Digital twinborn AI intelligent agent-based middle table rapid application development method, system and device, and storage medium

Abstract

The invention discloses a digital twin AI agent-based intermediate station rapid application development method, system and device, and a storage medium, and relates to the technical field of application development and operation and maintenance management, and the method comprises the steps: analyzing a static data format and an interaction demand according to a business scene, and constructing a static data format standard and a static data transmission rule based on an intermediate station; based on a static data format standard and a static data transmission rule, decomposing a service demand, and establishing a service processing flow; and business link operation data is acquired based on the business processing flow, the AI analysis model is accessed to a middle station, modeling and reasoning are performed on the business link operation data, and dynamic monitoring is performed on the business processing flow. According to the method, by constructing the static data format standard and the transmission rule, unified access and standard processing of multi-source heterogeneous data are achieved; modeling and reasoning are carried out on the operation data by accessing the AI analysis model, dynamic monitoring and anomaly recognition of the service process are achieved, and the operation controllability and the intelligent decision-making level are improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of application development and operation and maintenance management, and particularly relates to a middle platform rapid application development method, system and device based on digital twin AI intelligent agent and a storage medium. BACKGROUND

[0002] With the continuous improvement of enterprise informatization level, the demand for digital infrastructure for efficient business collaboration and resource sharing is increasing. Especially in the complex environment of parallel operation of multiple business systems and serious data island, the traditional monolithic architecture or loose integration development mode has been difficult to support dynamic and changing business needs. Under this background, the enterprise middle platform architecture with the core concept of "shared ability and unified governance" gradually emerges. The essence of the middle platform technology is to platformize the general capabilities of the enterprise, and to support the diversified and rapid iteration of the front-end business needs by centrally managing and reusing the back-end resource capabilities. With the increasing demand for flexible deployment and efficient response capability in typical scenarios such as industrial internet and smart city, the role of the middle platform as a "decentralized capability center" is gradually established. At the same time, with the penetration of AI technology in various industries, data-driven business intelligent decision-making has become the mainstream trend, and the traditional development logic centered on process orientation has gradually shifted to a new business building paradigm driven by data elements and intelligent models.

[0003] Currently, in the typical middle platform construction and application development practice, although the reuse and flexible combination of capabilities are emphasized, there are still many technical bottlenecks in actual application. In the early stage of business system integration, due to the lack of unified data format standards, it often leads to incompatible data structures and non-uniform semantics between different business systems, thereby causing complex interface connection, low data parsing efficiency and other problems; the predefinition of static data format is often limited to a small number of scenarios, and it is difficult to adapt to the diversified and dynamic business needs in the industry. The current mainstream middle platform development process relies on manual configuration of processes and logic rules, and the processing logic is often expressed in the form of flowcharts or conditional trees, lacking the ability of automatic combination and structure optimization based on standardized data flow, which easily causes processing node redundancy, repeated execution path, unclear logic flow, and other phenomena. Although some platforms have begun to introduce running monitoring mechanisms to assist operation and maintenance, most of them still remain at the stage of index collection and display, lacking deep data modeling and business behavior insight, and being difficult to support dynamic adjustment and intelligent optimization needs. Especially during the running process, the execution state of the processing flow, node performance, data anomalies and the like often cannot form a closed-loop feedback, resulting in insufficient system running reliability and decision adaptability. SUMMARY

[0004] In view of the above problems, the present application is proposed.

[0005] Therefore, the technical problem solved by the present application is that the existing technology has the problems of non-uniform static data format standard, low transmission rule configuration efficiency, and lack of dynamic adaptability of business process, and how to realize static data format driven process construction and multi-dimensional operation monitoring based on business scenarios.

