Organizational digital transformation and upgrading system and method based on A-DFCT technology

Abstract

The present invention provides a system and method for digital transformation and upgrading of organizations based on A‑DFCT technology, the system including an artificial intelligence model platform, a digital twin and big data platform, a unified login and business integration platform, and an Internet of Things management and control platform. Among them, the artificial intelligence model platform (A) provides algorithms and models that meet organizational decision-making; the digital twin and big data platform (D) can integrate and process multiple data sources to provide users with in-depth data analysis and insight services; the unified login and business integration platform (F) aims to extract and integrate process data, and ensure the accuracy and integrity of the data through standardized interfaces and efficient processing mechanisms; the Internet of Things management and control platform (C) focuses on the rapid deployment of intelligent hardware, and provides stable and reliable support for Internet of Things applications. The present invention uses artificial intelligence models to conduct in-depth mining and analysis of organizational business, improve the accuracy of decision-making, help organizations reduce costs, improve quality and efficiency, and achieve high-quality sustainable development.

Description

Technical Field

[0001] The present invention belongs to the field of digital technology, and in particular relates to a system and method for digital transformation and upgrading of an organization based on A-DFCT technology. Background Art

[0002] Enterprise digital transformation refers to the use of digital and intelligent technologies by enterprises to comprehensively transform and upgrade business processes, management models, organizational structures, etc., in order to improve the operational efficiency, innovation capabilities and competitiveness of enterprises and achieve sustainable development. Enterprise digital transformation is a profound change, and technology plays a key role in promoting it.

[0003] In the process of digital transformation of enterprises, the integration and application of technology is a complex process. Enterprises need to select appropriate technology solutions based on their business needs and development strategies, and integrate and apply them effectively. The degree of digitalization of enterprises in existing technologies still needs to be improved. Summary of the invention

[0004] In view of this, the present invention provides a system and method for the digital transformation and upgrading of an organization based on A-DFCT technology, aiming to solve the problem that the degree of digitalization of enterprises in the prior art still needs to be improved.

[0005] A first aspect of an embodiment of the present invention provides a method for digital transformation and upgrading of an organization based on A-DFCT technology, including:

[0006] Artificial intelligence model platform, digital twin and big data platform, unified login and business integration platform, and Internet of Things management and control platform;

[0007] The IoT management and control platform is used to collect data from devices in the physical world and obtain monitoring data;

[0008] The unified login and business integration platform is used to integrate various business systems of the enterprise to obtain business operation data;

[0009] The artificial intelligence model platform is used to predict various pre-adjustment strategies for the enterprise business based on the enterprise operation data, monitoring data and the first intelligent model;

[0010] The digital twin and big data platform is used to build a digital mapping model of the physical world based on the data of the IoT management and control platform, and based on the digital mapping model, digitally simulate the enterprise business according to a variety of pre-adjustment strategies to obtain the simulation results of each pre-adjustment strategy;

[0011] The artificial intelligence model platform is also used to determine a target adjustment strategy based on multiple pre-adjustment strategies, simulation results of each pre-adjustment strategy and a second intelligent model.

[0012] In one possible implementation, the artificial intelligence model platform is used to:

[0013] Clustering enterprise operation data and monitoring data to determine the direct and indirect related data corresponding to each enterprise business;

[0014] The directly associated data and the indirectly associated data corresponding to each enterprise business are input into the first intelligent model corresponding to the enterprise business to predict multiple adjustment strategies for each device.

[0015] In one possible implementation, the artificial intelligence model platform is specifically used to:

[0016] Cluster the business operation data of enterprises to obtain the first classification result;

[0017] Cluster the monitoring data to obtain the second classification result;

[0018] According to the first classification result, the second classification result and the preset association relationship table, directly associated data and indirectly associated data are determined; wherein the association analysis table is used to represent the association relationship between each enterprise operation data and each monitoring data.

[0019] In one possible implementation, the digital twin and big data platform are used to:

[0020] Under the boundary conditions and initial conditions of the simulation of the digital twin and big data platform, the parameters of the digital mapping model are adjusted according to each pre-adjustment strategy, and digital simulation is performed to obtain the simulation results of each pre-adjustment strategy.

[0021] In a possible implementation, the digital model includes at least one of the following: a geometric model, a physical property model, a behavior model, and an environment model.

[0022] In one possible implementation, the artificial intelligence model platform is specifically used to:

[0023] Evaluate the simulation results of each pre-adjustment strategy according to the second intelligent model to obtain an evaluation result of each pre-adjustment strategy;

[0024] Based on the evaluation results, the target adjustment strategy is determined from a variety of pre-adjustment strategies.

[0025] In one possible implementation, the artificial intelligence model platform is specifically used to:

[0026] According to multiple evaluation indicators, corresponding indicator values ​​are extracted from the simulation results of each pre-adjustment strategy to form an evaluation feature vector;

[0027] The evaluation feature vector is input into the second intelligent model to obtain the evaluation result of each pre-adjustment strategy.

[0028] In a possible implementation, the unified login and service integration platform is used to:

[0029] Obtain the database structure of each business system of the enterprise, and determine the corresponding integration algorithm for each business system based on the database structure;

[0030] According to the integration algorithms corresponding to each business system, the databases of each business system are integrated to obtain the enterprise operating data.

[0031] In a possible implementation, the integration algorithm includes at least one of the following: a data matching algorithm, a data fusion algorithm, a data deduplication algorithm, a data conversion algorithm, and a data evaluation algorithm.

