并运行计算机程序,以实现本申请实施例中的方法。
其中,存储器2320可以是独立于处理器2310的一个单独的器件,也可以集成在处理器2310中。
可选地,如图23所示,通信设备2300还可以包括收发器2330,处理器2310可以控制该收发器2330与其他设备进行通信,具体地,可以向其他设备发送信息或数据,或接收其他设备发送的信息或数据。
其中,收发器2330可以包括发射机和接收机。收发器2330还可以进一步包括天线,天线的数量可以为一个或多个。
可选地,该通信设备2300可为本申请实施例的终端设备,并且该通信设备2300可以实现本申请实施例的各个方法中由终端设备实现的相应流程,为了简洁,在此不再赘述。
可选地,该通信设备2300可为本申请实施例的网络设备,并且该通信设备2300可以实现本申请实施例的各个方法中由网络设备实现的相应流程,为了简洁,在此不再赘述。
图24是根据本申请实施例的芯片2400的示意性结构图。图24所示的芯片2400包括处理器2410,处理器2410可以从存储器中调用并运行计算机程序,以实现本申请实施例中的方法。
可选地,如图24所示,芯片2400还可以包括存储器2420。其中,处理器2410可以从存储器2420中调用并运行计算机程序,以实现本申请实施例中的方法。
其中,存储器2420可以是独立于处理器2410的一个单独的器件,也可以集成在处理器2410中。
可选地,该芯片2400还可以包括输入接口2430。其中,处理器2410可以控制该输入接口2430与其他设备或芯片进行通信,具体地,可以获取其他设备或芯片发送的信息或数据。
可选地,该芯片2400还可以包括输出接口2440。其中,处理器2410可以控制该输出接口2440与其他设备或芯片进行通信,具体地,可以向其他设备或芯片输出信息或数据。
可选地,该芯片可应用于本申请实施例中的终端设备,并且该芯片可以实现本申请实施例的各个方法中由终端设备实现的相应流程,为了简洁,在此不再赘述。
可选地,该芯片可应用于本申请实施例中的网络设备,并且该芯片可以实现本申请实施例的各个方法中由网络设备实现的相应流程,为了简洁,在此不再赘述。
应理解,本申请实施例提到的芯片还可以称为系统级芯片,系统芯片,芯片系统或片上系统芯片等。
上述提及的处理器可以是通用处理器、数字信号处理器(digital signal processor,DSP)、现成可编程门阵列(field programmable gate array,FPGA)、专用集成电路(application specific integrated circuit,ASIC)或者其他可编程逻辑器件、晶体管逻辑器件、分立硬件组件等。其中,上述提到的通用处理器可以是微处理器或者也可以是任何常规的处理器等。
上述提及的存储器可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(read-only memory,ROM)、可编程只读存储器(programmable ROM,PROM)、可擦除可编程只读存储器(erasable PROM,EPROM)、电可擦除可编程只读存储器(electrically EPROM,EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory,RAM)。
应理解,上述存储器为示例性但不是限制性说明,例如,本申请实施例中的存储器还可以是静态随机存取存储器(static RAM,SRAM)、动态随机存取存储器(dynamic RAM,DRAM)、同步动态随机存取存储器(synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(synch link DRAM,SLDRAM)以及直接内存总线随机存取存储器(Direct Rambus RAM,DR RAM)等等。也就是说,本申请实施例中的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。该计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行该计算机程序指令时,全部或部分地产生按照本申请实施例的流程或功能。该计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。该计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,该计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(Digital Subscriber Line,DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。该计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一 个或多个可用介质集成的服务器、数据中心等数据存储设备。该可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质(例如固态硬盘(Solid State Disk,SSD))等。
应理解,在本申请的各种实施例中,上述各过程的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请实施例的实施过程构成任何限定。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
以上所述仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以该权利要求的保护范围为准。

Claims (103)

