6g network-based ai service resource orchestration method and apparatus, device, medium, and product

Abstract

The application discloses an AI service resource arrangement method and device based on a 6G network, equipment, a medium and a product, and the method comprises the following steps: acquiring AI service arrangement parameters, hardware resource information and AI service information; arranging resource types and resource sizes according to the AI service arrangement parameters, the hardware resource information and the AI service information, generating an arrangement result, and sending the arrangement result to a corresponding function module. According to the AI service resource arrangement based on the AI service arrangement parameters, the application can effectively improve resource utilization and AI service quality, and save costs.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method, apparatus, device, medium and product for orchestrating AI service resources based on a 6G network. Background Technology

[0002] In the current cost of AI services, besides the significant upfront development costs, the subsequent hardware, energy, and maintenance costs are also substantial expenses. Therefore, proper resource allocation can improve hardware utilization and reduce maintenance costs. Existing cloud and edge AI service solutions are all add-on, making it difficult to guarantee the factuality, validity, and consistency of data. Furthermore, the network, acting as a transparent conduit, struggles to efficiently utilize its resources such as sensing and computing to ensure the quality of AI services. Therefore, networks designed for 6G-based endogenous AI will provide AI services across multiple scenarios.

[0003] In an endogenous AI network architecture geared towards 6G wireless services, various functions will exist as separate modules. Business requirements will dictate which functions to combine and establish the necessary links. AI services will follow a similar approach, but with a key difference: 6G networks will need to add new AI task management, AI model storage, and computation execution functions. Using these functions presents two challenges: first, the AI ​​service needs to orchestrate and decide which functions to activate; second, the AI ​​service needs to allocate resources to these functions based on demand to improve resource utilization and save costs. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, apparatus, device, medium and product for orchestrating AI service resources based on 6G network. By orchestrating AI service resources according to AI service orchestration parameters, the resource utilization rate and AI service quality can be effectively improved and costs can be saved.

[0005] To achieve the above objectives, embodiments of the present invention provide an AI service resource orchestration method based on a 6G network, comprising:

[0006] Obtain AI service orchestration parameters, hardware resource information, and AI service information;

[0007] Based on the AI ​​service orchestration parameters, the hardware resource information, and the AI ​​service information, the resource types and sizes are orchestrated, an orchestration result is generated, and the orchestration result is sent to the corresponding functional modules.

[0008] As an improvement to the above solution, the acquisition of AI service orchestration parameters includes:

[0009] Obtain pre-configured AI service orchestration parameters, wherein the pre-configured AI service orchestration parameters include at least one of the following parameters:

[0010] AI service scope;

[0011] AI service area types;

[0012] AI service orchestration cycle.

[0013] As an improvement to the above solution, the AI ​​service range is the area where one or more base stations provide AI services;

[0014] The AI ​​service area types include dense, mobile-intensive, and distributed types, and the corresponding resource sizes are ordered as mobile-intensive > dense > distributed.

[0015] As an improvement to the above solution, the acquisition of AI service orchestration parameters includes:

[0016] Receive service requests sent by the terminal;

[0017] The AI ​​service orchestration parameters are obtained by parsing the corresponding business feature parameters based on the business request.

[0018] As an improvement to the above solution, the business characteristic parameters include at least one of the following parameters:

[0019] Terminal type;

[0020] Business type.

[0021] As an improvement to the above solution, the method further includes:

[0022] Resource utilization rate for acquiring AI services;

[0023] The AI ​​service resources are rearranged based on the resource utilization rate.

[0024] This invention also provides an AI service resource orchestration device based on a 6G network, comprising:

[0025] The data acquisition module is used to acquire AI service orchestration parameters, hardware resource information, and AI service information.

[0026] The resource orchestration module is used to orchestrate resource types and sizes based on the AI ​​service orchestration parameters, the hardware resource information, and the AI ​​service information, generate orchestration results, and send the orchestration results to the corresponding functional modules.

[0027] This invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the AI ​​service resource orchestration method based on a 6G network as described above.

