An AI model scheduling method, system and device

Abstract

The present disclosure relates to the field of communication technology, and provides an AI model scheduling method, system and device, the method comprising: a visited place AI capability management module receiving position information, intelligent calculation business identification and intelligent calculation model identification, determining a same area model scheduling to be performed by using a stored intelligent calculation model registration table, interacting with a deployment place AI capability application module and the visited place AI capability application module, and respectively performing control plane signaling interaction with a visited place business transmission channel user plane network element and a deployment place business transmission channel user plane network element through a business transmission channel control plane network element, so that the visited place AI capability application module, the visited place business transmission channel user plane network element, the deployment place business transmission channel user plane network element and the deployment place AI capability application module acquire core network tunnel information of adjacent network elements, and a user plane data transmission channel is established to transfer an intelligent calculation model copy. The copy is transferred from the deployment place to the visited place AI capability application module, thereby providing support for intelligent calculation business.

Description

Technical Field

[0001] This disclosure belongs to the field of communication technology, and in particular relates to an AI model scheduling method, system and device. Background Technology

[0002] On the one hand, with the rapid development of artificial intelligence technology, generative AI, general-purpose large-scale models, and industry-specific large-scale models are gradually maturing and entering people's daily lives. On the other hand, with the development of mobile communication technology, mobile communication has become an inseparable part of production and life. The characteristics of 5G and 5G-A, such as high bandwidth, low latency, and wide connectivity, are naturally suited to the application needs of AI technology. How to combine the two to further improve social productivity and gradually empower various industries has become a key area of ​​exploration.

[0003] The current network architecture for edge computing in mobile communication networks can be divided into the following four types:

[0004] The first type: Edge computing power is provided by mobile user terminals, and the edge inference model is deployed locally on the mobile terminals;

[0005] The second type: edge computing power is set up in edge data centers (such as city-level data centers or park data centers), and users access the corresponding DN (Data Network) through the mobile communication network to obtain edge computing services;

[0006] The third type: combining intelligent computing power with mobile communication network gateways (such as UPF (User Plane Function)), such as MEC (Mobile Edge Computing) technology;

[0007] The fourth type: intelligent computing power in mobile communication networks, such as NWDAF (Network Data Analytics Function).

[0008] However, all of the above methods have problems:

[0009] The first architecture uses mobile users' mobile terminals, but the computing power and battery life of mobile terminals are limited, making it unable to support high computing power, long duration, and diverse intelligent computing needs.

[0010] For the second architecture, the intelligent computing power is deployed in the edge data center. The mobile communication network needs to establish a bearer between the terminal and the DN for the user before calling the intelligent computing service, which has a latency problem. Generally, the user side needs to manually initiate a specific SaaS service to trigger it, which has poor versatility.

[0011] For the third architecture, 5G MEC can integrate artificial intelligence and machine learning algorithms at the network edge. Although it is closer to the user edge, it is logically decoupled from the mobile communication network and depends on the deployment location of the core network gateway (such as UPF).

[0012] For the fourth architecture, NWDAF is a core network element, but it analyzes network data to improve network capabilities and cannot provide users with business-related AI capabilities.

[0013] As can be seen from the above analysis, in the face of the ever-increasing demand for AI computing, existing mobile communication networks use AI capabilities as one of the means to improve network capabilities. However, when faced with the demand for intelligent computing services with low latency and high versatility, none of the above four architectures are a complete solution for implementing intelligent computing services.

[0014] In view of this, there is an urgent need to propose an intelligent computing network architecture, on which intelligent computing model scheduling is carried out to support intelligent computing services. Summary of the Invention

[0015] To address the aforementioned issues, this disclosure provides an AI model scheduling method, system, and apparatus to support intelligent computing services.

[0016] Firstly, an AI model scheduling method is provided, including:

[0017] The visited location AI capability management module receives location information, intelligent computing service identifier, and intelligent computing model identifier;

[0018] The visited location AI capability management module uses the stored intelligent computing model registration table to determine if there is an AI capability application module that matches both the intelligent computing service identifier and the intelligent computing model identifier, but the area information corresponding to the matching AI capability application module does not match the received location information. In this case, the module performs the following same-area scheduling:

[0019] The visited AI capability management module initiates an AI model scheduling service request to the visited AI capability application module, requesting the allocation of core network tunnel information for the visited AI capability application module. The intelligent computing model registration table stores the correspondence between intelligent computing service identifier, intelligent computing model identifier, regional information, and AI capability application module information. The visited AI capability application module returns the first core network tunnel information to the visited AI capability management module.

[0020] The visited AI capability management module initiates an AI model scheduling service request to the deployed AI capability application module, which is indicated by the matching AI capability application module information. The request requests the allocation of core network tunnel information on the side of the deployed AI capability application module, and carries the intelligent computing service identifier and intelligent computing model identifier in the request. The deployed AI capability application module returns the fourth core network tunnel information to the visited AI capability management module.

[0021] The visited site AI capability management module initiates an AI model scheduling service request to the network element of the visited site service transmission channel control plane. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the AI ​​capability application module at the deployment site.

[0022] The visited service transport channel control plane network element uses the location information carried in the service request to schedule the location of the visited service transport channel user plane network element, and uses the area information to address the deployed service transport channel user plane network element. When it is determined that the visited service transport channel user plane network element and the deployed service transport channel user plane network element are the same network element, it sends a request to the visited service transport channel user plane network element to establish a user plane tunnel, carrying the first core network tunnel information and the fourth core network tunnel information.

[0023] The user plane network element of the visited service transport channel sends the second core network tunnel information to the control plane network element of the visited service transport channel.

[0024] The control plane network element of the visited service transmission channel sends the second core network tunnel information to the visited AI capability application module and the deployed AI capability application module respectively via the visited AI capability management module. Thus, the visited AI capability application module and the deployed AI capability application module establish a user plane intelligent computing service model transmission channel.

[0025] The deployment site AI capability application module uses the intelligent computing business identifier and intelligent computing model identifier to select an intelligent computing model, and then passes a copy of the selected intelligent computing model to the visited site AI capability application module.

[0026] Furthermore, the method also includes:

[0027] The control plane network element of the visited service transport channel uses the location and area information carried in the service request to schedule the service request. When it is determined that the user plane network element of the visited service transport channel and the user plane network element of the deployed service transport channel are different network elements, it sends a request to establish a user plane tunnel carrying the first core network tunnel information to the user plane network element of the visited service transport channel, and sends a request to establish a user plane tunnel carrying the fourth core network tunnel information to the user plane network element of the deployed service transport channel.

[0028] The user plane network element of the visited service transport channel sends the second core network tunnel information to the control plane network element of the visited service transport channel.

[0029] The user plane network element of the deployed service transport channel sends third core network tunnel information to the control plane network element of the visited service transport channel.

[0030] The visited service transmission channel control plane network element sends the second core network tunnel information to the visited AI capability application module via the visited AI capability management module, and sends the third core network tunnel information to the deployment site AI capability application module.

[0031] The visited service transport channel control plane network element sends the second core network tunnel information to the deployed service transport channel user plane network element, and sends the third core network tunnel information to the visited service transport channel user plane network element. Thus, the visited AI capability application module and the deployed AI capability application module establish a user plane intelligent computing service model transport channel.

[0032] The deployment site AI capability application module uses the intelligent computing business identifier and intelligent computing model identifier to select an intelligent computing model, and then passes a copy of the selected intelligent computing model to the visited site AI capability application module.

[0033] Secondly, an AI model scheduling method is provided, the method comprising:

[0034] The visited location AI capability management module receives location information, intelligent computing service identifier, and intelligent computing model identifier;

[0035] The visited location AI capability management module uses the stored intelligent computing model registration table to determine if there is an AI capability application module that matches both the intelligent computing business identifier and the intelligent computing model identifier, and then performs the following cross-region scheduling:

[0036] The visited AI capability management module initiates an AI model scheduling service request to the visited AI capability application module, requesting the allocation of core network tunnel information on the visited AI capability application module side. The intelligent computing model registration table stores the correspondence between intelligent computing service identifier, intelligent computing model identifier, regional information and AI capability application module information. The visited AI capability application module returns the first core network tunnel information to the visited AI capability management module.

[0037] The visited site AI capability management module initiates an AI model scheduling service request to the visited site service transport channel control plane network element, which carries the first core network tunnel information and location information. The visited site service transport channel control plane network element addresses the visited site service transport channel user plane network element according to the location information and sends a user plane tunnel establishment request, which carries the first core network tunnel information. The visited site service transport channel control plane network element receives the second core network tunnel information fed back by the user plane network element of the visited site service transport channel and transmits it to the visited site AI capability application module via the visited site AI capability management module.

[0038] The visited AI capability management module addresses the deployed AI capability management module based on the intelligent computing service identifier and the intelligent computing model identifier, and sends an AI model scheduling service request to the deployed AI capability management module. The request carries the intelligent computing service identifier, the intelligent computing model identifier, and the second core network tunnel information.

[0039] The deployment site AI capability management module determines the deployment site AI capability application module based on the intelligent computing service identifier and the intelligent computing model identifier, and initiates an AI model scheduling service process to it, requesting the deployment site AI capability application module to allocate core network tunnel information;

[0040] The AI ​​capability application module at the deployment site returns the fourth core network tunnel information to the AI ​​capability management module at the deployment site.

[0041] The deployment site AI capability management module initiates an AI model scheduling service request to the deployment site service transport channel control plane network element. The request carries the fourth core network tunnel information, the second core network tunnel information, and the area information that the deployment site AI capability application module is responsible for. Among them, the deployment site service transport channel control plane network element and the visited site service transport channel control plane network element are the same network element or different network elements.

[0042] Based on the area information of the AI ​​capability application module at the deployment location, the control plane network element of the service transport channel at the deployment location addresses the user plane network element of the service transport channel at the deployment location and initiates a request to establish a user plane tunnel to the user plane network element of the service transport channel at the deployment location. The request carries the fourth core network tunnel information and the second core network tunnel information.

[0043] The user plane network element of the deployment site service transport channel returns the third core network tunnel information to the control plane network element of the deployment site service transport channel.

[0044] The network element of the service transmission channel at the deployment site returns the third core network tunnel information to the AI ​​capability management module at the deployment site.

[0045] The AI ​​capability management module at the deployment site returns the AI ​​model scheduling service request establishment result to the AI ​​capability management module at the visited site. The result includes: third core network tunnel information.

[0046] The visited site AI capability management module returns the third core network tunnel information to the visited site service transmission channel control plane network element; the visited site service transmission channel control plane network element returns the third core network tunnel information to the visited site service transmission channel user plane network element. At this point, the intelligent computing model scheduling service transmission channel is established.

[0047] The deployment site AI capability application module uses the intelligent computing business identifier and intelligent computing model identifier to select an intelligent computing model, and then passes a copy of the selected intelligent computing model to the visited site AI capability application module.

[0048] Furthermore, the visited site AI capability management module sends an AI model scheduling service request to the deployed site AI capability management module, including:

[0049] The visited site AI capability management module sequentially sends AI model scheduling service requests to the deployed site AI capability management module via the visited site service transport channel control plane network element and the deployed site service transport channel control plane network element; and / or

[0050] The deployment site AI capability management module returns the AI ​​model scheduling business request establishment result to the visited site AI capability management module, including:

[0051] The deployment site AI capability management module sequentially returns the AI ​​model scheduling service request establishment result to the visited site AI capability management module via the visited site service transmission channel control plane network element and the deployment site service transmission channel control plane network element.

[0052] Furthermore, after the deployment site AI capability application module selects an intelligent computing model using the intelligent computing service identifier and the intelligent computing model identifier, and transmits a copy of the selected intelligent computing model to the visited site AI capability application module, the method further includes:

[0053] The visited site AI capability application module returns the intelligent computing model transmission completion information to the visited site AI capability management module, and the AI ​​capability management module registers the model.

[0054] Furthermore, the visited location AI capability management module uses either of the following two methods for addressing:

[0055] Method 1: Configure the global intelligent computing model registration information table locally and notify the global and other AI capability management modules when the registration information changes;

[0056] Method 2: When the intelligent computing model registration information changes, the AI ​​capability management module completes registration with the network resource database. The registration information includes: AI capability management module identifier, AI capability management module address, intelligent computing business identifier, intelligent computing model identifier, AI capability application module identifier, and region information. The AI ​​capability management module performs AI capability management module service discovery with the network resource database. The request message includes the intelligent computing business identifier and the intelligent computing model identifier. Based on the AI ​​capability management module service discovery result returned by the network resource database, the AI ​​capability management module is selected.

[0057] Thirdly, an AI model scheduling method is provided, which is applied to the visited site AI capability management module, including:

[0058] Receive location information, intelligent computing service identifier, and intelligent computing model identifier;

[0059] Using the stored intelligent computing model registration table, it is determined that there is an AI capability application module that matches both the intelligent computing service identifier and the intelligent computing model identifier, but the area information corresponding to the matching AI capability application module does not match the received location information. In this case, intra-area scheduling is performed, and an AI model scheduling service request is initiated to the visited AI capability application module to request the allocation of core network tunnel information on the visited AI capability application module side. The intelligent computing model registration table stores the correspondence between the intelligent computing service identifier, the intelligent computing model identifier, the area information, and the AI ​​capability application module information.

[0060] Receive the first core network tunnel information returned by the AI ​​capability application module of the visited site;

[0061] An AI model scheduling service request is initiated to the AI ​​capability application module at the deployment location indicated by the matching AI capability application module information. The request requests the allocation of core network tunnel information on the side of the AI ​​capability application module at the deployment location. The request carries the intelligent computing service identifier and the intelligent computing model identifier.

[0062] Receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site;

[0063] The system initiates an AI model scheduling service request to the control plane network element of the service transmission channel at the visited location. The request carries information about the first core network tunnel, the fourth core network tunnel, location information, and the regional information of the AI ​​capability application module at the deployment location.

[0064] When it is determined that the user plane network element of the visited service transport channel and the user plane network element of the deployed service transport channel are the same network element, the second core network tunnel information sent by the control plane network element of the visited service transport channel is forwarded to the AI ​​capability application module of the visited location and the AI ​​capability application module of the deployed location. The second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transport channel.

[0065] Furthermore, when it is determined that the user plane network element of the visited service transport channel and the user plane network element of the deployed service transport channel are different network elements, the second core network tunnel information sent by the control plane network element of the visited service transport channel is forwarded to the AI ​​capability application module of the visited location, and the third core network tunnel information is forwarded to the AI ​​capability application module of the deployed location. The third core network tunnel information is the core network tunnel information of the user plane network element of the deployed service transport channel.

[0066] Fourthly, an AI model scheduling method is provided, applied in the visited site AI capability management module, including:

[0067] Receive location information, intelligent computing service identifier, and intelligent computing model identifier;

[0068] Using the stored intelligent computing model registration table, it is determined that there is no AI capability application module that matches both the intelligent computing service identifier and the intelligent computing model identifier. An AI model scheduling service request is then initiated to the visited AI capability application module, requesting the allocation of core network tunnel information on the visited AI capability application module side. The intelligent computing model registration table stores the correspondence between the intelligent computing service identifier, the intelligent computing model identifier, the regional information, and the AI ​​capability application module information.

[0069] Receive the first core network tunnel information returned by the AI ​​capability application module of the visited site;

[0070] The system initiates an AI model scheduling service request to the control plane network element of the visited service transmission channel, and the request carries the first core network tunnel information and location information.

[0071] Forward the second core network tunnel information sent by the control plane network element of the visited service transmission channel to the visited AI capability application module;

[0072] The AI ​​capability management module at the deployment location is located based on the intelligent computing service identifier and the intelligent computing model identifier, and an AI model scheduling service request is sent. The request carries the intelligent computing service identifier, the intelligent computing model identifier, and the second core network tunnel information.

[0073] The AI ​​model scheduling service request establishment result returned by the AI ​​capability management module at the deployment site is received. The result includes: third core network tunnel information, where the third core network tunnel information is the core network tunnel information of the user plane network element of the service transmission channel at the deployment site.

[0074] Return third core network tunnel information to the network element of the access control plane of the visited service transmission channel.

[0075] Furthermore, it also includes:

[0076] Receive the intelligent computing model transmission completion information returned by the AI ​​capability application module of the visited location, and register the intelligent computing model.

[0077] Furthermore, addressing can be performed using either of the following two methods:

[0078] Method 1: Configure the global intelligent computing model registration information table locally and notify the global and other AI capability management modules when the registration information changes;

[0079] Method 2: When the registration information of the intelligent computing model changes, the registration with the network resource database is completed. The registration information includes: AI capability management module identifier, AI capability management module address, intelligent computing business identifier, intelligent computing model identifier, AI capability application module identifier, and regional information. The AI ​​capability management module performs AI capability management module service discovery with the network resource database. The request message contains the intelligent computing business identifier and the intelligent computing model identifier. Based on the AI ​​capability management module service discovery result returned by the network resource database, the AI ​​capability management module is selected.