  1. 一种网络资源选择方法,包括:
    终端设备向第一网络设备发送人工智能AI服务参数,所述AI服务参数用于为所述终端设备选择对应的AI域资源。
  2. 根据权利要求1所述的方法,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  3. 根据权利要求1或2所述的方法,其中,所述AI域资源包括用于供至少一种AI服务使用的资源。
  4. 根据权利要求1至3任一所述的方法,其中,所述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
  5. 根据权利要求1至4任一所述的方法,其中,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  6. 根据权利要求1至5任一所述的方法,所述终端设备向第一网络设备发送AI服务参数,包括:
    终端设备接收第一网络中允许或支持的AI服务参数,所述第一网络中允许或支持的AI服务参数对应所述第一网络中允许或支持的AI服务;其中,所述第一网络包括终端、基站、核心网和应用服务器中的至少一个;
    所述终端设备根据所述第一网络允许或支持的AI服务及所述终端设备所需的AI服务,向所述第一网络设备发送AI服务参数。
  7. 根据权利要求6所述的方法,其中,所述向所述第一网络设备发送AI服务参数包括:
    终端设备使用所述第一网络中允许或支持的AI服务参数,与所述第一网络建立数据连接。
  8. 根据权利要求1至7任一所述的方法,还包括:
    接收允许的AI服务参数,所述允许的AI服务参数对应为所述终端设备提供的AI服务。
  9. 根据权利要求1至8任一所述的方法,其中,所述终端设备向第一网络设备发送AI服务参数,包括:
    终端设备向第一网络设备发送注册请求消息,所述注册请求消息中携带AI服务参数;或者,
    终端设备向第一网络设备发送会话建立/修改请求消息,所述会话建立/修改请求消息中携带AI服务参数;或者,
    终端设备向第一网络设备发送AS层消息,所述AS层消息中携带AI服务参数。
  10. 一种网络资源选择方法,包括:
    第一网络设备从终端设备接收AI服务参数;
    所述第一网络设备根据所述AI服务参数为所述终端设备选择对应的AI域资源。
  11. 根据权利要求10所述的方法,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  12. 根据权利要求10或11所述的方法,所述AI域资源包括用于供至少一种AI服务使用的资源。
  13. 根据权利要求10至12任一所述的方法,所述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
  14. 根据权利要求10至13任一所述的方法,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  15. 根据权利要求10至14任一所述的方法,所述第一网络设备根据所述AI服务参数为所述终端设备选择对应的AI域资源,包括:
    所述第一网络设备根据所述AI服务参数为所述终端设备选择对应的核心网设备。
  16. 根据权利要求10至15任一所述的方法,还包括:
    所述第一网络设备广播第一网络允许或支持的AI服务参数,所述第一网络允许或支持的AI服务参数对应所述第一网络允许或支持的AI服务;其中,所述第一网络包括终端、基站、核心网和应用服务器中的至少一个。
  17. 一种网络资源选择方法,包括:
    第二网络设备接收AI服务参数;
    所述第二网络设备根据所述AI服务参数为所述终端设备选择对应的AI域资源。
  18. 根据权利要求17所述的方法,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  19. 根据权利要求17或18所述的方法,所述AI域资源包括用于供至少一种AI服务使用的资源。
  20. 根据权利要求17至19任一所述的方法,所述AI域资源包括AI模型、网络算力、通信资源和 数据中的至少一个。
  21. 根据权利要求17至20任一所述的方法,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  22. 根据权利要求17至21任一所述的方法,其中,所述第二网络设备根据所述AI服务参数为所述终端设备选择对应的AI域资源,包括:
    第二网络设备根据所述AI服务参数、以及终端设备与AI服务的对应关系信息,确定为所述终端设备提供的AI服务;
    第二网络设备向所述终端设备发送允许的AI服务参数,所述允许的AI服务参数对应所述为所述终端设备提供的AI服务。
  23. 根据权利要求22所述的方法,其中,
    所述第二网络设备预配置所述对应关系信息;和/或,
    所述第二网络设备从其他网络设备获取所述对应关系信息。
  24. 根据权利要求17至23任一所述的方法,其中,所述第二网络设备根据所述AI服务参数为所述终端设备选择对应的会话管理功能SMF。
  25. 根据权利要求24所述的方法,还包括:
    所述第二网络设备向所述对应的SMF发送会话建立请求,所述会话建立请求中携带所述AI服务参数。
