Network service request processing method and system, storage medium and electronic equipment

Abstract

The invention relates to a network service request processing method and system, a storage medium and electronic equipment, and relates to the technical field of communication, and the method comprises the steps that a task arrangement agent analyzes a network service request sent by user equipment to obtain a to-be-executed task instruction, and determines a service management agent corresponding to the to-be-executed task instruction; the task arrangement agent issues a to-be-executed task instruction to the service management agent, and the service management agent allocates a task execution function network element for the to-be-executed task instruction; the service management agent calls an instruction translation agent to perform instruction conversion on the to-be-executed task instruction to obtain a to-be-executed task signaling, and issues the to-be-executed task signaling to a task execution function network element; and the task execution function network element executes the to-be-executed task signaling to obtain a signaling execution result, performs instruction conversion on the signaling execution result to obtain a task execution result corresponding to the network service request, and feeds back the task execution result to the user equipment. The processing efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of communication technologies, and in particular, to a method for processing a network service request, a system for processing a network service request, a computer-readable storage medium, and an electronic device. Background Art

[0002] The existing method for processing network service requests has the following defects: the rigidity of network element functions makes it difficult to flexibly support the dynamic combination requirements of emerging network services, which in turn results in low accuracy of task execution results.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0004] The purpose of the present disclosure is to provide a method for processing network service requests, a system for processing network service requests, a computer-readable storage medium, and an electronic device, thereby at least to a certain extent overcoming the problem of low accuracy of task execution results caused by the limitations and defects of related technologies.

[0005] According to one aspect of the present disclosure, a method for processing a network service request is provided, comprising:

[0006] The task scheduling agent parses the network service request sent by the user device to obtain a task instruction to be executed, and determines a service management agent corresponding to the task instruction to be executed;

[0007] The task scheduling agent sends the to-be-executed task instructions to the service management agent, and the service management agent allocates a task execution function network element to the to-be-executed task instructions;

[0008] The service management agent calls the instruction translation agent to convert the instruction of the task to be executed to obtain the signaling of the task to be executed, and sends the signaling of the task to be executed to the task execution function network element;

[0009] The task execution function network element executes the signaling of the task to be executed to obtain a signaling execution result, and performs instruction conversion on the signaling execution result to obtain a task execution result corresponding to the network service request, so as to feed back the task execution result to the user equipment.

[0010] In an exemplary embodiment of the present disclosure, a task orchestration agent parses a network service request sent by a user device to obtain instructions for tasks to be executed, including: an access and mobility management function network element receives an original network service request sent by a user device, and performs instruction translation on the original network service request to obtain a target network service request; the task orchestration agent receives the target network service request, and performs service parsing on the target network service request task to obtain multiple subtasks with dependencies; the task orchestration agent configures a unique task identifier for the subtask, and generates the instructions for tasks to be executed based on the subtask, the unique task identifier, the request sending address of the network service request, and the data output address of the task execution result; wherein the instructions for tasks to be executed include network connection service tasks and / or other network service tasks other than network connection service tasks, and the other network service tasks include at least one of data acquisition service tasks, data calculation service tasks, context awareness service tasks, and artificial intelligence service tasks.

[0011] In an exemplary embodiment of the present disclosure, the task orchestration agent includes a task decomposition model, which includes an embedding mapping layer, an encoding layer and a hybrid expert model; wherein, a target network service request task is subjected to service parsing to obtain a plurality of subtasks with dependency relationships, including: parsing the target network service request to obtain service request details, the device service area to which the user device belongs, and the service level requirements corresponding to the device service area; generating basic information to be predicted based on the service request details, the device service area and the service level requirements, and generating context information to be predicted based on preset model prompt parameters; embedding mapping processing is performed on the basic information to be predicted based on the embedding mapping layer to obtain network service features, and embedding mapping processing is performed on the context information to be predicted based on the embedding mapping layer to obtain a context flag sequence; encoding processing is performed on the network service features and the context flag sequence based on the encoding layer to obtain a context overall representation, and service parsing is performed on the context flag sequence and the context overall representation based on the hybrid expert model to obtain a plurality of subtasks with dependency relationships.

[0012] In an exemplary embodiment of the present disclosure, the hybrid expert model includes a gating network model and multiple expert neural network models; wherein, based on the hybrid expert model, the context flag sequence and the overall context representation are subjected to service parsing to obtain multiple subtasks with dependencies, including: determining, based on the gating network model and the context flag sequence, a first model weight of each expert neural network model in the resource requirement dimension, a second model weight in the service quality dimension, and a third model weight in the dependency dimension; based on the first model weight, the second model weight, and the third model weight, determining from each expert neural network model a first target neural network model required for performing a service parsing task in the resource requirement dimension, a second target neural network model required for performing a service parsing task in the service quality dimension, and a third target neural network model required for performing a service parsing task in the dependency dimension; inputting the context flag sequence and the overall context representation into the first target neural network model, the second target neural network model, and the third target neural network model, respectively, to obtain a first prediction result in the resource requirement dimension, a second prediction result in the service instruction dimension, and a third prediction result in the dependency dimension, and obtaining multiple subtasks with dependencies based on the first prediction result, the second prediction result, and the third prediction result.

[0013] In an exemplary embodiment of the present disclosure, determining the service management agent corresponding to the to-be-executed task instruction includes: determining a candidate management agent based on the device service area to which the user device belongs, and matching the to-be-executed task instruction with a corresponding service management agent from the candidate management agents based on the instruction type of the to-be-executed task instruction; wherein, if the instruction type is a first to-be-executed task corresponding to a network connection service task, determining the service management agent corresponding to the first to-be-executed task to be a network connection management agent; if the instruction type is a second to-be-executed task corresponding to other network service tasks, determining the service management agent corresponding to the second to-be-executed task to be a data management agent; the data management agent includes at least one of a data acquisition management agent, a data calculation management agent, a context-aware management agent, and an artificial intelligence management agent.

[0014] In an exemplary embodiment of the present disclosure, task execution function network elements are assigned to the task instructions to be executed, including: a network connection management agent assigns a first task execution function network element to the first task to be executed from the user plane function network elements included in the device service area to which the user device belongs; a data management agent assigns a second task execution function network element to the second task to be executed from the current data management function network elements included in the device service area to which the user device belongs; wherein the current data management function network element includes at least one of a data acquisition function network element, a data calculation function network element, a context perception function network element, and an artificial intelligence function network element.

[0015] In an exemplary embodiment of the present disclosure, a second task execution function network element is allocated to a second task to be executed from a current data management function network element included in a device service area to which a user device belongs, including: receiving current computing power capability information and current computing power resource information reported by a current data management function network element included in a device service area to which the user device belongs; calculating a first matching degree between the current computing power capability information and the service quality requirement of the task to be executed, and calculating a second matching degree between the current computing power resource information and the resource requirement of the task to be executed; and allocating a task execution function network element to the task to be executed from the current function network element according to the first matching degree and the second matching degree.

