Industrial agent system

Abstract

The invention discloses an industrial agent system, which comprises an intelligent decision-making platform, an equipment service bus, an application service bus and an open service bus, and is characterized in that the equipment service bus integrates real-time data of an OT domain production field; an open service bus integrates enterprise external information; the application service bus integrates management data in an enterprise IT domain, production field real-time data integrated by the equipment service bus and enterprise external information integrated by the open service bus, and provides the data to the intelligent decision-making platform for calling in a service form, and the application service bus provides a service directory to the intelligent decision-making platform; the intelligent decision-making platform comprises a core processing unit, a general large model and a local knowledge base; and the core processing unit processes task requirements in input information and generates corresponding responses by calling services provided by the general large model, the local knowledge base and the application service bus and integrated functional components. The method can provide powerful support for intelligent transformation of the manufacturing industry.

Description

Technical Field

[0001] The present invention relates to the field of industrial intelligent agents, and in particular to an industrial intelligent agent system. Background Art

[0002] With the rapid development of information technology, in the field of intelligent manufacturing, industrial intelligent agents are gradually becoming the core driving force for the upgrading of the manufacturing industry with their unique intelligent decision-making, autonomous control and optimized management capabilities. 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, covering everything from real-time data on production sites to enterprise management system data, and massive amounts of information on supply chains and markets. How to effectively integrate these scattered, heterogeneous, and diverse data to form valuable information resources for industrial intelligence is the key to building industrial intelligence.

[0004] Secondly, the manufacturing industry’s production process is complex and changeable, involving multiple links and departments, requiring industrial intelligence to be able to perceive changes in the production environment in real time and respond accurately and quickly.

[0005] In addition, with the continuous advancement of technology and the rapid changes in the market, new data resources and business needs continue to emerge. This requires industrial intelligence to have good scalability and flexibility to adapt to the ever-changing environment and needs. Summary of the invention

[0006] The present invention provides an industrial intelligent body system to solve the problem that the existing industrial intelligent body cannot effectively integrate and utilize data resources and cannot quickly respond to production service requirements.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is: An industrial intelligent system includes an intelligent decision-making platform, a device service bus, an application service bus, and an open service bus, wherein the device service bus integrates real-time data of production sites in the OT domain; the open service bus integrates external information of the enterprise; the application service bus integrates management data in the enterprise IT domain, as well as real-time data of production sites integrated by the device service bus and external information of the enterprise integrated by the open service bus, and the application service bus divides the integrated data and information according to set logic or functional requirements and provides them to the intelligent decision-making platform in the form of services, and the application service bus provides a service catalog to the intelligent decision-making platform; The intelligent decision-making platform includes a core processing unit, a general large model, and a local knowledge base; the general large model is used to process and analyze the input natural language, understand the core intent in the input natural language, and output responses related to the core intent; the local knowledge base is used to store, manage and retrieve knowledge, experience and rules in a specific field, and the local knowledge base stores the service directory of the application service bus; the core processing unit is integrated with functional components and receives external input information. The core processing unit processes the task requirements in the input information and generates corresponding responses by calling the general large model, the local knowledge base, the services provided by the application service bus and the integrated functional components.

[0008] Furthermore, the core processing unit also performs feedback learning and optimization according to the output response results.

[0009] Furthermore, the core processing unit processes the task requirements in the input information as follows: S1, the core processing unit retrieves the service set related to the input information from the local knowledge base; S2, the core processing unit further screens the service set through the 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, and generates request parameters required for requesting the target service; S4, the core processing unit uses the generated request parameters to initiate a request to the target service; S5. The core processing unit receives a response message from the target service; 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; S7. The core processing unit returns a response content.

[0010] The present invention integrates the data resources of IT, OT and ET of manufacturing enterprises to realize the rapid construction and intelligent application of industrial intelligent entities, providing strong support for the intelligent transformation of the manufacturing industry. Compared with the existing technology, the present invention has the following advantages: 1. Data integration capability: This method integrates IT, OT and ET data resources to achieve efficient integration of various data of manufacturing enterprises, break data silos, improve data utilization, and provide comprehensive data support for the construction of industrial intelligence.

[0011] 2. Rapid construction and intelligent application: This method can deploy and use industrial intelligent bodies more quickly, thereby accelerating the intelligent transformation process of the manufacturing industry.

[0012] 3. Flexibility and scalability: The industrial intelligent agent constructed by this method has high flexibility and scalability, ensuring that the industrial intelligent agent can quickly respond to various changes in production and meet the ever-changing needs of enterprises.

[0013] 4. Improve competitiveness: By introducing industrial intelligence, enterprises can better utilize data resources, optimize production processes, and improve production efficiency and quality. This will help enterprises improve their competitiveness and stand out in the fierce market competition. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a system architecture diagram of an embodiment of the present invention.

[0015] Figure 2 It is a functional architecture diagram of an application service bus according to an embodiment of the present invention.

[0016] Figure 3 It is a service directory information set architecture diagram of an embodiment of the present invention.

[0017] Figure 4 It is a processing logic flow chart of the core processing unit of an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0019] like Figure 1 As shown, this embodiment discloses an industrial intelligent system, including an intelligent decision-making platform and a fusion and interconnection platform, wherein the fusion and interconnection platform includes a device service bus, an application service bus, and an open service bus.