  26. 根据权利要求17至25任一所述的方法,还包括,所述第二网络设备发送签约信息获取请求,所述签约信息获取请求中携带所述AI服务参数,用以获取与所述AI服务参数相关的签约信息。
  27. 根据权利要求17至25任一所述的方法,还包括,所述第二网络设备发送策略或规则获取请求,所述策略或规则获取请求中携带所述AI服务参数,用以获取与所述AI服务参数相关的策略或规则。
  28. 一种网络资源选择方法,包括:
    第三网络设备接收AI服务参数;
    所述第三网络设备根据所述AI服务参数为所述终端设备选择对应的AI域资源。
  29. 根据权利要求28所述的方法,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  30. 根据权利要求28或29所述的方法,所述AI域资源包括用于供至少一种AI服务使用的资源。
  31. 根据权利要求28至30任一所述的方法,所述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
  32. 根据权利要求28至31任一所述的方法,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  33. 根据权利要求28至32任一所述的方法,其中,所述第三网络设备根据所述AI服务参数为所述终端设备选择对应的用户面功能UPF。
  34. 根据权利要求28至33任一所述的方法,其中,第三网络设备接收AI服务参数,包括:
    所述第三网络设备接收会话建立请求,所述会话建立请求中携带所述AI服务参数。
  35. 根据权利要求28至34任一所述的方法,还包括,所述第三网络设备发送签约信息获取请求,所述签约信息获取请求中携带AI服务参数,用以获取与所述AI服务参数相关的签约信息。
  36. 根据权利要求28至34任一所述的方法,还包括,所述第三网络设备发送策略或规则获取请求,所述策略或规则获取请求中携带所述AI服务参数,用以获取与所述AI服务参数相关的策略或规则。
  37. 一种签约信息发送方法,包括:
    第四网络设备接收签约信息获取请求,所述签约信息获取请求中携带AI服务参数;
    所述第四网络设备发送与所述AI服务参数相关的签约信息。
  38. 根据权利要求37所述的方法,其中,所述AI服务参数包括:
    终端设备请求、选择或允许的AI服务对应的AI服务参数。
  39. 一种策略或规则发送方法,包括:
    第五网络设备接收策略或规则获取请求,所述策略或规则获取请求中携带AI服务参数;
    所述第五网络设备发送与所述AI服务参数相关的策略或规则。
  40. 根据权利要求39所述的方法,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  41. 一种网络资源划分方法,包括:
    将网络资源划分为多个AI域资源,各个所述AI域资源包括用于供至少一种AI服务使用的资源。
  42. 根据权利要求41所述的方法,所述AI域资源包括AI模型、网络算力、通信资源和数据中的至 少一个。
  43. 根据权利要求41或42所述的方法,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  44. 根据权利要求41至43任一所述的方法,所述AI域资源通过业务、地点、用户和第三方定制中的至少一项划分。
  45. 一种终端设备,包括:
    第一发送模块,用于向第一网络设备发送人工智能AI服务参数,所述AI服务参数用于为所述终端设备选择对应的AI域资源。
  46. 根据权利要求45所述的终端设备,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  47. 根据权利要求45或46所述的终端设备,其中,所述AI域资源包括用于供至少一种AI服务使用的资源。
  48. 根据权利要求45至47任一所述的终端设备,其中,所述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
  49. 根据权利要求45至48任一所述的终端设备,其中,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  50. 根据权利要求45至49任一所述的终端设备,所述第一发送模块用于:
    接收第一网络中允许或支持的AI服务参数,所述第一网络中允许或支持的AI服务参数对应所述第一网络中允许或支持的AI服务;其中,所述第一网络包括终端、基站、核心网和应用服务器中的至少一个;
    根据所述第一网络允许或支持的AI服务及所述终端设备所需的AI服务,向所述第一网络设备发送AI服务参数。
  51. 根据权利要求50所述的终端设备,所述第一发送模块用于:使用所述第一网络中允许或支持的AI服务参数,与所述第一网络建立数据连接。
  52. 根据权利要求45至51任一所述的终端设备,还包括:
    第一接收模块,用于接收允许的AI服务参数,所述允许的AI服务参数对应为所述终端设备提供的AI域资源。
  53. 根据权利要求44至52任一所述的终端设备,其中,所述第一发送模块用于:
    向第一网络设备发送注册请求消息,所述注册请求消息中携带AI服务参数;或者,
    向第一网络设备发送会话建立/修改请求消息,所述会话建立/修改请求消息中携带AI服务参数;或者,
    向第一网络设备发送AS层消息,所述AS层消息中携带AI服务参数。