[0080] Fifthly, an AI model scheduling method is provided, applied in the visited site AI capability application module, including:

[0081] Receives an AI model scheduling service request initiated by the AI ​​capability management module of the visited location;

[0082] Allocate the first core network tunnel information and return it to the visited AI capability management module;

[0083] Receive the second core network tunnel information sent by the visited AI capability management module; the second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transmission channel.

[0084] Receive a copy of the intelligent computing model sent by the AI ​​capability application module at the deployment site.

[0085] Sixthly, an AI model scheduling method is provided, applied to the control plane network element of the visited service transport channel. When performing intra-area scheduling, the method includes:

[0086] Receive AI model scheduling service request initiated by the visited site AI capability management module. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the deployed site AI capability application module. Among them, the first core network tunnel information refers to the core network tunnel information of the visited site AI application module, and the fourth core network tunnel information refers to the core network tunnel information of the deployed site AI application module.

[0087] The AI ​​model schedules the user plane network element of the service transmission channel at the visited location by using the location information carried in the service request, and uses the area information to address the user plane network element of the service transmission channel at the deployment location. When it is determined that the user plane network element of the service transmission channel at the visited location and the user plane network element of the service transmission channel at the deployment location are the same network element, a request to establish a user plane tunnel carrying the first core network tunnel information and the fourth core network tunnel information is sent to the user plane network element of the service transmission channel at the visited location.

[0088] Receive second core network tunnel information sent by user plane network elements of the visited service transmission channel;

[0089] The second core network tunnel information is sent to the visited AI capability application module and the deployment site AI capability application module via the visited site AI capability management module.

[0090] Furthermore, the method also includes:

[0091] By utilizing the location and regional information carried in the service request to schedule the AI ​​model, when it is determined that the user plane network element of the service transport channel at the visited location and the user plane network element of the service transport channel at the deployment location are different network elements, a user plane tunnel establishment request carrying the first core network tunnel information is sent to the user plane network element of the service transport channel at the visited location, and a user plane tunnel establishment request carrying the fourth core network tunnel information is sent to the user plane network element of the service transport channel at the deployment location.

[0092] Receive second core network tunnel information sent by user plane network elements of the visited service transmission channel;

[0093] Receive third core network tunnel information sent by user plane network elements of the service transmission channel at the deployment site;

[0094] The second core network tunnel information is sent to the visited AI capability application module via the visited AI capability management module, and the third core network tunnel information is sent to the deployment site AI capability application module.

[0095] Send the second core network tunnel information to the user plane network element of the service transport channel at the deployment site, and send the third core network tunnel information to the user plane network element of the service transport channel at the visited site.

[0096] Seventhly, an AI model scheduling method is provided, applied to the control plane network element of the visited service transport channel. When performing cross-region scheduling, the method includes:

[0097] Receives an AI model scheduling service request initiated by the visited site's AI capability management module, which carries the first core network tunnel information and location information;

[0098] Based on the location information, the user plane network element of the visited service transmission channel is addressed, and a request to establish a user plane tunnel is sent, which carries the first core network tunnel information.

[0099] The second core network tunnel information is received from the user plane network element of the user visited service transmission channel and transmitted to the visited AI capability application module via the visited AI capability management module.

[0100] Receive the third core network tunnel information returned by the AI ​​capability management module of the visited location. The third core network tunnel information is the core network tunnel information of the user plane network element of the service transmission channel at the deployment location.

[0101] Return third core network tunnel information to the user plane network element of the visited service transmission channel.

[0102] Eighthly, an AI model scheduling method is provided, applied to the AI ​​capability application module in the deployment area, including the following when performing intra-region scheduling:

[0103] The system receives an AI model scheduling service request initiated by the AI ​​capability management module of the visited location, which allocates and deploys the core network tunnel information of the AI ​​capability application module. The request carries the intelligent computing service identifier and the intelligent computing model identifier.

[0104] Allocate tunnel information for the fourth core network;

[0105] Return the fourth core network tunnel information to the AI ​​capability management module of the visited site;

[0106] When the user plane network element of the visited service transport channel and the user plane network element of the deployment service transport channel are the same network element, the second core network tunnel information sent by the visited AI capability management module is received, and the visited service transport channel user plane network element is interacted with so that the visited AI capability application module and the deployment AI capability application module can establish a user plane intelligent computing service model transport channel; wherein, the second core network tunnel information is the core network tunnel information at the user plane network element end of the visited service transport channel.

[0107] The intelligent computing model is selected using the intelligent computing business identifier and the intelligent computing model identifier. The selected intelligent computing model copy is then transmitted to the visited AI capability application module through the established user plane intelligent computing business model transmission channel.

[0108] Furthermore, when it is determined that the user plane network element of the visited service transport channel and the user plane network element of the deployment service transport channel are not the same network element, the third core network tunnel information sent by the visited AI capability management module is received. The third core network tunnel information is the core network tunnel information of the user plane network element of the deployment service transport channel.

[0109] Ninthly, an AI model scheduling method is provided, applied to the AI ​​capability application module in the deployment location, including the following when performing cross-region scheduling:

[0110] The AI ​​capability management module at the deployment site initiates a business process to request the AI ​​capability application module at the deployment site to allocate core network tunnel information AI model scheduling services.

[0111] Allocate tunnel information for the fourth core network;

[0112] The fourth core network tunnel information is returned to the AI ​​capability management module at the deployment site, so that the AI ​​capability management module at the deployment site can send the fourth core network tunnel information, the second core network tunnel information, and the regional information to the control plane network element of the service transmission channel at the deployment site in the AI ​​model scheduling service request. The second core network tunnel information refers to the core network tunnel information at the user plane network element of the service transmission channel at the visited site.

[0113] The intelligent computing model is selected using the intelligent computing business identifier and the intelligent computing model identifier. The selected intelligent computing model copy is then transmitted to the visited AI capability application module through the established user plane intelligent computing business model transmission channel.

[0114] Tenthly, an AI model scheduling method is provided, applied to user plane network elements of visited service transport channels, including the following when performing intra-area scheduling:

[0115] Receive a request to establish a user plane tunnel from the control plane network element of the visited service transport channel. The request carries the first core network tunnel information and the fourth core network tunnel information. The first core network tunnel information refers to the core network tunnel information of the visited AI application module, and the fourth core network tunnel information refers to the core network tunnel information of the deployed AI application module.

[0116] Allocate information for the second core network tunnel;

[0117] Send the second core network tunnel information to the control plane network element of the visited service transmission channel;

[0118] Forward the copy of the intelligent computing model sent by the AI ​​capability module at the deployment site to the AI ​​capability application module at the visited site.

[0119] Eleventhly, an AI model scheduling method is provided, applied to user plane network elements of visited service transport channels, including the following when performing cross-region scheduling:

[0120] Receive a request to establish a user plane tunnel from the control plane network element of the visited service transport channel. The request carries the first core network tunnel information, which refers to the core network tunnel information of the visited AI application module.

[0121] Allocate information for the second core network tunnel;

[0122] Send the second core network tunnel information to the control plane network element of the visited service transmission channel;

[0123] Receive the third core network tunnel information sent by the control plane network element of the visited service transport channel, wherein the third core network tunnel information refers to the core network tunnel information of the user plane network element of the deployed service transport channel.

[0124] The intelligent computing model copy sent by the user plane network element of the service transmission channel at the deployment site is forwarded to the visited AI capability application module.

[0125] In the twelfth aspect, an AI model scheduling method is provided, applied to user plane network elements of the service transmission channel in the deployment location, including the following when performing intra-area scheduling:

[0126] Receive a request to establish a user plane tunnel from the control plane network element of the visited service transmission channel. The request carries the fourth core network tunnel information, which refers to the core network tunnel information of the AI ​​capability application module at the deployment site.

[0127] Allocate information for the third core network tunnel;

[0128] Send the third core network tunnel information to the control plane network element of the visited service transmission channel;

[0129] Receive the second core network tunnel information sent by the control plane network element of the visited service transport channel, wherein the second core network tunnel information refers to the core network tunnel information at the user plane network element end of the visited service transport channel.

[0130] Forward the copy of the intelligent computing model sent by the AI ​​capability application module at the deployment site to the AI ​​capability application module at the visited site.

[0131] Thirteenthly, an AI model scheduling method is provided, applied to user plane network elements of the service transmission channel in the deployment location, including the following when performing cross-region scheduling:

[0132] Receive a request to establish a user plane tunnel from the control plane network element of the service transport channel at the deployment site. The request carries the fourth core network tunnel information and the second core network tunnel information. The second core network tunnel information is the core network tunnel information of the user plane network element at the visited site, and the fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site.

[0133] Allocate information for the third core network tunnel;

[0134] The third core network tunnel information is returned to the control plane network element of the service transmission channel at the deployment site;

[0135] Forward the copy of the intelligent computing model sent by the AI ​​capability application module at the deployment site to the control plane network element of the business transmission channel at the visited site.

[0136] Fourteenthly, an AI model scheduling method is provided, applied to the control plane network element of the service transmission channel in the deployment location, including the following when performing cross-regional scheduling:

[0137] Receive AI model scheduling service request sent by the AI ​​capability management module at the deployment site. The request carries the fourth core network tunnel information, the second core network tunnel information, and the area information that the AI ​​capability application module at the deployment site is responsible for. Among them, the second core network tunnel information is the core network tunnel information of the user plane network element end of the visited service transmission channel, and the fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site.

[0138] Based on the regional information of the AI ​​capability application module at the deployment site, the system addresses the user plane network element of the service transmission channel at the deployment site and initiates a request to establish a user plane tunnel to the user plane network element of the service transmission channel at the deployment site. The request carries the fourth core network tunnel information and the second core network tunnel information.

[0139] Receive the third core network tunnel information returned by the user plane network element of the service transmission channel at the deployment site;

[0140] Return the third core network tunnel information to the AI ​​capability management module at the deployment site.

[0141] The fifteenth aspect provides an AI model scheduling method, applied in the AI ​​capability management module of the deployment site, including:

[0142] Receive AI model scheduling service request sent by the visited AI capability management module. The request carries the second core network tunnel information, which is the core network tunnel information of the user plane network element of the visited service transmission channel.

[0143] An AI model scheduling service request is initiated to the AI ​​capability application module at the deployment site to allocate the core network tunnel information of the AI ​​capability application module at the deployment site. The request carries the intelligent computing service identifier and the intelligent computing model identifier.

[0144] Receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site. The fourth core network tunnel information is the core network tunnel information at the AI ​​capability application module at the deployment site.

[0145] Send an AI model scheduling service request to the network element of the service transmission channel control plane at the deployment site. The request carries the fourth core network tunnel information, the second core network tunnel information, and the area information of the AI ​​capability application module at the deployment site.

[0146] Receive the third core network tunnel information sent by the control plane network element of the service transport channel at the deployment site, wherein the third core network tunnel information is the core network tunnel information at the user plane network element end of the service transport channel at the deployment site;

[0147] The AI ​​model scheduling service request establishment result is returned to the AI ​​capability management module of the visited location. The result includes: third core network tunnel information.

[0148] Sixteenthly, a visited site AI capability management module includes:

[0149] The first receiving module is used to receive location information, intelligent computing service identifier, and intelligent computing model identifier;

[0150] The first sending module is used to utilize the stored intelligent computing model registration table to perform intra-region scheduling when it is determined that there is an AI capability application module that matches both the intelligent computing service identifier and the intelligent computing model identifier, and the area information corresponding to the matching AI capability application module does not match the received location information. The module then initiates an AI model scheduling service request to the visited AI capability application module and requests the allocation of core network tunnel information on the visited AI capability application module side. The intelligent computing model registration table stores the correspondence between the intelligent computing service identifier, the intelligent computing model identifier, the area information, and the AI ​​capability application module information.

[0151] The second receiving module is used to receive the first core network tunnel information returned by the visited AI capability application module.

[0152] The second sending module is used to initiate an AI model scheduling service request to the AI ​​capability application module at the deployment location pointed to by the matching AI capability application module information, requesting the allocation of core network tunnel information on the side of the AI ​​capability application module at the deployment location, and the request carries the intelligent computing service identifier and intelligent computing model identifier.

[0153] The third receiving module is used to receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site;

[0154] The third sending module is used to initiate an AI model scheduling service request to the control plane network element of the visited service transmission channel. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the AI ​​capability application module at the deployment location.

[0155] When the forwarding module determines that the user plane network element of the visited service transport channel and the user plane network element of the deployment service transport channel are the same network element, it forwards the second core network tunnel information sent by the control plane network element of the visited service transport channel to the AI ​​capability application module of the visited location and the AI ​​capability application module of the deployment location. The second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transport channel.

[0156] The seventeenth aspect provides a visited site AI capability application module, including:

[0157] The first receiving module is used to receive AI model scheduling service requests initiated by the AI ​​capability management module of the visited location.

[0158] The allocation module is used to allocate tunnel information in the first core network.

[0159] The sending module is used to return data to the AI ​​capability management module of the visited location;

[0160] The second receiving module is used to receive the second core network tunnel information sent by the visited AI capability management module; wherein the second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transmission channel.

[0161] The third receiving module is used to receive copies of the intelligent computing model sent by the AI ​​capability application module at the deployment site.

[0162] Eighteenth aspect, a visited service transport channel control plane network element is provided, which includes, during intra-area scheduling:

[0163] The first receiving module is used to receive AI model scheduling service requests initiated by the AI ​​capability management module of the visited location when performing intra-regional scheduling. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the AI ​​capability application module of the deployment location. Among them, the first core network tunnel information refers to the core network tunnel information of the AI ​​application module at the visited location, and the fourth core network tunnel information refers to the core network tunnel information of the AI ​​application module at the deployment location.

[0164] The addressing module is used to address the user plane network elements of the service transmission channel in the visited location using the location information carried in the service request of the AI ​​model, and to address the user plane network elements of the service transmission channel in the deployment location using the area information.

[0165] The first sending module is used to send a request to establish a user plane tunnel to the user plane network element of the service transport channel at the visited location, carrying the first core network tunnel information and the fourth core network tunnel information, when it is determined that the user plane network element of the service transport channel at the visited location and the user plane network element of the service transport channel at the deployed location are the same network element.

[0166] The second receiving module is used to receive the second core network tunnel information sent by the user plane network element of the visited service transmission channel.

[0167] The second sending module is used to send the second core network tunnel information to the visited AI capability application module and the deployment site AI capability application module respectively via the visited site AI capability management module.

[0168] Nineteenth aspect, a visited service transport channel control plane network element is provided, which includes the following for cross-regional scheduling:

[0169] The third receiving module is used to receive AI model scheduling service requests initiated by the visited AI capability management module. The requests carry the first core network tunnel information and location information. The first core network tunnel information refers to the core network tunnel information of the visited AI application module.

[0170] The addressing module is used to address the user plane network element of the visited service transmission channel based on the location information;

[0171] The third sending module is used to send a request to establish a user plane tunnel to the user plane network element of the visited service transport channel. The request carries the first core network tunnel information.

[0172] The fourth receiving module is used to receive the second core network tunnel information fed back by the user plane network element of the user visited service transmission channel, and transmit it to the visited AI capability application module via the visited AI capability management module.

[0173] The fifth receiving module is used to receive the third core network tunnel information returned by the visited AI capability management module. The third core network tunnel information is the core network tunnel information of the user plane network element of the service transmission channel at the deployment site.

[0174] The fourth sending module is used to return the third core network tunnel information to the user plane network element of the visited service transmission channel.

[0175] The twentieth aspect provides a deployment location AI capability application module, which, when performing intra-regional scheduling, includes:

[0176] The first receiving module is used to receive AI model scheduling service requests initiated by the visited AI capability management module, which allocates and deploys AI capability application module core network tunnel information. The requests carry intelligent computing service identifier and intelligent computing model identifier.

[0177] The first allocation module is used to allocate tunnel information for the fourth core network.

[0178] The first sending module is used to return the fourth core network tunnel information to the visited AI capability management module.

[0179] The second receiving module is used to receive the second core network tunnel information sent by the visited AI capability management module when the visited service transport channel control plane network element determines that the visited service transport channel user plane network element and the deployed service transport channel user plane network element are the same network element. The second core network tunnel information is the core network tunnel information of the visited service transport channel user plane network element.

[0180] The selection module is used to select an intelligent computing model using intelligent computing business identifiers and intelligent computing model identifiers;

[0181] The second sending module transmits the selected intelligent computing model copy to the visited AI capability application module.

[0182] The twenty-first aspect provides a deployment location AI capability application module that, when performing cross-regional scheduling, includes:

[0183] The third receiving module is used to receive the AI ​​capability management module at the deployment site from the business process of requesting the AI ​​capability application module at the deployment site to allocate core network tunnel information AI model scheduling services.

