An industrial intelligent system

Abstract

This invention discloses an industrial intelligent agent system, including an intelligent decision-making platform, an equipment service bus, an application service bus, and an open service bus. The equipment service bus integrates real-time data from the production site in the OT domain; the open service bus integrates external enterprise information; and the application service bus integrates management data from the enterprise IT domain. These, along with the real-time production site data integrated by the equipment service bus and the external enterprise information integrated by the open service bus, are provided to the intelligent decision-making platform as services. The application service bus also provides a service catalog to the intelligent decision-making platform. The intelligent decision-making platform includes a core processing unit, a general-purpose model, and a local knowledge base. The core processing unit processes task requirements from input information and generates corresponding responses by calling the services provided by the general-purpose model, the local knowledge base, the application service bus, and integrated functional components. This invention can provide strong support for the intelligent transformation of the manufacturing industry.

Description

Technical Field

[0001] This invention relates to the field of industrial intelligent agents, specifically an industrial intelligent agent system. Background Technology

[0002] With the rapid development of information technology, industrial intelligent agents, with their unique intelligent decision-making, autonomous control, and optimized management capabilities, are gradually becoming the core driving force for the upgrading of the manufacturing industry in the field of intelligent manufacturing. However, the realization of industrial intelligent agents is not easy, and they face many challenges in the process of construction and operation.

[0003] First, the data environment of manufacturing enterprises is extremely complex, encompassing massive amounts of information from real-time production data to enterprise management system data, and then to supply chain and market data. The key to building an industrial intelligent agent lies in effectively integrating this scattered, heterogeneous, and diverse data to form valuable information resources.

[0004] Secondly, the manufacturing process is complex and ever-changing, involving multiple links and departments, requiring industrial intelligent agents to be able to perceive changes in the production environment in real time and make accurate and rapid responses.

[0005] Furthermore, with continuous technological advancements and rapid market changes, new data resources and business demands are constantly emerging. This necessitates that industrial intelligent agents possess strong scalability and flexibility to adapt to ever-changing environments and needs. Summary of the Invention

[0006] This invention provides an industrial intelligent agent system to solve the problems of existing industrial intelligent agents being unable to effectively integrate and utilize data resources and unable to quickly respond to production service requirements.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0008] An industrial intelligent agent system includes an intelligent decision-making platform, an equipment service bus, an application service bus, and an open service bus. The equipment service bus integrates real-time data from the production site in the OT domain; the open service bus integrates external enterprise information; and the application service bus integrates management data from the enterprise IT domain. The integrated data and information, after being divided according to predefined logic or functional requirements, are provided to the intelligent decision-making platform as services. Furthermore, the application service bus provides a service catalog to the intelligent decision-making platform.

[0009] The intelligent decision-making platform includes a core processing unit, a general-purpose large model, and a local knowledge base. The general-purpose large model is used to process and analyze the input natural language, understand the core intent in the input natural language, and output a response related to the core intent. The local knowledge base is used to store, manage, and retrieve knowledge, experience, and rules in a specific domain, and also stores the service directory of the application service bus. The core processing unit integrates functional components and receives external input information. By calling the services provided by the general-purpose large model, the local knowledge base, the application service bus, and the integrated functional components, the core processing unit processes the task requirements in the input information and generates corresponding responses.

[0010] Furthermore, the core processing unit also performs feedback learning and optimization based on the output response results.

[0011] Furthermore, the core processing unit processes the task requirements in the input information as follows:

[0012] S1. The core processing unit retrieves a set of services related to the input information from the local knowledge base;

[0013] S2. The core processing unit further filters the service set through a general large model to determine the target service that meets the requirements and the service identifier of the target service.

[0014] S3. The core processing unit obtains the general large model description of the target service from the application service bus through the service identifier of the target service;

[0015] S4. The core processing unit sends the general large model description and input information to the general large model to generate the request parameters required to request the target service.

[0016] S4. The core processing unit uses the generated request parameters to send a request to the target service;

[0017] S5. The core processing unit receives response information from the target service;

[0018] S6. The core processing unit sends the input information and the response information of the target service to the general large model and generates response content related to the input information.