[0006] To solve the above technical problems, the present application provides the following technical solutions: A middle platform rapid application development method based on digital twin AI agent, including analyzing static data format and interaction requirements according to business scenarios, constructing static data format standard and static data transmission rules based on the middle platform; decomposing business requirements based on the static data format standard and the static data transmission rules, and establishing a business process; collecting business link operation data based on the business process, connecting an AI analysis model to the middle platform, modeling and reasoning the business link operation data, and dynamically monitoring the business process; establishing the business process includes arranging the execution order of the processing logic and the parameter dependency path, matching the static data transmission path between the input fields and the output fields of the processing logic, and configuring the execution jump relationship and the trigger strategy between the processing logics; dynamically monitoring the business process includes inputting the standardized operation data into the AI analysis model connected to the middle platform, extracting multi-dimensional feature data based on the AI analysis model, analyzing the operation behavior of the business process, performing trend modeling and stability judgment, identifying abnormal nodes and mapping them to the business process.

[0007] As a preferred scheme of the middle platform rapid application development method based on digital twin AI agent, wherein: the static data flow between business nodes is extracted, and the dependency relationship between static data is analyzed according to the action order of static data in the business scenario.

[0008] As a preferred scheme of the middle platform rapid application development method based on digital twin AI agent, wherein: the static data format standard and the static data transmission rules are constructed based on the middle platform, including matching the dependency relationship between static data according to the preset format template of the middle platform, obtaining the static data format standard, determining the starting point, the ending point and the intermediate stop link of the static data transmission based on the static data flow, obtaining the transmission direction and the order of the static data between different business nodes, setting the static data transmission frequency, the transmission trigger condition and the fault tolerance strategy in the transmission process, and obtaining the static data transmission rule.

[0009] As a preferred embodiment of the rapid application development method for the middleware based on digital twin AI intelligent agents described in this invention, the decomposition of business requirements includes: based on static data format standards and static data transmission rules, splitting the processing logic in the business requirements one by one, analyzing the input fields and output target data that each processing logic depends on, and obtaining the execution order and parameter dependency path of the processing logic.

[0010] As a preferred embodiment of the rapid application development method for the middleware based on digital twin AI intelligent agents described in this invention, the establishment of the business processing flow includes: arranging each processing logic according to the execution order and parameter dependency path of the processing logic, matching the static data transmission path between the input fields and output fields of the processing logic, and configuring the execution jump relationship and triggering strategy between the processing logics.

[0011] As a preferred embodiment of the rapid application development method for the middleware based on digital twin AI intelligent agents described in this invention, the step of collecting operational data of business processes based on business processing flow includes: during the execution of the business processing flow, determining the start and end time, execution status and parameter call status of each processing logic, setting operational data collection instructions for each processing logic node, recording the operational data of each step in real time, and comparing the operational data with static data format standards and static data transmission rules to obtain operational data that conforms to the specifications.

[0012] Compliant operational data includes operational data that conforms to static data format standards and static data transmission rules.

[0013] As a preferred embodiment of the rapid application development method for the middle platform based on digital twin AI intelligent agents described in this invention, the dynamic monitoring of the business processing flow includes: inputting compliant operating data into the AI ​​analysis model accessed by the middle platform; extracting multi-dimensional features from the compliant operating data based on the AI ​​analysis model; analyzing the multi-dimensional feature extracted data through the AI ​​analysis model; performing trend modeling and stability judgment on the operating behavior of the business processing flow; extracting abnormal nodes of the operating behavior; and mapping the abnormal nodes to the business processing flow.

[0014] Abnormal nodes include the stability score of the operational behavior of the computing business process. When the stability score exceeds the stability score threshold, it is determined to be an abnormal node.

[0015] Another objective of this invention is to provide a rapid application development system for a middleware platform based on digital twin AI intelligent agents. This system solves the problems of current business middleware technologies, such as the lack of standardized static data formats, weak automatic business process construction capabilities, and weak dynamic monitoring capabilities during operation, by using a combination of static data format construction modules, business process generation modules, and runtime data modeling and monitoring modules.

