MAS management platform

Abstract

The invention provides an MAS management platform, and relates to the technical field of informatization management. The platform comprises a data integration layer, a business management layer, an organization management layer, an AI technology layer and a talent support layer, the data integration layer collects and uniformly manages data from various systems, and the business management layer carries out business management and process control on equipment operation, a technological process, production efficiency and energy consumption based on the data provided by the data integration layer. The organization management layer carries out distribution, cooperation and performance feedback on employee tasks based on all businesses of the business management layer, and the AI technology layer carries out intelligent analysis on data of the data integration layer, generates a business optimization instruction and provides the business optimization instruction for the business management layer. And the talent support layer generates a personalized learning path, an ability portrait and an incentive strategy based on the performance data and learning data of the organization management layer, and feeds back a learning result and a performance result to the organization management layer. According to the invention, intelligentization of enterprise production and operation is realized.

Description

Technical Field

[0001] This invention relates to the field of information management technology, and more specifically, to an MAS management platform. Background Technology

[0002] In the process of digital transformation, manufacturing enterprises typically rely on a variety of independent information systems such as ERP (Enterprise Resource Planning), MES (Manufacturing Execution System), EAM (Equipment Asset Management System), and SCADA (Supervisory and Data Acquisition System) to manage production, equipment, and processes.

[0003] While existing management systems have improved the level of information technology in enterprise production to some extent, they still have significant limitations. For example, data interfaces between systems are not unified, information silos are severe, and it is difficult to achieve integrated analysis of multi-dimensional data such as equipment, processes, energy consumption, and personnel. For instance, equipment operating status and process parameters often rely on manual monitoring and statistics, making real-time diagnosis and predictive maintenance impossible. Furthermore, process optimization lacks dynamic modeling support, limiting the improvement of production efficiency. At the same time, enterprise organizational management is still mainly based on manual assignment and hierarchical reporting, task collaboration and performance evaluation lack intelligent tools, and employee growth and skills training mechanisms are fragmented, failing to form a digital closed-loop management system. Summary of the Invention

[0004] The problem addressed by this invention is how to achieve intelligent production and operation in enterprises.

[0005] To address the aforementioned issues, this invention provides a Management System (MAS) platform, comprising a data integration layer, a business management layer, an organizational management layer, an AI technology layer, and a talent support layer. The data integration layer collects and manages data from various systems in a unified manner. The business management layer manages and controls equipment operation, processes, production efficiency, and energy consumption based on the data provided by the data integration layer. The organizational management layer allocates, coordinates, and provides performance feedback to employees based on the various business functions of the business management layer. The AI ​​technology layer intelligently analyzes the data from the data integration layer, generates business optimization instructions, and provides them to the business management layer to support business management upgrades. The talent support layer generates personalized learning paths, competency profiles, and incentive strategies based on the performance and learning data of the organizational management layer, and feeds back learning outcomes and performance results to the organizational management layer to support organizational management upgrades.

[0006] Optionally, the business management layer includes an equipment management system, a process management system, an efficiency management system, and an energy management system. The business management layer operates based on a multi-dimensional linkage mechanism. The equipment management system, the process management system, the efficiency management system, and the energy management system are used to respectively realize equipment health maintenance, process parameter optimization, efficiency improvement, and energy conservation management under the multi-dimensional linkage mechanism.

[0007] Optionally, the device management system is used to collect device operation data through IoT, and to call the AI ​​technology layer to analyze fault data in the device operation data, and to generate the best maintenance guidance plan based on the analysis results.

[0008] Optionally, the process management system is used to collect production process parameters through IoT, analyze process trends based on the production process parameters, trigger process anomaly alarms when the production process parameters are abnormally out of tolerance, and call the AI ​​technology layer to analyze the optimal process standard.

[0009] Optionally, the efficiency management system is used to monitor production line data in real time via IoT, and to identify production bottlenecks and efficiency deviations based on the production line data to generate efficiency improvement tasks.

[0010] Optionally, the energy management system is used to perform hierarchical monitoring and analysis of energy consumption data, and to call the AI ​​technology layer to generate energy-saving tasks based on the analysis results and send them to the corresponding level for execution.