[0184] The second allocation module is used to allocate the fourth core network tunnel information;

[0185] The third sending module is used to return the fourth core network tunnel information to the AI ​​capability management module at the deployment site, so that the AI ​​capability management module at the deployment site can send the fourth core network tunnel information, the second core network tunnel information and the regional information to the control plane network element of the service transmission channel at the deployment site in the AI ​​model scheduling service request. The second core network tunnel information refers to the core network tunnel information at the user plane network element of the service transmission channel at the visited site.

[0186] The fourth sending module is used to transmit the selected intelligent computing model copy to the visited AI capability application module through the established user plane intelligent computing business model transmission channel.

[0187] A twenty-second aspect, a user plane network element of a visited service transport channel, when performing intra-area scheduling, includes:

[0188] The first receiving module is used to receive the request to establish a user plane tunnel sent by the control plane network element of the visited service transmission channel. The request carries the first core network tunnel information and the fourth core network tunnel information. The first core network tunnel information refers to the core network tunnel information of the visited AI application module end, and the fourth core network tunnel information refers to the core network tunnel information of the deployed AI application module end.

[0189] The first allocation module is used to allocate the second core network tunnel information;

[0190] The first sending module is used to send the second core network tunnel information to the control plane network element of the visited service transmission channel.

[0191] A twenty-third aspect, a user plane network element of a visited service transport channel, when performing cross-regional scheduling, includes:

[0192] The second receiving module is used to receive a request to establish a user plane tunnel sent by the control plane network element of the visited service transmission channel. The request carries the first core network tunnel information, which refers to the core network tunnel information of the visited AI application module.

[0193] The second allocation module is used to allocate the second core network tunnel information;

[0194] The second sending module sends the second core network tunnel information to the control plane network element of the visited service transmission channel.

[0195] The third receiving module is used to receive the third core network tunnel information sent by the control plane network element of the visited service transport channel. The third core network tunnel information refers to the core network tunnel information of the user plane network element of the deployed service transport channel.

[0196] The third sending module forwards the copy of the intelligent computing model sent by the user plane network element of the service transmission channel at the deployment site to the visited AI capability application module.

[0197] A twenty-fourth aspect provides a user plane network element for a deployed service transport channel, which, when performing intra-area scheduling, includes:

[0198] The first receiving module is used to receive the request to establish a user plane tunnel sent by the control plane network element of the visited service transmission channel. The request carries the fourth core network tunnel information, which refers to the core network tunnel information of the AI ​​capability application module at the deployment site.

[0199] The allocation module is used to allocate third core network tunnel information;

[0200] The first sending module is used to send the third core network tunnel information to the control plane network element of the visited service transmission channel;

[0201] The second receiving module is used to receive the second core network tunnel information sent by the control plane network element of the visited service transmission channel, wherein the second core network tunnel information refers to the core network tunnel information at the user plane network element end of the visited service transmission channel.

[0202] The second sending module is used to forward the copy of the intelligent computing model sent by the AI ​​capability application module at the deployment site to the AI ​​capability application module at the visited site.

[0203] In a twenty-fifth aspect, a deployment location service transport channel control plane network element is provided, which, when performing cross-regional scheduling, includes:

[0204] The first receiving module is used to receive the AI ​​model scheduling service request sent by the AI ​​capability management module at the deployment site. The request carries the fourth core network tunnel information, the second core network tunnel information, and the area information that the AI ​​capability application module at the deployment site is responsible for. Among them, the second core network tunnel information is the core network tunnel information of the user plane network element end of the visited service transmission channel, and the fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site.

[0205] The addressing module is used to address the user plane network elements of the service transmission channel at the deployment location based on the area information of the AI ​​capability application module at the deployment location.

[0206] The first sending module is used to initiate a request to establish a user plane tunnel to the user plane network element of the service transmission channel at the deployment site. The request carries the fourth core network tunnel information and the second core network tunnel information.

[0207] The second receiving module is used to receive the third core network tunnel information returned by the user plane network element of the service transmission channel at the deployment site;

[0208] The second sending module is used to return the third core network tunnel information to the AI ​​capability management module at the deployment site.

[0209] The twenty-sixth aspect provides a deployment site AI capability management module, including:

[0210] The first receiving module is used to receive the AI ​​model scheduling service request sent by the visited AI capability management module. The request carries the second core network tunnel information, which is the core network tunnel information of the user plane network element of the visited service transmission channel.

[0211] The first sending module is used to initiate an AI model scheduling service request to the AI ​​capability application module at the deployment site to allocate the core network tunnel information of the AI ​​capability application module at the deployment site. The request carries the intelligent computing service identifier and the intelligent computing model identifier.

[0212] The second receiving module is used to receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site. The fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site.

[0213] The second sending module is used to send AI model scheduling service requests to the network elements of the service transmission channel control plane at the deployment site. The requests carry the fourth core network tunnel information, the second core network tunnel information, and the area information of the AI ​​capability application module at the deployment site.

[0214] The third receiving module is used to receive the third core network tunnel information sent by the control plane network element of the service transmission channel at the deployment site. The third core network tunnel information is the core network tunnel information of the user plane network element at the deployment site.

[0215] The third sending module is used to return the AI ​​model scheduling service request establishment result to the visited AI capability management module. The result includes: third core network tunnel information.

[0216] In the twenty-seventh aspect, an AI model scheduling system is provided, which, when scheduling within the same area, includes: the visited site AI capability management module described in the sixteenth aspect, the visited site AI capability application module described in the seventeenth aspect, the visited site service transmission channel control plane network element described in the eighteenth aspect, the deployment site AI capability application module described in the twentieth aspect, the visited site service transmission channel user plane network element described in the twenty-second aspect, and the deployment site service transmission channel user plane network element described in the twenty-fourth aspect.

[0217] The cross-regional scheduling includes: the visited location AI capability management module as described in aspect sixteen, the visited location AI capability application module as described in aspect seventeen, the visited location service transmission channel control plane network element as described in aspect nineteen, the visited location service transmission channel user plane network element as described in aspect twenty-three, the deployment location service transmission channel control plane network element as described in aspect twenty-five, the deployment location AI capability application module as described in aspect twenty-one, and the deployment location AI capability management module as described in aspect twenty-six.

[0218] In a twentieth aspect, an electronic device is provided, comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0219] Memory, used to store computer programs;

[0220] The processor implements the above method when executing programs stored in memory.

[0221] A twenty-ninth aspect is a computer storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0222] Compared with the prior art, this disclosure has the following advantages:

[0223] This disclosure provides AI capabilities to mobile terminal users in the form of services, integrating AI service capabilities into the mobile communication network and providing AI computing power to users from the core network side. Compared with deployment in the data network (DN), the computing power is closer to the user, and the business process is greatly shortened; compared with being carried by the mobile terminal, moving the intelligent computing power to the edge network eliminates the need for terminal computing, reduces terminal power consumption, and enables the terminal to operate under light load; compared with being carried by MEC, moving the intelligent computing power to the core network side enables the core network to realize functions such as mobility management and service expansion. It solves problems such as high computing latency, poor versatility, and difficulty in mobility management.

[0224] This disclosure proposes a method for providing AI services to mobile terminal users via a mobile communication core network. It provides methods for establishing service transmission channels and model scheduling. The service transmission channel establishment method establishes service transmission channels, which can then be used to provide AI services to user terminals. The model scheduling method transfers copies of intelligent computing models from the deployment site to visited AI capability application modules, supporting intelligent computing services.

[0225] Other features and advantages of this disclosure will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the disclosure. The objects and other advantages of this disclosure may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0226] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0227] Figure 1 A schematic diagram of an edge intelligent computing network architecture for mobile communication network users is shown according to an embodiment of the present disclosure;

[0228] Figure 2 A schematic diagram of a user's use of intelligent computing services according to an embodiment of the present disclosure is shown;

[0229] Figure 3 A schematic diagram of the network topology for AI model scheduling service processes according to embodiments of this disclosure is shown.

[0230] Figure 4 A flowchart of the intra-regional scheduling service process of the AI ​​model according to an embodiment of the present disclosure is shown;

[0231] Figure 5 This diagram illustrates the interaction between network elements in a local area scheduling service using an AI model according to an embodiment of this disclosure.

[0232] Figure 6 This diagram illustrates the inter-network element interaction of an AI model for cross-regional scheduling services according to an embodiment of this disclosure.

[0233] Figure 7 Another interaction diagram between network elements is shown for cross-regional scheduling services using an AI model according to an embodiment of this disclosure;

[0234] Figure 8 A flowchart illustrating the cross-regional scheduling service process of an AI model according to an embodiment of this disclosure is shown. Detailed Implementation

[0235] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0236] Figure 1 A schematic diagram of an edge intelligent computing network architecture for mobile communication network users according to an embodiment of the present disclosure is shown. Figure 1 As shown in this embodiment, an edge intelligent computing network architecture for mobile communication network users includes: an AI capability application module, an AI capability management module, a service transport channel control plane network element, a service transport channel user plane network element, a user data network element, a user PCC (Policy Control and Charging) policy control network element, and an access and mobility management network element. The service transport channel user plane network element is connected to an external data network (DN), which has application functions (AF).

[0237] The edge intelligent computing network architecture disclosed herein can be based on the existing 5G core network (5GC) or 4G core network (EPC) network architecture, adding AI capability application modules and AI capability management modules, and updating the functions of the control plane network elements and user plane network elements of the service transport channel. This disclosure provides a process for introducing intelligent computing models into mobile communication networks, a service / signaling process for establishing intelligent computing service data transmission channels for mobile communication users (UEs), and a service / signaling process for completing intelligent computing model scheduling. These processes involve modifications to the interfaces between the aforementioned network elements. Figure 1 The dashed lines represent signaling interactions between control plane channels, while the solid lines represent service interactions between user plane channels. The purple solid lines represent the established user plane transmission channels for intelligent computing services, and the purple dashed lines represent the signaling interactions between the AI ​​capability application module and the AI ​​capability management module, as well as the signaling interactions between the AI ​​capability management module and the control plane network elements of the service transmission channels.

[0238] The service transport channel control plane network element disclosed herein can be SMF (Session Management Function) in the 5G core network and SGW-C / SGW (Serving Gateway-Control / Serving Gateway) in the 4G core network.

[0239] The user plane network element of the service transport channel disclosed herein can be a UPF in the 5G core network and an SGW-U / SGW (Serving Gateway-User / Serving Gateway) in the 4G core network.

[0240] The user data network element disclosed herein can be a UDM (Unified Data Management) in the 5G core network and an HSS (Home Subscriber Server) in the 4G core network.

[0241] The user PCC policy control network element disclosed herein can be PCF (Policy Control Function) in the 5G core network and PCRF (Policy and Charging Control Function) in the 4G core network.

[0242] in:

[0243] (1) AI capability application module, which is used to carry intelligent computing power, provide users with a variety of intelligent computing models, and create core network tunnels according to the request of AI capability management module during the establishment of intelligent computing service transmission channels, and complete the corresponding business processes as the tunnel start point or end point.

[0244] This includes providing users with various intelligent computing models: a general intelligent computing model and / or a user-customized intelligent computing model. The user-customized intelligent computing model can be divided into user-initiated contracts for ToC (business-to-consumer) and user-initiated contracts for ToB (business-to-business).

[0245] AI capability application modules can be deployed hierarchically or in a distributed manner; they can be logically co-located with existing network elements (such as UPF, radio access network elements, NWDAF); one AI capability application module can correspond to one or more radio access network elements, and one AI capability application module can correspond to multiple service transmission channel user plane network elements.

[0246] (2) The AI ​​capability management module is used to manage and schedule intelligent computing models and computing power. When a new intelligent computing model is added to the mobile network, it interacts with the control plane network elements of the service transmission channel and the user plane network elements of the service transmission channel to deploy the intelligent computing model to the AI ​​capability application module. After the user accesses the mobile network, it addresses the AI ​​capability application module to provide intelligent computing services. When the corresponding intelligent computing model is not deployed locally, the AI ​​capability management module interacts with the control plane network elements of the service transmission channel and the AI ​​capability application module to complete model scheduling and updates; it cleans up intelligent computing models that have not been used for a long time in the AI ​​capability application module; and it periodically checks and updates the AI ​​capability management information. It can be logically co-located with existing network elements (such as the control plane network elements of the service transmission channel).

[0247] In this disclosure, one AI capability management module may correspond to one or more AI capability application modules, and one or more AI capability management modules may correspond to one service transmission channel control plane network element.

[0248] The AI ​​capability management module includes a smart computing service identifier, a smart computing model identifier, and information about the AI ​​capability application module that has deployed the smart computing model represented by the smart computing model identifier. The AI ​​capability application module information includes: the AI ​​capability application module identifier and / or the AI ​​capability application module address, as well as the regional information served by the AI ​​capability application module. The information contained in the AI ​​capability management module can be specifically described by the smart computing model registration table shown in Table (1) below.

[0249] Table (1) Intelligent Computing Model Registration Form (Example)

[0250]

[0251] The aforementioned intelligent computing service identifier can be S-NSSAI+DNN used in 5G networks or APN used in 4G networks, used to distinguish intelligent computing services from other service types (such as data services and voice services).

[0252] The intelligent computing model identifier is used to distinguish the uniqueness of intelligent computing models under the same intelligent computing service identifier. Intelligent computing models can be divided into: general intelligent computing models and user-customized contracted intelligent computing models. The same intelligent computing model can be stored in different AI capability application modules, and the same AI capability application module can store different intelligent computing models.

[0253] (3) The control plane network element of the service transmission channel is used to select the AI ​​capability management module according to the intelligent computing service identifier. It works with the AI ​​capability management module, the user plane network element of the service transmission channel, and the user data network element to complete the intelligent computing model scheduling service process.

[0254] (4) Service transmission channel user plane network element, used to jointly establish the service transmission channel for AI model scheduling service with AI capability application module according to the request of the service transmission channel control plane network element in the AI ​​model scheduling service process.

[0255] (5) User data network element, used for signing up for and storing smart computing service contract data. Smart computing service contract data includes: smart computing service identifier and smart computing model identifier.

[0256] (6) User PCC policy control network element, used for subscription and storage of intelligent computing-related policy control information. The relevant policy control information is used to provide users with a differentiated intelligent computing service experience.

[0257] The business process disclosed herein is explained below:

[0258] 1. Intelligent computing model is introduced into business processes

[0259] 1) User contracts for intelligent computing services

[0260] When a user signs up for a smart computing service at a business hall, the user's data network element signs up the user's smart computing service identifier and smart computing model identifier. At the same time, the user's PCC policy data network element signs up the user's smart computing service-related policy control information.

[0261] 2) Local deployment of the signing model

[0262] When the intelligent computing model that the user has signed up for is not in the local AI capability application module, it can be deployed in the following way:

[0263] 1. Upload the corresponding intelligent computing model locally to the AI ​​capability application module;

[0264] 2. If the intelligent computing model is in another region's AI capability application module, a copy of the intelligent computing model can be transferred from the management plane to the user plane's AI capability application module in the user's contracted location. The AI ​​capability application module initiates the AI ​​model scheduling business process, specifically the cross-regional intelligent computing model scheduling in the AI ​​model scheduling business process described in process 3. The user plane model transfer process is as follows: other region AI capability application module - other region business transmission channel user plane network element - contracted location business transmission channel user plane network element - contracted location AI capability application module.

[0265] 3) Model Update

[0266] When the intelligent computing model is iterated and updated, the AI ​​capability application module works together to complete the global intelligent computing model update.

[0267] 4) Model Registration

[0268] After the intelligent computing model is introduced, scheduled, or changed, the AI ​​capability management module registers the relevant information of the intelligent computing model.

[0269] 2. Business process for establishing user intelligent computing service channels

[0270] The establishment of a user's intelligent computing service session first requires interaction with the network. Specifically, the user plane intelligent computing service transmission channel is established through core network control plane signaling interaction. Subsequently, the user uses the established intelligent computing service channel to transmit intelligent computing service data.

[0271] The essence of establishing an intelligent computing service channel is that the core network selects the AI ​​capability application module to be used for this service based on user-related information and establishes a core network user plane service transmission channel. The establishment of the service transmission channel includes: the service transmission channel control plane network element assigning an IP address to the UE; the AI ​​capability application module assigning core network tunnel information for the user's intelligent computing session; and the radio access network element assigning access network tunnel information for the user's intelligent computing session. Furthermore, the UE needs to know the assigned IP address, the radio access network element needs to know the core network tunnel information, and the AI ​​capability application module needs to know the access network tunnel information. Simultaneously, the core network also needs to complete related processes such as authentication and authorization for the user's intelligent computing service, association of intelligent computing session management policies, and user data network element session registration.

[0272] The following steps describe the business process for establishing a smart computing service channel, based on the essence described above and the user's smart computing service subscription status, such as... Figure 2 As shown, it includes the following steps:

[0273] Step 0: The user equipment (UE) connects to the network and completes registration.

[0274] Specifically, when a UE accesses the network, the access and mobility management network elements in the network interact with relevant network elements to complete two-way authentication and location updates between the network and the UE, and the UE enters the registered state.