[0016] In an exemplary embodiment of the present disclosure, instruction conversion is performed on the task instruction to be executed to obtain a task signaling to be executed, including: performing word segmentation processing on the task instruction to be executed to obtain a word segmentation processing result, and determining a grammatical role of the word segmentation processing result in the task instruction to be executed; performing named entity recognition on the word segmentation processing result according to the grammatical role to obtain an entity recognition result, and determining a task execution intention and task execution parameters based on the entity recognition result; constructing a protocol data unit according to the task execution intention and task execution parameters, and encoding the protocol data unit to obtain a task signaling to be executed.

[0017] In an exemplary embodiment of the present disclosure, executing the signaling of the task to be executed to obtain a signaling execution result, including: the first task execution function network element executes the signaling of the task to be executed to obtain a protocol data unit session connection between the user equipment and the data network; the second task execution function network element executes the signaling of the task to be executed to obtain a data acquisition result and / or a data calculation result and / or a situational perception result and / or an artificial intelligence prediction result.

[0018] According to one aspect of the present disclosure, a system for processing a network service request is provided, comprising:

[0019] A task scheduling agent is used to parse the network service request sent by the user device to obtain a task instruction to be executed, and determine a service management agent corresponding to the task instruction to be executed;

[0020] The task scheduling agent is used to send the instructions of the tasks to be executed to the service management agent;

[0021] The service management agent is configured to allocate a task execution function network element to the task instruction to be executed; and call an instruction translation agent to convert the task instruction to be executed to obtain a task signaling to be executed, and send the task signaling to the task execution function network element;

[0022] The task execution function network element is used to execute the signaling of the task to be executed to obtain a signaling execution result, and perform instruction conversion on the signaling execution result to obtain a task execution result corresponding to the network service request, so as to feed back the task execution result to the user equipment.

[0023] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for processing a network service request described in any one of the above is implemented.

[0024] According to one aspect of the present disclosure, there is provided an electronic device, including:

[0025] processor; and

[0026] a memory for storing executable instructions of the processor;

[0027] The processor is configured to execute any one of the above-mentioned methods for processing a network service request by executing the executable instructions.

[0028] The embodiment of the present disclosure provides a method for processing a network service request. On the one hand, a task scheduling agent parses a network service request sent by a user device to obtain a task instruction to be executed, and determines a service management agent corresponding to the task instruction to be executed; then the task scheduling agent sends the task instruction to be executed to the service management agent, and the service management agent assigns a task execution function network element to the task instruction to be executed; then the service management agent calls an instruction translation agent to convert the task instruction to be executed to obtain a task signaling to be executed, and sends the task signaling to the task execution function network element; finally, the task execution function network element executes the task signaling to be executed to obtain a signaling execution result. The signaling execution result is converted into an instruction to obtain a task execution result corresponding to the network service request, so as to feed back the task execution result to the user device, thereby realizing the processing of network service requests in combination with corresponding functional network elements on the basis of the intelligent body, thereby solving the problem in the existing technology that it is difficult to flexibly support the dynamic combination of emerging network services due to the solidification of network element functions, thereby making the accuracy of the obtained task execution results low, and improving the accuracy of the task execution results; on the other hand, since the network service request can be processed on the basis of the intelligent body in combination with the corresponding functional network elements, the processing efficiency of the network service request is improved, the response time of the user device is reduced, and the user experience is improved.

[0029] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0031] Figure 1 A flowchart schematically illustrates a method for processing a network service request according to an exemplary embodiment of the present disclosure.

[0032] Figure 2 A diagram schematically illustrates an example structure of a system for processing network service requests according to an example embodiment of the present disclosure.

[0033] Figure 3 A diagram schematically illustrates an example scenario of the interaction process among various intelligent agents in the process of processing a network service request according to an exemplary embodiment of the present disclosure.

[0034] Figure 4A diagram schematically illustrates an example scenario of a task instruction to be executed obtained according to an example embodiment of the present disclosure.

[0035] Figure 5 A diagram schematically illustrates an example structure of a task decomposition model included in a task orchestration agent according to an exemplary embodiment of the present disclosure.

[0036] Figure 6 A diagram schematically illustrates an example structure of a hybrid expert model in a task decomposition model according to an exemplary embodiment of the present disclosure.

[0037] Figure 7 A diagram schematically illustrates a structural example of an apparatus for processing a network service request according to an exemplary embodiment of the present disclosure.

[0038] Figure 8 An electronic device for implementing a method for processing a network service request according to an exemplary embodiment of the present disclosure is schematically illustrated. DETAILED DESCRIPTION

[0039] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present disclosure will be more comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or that other methods, components, devices, steps, etc. may be employed. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0040] In addition, the accompanying drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0041] Currently, with the rapid development of network technology, the types of services that network systems (i.e., core networks) need to handle are becoming increasingly diverse. Specific service types include, but are not limited to, data acquisition, data cleansing, and data standardization. Furthermore, in recent years, intelligent agent technology has been recognized by the 3rd Generation Partnership Project (3GPP) as a core enabling technology for 6G due to its autonomous decision-making and dynamic adaptability. SA (Standalone) 1 has initiated research on intelligent agent use cases, and SA2 is also about to begin related research.

[0042] The service-based architecture (SBA) of the traditional 5G core network realizes network element interaction through standardized interfaces (such as SBI, Service-Based Interface); however, the functional network element interaction based on this interface has the following shortcomings: on the one hand, the functions are static; that is, due to the solidification of network element functions, it is difficult to flexibly support the dynamic combination requirements of emerging services such as AI, perception, and computing; on the other hand, the collaboration capability is weak; that is, in the process of interaction, if cross-service is required, it is necessary to rely on manual orchestration, and there is a lack of automated task decomposition and intelligent collaboration mechanism; on the other hand, the terminal compatibility is insufficient; that is, non-intelligent terminals (such as traditional user equipment) cannot directly call intent-driven services, and intelligent terminals cannot directly call traditional network functions.

[0043] In some related technical solutions, although some studies have attempted to introduce artificial intelligence to optimize network management, they mostly focus on a single function and have not yet built a full-stack intelligent architecture covering "task decomposition-intelligent agent collaboration-dynamic resource scheduling", which restricts the evolution of the network towards the intelligent connection of all things.

[0044] Based on this, this exemplary embodiment first provides a method for processing network service requests, which can be run on a server, server cluster, or cloud server where the 5G core network is located; of course, those skilled in the art can also run the method disclosed in this disclosure on other platforms as needed, and this exemplary embodiment does not specifically limit this. Specifically, refer to Figure 1 As shown, the method for processing the network service request may include the following steps:

[0045] Step S110: The task scheduling agent parses the network service request sent by the user device to obtain a task instruction to be executed, and determines a service management agent corresponding to the task instruction to be executed;

[0046] Step S120. The task scheduling agent sends the task instructions to be executed to the service management agent, and the service management agent assigns the task execution function network element to the task instructions to be executed;

[0047] Step S130: The service management agent calls the instruction translation agent to convert the instruction to be executed into a task signaling to be executed, and sends the task signaling to the task execution function network element;

[0048] Step S140: The task execution function network element executes the signaling of the task to be executed to obtain a signaling execution result, and performs instruction conversion on the signaling execution result to obtain a task execution result corresponding to the network service request, so as to feed back the task execution result to the user equipment.