[0032] A second aspect of an embodiment of the present invention provides a method for digital transformation and upgrading of an organization based on A-DFCT technology, including:

[0033] The artificial intelligence model platform (A) provides the digital intelligence system (DFCT) with strategies, algorithms and models that meet organizational decision-making and prediction, and provides strategic support for organizational transformation and upgrading;

[0034] The digital twin and big data platform (D) can integrate and process multiple data sources in the IoT management and control platform and the unified login and business integration platform, providing in-depth analysis and insight services of 3D panoramic multi-perspective full data for users at all levels of the organization;

[0035] The unified login and business integration platform (F) aims to extract and integrate process data of key nodes from the original business system, ensure the accuracy and integrity of data through standardized data interfaces and efficient data processing mechanisms, and provide support for business collaboration and operation management;

[0036] The IoT management and control platform (C) focuses on the rapid deployment of intelligent hardware, and realizes the state perception, time series data collection and processing of spatial nodes, providing stable and reliable support for IoT applications.

[0037] The embodiment of the present invention provides an organization digital transformation and upgrading system and method based on A-DFCT technology, first of all, an artificial intelligence model platform, a digital twin and big data platform, a unified login and business integration platform and an Internet of Things management and control platform; the artificial intelligence model platform (A) provides the digital system (DFCT) with strategies, algorithms and models that meet the organization's decision-making and prediction, and serves the strategic support of the organization's transformation and upgrading; the digital twin and big data platform (D) can integrate and process multiple data sources in the Internet of Things management and control platform and the unified login and business integration platform, and provide users at all levels of the organization with three-dimensional panoramic multi-perspective full-scale data in-depth analysis and insight services; the unified login and business integration platform (F) aims to extract and integrate the process data of key nodes from the original business system, and ensure the accuracy and integrity of the data through standardized data interfaces and efficient data processing mechanisms, so as to provide support for business collaboration and operation management; the Internet of Things management and control platform (C) focuses on the rapid deployment of intelligent hardware, and realizes the state perception, time series data collection and processing of spatial nodes, providing stable and reliable support for Internet of Things applications. The present invention utilizes artificial intelligence models and integrates several platforms with different functions. By deeply mining and analyzing the organization's business, it provides corresponding adjustment strategies, optimizes business processes, improves the accuracy of decision-making, and helps organizations reduce costs, improve quality and efficiency, and achieve high-quality sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 It is a structural diagram of the organization digital transformation and upgrading system based on A-DFCT technology provided by an embodiment of the present invention;

[0040] Figure 2 It is a flowchart for implementing the method for digital transformation and upgrading of an organization based on A-DFCT technology provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0042] Figure 1 Schematic diagram of the structure of the organizational digital transformation and upgrading system based on A-DFCT technology provided by the embodiment of the present invention. Figure 1 As shown, in some embodiments, the digital transformation and upgrading system of an organization based on the A-DFCT technology includes: an artificial intelligence model platform A, a digital twin and big data platform D, a unified login and business integration platform F, and an Internet of Things management and control platform C;

[0043] The IoT control platform C is used to collect data from devices in the physical world and obtain monitoring data;

[0044] like Figure 1 As shown in the figure, the A-DFCT technical architecture consists of the following core components:

[0045] A (Artificial Intelligence Model Platform): As the intelligent engine of the entire architecture, the artificial intelligence model platform conducts in-depth analysis, mining and intelligent decision-making on data from the D, F, and C platforms to drive the digital transformation of the organization. It provides the digital intelligence system (DFCT) with strategies, algorithms, and models that meet organizational decision-making and prediction, and serves as strategic support for organizational transformation and upgrading.

[0046] D (Data Analysis and Visualization Application Platform): Digital twin and big data platform, by building a virtual mapping of the physical world, to achieve real-time monitoring, simulation prediction and optimization control of physical systems. It mainly relies on digital twins to realize the digitization of physical space, and through digital governance, data assets and data visualization applications, it realizes the digital mapping of the physical world and dynamic management of the entire life cycle. It can integrate and process multiple data sources in the Internet of Things management and control platform and the unified login and business integration platform, and provide users at all levels of the organization with in-depth analysis and insight services of three-dimensional panoramic multi-perspective full data.

[0047] F (Fusion Platform for Unified Login & Business Integration): Unified login and business integration platform, providing a unified user authentication portal and business system integration capabilities, mainly for the continuous integration of various business systems, by integrating the software and business data required for organizational business activities, to achieve one account to integrate multiple systems, promote cross-departmental and cross-system data sharing and business collaboration. It aims to extract and integrate process data of key nodes from the original business system, ensure the accuracy and integrity of the data through standardized data interfaces and efficient data processing mechanisms, and provide support for business collaboration and operation management.

[0048] C (Connected Things Management & Control Platform): IoT management and control platform, responsible for device access, data collection, communication protocol conversion and device management, to ensure the stable and efficient operation of the IoT environment. It is mainly aimed at the management and operation of people, machines, goods and venues in the physical world, and realizes status monitoring, real-time management and control through rapid access to various physical entities. It focuses on the rapid deployment of intelligent hardware, and realizes the status perception, time series data collection and processing of spatial nodes, providing stable and reliable support for IoT applications.

[0049] Among them, CN_CD refers to the automation process, specifically the perception and control process when the physical entity is connected with the virtual model, such as automatic production lines, CNC machine tools, smart homes, etc.; CN_FD refers to the digitalization process, specifically the process of connecting the physical entity with the virtual model, such as cockpits, VR roaming of cultural and tourism attractions, etc.; CN_FC refers to the information process, specifically the process of connecting the physical entity with the business, such as electronic processes, online approval, etc.; CN_AC refers to terminal intelligence, specifically the connection between the physical entity and AI, such as face recognition cameras, robots, etc.; CN_AD refers to simulation intelligence, specifically the connection between virtual simulation and AI, such as new product design, motion posture simulation, emergency drills, etc.; CN_AF is data intelligence, specifically the connection between business data and AI, such as data mining, decision analysis, etc.

