Service orchestration processing method, device and equipment

Abstract

The application provides a service arrangement processing method, device and equipment. The service arrangement processing method comprises the following steps: receiving an intelligent service request sent by a target object; interacting with at least one target unit according to the intelligent service request, obtaining an intelligent service arranged for the target object; and sending the intelligent service to the target object through an intelligent service channel. The scheme of the application can better meet the service demand of intelligent application, makes the provision of intelligent service more flexible and efficient in resource utilization, and realizes the quality guarantee of intelligent service.

Description

Technical Field

[0001] This invention relates to the field of core network technology, and in particular to a service orchestration processing method, apparatus and equipment. Background Technology

[0002] Current 5G networks only provide connectivity services. Network intelligence applications are handled externally, meaning network data is collected offline, and then a separate artificial intelligence platform is responsible for training and inference of AI (Artificial Intelligence) models. Although computing power is introduced through MEC (Mobile Edge Computing), the scope and global architectural characteristics of the previous generation are basically retained, with the focus on the decentralization of computing power. Therefore, the network and computing components are relatively loosely coupled and are not native capabilities of the network architecture.

[0003] Towards 6G, the network will not only provide communication capabilities but also integrate sensing and computing functions to support the intelligent needs of all industries and society, providing the necessary sensing and computing power services to meet the demands of society and industries for high computing power and extremely low latency. The current separation of intelligence, computing power, and connectivity cannot meet the needs of future networks. Summary of the Invention

[0004] The technical problem this invention aims to solve is to provide a service orchestration processing method, apparatus, and device. It addresses the issue that the current separate approach to intelligence, computing power, and connectivity in 6G networks cannot meet the needs of future networks.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0006] A service orchestration method, the method comprising:

[0007] Receive intelligent service requests sent by the target object;

[0008] Based on the intelligent service request, interact with at least one target unit to obtain intelligent services orchestrated for the target object;

[0009] The intelligent service is sent to the target object through the intelligent service channel.

[0010] Optionally, receive smart service requests sent by the target object, including:

[0011] The receiving terminal and / or application function send intelligent service requests through the control plane unit. The intelligent service requests carry the parameters required for the intelligent service and the carrying information of the intelligent service.

[0012] Optionally, when the receiving terminal sends an intelligent service request through the control plane unit, it interacts with at least one target unit according to the intelligent service request to obtain intelligent services orchestrated for the target object, including:

[0013] Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results;

[0014] Based on the processing result, a service instance startup request is sent to the intelligent service unit; the service instance startup request is used to trigger the intelligent service unit to start an instance of the intelligent service. Optionally, the intelligent service is sent to the target object through the intelligent service channel, including:

[0015] The intelligent service is sent to the terminal through the bearer channel and the data channel.

[0016] Optionally, upon receiving the joint learning requirements of the application function and the terminal, when sending an intelligent service request through the control plane unit, the system interacts with at least one target unit according to the intelligent service request to obtain intelligent services orchestrated for the target object, including:

[0017] Send a resource information query request to the resource management unit and receive resource information from the resource management unit in response to the resource information query request;

[0018] Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results;

[0019] A collaborative service instance startup request is sent to the inter-service routing scheduling unit; the collaborative service instance startup request is used to trigger the inter-service routing scheduling unit to start an instance of the collaborative intelligent service.

[0020] Optionally, the intelligent service is sent to the target object through the intelligent service channel, including:

[0021] The intelligent service is sent to the application function through the bearer channel and the data channel.

[0022] Optionally, receive smart service requests sent by the target object, including:

[0023] Receive intelligent service requests from at least one network function.

[0024] Optionally, upon receiving an intelligent service request from at least one network function, the system interacts with at least one target unit based on the intelligent service request to obtain intelligent services orchestrated for the target object, including:

[0025] Send a resource information query request to the resource management unit and receive resource information from the resource management unit in response to the resource information query request;

[0026] Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results;

[0027] Based on the processing result, a service instance startup request is sent to the intelligent service unit; the service instance startup request is used to trigger the intelligent service unit to start at least one intelligent service instance and / or an instance of a collaborative intelligent service.

[0028] Optionally, the intelligent service is sent to the target object through the intelligent service channel, including:

[0029] The intelligent service is sent to the at least one network function via the bearer channel and the data channel.

[0030] The present invention also provides a service orchestration processing apparatus, the apparatus comprising:

[0031] The receiving module is used to receive intelligent service requests sent by the target object;

[0032] The processing module is configured to interact with at least one target unit according to the intelligent service request, obtain intelligent services orchestrated for the target object, and send the intelligent services to the target object through the intelligent service channel.

[0033] The present invention also provides a communication device, comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the service arrangement processing method described above.

[0034] The present invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform an orchestration processing method for services as described above.