[0049] In the method for processing network service requests recorded above, on the one hand, the network service request sent by the user equipment is parsed by the task scheduling agent to obtain the task instruction to be executed, and the service management agent corresponding to the task instruction to be executed is determined; the task scheduling agent then sends the task instruction to be executed to the service management agent, and the service management agent assigns the task execution function network element to the task instruction to be executed; then the service management agent calls the instruction translation agent to convert the task instruction to be executed to obtain the task signaling to be executed, and sends the task signaling to the task execution function network element; finally, the task execution function network element executes the task signaling to be executed to obtain the signaling execution result, and performs the task execution. The signaling execution result is converted into an instruction to obtain a task execution result corresponding to the network service request, so as to feed back the task execution result to the user device, thereby realizing the processing of the network service request in combination with the corresponding functional network element on the basis of the intelligent body, thereby solving the problem in the existing technology that it is difficult to flexibly support the dynamic combination of emerging network services due to the solidification of network element functions, thereby making the accuracy of the obtained task execution result low, and improving the accuracy of the task execution result; on the other hand, since the network service request can be processed on the basis of the intelligent body in combination with the corresponding functional network element, the processing efficiency of the network service request is improved, the response time of the user device end is reduced, and the user experience is improved.

[0050] Hereinafter, the method for processing a network service request according to an exemplary embodiment of the present disclosure will be explained and illustrated in detail with reference to the accompanying drawings.

[0051] First, the terms involved in the exemplary embodiments of the present disclosure are explained and illustrated.

[0052] AI agent: An automated intelligent entity that can interact with its environment and acquire contextual information to reason, self-learn, make decisions, and execute tasks (autonomously or in collaboration with other agents) to achieve specific goals. The AI ​​agents described here may include, but are not limited to, virtual agents represented by AI digital humans / digital assistants and physical agents represented by embodied AI robots.

[0053] UE (User Equipment): A user equipment (UE) is also referred to as a terminal device. This UE may include, but is not limited to, mobile phones, computers, IoT devices, and in-vehicle terminals. The UEs described in the exemplary embodiments of this disclosure may be embodied intelligent devices, such as embodied AI robots and drones.

[0054] RAN (Radio Access Network): The radio network part that connects the UE to the core network, which may include base stations (gNBs) and radio resource management functions.

[0055] AMF (Access and Mobility Management Function) network element: This network element is a control plane network element of the core network, which can be responsible for managing the access, mobility and session control of user equipment (UE).

[0056] UPF (User Plane Function) network element: A user plane network element that is responsible for routing, forwarding, and QoS processing of user data packets sent by user equipment.

[0057] DN (Data Network): It is a data network outside the network, such as but not limited to the Internet, enterprise private network or cloud service, etc.

[0058] SBI (Service-Based Interface): It is a standard interface for implementing service-oriented interaction of network functions in the 5G core network. It can be built based on HTTP / 2 (Hypertext Transfer Protocol Bis) and JSON (JavaScript Object Notation) protocols. In actual application, SBI can draw on the microservice architecture concept in the IT (Information Technology) field and replace the traditional point-to-point interface with a unified service-oriented interface, thereby achieving the purpose of supporting modularization, loose coupling and dynamic calling of network functions.

[0059] ABI (Agent Based Interface): It can be responsible for facilitating communication between network agents. In actual application, it can support imperative, declarative and intent-driven interactions by leveraging artificial intelligence models and functions (such as natural language processing and intent-driven methods). In addition, ABI can also understand the purpose of the received message and direct it to the appropriate agent.

[0060] Secondly, the technical implementation principle of the example embodiment of the present disclosure is explained and illustrated. Specifically, the method for processing network service requests recorded in the example embodiment of the present disclosure aims to manage and control network service requests by utilizing the automation and intelligent characteristics of the intelligent body, and then flexibly process the data of new types of network services according to the dynamic needs of various applications, to achieve flexible management of diversified services and optimal allocation of resources, thereby improving the service capabilities and efficiency of the network system. Its core objectives include the following aspects: on the one hand, to build an intelligent network architecture; that is, to add new intelligent bodies in the core network or embed intelligent bodies in network elements to achieve automatic decomposition, orchestration and execution of tasks; on the other hand, to support dynamic combination of diversified services; that is, to seamlessly integrate heterogeneous services such as connection, data, computing, AI and perception through the intelligent body collaboration mechanism; on the other hand, to be compatible with multiple types of terminals; that is, to support intelligent body terminals to initiate intent-driven service requests through intelligent body-based interfaces and instruction translation mechanisms.

[0061] Furthermore, the processing system of the network service request involved in the exemplary embodiment of the present disclosure is explained and illustrated. Figure 2As shown, the network service request processing system may include user equipment (UE) 210, radio access network (RAN) 220, user plane function (UPF) network element 230, data network (DN) 240, access and mobility management function (AMF) network element 250, connection management agent 260, data management agent 270, task orchestration agent 280, instruction translation agent 290, and task execution function network elements with different functions (such as network element 1 and network element 2, etc.) and other network function network elements (other NFs) or agents, etc.; in actual application, the user equipment is connected to the AMF network element through the radio access network, or directly to the AMF network element; the AMF network element is connected to other functional network elements or agents based on SBI (Service-Based Interface, service-based interface) or ABI (Agent-Based Interface, agent-based interface); UPF is respectively connected to RAN, DN and connection management agent; each agent or network element can be connected through SBI and / or ABI.

[0062] Furthermore, in the specific process of processing network service requests, the task scheduling agent is used to parse the network service request sent by the user device to obtain the task instructions to be executed, and determine the service management agent (that is, the connection management agent 260 and the data management agent 270) corresponding to the task instructions to be executed; the task scheduling agent is used to send the task instructions to be executed to the service management agent; the service management agent is used to allocate the task execution function network element for the task instructions to be executed; and the instruction translation agent is called to perform instruction conversion on the task instructions to be executed to obtain the task signaling to be executed, and send the task signaling to the task execution function network element; the task execution function network element is used to execute the task signaling to be executed to obtain the signaling execution result, and perform instruction conversion on the signaling execution result to obtain the task execution result corresponding to the network service request, so as to feed back the task execution result to the user device.

[0063] In an exemplary embodiment, referring to Figure 2 As shown, the intelligent agent recorded above can be set up on the core network side in an independent new manner, or the intelligent agent function can be directly built into the existing network elements of the core network. This example does not impose any special restrictions on this; at the same time, the network system supports a variety of network services; for example, it can include but is not limited to connection services, data acquisition services, data computing services, situational awareness services, and artificial intelligence services, etc.; the network service request processing system recorded above can use multiple intelligent agents with different functions to manage and control the network, and flexibly process the data of new services according to the dynamic needs of various applications.

[0064] In an example embodiment, during actual application, after the network side receives a network service request sent by a user device, it can determine the corresponding service management agent through the task orchestration agent, and then select a network element that can meet the business needs based on the service management agent to provide services; in this process, RAN, UE and corresponding functional network elements can all serve as task execution entities and can be selected according to actual needs. This example does not impose any special restrictions on this.