  54. 一种网络设备,包括:
    第二接收模块,用于从终端设备接收AI服务参数;
    第一选择模块,用于根据所述AI服务参数为所述终端设备选择对应的AI域资源。
  55. 根据权利要求54所述的网络设备,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  56. 根据权利要求54或55所述的网络设备,所述AI域资源包括用于供至少一种AI服务使用的资源。
  57. 根据权利要求54至56任一所述的网络设备,所述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
  58. 根据权利要求54至57任一所述的网络设备,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  59. 根据权利要求54至58任一所述的网络设备,所述第一选择模块用于,根据所述AI服务参数为所述终端设备选择对应的核心网设备。
  60. 根据权利要求54至59任一所述的网络设备,还包括:
    广播模块,用于广播所述网络设备所属的第一网络允许或支持的AI服务参数,所述第一网络允许或支持的AI服务参数对应所述第一网络允许或支持的AI服务。
  61. 一种网络设备,包括:
    第三接收模块,用于接收AI服务参数;
    第二选择模块,用于根据所述AI服务参数为所述终端设备选择对应的AI域资源。
  62. 根据权利要求61所述的网络设备,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  63. 根据权利要求61或62所述的网络设备,所述AI域资源包括用于供至少一种AI服务使用的资源。
  64. 根据权利要求61至63任一所述的网络设备,所述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
  65. 根据权利要求61至64任一所述的网络设备,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  66. 根据权利要求61至65任一所述的网络设备,其中,所述第二选择模块用于,根据所述AI服务参数、以及终端设备与AI服务的对应关系信息,确定为所述终端设备提供的AI服务;向所述终端设备发送允许的AI服务参数,所述允许的AI服务参数对应所述为所述终端设备提供的AI服务。
  67. 根据权利要求66所述的网络设备,其中,
    所述网络设备预配置所述对应关系信息;和/或,
    所述网络设备从其他网络设备获取所述对应关系信息。
  68. 根据权利要求61至67任一所述的网络设备,其中,所述第二选择模块,用于根据所述AI服务参数为所述终端设备选择对应的会话管理功能SMF。
  69. 根据权利要求68所述的网络设备,还包括:
    会话建立请求模块,用于向所述对应的SMF发送会话建立请求,所述会话建立请求中携带所述AI服务参数。
  70. 根据权利要求61至69任一所述的网络设备,还包括,第一签约信息获取模块,用于发送签约信息获取请求,所述签约信息获取请求中携带所述AI服务参数,用以获取与所述AI服务参数相关的签约信息。
  71. 根据权利要求61至69任一所述的网络设备,还包括,第一策略或规则获取模块,用于发送策略或规则获取请求,所述策略或规则获取请求中携带所述AI服务参数,用以获取与所述AI服务参数相关的策略或规则。
  72. 一种网络设备,包括:
    第四接收模块,用于接收AI服务参数;
    第三选择模块,用于根据所述AI服务参数为所述终端设备选择对应的AI域资源。
  73. 根据权利要求72所述的网络设备,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  74. 根据权利要求72或73所述的网络设备,所述AI域资源包括用于供至少一种AI服务使用的资源。
  75. 根据权利要求72至74任一所述的网络设备,所述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
  76. 根据权利要求72至75任一所述的网络设备,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  77. 根据权利要求72至76任一所述的网络设备,其中,所述第三选择模块根据所述AI服务参数为所述终端设备选择对应的用户面功能UPF。
  78. 根据权利要求72至77任一所述的网络设备,其中,所述第四接收模块接收会话建立请求,所述会话建立请求中携带所述AI服务参数。
  79. 根据权利要求72至78任一所述的网络设备,还包括,第二签约信息获取模块,用于发送签约信息获取请求,所述签约信息获取请求中携带所述AI服务参数,用以获取与所述AI服务参数相关的签约信息。
  80. 根据权利要求72至78任一所述的网络设备,还包括,第二策略或规则获取模块,用于发送策略或规则获取请求,所述策略或规则获取请求中携带所述AI服务参数,用以获取与所述AI服务参数相关的策略或规则。
  81. 一种网络设备,包括:
    第五接收模块,用于接收签约信息获取请求,所述签约信息获取请求中携带AI服务参数;
    第二发送模块,用于发送与所述AI服务参数相关的签约信息。