[0275] During the UE registration process, the access and mobility management network element obtains the user identifier, user location information, and user policy control network element identifier information.

[0276] The aforementioned user identifier can be SUPI / IMSI (Subscription Permanent Identifier / International Mobile Subscriber Identity) or GPSI / MSISDN (Generic Public Subscription Identifier / Mobile Subscriber ISDN Number). In the 5G core network, the user policy control network element is PCF, therefore the above user policy control network element identifier is PCF ID; in the 4G core network, the user policy control network element is PCRF, therefore the above user policy control network element identifier is PCRF ID.

[0277] The above process can specifically follow existing 5G standards, 4G standards, and next-generation mobile communication standards.

[0278] Step 1: The UE sends a smart computing service channel establishment request to the access and mobility management network element via the radio access network element; the access and mobility management network element determines the service transport channel control plane network element according to the smart computing service identifier, and sends the user identifier, user location information, user PCC policy control network element identifier, smart computing service identifier and smart computing model identifier to the determined service transport channel control plane network element.

[0279] In step 1, when a user needs to use intelligent computing services, the UE sends an intelligent computing service channel establishment request to the network.

[0280] The intelligent computing service channel establishment request includes an intelligent computing service identifier and an intelligent computing model identifier.

[0281] Specifically, the intelligent computing service identifier here can be represented by S-NSSAI+DNN in 5G networks and by APN in 4G networks.

[0282] The access and mobility management network element can determine the service transport channel control plane network element through any of the following three methods based on the intelligent computing service identifier:

[0283] Method 1: When the access and mobility management network element configures the intelligent computing service identifier to the matching list of the identifier and address of the service transport channel control plane network element locally, the access and mobility management network element can search the matching list for the identifier and address of the service transport channel control plane network element that matches the intelligent computing service identifier carried in the intelligent computing service channel establishment request.

[0284] Method 2: During or before the UE registration process in step S1, the service transport channel control plane network element sends a registration message to the network resource database (e.g., NRF) carrying its own intelligent computing service identifier and its own address information, thus completing the registration in the network resource database. At this time, the access and mobility management network element executes a service discovery request for the service transport channel control plane network element to the network resource database, the request containing the intelligent computing service identifier; the network resource database uses the intelligent computing service identifier contained in the discovery request to find the matching transport channel control plane network element identifier and address from the stored service transport channel control plane network element registration information; the network resource database returns a service discovery result carrying the matching transport channel control plane network element identifier and address to the access and mobility management network element, and then the access and mobility management network element can select the service transport channel control plane network element according to the transport channel control plane network element identifier and address in the service discovery result.

[0285] Method 3: The network resource database (e.g., DNS (Domain Name System)) pre-configures the intelligent computing service identifier to a matching list of identifiers and addresses of the service transport channel control plane network elements; the access and mobility management network element initiates a query request to the network resource database, which includes the intelligent computing service identifier; the network resource database uses the intelligent computing service identifier in the query request to find the identifier and address of the matching transport channel control plane network element in the configured matching list, and returns it to the access and mobility management network element in the query result; the access and mobility management network element then selects the service transport channel control plane network element based on the query result returned by the network resource database.

[0286] Step 2: The service transmission channel control plane network element interacts with the user PCC policy data network element based on the user identifier to obtain user session management subscription data. Using the user session management subscription data, it determines whether to accept or reject the UE's intelligent computing service channel establishment request. If accepted, proceed to Step 3; if rejected, the process ends.

[0287] Specifically, in step 2, the service transport channel control plane network element determines whether it has already stored the user session management subscription data corresponding to the user identifier locally. If so, it accepts or rejects the UE's intelligent computing service channel establishment request based on the UE's user session management subscription data. If not, it accesses the user data network element (e.g., UDM) to obtain the user session management subscription data and accepts or rejects the UE's intelligent computing service channel establishment request based on the UE's user session management subscription data. The service transport channel control plane network element accepts the UE's intelligent computing service notification establishment request when the user represented by the user identifier has subscribed to an intelligent computing session; otherwise, it rejects the UE's intelligent computing service channel establishment request.

[0288] It should be noted that if there is a scenario where AI capability application modules are selected based on policy information, then in step 2, the service transmission channel control plane network element will also determine whether it is necessary to select AI capability application modules based on the user session management subscription data. If so, it will use the user PCC policy control network element identifier to access the user PCC policy control network element, obtain policy information containing QoS (Quality of Service) information from the user PCC policy control network element, use the policy information to establish a smart computing session management policy association, associate the policy with smart computing session management, and after completing the selection of AI capability application modules and the allocation of user IP addresses, execute step 4 to modify the smart computing session management policy association, and also send the IP address allocated to the user to the user PCC policy control network element. If not, step 3 will be executed.

[0289] Here, the PCC policy control network element needs to record the user's IP address and other information (such as IP domain) to distinguish unique sessions. If a subsequent service triggers a policy, the PCC policy control network element will select the corresponding session and issue the policy based on the saved user IP address and other information.

[0290] The aforementioned user PCC policy control network element stores intelligent computing session-related policy information (including QoS information), intelligent computing policy control rule information, and intelligent computing policy control request triggering information.

[0291] Step 3: The service transport channel control plane network element assigns an IP address to the UE and selects the intelligent computing capability management module; it transmits the intelligent computing service identifier, intelligent computing model identifier, policy information (if the policy network element is accessed in Step 2), user session management subscription data, and user location information to the selected AI capability management module and requests the AI ​​capability management module to select an AI capability application module; the AI ​​capability management module selects an AI capability application module based on the intelligent computing service identifier, intelligent computing model identifier, user session management subscription data, policy information, and user location information, and sends the selected AI capability application module information to the service transport channel control plane network element.

[0292] In step 3, the network element of the service transmission channel control plane can be co-located with the AI ​​capability management module, or it can have the capability to address the AI ​​capability management module.

[0293] When the service transmission channel control plane network element and the AI ​​capability management module are co-located, in step 3, the service transmission channel control plane network element will transmit the intelligent computing service identifier, intelligent computing model identifier, user session management subscription data and user location information to the AI ​​capability management module.

[0294] When the service transmission channel control plane network element and the AI ​​capability management module are not co-located, the service transmission channel control plane network element addresses the AI ​​capability management module according to the intelligent computing service identifier, and transmits the intelligent computing service identifier, intelligent computing model identifier, user session management subscription data and user location information to the AI ​​capability management module.

[0295] The AI ​​capability management module selects AI capability application modules based on intelligent computing service identifiers, intelligent computing model identifiers, user session management subscription data, policy information, and user location information. Specifically, the AI ​​capability management module filters out AI capability application module information that matches the intelligent computing service identifier, intelligent computing model identifier, and user location information transmitted by the control plane network element of the service transmission channel from the stored intelligent computing model registration table. Then, based on the service load and capacity of the user session management subscription data and the filtered AI capability application module information, as well as policy information, the module further filters out the AI ​​capability application modules. The intelligent computing model registration table stores the correspondence between intelligent computing service identifiers, intelligent computing model identifiers, regional information, and AI capability application module information. The AI ​​capability application module information includes: AI application module identifier and / or AI application module address.

[0296] For example, if a user is in a residential community in Chaoyang District, Beijing, with the core network location identifier TAI1, and the requested intelligent computing service identifier is 1 and the intelligent computing model identifier is 1, the AI ​​capability management module will filter out AI capability application modules 1, 2, 3, 4, and 5 that meet the request. Simultaneously, considering the user's subscribed user session management data and the workload and capacity of each AI capability application module, the optimal AI capability application module will be selected. Finally, the identifier or address of the selected AI capability application module will be returned.

[0297] Furthermore, if the AI ​​capability management module finds no corresponding AI capability application module to choose from after the above screening, it needs to initiate the AI ​​model scheduling business process (see the AI ​​model scheduling business process in process 3) and complete the model management registration. Afterwards, the AI ​​capability management module will send the selected AI capability application module information to the business transmission channel control plane network element.

[0298] Step 4: If the user PCC policy data network element was not accessed and policy information was not obtained in Step 2, then in Step 4, the service transport channel control plane network element needs to execute the PCC process for intelligent computing session management policy control. This involves: using the user PCC policy control network element identifier to access the user PCC policy control network element, obtaining policy information, establishing an intelligent computing session management policy association, linking the policy with intelligent computing session management, and sending the policy information to the AI ​​capability management module. The policy information includes QoS information. If the policy data network element was accessed and policy information was obtained in Step 2, then in Step 4, the service transport channel control plane network element initiates session management modification to the user PCC policy data network element.

[0299] Step 5: The service transmission channel control plane network element sends user location information, intelligent computing service identifier, and intelligent computing model identifier to the AI ​​capability application module through the AI ​​capability management network element, requesting the AI ​​capability application module to allocate core network tunnel information; the AI ​​capability application module allocates core network tunnel information and reports the core network tunnel information to the service transmission channel control plane network element through the AI ​​capability management module.

[0300] The core network tunnel information contains the address of the interface tunnel used for a specific intelligent computing session, which consists of TEID (TunnelEndpoint Identifier) ​​and IP address.

[0301] Step 6: The service transport channel control plane network element returns the session identifier, intelligent computing service identifier, IP address allocated to the user, core network tunnel information of the AI ​​capability application module, session establishment acceptance information, and QoS information to the access and mobility management network element. Information exchange related to intelligent computing session establishment is completed between the access and mobility management network element, the radio access network, and the UE. The radio access network element allocates an access network tunnel for the intelligent computing session. The user terminal sends the accepted or rejected QoS list to the radio access network element, and the radio access network element sends the access network tunnel information and QoS list to the service transport channel control plane network element via the access and mobility management network element.

[0302] The access and mobility management network element stores the received information in the UE's associated intelligent computing session context.

[0303] Specifically, the information exchange related to the establishment of intelligent computing sessions includes: the access and mobility management network element forwards the intelligent computing session identifier, core network tunnel information, QoS information, and session establishment acceptance information to the radio access network element, and transmits the intelligent computing service identifier, the IP address assigned to the user, QoS information, and session establishment acceptance information as information in the intelligent computing service channel establishment response to the UE through the radio access network element.

[0304] The wireless access network element allocates an access network tunnel for the intelligent computing session.

[0305] Step 7: The service transmission channel control plane network element releases the corresponding QoS configuration file according to the QoS list rejected by the user terminal, and sends the access network tunnel information to the AI ​​capability application module through the AI ​​capability management module.

[0306] Step 8: The service transmission channel control plane network element initiates a registration process with the user's home user data network element, and the user's home user data network element saves the intelligent computing service transmission channel status information.

[0307] The registration message in the registration process includes: user identifier, intelligent computing service identifier, session identifier, and service transmission channel control plane network element identifier.

[0308] The user data network element to which the user belongs stores the intelligent computing service transmission channel status information, including: user identifier, established intelligent computing session identifier and its intelligent computing service identifier, and service transmission channel control plane network element identifier; at the same time, it stores it in the UE context in the subscription data corresponding to the user identifier and the service transmission channel control plane network element data.

[0309] Step 9: The service transport channel control plane network element, access and mobility management network element, radio access network element, and UE complete the subsequent processes for establishing service transport.

[0310] Subsequent business processes include: IPv6 address allocation, intelligent computing service transmission channel control plane network elements subscribing to UE mobility events from access and mobility management network elements, etc.

[0311] Steps 6-9 above are similar to the existing data service service transmission channel establishment process. The difference is that the user plane network element of the service transmission channel is replaced by the AI ​​capability application module in this proposal.

[0312] At this point, the control plane has completed the establishment of the service transmission channel. The user plane can then transmit intelligent computing service data through the user plane routing (UE - radio access network element - AI capability application module).

[0313] The disclosed solution adds edge computing AI capabilities to the mobile communication network architecture, making AI capabilities a part of the network capabilities, just like SMS, telephone, and Internet services, so that mobile users can access and use the intelligent computing model on demand.

[0314] 3. AI Model Scheduling Process

[0315] Step 0: After the user completes registration on the network, the intelligent computing service process is initiated. The visited AI capability management module does not match the corresponding AI capability application module address based on the intelligent computing service identifier (e.g., S-NSSAI+DNN (Single Network Slice Selection Assistance Information + Data Network Name) used in 5G networks, APN (Access Point Name) used in 4G networks), intelligent computing model identifier, and user location information (e.g., TAI).

[0316] Scenario 1: Intelligent Computing Model Scheduling within the Same Region. If the visited location AI capability management module can simultaneously match intelligent computing service identifiers (e.g., S-NSSAI+DNN used in 5G networks, APN used in 4G networks) and intelligent computing model identifiers, then scheduling of intelligent computing models for different AI application modules under the same AI capability management module is required. That is, the intelligent computing model requested by the user is within the AI ​​capability application modules managed by the visited location AI capability management module, but not within the AI ​​capability application modules of the user's visited location.

[0317] For example: Suppose a user has subscribed to Intelligent Computing Service 1 with Intelligent Computing Model 1. Intelligent Computing Model 1 of Intelligent Computing Service 1 is deployed in the Haidian District AI Capability Application Module, but not in the Chaoyang District AI Capability Application Module. Both the Haidian and Chaoyang District AI Capability Application Modules are managed by the Beijing AI Capability Management Module. When a user accesses the mobile communication network in Chaoyang District, Beijing, Chaoyang District is the user's visited location. When applying to use the subscribed Intelligent Computing Service with Intelligent Computing Model 1, since the Chaoyang District AI Capability Application Module has not deployed Intelligent Computing Model 1, the Beijing AI Capability Management Module initiates a model scheduling process, rescheduling Intelligent Computing Service 1's Intelligent Computing Model 1 from the Haidian District AI Capability Application Module to the Chaoyang District AI Capability Application Module. Subsequently, the AI ​​capability application module in Chaoyang District deployed the intelligent computing model 1 of the intelligent computing service 1. When the user accesses the mobile communication network in Chaoyang District, Beijing again to use the intelligent computing model 1, if the model has not been cleared, it can be directly matched to the intelligent computing model 1 of the intelligent computing service 1 in the AI ​​capability application module in Chaoyang District, without having to perform AI scheduling services again.

[0318] Scenario 2: Cross-regional intelligent computing model scheduling. If the AI ​​capability management module at the visited location does not simultaneously match the intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks, APN used in 4G networks) and the intelligent computing model identifier, then scheduling of intelligent computing models across AI capability management modules and across AI application modules needs to be completed. That is, the intelligent computing model requested by the user is in the AI ​​capability application modules managed by the AI ​​capability management modules in different regions, but not in the AI ​​capability application modules of the user's visited location.

[0319] For example: A user accesses the mobile communication network in Chaoyang District, Beijing, and applies to use the intelligent computing model 1 of the contracted intelligent computing service. However, the intelligent computing model 1 is not deployed in the Chaoyang District AI capability application module. Instead, it is deployed in the Zhengzhou AI capability application module managed by the Henan AI capability management module. Therefore, the Beijing AI capability management module initiates a model scheduling process to schedule the intelligent computing model 1 from the Zhengzhou AI capability application module to the Chaoyang District AI capability application module.

[0320] For scenario one, execute steps 1, 2.a, 3.a, 4.a, 5, and 6, as follows: Figure 4 and Figure 5 As shown;

[0321] For scenario two, execute steps 1, 2.b, 3.b, 4.b, 5, and 6, as follows: Figure 6 , Figure 7 and Figure 8 As shown.

[0322] Figure 5 The example shown is a diagram illustrating the interaction between network elements in the same area scheduling service using an AI model; Figure 6 The example illustrates the interaction diagram when the network elements of the service transport channel control plane in the user's visited area and the network elements of the service transport channel control plane in the model's area are different network elements. Figure 7 The example illustrates the interaction diagram when the service transport channel control plane network element in the user's visited area and the service transport channel control plane network element in the model's area are the same network element.

[0323] It should be noted that in the scheme disclosed herein, the initiation of the AI ​​model scheduling process is not limited to the triggering of step 0 above. For example, if the user makes an appointment for the visit in advance or if the user's visit location is known in advance based on the relevant information provided by the user, and it is determined that there is no intelligent computing model contracted by the user in the visit location, the scheduling of the AI ​​model from the model's location to the visit area can be triggered. Based on the relevant statistical data of the intelligent computing model, when it is necessary to promote a certain intelligent computing model that meets the conditions from its location to the visit location, the scheduling of the AI ​​model from the model's location to the visit area can also be triggered.

[0324] The execution of the scheduling requires the visited location AI capability management module to receive location information, intelligent computing service identifier, and intelligent computing model identifier. Using the stored intelligent computing model registration table, if it is determined that no AI capability application module information matches the intelligent computing service identifier, intelligent computing model identifier, and location information, the module can initiate the corresponding AI model scheduling process based on the specific matching situation. The following steps are explained based on the premise that the received location information is user location information.

[0325] Step 1: The visited AI capability management module initiates the AI ​​model scheduling business process to the user's visited AI capability application module and requests the visited AI capability application module to allocate core network tunnel information (including the address information of the visited AI capability application module). The visited AI capability application module returns the first core network tunnel information to the visited AI capability management module, which means that the visited AI capability application module allocates core network tunnel information.