[0065] Furthermore, the task orchestration agent described herein can be used to receive input strategies, information, and knowledge, which can be imperative, declarative, or intent-based requests; in actual application, it is responsible for decomposing the input into one or more executable tasks, wherein the executable tasks described herein can be divided into two parts, the first part can be used to connect services, and the second part can be used to deploy other services beyond the connection, such as data acquisition services and data computing services, etc.; after the task decomposition is completed, it is also necessary to determine the appropriate service management agent and output the corresponding task list; wherein each entry in the list can include a task ID, task input, and task dependency indication, etc.

[0066] Furthermore, the aforementioned service management agent may include a connection management agent and a data management agent. The connection management agent is responsible for receiving connection tasks from the task orchestration agent to manage connection services, such as controlling the establishment, modification, and release of session connections. Meanwhile, the data management agent may be responsible for receiving data tasks from the task orchestration agent, determining appropriate data execution agents / network elements for the tasks, and then determining a logical topology work chain based on task dependencies. This work chain is then controlled to implement specific data service functions. Furthermore, the data management agent must support data service capability and resource reporting by the data execution agents / network elements.

[0067] In a possible example embodiment, the data management agent described above may include a data computing management agent; specifically, the data computing management agent can be oriented towards computing power service needs, and be responsible for the management of computing services and the allocation and optimization of computing resources; in the actual application process, it can be responsible for receiving data computing tasks issued by the task orchestration agent, determining the appropriate computing execution function network element for the data computing task, and then determining the logical topology based on the task dependency and ensuring that the computing service can be dynamically deployed and uninstalled according to demand; further, the data computing management agent also needs to support the capability and resource reporting of the data computing execution function network element.

[0068] In an example embodiment, when executing a data acquisition network service task, it is necessary to implement it based on a data acquisition execution function network element; wherein, the data acquisition execution function network element can be used to be responsible for executing specific data acquisition tasks and realizing functions such as data collection, processing, and analysis. Furthermore, when executing a data computing network service task, it is necessary to implement it based on a data computing execution function network element; wherein, the data computing execution function network element can be used for scheduling based on a data computing management intelligent agent, be responsible for executing specific computing tasks and returning computing results, and report the status of its own computing resources to the data computing management intelligent agent in real time.

[0069] In an exemplary embodiment, the network service request processing system described above also includes an instruction translation agent; specifically, the instruction translation agent can be responsible for converting the management and control instructions received from the agent into control signaling for non-intelligent UE, RAN and functional network elements, etc.; at the same time, it is also responsible for converting signaling information from non-intelligent UE, RAN and functional network elements into instructions and information for the agent.

[0070] It should be further clarified that the aforementioned intelligent agents can be deployed independently, or multiple functions can be combined into a single network intelligent agent for functional integration. For example, the command translation function can be integrated into another network intelligent agent, or the data management intelligent agent and the data computing management intelligent agent can be combined into a service management intelligent agent. In another alternative network system, intelligent agent functions can be embedded in existing functional network elements to enhance network functionality and implement task-oriented intelligent orchestration, environmental awareness, intelligent invocation, and so on.

[0071] In an exemplary embodiment, referring to Figure 3As shown, the specific interaction process between the agents during network service request processing is as follows: the task orchestration agent accepts user requests, decomposes the complex service into multiple dependent connection tasks and other tasks, generates the QoS and resource requirements for each task, and then assigns the tasks to the appropriate service management agent for deployment. After receiving the task list decomposed by the task orchestration agent, the connection management agent and the data management agent within the service management agent determine the network elements (NEs) to execute the tasks, establish the connection topology between the NEs, and send the task deployment information to the corresponding execution functional NEs. For example, the connection management agent selects the user plane functional NE to execute the connection service, allocates the UE's IP address, and establishes a PDU session; the data management agent selects the appropriate data execution functional NE to deploy the corresponding data task. Furthermore, the service management agent's instructions are first translated and converted by the instruction translation agent before being transmitted to the functional NE executing the task. Furthermore, if the connection management agent or the data management agent discovers that the configured or deployed functional NE is resource-constrained, they will reselect a new functional NE to execute the task. Moreover, during the task execution process, if the status of the executing network element changes (such as power failure, busy, high load), the corresponding service management agent will automatically replace the task execution network element or dynamically reschedule resources to cope with the change.

[0072] It should be further explained here that the above process is for the case where the intelligent terminal initiates a service request. Here is a supplementary explanation for another possible situation: if a non-intelligent terminal initiates a request to the task scheduling intelligent agent, the request must first be translated and converted by the instruction translation intelligent agent before continuing the subsequent process between network intelligent agents.

[0073] In an example embodiment, to facilitate the task orchestration agent to better orchestrate services and map decomposed tasks to appropriate service management agents, the task orchestration agent must possess the resources (such as data and computing power) and specific capabilities of each service management agent. Furthermore, to enable the service management agent to deploy tasks to appropriate task execution function network elements, the service management agent must possess the capabilities (such as data collection / processing / analysis, AI, perception, computing, etc.) and resource information of each task execution function network element in the region. To this end, the service management agent and the task execution function network elements must report their resources and capabilities. Specifically, the reporting process is as follows: First, each execution NF (Network Function) network element with data / computing service capabilities periodically reports its service capabilities and resource information to the data management agent. This reporting process may also include information such as its deployment location and service coverage area. Second, the data management agent stores and aggregates the capability and resource information of each execution NF, and then reports the total capability and resource information to the task orchestration agent.

[0074] The following will Figure 1 The processing method of the network service request shown in is further explained and illustrated. Specifically:

[0075] In step S110, the task scheduling agent parses the network service request sent by the user device to obtain a task instruction to be executed, and determines a service management agent corresponding to the task instruction to be executed.

[0076] In this example embodiment, first, a task instruction to be executed is generated; specifically, it can be implemented in the following ways: ① The access and mobility management function (AMF) network element receives the original network service request sent by the user equipment (UE, for example, it can be an intelligent terminal or a non-intelligent terminal), and translates the original network service request into a target network service request; specifically, if the user equipment is a non-intelligent terminal, the instruction needs to be translated before it is sent to the task scheduling agent; if the user equipment is an intelligent terminal, it can be sent directly to the task scheduling agent; ② The task scheduling agent receives the target network service request ③ The task scheduling agent configures a unique task identifier for the subtask, and generates a task instruction to be executed based on the subtask, the unique task identifier, the request sending address of the network service request, and the data output address of the task execution result; wherein, the task instruction to be executed includes the network connection service task and / or other network service tasks other than the network connection service task, and other network service tasks include data acquisition service tasks, data calculation service tasks, situational awareness service tasks, and artificial intelligence (AI) service tasks, etc. Among them, the task instruction to be executed can be referred to Figure 4 shown.