[0019] S7, The core processing unit returns the response content.

[0020] This invention integrates IT, OT, and ET data resources of manufacturing enterprises to achieve rapid construction and intelligent application of industrial intelligent agents, providing strong support for the intelligent transformation of the manufacturing industry. Compared with existing technologies, the advantages of this invention are:

[0021] 1. Data Integration Capability: This method achieves efficient integration of various types of data from manufacturing enterprises by integrating IT, OT, and ET data resources. It breaks down data silos, improves data utilization, and provides comprehensive data support for the construction of industrial intelligent agents.

[0022] 2. Rapid Construction and Intelligent Application: This method enables faster deployment and use of industrial intelligent agents, thereby accelerating the intelligent transformation of the manufacturing industry.

[0023] 3. Flexibility and Scalability: The industrial intelligent agent constructed using this method exhibits high flexibility and scalability. This ensures that the industrial intelligent agent can quickly respond to various changes in production and meet the ever-changing needs of the enterprise.

[0024] 4. Enhance competitiveness: By introducing industrial intelligence, enterprises can better utilize data resources, optimize production processes, and improve production efficiency and quality. This will help enterprises enhance their competitiveness and stand out in the fierce market competition. Attached Figure Description

[0025] Figure 1 This is a system architecture diagram of an embodiment of the present invention.

[0026] Figure 2 This is a functional architecture diagram of the application service bus in an embodiment of the present invention.

[0027] Figure 3 This is a service catalog information collection architecture diagram according to an embodiment of the present invention.

[0028] Figure 4 This is a flowchart of the processing logic of the core processing unit in an embodiment of the present invention. Detailed Implementation

[0029] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0030] like Figure 1 As shown in the figure, this embodiment discloses an industrial intelligent agent system, including an intelligent decision-making platform and a converged interconnection platform, wherein the converged interconnection platform includes a device service bus, an application service bus, and an open service bus.

[0031] In this embodiment's converged interconnection platform, the Device Service Bus integrates real-time data generated by sensors, automated equipment, and SCADA systems in the OT domain production site. The Open Service Bus integrates information from cloud services, partners, and the supply chain in the external ET domain. The Application Service Bus integrates management data from the ERP (Enterprise Resource Planning) system, MES (Manufacturing Execution System), and CRM (Customer Relationship Management) system in the enterprise IT domain, as well as real-time production site data integrated by the Device Service Bus and external enterprise information integrated by the Open Service Bus. The Application Service Bus then divides the integrated data and information according to predefined logical or functional requirements and provides it as services to the intelligent decision-making platform. A service catalog describing the information sets of these services is also provided to the intelligent decision-making platform by the Application Service Bus.

[0032] Among them, such as Figure 2 As shown, the application service bus functions include service registration, service publishing, service management, format conversion, protocol conversion, and service catalog. Detailed explanations are as follows:

[0033] Service Registration: This is used to register data access services of application systems in the Open Service Bus, Device Service Bus, and Enterprise IT Domain to the Application Service Bus. The registration information includes service identifier, service name, service request address, service request method, service request parameter description, and service response parameter description.

[0034] Service publishing: This is used to publish registered services so that they can be discovered and invoked by service requesters. Published services are divided according to specific logic or functional requirements.

[0035] Service Management: Used for the full lifecycle management of registered and published services, including service modification, deletion, and version control.

[0036] Format conversion: Used to convert different data formats in a unified manner.

[0037] Protocol conversion: Used to uniformly convert different communication protocols.

[0038] Dynamic provisioning: This is used to provide the service catalog to the local knowledge base via web pages, files, or interfaces, and dynamically modify the service dependencies and query templates in the service catalog according to user needs.

[0039] The service catalog is a collection of information describing the services in the application service bus, such as... Figure 3 As shown, the service catalog includes service identifiers, service names, service descriptions, inter-service dependencies, and query templates. The query templates contain service-related keywords, phrases, and question examples.