[0050] In the embodiment of the present invention, the Internet of Things is to collect various required information such as any object or process that needs to be monitored, connected, and interacted in real time through various devices and technologies such as various information sensors, radio frequency identification technology, global positioning system, infrared sensor, laser scanner, etc. In the context of the digital transformation of enterprises, the Internet of Things enables the devices in the enterprise to be connected to the network to form an interconnected network system. In the enterprise environment, not only large equipment in the traditional sense, but also various small devices and sensors can be interconnected. For example, in a manufacturing enterprise, not only the large machine tools on the production line, but also the surrounding temperature sensors, humidity sensors, material transport carts, etc. can be connected to the Internet of Things management and control platform.

[0051] Equipment in the physical world covers various facilities and tools used in business operations. Taking the manufacturing industry as an example, these equipment include but are not limited to production equipment (such as CNC machine tools, injection molding machines, etc.), logistics equipment (such as automated storage shelves, trolleys, etc.), and environmental control equipment (such as air conditioners, ventilation equipment, etc.). Different types of equipment generate different types of data. Production equipment may generate process parameter data such as temperature, pressure, speed, etc. during the production process; logistics equipment may generate location information and transportation status data; environmental control equipment may generate data such as ambient temperature and humidity.

[0052] There are different ways to collect data for different devices. Some devices may have built-in data collection interfaces that can directly transmit data to the IoT management and control platform. For example, modern CNC machine tools are usually equipped with Ethernet interfaces or dedicated industrial communication interfaces, which can transmit the operating parameters of the machine tools (such as tool wear data, processing accuracy data, etc.) in real time. For some devices that do not have their own interfaces, data collection can be achieved by adding sensors and data collection terminals. For example, for traditional warehouse shelves, weight sensors can be installed to collect the weight change data of the goods, and then the data is sent to the IoT management and control platform through the wireless communication module.

[0053] These monitoring data are an important basis for the digital operation of enterprises. Enterprises can optimize production plans based on the operation data of equipment. For example, if the failure rate of a key production equipment is detected to increase, the enterprise can adjust the production task allocation to avoid production stagnation due to equipment failure. At the same time, monitoring data is also helpful for equipment maintenance management. Enterprises can arrange maintenance work in advance based on the wear data of equipment to improve the service life and reliability of equipment.

[0054] Monitoring data is the data foundation of the entire enterprise digital transformation system. Together with other data such as enterprise operating data obtained by the unified login and business integration platform, it provides input data for the artificial intelligence model platform to perform operations such as enterprise business prediction and strategy adjustment.

[0055] The unified login and business integration platform is used to integrate various business systems of the enterprise to obtain business operation data;

[0056] In the embodiment of the present invention, there are various business systems in the enterprise. For example, in the sales business, there is a customer relationship management system, which records the basic information of customers, purchase history, customer needs and other data; in the production and manufacturing link, there is an enterprise resource planning system, which covers the data related to the functions of production planning, material management, inventory management, etc.; there is also a financial management system, which is responsible for processing the financial data of the enterprise's financial income and expenditure, cost accounting, budget management, etc.

[0057] The data structure and storage methods of different business systems vary greatly. A customer relationship management system may build data relationships with customers as the center, using relational database storage, and the data fields focus on customer attributes and interactive behaviors. The data structure of an enterprise resource planning system is more complex, involving associations between multiple modules, and may contain both structured and unstructured data. For example, bill of materials data is structured, while some production process documents may be unstructured.

[0058] In some embodiments, the unified login and business integration platform F is used to: obtain the database structure of each business system of the enterprise, and determine the integration algorithm corresponding to each business system according to the database structure; integrate the databases of each business system according to the integration algorithm corresponding to each business system to obtain the business data of the enterprise. In some embodiments, the integration algorithm includes at least one of the following: data matching algorithm, data fusion algorithm, data deduplication algorithm, data conversion algorithm, data evaluation algorithm.

[0059] In an embodiment of the present invention, in an enterprise environment, there are usually multiple business systems with different functions, such as a sales management system, a production management system, a financial management system, etc. Each business system has its own independently constructed database structure. The database structure contains information from multiple aspects. For example, in terms of table structure, different business systems will define different tables according to their own business needs. Taking the sales management system as an example, there may be a customer table (including fields such as customer name, contact information, purchase history, etc.), an order table (including fields such as order number, order time, product information, customer ID, etc.); while the production management system may have a material table (including fields such as material name, specification, inventory quantity, etc.), a production plan table (including fields such as production batch, planned start time, planned output, etc.), etc.

[0060] In addition to the table structure, the database structure also includes the data type of the field (such as numeric, character, date, etc.), index settings (a structure used to improve data query efficiency), and the relationship between tables (such as foreign key relationships, used to associate data in different tables), etc. The unified login and business integration platform F needs to have a deep understanding of these database structure information, which is the basis for subsequent integration work.

[0061] When there are interrelated data between different business systems of an enterprise, a data matching algorithm is needed. For example, the customer information in the sales management system and the customer service system may overlap partially, but because they are recorded in different systems, there may be differences in format, coding or some field contents. The data matching algorithm can find the corresponding customer records in the databases of the two systems by comparing key fields (such as unique identification fields such as customer ID and mobile phone number), ensuring that the data about the same customer in different systems can be accurately associated.

[0062] Different business systems of an enterprise may record data related to the same business object from different perspectives. For example, the production management system records the production process data of the product, while the quality management system records the quality inspection data of the product. The role of the data fusion algorithm is to fuse these product-related data from different systems to form a more comprehensive data set about the product. This may involve processing different data formats and data semantics to ensure that the fused data can accurately reflect the full picture of the product and provide more complete information for the company's decision-making.

