Industrial scene-oriented intelligent Agent system with body and implementation method thereof

Abstract

The invention discloses an industrial scene-oriented intelligent Agent system and an implementation method thereof, and the system comprises a user interaction layer which is used for providing a diversified interface and carrying out the communication with a back-end service through an API gateway; the intelligent layer is used for realizing task management, task planning and resource scheduling functions by adopting a micro-service architecture arranged based on a container; the physical equipment layer is used for being integrated with an upper-layer system through an industrial Internet of Things protocol and processing time-sensitive applications by adopting an edge computing technology; wherein the user interaction layer is bidirectionally connected with the body intelligent layer, and the body intelligent layer is bidirectionally connected with the physical equipment layer. According to the invention, a series of operations such as order analysis, material planning, production planning, task distribution, material preparation, production execution, quality control and exception handling can be autonomously carried out, manual intervention is greatly reduced, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to an embodied intelligent Agent system for industrial scenarios and an implementation method thereof. Background Art

[0002] In today's rapidly developing intelligent manufacturing field, the application of artificial intelligence technology has become a key driving force for improving production efficiency and product quality. With the continuous advancement of technologies such as big data, machine learning, and computer vision, intelligent manufacturing systems are gradually developing in the direction of intelligence, automation, and integration. However, although existing technologies have shown significant advantages, their development and application still face many challenges and limitations.

[0003] The prior art discloses an intelligent manufacturing system based on artificial intelligence, including a manufacturing module, a management module, a quality module and a power supply module. The quality module includes a shooting unit, an analysis unit and a material picking unit. The management module controls the operation of the manufacturing module and the quality module. The manufacturing module automatically assembles and manufactures power equipment. The shooting unit shoots and collects pictures of the power equipment to obtain shooting data. The analysis unit identifies the shooting data and analyzes it in combination with preset defective product parameters to obtain analysis information. The material picking unit screens out defective products in the power equipment based on the analysis information. The system manages the power equipment production line through artificial intelligence technology, shoots pictures of the power equipment during the production process, and uses image recognition technology to analyze and judge defective products. Compared with the randomness of traditional manual sampling, defective products can be eliminated one by one, greatly improving the qualified quality of the power equipment.

[0004] However, the above system only targets a specific scenario and lacks generalization. It simply divides the system into modules without considering the planning and scheduling between modules, and does not have general artificial intelligence capabilities.

[0005] Existing intelligent manufacturing systems usually rely on a variety of digital systems and equipment, but lack a unified intelligent control and coordination mechanism, making it difficult to achieve full automation and intelligence in the production process. Therefore, there is an urgent need for an intelligent system that can integrate various digital systems and equipment and has autonomous decision-making and execution capabilities to improve production efficiency and flexibility. Summary of the invention

[0006] In order to solve the above technical problems, the present invention proposes an embodied intelligent Agent system for industrial scenarios and its implementation method, which utilizes all digital systems and equipment in the factory, combines related systems and databases, process documents and other prior information, and realizes autonomous production process planning and execution after order input.

[0007] On the one hand, to achieve the above-mentioned purpose, the present invention provides an embodied intelligent agent system for industrial scenarios, comprising:

[0008] User interaction layer: used to provide diversified interfaces and communicate with backend services through API gateway;

[0009] Embodied intelligence layer: used to adopt a microservice architecture based on container orchestration to implement task management, task planning, and resource scheduling functions;

[0010] Physical device layer: used to integrate with upper-layer systems through industrial IoT protocols and use edge computing technology to handle time-sensitive applications;

[0011] The user interaction layer is bidirectionally connected to the embodied intelligence layer, and the embodied intelligence layer is bidirectionally connected to the physical device layer.

[0012] Preferably, the diversified interfaces in the user interaction layer include:

[0013] An order subsystem interface based on a modern web framework, a cross-platform mobile application interface, a voice interaction subsystem interface with integrated deep learning, and an AR / VR monitoring interface.