[0035] The above-described solution of the present invention has at least the following beneficial effects:

[0036] By receiving intelligent service requests sent by a target object; interacting with at least one target unit based on the intelligent service requests to obtain intelligent services orchestrated for the target object; and sending the intelligent services to the target object through an intelligent service channel, this approach solves the problem that the separation of intelligence, computing power, and connectivity in 6G networks cannot meet the needs of future networks. It improves the service quality of intelligent services, user convenience, and application experience, and better meets the service needs of intelligent applications. Attached Figure Description

[0037] Figure 1 A flowchart illustrating the service orchestration processing method according to an embodiment of the present invention is shown;

[0038] Figure 2This diagram illustrates a structural schematic of an architecture for intelligent, computing, and network convergence oriented towards a 6G core network, according to an embodiment of the present invention.

[0039] Figure 3 This is a flowchart illustrating a service orchestration method for a receiving terminal sending an intelligent service request through a control plane unit, according to an embodiment of the present invention.

[0040] Figure 4 This is a flowchart illustrating the service orchestration processing method provided by the present invention after receiving the joint learning requirements of the application function and the terminal.

[0041] Figure 5 This is a flowchart illustrating a service orchestration method for receiving a smart service request sent by a network function, according to an embodiment of the present invention.

[0042] Figure 6 A flowchart illustrating a service orchestration processing method for receiving intelligent service requests from at least two network functions, according to an embodiment of the present invention, is shown.

[0043] Figure 7 This is a schematic diagram of the module block of the service orchestration processing device according to an embodiment of the present invention. Detailed Implementation

[0044] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0045] Figure 1 A flowchart illustrating the service orchestration method according to an embodiment of the present invention is shown; as follows: Figure 1 As shown, an embodiment of the present invention provides a service orchestration method, the method comprising:

[0046] Step 11: Receive the smart service request sent by the target object;

[0047] Step 12: Interact with at least one target unit according to the intelligent service request to obtain intelligent services orchestrated for the target object;

[0048] Step 13: Send the intelligent service to the target object through the intelligent service channel.

[0049] This embodiment is applied to an intelligent service orchestration unit. Based on an architecture that integrates intelligence, computing power, and network for the 6G core network, it receives intelligent service requests sent by target objects, interacts with at least one target unit to obtain intelligent services orchestrated for the target objects, and then sends the intelligent services to the target objects through the intelligent service channel. This solves the problem that the separate approach of intelligence, computing power, and connectivity in 6G networks cannot meet the needs of future networks, improves the service quality of intelligent services, and enhances the convenience and application experience for users, thus better meeting the service needs of intelligent applications.

[0050] It should be noted that the intelligent service request initiated can be a single intelligent service, multiple intelligent services, or multiple intelligent service instances corresponding to a single intelligent service. This application does not limit it in this way.

[0051] Figure 2 This illustration shows a schematic diagram of an architecture for intelligent, computing, and network convergence in a 6G core network, based on an embodiment of the present invention; as shown. Figure 2 As shown, it should be noted that the architecture based on the convergence of intelligence, computing power and network for 6G core network consists of a centralized cross-domain functional layer and at least one distributed single domain; in the embodiments of the present invention, AI service orchestration in a single domain is used for illustration, and the network architecture may also include only one single domain or multiple distributed single domains.

[0052] The centralized cross-domain functional layer includes cross-domain connection control, cross-domain service orchestration, and cross-domain routing scheduling, which can provide cross-domain coordination and control functions; while the distributed single-domain layer includes a target area service orchestration module, a target area service routing module, at least one data service module, at least one intelligent service module, a connection control function module, a connection bearer module, a connection software / hardware resource module, and a management module composed of a resource management unit, a data management unit, and a model management unit.

[0053] Furthermore, the connection control module provides bearer establishment and maintenance control functions from the terminal to the core network; the target area service orchestration module provides the ability to build artificial intelligence services, and can query relevant information from the resource management unit, data management unit, and model management unit in the management module. After comprehensive analysis and orchestration based on user needs, user location, user resource status, etc., it applies for the hardware resources and software required for artificial intelligence services, and requests the creation of at least one associated intelligent service and data service workflow. It also applies for and connects data services and / or model services according to user needs; the target area service routing and scheduling module is used to realize routing scheduling and optimization between services after the intelligent service orchestration is completed. At the same time, it works in conjunction with the connection control to jointly ensure the channel quality of the end-to-end intelligent service plane.

[0054] The connection bearer module is used to establish a user plane bearer channel through the connection control function module;

[0055] The connection software / hardware resource module includes software resource units and hardware resource units. The hardware resource units specifically include at least one of CPU (central processing unit), GPU (graphics processing unit), memory, spectrum, and network, which can realize the software and hardware resources required for network connection. Through the connection control function module, connection bearer module, and connection software / hardware resource module, the distributed single domain can have the complete intelligent computing network converged service provision capability and can provide services to users in the region.