[0016] As a preferred embodiment of the rapid application development system for a digital twin AI intelligent agent-based middleware platform according to the present invention, it includes: a static data format construction module, a business process generation module, and an operational data modeling and monitoring module; the static data format construction module is used to construct static data format standards and transmission rules suitable for data interaction in the middleware platform based on the business scenario analysis results, serving as the data foundation for subsequent process processing; the business process generation module is used to logically decompose business requirements and identify dependencies based on the static data format standards and transmission rules, establishing a clearly structured and executable business processing flow; the operational data modeling and monitoring module is used to collect operational data based on the business processing flow and connect it to the AI ​​analysis model, monitoring the business process status through modeling and inference, and identifying operational anomalies.

[0017] Another objective of this invention is to provide a rapid application development device for a platform based on a digital twin AI agent, comprising a memory and a processor. The memory stores a computer program, and the processor executes the computer program as a step in implementing a rapid application development method for a platform based on a digital twin AI agent.

[0018] Another object of the present invention is to provide a storage medium for rapid application development of a platform based on a digital twin AI agent, wherein a computer program is stored thereon, and when the computer program is executed by a processor, the steps of the rapid application development method of the platform based on a digital twin AI agent are implemented.

[0019] The beneficial effects of this invention are as follows: The rapid application development method for a middleware platform based on digital twin AI agents provided by this invention achieves unified access and standardized processing of multi-source heterogeneous data by constructing static data format standards and transmission rules; it achieves structured modeling and process-oriented execution of business logic by decomposing business requirements based on standards and generating business processing flows; and it achieves dynamic monitoring and anomaly identification of business processes by accessing AI analysis models to model and infer operational data. This forms a closed loop for middleware platform development that combines standardized data management, structured business orchestration, and intelligent operational analysis, improving flexible configuration capabilities, operational controllability, and intelligent decision-making levels. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is an overall flowchart of a rapid application development method for a middleware platform based on a digital twin AI agent, provided in Embodiment 1 of the present invention.

[0022] Figure 2 This is an overview interface diagram of an industrial application of a rapid application development system based on a digital twin AI agent provided in Embodiment 2 of the present invention.

[0023] Figure 2-1 This is a diagram of a warehousing and logistics application interface for a rapid application development system based on a digital twin AI agent, provided in Embodiment 2 of the present invention.

[0024] Figure 2-2 This is a diagram of the application interface of a rapid application development system for a digital twin AI agent-based middleware platform, as provided in Embodiment 2 of the present invention, for supply chain management.

[0025] Figure 2-3 This is a diagram of a safety production site application interface for a rapid application development system based on a digital twin AI agent, provided in Embodiment 2 of the present invention.

[0026] Figure 2-4 This is a diagram of a production and manufacturing application interface for a rapid application development system based on a digital twin AI agent provided in Embodiment 2 of the present invention.

[0027] Figure 2-5 This is a diagram of the R&D design application interface of a rapid application development system based on a digital twin AI agent provided in Embodiment 2 of the present invention.

[0028] Figure 2-6 This is an application interface diagram of an energy-saving and emission-reduction scenario of a rapid application development system based on a digital twin AI agent provided in Embodiment 2 of the present invention.

[0029] Figure 2-7 This is a diagram of the operation and maintenance service application interface of a rapid application development system based on a digital twin AI agent provided in Embodiment 2 of the present invention.

[0030] Figure 2-8 This is an operation and management application interface diagram of a rapid application development system for a digital twin AI intelligent agent-based middleware, provided in Embodiment 2 of the present invention. Detailed Implementation

[0031] 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. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0032] Example 1, referring to Figure 1 As an embodiment of the present invention, a method for rapid application development based on a digital twin AI agent platform is provided, comprising: S1: Based on business scenario 100, analyze static data format 101 and interaction requirements 102, and build static data format standard 200 and static data transmission rules 201 based on the middle platform.

[0033] Furthermore, the analysis of static data format 101 and interaction requirements 102 based on business scenario 100 includes extracting the static data flow between business nodes and analyzing the dependencies between static data based on the order of their roles in business scenario 100.