[0014] Preferably, the embodied intelligence layer comprises:

[0015] Central Agent module: used for microservice architecture based on container orchestration to realize order management, task planning, resource scheduling, and embodied intelligent Agent group management functions;

[0016] Embodied Intelligent Agent Swarm: Used to adopt a multi-agent architecture to give each agent the ability to perceive, reason, plan, and learn;

[0017] Integration module: used to integrate subsystems through service bus technology and use change data capture technology to ensure real-time data synchronization;

[0018] Intelligent function module: used to integrate AI and big data technologies to control the central Agent module.

[0019] Preferably, the embodied intelligence layer further includes:

[0020] Data analysis module: used for data analysis based on a distributed computing framework combined with a deep learning library;

[0021] Digital twin module: used to synchronize the real-time data with the physical device layer through the IoT platform;

[0022] Knowledge management module: used to store knowledge graphs using graph databases and implement natural language understanding in combination with pre-trained language models;

[0023] Decision support module: used to make optimized decisions in complex environments.

[0024] Preferably, the physical device layer is integrated with the upper system through the industrial Internet of Things protocol, and uses edge computing methods to process time-sensitive applications.

[0025] Preferably, the physical device layer also includes a sensor network, and the sensor network is used to connect with large-scale IoT devices through a lightweight communication protocol.

[0026] On the other hand, to achieve the above-mentioned purpose, the present invention also provides a method for implementing an embodied intelligent Agent system for industrial scenarios, comprising:

[0027] Input the pending orders, the pending orders are semantically analyzed by the central agent module, the key information of the orders is extracted, and order management, task planning and resource scheduling are performed according to the key information. After the planning of the central agent module is completed, the embodied intelligent agent group is started, and each completes the corresponding task.

[0028] Preferably, order management, task planning and resource scheduling are performed based on the key information, including:

[0029] The central agent module performs semantic analysis to extract key order information, and then performs order analysis, material planning, production planning and task distribution based on the key information;

[0030] The order analysis uses the knowledge graph and graph computing technology in the knowledge management module to perform knowledge reasoning and estimate production time and cost;

[0031] The material planning is based on real-time query of the inventory management system by the digital twin module, triggering the intelligent procurement system when necessary;

[0032] The production planning adopts a multi-objective optimization algorithm through an embodied intelligent agent group, taking into account production efficiency, energy consumption and delivery time factors.

[0033] The task distribution uses a decentralized task allocation mechanism through a decision support module.

[0034] Preferably, the AGV and equipment agent will perform material preparation and production execution after receiving the task, wherein the material preparation and production execution utilize intelligent scheduling algorithms and edge computing technology to achieve near real-time equipment control and parameter adjustment, and also predict possible equipment failures through predictive maintenance models.

[0035] Preferably, in the implementation method, the quality inspection agent and maintenance agent in the embodied intelligent agent group will be executed throughout the entire production process, wherein the quality inspection agent runs through the entire production process, uses detection technology to perform real-time quality detection and analyzes the results. If an abnormality occurs, the exception handling module of the maintenance agent combines case reasoning and rule engine to autonomously handle the abnormal situation and provide decision support when necessary.

[0036] Compared with the prior art, the present invention has the following advantages and technical effects:

[0037] (1) Improve production efficiency: By integrating multiple advanced technologies, such as natural language processing, knowledge graphs, reinforcement learning, edge computing, and computer vision, the embodied intelligent agent system of the present invention can achieve full automation and intelligence of the production process. The system can autonomously perform a series of operations such as order analysis, material planning, production planning, task distribution, material preparation, production execution, quality control, and exception handling, greatly reducing manual intervention and improving production efficiency;

[0038] (2) Improve production quality: The present invention uses advanced detection technology for real-time quality detection, combined with predictive maintenance algorithms, to predict and handle equipment failures in advance, ensuring the stability of the production process and the consistency of product quality. Through real-time monitoring and automatic adjustment of production parameters, the system can continuously optimize the production process and improve product quality;