[0056] During the intelligent service process, the terminal can transmit service requirements and QoS parameters through the control plane or intelligent bearer plane, and then optimize routes and control QoS policies based on service requirements, network status detection and other information by connecting the control function module and the service routing module.

[0057] In an optional embodiment of the present invention, step 11 includes:

[0058] Step 111: Receive intelligent service requests sent by the terminal and / or application functions through the control plane unit; or

[0059] Step 112: Receive a smart service request sent by at least one network function.

[0060] In this embodiment, the intelligent service orchestration unit can receive intelligent service requests from terminals and / or application functions or at least one network function. Here, the target object in step 11 can be a terminal and / or application function (AF), or a network function (NF), or any other object that interacts with the intelligent service orchestration unit. This application is not limited to this. The intelligent service orchestration unit interacts with terminals, application functions, or at least one network function, and can select interaction objects as needed according to user requirements and create and deploy intelligent service instances, making the provision of intelligent services more flexible and resource-efficient.

[0061] Specifically, intelligent service requests from terminals and / or application functions need to be forwarded to the intelligent service orchestration unit through the control plane unit. Optionally, the terminal and / or application function sends an intelligent service request to the control plane unit. The control plane unit can select a suitable user plane unit based on the location of the terminal and / or application function and initiate the establishment of an intelligent bearer. The establishment of the intelligent bearer here better meets and adapts to the needs of intelligent services. Furthermore, the control plane unit forwards the intelligent service request to the intelligent service orchestration unit.

[0062] It should be noted that the intelligent service request sent by the terminal and / or application function to the control plane unit carries intelligent service requirement parameters, which include at least one of the following: intelligent service type, intelligent service data source requirement, intelligent service model source requirement, intelligent service computation requirement, and intelligent service QoS (Quality of Service) parameter / level.

[0063] Specifically, the preferred types of intelligent services are intelligent inference services and / or intelligent training services; the preferred data source requirements for intelligent services are at least one of terminal upload, public network data source link, operator network data source link, and data interface parameters; the preferred model source requirements for intelligent services are at least one of terminal upload, public network model source link, operator network model source link, and model interface parameters; the preferred computational requirements for intelligent services are streaming computation or batch computation; and the preferred QoS parameters / levels for intelligent services are at least one of latency parameters, jitter parameters, packet loss parameters, or comprehensive level.

[0064] In an optional embodiment of the present invention, step 111 includes:

[0065] Step 1111: Receive a smart service request sent by the terminal and / or application function through the control plane unit. The smart service request carries the parameters required for the smart service and the carrying information of the smart service.

[0066] In this embodiment, the parameters required by the intelligent service carried in the intelligent service request include at least one of the following: type of intelligent service, data source requirements of intelligent service, model source requirements of intelligent service, computational requirements of intelligent service, and QoS (Quality of Service) parameters / levels of intelligent service. When the intelligent service request forwards the terminal and / or application functions to the intelligent service orchestration unit through the control plane unit, the parameters required by the intelligent service will be forwarded to the intelligent service orchestration unit accordingly.

[0067] In an optional embodiment of the present invention, when the receiving terminal sends a smart service request through the control plane unit, step 12 includes:

[0068] Optionally, before step 12a1, the process may further include: receiving a smart service request sent by the control plane unit; querying data information related to the smart service request from the data management unit and / or querying model information related to the smart service request from the model management unit according to the smart service request;

[0069] Step 12a1: Send a resource information query request to the resource management unit and receive the resource information fed back by the resource management unit based on the resource information query request;

[0070] Step 12a2: Perform intelligent service analysis and orchestration based on the resource information; Optionally, perform intelligent service analysis and orchestration based on the resource information, the data information, and the model information to obtain the processing result;

[0071] Step 12a3: Based on the processing result, send a service instance startup request to the intelligent service unit; the service instance startup request is used to trigger the intelligent service unit to start an instance of the intelligent service.

[0072] Optionally, step 12a3 may also include:

[0073] Step 12a4: Receive the intelligent service scheduling requirements and parameter configurations fed back by the inter-service routing scheduling unit based on the instance of the intelligent service;

[0074] Step 12a5: Feedback the intelligent service request establishment response to the control plane unit.

[0075] In an optional embodiment of the present invention, step 13 includes:

[0076] Step 13a1: Send the intelligent service to the terminal through the bearer channel and the data channel. Figure 3 This illustration shows a flowchart of a service orchestration method for a receiving terminal sending an intelligent service request via a control plane unit, according to an embodiment of the present invention. Figure 3 As shown in this embodiment, the specific process of a terminal requesting intelligent services includes:

[0077] 1. The terminal completes the user registration process.