[0034] It should be noted that the static data sources involved in the target business scenario 100 are identified, and static data content existing in the form of files, interfaces, or forms in each business link is collected. The static data types, structures, and uses are classified and sorted. Data sources include, but are not limited to, business instructions, basic information tables, design output data, approval records, etc. The static data interaction requirements 102 between business nodes in different industry scenarios are analyzed, and the static data elements transmitted in business actions involving static data exchange, such as task issuance, process synchronization, configuration sharing, version change, etc., are extracted. The set of fields contained in these interactive behaviors and their upstream and downstream dependencies are determined. Based on the identification results, the field structure of static data is uniformly abstracted, and common field definitions are extracted, such as "work order number", "material code", "submission time", etc. The types, constraints and naming conventions of the fields are defined, and a unified static data format standard 2 is constructed. 00 serves as the foundational template for static data exchange in subsequent business processes. It clarifies the timing, direction, and triggering conditions for static data transmission during business interactions, determines the flow logic of static data between different business nodes, defines data exchange methods (such as proactive push, scheduled retrieval, periodic updates, etc.), and formulates corresponding transmission rules to ensure the sequentiality, consistency, and integrity of data interaction. In conjunction with the overall business framework of the middle platform, based on the data interaction paths under different business scenarios, a static data transmission mapping table is established. The source node, target node, dependent fields, synchronization cycle, and other information of each type of static data are registered and archived as a structural basis for subsequent process design and dynamic monitoring.

[0035] It should also be noted that by identifying the static data sources in business scenario 100, collecting and organizing the static data interaction requirements 102 between various business nodes, extracting static data fields and their upstream and downstream dependencies, and based on this information, uniformly abstracting the field model and semantic expression, and constructing static data templates, not only is the consistency and reusability of data modeling improved, but a data foundation is also provided for subsequent automated process configuration. Furthermore, by defining the data transmission triggering time, triggering conditions, transmission direction, and exchange method, explicit modeling of data interaction logic is achieved, which helps to eliminate implicit dependencies in data interface design and improve the visibility and maintainability of process construction.

[0036] Furthermore, the construction of static data format standard 200 and static data transmission rules 201 based on the middle platform includes: matching the dependencies between static data according to the preset format template of the middle platform to obtain static data format standard 200; determining the starting point, ending point and intermediate stopping points of static data transmission based on the static data flow direction to obtain the transmission direction and order of static data between different business nodes; and setting the static data transmission frequency, transmission triggering conditions and fault tolerance strategies during the transmission process to obtain static data transmission rules 201.

[0037] It should be noted that by calling the pre-defined static data format 101 template in the middle platform, the name, type, source path, and upstream and downstream dependent fields of each static data field in business scenario 100 are identified and extracted. Combined with business process logic, field dependency relationships are matched to obtain a complete data dependency chain. Based on this dependency chain, a static data format standard 200 is constructed to unify the structured expression of static data across different business stages, ensuring consistency and parsability of data interaction within the middle platform and between various businesses. Based on the flow information of static data in the business processing stages, the position and role of the data during data transmission are analyzed, including the data starting point (e.g., data entry source). The system defines the transmission control specifications for static data across different business nodes, including intermediate transmission nodes (such as cache nodes and interface processing nodes) and endpoint nodes (such as business consumers or archiving stages). It also specifies transmission frequencies (e.g., by minute, hour, day, or real-time), triggering conditions (e.g., depending on upstream completion status or specific time points), and fault tolerance strategies (e.g., failure retry, default value replacement, alarm logging, etc.). Based on these specifications, a set of 201 static data transmission rules is generated, including a dependency mapping table between fields, the execution order of the transmission process, the response method of the triggering mechanism, and recovery logic under abnormal conditions.

[0038] It should also be noted that, by using preset format templates based on the middle platform, the names, types, source paths, and upstream and downstream dependent fields of static data fields involved in business scenario 100 are identified and extracted. Combined with business process logic, field dependency matching relationships are established, thereby constructing a complete data dependency chain and achieving standardized modeling of various static data formats 101. This unifies the expression of static data structures across different stages of the business, improving the compatibility of data transmission across business systems.