[0326] Step 2.a: The visited AI capability management module initiates an AI model scheduling service process to the AI ​​capability application module that has deployed the intelligent computing model, i.e., the deployment location AI capability application module, and requests the deployment location AI capability application module to allocate core network tunnel information (including the address information of the deployment location AI capability application module), i.e., the fourth core network tunnel information; the deployment location AI capability application module returns the fourth core network tunnel information to the visited AI capability management module, i.e., the core network tunnel information of the deployment location AI capability application module; the visited AI capability management module initiates an AI model scheduling service request to the control plane network element of the visited service transmission channel, the request carrying the core network tunnel information of the user's visited location AI capability application module (including the address information of the AI ​​capability application module), the core network tunnel information of the AI ​​capability application module that has deployed the intelligent computing model (including the address information of the AI ​​capability application module), the area information of the AI ​​capability application module that has deployed the intelligent computing model (e.g., TAI List), and the user's location information (e.g., TAI (Tracking Area Identity)).

[0327] It should be noted that the user visited location is the same as the visited location, the intelligent computing deployment location is the same as the location of the intelligent computing model, the user plane network element of the service transmission channel of the user visited location is the same as the user plane network element of the service transmission channel of the visited location, and the names of other network elements are similar, so they will not be repeated here.

[0328] Step 3.a: The visited service transport channel control plane network element addresses the visited service transport channel user plane network element based on the user's location information and sends a request to establish a user plane tunnel. This request carries the core network tunnel information of the visited AI capability application module (including the address information of the AI ​​capability application module). The visited service transport channel user plane network element returns its local core network tunnel information (including the address information of the service transport channel user plane network element), which is the second core network tunnel information. The visited service transport channel control plane network element addresses the intelligent computing deployment location service transport channel user plane network element based on the area information (e.g., TAI List) of the AI ​​capability application module deployed with this intelligent computing model and sends a request to establish a user plane tunnel. This information includes the core network tunnel information of the AI ​​capability application module deployed with this intelligent computing model (including the address information of the AI ​​capability application module), which is the fourth core network information. The intelligent computing deployment location service transport channel user plane network element returns its local core network tunnel information (including the address information of the service transport channel user plane network element), which is the third core network tunnel information.

[0329] Figure 3 The intra-region scheduling process is shown in Region A. When the user plane network element of the service transport channel in the user's visited location and the user plane network element of the service transport channel in the intelligent computing deployment location are the same network element, the established intelligent computing model schedules the user plane route as follows: Figure 3 As shown in process ①; when the user plane network element of the service transport channel at the user's visited location and the user plane network element of the service transport channel at the intelligent computing deployment location are different network elements, the established intelligent computing model schedules the user plane routing as follows: Figure 3 As shown in process ②.

[0330] In addition, in specific implementation, the control plane network element of the visited service transport channel can use the location information carried in the service request to schedule the user plane network element of the visited service transport channel using the AI ​​model, and use the area information to address the user plane network element of the deployed service transport channel. When it is determined that the user plane network element of the visited service transport channel and the user plane network element of the deployed service transport channel are the same network element, a user plane tunnel establishment request carrying the first core network tunnel information and the fourth core network tunnel information is sent to the user plane network element of the visited service transport channel; the user plane network element of the visited service transport channel sends the second core network tunnel information to the control plane network element of the visited service transport channel.

[0331] When it is determined that the user plane network element of the visited service transport channel and the user plane network element of the deployment service transport channel are different network elements, a user plane tunnel establishment request carrying the first core network tunnel information is sent to the user plane network element of the visited service transport channel, and a user plane tunnel establishment request carrying the fourth core network tunnel information is sent to the user plane network element of the deployment service transport channel; the user plane network element of the visited service transport channel sends the second core network tunnel information to the control plane network element of the visited service transport channel.

[0332] Step 4.a: The visited service transport channel control plane network element sends the core network tunnel information of the user plane network element of the visited service transport channel (including the address information of the user plane network element of the service transport channel) to the user's visited AI capability application module through the visited AI capability management network element. It also sends the core network tunnel information of the user plane network element of the visited service transport channel (including the address information of the user plane network element of the service transport channel) to the intelligent computing deployment service transport channel user plane network element. Furthermore, it sends the core network tunnel information of the intelligent computing deployment service transport channel user plane network element (including the address information of the user plane network element of the service transport channel) to the AI ​​capability application module that has deployed the intelligent computing model through the AI ​​capability management network element. Finally, it sends the core network tunnel information of the intelligent computing deployment service transport channel user plane network element (including the address information of the user plane network element of the service transport channel) to the user's visited service transport channel user plane network element.

[0333] If the user plane network element of the service transport channel at the user's visited location and the user plane network element of the service transport channel at the intelligent computing deployment location are the same network element, then this step does not require information exchange between the user plane network element of the service transport channel at the user's visited location and the user plane network element of the service transport channel at the intelligent computing deployment location.

[0334] User plane routing ① (e.g.) Figure 3 Process ①): User Visit Location AI Capability Application Module - User Visit Location Service Transmission Channel User Plane Network Element (Intelligent Computing Deployment Location Service Transmission Channel User Plane Network Element) - Intelligent Computing Deployment AI Capability Application Module.

[0335] User plane routing ② (e.g.) Figure 3 Process ②): User Visit Location AI Capability Application Module - User Visit Location Service Transmission Channel User Plane Network Element - Intelligent Computing Deployment Location Service Transmission Channel User Plane Network Element - Intelligent Computing Deployment AI Capability Application Module.

[0336] Step 2.b: The visited AI capability management module initiates an AI model scheduling service request to the control plane network element of the visited service transport channel. The message includes: core network tunnel information of the user's visited AI capability application module (including the address information of the AI ​​capability application module) and user location information (e.g., TAI). The visited service transport channel control plane network element, based on the user location information, addresses the user plane network element of the visited service transport channel to send a request to establish a user plane tunnel. This request includes: core network tunnel information of the user's visited AI capability application module (including the address information of the AI ​​capability application module). The visited service transport channel control plane network element receives the core network tunnel information (including the address information of the service transport channel user plane network element) fed back by the user's visited service transport channel user plane network element and synchronizes this information to the visited AI capability management module. The visited AI capability management module then sends the core network tunnel information (including the address information of the service transport channel user plane network element) fed back by the user's visited service transport channel user plane network element to the user's visited AI capability application module.

[0337] Step 3.b: The visited AI capability management module addresses other regional AI capability management modules based on the intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks, APN used in 4G networks) and the intelligent computing model identifier (see Process 4. AI Capability Management Module Addressing Process). The visited AI capability management module sends an AI model scheduling service request to the addressed deployment site AI capability management module. The request includes: the intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks, APN used in 4G networks), the intelligent computing model identifier, and the core network tunnel information of the user plane network element of the service transport channel in the visited location (including the address information of the user plane network element of the service transport channel).

[0338] Specifically, sending an AI model scheduling service request to the AI ​​capability management module at the addressed location includes: the AI ​​capability management module at the visited location sends the AI ​​model scheduling service request to the AI ​​capability management module at the deployment location via the control plane network element of the service transmission channel at the visited location and the control plane network element of the service transmission channel at the deployment location in sequence.

[0339] Step 4.b: After receiving the AI ​​model scheduling service request, the AI ​​capability management module at the intelligent computing deployment site initiates the AI ​​model scheduling service process to the AI ​​capability application module deployed by the intelligent computing model based on the intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks, APN used in 4G networks) and the intelligent computing model identifier. It also requests the AI ​​capability application module to allocate core network tunnel information (including the address information of the AI ​​capability application module). The AI ​​capability application module returns the allocated core network tunnel information (including the address information of the AI ​​capability application module). The AI ​​capability management module at the intelligent computing deployment site then initiates the AI ​​model scheduling service request to the control plane network element of the service transport channel at the intelligent computing deployment site. The message includes: the core network tunnel information of the AI ​​capability application module at the deployment site (including the address information of the AI ​​capability application module), the area information of the AI ​​capability application module at the deployment site (e.g., TAIList), and the core network tunnel information of the user plane network element of the service transport channel at the user's visited location.

[0340] The control plane network element of the intelligent computing deployment site's service transport channel addresses the user plane network element of the service transport channel based on the deployment site's AI capability application module area information (e.g., TAI List), and initiates a user plane tunnel establishment request to the user plane network element of the service transport channel. This request includes: the core network tunnel information of the deployment site's AI capability application module (including the address information of the AI ​​capability application module) and the core network tunnel information of the user plane network element of the service transport channel visited by the user. The user plane network element of the deployment site's service transport channel returns its core network tunnel information (including the address information of the AI ​​capability application module); the control plane network element of the intelligent computing deployment site's service transport channel returns its core network tunnel information (including the address information of the AI ​​capability application module) to the AI ​​capability management module of the intelligent computing deployment site.

[0341] The AI ​​capability management module at the deployment site returns the AI ​​model scheduling service request establishment result to the AI ​​capability management module at the visited site (including: core network tunnel information of the user plane network element of the service transmission channel at the deployment site); the AI ​​capability management module at the visited site returns the core network tunnel information of the user plane network element of the service transmission channel at the deployment site to the control plane network element of the service transmission channel at the visited site; the control plane network element of the service transmission channel at the visited site returns the core network tunnel information of the user plane network element of the service transmission channel at the deployed site to the user plane network element of the service transmission channel at the visited site.

[0342] Specifically, the AI ​​capability management module at the intelligent computing deployment site returns the AI ​​model scheduling business request establishment result to the visited site AI capability management module, including:

[0343] The AI ​​capability management module at the intelligent computing deployment site returns the AI ​​model scheduling service request establishment result to the AI ​​capability management module at the visited site via the control plane network element of the service transmission channel at the visited site and the control plane network element of the service transmission channel at the deployment site.

[0344] Figure 3 The text shows the cross-regional scheduling route between region A (visited location) and region B (deployment location), which is user plane route ③: Visited location AI capability application module - Visited location service transport channel user plane network element - Deployment location service transport channel user plane network element - Deployment location AI capability application module.

[0345] Step 5: The AI ​​capability application module at the intelligent computing deployment site selects the corresponding intelligent computing model based on the intelligent computing model identifier and intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks and APN used in 4G networks), and sends a copy of the model to the AI ​​capability application module at the user's visited site through the user plane service transmission channel; the AI ​​capability application module at the user's visited site sends a model delivery completion message to the AI ​​capability management module at the user's visited site (intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks and APN used in 4G networks), intelligent computing model identifier, area information (e.g., TAI List), AI capability application module identifier and / or address information).

[0346] Step 6: The AI ​​capability management module at the user's visited location completes the registration of model information (intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks, APN used in 4G networks), intelligent computing model identifier, regional information (e.g., TAI List), AI capability application module identifier and / or address information).

[0347] In the above AI model scheduling service, the essence is to use the AI ​​capability management module and the transmission channel control plane network element to establish the user plane channel between the visited AI capability application module, the visited service transmission channel user plane network element, the deployed service transmission channel user plane network element and the deployed AI capability application module. Each network element allocates its own core network tunnel information for model scheduling, and also needs to obtain the core network tunnel information of adjacent network elements through interaction with other network elements, as shown in Table (2) below.

[0348] Table (2) Tunnel Information

[0349]

[0350] 4. AI Capability Management Module Addressing Business Process

[0351] This can be achieved in the following ways:

[0352] Method 1: Configure the global intelligent computing model registration information table locally

[0353] When the intelligent computing model registration information changes, the AI ​​capability management module notifies other AI capability management modules globally of the local intelligent computing model registration information (or the information of this change). Each AI capability management module maintains a global intelligent computing model registration information table, which includes: AI capability management module identifier, AI capability management module address, intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks, APN used in 4G networks), intelligent computing model identifier, AI capability application module identifier, and regional information (e.g., TAI List).

[0354] Method 2: Service Registration and Service Discovery

[0355] When the intelligent computing model registration information changes, the AI ​​capability management module completes registration with the network resource database (e.g., NRF). The registration information includes: AI capability management module identifier, AI capability management module address, intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks, APN used in 4G networks), intelligent computing model identifier, AI capability application module identifier, and regional information (e.g., TAI List). The AI ​​capability management module performs AI capability management module service discovery with the network resource database (e.g., NRF). The request message includes the intelligent computing service identifier (e.g., S-NSSAI+DNN used in 5G networks, APN used in 4G networks) and the intelligent computing model identifier. Based on the AI ​​capability management module service discovery results returned by the network resource database (e.g., NRF), the AI ​​capability management module is selected.

[0356] In summary, the main innovation of this disclosure lies in:

[0357] 1) An edge intelligent computing network architecture for mobile communication network users is proposed, along with methods for establishing service transmission channels and scheduling intelligent computing services. Based on the existing 5G core network (5GC) and 4G core network (EPC) network architectures, an AI capability application module and an AI capability management module are added. The functions of the user service transmission channel control network element and the user plane network element of the user service transmission channel are updated. The service / signaling process for introducing intelligent computing models into mobile communication networks, establishing intelligent computing service data transmission channels for mobile communication users (UEs), and completing intelligent computing model scheduling is defined, and modifications are made to the interfaces between the aforementioned network elements.

[0358] 2) Added AI capability application module. It carries intelligent computing power and provides users with a variety of intelligent computing models, such as: general intelligent computing model and user-customized intelligent computing model (which can be divided into ToC user-initiated contract and ToB user-initiated contract); during the establishment of intelligent computing service transmission channel, according to the request of AI capability management module, it creates core network tunnel, which serves as the tunnel start point or end point to complete the corresponding business process;

[0359] 3) A new AI capability management module has been added. This module manages and schedules models and computing power. When a new intelligent computing model is added to the mobile network, it interacts with the service transmission channel control network element and the service transmission channel user plane network element to deploy the intelligent computing model to the AI ​​capability application module. After a user accesses the mobile network, it addresses the AI ​​capability application module to provide intelligent computing services. When the corresponding intelligent computing model is not deployed locally, it interacts with the service transmission channel control network element and the AI ​​capability application module to complete model scheduling and updates. It also periodically checks and updates AI capability management information.

[0360] 4) The service transmission channel control network element selects the AI ​​capability management module according to the intelligent computing service identifier, and works with the AI ​​capability management module, the service transmission channel user plane network element, the user data network element, etc. to complete the intelligent computing model scheduling service process;

[0361] 5) In the AI ​​model scheduling service process, the user plane network element of the service transmission channel, together with the AI ​​capability application module, establishes the AI ​​model scheduling service transmission channel according to the request of the service transmission channel control network element.

[0362] 6) New interfaces: interfaces between the AI ​​capability application module and the wireless access network element, interfaces between the AI ​​capability application module and the user plane network element of the service transmission channel, interfaces between the AI ​​capability application module and the AI ​​capability management module, interfaces between the AI ​​capability management module and the control network element of the service transmission channel, and interfaces between cross-regional AI capability management modules.

[0363] Based on the above-described intelligent computing service channel establishment method, this disclosure also provides an intelligent computing service channel establishment system corresponding to the above-described intelligent computing service channel establishment method, the system as follows: Figure 1 As shown, it includes: access and mobility management network elements, service transport channel control plane network elements, AI capability management module, AI capability application module, and radio access network elements; among which:

[0364] The access and mobility management network element is used to receive a smart computing service channel establishment request sent by the radio access network element after the user terminal (UE) accesses the network and completes registration. The request carries a smart computing service identifier and a smart computing model identifier. Based on the smart computing service identifier, the element determines the service transport channel control plane network element and sends the user location information, smart computing service identifier, and smart computing model identifier to the determined service transport channel control plane network element. The element also forwards the smart computing session identifier, core network tunnel information, and session establishment acceptance information to the radio access network element. The element transmits the smart computing service identifier, the IP address assigned to the user, and the session establishment acceptance information as information carried in the smart computing service channel establishment response to the UE through the radio access network element.

[0365] The service transport channel control plane network element is used to send user location information, intelligent computing service identifier, and intelligent computing model identifier to the AI ​​capability management module, and to allocate an IP address to the UE; and to send user location information, intelligent computing service identifier, and intelligent computing model identifier to the AI ​​capability application module pointed to by the AI ​​capability application module information, requesting the AI ​​capability application module to allocate core network tunnel information; and to return intelligent computing session identifier, intelligent computing service identifier, IP address allocated to the user, and core network tunnel information to the access and mobility management network element.

[0366] The AI ​​capability management module is used to determine the AI ​​capability application module information based on the intelligent computing service identifier, intelligent computing model identifier, and user location information, and to feed it back to the network element of the service transmission channel control plane.

[0367] The AI ​​capability application module is used to allocate core network tunnel information and feed back core network tunnel information to the control plane network elements of the service transmission channel.