[0028] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to execute the AI ​​service resource orchestration method based on a 6G network as described above.

[0029] This invention also provides a computer program product, which includes a computer program or computer instructions. When the computer program or computer instructions are executed by a processor, they implement the AI ​​service resource orchestration method based on a 6G network described above.

[0030] Compared to existing technologies, the beneficial effects of the AI ​​service resource orchestration method, apparatus, device, medium, and product based on a 6G network provided by this invention are as follows: By acquiring AI service orchestration parameters, hardware resource information, and AI service information; based on the AI ​​service orchestration parameters, hardware resource information, and AI service information, the resource types and sizes are orchestrated, an orchestration result is generated, and the orchestration result is sent to the corresponding functional modules. This invention, by orchestrating AI service resources according to AI service orchestration parameters, can effectively improve resource utilization and AI service quality while saving costs. Attached Figure Description

[0031] Figure 1 This is a flowchart illustrating a preferred embodiment of an AI service resource orchestration method based on a 6G network provided by the present invention.

[0032] Figure 2 This is a schematic diagram of the first process of an AI service resource orchestration method based on a 6G network provided by the present invention;

[0033] Figure 3 This is a schematic diagram of the second process of an AI service resource orchestration method based on a 6G network provided by the present invention;

[0034] Figure 4 This is a schematic diagram of a preferred embodiment of an AI service resource orchestration device based on a 6G network provided by the present invention;

[0035] Figure 5 This is a schematic diagram of a preferred embodiment of a terminal device provided by the present invention. Detailed Implementation

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] Please see Figure 1 , Figure 1 This is a flowchart illustrating a preferred embodiment of an AI service resource orchestration method based on a 6G network provided by the present invention. The AI ​​service resource orchestration method based on a 6G network includes:

[0038] S1, obtain AI service orchestration parameters, hardware resource information and AI service information;

[0039] S2, based on the AI ​​service orchestration parameters, the hardware resource information, and the AI ​​service information, orchestrate the resource types and resource sizes, generate orchestration results, and send the orchestration results to the corresponding functional modules.

[0040] It's worth noting that as artificial intelligence is applied more widely across various industries and the number of people using it increases, the rational allocation of resources is a crucial step in improving resource utilization and reducing costs. Currently, cloud servers and edge servers provide AI services in various ways, such as virtual machines, bare metal servers, and containers. Among these, containers offer key advantages for AI services, including environmental consistency, fast startup, isolation, portability, and ease of management, and may become the main method for future wireless network deployments.

[0041] Orchestration refers to the process of initially / adjusting the deployment of AI service resources, including the startup, scaling up and down of resources (containers) such as computing and models at or between base stations, and message interaction between resources (containers).

[0042] A container is a lightweight, portable, and self-sufficient software runtime environment that allows developers to package applications and their dependencies together so that they can run consistently across different environments. At the heart of container technology is containerization, which provides an isolation mechanism that allows applications to run in independent containers without interfering with each other.

[0043] Based on this, this invention provides an AI service resource orchestration method for 6G networks with endogenous AI, by acquiring AI service orchestration parameters, hardware resource information, and AI service information. The AI ​​service orchestration parameters can be pre-configured or obtained based on terminal service requests. Hardware resource information can be obtained from a cloud management center, which has the function of uniformly managing wireless computing resources within a region. AI service information can be authorized AI service information obtained from a service application marketplace, such as AI service model files. The service application marketplace can be a third-party marketplace or one within a network operator. Then, based on the AI ​​service orchestration parameters, hardware resource information, and AI service information, the resource type and size are orchestrated, an orchestration result is generated, and the orchestration result is sent to the corresponding functional module (i.e., container) to activate the corresponding AI service resource. The functional module includes at least one of the following: AI task management, AI model storage, and computation execution functions.

[0044] It's important to note that AI service containers are divided into control plane containers and user plane containers. The AI ​​model storage can serve as both the control plane and the data plane, as its container can monitor model updates and performance data control plane information through feedback from the computation execution unit, and can also transmit model data to the execution unit and link forwarding unit. AI service orchestration involves launching the wireless network function containers and establishing connections between them.

