Intelligent decision-making method and system based on digital benefit evaluation

Abstract

The present application provides an intelligent decision-making method and system based on digital benefit evaluation, which relates to the field of data mining technology. The method includes: interconnecting data islands, determining a digital topology network, and then establishing a channel connection between a data port and a third-party platform, and then reading pre-decision tasks, traversing the data topology network and determining that the data system integrates data and transmits it to a third-party platform, screening decision-influencing characteristic values, and then performing single evaluation and collaborative evaluation on the task source data, determining the target decision plan, and then real-time tracking and monitoring and making deviation decisions, returning trend deviation data, and finally performing calibration compensation, determining compensation plans and updating. The present application mainly solves the problems of poor data association and integration in existing methods, the problem of data islands, the lack of real-time program execution monitoring, and the inability to detect decision deviations in a timely manner. Through intelligent decision support and timely calibration compensation, the quality of decision-making is improved, and the scientificity and objectivity of decision-making are enhanced.

Description

Technical Field

[0001] The present application relates to the field of data mining technology, and specifically to an intelligent decision-making method and system based on digital benefit evaluation. Background Art

[0002] With the advent of the digital age, data has become an important basis for corporate decision-making. Traditional decision-making methods are often based on experience and intuition, and are difficult to cope with complex and changing market environments. In an era of low productivity and simple social activities, due to the limitations of leaders' personal experience and wisdom, they mainly rely on their personal experience, experience, knowledge and thinking to make decisions. This decision-making method is feasible in an era of low social productivity and simple social activities. However, with the development of society and the advancement of science and technology, the decision-making environment has become more and more complex, and decision-making problems have become more and more diverse. The limitations of traditional decision-making methods have gradually emerged. It lacks scientificity and systematicness, and mainly makes decisions based on experience and intuition.

[0003] However, in the process of implementing the technical solution of the invention in the embodiment of the present application, it is found that the above technology has at least the following technical problems:

[0004] The existing methods have poor data association and integration issues, resulting in data silos, lack of real-time program execution monitoring, and inability to detect decision deviations in a timely manner. Summary of the invention

[0005] This application mainly solves the problems of poor data association and integration in existing methods, the occurrence of data island problems, the lack of real-time program execution monitoring, and the inability to detect decision deviations in a timely manner.

[0006] In view of the above problems, the present application provides an intelligent decision-making method and system based on digital benefit evaluation. In the first aspect, the present application provides an intelligent decision-making method based on digital benefit evaluation, the method comprising: performing correlation assessment on multiple data systems, interconnecting data islands, and determining a digital topology network; based on the digital topology network, establishing a channel connection between each data port and a third-party platform, wherein the third-party platform is provided with an intelligent decision-making model; reading pre-decision tasks, traversing the digital topology network to determine the target data system, integrating task source data and transmitting it to the third-party platform; reading market driving factors and quantitative variables, and screening decision-influencing characteristic values; based on the intelligent decision-making model of the third-party platform, combined with the decision-influencing characteristic values, performing single evaluation and collaborative evaluation on the task source data, determining data evaluation results and making intelligent decisions, and determining a target decision plan; delegating the execution of the target decision plan, tracking and monitoring in real time and making deviation decisions, and returning trend deviation data; combined with the intelligent decision-making model, performing calibration compensation based on the trend deviation data on the target decision plan, determining and updating the scenario decision compensation plan.

[0007] In the second aspect, the present application provides an intelligent decision-making system based on digital benefit evaluation, the system comprising: a digital topology network determination module, the digital topology network determination module is used to perform correlation assessment on multiple data systems, interconnect data islands, and determine the digital topology network; a channel connection establishment module, the channel connection establishment module is based on the digital topology network, and establishes a channel connection between each data port and a third-party platform, wherein the third-party platform is equipped with an intelligent decision-making model; a data transmission module, the data transmission module is used to read pre-decision tasks, traverse the digital topology network to determine the target data system, integrate task source data and transmit it to the third-party platform; an impact feature value screening module, the impact feature value screening module is used to read market drivers dynamic factors and quantitative variables, screening decision-influencing characteristic values; target decision-making solution determination module, the target decision-making solution determination module is based on the intelligent decision-making model of the third-party platform, combined with the decision-influencing characteristic values, performs single evaluation and collaborative evaluation on the task source data, determines the data evaluation results and makes intelligent decisions, and determines the target decision solution; deviation data feedback module, the deviation data feedback module is used to delegate the execution of the target decision solution, track and monitor in real time and make deviation decisions, and return trend deviation data; data calibration compensation module, the data calibration compensation module is used to combine the intelligent decision-making model to perform calibration compensation based on the trend deviation data on the target decision solution, determine the scenario decision compensation solution and update it.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The present application provides an intelligent decision-making method and system based on digital benefit evaluation, which relates to the field of data mining technology. The method includes: interconnecting data islands, determining a digital topology network, and then establishing a channel connection between a data port and a third-party platform, and then reading pre-decision tasks, traversing the data topology network and determining that the data system integrates data and transmits it to the third-party platform, screening decision-influencing characteristic values, and then performing single evaluation and collaborative evaluation on the task source data, determining the target decision plan, and then real-time tracking and monitoring and making deviation decisions, returning trend deviation data, and finally performing calibration compensation, determining the compensation plan and updating it.