[0011] Optionally, the business management layer operates based on a three-dimensional linkage mechanism of model-driven, data-driven, and process-driven approaches.

[0012] Optionally, the organizational management layer includes a digital organization module, a continuous improvement module, a task management module, and a daily management module; The digital organization module is used to build a virtualized organizational collaboration system based on artificial intelligence technology, and realizes organizational structure digitization, knowledge sharing and skills transfer through work assistants, domain experts and trained digital humans; The continuous improvement module is used to analyze organizational operational data and business performance, automatically identify improvement opportunities, generate improvement tasks, and evaluate improvement results; The task management module is used to establish a unified mechanism for task generation, allocation and supervision. It automatically creates tasks when abnormal events or business needs are triggered, and performs task flow and process monitoring according to job permissions and execution status to achieve collaborative task management. The daily management module is used to uniformly plan and execute individual work plans, collaborative plans, and standardized operations, supporting the digital management of employee self-management, team collaboration, and organizational routine work.

[0013] Optionally, the AI ​​technology layer includes an intelligent support system composed of artificial intelligence algorithms, virtual simulation, and data processing technologies.

[0014] Optionally, the talent support layer includes a multi-role collaborative system corresponding to the intelligent support system of the AI ​​technology layer.

[0015] The beneficial effects of the MAS management platform of this invention are as follows: By establishing a MAS management platform that includes a data integration layer, a business management layer, an organizational management layer, an AI technology layer, and a talent support layer, a closed-loop system is formed from data collection, business operation, organizational management to intelligent decision-making and talent development. This effectively solves the problems of data silos, business fragmentation, and decision-making lag in existing manufacturing systems, realizes centralized data management and multi-level collaboration, promotes the integrated intelligent upgrade of manufacturing enterprises in production, management, and talent training, and ultimately realizes intelligent production and operation of enterprises. Attached Figure Description

[0016] Figure 1 This is a schematic diagram illustrating the composition of the MAS management platform according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the architecture of the MAS management platform according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the device management system architecture according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the architecture of the process management system according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the architecture of the efficiency management system according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the energy management system architecture according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the architecture of the personnel self-driving platform according to an embodiment of the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0018] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0019] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to"; the term "based on" means "at least partially based on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; and the term "optionally" means "optional embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first," "second," etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0020] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0021] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0022] like Figure 1 As shown in the figure, an MAS management platform provided by this invention includes a data integration layer, a business management layer, an organizational management layer, an AI technology layer, and a talent support layer. The data integration layer is used to collect and manage data from various systems in a unified manner. The business management layer is used to perform business management and process control on equipment operation, process flow, production efficiency, and energy consumption based on the data provided by the data integration layer. The organizational management layer is used to allocate, coordinate, and provide performance feedback for employee tasks based on the various business functions of the business management layer. The AI ​​technology layer is used to perform intelligent analysis on the data of the data integration layer, generate business optimization instructions, and provide them to the business management layer to support business management upgrades. The talent support layer is used to generate personalized learning paths, competency profiles, and incentive strategies based on the performance and learning data of the organizational management layer, and feed back the learning outcomes and performance results to the organizational management layer to support organizational management upgrades.