[0368] The wireless access network element is used to forward the intelligent computing service channel establishment request sent by the user equipment (UE) to the access and mobility management network element, allocate access network tunnel information for the intelligent computing session; forward and receive the intelligent computing service channel establishment response sent by the access and mobility management network element to the UE, and send the access network tunnel information to the AI ​​capability application module through the access and mobility management network element, the service transport channel control plane network element and the AI ​​capability management module.

[0369] Furthermore, the access and mobility management network element is specifically used to determine the service transport channel control plane network element in any of the following three ways: Method 1: The access and mobility management network element searches a locally configured matching list for the identifier and address of the service transport channel control plane network element that matches the intelligent computing service identifier. The network element pointed to by the found identifier and address of the service transport channel control plane network element is taken as the service transport channel control plane network element. The matching list contains the matching relationship between the intelligent computing service identifier and the identifier and address of the service transport channel control plane network element. Method 2: The access and mobility management network element executes a service discovery request for the service transport channel control plane network element to the network resource database. The request contains the intelligent computing service identifier. The access and mobility management network element receives the service discovery result returned by the network resource database. The results include the transport channel control plane network element identifier and address that match the intelligent computing service identifier; the network element pointed to by the discovery result is taken as the service transport channel control plane network element; wherein, the service transport channel control plane network element registers the intelligent computing service identifier it is responsible for and its own address information in the network resource database; Method 3: The access and mobility management network element initiates a query request to the network resource database, wherein the query request includes the intelligent computing service identifier; receives the query response returned by the network resource database, wherein the query response includes the transport channel control plane network element identifier and address that match the intelligent computing service identifier; the network element pointed to by the query response is taken as the service transport channel control plane network element; wherein, the network resource database pre-configures a matching list of the identifier and address of the intelligent computing service identifier to the service transport channel control plane network element.

[0370] Furthermore, the AI ​​capability management module is specifically used to filter out AI capability application module information that matches the intelligent computing service identifier, intelligent computing model identifier, and user location information transmitted by the control plane network element of the service transmission channel from the stored intelligent computing model registration table; based on the service load and capacity of the user session management subscription data and the filtered AI capability application module information, it further filters out AI capability application modules. The intelligent computing model registration table stores the correspondence between intelligent computing service identifier, intelligent computing model identifier, regional information, and AI capability application module information. The AI ​​capability application module information includes: AI application module identifier and / or AI application module address.

[0371] Furthermore, the access and mobility management network element is also used to send the user identifier to the control plane network element of the designated service transport channel;

[0372] The service transmission channel control plane network element is also used to obtain user session management subscription data using the user identifier before sending user location information, intelligent computing service identifier and intelligent computing model identifier to the AI ​​capability management module and allocating an IP address to the UE, determine that the user represented by the user identifier has subscribed to an intelligent computing session, and accept the UE's intelligent computing service announcement establishment request.

[0373] Furthermore, the access and mobility management network element is also used to send the user PCC policy control network element identifier to the designated service transport channel control plane network element;

[0374] The service transport channel control plane network element is also used to determine, based on user session management subscription data, whether to select an AI capability application module according to policy information before sending intelligent user location information, intelligent computing service identifier, and intelligent computing model identifier to the AI ​​capability management module and allocating an IP address for the intelligent computing service to the UE; access the user PCC policy control network element using the user PCC policy control network element identifier to obtain the user's policy information, and establish an intelligent computing session management policy association using the policy information; and after receiving the AI ​​capability application module information, execute the intelligent computing session management policy association modification and send the IP address allocated to the user to the user PCC policy control network element.

[0375] Furthermore, the access and mobility management network element is also used to send the user PCC policy control network element identifier to the designated service transport channel control plane network element;

[0376] The service transmission channel control plane network element is also used to perform intelligent computing session management policy association modification after receiving information from the AI ​​capability application module, and to send the IP address assigned to the user to the user's PCC policy control network element.

[0377] Furthermore, the control plane network element of the service transmission channel is specifically used to transmit the intelligent computing service identifier, intelligent computing model identifier, user session management subscription data, and user location information to the AI ​​capability management module when it is co-located with the AI ​​capability management module; when it is not co-located with the AI ​​capability management module, it addresses the AI ​​capability management module according to the intelligent computing service identifier and transmits the intelligent computing service identifier, intelligent computing model identifier, user session management subscription data, and user location information to the AI ​​capability management module.

[0378] Furthermore, the strategy information includes QoS information;

[0379] The service transport channel control plane network element is also used to return QoS information to the access and mobility management network element;

[0380] The access and mobility management network element is also used to transmit QoS information to the UE through the radio access network element;

[0381] The wireless access network element is also used to receive the QoS list of acceptance or rejection sent by the user terminal after allocating access network tunnel information for the intelligent computing session; and to send the QoS list of acceptance or rejection and the access network tunnel information to the service transport channel control plane element via the access and mobility management network element.

[0382] The service transmission channel control plane network element is also used to release the corresponding QoS configuration file according to the QoS list rejected by the user terminal, and to send access network tunnel information to the AI ​​capability application module through the AI ​​capability management module.

[0383] This disclosure also provides a scheduling method based on the above-described AI model, and embodiments of this disclosure further provide an apparatus corresponding to the above-described AI model scheduling method, as follows:

[0384] 1) A visited site AI capability management module, comprising:

[0385] The first receiving module is used to receive location information, intelligent computing service identifier, and intelligent computing model identifier;

[0386] The first sending module is used to utilize the stored intelligent computing model registration table to perform intra-region scheduling when it is determined that there is an AI capability application module that matches both the intelligent computing service identifier and the intelligent computing model identifier, and the area information corresponding to the matching AI capability application module does not match the received location information. The module then initiates an AI model scheduling service request to the visited AI capability application module and requests the allocation of core network tunnel information on the visited AI capability application module side. The intelligent computing model registration table stores the correspondence between the intelligent computing service identifier, the intelligent computing model identifier, the area information, and the AI ​​capability application module information.

[0387] The second receiving module is used to receive the first core network tunnel information returned by the visited AI capability application module.

[0388] The second sending module is used to initiate an AI model scheduling service request to the AI ​​capability application module at the deployment location pointed to by the matching AI capability application module information, requesting the allocation of core network tunnel information on the side of the AI ​​capability application module at the deployment location, and the request carries the intelligent computing service identifier and intelligent computing model identifier.

[0389] The third receiving module is used to receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site;

[0390] The third sending module is used to initiate an AI model scheduling service request to the control plane network element of the visited service transmission channel. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the AI ​​capability application module at the deployment location.

[0391] When the forwarding module determines that the user plane network element of the visited service transport channel and the user plane network element of the deployment service transport channel are the same network element, it forwards the second core network tunnel information sent by the control plane network element of the visited service transport channel to the AI ​​capability application module of the visited location and the AI ​​capability application module of the deployment location. The second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transport channel.

[0392] 2) Provide a visited site AI capability application module, including:

[0393] The first receiving module is used to receive AI model scheduling service requests initiated by the AI ​​capability management module of the visited location.

[0394] The allocation module is used to allocate tunnel information in the first core network.

[0395] The sending module is used to return data to the AI ​​capability management module of the visited location;

[0396] The second receiving module is used to receive the second core network tunnel information sent by the visited AI capability management module; wherein the second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transmission channel.

[0397] The third receiving module is used to receive copies of the intelligent computing model sent by the AI ​​capability application module at the deployment site.

[0398] 3) Provide a control plane network element for a visited service transport channel, which, when performing intra-area scheduling, includes:

[0399] The first receiving module is used to receive an AI model scheduling service request initiated by the visited AI capability management module. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the deployed AI capability application module. The first core network tunnel information refers to the core network tunnel information of the visited AI application module, and the fourth core network tunnel information refers to the core network tunnel information of the deployed AI application module.

[0400] The addressing module is used to address the user plane network elements of the service transmission channel in the visited location using the location information carried in the service request of the AI ​​model, and to address the user plane network elements of the service transmission channel in the deployment location using the area information.

[0401] The first sending module is used to send a request to establish a user plane tunnel to the user plane network element of the service transport channel at the visited location, carrying the first core network tunnel information and the fourth core network tunnel information, when it is determined that the user plane network element of the service transport channel at the visited location and the user plane network element of the service transport channel at the deployed location are the same network element.

[0402] The second receiving module is used to receive the second core network tunnel information sent by the user plane network element of the visited service transmission channel.

[0403] The second sending module is used to send the second core network tunnel information to the visited AI capability application module and the deployment site AI capability application module respectively via the visited site AI capability management module.

[0404] 4) A visited service transport channel control plane network element, which, when performing cross-regional scheduling, includes:

[0405] The third receiving module is used to receive AI model scheduling service requests initiated by the visited AI capability management module. The requests carry the first core network tunnel information and location information. The first core network tunnel information refers to the core network tunnel information of the visited AI application module.

[0406] The addressing module is used to address the user plane network element of the visited service transmission channel based on the location information;

[0407] The third sending module is used to send a request to establish a user plane tunnel to the user plane network element of the visited service transport channel. The request carries the first core network tunnel information.

[0408] The fourth receiving module is used to receive the second core network tunnel information fed back by the user plane network element of the user visited service transmission channel, and transmit it to the visited AI capability application module via the visited AI capability management module.

[0409] The fifth receiving module is used to receive the third core network tunnel information returned by the visited AI capability management module. The third core network tunnel information is the core network tunnel information of the user plane network element of the service transmission channel at the deployment site.

[0410] The fourth sending module is used to return the third core network tunnel information to the user plane network element of the visited service transmission channel.

[0411] 5) Provide a deployment location AI capability application module, which includes the following features when performing intra-region scheduling:

[0412] The first receiving module is used to receive AI model scheduling service requests initiated by the visited AI capability management module, which allocates and deploys AI capability application module core network tunnel information. The requests carry intelligent computing service identifier and intelligent computing model identifier.

[0413] The first allocation module is used to allocate tunnel information for the fourth core network.

[0414] The first sending module is used to return the fourth core network tunnel information to the visited AI capability management module.

[0415] The second receiving module is used to receive the second core network tunnel information sent by the visited AI capability management module when the visited service transport channel control plane network element determines that the visited service transport channel user plane network element and the deployed service transport channel user plane network element are the same network element. The second core network tunnel information is the core network tunnel information of the visited service transport channel user plane network element.

[0416] The selection module is used to select an intelligent computing model using intelligent computing business identifiers and intelligent computing model identifiers;

[0417] The second sending module transmits the selected intelligent computing model copy to the visited AI capability application module.

[0418] 6) Provide a deployment location AI capability application module, which includes the following features when performing cross-regional scheduling:

[0419] The third receiving module is used to receive the AI ​​capability management module at the deployment site from the business process of requesting the AI ​​capability application module at the deployment site to allocate core network tunnel information AI model scheduling services.

[0420] The second allocation module is used to allocate the fourth core network tunnel information;

[0421] The third sending module is used to return the fourth core network tunnel information to the AI ​​capability management module at the deployment site;

[0422] The fourth sending module is used to transmit the selected intelligent computing model copy to the visited AI capability application module through the established user plane intelligent computing business model transmission channel.

[0423] 7) A visited service transport channel user plane network element, when performing intra-area scheduling, includes:

[0424] The first receiving module is used to receive the request to establish a user plane tunnel sent by the control plane network element of the visited service transmission channel. The request carries the first core network tunnel information and the fourth core network tunnel information. The first core network tunnel information refers to the core network tunnel information of the visited AI application module end, and the fourth core network tunnel information refers to the core network tunnel information of the deployed AI application module end.

[0425] The first allocation module is used to allocate the second core network tunnel information;

[0426] The first sending module is used to send the second core network tunnel information to the control plane network element of the visited service transmission channel.

[0427] 8) A visited service transport channel user plane network element, when performing cross-regional scheduling, includes:

[0428] The second receiving module is used to receive a request to establish a user plane tunnel sent by the control plane network element of the visited service transmission channel. The request carries the first core network tunnel information, which refers to the core network tunnel information of the visited AI application module.

[0429] The second allocation module is used to allocate the second core network tunnel information;

[0430] The second sending module sends the second core network tunnel information to the control plane network element of the visited service transmission channel.

[0431] The third receiving module is used to receive the third core network tunnel information sent by the control plane network element of the visited service transport channel. The third core network tunnel information refers to the core network tunnel information of the user plane network element of the deployed service transport channel.

[0432] The third sending module forwards the copy of the intelligent computing model sent by the user plane network element of the service transmission channel at the deployment site to the visited AI capability application module.

[0433] 9) Provide a user plane network element for a deployed service transport channel, which, when performing intra-area scheduling, includes:

[0434] The first receiving module is used to receive the request to establish a user plane tunnel sent by the control plane network element of the visited service transmission channel. The request carries the fourth core network tunnel information, which refers to the core network tunnel information of the AI ​​capability application module at the deployment site.

[0435] The allocation module is used to allocate third core network tunnel information;

[0436] The first sending module is used to send the third core network tunnel information to the control plane network element of the visited service transmission channel;

[0437] The second receiving module is used to receive the second core network tunnel information sent by the control plane network element of the visited service transmission channel, wherein the second core network tunnel information refers to the core network tunnel information at the user plane network element end of the visited service transmission channel.

[0438] The second sending module is used to forward the copy of the intelligent computing model sent by the AI ​​capability application module at the deployment site to the AI ​​capability application module at the visited site.

[0439] 10) Provide a deployment location service transport channel control plane network element that, when performing cross-regional scheduling, includes:

[0440] The first receiving module is used to receive the AI ​​model scheduling service request sent by the AI ​​capability management module at the deployment site. The request carries the fourth core network tunnel information, the second core network tunnel information, and the area information that the AI ​​capability application module at the deployment site is responsible for. Among them, the second core network tunnel information is the core network tunnel information of the user plane network element end of the visited service transmission channel, and the fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site.

[0441] The addressing module is used to address the user plane network elements of the service transmission channel at the deployment location based on the area information of the AI ​​capability application module at the deployment location.

[0442] The first sending module is used to initiate a request to establish a user plane tunnel to the user plane network element of the service transmission channel at the deployment site. The request carries the fourth core network tunnel information and the second core network tunnel information.

[0443] The second receiving module is used to receive the third core network tunnel information returned by the user plane network element of the service transmission channel at the deployment site;

[0444] The second sending module is used to return the third core network tunnel information to the AI ​​capability management module at the deployment site.

[0445] 11) Provide a deployment site AI capability management module, including:

[0446] The first receiving module is used to receive the AI ​​model scheduling service request sent by the visited AI capability management module. The request carries the second core network tunnel information, which is the core network tunnel information of the user plane network element of the visited service transmission channel.

[0447] The first sending module is used to initiate an AI model scheduling service request to the AI ​​capability application module at the deployment site to allocate the core network tunnel information of the AI ​​capability application module at the deployment site. The request carries the intelligent computing service identifier and the intelligent computing model identifier.

[0448] The second receiving module is used to receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site. The fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site.

[0449] The second sending module is used to send AI model scheduling service requests to the network elements of the service transmission channel control plane at the deployment site. The requests carry the fourth core network tunnel information, the second core network tunnel information, and the area information of the AI ​​capability application module at the deployment site.

[0450] The third receiving module is used to receive the third core network tunnel information sent by the control plane network element of the service transmission channel at the deployment site. The third core network tunnel information is the core network tunnel information of the user plane network element at the deployment site.

[0451] The third sending module is used to return the AI ​​model scheduling service request establishment result to the visited AI capability management module. The result includes: third core network tunnel information.

[0452] This disclosure also provides an AI model scheduling system. When scheduling within the same region, see [link to relevant documentation]. Figure 4 It includes: the visited site AI capability management module, the visited site AI capability application module, the visited site service transmission channel control plane network element for intra-area scheduling, the deployed site AI capability application module for intra-area scheduling, the visited site service transmission channel user plane network element for intra-area scheduling, and the deployed site service transmission channel user plane network element for intra-area scheduling.

[0453] When scheduling across regions, see [link / reference]. Figure 8It includes: the visited location AI capability management module, the visited location AI capability application module, the control plane network element of the visited location service transmission channel for cross-regional scheduling of users, the user plane network element of the visited location service transmission channel for cross-regional scheduling of users, the control plane network element of the deployment location service transmission channel for cross-regional scheduling of users, the deployment location AI capability application module for cross-regional scheduling of users, and the deployment location AI capability management module for cross-regional scheduling of users.

[0454] Based on the same inventive concept as the above disclosure, this disclosure also provides an electronic device. The electronic device of this disclosure includes at least one processor and at least one memory electrically connected to the processor. The memory is electrically connected to the processor, wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method described above.

[0455] It should be noted that the electrical connection between the above-mentioned units does not necessarily mean the connection between lines. The indirect connection method can be applied to the embodiments of this disclosure as long as it achieves the purpose of this disclosure.

[0456] Based on the same inventive concept, this disclosure also provides a computer storage medium storing a computer program, which, when executed by a processor, implements the steps of the above method.