  82. 根据权利要求81所述的网络设备,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  83. 一种网络设备,包括:
    第六接收模块,用于接收策略或规则获取请求,所述策略或规则获取请求中携带AI服务参数;
    第三发送模块,用于发送与所述AI服务参数相关的策略或规则。
  84. 根据权利要求83所述的网络设备,其中,所述AI服务参数包括:
    所述终端设备请求、选择或允许的AI服务对应的AI服务参数。
  85. 一种网络资源划分装置,包括:
    划分模块,用于将网络资源划分为多个AI域资源,各个所述AI域资源包括用于供至少一种AI服务使用的资源。
  86. 根据权利要求85所述的装置,所述AI域资源包括AI模型、网络算力、通信资源和数据中的至少一个。
  87. 根据权利要求85或86所述的装置,所述AI域资源分布在终端设备、接入网设备、核心网设备和应用服务器中的至少一个。
  88. 根据权利要求85至87任一所述的装置,所述AI域资源通过业务、地点、用户和第三方定制中的至少一项划分。
  89. 一种终端设备,包括:处理器和存储器,该存储器用于存储计算机程序,所述处理器用于调用并运行所述存储器中存储的计算机程序,执行如权利要求1至9中任一项所述的方法。
  90. 一种网络设备,包括:处理器和存储器,该存储器用于存储计算机程序,所述处理器用于调用并运行所述存储器中存储的计算机程序,执行如权利要求10至40中任一项所述的方法。
  91. 一种设备,包括:处理器和存储器,该存储器用于存储计算机程序,所述处理器用于调用并运行所述存储器中存储的计算机程序,执行如权利要求41至44中任一项所述的方法。
  92. 一种芯片,包括:处理器,用于从存储器中调用并运行计算机程序,使得安装有所述芯片的设备执行如权利要求1至9中任一项所述的方法。
  93. 一种芯片,包括:处理器,用于从存储器中调用并运行计算机程序,使得安装有所述芯片的设备执行如权利要求10至40中任一项所述的方法。
  94. 一种芯片,包括:处理器,用于从存储器中调用并运行计算机程序,使得安装有所述芯片的设备执行如权利要求41至44中任一项所述的方法。
  95. 一种计算机可读存储介质,用于存储计算机程序,所述计算机程序使得计算机执行如权利要求1至9中任一项所述的方法。
  96. 一种计算机可读存储介质,用于存储计算机程序,所述计算机程序使得计算机执行如权利要求10至40中任一项所述的方法。
  97. 一种计算机可读存储介质,用于存储计算机程序,所述计算机程序使得计算机执行如权利要求41至44中任一项所述的方法。
  98. 一种计算机程序产品,包括计算机程序指令,该计算机程序指令使得计算机执行如权利要求1至9中任一项所述的方法。
  99. 一种计算机程序产品,包括计算机程序指令,该计算机程序指令使得计算机执行如权利要求10至40中任一项所述的方法。
  100. 一种计算机程序产品,包括计算机程序指令,该计算机程序指令使得计算机执行如权利要求41至44中任一项所述的方法。
  101. 一种计算机程序,所述计算机程序使得计算机执行如权利要求1至9中任一项所述的方法。
  102. 一种计算机程序,所述计算机程序使得计算机执行如权利要求10至40中任一项所述的方法。
  103. 一种计算机程序,所述计算机程序使得计算机执行如权利要求41至44中任一项所述的方法。
PCT/CN2020/137414 2020-12-17 2020-12-17 网络资源选择方法、终端设备和网络设备 WO2022126563A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
EP20965579.4A EP4266756A4 (en) 2020-12-17 2020-12-17 NETWORK RESOURCE SELECTION METHOD, AND TERMINAL DEVICE AND NETWORK DEVICE
CN202080107755.5A CN116569605A (zh) 2020-12-17 2020-12-17 网络资源选择方法、终端设备和网络设备
PCT/CN2020/137414 WO2022126563A1 (zh) 2020-12-17 2020-12-17 网络资源选择方法、终端设备和网络设备
US18/335,499 US20230337065A1 (en) 2020-12-17 2023-06-15 Network resource selection method, and terminal device and network device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/137414 WO2022126563A1 (zh) 2020-12-17 2020-12-17 网络资源选择方法、终端设备和网络设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/335,499 Continuation US20230337065A1 (en) 2020-12-17 2023-06-15 Network resource selection method, and terminal device and network device