[0023] Specifically, the MAS management platform includes a data integration layer, a business management layer, an organizational management layer, an AI technology layer, and a talent support layer, combined with... Figure 2As shown, the data integration layer, acting as the data hub, is the platform's data center, used to integrate multi-source data from both internal and external sources. It provides the business management layer with "complete and real-time" business decision-making data and the AI ​​technology layer with "raw and multi-dimensional" data materials, supporting AI model training and intelligent analysis. For example, it can collect and aggregate multi-source data from internal enterprise systems such as ERP, MES, equipment control systems, energy monitoring systems, and human resource systems, and achieve centralized data management through unified data standards and interfaces. The business management layer, as the business value embodiment layer, is the direct operational layer of the platform's core business. It relies on multi-dimensional support to carry out its work, using the "integrated and multi-source data" provided by the data integration layer as the basis for decision-making. It leverages the intelligent algorithms of the AI ​​technology layer to optimize business logic, implementing its solutions within the organizational management structure and rules. The planning, execution, and monitoring of specific business operations can be achieved through comprehensive management and process control of equipment operation, technological processes, production efficiency, and energy consumption, based on data provided by the data integration layer, thus realizing the digitalization and visualization of the production process. The organizational management layer, acting as the organizational support layer, relies on the management talent of the talent support layer to build the platform's organizational structure, formulate departmental collaboration rules and role-based access control systems. For example, based on business tasks generated by the business management layer, it can automatically allocate, collaboratively execute, and provide performance feedback for employee tasks, establishing a closed-loop task system for organizational operation. It can also provide organizational mechanism guarantees for the business management layer, ensuring that business processes operate efficiently under the norms of "departmental division of labor, role responsibilities, and collaborative processes." The AI ​​technology layer, as the core technology foundation, relies on the technical talent of the talent support layer to provide intelligent technology empowerment to the upper layers (business, data, etc.). For example, it can intelligently analyze and model the data collected by the data integration layer, generate business optimization instructions, and feed them back to the business management layer, achieving process parameter optimization, predictive equipment maintenance, and improved production efficiency. It can also provide the data integration layer with algorithmic tools for data cleaning, feature extraction, and intelligent analysis, and provide the business management layer with technical capabilities for intelligent decision-making, process automation, and predictive analysis (such as anomaly warning models).The talent support layer, serving as the foundational guarantee layer and the talent supply base of the MAS management platform, provides core capability support for other layers. For example, it can generate personalized learning paths, competency profiles, and incentive strategies based on the performance and learning data of the organization's management team. This allows for the feedback of learning outcomes and performance results to the management team, achieving a two-way optimization of employee growth and organizational performance. Furthermore, it can support AI... The technology layer provides professional technical talent for AI algorithm development and model optimization; it also provides management talent for organizational management (management architecture design and team collaboration); and it provides business management talent for business process operation and scenario implementation. In other words, the talent support layer empowers the AI ​​technology layer and organizational management; the data integration layer provides data to the business management and AI technology layers; the organizational management layer sets rules for the business management layer; and the AI ​​technology layer empowers the business management and data integration layers. All layers collaborate to support the overall operation of the MAS management platform. Through this five-layer collaborative architecture, it breaks through the limitations of focusing on a single business or technology, forming a cross-dimensional management closed loop. This achieves intelligent management across the entire chain, from data collection and business operation to organizational management and talent development, forming a closed-loop system that integrates data-driven and human-machine collaboration, realizing closed-loop linkage between "data-technology-organization-business-talent".

[0024] This embodiment can be broken down layer by layer into BU-level operational indicators, factory-level operational indicators, class / workshop-level process indicators, and production line-level process indicators, based on operational management needs. It enables self-driven personnel management, equipment management, process management, efficiency management, and energy management based on on-site execution indicators, supporting operational process management with a business operation process as the guide. When employees log in to the operational indicator management interface, they can access the corresponding management interface according to their employee level. For example, BU-level employees can access the BU-level performance (operations) or BU-level performance (finance) interfaces, while factory-level employees can access the operations, finance, organization, and safety sections. In self-driven personnel management, key processes can be managed through personnel task allocation and tracking. Real-time transparency in process management and performance empowers learning and creates an intelligent self-driving assistant; in equipment management, real-time data collection, data analysis, and fault diagnosis and prediction via IoT enable full lifecycle management of equipment and improve equipment utilization; in process management, it accurately senses and controls process variation factors, recommends optimal process parameters through models, and improves process level; in efficiency management, it uses IoT combined with IE action analysis to accurately locate efficiency improvement points, intelligently drives and tracks efficiency improvement tasks, and continuously manages the PDCA efficiency improvement cycle; in energy management, it enables energy data visualization, multi-dimensional energy efficiency analysis, and energy-saving optimization combined with AI models, significantly reducing energy costs.

[0025] In this embodiment, edge node preprocessing equipment and process data (such as screening key fault characteristics and cleaning process anomalies) can be deployed on the production line. A lightweight data bus enables extremely simple data flow, synchronizing only core business data to the management platform, reducing data integration complexity and meeting the basic business-data linkage requirements.