[0078] 2. The terminal initiates an AI (Artificial Intelligence) service request to the control plane unit, carrying AI service requirement parameters, including, for example, the type of AI service (e.g., AI inference, AI training service), the data source requirements of the AI ​​service (e.g., uploaded by the terminal, public network data source link, carrier network data source link, data interface parameters), the model source requirements of the AI ​​service (e.g., uploaded by the terminal, public network model source link, carrier network model source link, model interface parameters), the computing requirements of the AI ​​service (streaming computing, batch computing, etc.), and the QoS parameters or level of the AI ​​service (latency, jitter, packet loss, or comprehensive level).

[0079] 3. Based on the service request requirements and user location information, the control plane unit sends an AI bearer pre-establishment request to the UPF (User Plane Function) unit.

[0080] 4. Send an AI bearer pre-establishment request to the terminal.

[0081] 5. Send an AI service establishment request to the service orchestration unit, which includes the AI ​​service requirements parameters and AI host information.

[0082] 6. Optionally, the service orchestration unit may query the data management unit for data information related to the AI ​​service as needed.

[0083] 7. Optionally, the service orchestration unit may query the model management unit for model information related to the AI ​​service as needed.

[0084] 8. The service orchestration unit queries the resource management unit for relevant software and hardware resource information.

[0085] 9. The service orchestration unit performs comprehensive analysis and process orchestration based on AI service requirements, as well as information such as hardware and software resources, data, and model information.

[0086] 10. The service orchestration unit initiates a request for hardware and software resources to the resource management unit.

[0087] 11. Optionally, the service orchestration unit may start data service instances as needed to provide data processing services to external parties.

[0088] 12. The service orchestration unit creates and starts an AI service instance, which integrates the above service processes and serves as an external service interface to provide AI services.

[0089] 13. The service orchestration unit sends the AI ​​service scheduling requirements and parameter configurations to the inter-service routing and scheduling unit. Subsequently, the inter-service routing and scheduling unit is responsible for ensuring the quality of data transmission channels between services.

[0090] 14. The service orchestration unit responds to the AI ​​service establishment request from the control plane unit and indicates that the AI ​​service establishment is complete.

[0091] 15. The control plane unit sends an AI bearer channel activation message to the UPF.

[0092] 16. The control plane unit sends an AI service establishment request response to the terminal UE.

[0093] At this point, the AI ​​transport channel and the data channel for AI services are established. The AI ​​data plane transmission protocol can use a rich semantic IP protocol (e.g., SRV6), where QoS requirements and status information are carried within the rich semantics. After detection by the transport plane, these are reported to the control plane for routing and scheduling decisions. Alternatively, QoS requirements and status information can be transmitted through the control plane. The processing results of AI services, such as training models and inference results, are either stored in the model library or delivered to the terminal, depending on the configuration at the time of request.

[0094] In this embodiment, the intelligent service is sent to the terminal through the bearer channel and the data channel. When the data is sent through the data channel, the data plane transmission protocol can adopt the rich semantic IP (Internet Protocol) protocol (preferably SRV6 protocol). The QoS requirements, status information and other indications can be carried in the rich semantics. After being detected by the bearer plane, it is sent to the control plane unit for routing and scheduling decision. Alternatively, the QoS requirements and status information can be directly transmitted through the control plane unit. The processing result of the intelligent service can be stored in the terminal or the model management unit according to the configuration when the intelligent service establishment request is sent.

[0095] In this embodiment, the intelligent service channel includes a bearer channel and a data channel. The bearer channel is the channel between the intelligent service orchestration unit and the terminal, and the data channel is the channel between the intelligent service orchestration unit and the intelligent service unit. If the data service unit triggers a data service instance before the intelligent service unit triggers an intelligent service instance, then the data channel also includes the channel between the intelligent service orchestration unit and the data service unit.

[0096] In an optional embodiment of the present invention, when receiving the joint learning requirements of the application function and the terminal, and then sending an intelligent service request through the control plane unit, step 12 includes:

[0097] Optionally, before step 12b1, the process may further include: receiving a smart service request sent by the control plane unit; querying data information related to the smart service request from the data management unit and / or querying model information related to the smart service request from the model management unit according to the smart service request;

[0098] Step 12b1: Send a resource information query request to the resource management unit and receive the resource information fed back by the resource management unit based on the resource information query request;

[0099] Step 12b2: Perform intelligent service analysis and orchestration based on the resource information; Optionally, perform intelligent service analysis and orchestration based on the resource information, the data information, and the model information to obtain the processing result;

[0100] Step 12b3: Based on the processing result, send a collaborative service instance startup request to the inter-service routing scheduling unit; the collaborative service instance startup request is used to trigger the inter-service routing scheduling unit to start an instance of the collaborative intelligent service.