[0039] (3) Reduce production costs: Through intelligent scheduling and optimization algorithms, the present invention can effectively allocate and utilize resources, reduce material waste and equipment idle time. The AGV scheduling system and intelligent logistics system can optimize material transportation and finished product distribution paths, reducing logistics costs. The application of edge computing technology reduces data transmission delays, improves real-time response capabilities, and further reduces operating costs;

[0040] (4) Enhanced system flexibility: The embodied intelligent agent system adopts a microservice architecture and is highly scalable and flexible. The system can dynamically adjust resource allocation and task planning according to production needs and adapt to production tasks of different scales and complexities. Through federated learning technology, the system can achieve cross-factory knowledge sharing and continuous optimization while protecting data privacy, enhancing the adaptability and flexibility of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1This is a structural diagram of an embodied intelligent Agent system for industrial scenarios according to an embodiment of the present invention;

[0043] Figure 2 The present invention is a flowchart of an implementation method of an embodied intelligent Agent system for industrial scenarios according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0045] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0046] This paper proposes an embodied intelligent agent system for industrial scenarios, such as Figure 1 ,include:

[0047] User interaction layer: used to provide diversified interfaces and communicate with backend services through API gateway;

[0048] Embodied intelligence layer: used to adopt a microservice architecture based on container orchestration to implement task management, task planning, and resource scheduling functions;

[0049] Physical device layer: used to integrate with upper-layer systems through industrial IoT protocols and use edge computing technology to handle time-sensitive applications;

[0050] Among them, the user interaction layer is bidirectionally connected to the embodied intelligence layer, and the embodied intelligence layer is bidirectionally connected to the physical device layer.

[0051] The diverse interfaces in the user interaction layer include:

[0052] An order subsystem interface based on a modern web framework, a cross-platform mobile application interface, a voice interaction subsystem interface with integrated deep learning, and an AR / VR monitoring interface.

[0053] Specifically, the user interaction layer provides a variety of interfaces, including an order system based on a modern Web framework, cross-platform mobile applications, a voice interaction system integrated with deep learning, and an AR / VR monitoring interface. All front-end applications communicate with back-end services through an API gateway to ensure the efficiency and flexibility of data transmission.

[0054] The embodied intelligence layer includes:

[0055] Central Agent module: used for microservice architecture based on container orchestration to realize order management, task planning, resource scheduling, and embodied intelligent Agent group management functions;

[0056] Embodied Intelligent Agent Swarm: Used to adopt a multi-agent architecture to give each agent the ability to perceive, reason, plan, and learn;

[0057] Integration module: used to integrate subsystems through service bus technology and use change data capture technology to ensure real-time data synchronization;

[0058] Intelligent function module: used to integrate AI and big data technologies to control the central Agent module.

[0059] Data analysis module: used for data analysis based on a distributed computing framework combined with a deep learning library;

[0060] Digital twin module: used to synchronize the real-time data with the physical device layer through the IoT platform;

[0061] Knowledge management module: used to store knowledge graphs using graph databases and implement natural language understanding in combination with pre-trained language models;

[0062] Decision support module: used to make optimized decisions in complex environments.

[0063] The embodied intelligence layer is the core layer of the system, including the central agent module, embodied intelligent agent group, integration module, intelligent function module, data analysis module, data twin module, knowledge management module and decision support module.

[0064] The central agent module is a first-level embodied intelligent agent that adopts a microservice architecture based on container orchestration to implement core functions such as order management, task planning, resource scheduling, and embodied intelligent agent group management.

[0065] The embodied intelligent agent group adopts a multi-agent system architecture, and each agent has the ability to perceive, reason, plan and learn. Different types of agents (such as scheduling, equipment, AGV, quality inspection, etc.) use specialized algorithms to complete their respective tasks.

[0066] The integration module uses enterprise service bus technology to seamlessly integrate ERP, MES, WMS and other systems, and adopts change data capture technology to ensure real-time data synchronization.

[0067] The intelligent function module is the brain of the Agent, integrating AI and big data technologies.

[0068] The data analysis module is based on a distributed computing framework and combines deep learning libraries to perform data analysis and implement complex machine learning.