[0026] In this embodiment, by establishing a MAS management platform that includes a data integration layer, a business management layer, an organizational management layer, an AI technology layer, and a talent support layer, a closed-loop system is formed, encompassing data collection, business operation, organizational management, intelligent decision-making, and talent development. This effectively solves the problems of data silos, business fragmentation, and delayed decision-making in existing manufacturing systems, achieving centralized data management and multi-level collaboration. It promotes the integrated intelligent upgrade of manufacturing enterprises in production, management, and talent development, thereby realizing intelligent production and operation of enterprises.

[0027] Optionally, the business management layer includes an equipment management system, a process management system, an efficiency management system, and an energy management system. The business management layer operates based on a multi-dimensional linkage mechanism. The equipment management system, the process management system, the efficiency management system, and the energy management system are used to respectively realize equipment health maintenance, process parameter optimization, efficiency improvement, and energy conservation management under the multi-dimensional linkage mechanism.

[0028] Specifically, in combination Figure 2 As shown, the business management layer includes an equipment management system, a process management system, an efficiency management system, and an energy management system. These systems operate collaboratively under the same platform architecture and achieve data sharing and optimized linkage through a multi-dimensional linkage mechanism. The equipment management system is used to monitor the health of equipment and perform predictive maintenance; the process management system is used to optimize process parameters and control anomalies in the production process; the efficiency management system is used to perform real-time analysis and continuous improvement of production efficiency; and the energy management system is used to perform graded monitoring and energy-saving optimization of energy consumption. Data between the four systems can be exchanged in real time. For example, process fluctuation data can be transmitted to the equipment system to determine the source of failure, and equipment energy consumption data can be fed back to the energy system for energy efficiency analysis, realizing cross-system business linkage and collaborative decision-making.

[0029] In this optional embodiment, by setting up an equipment management system, a process management system, an efficiency management system, and an energy management system in the business management layer, and introducing a multi-dimensional linkage driving mechanism, collaborative management of equipment operation, process control, production efficiency, and energy utilization is realized. This makes data exchange and optimized linkage between various business systems possible, improves the systematization and transparency of the manufacturing process, and significantly enhances the enterprise's lean production and real-time response capabilities in the production process.

[0030] Optionally, the device management system is used to collect device operation data through IoT, and to call the AI ​​technology layer to analyze fault data in the device operation data, and to generate the best maintenance guidance plan based on the analysis results.

[0031] Specifically, in combination Figure 3 As shown, the equipment management system collects equipment operation data through IoT, such as vibration, temperature, current, voltage, and alarm signals. It then calls upon the AI ​​technology layer to analyze fault data within the equipment operation data, such as feature extraction and anomaly identification. When a fault mode is detected, diagnostic results and fault type labels are generated. Based on the analysis results, the system can generate the best maintenance guidance plan and push it to the maintenance personnel's terminal or system interface, thus achieving predictive maintenance of the equipment. In other words, IoT enables the equipment to have autonomous perception capabilities, automatically call for repairs and analyze faults, and provides the best fault repair guidance through AI Agent. Intelligent equipment diagnosis can reduce equipment downtime and thus improve overall production efficiency.

[0032] In this optional embodiment, the equipment management system collects equipment operation data through the Internet of Things and calls the AI ​​technology layer for intelligent diagnosis, which can automatically identify fault types and generate the best maintenance guidance plan. This solution enables the equipment to have autonomous perception and predictive maintenance capabilities, reduces manual inspection and downtime, improves equipment uptime and maintenance efficiency, thereby enhancing overall production stability and equipment utilization.

[0033] Optionally, the process management system is used to collect production process parameters through IoT, analyze process trends based on the production process parameters, trigger process anomaly alarms when the production process parameters are abnormally out of tolerance, and call the AI ​​technology layer to analyze the optimal process standard.

[0034] Specifically, in combination Figure 4 As shown, the process management system collects production process parameters through IoT, such as temperature, pressure, ratio, flow rate, and time. Based on these parameters, it analyzes process trends. When a production process parameter deviates from its set range (e.g., a parameter exceeds the set range), a process anomaly alarm is triggered. It can also utilize AI technology to analyze optimal process standards. For example, it uses a deep learning model to analyze historical process data and quality inspection results, generating optimal process standards and parameter adjustment schemes. In short, by collecting production process parameters in real time via IoT, analyzing big data on process trends, automatically triggering alerts for process anomalies, analyzing optimal process standards using AI models, and intelligently linking personnel or equipment for parameter adjustment tasks, a closed loop is formed, improving efficiency and process quality. Precise process optimization can effectively reduce the defect rate, thereby improving overall production efficiency.