[0077] In an exemplary embodiment, the task scheduling agent described herein may include a task decomposition model; Figure 5As shown, the task decomposition model includes an embedded mapping layer 501, a coding layer 502 and a hybrid expert model 503; under this premise, the target network service request task is service parsed to obtain multiple subtasks with dependencies, which can be achieved in the following way: first, the target network service request is parsed to obtain service request details (such as service name (such as PDU session establishment request and other service requests for perception service, AI service, data computing service and data acquisition service, etc.) and specific service content, etc.), the device service area to which the user device belongs (which can be determined based on the IP address or MAC address of the user device) and the service level agreement (SLA) corresponding to the device service area Agreement) requirements (which can be determined based on the device service area); secondly, the basic information to be predicted is generated according to the service request details, the device service area and the service level requirements, and the context information to be predicted is generated according to the preset model prompt parameters; then, the basic information to be predicted is embedded and mapped based on the embedding mapping layer to obtain network service features, and the context information to be predicted is embedded and mapped based on the embedding mapping layer to obtain a context marker sequence; finally, the network service features and the context marker sequence are encoded based on the encoding layer to obtain the overall context representation, and the context marker sequence and the overall context representation are service parsed based on the hybrid expert model to obtain multiple subtasks with dependent relationships. Specifically, the embedding mapping layer described herein may include an Embedding embedding mapping layer and a Bert embedding mapping layer. In actual application, the Embedding embedding mapping layer may be used to perform embedding mapping processing on the basic information to be predicted to obtain network service features, and the Bert embedding mapping layer may be used to perform embedding mapping processing on the context information to be predicted to obtain a context marker sequence. Furthermore, the preset model prompt parameters described herein may include, for example: your task is to decompose the task based on the input information to obtain subtasks with dependencies; during the task decomposition process, xxxx is required, etc. Specific settings can be made based on actual needs, and this example does not impose any special restrictions on this.

[0078] In an exemplary embodiment, referring to Figure 6As shown, the hybrid expert model described herein includes a gating network model and multiple expert neural network models; under this premise, the context flag sequence and the overall context representation are subjected to service parsing based on the hybrid expert model to obtain multiple subtasks with dependencies, which can be specifically achieved in the following manner: based on the gating network model, the first model weight of each expert neural network model in the resource requirement dimension, the second model weight in the service quality dimension, and the third model weight in the dependency dimension are determined according to the context flag sequence; based on the first model weight, the second model weight, and the third model weight, the first target neural network model required for performing the service parsing task in the resource requirement dimension, the second target neural network model required for performing the service parsing task in the service quality dimension, and the third target neural network model required for performing the service parsing task in the dependency dimension are determined from each expert neural network model; the context flag sequence and the overall context representation are respectively input into the first target neural network model, the second target neural network model, and the third target neural network model to obtain a first prediction result in the resource requirement dimension, a second prediction result in the service instruction dimension, and a third prediction result in the dependency dimension, and based on the first prediction result, the second prediction result, and the third prediction result, multiple subtasks with dependencies are obtained.

[0079] In an example embodiment, in the process of obtaining multiple sub-tasks with dependencies based on the first prediction result, the second prediction result, and the third prediction result, the first prediction result, the second prediction result, and the third prediction result can be directly spliced ​​to obtain multiple sub-tasks with dependencies, or they can be implemented by weighted summation. This example does not impose any special restrictions on this. At the same time, when using the weighted summation method, the weight values ​​corresponding to different dimensions can be set according to actual needs. This example does not impose any special restrictions on this.

[0080] Secondly, determine the service management agent corresponding to the task instruction to be executed; specifically, this can be achieved in the following way: determine the candidate management agent based on the device service area to which the user device belongs, and match the corresponding service management agent for the task instruction to be executed from the candidate management agents based on the instruction type of the task instruction to be executed; wherein, if the instruction type is a first task to be executed corresponding to a network connection service task, then determine that the service management agent corresponding to the first task to be executed is a network connection management agent; if the instruction type is a second task to be executed corresponding to other network service tasks, then determine that the service management agent corresponding to the second task to be executed is a data management agent; data management agents include data acquisition management agents, data calculation management agents, contextual awareness management agents, and artificial intelligence management agents, etc. That is, in the actual application process, when assigning a service management agent to a task instruction to be executed, in addition to considering the device service area, it is also necessary to consider the instruction type and the agent's resource capability information (that is, it is necessary to match the service management agent corresponding to the resource information required by the task instruction to be executed).

[0081] In step S120, the task scheduling agent sends the to-be-executed task instructions to the service management agent, and the service management agent allocates task execution functional network elements to the to-be-executed task instructions.

[0082] In this example embodiment, first, the task instructions to be executed are sent to the service management intelligent body; specifically, in the process of sending the task instructions to be executed, the corresponding ABI interface can be called to implement it; the task instructions to be executed sent can include task ID (that is, unique task identifier), task resource requirements, QoS (Quality of Service) requirements (specifically included in each corresponding subtask), task input data address (which can be the IP address or Mac address of the user device), output result address (which can be the IP address or Mac address of the user device, or other addresses, this example does not impose special restrictions on this) and other information.

[0083] Secondly, a task execution function network element is assigned to the task instruction to be executed. Specifically, this can be achieved as follows: the network connection management agent assigns a first task execution function network element to the first task to be executed from the user plane function network elements included in the device service area to which the user equipment belongs; the data management agent assigns a second task execution function network element to the second task to be executed from the current data management function network elements included in the device service area to which the user equipment belongs; the current data management function network elements include data acquisition function network elements, data calculation function network elements, context awareness function network elements, and artificial intelligence function network elements, etc. That is, in actual application, for connection tasks, the user plane function network element of the matching area can be directly used as the corresponding task execution function network element; for other tasks, matching can be based on actual needs.

[0084] In an exemplary embodiment, allocating a second task execution functional network element to a second task to be executed from the current data management functional network element included in the device service area to which the user device belongs can be achieved in the following manner: receiving the current computing power capability information and the current computing power resource information reported by the current data management functional network element included in the device service area to which the user device belongs; calculating the first matching degree between the current computing power capability information and the service quality requirement of the task to be executed, and calculating the second matching degree between the current computing power resource information and the resource requirement of the task to be executed; and allocating a task execution functional network element to the task to be executed from the current functional network element based on the first matching degree and the second matching degree. That is, for other tasks, the specific execution process needs to take into account the computing power capability and computing power resources of the functional network element, and only on this basis can the second task execution functional network element be allocated to the second task to be executed. Furthermore, in the process of calculating the matching degree, the current computing power capability information and current computing power resource information of the current data management function network element, the service quality requirements and resource requirements of the task to be executed can be embedded and mapped into corresponding feature vectors respectively, and then the feature similarity between the feature vectors is calculated to determine the matching degree; in the actual matching process, the computing power capability can be matched first and then the computing power resources can be matched, or a weighted summation method can be used to achieve it. This example does not impose any special restrictions on this.

[0085] In step S130, the service management agent calls the instruction translation agent to convert the to-be-executed task instruction to obtain a to-be-executed task signaling, and sends the to-be-executed task signaling to the task execution function network element.