[0063] In multiple business systems of an enterprise, data duplication may exist due to various data sources or imperfect data entry processes. For example, some supplier information may be recorded in the business systems of different departments, and there may be exactly the same records. The data deduplication algorithm will identify and delete duplicate data records based on pre-set rules (such as comparison based on key information such as supplier name and contact information), thereby improving data accuracy and storage efficiency.

[0064] Different business systems may use different units of measurement, data encoding methods, or data representation forms. For example, in the sales systems of international business and domestic business, the currency units may be US dollars and RMB respectively; or in production systems in different regions, the units of measurement of product specifications may be British and metric respectively. Data conversion algorithms can convert these different units of measurement or encoding methods, so that data from different systems can be compared and analyzed under the same standard after integration.

[0065] Data evaluation algorithms are mainly used to evaluate the quality of data obtained from various business systems. They check the integrity of the data (such as whether all required fields have values), accuracy (such as whether the data is within a reasonable range of values), consistency (such as whether the values ​​of the same data in different systems are consistent), etc. For example, in a financial management system, it checks whether each income and expenditure record has a corresponding date, whether the amount is reasonable, etc., to ensure that the data integrated into the business data is reliable.

[0066] Taking a manufacturing company as an example, the customer orders in the sales system are linked to the production plans in the production system through the data matching algorithm to ensure that production can meet sales demand; the cost data, quality data and sales data in the production process are integrated with the data fusion algorithm to analyze the profitability of the product; the data deduplication algorithm is used to clean up the duplicate supplier, customer and other information in each system; the inconsistent measurement units and data formats in different departments or different business links are unified through the data conversion algorithm; finally, the quality of the integrated data is guaranteed with the help of the data evaluation algorithm.

[0067] After the above integration operation, the business data obtained is a comprehensive data set that fully reflects the business status of the enterprise. This data set includes information on the enterprise's sales (such as sales, sales volume, sales channel distribution, etc.), production (such as output, production efficiency, production cost, etc.), financial (such as income, cost, profit, etc.), customer (such as customer number, customer satisfaction, etc.), etc., providing important data support for the enterprise's decision-making, planning and management.

[0068] The artificial intelligence model platform A is used to predict various pre-adjustment strategies for the enterprise's business based on the enterprise's operating data, monitoring data and the first intelligent model;

[0069] In the embodiment of the present invention, the artificial intelligence model platform A plays a key role in the enterprise digital transformation system, and is responsible for predicting various pre-adjustment strategies for the enterprise's business. This means that platform A can comprehensively utilize data from different channels and, with the help of the analysis capabilities of the intelligent model, provide the enterprise with a variety of possible adjustment directions to optimize the enterprise's business processes and improve operational efficiency and competitiveness.

[0070] In some embodiments, artificial intelligence model platform A is used to: cluster business operation data and monitoring data to determine the direct and indirect related data corresponding to each business of the enterprise; input the direct and indirect related data corresponding to each business of the enterprise into the first intelligent model corresponding to the business of the enterprise, and predict multiple adjustment strategies for each device.

[0071] In some embodiments, artificial intelligence model platform A is specifically used to: cluster business data to obtain a first classification result; cluster monitoring data to obtain a second classification result; determine directly related data and indirectly related data based on the first classification result, the second classification result and a pre-set association table; wherein the association analysis table is used to represent the association relationship between each item of business data and each item of monitoring data.

[0072] In an embodiment of the present invention, the business data of an enterprise includes information on various aspects of the enterprise, such as sales data (sales, sales volume, customer distribution, etc.), production data (output, production efficiency, material consumption, etc.), financial data (income, cost, profit, etc.), etc. The purpose of clustering the business data of an enterprise is to group similar data points into one category so as to better understand the inherent structure and characteristics of the data. For example, products with similar sales trends can be grouped into one category, or production batches with similar production costs can be grouped into one category through clustering. After the clustering operation, a first classification result is obtained. This result can present different types of business data groups, each group having specific characteristics and patterns.

[0073] Monitoring data is the data of physical world devices collected from the IoT management and control platform, such as the operating status data of the equipment (temperature, pressure, speed, etc.), environmental data (humidity, temperature, air quality, etc.), etc. Similarly, clustering monitoring data is to group similar monitoring data points together. For example, the monitoring data of devices in similar operating states can be grouped together, or the monitoring data with similar environmental conditions can be grouped together. After clustering, the second classification result is obtained, which shows different types of monitoring data groups.

[0074] In the embodiment of the present invention, the pre-set association table is used to represent the association between each enterprise operation data and each monitoring data. This association table is established based on the business knowledge and experience of the enterprise, and it reflects the possible relationship between different types of data. For example, in a manufacturing enterprise, the temperature monitoring data of the production equipment may be associated with the quality data of the product, and the number of sales orders may be associated with the operating time of the production equipment.

[0075] According to the first classification results (clustering results of enterprise business data), the second classification results (clustering results of monitoring data) and the association relationship table, artificial intelligence model platform A can determine the directly related data and indirectly related data corresponding to each enterprise business. Directly related data is data that has an obvious and direct connection with a specific enterprise business. For example, for production business, the operating parameters of production equipment (such as temperature, pressure, etc.) are data directly related to production business. Indirectly related data is data that has a relatively indirect connection with the enterprise business. For example, the ambient temperature of the production workshop may not be a factor that directly affects the production process, but it may indirectly affect the production business by affecting the operating stability of the equipment, etc., so the ambient temperature data can be regarded as indirectly related data. The same is true for enterprise business data, which will not be described here.