[0039] S2: Based on the static data format standard 200 and the static data transmission rule 201, the business requirements are decomposed and the business processing flow 300 is established.

[0040] Furthermore, the business requirements are decomposed by breaking them down one by one based on the static data format standard 200 and the static data transmission rule 201. The input fields and output target data that each processing logic depends on are analyzed to obtain the execution order and parameter dependency path of the processing logic.

[0041] It should be noted that, during the decomposition of business requirements, based on the established static data format standard 200 and static data transmission rule 201, the overall objectives involved in the business requirements are extracted, and the processing actions, business semantics, and corresponding field operations contained in the business requirements are identified. The business operation process described by the business requirements is broken down into several processing logic units with clear boundaries. Each logic unit corresponds to a type of field processing, data transformation, or judgment rule. In the process of decomposition, combined with the field types, field naming rules, and data transmission conventions defined in the static data format standard 200, the input fields that each processing logic depends on are identified, including field names, source field links, and data format types; and the target data fields that the processing logic needs to output are also marked, including data meaning, data location, and subsequent use purpose. Through the input-output correspondence of dependent fields, a complete data dependency mapping link is formed. After all processing logics are decomposed and the input-output relationships are clarified, topological sorting is performed according to the field dependency relationships to obtain the execution order between each processing logic. The logic execution path is constructed in the form of a graph structure, and each path identifies the triggering order of the processing logic and its corresponding field parameter dependencies.

[0042] It should also be noted that by breaking down the processing logic in business requirements one by one based on the static data format standard 200, and building a complete data mapping relationship link with field dependencies as the core, the input fields and output target data of each processing unit can be accurately obtained, thereby sorting out a clear execution order and parameter path. This enables the structured, visualized and standardized processing operations at the logical level, improving the accuracy, consistency and reconfigurability of converting business requirements into data processing instructions for the middle platform. It provides basic support for automatically generating execution paths, dynamically adjusting task processes and anomaly tracing, and effectively enhances the flexibility and reliability of the business middle platform when dealing with complex data dependencies.

[0043] Furthermore, establishing the business processing flow 300 includes arranging each processing logic according to its execution order and parameter dependency path, matching the static data transfer path between the input and output fields of the processing logic, and configuring the execution jump relationship and triggering strategy between processing logics.

[0044] It should be noted that in establishing the 300 business processing flow, a unified execution flowchart was constructed based on the execution order and parameter dependency paths, according to the sequential call relationships between processing logics. The flowchart uses processing logic units as basic nodes, and arranges paths according to the static data dependencies between input and output fields to form a clear business operation chain. During the arrangement process, by identifying the preconditions and postconditions for data transfer between each logic unit, the input-output mapping relationships of fields are marked. Combined with the standard template for static data transfer paths, field-level dependency path connections are completed, ensuring that the data required by each processing logic can be output on demand by its preconditions, eliminating data silos. Configurations are made for possible jump relationships between different logic units (such as conditional branches, abnormal interruptions, etc.), clarifying the triggering conditions and methods for processing jumps, and formulating jump strategies. Jump strategies include jump path switching based on field value judgments and selection of fallback paths for abnormal processes, used to support flexible jumps and fault-tolerant execution during dynamic process operation.

[0045] It should also be noted that by constructing a unified execution flowchart based on execution order and parameter dependency paths, the organization and visualization of business processing logic are significantly improved, making the data dependencies between processing units clear and easy to maintain and optimize in the future. Combined with field input / output mapping relationships and standard templates for static data transfer paths, automatic connection of field-level dependencies is effectively achieved, reducing manual configuration errors and avoiding data silos.

[0046] S3: Collect operational data of business processes based on business processing flow, connect AI analysis models to the middle platform 400, model and infer operational data of business processes, and dynamically monitor business processing flow 401.