[0010] This application mainly solves the existing problems of poor data association and integration, data island problems, lack of real-time program execution monitoring, and failure to timely detect decision deviations. Through intelligent decision support and timely calibration compensation, the quality of decision-making is improved and the scientificity and objectivity of decision-making are enhanced.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 A flowchart of an intelligent decision-making method based on digital benefit evaluation is provided for the embodiment of the present application;

[0014] Figure 2 A schematic flow chart of a method for determining adjusted task source data in an intelligent decision-making method based on digital benefit evaluation is provided for an embodiment of the present application;

[0015] Figure 3 A schematic flow chart of a method for acquiring trend deviation data in an intelligent decision-making method based on digital benefit evaluation is provided for an embodiment of the present application;

[0016] Figure 4 A structural diagram of an intelligent decision-making system based on digital benefit evaluation is provided for an embodiment of the present application.

[0017] Explanation of the reference numerals: digital topology network determination module 10 , channel connection establishment module 20 , data transmission module 30 , influencing characteristic value screening module 40 , target decision scheme determination module 50 , deviation data feedback module 60 , data calibration compensation module 70 . DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] This application mainly solves the existing problems of poor data association and integration, data island problems, lack of real-time program execution monitoring, and failure to timely detect decision deviations. Through intelligent decision support and timely calibration compensation, the quality of decision-making is improved and the scientificity and objectivity of decision-making are enhanced.

[0020] In order to better understand the above technical solution, the above solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods:

[0021] Embodiment 1

[0022] like Figure 1 The intelligent decision-making method based on digital benefit evaluation is shown, and the method comprises:

[0023] Assess the correlation of multiple data systems, interconnect data islands, and determine the digital topology network;

[0024] Specifically, first, collect data from each data system. It can be collected from databases, data warehouses, cloud computing platforms, etc. After collecting the data, clean and integrate the data. Including processing missing values, outliers, duplicate values, etc., by analyzing the internal connections and laws of the data, the correlation between the data can be discovered. Analyze through association rule mining, cluster analysis, correlation analysis, etc. According to the results of data association analysis, data islands can be classified. Different categories of data islands can represent different data sets or data subsets. According to the classification and correlation of data islands, a digital topological network can be constructed. The digital topological network can represent the logical relationship and topological structure between data, and interconnect various data islands by establishing appropriate connections and channels. This can be achieved through data integration, data exchange, etc., so that data can be exchanged and shared between different data islands.

[0025] Based on the digital topology network, establishing a channel connection between each data port and a third-party platform, wherein the third-party platform is equipped with an intelligent decision-making model;

[0026] Specifically, define the data ports in the digital topology network, including databases, API interfaces, data files, etc. Identify the type, format, access rights, and other information of each data port. According to business needs and goals, select appropriate third-party platforms that should have the integration capabilities of intelligent decision-making models. Establish connections with third-party platforms to ensure the interoperability of data ports. Design appropriate channel connection methods based on the characteristics of data ports and third-party platforms. This can include API docking, data file transfer, database links, etc. When establishing channels, ensure the efficiency, security, and stability of data transmission. On the third-party platform, integrate the intelligent decision-making model. Include steps such as model deployment, configuration, and optimization to ensure that the model can operate normally and provide accurate decision support. Through the established channel connection, obtain data from each data port for use by the intelligent decision-making model. The model uses this data for training and optimization to improve the accuracy and effectiveness of decision-making. Establish a monitoring mechanism to monitor the channel connection and the operating status of the intelligent decision-making model in real time. Make necessary adjustments and optimizations based on the monitoring results to ensure the stability and performance of the entire system. Assume that an enterprise wants to optimize its sales strategy through an intelligent decision-making model. The enterprise has multiple data ports, including sales databases, market research data, etc. The company chose to cooperate with a third-party platform, which has an advanced intelligent decision-making model. The company established a connection with the third-party platform through the API interface, and transferred sales data and market research data to the intelligent decision-making model of the third-party platform for training and optimization. At the same time, the third-party platform also provided some other relevant market information and data analysis tools to help the company better understand and apply these data. Through continuous data interaction and model optimization, the company's sales strategy has been significantly improved, achieving better business results.