[0457] Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. An AI model scheduling method, characterized in that, include: The visited location AI capability management module receives location information, intelligent computing service identifier, and intelligent computing model identifier; The visited location AI capability management module uses the stored intelligent computing model registration table to determine if there is an AI capability application module that matches both the intelligent computing service identifier and the intelligent computing model identifier, but the area information corresponding to the matching AI capability application module does not match the received location information. In this case, the module performs the following same-area scheduling: The visited AI capability management module initiates an AI model scheduling service request to the visited AI capability application module, requesting the allocation of core network tunnel information for the visited AI capability application module. The intelligent computing model registration table stores the correspondence between intelligent computing service identifier, intelligent computing model identifier, regional information, and AI capability application module information. The visited AI capability application module returns the first core network tunnel information to the visited AI capability management module. The visited AI capability management module initiates an AI model scheduling service request to the deployed AI capability application module, which is indicated by the matching AI capability application module information. The request requests the allocation of core network tunnel information on the side of the deployed AI capability application module, and carries the intelligent computing service identifier and intelligent computing model identifier in the request. The deployed AI capability application module returns the fourth core network tunnel information to the visited AI capability management module. The visited site AI capability management module initiates an AI model scheduling service request to the network element of the visited site service transmission channel control plane. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the AI ​​capability application module at the deployment site. The visited service transport channel control plane network element uses the location information carried in the service request to schedule the location of the visited service transport channel user plane network element, and uses the area information to address the deployed service transport channel user plane network element. When it is determined that the visited service transport channel user plane network element and the deployed service transport channel user plane network element are the same network element, it sends a request to the visited service transport channel user plane network element to establish a user plane tunnel, carrying the first core network tunnel information and the fourth core network tunnel information. The user plane network element of the visited service transport channel sends the second core network tunnel information to the control plane network element of the visited service transport channel. The control plane network element of the visited service transmission channel sends the second core network tunnel information to the visited AI capability application module and the deployed AI capability application module respectively via the visited AI capability management module. Thus, the visited AI capability application module and the deployed AI capability application module establish a user plane intelligent computing service model transmission channel. The deployment site AI capability application module uses the intelligent computing business identifier and intelligent computing model identifier to select an intelligent computing model, and then passes a copy of the selected intelligent computing model to the visited site AI capability application module.

2. The method according to claim 1, characterized in that, The method further includes: The control plane network element of the visited service transport channel uses the location and area information carried in the service request to schedule the service request. When it is determined that the user plane network element of the visited service transport channel and the user plane network element of the deployed service transport channel are different network elements, it sends a request to establish a user plane tunnel carrying the first core network tunnel information to the user plane network element of the visited service transport channel, and sends a request to establish a user plane tunnel carrying the fourth core network tunnel information to the user plane network element of the deployed service transport channel. The user plane network element of the visited service transport channel sends the second core network tunnel information to the control plane network element of the visited service transport channel. The user plane network element of the deployed service transport channel sends third core network tunnel information to the control plane network element of the visited service transport channel. The visited service transmission channel control plane network element sends the second core network tunnel information to the visited AI capability application module via the visited AI capability management module, and sends the third core network tunnel information to the deployment site AI capability application module. The visited service transport channel control plane network element sends the second core network tunnel information to the deployed service transport channel user plane network element, and sends the third core network tunnel information to the visited service transport channel user plane network element. Thus, the visited AI capability application module and the deployed AI capability application module establish a user plane intelligent computing service model transport channel. The deployment site AI capability application module uses the intelligent computing business identifier and intelligent computing model identifier to select an intelligent computing model, and then passes a copy of the selected intelligent computing model to the visited site AI capability application module.

3. An AI model scheduling method, characterized in that, The method includes: The visited location AI capability management module receives location information, intelligent computing service identifier, and intelligent computing model identifier; The visited location AI capability management module uses the stored intelligent computing model registration table to determine if there is an AI capability application module that matches both the intelligent computing business identifier and the intelligent computing model identifier, and then performs the following cross-region scheduling: The visited AI capability management module initiates an AI model scheduling service request to the visited AI capability application module, requesting the allocation of core network tunnel information on the visited AI capability application module side. The intelligent computing model registration table stores the correspondence between intelligent computing service identifier, intelligent computing model identifier, regional information and AI capability application module information. The visited AI capability application module returns the first core network tunnel information to the visited AI capability management module. The visited site AI capability management module initiates an AI model scheduling service request to the visited site service transport channel control plane network element, which carries the first core network tunnel information and location information. The visited site service transport channel control plane network element addresses the visited site service transport channel user plane network element according to the location information and sends a user plane tunnel establishment request, which carries the first core network tunnel information. The visited site service transport channel control plane network element receives the second core network tunnel information fed back by the user plane network element of the visited site service transport channel and transmits it to the visited site AI capability application module via the visited site AI capability management module. The visited AI capability management module addresses the deployed AI capability management module based on the intelligent computing service identifier and the intelligent computing model identifier, and sends an AI model scheduling service request to the deployed AI capability management module. The request carries the intelligent computing service identifier, the intelligent computing model identifier, and the second core network tunnel information. The deployment site AI capability management module determines the deployment site AI capability application module based on the intelligent computing service identifier and the intelligent computing model identifier, and initiates an AI model scheduling service process to it, requesting the deployment site AI capability application module to allocate core network tunnel information; The AI ​​capability application module at the deployment site returns the fourth core network tunnel information to the AI ​​capability management module at the deployment site. The deployment site AI capability management module initiates an AI model scheduling service request to the deployment site service transport channel control plane network element. The request carries the fourth core network tunnel information, the second core network tunnel information, and the area information that the deployment site AI capability application module is responsible for. Among them, the deployment site service transport channel control plane network element and the visited site service transport channel control plane network element are the same network element or different network elements. Based on the area information of the AI ​​capability application module at the deployment location, the control plane network element of the service transport channel at the deployment location addresses the user plane network element of the service transport channel at the deployment location and initiates a request to establish a user plane tunnel to the user plane network element of the service transport channel at the deployment location. The request carries the fourth core network tunnel information and the second core network tunnel information. The user plane network element of the deployment site service transport channel returns the third core network tunnel information to the control plane network element of the deployment site service transport channel. The network element of the service transmission channel at the deployment site returns the third core network tunnel information to the AI ​​capability management module at the deployment site. The AI ​​capability management module at the deployment site returns the AI ​​model scheduling service request establishment result to the AI ​​capability management module at the visited site. The result includes: third core network tunnel information. The visited site AI capability management module returns the third core network tunnel information to the visited site service transmission channel control plane network element; the visited site service transmission channel control plane network element returns the third core network tunnel information to the visited site service transmission channel user plane network element. At this point, the intelligent computing model scheduling service transmission channel is established. The deployment site AI capability application module uses the intelligent computing business identifier and intelligent computing model identifier to select an intelligent computing model, and then passes a copy of the selected intelligent computing model to the visited site AI capability application module.

4. The method according to claim 3, characterized in that, The visited site AI capability management module sends an AI model scheduling service request to the deployed site AI capability management module, including: The visited site AI capability management module sequentially sends AI model scheduling service requests to the deployed site AI capability management module via the visited site service transport channel control plane network element and the deployed site service transport channel control plane network element; and / or The deployment site AI capability management module returns the AI ​​model scheduling business request establishment result to the visited site AI capability management module, including: The deployment site AI capability management module sequentially returns the AI ​​model scheduling service request establishment result to the visited site AI capability management module via the visited site service transmission channel control plane network element and the deployment site service transmission channel control plane network element.

5. The method according to claim 3 or 4, characterized in that, After the deployment site AI capability application module selects an intelligent computing model using the intelligent computing service identifier and the intelligent computing model identifier, and passes a copy of the selected intelligent computing model to the visited site AI capability application module, the method further includes: The visited site AI capability application module returns the intelligent computing model transmission completion information to the visited site AI capability management module, and the AI ​​capability management module registers the model.

6. The method according to claim 3 or 4, characterized in that, The visited site AI capability management module uses either of the following two methods for addressing: Method 1: Configure the global intelligent computing model registration information table locally and notify the global and other AI capability management modules when the registration information changes; Method 2: When the intelligent computing model registration information changes, the AI ​​capability management module completes registration with the network resource database. The registration information includes: AI capability management module identifier, AI capability management module address, intelligent computing business identifier, intelligent computing model identifier, AI capability application module identifier, and region information. The AI ​​capability management module performs AI capability management module service discovery with the network resource database. The request message includes the intelligent computing business identifier and the intelligent computing model identifier. Based on the AI ​​capability management module service discovery result returned by the network resource database, the AI ​​capability management module is selected.

7. An AI model scheduling method, characterized in that, Applications in the visited site AI capability management module include: Receive location information, intelligent computing service identifier, and intelligent computing model identifier; Using the stored intelligent computing model registration table, it is determined that there is an AI capability application module that matches both the intelligent computing service identifier and the intelligent computing model identifier, but the area information corresponding to the matching AI capability application module does not match the received location information. In this case, intra-area scheduling is performed, and an AI model scheduling service request is initiated to the visited AI capability application module to request the allocation of core network tunnel information on the visited AI capability application module side. The intelligent computing model registration table stores the correspondence between the intelligent computing service identifier, the intelligent computing model identifier, the area information, and the AI ​​capability application module information. Receive the first core network tunnel information returned by the AI ​​capability application module of the visited site; An AI model scheduling service request is initiated to the AI ​​capability application module at the deployment location indicated by the matching AI capability application module information. The request requests the allocation of core network tunnel information on the side of the AI ​​capability application module at the deployment location. The request carries the intelligent computing service identifier and the intelligent computing model identifier. Receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site; The system initiates an AI model scheduling service request to the control plane network element of the service transmission channel at the visited location. The request carries information about the first core network tunnel, the fourth core network tunnel, location information, and the regional information of the AI ​​capability application module at the deployment location. When it is determined that the user plane network element of the visited service transport channel and the user plane network element of the deployed service transport channel are the same network element, the second core network tunnel information sent by the control plane network element of the visited service transport channel is forwarded to the AI ​​capability application module of the visited location and the AI ​​capability application module of the deployed location. The second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transport channel.

8. The method according to claim 7, characterized in that, When it is determined that the user plane network element of the visited service transport channel and the user plane network element of the deployed service transport channel are different network elements, the second core network tunnel information sent by the control plane network element of the visited service transport channel is forwarded to the AI ​​capability application module of the visited location, and the third core network tunnel information is forwarded to the AI ​​capability application module of the deployed location. The third core network tunnel information is the core network tunnel information of the user plane network element of the deployed service transport channel.

9. An AI model scheduling method, characterized in that, Applications in the visited site AI capability management module include: Receive location information, intelligent computing service identifier, and intelligent computing model identifier; Using the stored intelligent computing model registration table, it is determined that there is no AI capability application module that matches both the intelligent computing service identifier and the intelligent computing model identifier. An AI model scheduling service request is then initiated to the visited AI capability application module, requesting the allocation of core network tunnel information on the visited AI capability application module side. The intelligent computing model registration table stores the correspondence between the intelligent computing service identifier, the intelligent computing model identifier, the regional information, and the AI ​​capability application module information. Receive the first core network tunnel information returned by the AI ​​capability application module of the visited site; The system initiates an AI model scheduling service request to the control plane network element of the visited service transmission channel, and the request carries the first core network tunnel information and location information. Forward the second core network tunnel information sent by the control plane network element of the visited service transmission channel to the visited AI capability application module; The AI ​​capability management module at the deployment location is located based on the intelligent computing service identifier and the intelligent computing model identifier, and an AI model scheduling service request is sent. The request carries the intelligent computing service identifier, the intelligent computing model identifier, and the second core network tunnel information. The AI ​​model scheduling service request establishment result returned by the AI ​​capability management module at the deployment site is received. The result includes: third core network tunnel information, where the third core network tunnel information is the core network tunnel information of the user plane network element of the service transmission channel at the deployment site. Return third core network tunnel information to the network element of the service transmission channel control plane at the visited location.

10. The method according to claim 9, characterized in that, Also includes: Receive the intelligent computing model transmission completion information returned by the AI ​​capability application module of the visited location, and register the intelligent computing model.

11. The method according to claim 9 or 10, characterized in that, Addressing can be performed using either of the following two methods: Method 1: Configure the global intelligent computing model registration information table locally and notify the global and other AI capability management modules when the registration information changes; Method 2: When the registration information of the intelligent computing model changes, the registration with the network resource database is completed. The registration information includes: AI capability management module identifier, AI capability management module address, intelligent computing business identifier, intelligent computing model identifier, AI capability application module identifier, and regional information. The AI ​​capability management module performs AI capability management module service discovery with the network resource database. The request message contains the intelligent computing business identifier and the intelligent computing model identifier. Based on the AI ​​capability management module service discovery result returned by the network resource database, the AI ​​capability management module is selected.

12. An AI model scheduling method, characterized in that, The application of AI capabilities in the visited sites includes: Receives an AI model scheduling service request initiated by the AI ​​capability management module of the visited location; Allocate the first core network tunnel information and return it to the visited AI capability management module; Receive the second core network tunnel information sent by the visited AI capability management module; where the second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transmission channel. Receive a copy of the intelligent computing model sent by the AI ​​capability application module at the deployment site.

13. An AI model scheduling method, characterized in that, When applying to control plane network elements of visited service transport channels and performing intra-area scheduling, the method includes: Receive AI model scheduling service request initiated by the visited site AI capability management module. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the deployed site AI capability application module. Among them, the first core network tunnel information refers to the core network tunnel information of the visited site AI application module, and the fourth core network tunnel information refers to the core network tunnel information of the deployed site AI application module. The AI ​​model schedules the user plane network element of the service transmission channel at the visited location by using the location information carried in the service request, and uses the area information to address the user plane network element of the service transmission channel at the deployment location. When it is determined that the user plane network element of the service transmission channel at the visited location and the user plane network element of the service transmission channel at the deployment location are the same network element, a request to establish a user plane tunnel carrying the first core network tunnel information and the fourth core network tunnel information is sent to the user plane network element of the service transmission channel at the visited location. Receive second core network tunnel information sent by user plane network elements of the visited service transmission channel; The second core network tunnel information is sent to the visited AI capability application module and the deployment site AI capability application module via the visited site AI capability management module.

14. The method according to claim 13, characterized in that, The method further includes: By utilizing the location and regional information carried in the service request to schedule the AI ​​model, when it is determined that the user plane network element of the service transport channel at the visited location and the user plane network element of the service transport channel at the deployment location are different network elements, a user plane tunnel establishment request carrying the first core network tunnel information is sent to the user plane network element of the service transport channel at the visited location, and a user plane tunnel establishment request carrying the fourth core network tunnel information is sent to the user plane network element of the service transport channel at the deployment location. Receive second core network tunnel information sent by user plane network elements of the visited service transmission channel; Receive third core network tunnel information sent by user plane network elements of the service transmission channel at the deployment site; The second core network tunnel information is sent to the visited AI capability application module via the visited AI capability management module, and the third core network tunnel information is sent to the deployment site AI capability application module. Send the second core network tunnel information to the user plane network element of the service transport channel at the deployment site, and send the third core network tunnel information to the user plane network element of the service transport channel at the visited site.

15. An AI model scheduling method, characterized in that, When performing cross-region scheduling in the control plane network elements of the visited service transport channel, the method includes: Receives an AI model scheduling service request initiated by the visited site's AI capability management module, which carries the first core network tunnel information and location information; Based on the location information, the user plane network element of the visited service transmission channel is addressed, and a request to establish a user plane tunnel is sent, which carries the first core network tunnel information. The second core network tunnel information is received from the user plane network element of the user visited service transmission channel and transmitted to the visited AI capability application module via the visited AI capability management module. Receive the third core network tunnel information returned by the AI ​​capability management module of the visited location. The third core network tunnel information is the core network tunnel information of the user plane network element of the service transmission channel at the deployment location. Return third core network tunnel information to the user plane network element of the visited service transmission channel.

16. An AI model scheduling method, characterized in that, When the AI ​​capability application module is deployed in the same region, it includes: The system receives an AI model scheduling service request initiated by the AI ​​capability management module of the visited location, which allocates and deploys the core network tunnel information of the AI ​​capability application module. The request carries the intelligent computing service identifier and the intelligent computing model identifier. Allocate tunnel information for the fourth core network; Return the fourth core network tunnel information to the AI ​​capability management module of the visited site; When the user plane network element of the visited service transport channel and the user plane network element of the deployment service transport channel are the same network element, the second core network tunnel information sent by the visited AI capability management module is received, and the visited service transport channel user plane network element is interacted with so that the visited AI capability application module and the deployment AI capability application module can establish a user plane intelligent computing service model transport channel; wherein, the second core network tunnel information is the core network tunnel information at the user plane network element end of the visited service transport channel. The intelligent computing model is selected using the intelligent computing business identifier and the intelligent computing model identifier. The selected intelligent computing model copy is then transmitted to the visited AI capability application module through the established user plane intelligent computing business model transmission channel.