Publications (1)

Publication Number Publication Date
WO2022126563A1 true WO2022126563A1 (zh) 2022-06-23

Family

ID=82059964

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/137414 WO2022126563A1 (zh) 2020-12-17 2020-12-17 网络资源选择方法、终端设备和网络设备

Country Status (4)

Country Link
US (1) US20230337065A1 (zh)
EP (1) EP4266756A4 (zh)
CN (1) CN116569605A (zh)
WO (1) WO2022126563A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115333943A (zh) * 2022-08-10 2022-11-11 中国联合网络通信集团有限公司 确定性网络资源配置系统、方法、设备及存储介质
CN116056240A (zh) * 2023-04-03 2023-05-02 阿里巴巴(中国)有限公司 资源配置系统、方法及设备
WO2024012373A1 (zh) * 2022-07-12 2024-01-18 维沃移动通信有限公司 Ai模型信息传输方法、装置及设备
WO2024032270A1 (zh) * 2022-08-09 2024-02-15 大唐移动通信设备有限公司 一种策略确定方法、装置及存储介质
WO2024036456A1 (zh) * 2022-08-15 2024-02-22 北京小米移动软件有限公司 一种基于人工智能ai提供服务的方法、装置、设备及存储介质
WO2024050848A1 (zh) * 2022-09-09 2024-03-14 北京小米移动软件有限公司 人工智能ai任务处理方法和装置
WO2024099036A1 (zh) * 2022-11-07 2024-05-16 上海诺基亚贝尔股份有限公司 用于面向服务的网络的装置、方法、设备、及介质

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106506176A (zh) * 2016-10-31 2017-03-15 中国联合网络通信集团有限公司 一种策略和计费规则生成方法和系统
CN111837425A (zh) * 2020-06-10 2020-10-27 北京小米移动软件有限公司 一种接入方法、接入装置及存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11824732B2 (en) * 2018-12-28 2023-11-21 Intel Corporation Techniques for artificial intelligence capabilities at a network switch
KR102633426B1 (ko) * 2019-03-11 2024-02-02 오피노 엘엘씨 무선 네트워크에 의한 무선 디바이스 페이징
CN111126594B (zh) * 2019-11-25 2023-08-04 北京邮电大学 基于边缘计算的神经网络模型动态切分方法及装置
CN111770062B (zh) * 2020-06-03 2022-08-05 北京小米松果电子有限公司 一种信息处理方法、装置及存储介质
CN112035516B (zh) * 2020-09-30 2023-08-18 北京百度网讯科技有限公司 用于算子服务的处理方法、装置、智能工作站和电子设备

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106506176A (zh) * 2016-10-31 2017-03-15 中国联合网络通信集团有限公司 一种策略和计费规则生成方法和系统
CN111837425A (zh) * 2020-06-10 2020-10-27 北京小米移动软件有限公司 一种接入方法、接入装置及存储介质