[0076] In the embodiment of the present invention, the directly associated data and the indirectly associated data corresponding to each enterprise business are input into the first intelligent model corresponding to the enterprise business. The first intelligent model is a trained artificial intelligence model that can analyze and predict based on the input data.

[0077] Different enterprise businesses may require different first intelligence models because different businesses have different characteristics and needs. For example, the first intelligence model of the production business may focus on equipment parameter optimization and production process improvement, while the first intelligence model of the sales business may focus more on market trends and customer demand forecasting.

[0078] The first intelligent model is a model built based on artificial intelligence technology. Artificial intelligence technology covers a variety of algorithms such as machine learning and deep learning. For example, it may be built based on a neural network algorithm, which imitates the working method of neurons in the human brain and performs complex nonlinear transformations on input data through multiple hidden layers, so as to be able to handle complex enterprise data relationships. It may also adopt a decision tree algorithm to draw conclusions through layer-by-layer judgment of data features. The decision tree model can intuitively display the classification rules of data, which has certain advantages for the preliminary analysis and strategy formulation of enterprise business data.

[0079] First, in the process of building the intelligent model, a large amount of data related to the enterprise business needs to be collected as training samples. These data come from a wide range of sources, including enterprise operating data (such as sales records, cost data, inventory data, etc.) and monitoring data (such as equipment operating status data, environmental data, etc.). By analyzing and learning these data, the model can gradually grasp the inherent laws of the enterprise business.

[0080] The main function of the first intelligent model is to predict multiple adjustment strategies for each device based on the input association data. These adjustment strategies are designed to optimize various aspects of the enterprise's business. For example, in the production business, the adjustment strategy may include adjusting the parameters of the production equipment (such as adjusting the processing accuracy of the equipment, optimizing the running speed of the equipment, etc.), improving the production process (such as changing the order of production processes, adding quality inspection links, etc.), and optimizing resource allocation (such as reallocating the supply of raw materials, adjusting the allocation of human resources, etc.).

[0081] The model outputs multiple adjustment strategies because the optimization of an enterprise's business is often not solved by a single solution, and different adjustment strategies may have different risks and benefits. For example, one adjustment strategy may improve production efficiency in the short term, but may require higher costs; while another strategy may be lower in cost, but the effect may take a long time to show.

[0082] The output of these multiple strategies provides enterprises with a variety of options. Enterprises can choose the most suitable adjustment strategy according to their actual conditions (such as cost budget, time limit, market demand, etc.). At the same time, multiple strategies can also be referenced and compared with each other, so that enterprises can comprehensively evaluate the impact of different strategies on their business.

[0083] There may be errors in the above-mentioned data acquisition, data clustering, data integration, and first intelligent model prediction processes, which will lead to inaccurate final adjustment strategies. Therefore, the present invention performs simulations on the digital twin and big data platform D to select the optimal adjustment strategy.

[0084] The digital twin and big data platform D is used to build a digital mapping model of the physical world based on the data and business data of the IoT management and control platform, and based on the digital mapping model, digitally simulate the enterprise business according to a variety of pre-adjustment strategies to obtain the simulation results of each pre-adjustment strategy.

[0085] In an embodiment of the present invention, after collecting the IoT data of the IoT management and control platform and the business data of the unified login and business integration platform, the digital twin and big data platform D integrates and stores these data. Through unified data identification and data format specifications, data from different sources can be interrelated and integrated. Analyze the entity behavior patterns reflected in the IoT data and business data. For example, by analyzing the historical operation data of production equipment, determine its working mode during normal operation, periodic maintenance requirements and other behavioral characteristics. Based on data mining and machine learning technology, predictive modeling is performed on the behavior of entities. For example, use time series analysis methods to predict the future energy consumption trend of equipment, or use classification algorithms to predict whether equipment is about to fail.

[0086] At the same time, business processes involving the collaboration of multiple entities are modeled. In the logistics and distribution scenario, it is necessary to model the process of goods departing from the warehouse and going through a series of links such as transportation, sorting, and distribution, and to clarify the entities involved in each link (such as vehicles, warehouse staff, couriers, etc.) and the interaction processes between them. Combined with real-time data from the Internet of Things, the execution of business processes is dynamically monitored and analyzed to promptly identify bottlenecks and abnormal situations in the process. This completes the modeling process of the digital mapping model.

[0087] In some embodiments, the digital twin and big data platform D is used to: adjust the parameters of the digital mapping model according to each pre-adjustment strategy under the boundary conditions and initial conditions of the simulation of the digital twin and big data platform, and perform digital simulation to obtain the simulation results of each pre-adjustment strategy.

[0088] In the embodiment of the present invention, when the digital twin and big data platform are simulated, the boundary conditions and initial conditions are the basic settings of the simulation. The boundary conditions define the external limitations and constraints of the simulation system. For example, in the digital twin simulation of a production workshop, the boundary conditions may include the spatial size limit of the workshop, the maximum operating power limit of the equipment, etc. These boundary conditions ensure that the simulation is carried out within a reasonable range to avoid unrealistic results.

[0089] Initial conditions are the state settings of the system at the beginning of the simulation. For example, when simulating the production process of a new product, the initial conditions may include the initial quantity of raw materials, the initial state of the equipment, etc. The initial conditions determine the starting point of the simulation and have an important impact on the subsequent simulation results.

[0090] Digital twins and big data platforms achieve virtual reproduction of real physical systems by building a digital twin model of the physical world. This digital twin model can accurately reflect the various characteristics and behaviors of the physical system. For example, for a manufacturing plant, the digital twin model can include the layout of the plant, the geometry of the equipment, the operating parameters of the equipment, etc.