[0101] Optionally, step 12b3 may also include:

[0102] Step 12b4: Receive the intelligent service scheduling requirements and parameter configurations from the inter-service routing scheduling unit based on the service instance startup request;

[0103] Step 12b5: Send a smart service request to the application function to establish a response;

[0104] Step 12b6: Receive the application function intelligent joint learning result subscription request and forward the intelligent joint learning result subscription request to the collaborative intelligent service instance unit.

[0105] In an optional embodiment of the present invention, step 13 includes:

[0106] Step 13b1: Send the intelligent service to the application function through the bearer channel and the data channel.

[0107] Figure 4 This diagram illustrates a flowchart of a service orchestration method provided by an embodiment of the present invention, which receives the joint learning requirements of application functions and terminals; as shown below. Figure 4 As shown, in this embodiment, after receiving the joint learning request from the application function (AF) and the terminal, the application function and the terminal interact with the control plane unit, and the control plane unit initiates an intelligent service request to the intelligent service orchestration unit. The specific process includes:

[0108] 1. The AF requests AI federated learning services from the control plane unit through the network's external interface, carrying AI service parameters and terminal information requesting to join the federated learning.

[0109] 2. The control plane unit locates the corresponding terminal based on the terminal information carried by the AF, and sends an AI joint learning invitation to the terminal according to the joint learning requirements.

[0110] 3. After accepting the invitation to participate in AI joint learning, the terminal initiates an AI service establishment request to the control plane unit.

[0111] 4. The control plane unit sends a compute bearer pre-establishment request to the selected user plane unit.

[0112] 5. The control plane unit sends a computing bearer pre-establishment request to the terminal.

[0113] 6. The control plane unit sends an AI service establishment request to the service orchestration unit, carrying the AI ​​service requirement parameters and the AI ​​carrying information of the corresponding terminal.

[0114] 7. Optionally, the service orchestration unit may query the data management unit for data information related to the AI ​​service as needed.

[0115] 8. Optionally, the service orchestration unit may query the model management unit for model information related to the AI ​​service as needed.

[0116] 9. The service orchestration unit queries the resource management unit for relevant software and hardware resource information.

[0117] 10. The service orchestration unit performs comprehensive analysis and process orchestration based on AI service requirements, as well as information such as hardware and software resources, data information, and model information.

[0118] 11. The service orchestration unit initiates a request for hardware and software resources to the resource management unit.

[0119] 12. Optionally, the service orchestration unit may start data service instances as needed to provide data processing services to external parties.

[0120] 13. The service orchestration unit initiates AI service instances. Depending on the specific scenario, AI services can be multiple AI services providing services to different terminals, a single collaborative AI service (providing collaborative learning to terminal AI services), or a single collaborative AI service directly providing collaborative learning services to all terminals. The collaborative AI service is responsible for coordinating multiple AI (training) services participating in collaborative learning, such as integrating and distributing model training gradients, controlling the number of model training iterations, and comprehensively setting the parameters for collaborative learning training based on factors such as the computing power and transmission performance of each collaborative learning node.

[0121] 14. The service orchestration unit sends AI service scheduling requirements and parameter configurations to the inter-service routing and scheduling module. Subsequently, the inter-service routing and scheduling unit is responsible for ensuring the quality of data transmission channels between services.

[0122] 15. The service orchestration unit responds to the AI ​​service establishment request from the control plane unit and indicates that the AI ​​service establishment is complete.

[0123] 16. The control plane unit sends an AI bearer channel activation message to the UPF.

[0124] 17. The control plane unit sends an AI service request to the terminal to establish a response.

[0125] 18. The control plane unit sends an AI joint learning service request to the AF to establish a response.

[0126] 19. AF sends a subscription request for the AI ​​joint learning results to the control plane unit.

[0127] 20. The control plane unit sends an AI joint learning result subscription request to the service orchestration unit.

[0128] 21. The service orchestration unit sends an AI joint learning result subscription request to the collaborative intelligent service instance.

[0129] At this point, the AI ​​transport channel and the data channel for AI services are established. The AI ​​data plane transmission protocol can use a rich semantic IP protocol (e.g., SRV6), where QoS requirements and status information are carried within the rich semantics. After detection by the transport plane, these are reported to the control plane for routing and scheduling decisions. Alternatively, QoS requirements and status information can be transmitted through the control plane. The results of the joint learning are stored in the model library or delivered to the terminal, depending on the configuration at the time of the request.

[0130] Based on the subscription configuration of the AI ​​joint learning results, the AI ​​collaborative instance reports the joint learning result data to AF through the network external open unit.

[0131] In this embodiment, the intelligent service is sent to the terminal through the bearer channel and the data channel. When the data is sent through the data channel, the data plane transmission protocol can adopt the rich semantic IP protocol (preferably the SRV6 protocol). The QoS requirements, status information and other indications can be carried in the rich semantics. After being detected by the bearer plane, it is sent to the control plane unit for routing scheduling decision. Alternatively, the QoS requirements and status information can be directly transmitted through the control plane unit. The intelligent joint learning results are stored in the terminal or the model management unit according to the configuration at the time of request.