[0047] Furthermore, the collection of operational data for business processes based on the business processing flow includes determining the start and end times, execution status, and parameter call status of each processing logic during the execution of the business processing flow, setting operational data collection instructions for each processing logic node, recording the operational data of each link in real time, and comparing the operational data with the static data format standard 200 and the static data transmission rule 201 to obtain operational data that conforms to the specifications.

[0048] Compliant operational data includes operational data that is consistent with Static Data Format Standard 200 and Static Data Transmission Rule 201.

[0049] It should be noted that, in the process of collecting operational data of business processes based on the business processing flow, the start and end time range of the business processing flow is first determined, and a process scheduling timeline is generated based on a preset time resolution. For each logical node in the business processing flow, the corresponding running status collection trigger conditions and data collection instructions are set. The running status includes, but is not limited to, the start status, end status, parameter call status, abnormal status, and execution duration of the processing unit.

[0050] During actual data collection, an event listening mechanism or a timed polling mechanism is used to monitor the processing nodes. When the collection trigger conditions are met, a collection command is invoked to obtain real-time running data from the runtime environment. The collected data is reorganized according to the method of matching with the static data format standard 200 to construct data records with a unified structure. Based on the field comparison logic and transmission timing standard defined in the static data transmission rule 201, the currently collected running data is verified for compliance, and data entries that meet the structural requirements and scheduling specifications are selected as the basis for subsequent process operation monitoring and evaluation.

[0051] It should also be noted that by collecting operational data from business processes and filtering the data, it is ensured that the collected operational data not only has completeness and consistency, but can also be integrated with static configuration data to achieve dynamic correlation of multi-source information, which is conducive to supporting subsequent AI modeling, process performance analysis and operational status optimization.

[0052] Furthermore, dynamic monitoring of business processes 401 includes inputting compliant operational data into the AI ​​analysis model accessed by the middle platform, extracting multi-dimensional features from the compliant operational data based on the AI ​​analysis model, analyzing the multi-dimensional feature extracted data through the AI ​​analysis model, performing trend modeling and stability judgment on the operational behavior of the business process, extracting abnormal nodes in the operational behavior, and mapping the abnormal nodes to the business process.

[0053] Abnormal nodes include the stability score of the operational behavior of the computing business process. When the stability score exceeds the stability score threshold, it is determined to be an abnormal node.

[0054] It should be noted that during the dynamic monitoring of the business process using 401 redirects, the operational data conforming to static data specifications is standardized and preprocessed according to the node identifiers, timestamps, and data type fields in the business process, and then stored in a structured format in the pre-set data buffer of the middle platform. This standardized operational data is then input into the connected AI analysis model through a data pipeline. The AI ​​analysis model uses a combination of multi-dimensional feature extraction and time-series analysis to model the operational behavior.

[0055] It should also be noted that by constructing an operational status evaluation mechanism that combines feature compression and behavior modeling, dynamic monitoring and stability assessment of multi-dimensional operational data of business processes have been achieved.

[0056] Example 2, refer to Figures 2-2-8 As an embodiment of the present invention, a rapid application development system based on a digital twin AI agent is provided, including a static data format 101 construction module, a business process generation module, and a runtime data modeling and monitoring module.

[0057] like Figure 2 As shown, the system of the present invention realizes a multi-module collaborative display interface in the industrial Internet platform, forming an application cluster covering business areas such as warehousing and logistics, supply chain management, and safe production. It realizes modular configuration and integrated linkage, and supports switching at least a part of the displayed content 501 by clicking at least a part of the first button 500.

[0058] like Figure 2-1 As shown, in warehousing and logistics applications, the system automatically generates Factory Cloud-Logistics Management and Factory Cloud-Warehouse Management modules based on static data format standards, realizing unified definition and transmission rule setting for logistics inbound and outbound, material information and static fields, providing structured template support for data interaction in subsequent business processes.

[0059] like Figure 2-2 As shown, in the supply chain management scenario, the system automatically identifies business dependencies based on static data format and transmission rules, and generates supply chain process modules covering nodes such as orders, procurement, sales, raw materials, and products, realizing the visual generation and parameterized configuration of business logic.