[0020] In the Rongtong interconnection platform of this embodiment, the device service bus integrates the real-time data generated by sensors, automation equipment and SCADA systems in the OT domain production site. The open service bus integrates the cloud services, partners and supply chain information in the enterprise's external ET. The application service bus integrates the management data in the ERP enterprise resource planning system, MES manufacturing execution system and CRM customer relationship management system in the enterprise IT domain, as well as the real-time production site data integrated by the device service bus and the 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, and the service catalog describing the information set of the service is provided to the intelligent decision-making platform by the application service bus.

[0021] Among them Figure 2 As shown, the application service bus functions include service registration, service publishing, service management, format conversion, protocol conversion, and service catalog. The specific description is as follows: Service registration: used to register the data access services of the open service bus, device service bus and application systems in the enterprise IT domain into the application service bus. The registration information includes the service identifier, service name, service request address, service request method, service request parameter description and service response parameter description.

[0022] Service publishing: It is used to publish registered services so that they can be discovered and called by service requesters, and the published services are divided according to specific logic or functional requirements.

[0023] Service management: used for the full life cycle management of registered and published services, including modification, deletion, and version control of services.

[0024] Format conversion: used to convert different data formats into a unified format.

[0025] Protocol conversion: used to convert different communication protocols uniformly.

[0026] Dynamic provision: used to provide the service catalog to the local knowledge base through web pages, files or interfaces, and dynamically modify the service dependencies and query templates in the service catalog according to user needs.

[0027] The service catalog is a collection of information describing services in the application service bus, such as Figure 3 As shown, the service catalog includes service identification, service name, service description, inter-service dependencies, and query templates, where the query templates contain keywords, phrases, and question examples related to the service.

[0028] The intelligent decision-making platform of this embodiment includes a core processing unit, a general large model, and a local knowledge base. The general large model is used to process and analyze the input natural language, understand the core intent in the input natural language, and output responses related to the core intent. The local knowledge base is used to store, manage and retrieve knowledge, experience and rules in a specific field, and the local knowledge base stores the service directory of the application service bus. The core processing unit is integrated with functional components and receives external input information. The functional components include search engines, weather queries, and speech recognition. The core processing unit processes the task requirements in the input information and generates corresponding responses by calling the general large model, the local knowledge base, the services provided by the application service bus, and the integrated functional components. At the same time, the core processing unit performs feedback learning and optimization based on the output results to improve the performance and efficiency of the industrial intelligent body. Figure 4 As shown, the core processing unit processes the task requirements in the input information as follows: S1, the core processing unit retrieves the service set related to the input information from the local knowledge base; S2, the core processing unit further screens the service set through the 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, and generates request parameters required for requesting the target service; S4, the core processing unit uses the generated request parameters to initiate a request to the target service; S5. The core processing unit receives a response message from the target service; 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; S7. The core processing unit returns a response content.

[0029] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. The embodiments described in the present invention are merely descriptions of the preferred embodiments of the present invention, and do not limit the concept and scope of the present invention. The various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction, and such combinations should also be regarded as the contents disclosed in the present disclosure as long as they do not violate the concept of the present invention. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations.

[0030] The present invention is not limited to the specific details of the above-mentioned embodiments. Within the technical concept of the present invention and without departing from the design concept of the present invention, various modifications and improvements made to the technical solution of the present invention by technical personnel in this field should fall within the protection scope of the present invention. The technical contents for which protection is sought in the present invention have been fully recorded in the claims.

Claims

1. An industrial intelligent agent system, characterized in that: It includes an intelligent decision-making platform, as well as a device service bus, an application service bus, and an open service bus. The device service bus integrates real-time data from the OT domain production site; The open service bus integrates enterprise external information; The application service bus integrates the management data in the enterprise IT domain, the real-time data of the production site integrated by the device service bus, and the external information of the enterprise 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, and the application service bus provides the service catalog to the intelligent decision-making platform; The intelligent decision-making platform includes a core processing unit, a general large model, and a local knowledge base; the general large model is used to process and analyze the input natural language, understand the core intent in the input natural language, and output responses related to the core intent; the local knowledge base is used to store, manage and retrieve knowledge, experience and rules in a specific field, and the local knowledge base stores the service directory of the application service bus; the core processing unit is integrated with functional components and receives external input information. The core processing unit processes the task requirements in the input information and generates corresponding responses by calling the general large model, the local knowledge base, the services provided by the application service bus and the integrated functional components.

2. An industrial intelligent agent system according to claim 1, characterized in that: The core processing unit also performs feedback learning and optimization according to the output response results.

3. An industrial intelligent agent system according to claim 1, characterized in that: The core processing unit processes the task requirements in the input information as follows: S1, the core processing unit retrieves the service set related to the input information from the local knowledge base; S2, the core processing unit further screens the service set through the 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, and generates request parameters required for requesting the target service; S4, the core processing unit uses the generated request parameters to initiate a request to the target service; S5. The core processing unit receives a response message from the target service; 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; S7. The core processing unit returns a response content.

Images