[0027] Read the pre-decision task, traverse the digital topology network to determine the target data system, integrate the task source data and transmit it to the third-party platform;

[0028] Specifically, read the pre-decision task from the task management system. Including detailed information such as task description, objectives, requirements, etc. According to the needs of the pre-decision task, determine the target data system related to the task by traversing the digital topological network. This may involve the identification and selection of multiple data islands. Based on the association relationship and topological structure of the digital topological network, select the target data system that is most suitable for completing the task. Extract the source data related to the pre-decision task from the target data system. Including cleaning, screening, conversion and other processing of the data to ensure the accuracy and completeness of the data. Transmit the integrated task source data to the third-party platform through an appropriate channel connection. This is achieved through an API interface, file transfer protocol or other data transmission methods. Ensure the security and stability of data transmission.

[0029] Read market drivers and quantitative variables, and filter decision-making impact feature values;

[0030] Specifically, market-related data, including market trends, competitor situations, customer needs, etc., are read from the digital topology network. By analyzing the collected data, the main driving factors that affect market changes are identified. Including economic, technological, policy and other aspects. The identified market drivers are quantified and qualitative market information is converted into measurable values. For example, market trends are divided into different states such as growth, stability, and decline, and corresponding values ​​are assigned to each state. According to the needs and goals of the decision, the eigenvalues ​​that have a significant impact on the decision are screened out. This can be achieved by analyzing the correlation between the eigenvalues ​​and the decision results. The eigenvalues ​​that are highly correlated with the decision results are retained, and the eigenvalues ​​that are irrelevant or have little impact are removed. For the screened eigenvalues, necessary processing is performed, such as normalization, standardization or conversion, to ensure that they are on the same magnitude.

[0031] Based on the intelligent decision-making model of the third-party platform and in combination with the decision-influencing characteristic value, the task source data is evaluated individually and collaboratively, the data evaluation results are determined, and intelligent decisions are made to determine the target decision-making plan;

[0032] Specifically, the task source data is preprocessed and cleaned to ensure the accuracy and completeness of the data. Missing values, outliers, etc. are processed, and each eigenvalue is evaluated separately based on the selected decision-influencing eigenvalues. Including calculating the weight, correlation, contribution and other indicators of each eigenvalue to understand the degree of influence of each eigenvalue on the decision. In addition to the single evaluation, collaborative evaluation is also required. Collaborative evaluation takes into account the interaction and relationship between eigenvalues, and comprehensively evaluates their impact on the decision by analyzing the correlation and synergy between eigenvalues. According to the results of single evaluation and collaborative evaluation, the data evaluation results of each eigenvalue are determined. This can be a specific value, ranking or priority, indicating the importance and influence of the eigenvalue in the decision. Based on the data evaluation results and the intelligent decision-making model, intelligent decision-making is made. Using the analysis and prediction capabilities of the model, the evaluation results of all eigenvalues ​​are comprehensively considered to formulate the optimal decision-making plan. According to the results of intelligent decision-making, the target decision-making plan is determined. The target decision-making plan should be based on the comprehensive consideration of data evaluation results and model predictions, and can maximize the decision effect and business goals.

[0033] Decentralize the execution of the target decision plan, track and monitor in real time, make deviation decisions, and report back trend deviation data;

[0034] Specifically, the determined target decision-making plan will be delegated to the relevant departments or execution teams. Ensure the clear communication and accurate understanding of the decision-making plan, and establish a real-time tracking and monitoring mechanism during the execution of the decision-making plan. Collect the execution data and effect feedback of the plan in real time through data monitoring, indicator tracking, etc. Based on the tracking and monitoring data, determine whether the execution of the decision-making plan has deviated. For any deviation found, promptly report the trend deviation data. Feedback this data to decision makers and relevant teams so that necessary adjustments and interventions can be made.