[0060] like Figure 2-3 As shown, in a safe production scenario, the system integrates an AI intelligent agent model to collect and analyze data such as on-site video monitoring, sensor signals, and personnel work status in real time, dynamically monitoring construction safety, environmental risks, and operational compliance, forming a multi-source data fusion safety production management application cluster.

[0061] like Figure 2-3 As shown, in a safe production scenario, the system dynamically monitors video, sensor signals, and operational data to form an intelligent safe production management and control module.

[0062] like Figure 2-4 As shown, in the manufacturing scenario, the system decomposes the processing logic and identifies dependencies based on static data format standards and transmission rules, automatically generates executable process nodes such as project construction, production scheduling, production orders, production plans, and data analysis, and forms an orderly execution path with parameter dependencies as constraints.

[0063] likeFigure 2-5 As shown, in the R&D design scenario, the system uses field models and semantic abstraction as a foundation to define the format and map the dependencies of various types of static data involved in the design process, such as encoding / encryption, format conversion, statistical verification, and template generation. This forms a reusable standardized data template and transmission rule base, providing a foundation for the automatic generation of subsequent processes and cross-module data consistency.

[0064] like Figure 2-6 As shown, in the energy conservation and emission reduction scenario, the system collects and standardizes the operational data of charging piles, photovoltaics, environmental safety and other links in real time and inputs them into the model. It also connects to the AI ​​analysis model to extract multi-dimensional features and perform time series modeling, and outputs energy consumption trend, abnormal fluctuation and stability assessment results to realize online monitoring and strategy closed loop for green manufacturing.

[0065] like Figure 2-7 As shown, in the operation and maintenance service scenario, the system provides multiple types of components and service interface modules, including file storage management, distributed storage, local storage, request verification, middleware integration, intelligent question answering, intelligent map, intelligent scheduling, system management and other functions. Through the API interface and AI analysis model calling mechanism, the system realizes platform-level service orchestration and multi-source resource scheduling, providing unified support capabilities for upper-layer business modules.

[0066] like Figure 2-8 As shown, in the operation and management scenario, the system integrates multiple application modules such as assets, departments, leasing, taxation, industrial parks, Party building, and enterprise management, supporting full-process configuration from asset lifecycle management to organizational operation. Through the combination of static data formats and business process models, the system achieves unified management and analysis of enterprise resources, spatial information, and operational status, providing basic management support for multi-scenario digital twin operation.

[0067] Among them, the static data format 101 construction module is used to construct a static data format standard 200 and transmission rules suitable for data interaction in the middle platform based on the analysis results of business scenario 100, as the data foundation for subsequent process processing.

[0068] The business process generation module is used to logically decompose business requirements and identify dependencies based on static data format standard 200 and transmission rules, and to establish a clear and executable business processing flow.

[0069] The operational data modeling and monitoring module is used to collect operational data based on business processes and connect it to AI analysis models. Through modeling and inference, it monitors the status of business processes and identifies operational anomalies.

[0070] This embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a personnel positioning safety management visualization analysis system as proposed in the above embodiment.

[0071] This embodiment also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a personnel positioning safety management visualization analysis system as proposed in the above embodiment.

[0072] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0074] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0075] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0076] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A rapid application development method for a middleware platform based on digital twin AI intelligent agents, characterized in that, include: Based on the business scenario analysis, static data format and interaction requirements are defined, and static data format standards and static data transmission rules are built on the middle platform. Based on static data format standards and static data transmission rules, business requirements are decomposed and business processing flows are established. Based on the business process, collect operational data of business links, connect AI analysis models to the middle platform, model and infer the operational data of business links, and dynamically monitor the business process. Establishing a business process flow includes arranging the execution order of the processing logic according to the execution order and parameter dependency path, matching the static data transfer path between the input and output fields of the processing logic, and configuring the execution jump relationship and triggering strategy between the processing logics. Dynamic monitoring of business processes includes inputting compliant operational data into the AI ​​analysis model accessed by the middle platform, extracting multi-dimensional feature data based on the AI ​​analysis model, analyzing the operational behavior of the business processes, performing trend modeling and stability judgment, identifying abnormal nodes and mapping them to the business processes.