[0086] In this example embodiment, first, instruction conversion (i.e., instruction translation) is performed on the instructions for the task to be executed; specifically, the specific implementation process of the instruction translation can be achieved in the following manner: word segmentation processing is performed on the instructions for the task to be executed to obtain a word segmentation processing result, and the grammatical role of the word segmentation processing result in the instructions for the task to be executed is determined; named entity recognition is performed on the word segmentation processing result according to the grammatical role to obtain an entity recognition result, and the task execution intention and task execution parameters are determined based on the entity recognition result; a protocol data unit is constructed according to the task execution intention and the task execution parameters, and the protocol data unit is encoded to obtain the signaling of the task to be executed. Among them, the word segmentation processing recorded here can be implemented based on the corresponding word segmentation tool, and the specific determination process of the grammatical role recorded here can be determined according to the part of speech of the word segmentation; the named entity recognition recorded here can be implemented based on the corresponding entity recognition model, and the specific intentions and task execution parameters can be implemented by calling the corresponding large language model; the construction of the protocol data unit PDU needs to be implemented in a format suitable for the communication protocol, and the specific encoding process can be implemented based on the corresponding encoder; at the same time, these contents are integrated in the instruction translation intelligent agent. In the process of instruction translation, the corresponding instructions are input into the instruction translation intelligent agent to obtain the corresponding task signaling to be executed.

[0087] Secondly, the signaling of the task to be executed is sent to the task execution function network element; specifically, in the process of sending the signaling of the task to be executed, it is first necessary to establish an interaction path between the service management intelligent body and the task execution function network element, and then send the signaling of the task to be executed to the task execution function network element based on the interaction path; further, in the specific sending process, it can be implemented based on the corresponding SBI interface or ABI interface, which can be determined according to actual needs, and this example does not impose any special restrictions on this.

[0088] In step S140, the task execution function network element executes the signaling of the task to be executed to obtain a signaling execution result, and performs instruction conversion on the signaling execution result to obtain a task execution result corresponding to the network service request, so as to feed back the task execution result to the user equipment.

[0089] In this example embodiment, first, the signaling of the task to be executed is executed to obtain the signaling execution result; specifically, it can be achieved in the following way: the first task execution function network element executes the signaling of the task to be executed to obtain the protocol data unit session connection between the user equipment and the data network (that is, based on the UPF control, the PDU session connection between the user equipment and the network is established); the second task execution function network element executes the signaling of the task to be executed to obtain the data acquisition result and / or the data calculation result and / or the context perception result and / or the artificial intelligence prediction result. It should be supplemented here that, in the process of executing the signaling of the task to be executed, the second task execution function network element also needs to report its own resources and status to the data management intelligent agent in real time, so that the data management intelligent agent can dynamically adjust the task deployment and resource allocation according to the reported information; finally, after the signaling of the task to be executed is completed, the task execution network element function network element calls the corresponding instruction translation intelligent agent to convert the signaling execution result to obtain the task execution result corresponding to the network service request, and finally returns the task execution result to the user equipment.

[0090] It should be noted that, in the specific process of processing network service requests, all interactive processes involving intelligent agents and non-intelligent network elements require the translation and conversion of request instructions by an instruction translation agent; at the same time, the instruction translation agent can be deployed in the network as a separate intelligent agent, or it can be embedded in each network intelligent agent or network element as a functional module. It should be further noted that the network service requests involved in the example embodiments of the present disclosure may also involve situations where the terminal requests multiple services at the same time, such as requests for various element combination services such as data + AI services, connection + data services, connection + AI services, connection + AI + perception services, etc. The methods described in the example embodiments of the present disclosure are still applicable, and the processes are similar, so they will not be repeated here.

[0091] So far, the method for processing network service requests recorded in the example embodiments of the present disclosure has been fully realized. Based on the above-mentioned contents, it can be known that the method for processing network service requests recorded in the example embodiments of the present disclosure has at least the following advantages: on the one hand, it can improve the flexibility and intelligence level of the network; that is, by introducing intelligent agents, the network system can flexibly process the data of new services according to the dynamic needs of various applications, improve the flexibility and intelligence level of the network, and better adapt to the complex and changing network environment; on the other hand, it can optimize resource allocation; that is, the intelligent agent can manage and control network resources, dynamically allocate and optimize resources according to task requirements, improve resource utilization, and reduce network operating costs; on the other hand, it can improve service quality and user experience; that is, it can be achieved through the automation and intelligence of the intelligent agent. With the characteristics of digitization, the network system can respond to user requests more quickly and provide higher quality services, thereby improving user experience and enhancing user satisfaction and loyalty; further, it supports diversified services; that is, the network system can support diversified services, including but not limited to connection services, data acquisition services, data computing services, perception services, AI services, etc., which can meet the needs of different users and expand the application scope and market prospects of the network system; further, it can also be seamlessly compatible with existing networks; that is, it can be compatible with 5G terminals and network elements through command translation agents, protecting operators' existing investments; finally, intent-driven interaction; that is, users can initiate requests through natural language, lowering the threshold for use.

[0092] The following are embodiments of the apparatus disclosed herein, which can be used to implement the method embodiments disclosed herein. For details not disclosed in the apparatus embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0093] The exemplary embodiment of the present disclosure also provides a device for processing a network service request. Figure 7 As shown, the network service request processing device may include a network service request parsing module 710, a task execution function network element allocation module 720, a task instruction conversion module 730 and a task signaling execution module 740.

[0094] The network service request parsing module 710 may be configured to parse the network service request sent by the user device through the task scheduling agent to obtain a task instruction to be executed, and determine a service management agent corresponding to the task instruction to be executed;

[0095] The task execution function network element allocation module 720 can be used to send the to-be-executed task instructions to the service management agent through the task scheduling agent, and the service management agent allocates the task execution function network element to the to-be-executed task instructions;

[0096] The pending task instruction conversion module 730 may be configured to convert the pending task instruction into a pending task signaling through the service management agent calling the instruction translation agent, and then send the pending task signaling to the task execution function network element;

[0097] The pending task signaling execution module 740 can be used to execute the pending task signaling through the task execution function network element to obtain the signaling execution result, and perform instruction conversion on the signaling execution result to obtain the task execution result corresponding to the network service request, so as to feed back the task execution result to the user equipment.

[0098] In an exemplary embodiment of the present disclosure, a task orchestration agent parses a network service request sent by a user device to obtain instructions for tasks to be executed, including: an access and mobility management function network element receives an original network service request sent by a user device, and performs instruction translation on the original network service request to obtain a target network service request; the task orchestration agent receives the target network service request, and performs service parsing on the target network service request task to obtain multiple subtasks with dependencies; the task orchestration agent configures a unique task identifier for the subtask, and generates the instructions for tasks to be executed based on the subtask, the unique task identifier, the request sending address of the network service request, and the data output address of the task execution result; wherein the instructions for tasks to be executed include network connection service tasks and / or other network service tasks other than network connection service tasks, and the other network service tasks include at least one of data acquisition service tasks, data calculation service tasks, context awareness service tasks, and artificial intelligence service tasks.