[0035] In combination with the intelligent decision model, calibration compensation based on the trend deviation data is performed on the target decision solution, and a scenario decision compensation solution is determined and updated.

[0036] Specifically, in combination with the intelligent decision-making model, the target decision-making scheme is calibrated and compensated based on the trend deviation data, and the scenario decision compensation scheme is determined and updated. First, according to the trend deviation data transmitted back, the difference between the actual execution and the target decision scheme is analyzed to determine the areas and aspects that need calibration compensation. The trend deviation data is deeply analyzed using the intelligent decision-making model. The model can formulate a scenario decision compensation scheme based on historical data, market trends and other relevant factors, the analysis results of the intelligent decision-making model and actual business needs. Including measures such as adjusting goals, optimizing execution strategies, and supplementing resources. Integrate the scenario decision compensation scheme with the original target decision scheme to form an updated decision scheme. Ensure that the updated scheme can better adapt to the actual situation and improve the accuracy and effectiveness of the decision. Decentralize the updated decision scheme to the relevant departments or execution team to ensure the smooth implementation of the scheme. At the same time, continue to conduct real-time tracking and monitoring to ensure that the implementation effect of the scheme is consistent with the expected goals.

[0037] Furthermore, in the present invention, the correlation assessment of multiple data systems and interconnection of data islands include:

[0038] Based on the system correlation, the multiple data systems are associated and identified to determine the first interconnection layer;

[0039] Based on the data correlation, the multiple data systems are associated and identified to determine the second interconnection layer, wherein the data correlation evaluation criteria at least include sequential impact correlation and same-frequency impact correlation;

[0040] The first interconnection layer and the second interconnection layer are integrated to generate the digital topology network.

[0041] Specifically, collect relevant information about multiple data systems, including their connections, interactions, and data transmission. This can be done by using web crawlers, obtaining data from enterprise resource planning (ERP) systems, or directly from administrators or owners of data systems. After the data is collected, use system correlation analysis tools or algorithms to analyze the correlation between these data systems. This includes using methods such as graph theory, complex network analysis, or dependency analysis to determine dependencies between systems, common functional areas, or business processes. For example, system correlation can be evaluated by analyzing the frequency of communication between data systems, the frequency and amount of data sharing, or their roles and positions in business processes. Based on the results of the system correlation analysis, multiple data systems are associated and identified. This is achieved by creating a relationship matrix or network diagram between systems, where each node represents a data system and each edge represents the correlation or connection between them. Data systems with strong system correlation will be classified as the first interconnected layer. Then consider the logical relationship, time series relationship, or other related factors between the data. For example, if the change trends of two data systems are consistent in time, or the changes in one data system can predict the changes in another data system, then there is data correlation between them. Develop data relevance assessment criteria that include at least sequential impact association and co-frequency impact association. Sequential impact association refers to the association relationship between data that occurs in a certain order, such as cause and effect. This can be determined by analyzing the order of time series data or events. Co-frequency impact association refers to the association relationship between data that occurs within the same frequency or period. This can be evaluated by analyzing the periodic changes or frequency distribution of the data. According to the data relevance assessment criteria, multiple data systems are associated and identified. Create a relationship matrix or network diagram between data, where each node represents a data system and each edge represents the data correlation between them. Data systems with strong data correlation will be classified as the second interconnection layer. Merge the data systems identified in the first and second interconnection layers. Consider both system correlation and data correlation, and analyze the overall correlation relationship between each data system. This is achieved by merging the network structure of the two levels to form a more comprehensive digital topology network model. The digital topology network will show the hierarchical structure and connection relationship between each data system. It can be implemented using different visualization tools or software as needed, such as using network visualization software packages or graphics libraries to create interactive digital topology network diagrams. This network model can be used for further data processing, analysis, and decision support applications. For example, it can be used to identify key data systems, discover potential data flow paths, predict future trends in data, and develop optimization strategies or measures for specific data.

[0042] Furthermore, if Figure 2As shown, the present invention, after integrating the task source data, includes:

[0043] Performing data sensitivity analysis on the task source data and marking multi-level sensitive data groups;

[0044] For the multi-level sensitive data group, matching the data encryption method with the key database and performing sensitive data processing to determine the encrypted sensitive data;

[0045] Based on the encrypted sensitive data, the multi-level sensitive data group is replaced to determine the adjusted task source data.