[0069] The digital twin module achieves real-time data synchronization with physical devices through the IoT platform.

[0070] The knowledge management module uses a graph database to store knowledge graphs and combines it with a pre-trained language model to achieve efficient natural language understanding.

[0071] The decision support module is built based on reinforcement learning algorithms and is able to make optimized decisions in complex environments.

[0072] The physical device layer is integrated with the upper-layer system through the Industrial Internet of Things protocol and adopts edge computing methods to handle time-sensitive applications.

[0073] Specifically, the physical device layer is integrated with the upper-layer system through the Industrial Internet of Things protocol, and edge computing technology is used to process time-sensitive applications.

[0074] The physical device layer also includes a sensor network, which is used to connect with large-scale IoT devices through a lightweight communication protocol.

[0075] The workflow of the system is a highly automated and intelligent closed-loop process that integrates advanced artificial intelligence and automation technologies. Therefore, the present invention also provides an implementation method of an embodied intelligent Agent system for industrial scenarios. The technical flow chart is as follows: Figure 2 shown.

[0076] Input the pending orders, and the pending orders are semantically analyzed by the central agent module to extract the key information of the order, and the order management, task planning and resource scheduling are carried out according to the key information. After the planning of the central agent module is completed, the embodied intelligent agent group is started, and each completes the corresponding task.

[0077] Specifically, the process starts with order input. The order information first passes through the central agent module, which uses natural language processing technology to perform semantic analysis on the order, extract key information, and perform upper-level planning such as order management, task planning, and resource scheduling based on the key information. After the central agent plans, the embodied intelligent agent group will be activated and each will complete the corresponding task.

[0078] First, the scheduling agent will perform order analysis, material planning, production planning and task distribution. Order analysis uses the knowledge graph and graph computing technology in the knowledge management module to perform knowledge reasoning and estimate production time and cost; material planning is based on the digital twin module to query the inventory management system in real time and trigger the intelligent procurement system when necessary; production planning uses a multi-objective optimization algorithm through an embodied intelligent agent group, while considering production efficiency, energy consumption and delivery time factors, and task distribution uses a decentralized task allocation mechanism through the decision support module.

[0079] Next, the AGV and equipment agent will prepare materials and execute production after receiving the task. The material preparation and production execution stages use intelligent scheduling algorithms and edge computing technology to achieve near-real-time equipment control and parameter adjustment. The system also integrates a predictive maintenance model that can predict possible equipment failures in advance.

[0080] Once the task is started, the quality inspection agent and maintenance agent in the embodied intelligent agent group will execute throughout the entire production process. Among them, the quality inspection agent runs through the entire production process, using advanced detection technology to perform real-time quality detection and analyze the results. Once an exception occurs, the exception handling module of the maintenance agent will combine case reasoning and rule engines to autonomously handle most of the exceptions and provide decision support when necessary.

[0081] After production is completed, AGV and logistics agent will automatically perform finished product warehousing and logistics delivery tasks. Optimization algorithms are used to arrange goods and plan transportation routes during the finished product warehousing and logistics delivery stages. Distributed ledger technology is used to record logistics information throughout the process to ensure transparency and traceability of the supply chain.

[0082] Finally, both the central agent and the embodied intelligent agent group have their own data analysis and optimization functions. The data analysis and optimization stage adopts a big data architecture, combining batch processing and stream processing technologies. The machine learning module supports model version control and automated deployment. The entire process also integrates an explainable AI module to enhance the credibility and explainability of the system. At the same time, the application of digital twin technology allows the production process to be rehearsed and optimized in a virtual environment, further improving the accuracy of decision-making and the efficiency of production.

[0083] This embodied intelligent system integrates AI, big data, the Internet of Things and automation technologies to achieve full-process intelligence from order to delivery, greatly improving production efficiency and flexibility while maintaining high scalability and security.