[0035] In this optional embodiment, the process management system collects process parameters in real time through the Internet of Things (IoT) and uses AI technology to analyze process trends and calculate optimal process standards, achieving dynamic monitoring and intelligent optimization of the process. When process parameters deviate, the system can automatically issue an alarm and provide parameter adjustment suggestions, thereby effectively avoiding product quality fluctuations and improving process control accuracy and yield.

[0036] Optionally, the efficiency management system is used to monitor production line data in real time via IoT, and to identify production bottlenecks and efficiency deviations based on the production line data to generate efficiency improvement tasks.

[0037] Specifically, in combination Figure 5 As shown, the efficiency management system monitors production line data in real time through IoT, such as equipment utilization rate, output, yield rate, and downtime. Based on the production line data, it identifies production bottlenecks and efficiency deviations to generate efficiency improvement tasks. For example, IoT enables real-time online monitoring of "production line OEE (Overall Equipment Efficiency), time utilization, performance efficiency, yield rate, and equipment downtime distribution and trends." A large amount of real, raw data from the field supports precise positioning of efficiency improvement, and intelligent driving and tracking of specific efficiency improvement tasks.

[0038] In this optional embodiment, the efficiency management system utilizes the Internet of Things to monitor production line data in real time, identifies production bottlenecks and efficiency deviations through data analysis, and generates efficiency improvement tasks accordingly. This system achieves closed-loop management from data collection to problem identification and task execution, ensuring data-driven and continuous improvement in production efficiency, thereby enabling refined management and performance optimization of the production line.

[0039] Optionally, the energy management system is used to perform hierarchical monitoring and analysis of energy consumption data, and to call the AI ​​technology layer to generate energy-saving tasks based on the analysis results and send them to the corresponding level for execution.

[0040] Specifically, in combination Figure 6 As shown, the energy management system performs hierarchical monitoring and analysis of energy consumption data. It calls upon the AI ​​technology layer to generate energy-saving tasks based on the analysis results and distributes them to the corresponding levels for execution. For example, L1-group level management, L2-factory level management, L3-workshop level management, L4-line level management, and L5-unit level management deploy energy consumption acquisition nodes to collect real-time data on the use of energy media such as electricity, water, gas, and heat. After analysis by the AI ​​technology layer, energy-saving tasks are generated and distributed to the corresponding execution units according to the hierarchical structure. The execution units adjust the operation strategies or start / stop periods of production equipment according to the energy-saving tasks and feed back the energy consumption changes to the system. Through the hierarchical energy management mechanism, refined control and intelligent optimization of energy are achieved.

[0041] In this optional embodiment, the energy management system achieves intelligent optimization and hierarchical control of energy use by hierarchically monitoring and analyzing energy consumption data, and by calling the AI ​​technology layer to generate energy-saving tasks and sending them to the corresponding levels for execution. It can grasp the distribution and trend of energy consumption in real time, accurately locate high-energy-consuming links, thereby improving energy utilization efficiency and supporting the achievement of the enterprise's green manufacturing and carbon emission reduction goals.

[0042] Optionally, the business management layer operates based on a three-dimensional linkage mechanism of model-driven, data-driven, and process-driven approaches.

[0043] Specifically, the business management layer operates based on a three-dimensional linkage mechanism of model-driven, data-driven, and process-driven approaches. Model-driven approaches encapsulate business rules, data structures, and interaction logic into reusable models, which directly drive system functions (relying on predefined business / data / rule models), ultimately reducing repetitive coding. Data-driven approaches collect and analyze data, allowing it to directly trigger system operations or assist human decision-making (relying on multi-dimensional data sources, data processing, and analysis capabilities), with the core objective of eliminating reliance on fixed processes or human judgment. Process-driven approaches break down business operations into combinations of "ordered steps + role permissions + flow rules," allowing the system to advance work according to process nodes (relying on standardized flowcharts and node flow rules), with the core objective of ensuring the standardization and traceability of business execution. Unlike existing single-drive models, this embodiment, through a three-dimensional linkage mechanism, enables the business management layer to possess real-time perception, intelligent judgment, and autonomous execution capabilities, forming a dynamic operating mode of self-learning and continuous optimization, thereby achieving intelligent coverage of the entire business domain, from diagnosis to optimization, including equipment and processes.