[0132] The intelligent service channel in this embodiment includes a bearer channel and a data channel. The bearer channel is the channel between the intelligent service orchestration unit and the terminal, and the data channel is the channel between the intelligent service orchestration unit and the intelligent service unit and the collaborative intelligent service instance. If the data service unit triggers the data service instance before the intelligent service unit triggers the intelligent service instance, then the data channel also includes the channel between the intelligent service orchestration unit and the data service unit.

[0133] In an optional embodiment of the present invention, when receiving an artificial intelligence service request sent by at least one network function, step 12 includes:

[0134] Optionally, before step 12c1, the process may further include: receiving a smart service request sent by the network function; querying the data management unit for data information related to the smart service request and / or the model management unit for model information related to the smart service request based on the smart service request;

[0135] Step 12c1: Send a resource information query request to the resource management unit and receive the resource information fed back by the resource management unit based on the resource information query request;

[0136] Step 12c2: Analyze and orchestrate intelligent services based on the resource information; Optionally, analyze and orchestrate intelligent services based on the resource information, data information, and model information to obtain the processing result.

[0137] Step 12c3: Send a service instance startup request to the intelligent service unit; the service instance startup request is used to trigger the intelligent service unit to start at least one intelligent service instance and / or an instance of a collaborative intelligent service;

[0138] Optionally, step 12c3 may also include:

[0139] Step 12c4: Receive the intelligent service scheduling requirements and parameter configurations from the inter-service routing scheduling unit based on the service instance startup request;

[0140] Step 12c5: Feedback the intelligent service request response to the network function.

[0141] In an optional embodiment of the present invention, step 13 includes:

[0142] Step 13c1: Send the intelligent service to the at least one network function via the bearer channel and the data channel.

[0143] In this embodiment, the intelligent service channel includes a bearer channel and a data channel. The bearer channel is the channel between the intelligent service orchestration unit and the network function, and the data channel is the channel between the intelligent service orchestration unit, the intelligent service unit, and the collaborative intelligent service instance unit. If the data service unit triggers the data service instance before the intelligent service unit triggers the intelligent service instance, then the data channel also includes the channel between the intelligent service orchestration unit and the data service unit.

[0144] The intelligent service channel can receive intelligent service requests sent by a network function, and it can also receive intelligent service requests sent by at least one network function through intelligent joint learning, thereby improving the efficiency of control information transmission and ensuring the quality of intelligent services.

[0145] Figure 5 This illustration shows a flowchart of a service orchestration method for receiving a smart service request sent by a network function, according to an embodiment of the present invention; as shown below. Figure 5 As shown, in a specific embodiment 1, when only one network function (NF) requests intelligent services, it includes:

[0146] 1.NF requests AI services from the service orchestration unit, carrying the AI ​​service requirement parameters.

[0147] 2. Optionally, the service orchestration unit may query the data management unit for data information related to the AI ​​service as needed.

[0148] 3. Optionally, the service orchestration unit may query the model management unit for model information related to the AI ​​service as needed.

[0149] 4. The service orchestration unit queries the resource management unit for relevant software and hardware resource information.

[0150] 5. The service orchestration unit performs comprehensive analysis and process orchestration based on AI service requirements, as well as information such as hardware and software resources, data, and model information.

[0151] 6. The service orchestration unit initiates a request for hardware and software resources to the resource management unit.

[0152] 7. Optionally, the service orchestration unit may start data service instances as needed to provide data processing services to external parties.

[0153] 8. The service orchestration unit starts the AI ​​service instance.

[0154] 9. The service orchestration unit sends the AI ​​service scheduling requirements and parameter configurations to the inter-service routing and scheduling module. Subsequently, the routing and scheduling unit is responsible for ensuring the quality of data transmission channels between services.

[0155] The data channel for AI services is now established. AI data plane transmission can utilize rich semantic IP protocols (e.g., SRV6), where QoS requirements and status information are carried within the rich semantics. This information is detected by the bearer plane and reported to the control plane for routing and scheduling decisions. Alternatively, QoS requirements and status information can be transmitted through the control plane. The processing results of AI services, such as training models and inference results, are either stored in the model library or handed over to network function 1, depending on the configuration at the time of request.

[0156] Figure 6This diagram illustrates a flowchart of a service orchestration method for receiving intelligent service requests from at least two network functions, according to an embodiment of the present invention. Figure 6 As shown, multi-NF joint learning scenario

[0157] 1. Network function 1 requests AI joint learning services from the service orchestration unit, carrying AI service requirement parameters.

[0158] 2. The service orchestration unit finds the corresponding network function 2 participating in the joint service based on the request, and initiates an AI joint service request to network function 2.