[0046] Specifically, data sensitivity analysis is performed on the task source data. Data sensitivity analysis refers to the process of evaluating the importance and sensitivity of data to determine which data requires additional protection measures. Detailed information on the task source data is collected, including the type, content, purpose, and storage method of the data. Then, a data sensitivity analysis tool or algorithm is used to evaluate the sensitivity of these data. Factors such as data confidentiality, integrity, availability, and traceability are included. According to the results of the data sensitivity analysis, multi-level sensitive data groups are marked. These data groups may include highly sensitive data, medium sensitive data, and low sensitive data. Each sensitive data group will be marked and classified accordingly according to its sensitivity. For the multi-level sensitive data groups, the data encryption method is matched in combination with the key database and sensitive data processing is performed to determine the encrypted sensitive data; the marked multi-level sensitive data groups are processed. The appropriate encryption method is determined in combination with the key database to protect these sensitive data. The key database will contain key information for encryption and decryption. Sensitive data that needs to be encrypted is screened out from the multi-level sensitive data groups. These data may include highly sensitive data, data involving personal privacy or commercial secrets, etc. For each sensitive data group, select the appropriate encryption algorithm and key based on its sensitivity and encryption requirements. Use the encrypted sensitive data to replace the corresponding part in the original task source data. This is achieved by directly replacing or using the encrypted value to ensure that the original sensitive data is protected and hidden. By replacing the encrypted sensitive data in the multi-level sensitive data group, the adjusted task source data can be generated. These adjusted data will contain sensitive information after encryption while maintaining the integrity and availability of the data.

[0047] Furthermore, the present invention, before performing single evaluation and collaborative evaluation on the task source data, includes:

[0048] Identify the data volume of the task source data and determine whether the processing time limit constraint is met;

[0049] If not, balance the data value and processing efficiency and determine the preprocessing standard based on the data volume;

[0050] Based on the preprocessing standard, effective data information is extracted and normalized for the task source data to determine the preprocessed source data.

[0051] Specifically, information such as the total amount, data type, and structure of the task source data is collected. Then, whether the data volume meets the processing time limit constraint is evaluated. This is done by comparing the data volume with the available processing resources (such as computing power, storage capacity, etc.). If the data volume does not meet the processing time limit constraint, there will be a trade-off between data value and processing efficiency. Data value refers to the importance of data and the degree of contribution to business goals. Processing efficiency refers to the speed and effect of completing data processing while meeting the time limit constraint. In order to balance data value and processing efficiency, preprocessing standards will be determined based on data volume. Preprocessing standards may include operations such as screening, dimensionality reduction, compression, or approximate processing of data to reduce the amount of data and optimize processing efficiency. Based on the preprocessing standards, effective data information extraction and normalization processing are performed on the task source data. Effective data information extraction refers to extracting valuable information from the original data for subsequent processing and analysis. Normalization processing refers to standardizing the data so that it is on the same scale for comparison and analysis. Through effective data information extraction and normalization processing, the preprocessing source data can be determined. The preprocessed source data will contain valid data information that has been screened, standardized and organized for subsequent processing and analysis.

[0052] Furthermore, the present invention performs single evaluation and collaborative evaluation on the task source data, including:

[0053] Wherein, the intelligent decision-making model includes a data evaluation layer and a decision analysis layer;

[0054] Based on the data evaluation layer, the pre-processed source data is identified, and a single data evaluation is performed based on the belonging data system to determine the single evaluation result;

[0055] Identifying a data association identifier based on the digital topology network, performing data collaborative evaluation based on the data relevance evaluation criteria, and determining a collaborative evaluation result;

[0056] The single evaluation result and the collaborative evaluation result are added to the data evaluation result.

[0057] Specifically, the intelligent decision-making model includes a data evaluation layer and a decision analysis layer. The data evaluation layer is responsible for evaluating the preprocessed source data, while the decision analysis layer makes task decisions based on the data evaluation results. In the data evaluation layer, the preprocessed source data must first be identified. These data may come from different data systems or sources. Based on the benchmark of the data system, each data item is individually evaluated. The individual evaluation can include aspects such as integrity check, accuracy verification, and compliance check. Through the individual evaluation, the quality and reliability of each data item can be determined, and the corresponding individual evaluation results can be obtained. These results will provide basic data for subsequent decision analysis. In the data evaluation layer, data collaborative evaluation is also required. By identifying data association identifiers based on digital topological networks, the correlation and mutual influence between different data items can be analyzed. Based on the data relevance assessment criteria, the collaborative relationship between multiple data items is evaluated. Collaborative evaluation focuses on the correlation and consistency between different data items. Through collaborative evaluation, the overall quality and reliability of the data can be further understood, and the corresponding collaborative evaluation results can be obtained. These results will provide more comprehensive data support for decision analysis. After completing the single evaluation and collaborative evaluation, the single evaluation results and the collaborative evaluation results are combined into a comprehensive data evaluation result. This result will fully reflect the overall quality and reliability of the preprocessed source data, providing an important basis for subsequent decision analysis. In the decision analysis layer, task decisions will be made based on the comprehensive data evaluation results. Combined with the compensation prediction trend and other relevant factors, the final target decision plan is formulated.