[0099] In an exemplary embodiment of the present disclosure, the task orchestration agent includes a task decomposition model, which includes an embedding mapping layer, an encoding layer and a hybrid expert model; wherein, a target network service request task is subjected to service parsing to obtain a plurality of subtasks with dependency relationships, including: parsing the target network service request to obtain service request details, the device service area to which the user device belongs, and the service level requirements corresponding to the device service area; generating basic information to be predicted based on the service request details, the device service area and the service level requirements, and generating context information to be predicted based on preset model prompt parameters; embedding mapping processing is performed on the basic information to be predicted based on the embedding mapping layer to obtain network service features, and embedding mapping processing is performed on the context information to be predicted based on the embedding mapping layer to obtain a context flag sequence; encoding processing is performed on the network service features and the context flag sequence based on the encoding layer to obtain a context overall representation, and service parsing is performed on the context flag sequence and the context overall representation based on the hybrid expert model to obtain a plurality of subtasks with dependency relationships.

[0100] In an exemplary embodiment of the present disclosure, the hybrid expert model includes a gating network model and multiple expert neural network models; wherein, based on the hybrid expert model, the context flag sequence and the overall context representation are subjected to service parsing to obtain multiple subtasks with dependencies, including: determining, based on the gating network model and the context flag sequence, a first model weight of each expert neural network model in the resource requirement dimension, a second model weight in the service quality dimension, and a third model weight in the dependency dimension; based on the first model weight, the second model weight, and the third model weight, determining from each expert neural network model a first target neural network model required for performing a service parsing task in the resource requirement dimension, a second target neural network model required for performing a service parsing task in the service quality dimension, and a third target neural network model required for performing a service parsing task in the dependency dimension; inputting the context flag sequence and the overall context representation into the first target neural network model, the second target neural network model, and the third target neural network model, respectively, to obtain a first prediction result in the resource requirement dimension, a second prediction result in the service instruction dimension, and a third prediction result in the dependency dimension, and obtaining multiple subtasks with dependencies based on the first prediction result, the second prediction result, and the third prediction result.

[0101] In an exemplary embodiment of the present disclosure, determining the service management agent corresponding to the to-be-executed task instruction includes: determining a candidate management agent based on the device service area to which the user device belongs, and matching the to-be-executed task instruction with a corresponding service management agent from the candidate management agents based on the instruction type of the to-be-executed task instruction; wherein, if the instruction type is a first to-be-executed task corresponding to a network connection service task, determining the service management agent corresponding to the first to-be-executed task to be a network connection management agent; if the instruction type is a second to-be-executed task corresponding to other network service tasks, determining the service management agent corresponding to the second to-be-executed task to be a data management agent; the data management agent includes at least one of a data acquisition management agent, a data calculation management agent, a context-aware management agent, and an artificial intelligence management agent.

[0102] In an exemplary embodiment of the present disclosure, task execution function network elements are assigned to the task instructions to be executed, including: a network connection management agent assigns a first task execution function network element to the first task to be executed from the user plane function network elements included in the device service area to which the user device belongs; a data management agent assigns a second task execution function network element to the second task to be executed from the current data management function network elements included in the device service area to which the user device belongs; wherein the current data management function network element includes at least one of a data acquisition function network element, a data calculation function network element, a context perception function network element, and an artificial intelligence function network element.

[0103] In an exemplary embodiment of the present disclosure, a second task execution function network element is allocated to a second task to be executed from a current data management function network element included in a device service area to which a user device belongs, including: receiving current computing power capability information and current computing power resource information reported by a current data management function network element included in a device service area to which the user device belongs; calculating a first matching degree between the current computing power capability information and the service quality requirement of the task to be executed, and calculating a second matching degree between the current computing power resource information and the resource requirement of the task to be executed; and allocating a task execution function network element to the task to be executed from the current function network element according to the first matching degree and the second matching degree.

[0104] In an exemplary embodiment of the present disclosure, instruction conversion is performed on the task instruction to be executed to obtain a task signaling to be executed, including: performing word segmentation processing on the task instruction to be executed to obtain a word segmentation processing result, and determining a grammatical role of the word segmentation processing result in the task instruction to be executed; performing named entity recognition on the word segmentation processing result according to the grammatical role to obtain an entity recognition result, and determining a task execution intention and task execution parameters based on the entity recognition result; constructing a protocol data unit according to the task execution intention and task execution parameters, and encoding the protocol data unit to obtain a task signaling to be executed.

[0105] In an exemplary embodiment of the present disclosure, executing the signaling of the task to be executed to obtain a signaling execution result, including: the first task execution function network element executes the signaling of the task to be executed to obtain a protocol data unit session connection between the user equipment and the data network; the second task execution function network element executes the signaling of the task to be executed to obtain a data acquisition result and / or a data calculation result and / or a situational perception result and / or an artificial intelligence prediction result.

[0106] The specific details of each module in the above-mentioned network service request processing device have been described in detail in the corresponding network service request processing method, so they will not be repeated here.

[0107] It should be noted that although several modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0108] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0109] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0110] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods, or program products. Therefore, various aspects of the present disclosure may be implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits," "modules," or "systems."

[0111] Refer to the following Figure 8 800 according to this embodiment of the present disclosure will be described. Figure 8 The electronic device 800 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0112] like Figure 8 As shown, electronic device 800 is implemented as a general-purpose computing device. Components of electronic device 800 may include, but are not limited to, the aforementioned at least one processing unit 810, the aforementioned at least one storage unit 820, a bus 830 connecting various system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0113] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps described in the "Exemplary Method" section of the present disclosure according to various exemplary embodiments. For example, the processing unit 810 can perform the following steps: Figure 1 Step S110 shown in: the task scheduling agent parses the network service request sent by the user device to obtain the task instruction to be executed, and determines the service management agent corresponding to the task instruction to be executed; step S120: the task scheduling agent sends the task instruction to be executed to the service management agent, and the service management agent assigns a task execution function network element to the task instruction to be executed; step S130: the service management agent calls the instruction translation agent to perform instruction conversion on the task instruction to be executed to obtain the task signaling to be executed, and sends the task signaling to be executed to the task execution function network element; step S140: the task execution function network element executes the task signaling to be executed to obtain the signaling execution result, and performs instruction conversion on the signaling execution result to obtain the task execution result corresponding to the network service request, so as to feed back the task execution result to the user device.

[0114] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0115] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0116] Bus 830 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0117] The electronic device 800 can also communicate with one or more external devices 900 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 800, and / or any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication can occur via an input / output (I / O) interface 850. Furthermore, the electronic device 800 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 800, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0118] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0119] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, on which is stored a program product capable of implementing the aforementioned methods of this specification. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to execute the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of the present disclosure.