[0159] 3. After receiving the federated service request, Network Function 2 initiates an AI federated service request to the Service Orchestration Unit.

[0160] 4. Optionally, the service orchestration unit may query the data management unit for data information related to the AI ​​service as needed.

[0161] 5. Optionally, the service orchestration unit may query the model management unit for model information related to the AI ​​service as needed.

[0162] 6. The service orchestration unit queries the resource management unit for relevant software and hardware resource information.

[0163] 7. The service orchestration unit performs comprehensive analysis and process orchestration based on AI service requirements, as well as information such as software and hardware resources, data, and models.

[0164] 8. The service orchestration unit initiates a request for hardware and software resources to the resource management unit.

[0165] 9. Optionally, the service orchestration unit may start data service instances as needed to provide data processing services to external parties.

[0166] 10. The service orchestration unit starts a collaborative AI service instance.

[0167] 11. The Service Orchestration Unit starts an AI service instance 1.

[0168] 12. The service orchestration unit starts AI service 2 instances.

[0169] 13. The service orchestration unit sends AI service scheduling requirements and parameter configurations to the inter-service routing and scheduling module. Subsequently, the routing and scheduling unit is responsible for ensuring the quality of data transmission channels between services.

[0170] The data channel for AI services is now established. AI data plane transmission can utilize a semantically rich IP protocol (e.g., SRV6), where QoS requirements and status information are carried within the rich semantics. This information is detected by the bearer plane and reported to the control plane for routing and scheduling decisions. Alternatively, QoS requirements and status information can be transmitted through the control plane. The results of joint learning are stored in the model library or delivered to the network function entity based on the configuration at the time of the request.

[0171] The embodiments of the present invention receive intelligent service requests sent by a target object; interact with at least one target unit according to the intelligent service requests to obtain intelligent services orchestrated for the target object; and send the intelligent services to the target object through an intelligent service channel. This solves the problem that the separate approach of intelligence, computing power, and connectivity in 6G networks cannot meet the needs of future networks, improves the service quality of intelligent services and the convenience and application experience for users, better meets the service requirements of intelligent applications, and enables the creation and deployment of intelligent service instances on demand according to user needs. This makes the provision of intelligent services more flexible and resource-efficient, while also improving the efficiency of control information transmission and ensuring the quality of intelligent services.

[0172] like Figure 7 As shown, embodiments of the present invention also provide a service orchestration processing apparatus 70, the apparatus 70 comprising:

[0173] The receiving module 71 is used to receive intelligent service requests sent by the target object;

[0174] The processing module 72 is configured to interact with at least one target unit according to the intelligent service request, obtain intelligent services orchestrated for the target object, and send the intelligent services to the target object through an artificial intelligence service channel.

[0175] Optionally, the receiving module 71 includes:

[0176] The first receiving submodule is used to receive intelligent service requests sent by the terminal and / or application functions through the control plane unit. The intelligent service requests carry parameters required by the intelligent service and the bearing information of the intelligent service.

[0177] Optionally, when the receiving terminal sends an intelligent service request through the control plane unit, it interacts with at least one target unit according to the intelligent service request to obtain intelligent services orchestrated for the target object, including:

[0178] Send a resource information query request to the resource management unit and receive resource information from the resource management unit in response to the resource information query request;

[0179] Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results;

[0180] Based on the processing result, a service instance startup request is sent to the intelligent service unit; the service instance startup request is used to trigger the intelligent service unit to start an instance of the intelligent service.

[0181] Optionally, the intelligent service is sent to the target object through the intelligent service channel, including:

[0182] The intelligent service is sent to the terminal through the bearer channel and the data channel.

[0183] Optionally, receive smart service requests sent by the target object, including:

[0184] Receive intelligent service requests from at least one network function.

[0185] Optionally, upon receiving the joint learning requirements of the application function and the terminal, when sending an intelligent service request through the control plane unit, the system interacts with at least one target unit according to the intelligent service request to obtain intelligent services orchestrated for the target object, including:

[0186] Send a resource information query request to the resource management unit and receive resource information from the resource management unit in response to the resource information query request;

[0187] Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results;

[0188] Based on the processing result, a collaborative service instance startup request is sent to the inter-service routing scheduling unit; the collaborative service instance startup request is used to trigger the inter-service routing scheduling unit to start an instance of the collaborative intelligent service.

[0189] Optionally, the intelligent service is sent to the target object through the intelligent service channel, including:

[0190] The intelligent service is sent to the application function through the bearer channel and the data channel.

[0191] Optionally, upon receiving an intelligent service request from at least one network function, the system interacts with at least one target unit based on the intelligent service request to obtain intelligent services orchestrated for the target object, including:

[0192] Send a resource information query request to the resource management unit and receive resource information from the resource management unit in response to the resource information query request;

[0193] Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results;

[0194] Based on the processing result, a service instance startup request is sent to the intelligent service unit; the service instance startup request is used to trigger the intelligent service unit to start at least one intelligent service instance and / or an instance of a collaborative intelligent service.