[0091] By adjusting the parameters of the digital twin model, different scenarios and situations can be simulated. For example, adjusting the running speed parameters of the equipment can simulate the performance of the equipment under different working conditions; adjusting the material flow parameters on the production line can simulate the production efficiency under different production tasks.

[0092] For each pre-adjustment strategy, the digital twin and big data platform will adjust the parameters of the digital twin model according to the requirements of the strategy. For example, if a pre-adjustment strategy is to improve the operating efficiency of production equipment, the platform may adjust the equipment's operating speed, processing accuracy and other parameters.

[0093] The adjustment of these parameters is based on the understanding and analysis of the pre-adjustment strategy. The platform needs to convert the pre-adjustment strategy into a specific parameter adjustment plan to ensure that the simulation can accurately reflect the effect of the strategy.

[0094] After adjusting the parameters, the digital twin and big data platform conduct digital simulation. This simulation process is a virtual reproduction of the operation of the physical system under the pre-adjustment strategy. Through simulation, the performance of the physical system after implementing the pre-adjustment strategy, possible problems, and the impact on the entire enterprise business can be predicted. For example, in the simulated production process, changes in indicators such as product output, quality, and production cycle can be observed; in the simulated logistics system, changes in the transportation time of goods, inventory levels, etc. can be seen.

[0095] After digital simulation, the digital twin and big data platform obtain the simulation results of each pre-adjustment strategy. These simulation results are a quantitative evaluation of the effect of the pre-adjustment strategy, which can provide an important basis for enterprise decision-making. The simulation results may include various indicators and data, such as the percentage of increase in production efficiency, the extent of cost reduction, and the change in equipment failure rate. Enterprises can compare different pre-adjustment strategies based on these results and select the most suitable strategy for implementation.

[0096] In some embodiments, the digital model includes at least one of the following: a geometric model, a physical property model, a behavior model, and an environment model.

[0097] In an embodiment of the present invention, the geometric model is one of the basic components of the digital model. It mainly describes the geometric shape and spatial layout of the physical system. For example, for a digital twin model of a factory, the geometric model may include the building structure of the factory, the dimensions of the equipment, the layout of the production line, etc. The geometric model can help enterprises intuitively understand the spatial relationship of the physical system and provide a reference for the installation and layout optimization of the equipment. At the same time, the geometric model also provides a basic framework for the construction of other models.

[0098] The physical property model describes the physical properties of a physical system, such as mass, density, hardness, elasticity, etc. For production equipment, the physical property model can include the mechanical properties, electrical properties, thermal properties, etc. of the equipment. The physical property model can help companies predict the performance of equipment under different working conditions, such as wear and thermal deformation of the equipment. By simulating physical properties, companies can optimize the design and operating parameters of the equipment and improve the reliability and life of the equipment.

[0099] Behavioral models describe the behavior and dynamic characteristics of physical systems. For example, for production equipment, behavioral models can include the start, stop, and state changes of the equipment during operation. For logistics systems, behavioral models can include the transportation path, transportation speed, inventory changes, etc. of goods. Behavioral models can help companies predict the behavioral responses of physical systems in different situations and provide support for corporate decision-making. For example, companies can use behavioral models to predict the impact of equipment failures on production and develop emergency plans in advance; or use behavioral models to optimize logistics distribution routes and improve logistics efficiency.

[0100] Environmental models describe the environmental conditions in which a physical system is located. For example, for a production workshop, the environmental model may include environmental factors such as temperature, humidity, and air quality. For outdoor equipment, the environmental model may include factors such as weather conditions and topography. Environmental models can help companies understand the impact of environmental factors on physical systems and provide a reference for equipment operation and maintenance. For example, companies can adjust the operating parameters of equipment based on environmental models to adapt to different environmental conditions; or use environmental models to predict the impact of environmental changes on equipment performance and take protective measures in advance.

[0101] Artificial intelligence model platform A is also used to determine the target adjustment strategy based on multiple pre-adjustment strategies, simulation results of each pre-adjustment strategy and the second intelligent model.

[0102] In some embodiments, the artificial intelligence model platform A is specifically used to: evaluate the simulation results of each pre-adjustment strategy according to the second intelligent model to obtain the evaluation results of each pre-adjustment strategy; and determine the target adjustment strategy from multiple pre-adjustment strategies based on the evaluation results.

[0103] In an embodiment of the present invention, the second intelligent model may be constructed based on a variety of artificial intelligence technologies. For example, it may be a model based on a neural network, such as a multi-layer perceptron (MLP). MLP consists of an input layer, multiple hidden layers, and an output layer. The input layer receives an evaluation feature vector, and each neuron corresponds to the value of an evaluation index. The hidden layer performs a nonlinear transformation on the input data through the connection weights between neurons to learn the complex relationship between the evaluation indicators. The output layer outputs the evaluation result based on the processing result of the hidden layer. It may also be a support vector machine model. The support vector machine model divides data of different categories by finding a hyperplane (if the evaluation result is in classification form), or constructs a regression function (if the evaluation result is in numerical form). The support vector machine model has good performance when processing small samples and high-dimensional data, and can find the optimal classification or regression boundary in limited data.

[0104] The construction of the second intelligent model requires a large amount of data as a basis. These data include the simulation results of different pre-adjustment strategies in history and the corresponding actual business effect data. For example, in the past, the company implemented various equipment adjustment strategies, and recorded the evaluation index values ​​such as the production efficiency improvement and cost reduction percentage of these strategies in the simulation stage, as well as the actual business results after actual implementation (such as actual profit growth, market share changes, etc.).