[0044] In this optional embodiment, a three-dimensional linkage mechanism of model-driven, data-driven, and process-driven approaches is introduced into the business management layer, forming a dynamic closed loop of "perception-analysis-execution-feedback". This realizes an automated link from data collection to decision execution, enabling the system to learn and optimize itself based on real-time data and model predictions, thereby improving the intelligence level and dynamic response capability of business management.

[0045] Optionally, the organizational management layer includes a digital organization module, a continuous improvement module, a task management module, and a daily management module; The digital organization module is used to build a virtualized organizational collaboration system based on artificial intelligence technology, and realizes organizational structure digitization, knowledge sharing and skills transfer through work assistants, domain experts and trained digital humans; The continuous improvement module is used to analyze organizational operational data and business performance, automatically identify improvement opportunities, generate improvement tasks, and evaluate improvement results; The task management module is used to establish a unified mechanism for task generation, allocation and supervision. It automatically creates tasks when abnormal events or business needs are triggered, and performs task flow and process monitoring according to job permissions and execution status to achieve collaborative task management. The daily management module is used to uniformly plan and execute individual work plans, collaborative plans, and standardized operations, supporting the digital management of employee self-management, team collaboration, and organizational routine work.

[0046] Specifically, the organizational management layer includes a digital organization module, a continuous improvement module, a task management module, and a daily management module. The digital organization module builds a virtualized organizational collaboration system based on artificial intelligence technology, enabling knowledge sharing and skills transfer through work assistants, domain experts, and trained digital androids. The continuous improvement module analyzes organizational operational data and performance results, automatically identifies improvement opportunities and generates improvement tasks, and then conducts performance evaluation and experience accumulation based on the execution results. The task management module establishes a unified mechanism for task generation, allocation, and supervision. When the system detects abnormal events or business needs, it automatically creates tasks and allocates them according to job permissions, and tracks the process. The daily management module supports employee self-planning, team collaboration, and the management of standardized operating procedures, achieving the standardization and self-driving of organizational operations. Through the collaboration of these modules, the organizational management layer achieves digital closed-loop management from task allocation to improvement feedback, promoting organizational efficiency and innovation capabilities.

[0047] Among them, combined Figure 7 As shown, the employee self-driven platform achieves comprehensive employee self-driven management through a timed task-driven system, a real-time comprehensive digital performance system, an intelligent anomaly linkage management system, and an empowering learning and growth system. When employees log in to the employee self-driven platform, the corresponding management interface is displayed on the mobile terminal according to the employee's level. The management interface includes entry points to different functional interfaces. Exemplary functional interface entry points include virtual buttons such as My Performance (corresponding to the performance function interface), My Activities (corresponding to the activity function interface), My Growth (corresponding to the growth function interface), and My Team (involving team organizational charts and personnel performance role assignments, etc.). At the same time, the management interface also provides an entry point for standard document query functions, which are used to provide standard operating instructions (SOPs), quality inspection standards (SIPs), process inspection sheets, equipment operation standards, etc.

[0048] For example, after an employee clicks "My Performance," they enter the performance function interface. This interface displays corresponding performance indicators and performance evaluation dimensions (such as scoring indicators, non-scoring indicators, and deduction indicators) on the mobile device, based on the employee's level. Examples of scoring indicators include pass rate, non-scoring indicators include training rate, and deduction indicators include the number of times late. Based on production and task-related data, scores can be calculated for employee-completed tasks according to performance evaluation dimensions. Performance data analysis can be performed based on performance indicators and scoring results (such as daily, monthly, and yearly performance data analysis). Furthermore, outstanding employees can be recognized (e.g., through a wall of honor).

[0049] For example, after an employee clicks "My Activities," they enter the activity function interface, which retrieves and displays the employee's daily activity trajectory map. Based on the timestamp and location or device usage records (such as device clock-in records, operation logs, etc.) of the daily activity trajectory map, corresponding attendance data is generated. For example, if there is no login record within 10 minutes after the start of the shift, it is marked as late; if the number of logins is 0 and there is no leave record, it is marked as absent; if the operation is performed in a different location and there is a business trip approval, it is marked as a business trip.