[0045] This invention, by orchestrating AI service resources according to AI service orchestration parameters, can effectively improve resource utilization and AI service quality while saving costs.

[0046] In another preferred embodiment, obtaining the AI ​​service orchestration parameters includes:

[0047] Obtain pre-configured AI service orchestration parameters, wherein the pre-configured AI service orchestration parameters include at least one of the following parameters:

[0048] AI service scope;

[0049] AI service area types;

[0050] AI service orchestration cycle.

[0051] Specifically, considering the different types of business, there are two ways to launch AI service resource containers. One is for widely applied AI inference tasks that occur within a short timeframe, such as an image recognition or language translation task. This type of business targets a wide range of users, involves numerous random and discrete requests, and is considered a general-purpose AI service. The network should have the general capability to serve these AI tasks at any time. Therefore, AI service resource containers can be orchestrated through pre-configuration, such as for question-answering AI service applications like large models. The pre-configured AI service orchestration function configures and adjusts resource allocation based on the feedback feature parameters. It launches AI service-related container resources for one or more base stations through manual configuration or by downloading the container launch configuration file from the core node (core network). This pre-configured AI service can improve the response time of AI services, thereby improving the quality of general-purpose AI services. The pre-configured AI service orchestration parameters include at least one of the following:

[0052] AI service scope;

[0053] AI service area types;

[0054] AI service orchestration cycle.

[0055] The AI ​​service range (km) M represents the area where one or more base stations provide AI services. It generally depends on the actual coverage area of ​​the base station and can be obtained by measuring the strength of the antenna input signal power, reported by the physical layer. However, considering factors such as latency and transmission rate, AI services may not be available to users with poor signal quality at the edge. Therefore, M is typically set slightly smaller than the actual coverage area of ​​the base station to ensure a more accurate determination of the AI ​​service range and prevent resource waste caused by an excessively large range. For example, the AI ​​service range for 5G base stations is around 100 km. A larger M value allows for the orchestration and initiation of more container resources and types.

[0056] AI service area type A includes densely populated areas, such as office buildings and shopping malls; mobile-intensive areas, such as amusement parks and scenic spots, industrial parks, and main traffic arteries; and dispersed areas, such as suburbs, grasslands, and mountainous regions. The corresponding resource sizes for activation are ordered as mobile-intensive > dense > dispersed. Setting resource sizes according to density can avoid resource queuing and thus congestion.

[0057] The AI ​​service orchestration cycle T, considering the tidal phenomenon of most user activity times, can be set to schedule at 6 AM daily, with rescheduling every 12 hours. For special areas, such as shopping malls and tourist attractions, where there are weekdays and weekends, the cycle T can be set to reschedule AI services during the alternation of weekdays and weekends. This periodic AI service orchestration, based on tidal phenomena, facilitates dynamic resource adjustment and improves resource utilization.

[0058] For AI service scope M, AI service area type A, and AI service orchestration cycle T, a calculation formula for computing resources is provided: F(x+T)=f(x); where x is the set (M, A), and the value of A decreases in the order of mobile intensive > intensive > distributed.

[0059] It should be noted that when orchestrating AI service resources using the pre-configuration method, orchestration results can also be configured manually or generated by upper-layer nodes (core network), such as determining how much computing resources to activate and allocating high- or low-precision models. This method of orchestration occurs at higher nodes and can be directly deployed by operators, facilitating unified management of general AI computing resources by single or multiple base stations.

[0060] This invention employs a pre-configured method for AI service resource orchestration, which improves the response speed of initial AI services and is more suitable for discrete, random, and general-purpose AI services. This pre-configured orchestration method enhances automation and intelligence on the wireless side, facilitating the rational allocation of resources within a certain range.

[0061] In yet another preferred embodiment, obtaining the AI ​​service orchestration parameters includes:

[0062] Receive service requests sent by the terminal;

[0063] The AI ​​service orchestration parameters are obtained by parsing the corresponding business feature parameters based on the business request.