[0105] The evaluation result is in numerical form. The numerical value output by the model represents the comprehensive score of the pre-adjustment strategy. This score is based on the model's comprehensive evaluation of each evaluation indicator in the evaluation feature vector and their interrelationships. For example, a pre-adjustment strategy with a higher score indicates better performance in multiple business aspects (such as production, cost, quality, etc.) and higher comprehensive benefits.

[0106] In some embodiments, the artificial intelligence model platform A is specifically used to: extract corresponding indicator values ​​from the simulation results of each pre-adjustment strategy according to multiple evaluation indicators to form an evaluation feature vector; input the evaluation feature vector into the second intelligent model to obtain the evaluation results of each pre-adjustment strategy.

[0107] In the embodiment of the present invention, in the process of determining the target adjustment strategy, the artificial intelligence model platform A first uses the second intelligent model to evaluate the simulation results of each pre-adjustment strategy, and after obtaining the evaluation results, the target adjustment strategy is determined from the multiple pre-adjustment strategies based on these results. The specific implementation is divided into two main steps: extracting the evaluation index value to form an evaluation feature vector and inputting it into the second intelligent model to obtain the evaluation result.

[0108] First, it is necessary to determine multiple evaluation indicators that can comprehensively measure the effectiveness of the pre-adjustment strategy. These indicators can be determined based on the specific business needs and goals of the enterprise. For example, in a manufacturing enterprise, the evaluation indicators may include the increase in production efficiency, the percentage of cost reduction, the level of product quality improvement, the percentage of equipment failure rate reduction, etc. For a logistics enterprise, the evaluation indicators may include the percentage of transportation time reduction, the increase in inventory turnover rate, the distribution accuracy, etc. These evaluation indicators should cover all key aspects of the enterprise's operations to ensure that the evaluation of the pre-adjustment strategy is comprehensive and accurate.

[0109] For each simulation result of the pre-adjustment strategy, the corresponding index value is extracted according to the determined multiple evaluation indicators. For example, for a simulation result of a pre-adjustment strategy, if the performance of the strategy in terms of production efficiency is to increase the production efficiency of a production line from 1,000 pieces per day to 1,200 pieces per day, then according to the evaluation indicator of the increase in production efficiency, the index value of the strategy in terms of production efficiency can be calculated to be 20%.

[0110] This extraction operation is performed for each evaluation indicator, so that a set of corresponding indicator values ​​are obtained from the simulation results of each pre-adjustment strategy. The indicator values ​​of each extracted evaluation indicator are combined in a certain order to form an evaluation feature vector. For example, if there are three evaluation indicators: the increase in production efficiency, the percentage of cost reduction, and the level of product quality improvement, for a certain pre-adjustment strategy, the extracted indicator values ​​are 20%, 15%, and 1 respectively, then the composed evaluation feature vector can be expressed as [20%, 15%, 1].

[0111] The second intelligent model is a trained model that can evaluate the pre-adjustment strategy. It can give the evaluation result of the pre-adjustment strategy based on the input evaluation feature vector and the relationship between various evaluation indicators. For example, the second intelligent model can judge the pros and cons of the pre-adjustment strategy corresponding to the new evaluation feature vector by learning the strategy effects under different evaluation indicator combinations in historical data.

[0112] A threshold can be set to select pre-adjustment strategies with evaluation results higher than the threshold as candidate strategies. For example, if the comprehensive score is greater than or equal to 80 points, then all pre-adjustment strategies with a comprehensive score of 80 points or more will be included in the candidate range.

[0113] Further comprehensive consideration is given to the selected candidate pre-adjustment strategies to determine the final target adjustment strategy. This can be done in combination with the actual situation of the enterprise and specific decision-making needs. For example, if the enterprise currently has a more urgent need for cost control, then the strategy with the highest cost reduction percentage can be selected as the target adjustment strategy among the candidate strategies; if the enterprise pays more attention to long-term development and product quality improvement, then a strategy with a higher level of product quality improvement and other indicators that are relatively balanced can be selected as the target adjustment strategy. Through the above steps, artificial intelligence model platform A can use multiple pre-adjustment strategies, the simulation results of each pre-adjustment strategy, and the second intelligent model to accurately determine the target adjustment strategy that best suits the enterprise.

[0114] Figure 2 : is a flowchart of the implementation of the method for digital transformation and upgrading of organizations based on A-DFCT technology provided by an embodiment of the present invention. Figure 2 As shown in the figure, the digital transformation and upgrading method of organizations based on A-DFCT technology includes:

[0115] S210, the IoT management and control platform collects data from devices in the physical world to obtain monitoring data;

[0116] S220, a unified login and business integration platform integrates various business systems of the enterprise to obtain business operation data;

[0117] S230, the artificial intelligence model platform predicts multiple pre-adjustment strategies for the enterprise business based on the enterprise operation data, monitoring data and the first intelligent model;

[0118] S240, the digital twin and big data platform builds a digital mapping model of the physical world based on the data and business data of the IoT management and control platform, and digitally simulates the enterprise business according to multiple pre-adjustment strategies based on the digital mapping model to obtain simulation results for each pre-adjustment strategy;

[0119] S250, the artificial intelligence model platform determines the target adjustment strategy based on multiple pre-adjustment strategies, the simulation results of each pre-adjustment strategy and the second intelligent model.

[0120] In summary, the beneficial effects of the present invention are specifically as follows:

[0121] 1. Multi-dimensional data fusion and intelligent analysis: The A-DFCT architecture integrates the three major platforms of D, F, and C to achieve comprehensive collection and fusion of multi-dimensional data, and uses AI technology to deeply mine and analyze data to provide organizations with accurate business insights and decision-making support.