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Study on traffic characteristics and performance requirements for AI/ML model transfer in 5GS (Release 18)", 3GPP STANDARD; TECHNICAL REPORT; 3GPP TR 22.874, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, no. V0.1.0, 6 October 2020 (2020-10-06), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , pages 1 - 55, XP051961408 *
AT&T: "High-Level Overview of Artificial Intelligence in RAN", 3GPP DRAFT; R3-206333, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. RAN WG3, no. Online; 20201102 - 20201112, 22 October 2020 (2020-10-22), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP051941731 *
See also references of EP4266756A4 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024012373A1 (zh) * 2022-07-12 2024-01-18 维沃移动通信有限公司 Ai模型信息传输方法、装置及设备
WO2024032270A1 (zh) * 2022-08-09 2024-02-15 大唐移动通信设备有限公司 一种策略确定方法、装置及存储介质
CN115333943A (zh) * 2022-08-10 2022-11-11 中国联合网络通信集团有限公司 确定性网络资源配置系统、方法、设备及存储介质
WO2024036456A1 (zh) * 2022-08-15 2024-02-22 北京小米移动软件有限公司 一种基于人工智能ai提供服务的方法、装置、设备及存储介质
WO2024050848A1 (zh) * 2022-09-09 2024-03-14 北京小米移动软件有限公司 人工智能ai任务处理方法和装置
WO2024099036A1 (zh) * 2022-11-07 2024-05-16 上海诺基亚贝尔股份有限公司 用于面向服务的网络的装置、方法、设备、及介质
CN116056240A (zh) * 2023-04-03 2023-05-02 阿里巴巴(中国)有限公司 资源配置系统、方法及设备

Also Published As

Publication number Publication date
US20230337065A1 (en) 2023-10-19
CN116569605A (zh) 2023-08-08
EP4266756A1 (en) 2023-10-25
EP4266756A4 (en) 2024-02-21

Similar Documents

Publication Publication Date Title
WO2022126563A1 (zh) 网络资源选择方法、终端设备和网络设备
WO2022021247A1 (zh) 基于条件的辅节点或主辅小区变更方法及设备
US11399307B2 (en) Service authorization method, terminal device and network device
WO2020150876A1 (zh) 会话建立方法、终端设备和网络设备
KR20220044341A (ko) 보안 보호 모드 결정 방법 및 장치
US20230093178A1 (en) Method for service identification and terminal device
WO2019178776A1 (zh) 传输信息的方法和设备
CN114173368A (zh) 一种服务质量QoS的监测方法
WO2022160123A1 (zh) 接入方式选择方法、终端设备和网络设备
EP4109938A1 (en) Sidelink capability sending method and terminal device
WO2022126641A1 (zh) 无线通信方法、终端设备、第一接入网设备以及网元
WO2022160205A1 (zh) 一种数据传输方法、终端设备和网络设备
CN117560726A (zh) 管理网络资源的方法、装置及系统
WO2022027375A1 (zh) 选择接入小区的方法、终端设备和网络设备
CN115696217A (zh) 多播会话处理方法、网络功能实体、装置及存储介质
WO2022027211A1 (zh) 获取网络侧分析数据的方法、用户设备和网络设备
WO2022170558A1 (zh) 选择网络的方法、终端设备和网络设备
WO2022222748A1 (zh) 中继通信方法和装置
WO2022183317A1 (zh) 一种获取切片信息的方法和终端设备
US20220377547A1 (en) Wireless communication method, terminal device and network element
WO2022061838A1 (zh) 启用反向映射机制方法、终端设备和网络设备
WO2022036509A1 (zh) 请求多播控制信道信令的方法、终端设备和通信设备
WO2023221059A1 (zh) 无线通信方法、装置、设备、存储介质及程序产品
WO2022067568A1 (zh) 中继方式确定方法和设备
WO2022266870A1 (zh) 侧行链路通信方法、终端设备、网络设备及通信系统

Legal Events

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

Ref document number: 20965579

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202080107755.5

Country of ref document: CN

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020965579

Country of ref document: EP

Effective date: 20230717