2. The rapid application development method for a middleware platform based on digital twin AI intelligent agents as described in claim 1, characterized in that: The step of analyzing static data formats and interaction requirements based on business scenarios includes extracting the static data flow between business nodes and analyzing the dependencies between static data based on the order of their roles in the business scenario.

3. The rapid application development method for a middleware platform based on a digital twin AI intelligent agent as described in claim 1 or 2, characterized in that: The construction of static data format standards and static data transmission rules based on the middle platform includes: matching the dependencies between static data according to the preset format template of the middle platform to obtain static data format standards; determining the start point, end point and intermediate stops of static data transmission based on the static data flow direction to obtain the transmission direction and order of static data between different business nodes; and setting the static data transmission frequency, transmission triggering conditions and fault tolerance strategies during the transmission process to obtain static data transmission rules.

4. The rapid application development method for a middleware platform based on a digital twin AI intelligent agent as described in claim 3, characterized in that: The decomposition of business requirements includes breaking down the processing logic in the business requirements one by one based on static data format standards and static data transmission rules, analyzing the input fields and output target data that each processing logic depends on, and obtaining the execution order and parameter dependency path of the processing logic.

5. The rapid application development method for a middleware platform based on a digital twin AI intelligent agent as described in any one of claims 1, 2, and 4, characterized in that: The establishment of the business processing flow includes arranging each processing logic according to its execution order and parameter dependency path, matching the static data transfer path between the input and output fields of the processing logic, and configuring the execution jump relationship and triggering strategy between the processing logics.

6. The rapid application development method for a middleware platform based on a digital twin AI agent as described in claim 5, characterized in that: The process of collecting operational data for business processes based on business processing flow includes determining the start and end times, execution status, and parameter call status of each processing logic during the execution of the business processing flow, setting operational data collection instructions for each processing logic node, recording the operational data of each step in real time, and comparing the operational data with static data format standards and static data transmission rules to obtain operational data that conforms to the specifications. Compliant operational data includes operational data that conforms to static data format standards and static data transmission rules.

7. The rapid application development method for a middleware platform based on a digital twin AI intelligent agent as described in any one of claims 1, 2, 4, and 6, characterized in that: The dynamic monitoring of the business processing flow includes inputting compliant operational data into the AI ​​analysis model accessed by the middle platform, extracting multi-dimensional features from the compliant operational data based on the AI ​​analysis model, analyzing the multi-dimensional feature extracted data through the AI ​​analysis model, performing trend modeling and stability judgment on the operational behavior of the business processing flow, extracting abnormal nodes of the operational behavior, and mapping the abnormal nodes to the business processing flow. Abnormal nodes include the stability score of the operational behavior of the computing business process. When the stability score exceeds the stability score threshold, it is determined to be an abnormal node.

8. A rapid application development system for a middleware platform based on digital twin AI agents, employing the rapid application development method for a middleware platform based on digital twin AI agents as described in any one of claims 1 to 7, characterized in that: It includes a static data format construction module, a business process generation module, and a runtime data modeling and monitoring module; The static data format construction module is used to construct static data format standards and transmission rules suitable for data interaction in the middle platform based on the business scenario analysis results, as the data foundation for subsequent process processing; The business process generation module is used to logically decompose business requirements and identify dependencies based on static data format standards and transmission rules, and to establish a clear and executable business processing flow. The operational data modeling and monitoring module is used to collect operational data based on business processing flow and connect it to an AI analysis model. Through modeling and inference, it monitors the status of business processes and identifies operational anomalies.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the rapid application development method for a digital twin AI agent-based middleware platform as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the rapid application development method for a digital twin AI agent-based middleware platform as described in any one of claims 1 to 7.

Images