[0122] 2. Efficient business collaboration and process optimization: Through unified login and business integration, the F platform breaks down information silos and promotes cross-departmental and cross-system business collaboration. At the same time, based on data analysis results, it can automatically optimize business processes and improve operational efficiency.

[0123] 3. Real-time monitoring and predictive maintenance: The D platform combines AI technology to monitor the operating status of the physical system in real time and perform predictive maintenance, effectively reducing the occurrence of failures and reducing maintenance costs.

[0124] 4. Green, low-carbon and sustainable development: By optimizing resource allocation and improving energy utilization efficiency, the A-DFCT architecture helps organizations achieve green and low-carbon development, which is in line with the current global trend of sustainable development.

[0125] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0126] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0127] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0128] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0129] In the embodiments provided by the present invention, it should be understood that the disclosed devices / controllers and methods can be implemented in other ways. For example, the device / controller embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0132] If the integrated module / unit is implemented in the form of 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 present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0133] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An organizational digital transformation and upgrading system based on A-DFCT technology, characterized in that: include: Artificial intelligence model platform, digital twin and big data platform, unified login and business integration platform, and Internet of Things management and control platform; The IoT management and control platform is used to collect data from devices in the physical world and obtain monitoring data; The unified login and business integration platform is used to integrate various business systems of the enterprise to obtain business operation data; The artificial intelligence model platform is used to predict multiple pre-adjustment strategies for the enterprise business based on the enterprise operation data, the monitoring data and the first intelligent model; The digital twin and big data platform is used to build a digital mapping model of the physical world based on the data of the Internet of Things management and control platform, and based on the digital mapping model, digitally simulate the enterprise business according to the multiple pre-adjustment strategies to obtain the simulation results of each pre-adjustment strategy; The artificial intelligence model platform is also used to determine the target adjustment strategy based on the multiple pre-adjustment strategies, the simulation results of each pre-adjustment strategy and the second intelligent model.

2. The digital transformation and upgrading system for organizations based on A-DFCT technology according to claim 1 is characterized in that: The artificial intelligence model platform is used to: Clustering the enterprise operation data and the monitoring data to determine directly related data and indirectly related data corresponding to each enterprise business; The directly associated data and the indirectly associated data corresponding to each enterprise business are input into the first intelligent model corresponding to the enterprise business to predict multiple adjustment strategies for each device.

3. The digital transformation and upgrading system for organizations based on A-DFCT technology according to claim 2 is characterized in that: The artificial intelligence model platform is specifically used for: Clustering the business operation data to obtain a first classification result; Clustering the monitoring data to obtain a second classification result; According to the first classification result, the second classification result and a preset association relationship table, directly associated data and indirectly associated data are determined; wherein the association relationship table is used to represent the association relationship between each enterprise operating data and each monitoring data.

4. The digital transformation and upgrading system for organizations based on A-DFCT technology according to claim 1 is characterized in that: The digital twin and big data platform is used to: Under the boundary conditions and initial conditions of the simulation of the digital twin and the big data platform, the parameters of the digital mapping model are adjusted according to each pre-adjustment strategy, and digital simulation is performed to obtain the simulation results of each pre-adjustment strategy.

5. The digital transformation and upgrading system for organizations based on A-DFCT technology according to claim 4 is characterized in that: The digital mapping model includes at least one of the following: a geometric model, a physical property model, a behavior model, and an environment model.

6. The organizational digital transformation and upgrading system based on A-DFCT technology according to claim 1 is characterized in that: The artificial intelligence model platform is specifically used for: Evaluate the simulation results of each pre-adjustment strategy according to the second intelligent model to obtain an evaluation result of each pre-adjustment strategy; According to the evaluation result, a target adjustment strategy is determined from the multiple pre-adjustment strategies.

7. The organizational digital transformation and upgrading system based on A-DFCT technology according to claim 6 is characterized in that: The artificial intelligence model platform is specifically used for: According to multiple evaluation indicators, corresponding indicator values ​​are extracted from the simulation results of each pre-adjustment strategy to form an evaluation feature vector; The evaluation feature vector is input into the second intelligent model to obtain the evaluation result of each pre-adjustment strategy.

8. The digital transformation and upgrading system for organizations based on A-DFCT technology according to claim 1 is characterized in that: The unified login and business integration platform is used for: Obtain the database structure of each business system of the enterprise, and determine the integration algorithm corresponding to each business system based on the database structure; According to the integration algorithms corresponding to each business system, the databases of each business system are integrated to obtain the enterprise operating data.

9. The digital transformation and upgrading system for organizations based on A-DFCT technology according to claim 8 is characterized in that: The integration algorithm includes at least one of the following: a data matching algorithm, a data fusion algorithm, a data deduplication algorithm, a data conversion algorithm, and a data evaluation algorithm.

10. A method for digital transformation and upgrading of an organization based on A-DFCT technology, characterized in that: An organization digital transformation and upgrading system based on A-DFCT technology applied to any one of claims 1 to 9 above; the method comprises: The IoT management and control platform collects data from devices in the physical world to obtain monitoring data; The unified login and business integration platform integrates various business systems of the enterprise to obtain the enterprise's business data; The artificial intelligence model platform predicts multiple pre-adjustment strategies for the enterprise's business based on the enterprise's operating data, the monitoring data and the first intelligent model; The digital twin and big data platform constructs a digital mapping model of the physical world based on the data of the Internet of Things management and control platform, and based on the digital mapping model, digitally simulates the enterprise business according to the multiple pre-adjustment strategies to obtain the simulation results of each pre-adjustment strategy; The artificial intelligence model platform determines the target adjustment strategy based on the multiple pre-adjustment strategies, the simulation results of each pre-adjustment strategy and the second intelligent model.

Images