[0050] For example, after an employee clicks "My Growth," they enter the growth function interface. In this interface, employees can independently select learning content based on their permissions, supervisors can assign learning tasks, and the system can also push learning tasks based on performance, allocating learning resources in conjunction with performance and task assignments. The growth function interface provides skill level certification and personal skill resume management. It updates employees' skill resumes and production line qualifications based on their completion of learning resources. For instance, if an employee clicks on a learning resource and completes the course, the completion status is evaluated, the employee's skill level is updated, and a new production line qualification entry is added.

[0051] For example, after an employee clicks on "Process Monitoring" and "Daily Production Plan", they will enter the production function interface. On the production function interface, employees can view the process operation status in real time (such as process parameters, temperature, speed, yield, etc.) and the daily production plan (such as work order number, target output, priority), and can report equipment abnormalities. It also supports work handover between shifts.

[0052] In this optional embodiment, the organizational management layer includes a digital organization module, a continuous improvement module, a task management module, and a daily management module, which can realize digital and intelligent management from knowledge collaboration and task allocation to organizational improvement, enabling systematic linkage of employee work processes, task execution, and performance feedback, promoting organizational self-drive and continuous optimization, thereby enhancing organizational operational efficiency and innovation capabilities.

[0053] Optionally, the AI ​​technology layer includes an intelligent support system composed of artificial intelligence algorithms, virtual simulation, and data processing technologies.

[0054] Specifically, the AI ​​technology layer comprises an intelligent support system consisting of artificial intelligence algorithms, virtual simulation, and data processing technologies. Based on technologies such as the industrial metaverse, digital twins, AI agents, deep learning, machine learning, and big data analytics, this system models, analyzes, and predicts multi-source data from the data integration layer. It can generate equipment health scores, process optimization strategies, efficiency improvement suggestions, and energy-saving solutions, and output the results to the business management layer for execution. The AI ​​technology layer can achieve visualized simulation of the production process through augmented reality / virtual reality (AR / VR) technology, and generate knowledge documents and training content through generative artificial intelligence (AIGC) technology, achieving automated knowledge accumulation. Through this layer's design, the system possesses cross-domain intelligent analysis and self-learning capabilities, providing unified intelligent decision support for the business and organizational layers. In this embodiment, virtual scenes can be constructed through industrial metaverse and digital twins, and combined with AI Agent to realize the intelligent closed loop of "virtual-real mapping-simulation-decision". Alternatively, virtual scenes can be constructed through augmented reality (AR) and physical information system (CPS). AR enables the visualization of virtual and real equipment and production lines, while CPS collects physical equipment data in real time and builds a dynamic mapping model to complete equipment status monitoring and process simulation analysis, thus meeting the needs of virtual scene-assisted management.

[0055] In this optional embodiment, the AI ​​technology layer constructs an intelligent support system composed of artificial intelligence algorithms, virtual simulation, and data processing technologies, used for analyzing, modeling, and predicting multi-source business data. This layer provides a unified intelligent decision-making engine for business and organizational management, enabling process optimization, equipment diagnosis, and process automation, significantly improving the system's intelligent computing capabilities and decision-making accuracy, and providing technical support for the platform's self-learning and visualized operation.

[0056] Optionally, the talent support layer includes a multi-role collaborative system corresponding to the intelligent support system of the AI ​​technology layer.

[0057] Specifically, the talent support layer includes a multi-role collaborative system corresponding to the AI ​​technology layer's intelligent support system. This layer includes roles such as metaverse builders, digital twin builders, intelligent agent developers, algorithm model developers, process designers, big data analysts, and IoT experts, which support system model development and functional innovation. The talent support layer also includes a learning and growth platform, a continuous improvement platform, and a task management platform. The learning and growth platform pushes personalized learning paths and generates competency profiles based on employee performance and job requirements; the continuous improvement platform summarizes organizational and individual improvement results to achieve knowledge accumulation and reuse; and the task management platform provides task tracking and performance statistics to achieve performance linkage between individuals and teams. Through the dual support of technology and talent, an intelligent ecosystem of human-machine collaboration, autonomous learning, and continuous innovation is formed.