17. The method according to claim 16, characterized in that, When it is determined that the user plane network element of the service transport channel at the visited location and the user plane network element of the service transport channel at the deployment location are not the same network element, the third core network tunnel information sent by the AI ​​capability management module at the visited location is received. The third core network tunnel information is the core network tunnel information at the user plane network element end of the service transport channel at the deployment location.

18. An AI model scheduling method, characterized in that, When applying AI capabilities in the deployment location module to perform cross-regional scheduling, the following applies: The AI ​​capability management module at the deployment site initiates a business process to request the AI ​​capability application module at the deployment site to allocate core network tunnel information AI model scheduling services. Allocate tunnel information for the fourth core network; The fourth core network tunnel information is returned to the AI ​​capability management module at the deployment site, so that the AI ​​capability management module at the deployment site can send the fourth core network tunnel information, the second core network tunnel information, and the regional information to the control plane network element of the service transmission channel at the deployment site in the AI ​​model scheduling service request. The second core network tunnel information refers to the core network tunnel information at the user plane network element of the service transmission channel at the visited site. The intelligent computing model is selected using the intelligent computing business identifier and the intelligent computing model identifier. The selected intelligent computing model copy is then transmitted to the visited AI capability application module through the established user plane intelligent computing business model transmission channel.

19. An AI model scheduling method, characterized in that, When applying to user plane network elements in the visited service transport channel for intra-area scheduling, the following applies: Receive a request to establish a user plane tunnel from the control plane network element of the visited service transport channel. The request carries the first core network tunnel information and the fourth core network tunnel information. The first core network tunnel information refers to the core network tunnel information of the visited AI application module, and the fourth core network tunnel information refers to the core network tunnel information of the deployed AI application module. Allocate information for the second core network tunnel; Send the second core network tunnel information to the control plane network element of the visited service transmission channel; Forward a copy of the intelligent computing model sent by the AI ​​capability module at the deployment site to the AI ​​capability application module at the visited site.

20. An AI model scheduling method, characterized in that, When applying to user plane network elements in the visited service transport channel for cross-regional scheduling, the following applies: Receive a request to establish a user plane tunnel from the control plane network element of the visited service transport channel. The request carries the first core network tunnel information, which refers to the core network tunnel information of the visited AI application module. Allocate information for the second core network tunnel; Send the second core network tunnel information to the control plane network element of the visited service transmission channel; Receive the third core network tunnel information sent by the control plane network element of the visited service transport channel, wherein the third core network tunnel information refers to the core network tunnel information of the user plane network element of the deployed service transport channel. The intelligent computing model copy sent by the user plane network element of the service transmission channel at the deployment site is forwarded to the visited AI capability application module.

21. An AI model scheduling method, characterized in that, When using user plane network elements in the service transport channel at the deployment location for intra-area scheduling, the following applies: Receive a request to establish a user plane tunnel from the control plane network element of the visited service transmission channel. The request carries the fourth core network tunnel information, which refers to the core network tunnel information of the AI ​​capability application module at the deployment site. Allocate information for the third core network tunnel; Send the third core network tunnel information to the control plane network element of the visited service transmission channel; Receive the second core network tunnel information sent by the control plane network element of the visited service transport channel, wherein the second core network tunnel information refers to the core network tunnel information at the user plane network element end of the visited service transport channel. Forward the copy of the intelligent computing model sent by the AI ​​capability application module at the deployment site to the AI ​​capability application module at the visited site.

22. An AI model scheduling method, characterized in that, When user plane network elements in the service transport channel of the deployment location perform cross-regional scheduling, the following applies: Receive a request to establish a user plane tunnel from the control plane network element of the service transport channel at the deployment site. The request carries the fourth core network tunnel information and the second core network tunnel information. The second core network tunnel information is the core network tunnel information of the user plane network element at the visited site, and the fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site. Allocate information for the third core network tunnel; The third core network tunnel information is returned to the control plane network element of the service transmission channel at the deployment site; Forward the copy of the intelligent computing model sent by the AI ​​capability application module at the deployment site to the control plane network element of the business transmission channel at the visited site.

23. An AI model scheduling method, characterized in that, When using control plane network elements in the service transport channel at the deployment location for cross-regional scheduling, the following applies: Receive AI model scheduling service request sent by the AI ​​capability management module at the deployment site. The request carries the fourth core network tunnel information, the second core network tunnel information, and the area information that the AI ​​capability application module at the deployment site is responsible for. Among them, the second core network tunnel information is the core network tunnel information of the user plane network element end of the visited service transmission channel, and the fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site. Based on the regional information of the AI ​​capability application module at the deployment site, the system addresses the user plane network element of the service transmission channel at the deployment site and initiates a request to establish a user plane tunnel to the user plane network element of the service transmission channel at the deployment site. The request carries the fourth core network tunnel information and the second core network tunnel information. Receive the third core network tunnel information returned by the user plane network element of the service transmission channel at the deployment site; Return the third core network tunnel information to the AI ​​capability management module at the deployment site.

24. An AI model scheduling method, characterized in that, The AI ​​capability management module applied in the deployment site includes: Receive AI model scheduling service request sent by the visited AI capability management module. The request carries the second core network tunnel information, which is the core network tunnel information of the user plane network element of the visited service transmission channel. An AI model scheduling service request is initiated to the AI ​​capability application module at the deployment site to allocate the core network tunnel information of the AI ​​capability application module at the deployment site. The request carries the intelligent computing service identifier and the intelligent computing model identifier. Receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site. The fourth core network tunnel information is the core network tunnel information at the AI ​​capability application module at the deployment site. Send an AI model scheduling service request to the network element of the service transmission channel control plane at the deployment site. The request carries the fourth core network tunnel information, the second core network tunnel information, and the area information of the AI ​​capability application module at the deployment site. Receive the third core network tunnel information sent by the control plane network element of the service transport channel at the deployment site, wherein the third core network tunnel information is the core network tunnel information at the user plane network element end of the service transport channel at the deployment site; The AI ​​model scheduling service request establishment result is returned to the AI ​​capability management module of the visited location. The result includes: third core network tunnel information.

25. A visited location AI capability management module, characterized in that, include: The first receiving module is used to receive location information, intelligent computing service identifier, and intelligent computing model identifier; The first sending module is used to utilize the stored intelligent computing model registration table to perform intra-region scheduling when it is determined that there is an AI capability application module that matches both the intelligent computing service identifier and the intelligent computing model identifier, and the area information corresponding to the matching AI capability application module does not match the received location information. The module then initiates an AI model scheduling service request to the visited AI capability application module and requests the allocation of core network tunnel information on the visited AI capability application module side. The intelligent computing model registration table stores the correspondence between the intelligent computing service identifier, the intelligent computing model identifier, the area information, and the AI ​​capability application module information. The second receiving module is used to receive the first core network tunnel information returned by the visited AI capability application module. The second sending module is used to initiate an AI model scheduling service request to the AI ​​capability application module at the deployment location pointed to by the matching AI capability application module information, requesting the allocation of core network tunnel information on the side of the AI ​​capability application module at the deployment location, and the request carries the intelligent computing service identifier and intelligent computing model identifier. The third receiving module is used to receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site; The third sending module is used to initiate an AI model scheduling service request to the control plane network element of the visited service transmission channel. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the AI ​​capability application module at the deployment location. When the forwarding module determines that the user plane network element of the visited service transport channel and the user plane network element of the deployment service transport channel are the same network element, it forwards the second core network tunnel information sent by the control plane network element of the visited service transport channel to the AI ​​capability application module of the visited location and the AI ​​capability application module of the deployment location. The second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transport channel.

26. A visited site AI capability application module, characterized in that, include: The first receiving module is used to receive AI model scheduling service requests initiated by the AI ​​capability management module of the visited location. The allocation module is used to allocate tunnel information in the first core network. The sending module is used to return data to the AI ​​capability management module of the visited location; The second receiving module is used to receive the second core network tunnel information sent by the visited AI capability management module. The second core network tunnel information is the core network tunnel information of the user plane network element of the visited service transmission channel. The third receiving module is used to receive copies of the intelligent computing model sent by the AI ​​capability application module at the deployment site.

27. A visited service transmission channel control plane network element, characterized in that, When scheduling within the same area, this includes: The first receiving module is used to receive AI model scheduling service requests initiated by the visited AI capability management module. The request carries the first core network tunnel information, the fourth core network tunnel information, location information, and the regional information of the deployed AI capability application module. The first core network tunnel information refers to the core network tunnel information of the visited AI application module, and the fourth core network tunnel information refers to the core network tunnel information of the deployed AI application module. The addressing module is used to address the user plane network elements of the service transmission channel in the visited location using the location information carried in the service request of the AI ​​model, and to address the user plane network elements of the service transmission channel in the deployment location using the area information. The first sending module is used to send a request to establish a user plane tunnel to the user plane network element of the service transport channel at the visited location, carrying the first core network tunnel information and the fourth core network tunnel information, when it is determined that the user plane network element of the service transport channel at the visited location and the user plane network element of the service transport channel at the deployed location are the same network element. The second receiving module is used to receive the second core network tunnel information sent by the user plane network element of the visited service transmission channel. The second sending module is used to send the second core network tunnel information to the visited AI capability application module and the deployment site AI capability application module respectively via the visited site AI capability management module.

28. A visited service transmission channel control plane network element, characterized in that, When scheduling across regions, the following applies: The third receiving module is used to receive AI model scheduling service requests initiated by the visited AI capability management module. The requests carry the first core network tunnel information and location information. The first core network tunnel information refers to the core network tunnel information of the visited AI application module. The addressing module is used to address the user plane network element of the visited service transmission channel based on the location information; The third sending module is used to send a request to establish a user plane tunnel to the user plane network element of the visited service transport channel. The request carries the first core network tunnel information. The fourth receiving module is used to receive the second core network tunnel information fed back by the user plane network element of the user visited service transmission channel, and transmit it to the visited AI capability application module via the visited AI capability management module. The fifth receiving module is used to receive the third core network tunnel information returned by the visited AI capability management module. The third core network tunnel information is the core network tunnel information of the user plane network element of the service transmission channel at the deployment site. The fourth sending module is used to return the third core network tunnel information to the user plane network element of the visited service transmission channel.

29. A deployment-based AI capability application module, characterized in that, When performing intra-region scheduling, the following are included: The first receiving module is used to receive AI model scheduling service requests initiated by the visited AI capability management module, which allocates and deploys AI capability application module core network tunnel information. The requests carry intelligent computing service identifier and intelligent computing model identifier. The first allocation module is used to allocate tunnel information for the fourth core network. The first sending module is used to return the fourth core network tunnel information to the visited AI capability management module. The second receiving module is used to receive the second core network tunnel information sent by the visited AI capability management module when the visited service transport channel control plane network element determines that the visited service transport channel user plane network element and the deployed service transport channel user plane network element are the same network element. The second core network tunnel information is the core network tunnel information of the visited service transport channel user plane network element. The selection module is used to select an intelligent computing model using intelligent computing business identifiers and intelligent computing model identifiers; The second sending module transmits the selected intelligent computing model copy to the visited AI capability application module.

30. A deployment-based AI capability application module, characterized in that, When performing cross-regional scheduling, the following are included: The third receiving module is used to receive the AI ​​capability management module at the deployment site from the business process of requesting the AI ​​capability application module at the deployment site to allocate core network tunnel information AI model scheduling services. The second allocation module is used to allocate the fourth core network tunnel information; The third sending module is used to return the fourth core network tunnel information to the AI ​​capability management module at the deployment site, so that the AI ​​capability management module at the deployment site can send the fourth core network tunnel information, the second core network tunnel information and the regional information to the control plane network element of the service transmission channel at the deployment site in the AI ​​model scheduling service request. The second core network tunnel information refers to the core network tunnel information at the user plane network element of the service transmission channel at the visited site. The fourth sending module is used to transmit the selected intelligent computing model copy to the visited AI capability application module through the established user plane intelligent computing business model transmission channel.

31. A visited service transport channel user plane network element, characterized in that, When performing intra-region scheduling, the following are included: The first receiving module is used to receive the request to establish a user plane tunnel sent by the control plane network element of the visited service transmission channel. The request carries the first core network tunnel information and the fourth core network tunnel information. The first core network tunnel information refers to the core network tunnel information of the visited AI application module end, and the fourth core network tunnel information refers to the core network tunnel information of the deployed AI application module end. The first allocation module is used to allocate the second core network tunnel information; The first sending module is used to send the second core network tunnel information to the control plane network element of the visited service transmission channel.

32. A visited service transport channel user plane network element, characterized in that, When performing cross-regional scheduling, the following are included: The second receiving module is used to receive a request to establish a user plane tunnel sent by the control plane network element of the visited service transmission channel. The request carries the first core network tunnel information, which refers to the core network tunnel information of the visited AI application module. The second allocation module is used to allocate the second core network tunnel information; The second sending module sends the second core network tunnel information to the control plane network element of the visited service transmission channel. The third receiving module is used to receive the third core network tunnel information sent by the control plane network element of the visited service transport channel. The third core network tunnel information refers to the core network tunnel information of the user plane network element of the deployed service transport channel. The third sending module forwards the copy of the intelligent computing model sent by the user plane network element of the service transmission channel at the deployment site to the visited AI capability application module.

33. A user plane network element for a deployed service transport channel, characterized in that, When performing intra-region scheduling, the following are included: The first receiving module is used to receive the request to establish a user plane tunnel sent by the control plane network element of the visited service transmission channel. The request carries the fourth core network tunnel information, which refers to the core network tunnel information of the AI ​​capability application module at the deployment site. The allocation module is used to allocate third core network tunnel information; The first sending module is used to send the third core network tunnel information to the control plane network element of the visited service transmission channel; The second receiving module is used to receive the second core network tunnel information sent by the control plane network element of the visited service transmission channel, wherein the second core network tunnel information refers to the core network tunnel information at the user plane network element end of the visited service transmission channel. The second sending module is used to forward the copy of the intelligent computing model sent by the AI ​​capability application module at the deployment site to the AI ​​capability application module at the visited site.

34. A network element for a deployed service transport channel control plane, characterized in that, When performing cross-regional scheduling, the following are included: The first receiving module is used to receive the AI ​​model scheduling service request sent by the AI ​​capability management module at the deployment site. The request carries the fourth core network tunnel information, the second core network tunnel information, and the area information that the AI ​​capability application module at the deployment site is responsible for. Among them, the second core network tunnel information is the core network tunnel information of the user plane network element end of the visited service transmission channel, and the fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site. The addressing module is used to address the user plane network elements of the service transmission channel at the deployment location based on the area information of the AI ​​capability application module at the deployment location. The first sending module is used to initiate a request to establish a user plane tunnel to the user plane network element of the service transmission channel at the deployment site. The request carries the fourth core network tunnel information and the second core network tunnel information. The second receiving module is used to receive the third core network tunnel information returned by the user plane network element of the service transmission channel at the deployment site; The second sending module is used to return the third core network tunnel information to the AI ​​capability management module at the deployment site.

35. A deployment-based AI capability management module, characterized in that, include: The first receiving module is used to receive the AI ​​model scheduling service request sent by the visited AI capability management module. The request carries the second core network tunnel information, which is the core network tunnel information of the user plane network element of the visited service transmission channel. The first sending module is used to initiate an AI model scheduling service request to the AI ​​capability application module at the deployment site to allocate the core network tunnel information of the AI ​​capability application module at the deployment site. The request carries the intelligent computing service identifier and the intelligent computing model identifier. The second receiving module is used to receive the fourth core network tunnel information returned by the AI ​​capability application module at the deployment site. The fourth core network tunnel information is the core network tunnel information of the AI ​​capability application module at the deployment site. The second sending module is used to send AI model scheduling service requests to the network elements of the service transmission channel control plane at the deployment site. The requests carry the fourth core network tunnel information, the second core network tunnel information, and the area information of the AI ​​capability application module at the deployment site. The third receiving module is used to receive the third core network tunnel information sent by the control plane network element of the service transmission channel at the deployment site. The third core network tunnel information is the core network tunnel information of the user plane network element at the deployment site. The third sending module is used to return the AI ​​model scheduling service request establishment result to the visited AI capability management module. The result includes: third core network tunnel information.

36. An AI model scheduling system, characterized in that, When scheduling within the same area, it includes: the visited site AI capability management module as described in claim 25, the visited site AI capability application module as described in claim 26, the visited site service transmission channel control plane network element as described in claim 27, the deployment site AI capability application module as described in claim 29, the visited site service transmission channel user plane network element as described in claim 31, and the deployment site service transmission channel user plane network element as described in claim 33. The cross-regional scheduling includes: the visited location AI capability management module as described in claim 25, the visited location AI capability application module as described in claim 26, the visited location service transmission channel control plane network element as described in claim 28, the visited location service transmission channel user plane network element as described in claim 32, the deployment location service transmission channel control plane network element as described in claim 34, the deployment location AI capability application module as described in claim 30, and the deployment location AI capability management module as described in claim 35.

37. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method described in any one of claims 7-24.

38. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 7-24.

Images