[0195] Optionally, the intelligent service is sent to the target object through the intelligent service channel, including:

[0196] The intelligent service is sent to the at least one network function via the bearer channel and the data channel.

[0197] It should be noted that this device is a device corresponding to the above-mentioned service orchestration processing method. All implementations of the above-mentioned method are applicable to the embodiments of this device and can achieve the same technical effect. The device also includes a processing module 72 for processing the information received by the receiving module 71.

[0198] Embodiments of the present invention also provide a communication device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0199] Embodiments of the present invention also provide a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0200] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0201] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0202] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0203] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0204] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0205] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0206] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above-described series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0207] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0208] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A service orchestration method, characterized in that, The method includes: Receive intelligent service requests sent by the target object; Based on the intelligent service request, interact with at least one target unit to obtain intelligent services orchestrated for the target object; The intelligent service is sent to the target object through the intelligent service channel; The process of receiving the intelligent service request sent by the target object includes: The receiving terminal and / or application function send a smart service request through the control plane unit. The smart service request carries the parameters required for the smart service and the bearing information of the smart service. The smart service requirement parameters include at least one of the following: type of smart service, data source requirement of smart service, model source requirement of smart service, computing requirement of smart service, and QoS service quality parameter / level of smart service. The step of interacting with at least one target unit according to the intelligent service request to obtain intelligent services orchestrated for the target object includes: Send a resource information query request to the resource management unit and receive resource information from the resource management unit in response to the resource information query request; Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results; Based on the processing result, a service instance startup request is sent to the intelligent service unit; the service instance startup request is used to trigger the intelligent service unit to start an instance of the intelligent service.

2. The service orchestration method according to claim 1, characterized in that, Sending the intelligent service to the target object through the intelligent service channel includes: The intelligent service is sent to the terminal through the bearer channel and the data channel.

3. The service orchestration method according to claim 2, characterized in that, Upon receiving the joint learning requirements of the application function and the terminal, when a smart service request is sent through the control plane unit, the system interacts with at least one target unit according to the smart service request to obtain smart services orchestrated for the target object, including: Send a resource information query request to the resource management unit and receive resource information from the resource management unit in response to the resource information query request; Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results; Based on the processing result, a collaborative service instance startup request is sent to the inter-service routing scheduling unit; the collaborative service instance startup request is used to trigger the inter-service routing scheduling unit to start an instance of the collaborative intelligent service.

4. The service orchestration method according to claim 3, characterized in that, Sending the intelligent service to the target object through the intelligent service channel includes: The intelligent service is sent to the application function through the bearer channel and the data channel.

5. The service orchestration method according to claim 1, characterized in that, Receiving intelligent service requests sent by the target object also includes: Receive intelligent service requests from at least one network function.

6. The service orchestration method according to claim 5, characterized in that, When receiving an intelligent service request from at least one network function, the system interacts with at least one target unit based on the intelligent service request to obtain intelligent services orchestrated for the target object, including: Send a resource information query request to the resource management unit and receive resource information from the resource management unit in response to the resource information query request; Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results; Based on the processing result, a service instance startup request is sent to the intelligent service unit; the service instance startup request is used to trigger the intelligent service unit to start at least one intelligent service instance and / or an instance of a collaborative intelligent service.

7. The service orchestration method according to claim 6, characterized in that, Sending the intelligent service to the target object through the intelligent service channel includes: The intelligent service is sent to the at least one network function via the bearer channel and the data channel.

8. A service orchestration processing apparatus, characterized in that, The device includes: The receiving module is used to receive intelligent service requests sent by the target object; The processing module is configured to interact with at least one target unit according to the intelligent service request, obtain intelligent services orchestrated for the target object, and send the intelligent services to the target object through the intelligent service channel; The receiving module includes: The first receiving submodule is used to receive intelligent service requests sent by the terminal and / or application functions through the control plane unit. The intelligent service request carries parameters required by the intelligent service and the bearing information of the intelligent service. The intelligent service requirement parameters include at least one of the following: type of intelligent service, data source requirement of intelligent service, model source requirement of intelligent service, computing requirement of intelligent service, and QoS service quality parameter / level of intelligent service. The processing module is also used for: Send a resource information query request to the resource management unit and receive resource information from the resource management unit in response to the resource information query request; Based on the resource information, intelligent services are analyzed and orchestrated to obtain the processing results; Based on the processing result, a service instance startup request is sent to the intelligent service unit; the service instance startup request is used to trigger the intelligent service unit to start an instance of the intelligent service.

9. A communication device, characterized in that, include: A processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the service orchestration processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A storage instruction that, when executed on a computer, causes the computer to perform the orchestration processing method of the service as described in any one of claims 1 to 7.

Images