[0058] In this optional embodiment, the talent support layer constructs a multi-role collaborative system corresponding to the intelligent support system of the AI ​​technology layer. Through the learning and growth platform, the continuous improvement platform, and the task management platform, it provides employees with support for knowledge learning, skills enhancement, and performance improvement, realizing the intelligent linkage between talent growth and organizational development. This enables the platform to have a self-driven mechanism for knowledge accumulation, capability accumulation, and continuous innovation, supporting the long-term evolution and intelligent upgrading of the manufacturing organization.

[0059] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A MAS management platform, characterized in that, It comprises a data integration layer, a business management layer, an organizational management layer, an AI technology layer, and a talent support layer. The data integration layer is used to collect and manage data from various systems in a unified manner. The business management layer is used to manage and control equipment operation, processes, production efficiency, and energy consumption based on the data provided by the data integration layer. The organizational management layer is used to allocate, coordinate, and provide performance feedback to employees based on the various business functions of the business management layer. The AI ​​technology layer is used to intelligently analyze the data from the data integration layer, generate business optimization instructions, and provide them to the business management layer to support business management upgrades. The talent support layer is used to generate personalized learning paths, competency profiles, and incentive strategies based on the performance and learning data of the organizational management layer, and to feed back learning outcomes and performance results to the organizational management layer to support organizational management upgrades.

2. The MAS management platform according to claim 1, characterized in that, The business management layer includes an equipment management system, a process management system, an efficiency management system, and an energy management system. The business management layer operates based on a multi-dimensional linkage mechanism. The equipment management system, the process management system, the efficiency management system, and the energy management system are used to realize equipment health maintenance, process parameter optimization, efficiency improvement, and energy conservation management respectively under the multi-dimensional linkage mechanism.

3. The MAS management platform according to claim 2, characterized in that, The equipment management system is used to collect equipment operation data through IoT, and to call the AI ​​technology layer to analyze fault data in the equipment operation data, and to generate the best maintenance guidance plan based on the analysis results.

4. The MAS management platform according to claim 2, characterized in that, The process management system is used to collect production process parameters through IoT, analyze process trends based on the production process parameters, trigger process anomaly alarms when the production process parameters are abnormally out of tolerance, and call the AI ​​technology layer to analyze the optimal process standard.

5. The MAS management platform according to claim 2, characterized in that, The efficiency management system is used to monitor production line data in real time via IoT, and to identify production bottlenecks and efficiency deviations based on the production line data in order to generate efficiency improvement tasks.

6. The MAS management platform according to claim 2, characterized in that, The energy management system is used to perform hierarchical monitoring and analysis of energy consumption data, and to call the AI ​​technology layer to generate energy-saving tasks based on the analysis results and send them to the corresponding level for execution.

7. The MAS management platform according to any one of claims 2 to 6, characterized in that, The business management layer operates based on a three-dimensional linkage mechanism driven by models, data, and processes.

8. The MAS management platform according to claim 1, characterized in that, The organizational management layer includes a digital organization module, a continuous improvement module, a task management module, and a daily management module; The digital organization module is used to build a virtualized organizational collaboration system based on artificial intelligence technology, and realizes organizational structure digitization, knowledge sharing and skills transfer through work assistants, domain experts and trained digital humans; The continuous improvement module is used to analyze organizational operational data and business performance, automatically identify improvement opportunities, generate improvement tasks, and evaluate improvement results; The task management module is used to establish a unified mechanism for task generation, allocation and supervision. It automatically creates tasks when abnormal events or business needs are triggered, and performs task flow and process monitoring according to job permissions and execution status to achieve collaborative task management. The daily management module is used to uniformly plan and execute individual work plans, collaborative plans, and standardized operations, supporting the digital management of employee self-management, team collaboration, and organizational routine work.

9. The MAS management platform according to claim 1, characterized in that, The AI ​​technology layer includes an intelligent support system composed of artificial intelligence algorithms, virtual simulation, and data processing technologies.

10. The MAS management platform according to claim 9, characterized in that, The talent support layer includes a multi-role collaborative system corresponding to the intelligent support system of the AI ​​technology layer.

Images