[0120] According to an embodiment of the present disclosure, a program product for implementing the above-mentioned method can be a portable compact disc read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0121] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0122] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0123] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0124] The program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0125] Furthermore, the figures above are merely illustrative of the processes included in the methods according to exemplary embodiments of the present disclosure and are not intended to be limiting. It is readily understood that the processes illustrated in the figures above do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0126] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not invented herein. The specification and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

Claims

1. A method for processing a network service request, characterized in that: include: The task scheduling agent parses the network service request sent by the user device to obtain a task instruction to be executed, and determines a service management agent corresponding to the task instruction to be executed; The task scheduling agent sends the to-be-executed task instructions to the service management agent, and the service management agent allocates a task execution function network element to the to-be-executed task instructions; The service management agent calls the instruction translation agent to convert the instruction of the task to be executed to obtain the signaling of the task to be executed, and sends the signaling of the task to be executed to the task execution function network element; The task execution function network element executes the signaling of the task to be executed to obtain a signaling execution result, and performs instruction conversion on the signaling execution result to obtain a task execution result corresponding to the network service request, so as to feed back the task execution result to the user equipment.

2. The method for processing a network service request according to claim 1, wherein: The task scheduling agent parses the network service request sent by the user device to obtain the task instructions to be executed, including: The access and mobility management function network element receives the original network service request sent by the user equipment, and performs instruction translation on the original network service request to obtain a target network service request; The task scheduling agent receives the target network service request and performs service analysis on the target network service request task to obtain multiple subtasks with dependency relationships; The task scheduling agent configures a unique task identifier for the subtask, and generates the to-be-executed task instruction according to the subtask, the unique task identifier, the request sending address of the network service request, and the data output address of the task execution result; Among them, the task instructions to be executed include network connection service tasks and / or other network service tasks other than network connection service tasks, and the other network service tasks include at least one of data acquisition service tasks, data calculation service tasks, situational awareness service tasks and artificial intelligence service tasks.

3. The method for processing a network service request according to claim 2, wherein: The task orchestration agent includes a task decomposition model, which includes an embedded mapping layer, an encoding layer, and a hybrid expert model. The target network service request task is subjected to service parsing to obtain a plurality of subtasks with dependency relationships, including: Parsing the target network service request to obtain service request details, a device service area to which the user equipment belongs, and a service level requirement corresponding to the device service area; Generate basic information to be predicted based on the service request details, equipment service area, and service level requirements, and generate context information to be predicted based on preset model prompt parameters; Performing embedding mapping processing on the basic information to be predicted based on the embedding mapping layer to obtain network service features, and performing embedding mapping processing on the context information to be predicted based on the embedding mapping layer to obtain a context flag sequence; Based on the coding layer, network service features and context marker sequences are encoded to obtain a context overall representation, and based on the hybrid expert model, service parsing is performed on the context marker sequence and the context overall representation to obtain multiple subtasks with dependency relationships.

4. The method for processing a network service request according to claim 3, wherein: The hybrid expert model includes a gated network model and multiple expert neural network models; The context token sequence and the overall context representation are analyzed based on the hybrid expert model to obtain multiple subtasks with dependencies, including: Determining, based on the gating network model and according to the context flag sequence, a first model weight in the resource requirement dimension, a second model weight in the service quality dimension, and a third model weight in the dependency dimension for each of the expert neural network models; Based on the first model weight, the second model weight, and the third model weight, determining from each of the expert neural network models a first target neural network model required to perform the service resolution task in the resource requirement dimension, a second target neural network model required to perform the service resolution task in the service quality dimension, and a third target neural network model required to perform the service resolution task in the dependency dimension; The context flag sequence and the overall context representation are respectively input into the first target neural network model, the second target neural network model and the third target neural network model to obtain a first prediction result in the resource requirement dimension, a second prediction result in the service instruction dimension and a third prediction result in the dependency dimension, and based on the first prediction result, the second prediction result and the third prediction result, a plurality of subtasks with dependencies are obtained.

5. The method for processing a network service request according to claim 1, wherein: Determining a service management agent corresponding to the task instruction to be executed includes: A candidate management agent is determined based on the device service area to which the user device belongs, and a corresponding service management agent is matched for the task instruction to be executed from the candidate management agents based on the instruction type of the task instruction to be executed; wherein, if the instruction type is a first task to be executed corresponding to a network connection service task, the service management agent corresponding to the first task to be executed is determined to be a network connection management agent; if the instruction type is a second task to be executed corresponding to other network service tasks, the service management agent corresponding to the second task to be executed is determined to be a data management agent; the data management agent includes at least one of a data acquisition management agent, a data calculation management agent, a context-aware management agent, and an artificial intelligence management agent.

6. The method for processing a network service request according to claim 5, wherein: Allocating a task execution function network element to the task instruction to be executed includes: The network connection management agent allocates a first task execution function network element to the first to-be-executed task from user plane function network elements included in the device service area to which the user equipment belongs; The data management agent allocates a second task execution function network element to the second task to be executed from the current data management function network elements included in the device service area to which the user device belongs; wherein the current data management function network element includes at least one of a data acquisition function network element, a data calculation function network element, a context perception function network element and an artificial intelligence function network element.

7. The method for processing a network service request according to claim 6, wherein: Allocating a second task execution function network element for the second to-be-executed task from current data management function network elements included in the device service area to which the user equipment belongs includes: Receiving current computing capacity information and current computing resource information reported by a current data management function network element included in a device service area to which the user equipment belongs; Calculating a first matching degree between the current computing power capability information and the service quality requirement of the task to be executed, and calculating a second matching degree between the current computing power resource information and the resource requirement of the task to be executed; Allocate a task execution functional network element to the task to be executed from the current functional network elements according to the first matching degree and the second matching degree.

8. The method for processing a network service request according to claim 1, wherein: Converting the to-be-executed task instruction to obtain a to-be-executed task signaling includes: Performing word segmentation processing on the task instruction to be executed to obtain a word segmentation processing result, and determining a grammatical role of the word segmentation processing result in the task instruction to be executed; Performing named entity recognition on the word segmentation processing result according to the grammatical role to obtain an entity recognition result, and determining a task execution intention and a task execution parameter based on the entity recognition result; A protocol data unit is constructed according to the task execution intention and the task execution parameters, and the protocol data unit is encoded to obtain a signaling of the task to be executed.

9. The method for processing a network service request according to claim 1, wherein: Executing the task signaling to be executed to obtain a signaling execution result includes: The first task execution function network element executes the to-be-executed task signaling to obtain a protocol data unit session connection between the user equipment and the data network; The second task execution function network element executes the task signaling to be executed to obtain data acquisition results and / or data calculation results and / or situational perception results and / or artificial intelligence prediction results.

10. A network service request processing system, characterized in that: include: A task scheduling agent is used to parse the network service request sent by the user device to obtain a task instruction to be executed, and determine a service management agent corresponding to the task instruction to be executed; The task scheduling agent is used to send the instructions of the tasks to be executed to the service management agent; The service management agent is configured to allocate a task execution function network element to the task instruction to be executed; and call an instruction translation agent to convert the task instruction to be executed to obtain a task signaling to be executed, and send the task signaling to the task execution function network element; The task execution function network element is used to execute the signaling of the task to be executed to obtain a signaling execution result, and perform instruction conversion on the signaling execution result to obtain a task execution result corresponding to the network service request, so as to feed back the task execution result to the user equipment.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for processing a network service request according to any one of claims 1 to 9 is implemented.

12. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to execute the method for processing a network service request according to any one of claims 1 to 9 by executing the executable instructions.

Images