[0064] Specifically, considering the different types of business, there are two ways to launch AI service resource containers. The other is for long-term or B2B customized AI services, such as environmental monitoring and AI-generated video services. In this case, a container matching the specific business needs can be launched, making it more suitable for customized services and facilitating billing and management. This business-demand-driven AI service orchestration improves network resource utilization, eliminating the need to reserve resources for AI service requests. By receiving business requests from terminals, which carry identifiers such as Uai for different terminal types in different scenarios and Up for customized services, the corresponding business characteristic parameters of the request are parsed to obtain AI service orchestration parameters. These business characteristic parameters include at least one of the following:

[0065] Terminal type;

[0066] Business type.

[0067] In a business-demand-driven orchestration approach, when container resources are scarce, resource utilization reaches 95% (compared to pre-configured business, business-driven resources have less uncertainty, so a relatively high threshold can be set), and feedback is provided. The AI ​​service orchestration function then performs scaling up and down.

[0068] It's important to note that UAI (User Acquisition) is a terminal type label for different scenarios and terminal types. For specific smart terminal types, such as smart cars and transportation robots, which have similar AI business needs including navigation planning, road and pedestrian recognition, dedicated AI models are required. These terminals, providing similar AI services, are labeled as Category 1. When the terminal starts, a business request is established, and the relevant containers are launched. Similarly, home companion robots and smart tutoring terminals, which need to provide real-time question-and-answer and other AI services, require knowledge-rich models to generate downlink data and are labeled as Category 2. Different resource containers are configured for different types of terminals and their corresponding services. Category 1 terminals are allocated resources with less memory and computation but higher model accuracy, while Category 2 terminals are allocated resources with more memory and computation to run specialized large models.

[0069] Customized services (Up) refer to B2B businesses that are designed for customization, such as environmental monitoring in factories, video surveillance, and video generation services for media companies (similar to video production). These services involve pre-signing contracts, and when the business starts, container resources within a fixed range are allocated to serve this business based on the signed contract.

[0070] In yet another preferred embodiment, the method further includes:

[0071] Resource utilization rate for acquiring AI services;

[0072] The AI ​​service resources are rearranged based on the resource utilization rate.

[0073] Specifically, in the resource orchestration process, this embodiment of the invention can also obtain the resource utilization rate of AI services, and re-orchestrate the AI ​​service resources using the above-mentioned orchestration method based on the resource utilization rate. It should be noted that the resource utilization rate S is a parameter that measures the operating load status of AI service resources, and there can be resource utilization rates of multiple resource dimensions, such as memory utilization rate S1 and GPU utilization rate S2. When any one of them is greater than a preset threshold, it is judged as overloaded, and when it is less than the preset threshold, it is judged as idle.

[0074] Resource utilization is a statistical value over a period of time. The statistical method is as follows: within a certain period, the time during which the AI ​​service resource utilization exceeds or falls below a certain threshold (e.g., 80%) reaches a certain percentage (S, e.g., 90%). Considering user migration, if the load within the AI ​​service area is found to be too high or too low, scaling up or down should be implemented. This parameter can also be used in conjunction with the AI ​​service orchestration period T; when re-orchestrending based on the AI ​​service orchestration period T, the value of resource utilization S is taken into account.

[0075] Following the above method, AI resource status is marked as overloaded (O) and free (F), and this information is fed back to the service orchestration function for re-orchestration of the corresponding AI service resources. Adjusting orchestration based on resource utilization helps to promptly detect user overload, avoid providing prolonged periods of poor-quality AI services, and dynamically identify resource waste, thereby improving resource utilization.