[0084] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An embodied intelligent agent system for industrial scenarios, characterized in that: include: User interaction layer: used to provide diversified interfaces and communicate with backend services through API gateway; Embodied intelligence layer: used to adopt a microservice architecture based on container orchestration to implement task management, task planning, and resource scheduling functions; Physical device layer: used to integrate with upper-layer systems through industrial IoT protocols and use edge computing technology to handle time-sensitive applications; The user interaction layer is bidirectionally connected to the embodied intelligence layer, and the embodied intelligence layer is bidirectionally connected to the physical device layer.

2. The embodied intelligent agent system for industrial scenarios according to claim 1 is characterized in that: The diverse interfaces in the user interaction layer include: An order subsystem interface based on a modern web framework, a cross-platform mobile application interface, a voice interaction subsystem interface with integrated deep learning, and an AR / VR monitoring interface.

3. The embodied intelligent agent system for industrial scenarios according to claim 1 is characterized in that: The embodied intelligence layer includes: Central Agent module: used for microservice architecture based on container orchestration to realize order management, task planning, resource scheduling, and embodied intelligent Agent group management functions; Embodied Intelligent Agent Swarm: Used to adopt a multi-agent architecture to give each agent the ability to perceive, reason, plan, and learn; Integration module: used to integrate subsystems through service bus technology and use change data capture technology to ensure real-time data synchronization; Intelligent function module: used to integrate AI and big data technologies to control the central Agent module.

4. The embodied intelligent agent system for industrial scenarios according to claim 3 is characterized in that: The embodied intelligence layer also includes: Data analysis module: used for data analysis based on a distributed computing framework combined with a deep learning library; Digital twin module: used to synchronize the real-time data with the physical device layer through the IoT platform; Knowledge management module: used to store knowledge graphs using graph databases and implement natural language understanding in combination with pre-trained language models; Decision support module: used to make optimized decisions in complex environments.

5. The embodied intelligent agent system for industrial scenarios according to claim 1 is characterized in that: The physical device layer is integrated with the upper-layer system through the Industrial Internet of Things protocol and adopts edge computing methods to process time-sensitive applications.

6. The embodied intelligent agent system for industrial scenarios according to claim 5 is characterized in that: The physical device layer also includes a sensor network, which is used to connect with large-scale IoT devices through a lightweight communication protocol.

7. The method for implementing the embodied intelligent Agent system for industrial scenarios as described in any one of claims 1 to 6 is characterized in that: include: Input the pending orders, the pending orders are semantically analyzed by the central agent module, the key information of the orders is extracted, and order management, task planning and resource scheduling are performed according to the key information. After the planning of the central agent module is completed, the embodied intelligent agent group is started, and each completes the corresponding task.

8. The implementation method according to claim 7, characterized in that: Perform order management, task planning and resource scheduling based on the key information, including: The central agent module performs semantic analysis to extract key order information, and then performs order analysis, material planning, production planning and task distribution based on the key information; The order analysis uses the knowledge graph and graph computing technology in the knowledge management module to perform knowledge reasoning and estimate production time and cost; The material planning is based on real-time query of the inventory management system by the digital twin module, triggering the intelligent procurement system when necessary; The production planning adopts a multi-objective optimization algorithm through an embodied intelligent agent group, taking into account production efficiency, energy consumption and delivery time factors. The task distribution uses a decentralized task allocation mechanism through a decision support module.

9. The implementation method according to claim 7, characterized in that: After receiving the task, the AGV and equipment agent will perform material preparation and production execution. The material preparation and production execution use intelligent scheduling algorithms and edge computing technology to achieve near real-time equipment control and parameter adjustment, and also predict possible equipment failures through predictive maintenance models.

10. The implementation method according to claim 7, characterized in that: In the implementation method, the quality inspection agent and maintenance agent in the embodied intelligent agent group will be executed throughout the entire production process, wherein the quality inspection agent runs through the entire production process, uses detection technology to perform real-time quality detection and analyzes the results. If an abnormality occurs, the exception handling module of the maintenance agent combines case reasoning and rule engine to autonomously handle the abnormal situation and provide decision support when necessary.

Images