[0040] The intelligent decision-making platform in this embodiment includes a core processing unit, a general-purpose large model, and a local knowledge base. The general-purpose large model processes and analyzes the input natural language, understands the core intent within the input, and outputs a response related to that core intent. The local knowledge base stores, manages, and retrieves domain-specific knowledge, experience, and rules, and also stores the service directory of the application service bus. The core processing unit integrates functional components and receives external input information. These functional components include a search engine, weather query, and speech recognition. The core processing unit processes the task requirements in the input information and generates corresponding responses by calling the services provided by the general-purpose large model, the local knowledge base, the application service bus, and the integrated functional components. Simultaneously, the core processing unit performs feedback learning and optimization based on the output results to improve the performance and efficiency of the industrial intelligent agent. Figure 4 As shown, the core processing unit processes the task requirements in the input information as follows:

[0041] S1. The core processing unit retrieves a set of services related to the input information from the local knowledge base;

[0042] S2. The core processing unit further filters the service set through a general large model to determine the target service that meets the requirements and the service identifier of the target service.

[0043] S3. The core processing unit obtains the general large model description of the target service from the application service bus through the service identifier of the target service;

[0044] S4. The core processing unit sends the general large model description and input information to the general large model to generate the request parameters required to request the target service.

[0045] S4. The core processing unit uses the generated request parameters to send a request to the target service;

[0046] S5. The core processing unit receives response information from the target service;

[0047] S6. The core processing unit sends the input information and the response information of the target service to the general large model and generates response content related to the input information.

[0048] S7, The core processing unit returns the response content.

[0049] The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings. These embodiments are merely descriptions of preferred embodiments and are not intended to limit the scope or concept of the invention. The specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. Such combinations, as long as they do not violate the spirit of the present invention, should also be considered as part of this disclosure. To avoid unnecessary repetition, the present invention will not further describe the various possible combinations.

[0050] This invention is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this invention and without departing from the design idea of ​​this invention, all modifications and improvements made by those skilled in the art to the technical solutions of this invention should fall within the protection scope of this invention. The technical content for which protection is sought in this invention has been fully described in the claims.

Claims

1. An industrial intelligent agent system, characterized in that, It includes an intelligent decision-making platform, as well as an equipment service bus, an application service bus, and an open service bus, wherein the equipment service bus integrates real-time data from the OT domain production site; The open service bus integrates external enterprise information; The application service bus integrates management data in the enterprise IT domain, real-time production site data integrated by the equipment service bus, and external enterprise information integrated by the open service bus. The application service bus divides the integrated data and information according to the set logic or functional requirements and provides them to the intelligent decision-making platform in the form of services. The application service bus also provides the intelligent decision-making platform with a service catalog. The intelligent decision-making platform includes a core processing unit, a general-purpose large model, and a local knowledge base. The general-purpose large model is used to process and analyze the input natural language, understand the core intent in the input natural language, and output a response related to the core intent. The local knowledge base is used to store, manage, and retrieve knowledge, experience, and rules in a specific domain, and also stores the service directory of the application service bus. The core processing unit integrates functional components and receives external input information. By calling the services provided by the general-purpose large model, the local knowledge base, the application service bus, and the integrated functional components, the core processing unit processes the task requirements in the input information and generates corresponding responses. The core processing unit also performs feedback learning and optimization based on the output response results; The core processing unit processes the task requirements in the input information as follows: S1. The core processing unit retrieves a set of services related to the input information from the local knowledge base; S2. The core processing unit further filters the service set through a general large model to determine the target service that meets the requirements and the service identifier of the target service. S3. The core processing unit obtains the general large model description of the target service from the application service bus through the service identifier of the target service; S4. The core processing unit sends the general large model description and input information to the general large model to generate the request parameters required to request the target service. S5. The core processing unit uses the generated request parameters to send a request to the target service; S6. The core processing unit receives response information from the target service; S7. The core processing unit sends the input information and the response information of the target service to the general large model and generates response content related to the input information. S8, the core processing unit returns the response content.

Images