[0076] For example, please refer to Figure 2 and Figure 3 , Figure 2 This is a schematic diagram of the first process of an AI service resource orchestration method based on a 6G network provided by the present invention. Figure 3 This is a schematic diagram of the second process of an AI service resource orchestration method based on a 6G network provided by the present invention. The orchestration processes of the two orchestration methods provided in the embodiments of the present invention are as follows: Figure 2 and Figure 3 As shown, the interface between the container and the AI ​​service function orchestration is implemented by the container management platform. The orchestration results are generated according to the two orchestration methods described above, executed by the AI ​​service function, which then launches the corresponding container and broadcasts the notification to the terminal. Figure 2 and Figure 3 AI service broadcast messages are the network's AI capabilities and can be sent to users via broadcast. In pre-configured orchestration, they are broadcast to users when a container is launched; in service-driven orchestration, they are broadcast to users when they access the network. Broadcast messages can be sent to terminals via base station SIB messages.

[0077] To support the increasingly widespread and diverse applications of AI, 6G networks need to consider the rational deployment of network computing resources when providing AI services. Compared to external AI services, this invention proposes an intelligent, intrinsically generated AI service resource orchestration method. First, it fully considers application type factors, dividing resource orchestration into two methods: pre-configured and application-driven. Then, based on different service scopes and scenario markers, it orchestrates the type and resource size of relevant computing execution containers. Furthermore, it designs an orchestration update strategy triggered by resource utilization, i.e., resource scaling. This invention improves the flexibility of AI resource orchestration, avoids problems such as congestion and resource waste, and can promptly detect resource shortages, preventing prolonged periods of poor-quality service and ensuring a positive user experience for AI services.

[0078] Accordingly, the present invention also provides an AI service resource orchestration device based on a 6G network, which can implement all the processes of the AI ​​service resource orchestration method based on a 6G network in the above embodiments.

[0079] Please see Figure 4 , Figure 4 This is a schematic diagram of a preferred embodiment of an AI service resource orchestration device based on a 6G network provided by the present invention. The AI ​​service resource orchestration device based on a 6G network includes:

[0080] The data acquisition module 401 is used to acquire AI service orchestration parameters, hardware resource information, and AI service information.

[0081] The resource orchestration module 402 is used to orchestrate resource types and resource sizes according to the AI ​​service orchestration parameters, the hardware resource information and the AI ​​service information, generate orchestration results, and send the orchestration results to the corresponding functional modules.

[0082] Preferably, obtaining the AI ​​service orchestration parameters includes:

[0083] Obtain pre-configured AI service orchestration parameters, wherein the pre-configured AI service orchestration parameters include at least one of the following parameters:

[0084] AI service scope;

[0085] AI service area types;

[0086] AI service orchestration cycle.

[0087] Preferably, the AI ​​service range is the area where one or more base stations provide AI services;

[0088] The AI ​​service area types include dense, mobile-intensive, and distributed types, and the corresponding resource sizes are ordered as mobile-intensive > dense > distributed.

[0089] Preferably, obtaining the AI ​​service orchestration parameters includes:

[0090] Receive service requests sent by the terminal;

[0091] The AI ​​service orchestration parameters are obtained by parsing the corresponding business feature parameters based on the business request.

[0092] Preferably, the business characteristic parameters include at least one of the following parameters:

[0093] Terminal type;

[0094] Business type.

[0095] Preferably, the device further includes an orchestration and update module for:

[0096] Resource utilization rate for acquiring AI services;

[0097] The AI ​​service resources are rearranged based on the resource utilization rate.

[0098] In specific implementation, the working principle, control process and technical effects of the AI ​​service resource orchestration device based on 6G network provided in this embodiment of the invention are the same as those of the AI ​​service resource orchestration method based on 6G network in the above embodiments, and will not be repeated here.

[0099] Please see Figure 5 , Figure 5 This is a schematic diagram of a preferred embodiment of a terminal device provided by the present invention. The terminal device includes a processor 501, a memory 502, and a computer program stored in the memory 502 and configured to be executed by the processor 501. When the processor 501 executes the computer program, it implements the AI ​​service resource orchestration method based on a 6G network as described in any of the above embodiments.

[0100] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory 502 and executed by the processor 501 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0101] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor 501 may be any conventional processor. The processor 501 is the control center of the terminal device, connecting various parts of the terminal device through various interfaces and lines.

[0102] The memory 502 mainly includes a program storage area and a data storage area. The program storage area can store the operating system, applications required for at least one function, etc., while the data storage area can store related data, etc. Furthermore, the memory 502 can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart media card (SMC), a secure digital card (SD), and a flash card, or it can be other volatile solid-state storage devices.

[0103] It should be noted that the aforementioned terminal devices may include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 5 The structural diagram is merely an example of the terminal device described above and does not constitute a limitation on the terminal device described above. It may include more or fewer components than shown in the diagram, or combine certain components, or use different components.

[0104] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to execute the AI ​​service resource orchestration method based on a 6G network as described in any of the above embodiments.

[0105] This invention also provides a computer program product, which includes a computer program or computer instructions. When the computer program or computer instructions are executed by a processor, they implement the AI ​​service resource orchestration method based on a 6G network described in any of the above embodiments.

[0106] This invention provides a method, apparatus, device, medium, and product for orchestrating AI service resources based on a 6G network. The advantages of this method are as follows: by acquiring AI service orchestration parameters, hardware resource information, and AI service information; and based on these parameters, the method orchestrates resource types and sizes, generates orchestration results, and sends these results to the corresponding functional modules. This invention, by orchestrating AI service resources according to AI service orchestration parameters, can effectively improve resource utilization and AI service quality while saving costs.

[0107] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0108] 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 are also considered to be within the scope of protection of the present invention.

Claims

1. A method for orchestrating AI service resources based on a 6G network, characterized in that, include: Obtain AI service orchestration parameters, hardware resource information, and AI service information; Based on the AI ​​service orchestration parameters, the hardware resource information, and the AI ​​service information, the resource types and sizes are orchestrated, an orchestration result is generated, and the orchestration result is sent to the corresponding functional modules.

2. The AI ​​service resource orchestration method based on 6G network as described in claim 1, characterized in that, The acquisition of AI service orchestration parameters includes: Obtain pre-configured AI service orchestration parameters, wherein the pre-configured AI service orchestration parameters include at least one of the following parameters: AI service scope; AI service area types; AI service orchestration cycle.

3. The AI ​​service resource orchestration method based on a 6G network as described in claim 2, characterized in that, The AI ​​service range refers to the area where one or more base stations provide AI services. The AI ​​service area types include dense, mobile-intensive, and distributed types, and the corresponding resource sizes are ordered as mobile-intensive > dense > distributed.

4. The AI ​​service resource orchestration method based on 6G network as described in claim 1, characterized in that, The acquisition of AI service orchestration parameters includes: Receive service requests sent by the terminal; The AI ​​service orchestration parameters are obtained by parsing the corresponding business feature parameters based on the business request.

5. The AI ​​service resource orchestration method based on a 6G network as described in claim 4, characterized in that, The business characteristic parameters include at least one of the following parameters: Terminal type; Business type.

6. The AI ​​service resource orchestration method based on a 6G network as described in claim 1, characterized in that, The method further includes: Resource utilization rate for acquiring AI services; The AI ​​service resources are rearranged based on the resource utilization rate.

7. An AI service resource orchestration device based on a 6G network, characterized in that, include: The data acquisition module is used to acquire AI service orchestration parameters, hardware resource information, and AI service information. The resource orchestration module is used to orchestrate resource types and sizes based on the AI ​​service orchestration parameters, the hardware resource information, and the AI ​​service information, generate orchestration results, and send the orchestration results to the corresponding functional modules.

8. A terminal device, characterized in that, The system includes a processor and a memory, wherein the memory stores a computer program and the computer program is configured to be executed by the processor, wherein the processor executes the computer program to implement the AI ​​service resource orchestration method based on a 6G network as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the AI ​​service resource orchestration method based on a 6G network as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program or computer instructions, which, when executed by a processor, implement the AI ​​service resource orchestration method based on a 6G network as described in any one of claims 1 to 6.

Images