[0058] Furthermore, the present invention, after adding the single evaluation result and the collaborative evaluation result to the data evaluation result, comprises:

[0059] Conduct market trend forecasts in a predetermined time zone and determine trend forecast results;

[0060] Based on the decision-influencing characteristic value, compensating and adjusting the trend prediction result to determine a compensated prediction trend;

[0061] The data evaluation result is transferred to the decision analysis layer, and task decision is made to determine the target decision plan based on the compensation prediction trend.

[0062] Specifically, collect historical and real-time data related to market trends, including sales data, consumer behavior data, competitor data, etc. Clean and organize the collected data, remove outliers and missing values, and ensure data quality and accuracy. Use appropriate analytical methods (such as time series analysis, regression analysis, etc.) to process and analyze the data to identify market trends and predict future trends. Based on historical data and current market dynamics, establish a forecasting model or algorithm to predict future market trends. Obtain trend forecast results through the forecasting model, including key indicators such as market trends and growth rates in the future. Identify features or factors that have a significant impact on decision results, such as market demand, competitor dynamics, policies and regulations, etc. Analyze the degree of influence of decision-making influence feature values ​​on decision results in order to make reasonable compensation adjustments. Compensate and adjust the preliminary trend forecast results based on the degree of influence of decision-making influence feature values. This can be achieved by adjusting the forecasting model parameters, introducing new variables, etc. After compensation adjustment, re-evaluate the market trend to obtain a more accurate compensated forecast trend. Transfer the data evaluation results (including single evaluation results and collaborative evaluation results) to the decision analysis layer to provide key information for task decision-making. In the decision analysis layer, task decisions are made to determine the target decision plan based on the compensation prediction trend and other relevant factors. This may include selecting different strategies, formulating action plans, etc. The final target decision plan is output and further optimized.

[0063] Furthermore, if Figure 3 As shown, in the present invention, the real-time tracking and monitoring and deviation decision making include:

[0064] Execute the target decision plan and simultaneously monitor and determine real-time response data;

[0065] Divide the scope of program execution into time and space grids, and read and integrate grid monitoring data;

[0066] Identify the grid monitoring data, perform deviation trend analysis on single grid data, and determine multiple single analysis results;

[0067] Combining the multiple individual analysis results to determine a deviation decision result;

[0068] The data that does not meet the deviation tolerance interval in the deviation decision results are screened as the trend deviation data.

[0069] Specifically, response data can be collected through various sensors, monitoring systems, or real-time databases. For example, website click-through rate, conversion rate, user activity, etc. User feedback: user opinions and evaluations collected through surveys, comments, or real-time chats. Business data: For example, sales, order volume, return rate, etc. System log: operation log of server, database, or other software, which may contain error information, access records, etc. The scope of program execution can then be divided into different spatiotemporal grids. Grid monitoring data is identified and analyzed. For the data of each grid, deviation trend analysis can be performed to determine whether there are abnormalities or deviations from expectations. For example, statistical methods or machine learning algorithms can be used to detect outliers or trend changes in data. If the data of a grid shows abnormal growth or decline, it can be identified as a deviation from the trend. Multiple single analysis results can be determined. These results may include anomaly detection results, trend predictions, etc. for each grid unit. Based on the single analysis results of each grid, these results are combined to determine the overall deviation decision result. Then a comprehensive analysis and judgment are performed to identify the main deviation trends and influencing factors. For example, data visualization tools (such as heat maps, scatter plots, etc.) can be used to display the abnormal values ​​and trend changes of each grid. By comparing the data of different grids with historical data, abnormal areas and potential problem points can be found. Based on this information, corresponding adjustment measures and response strategies can be formulated. Data that does not meet the deviation tolerance interval can be screened out as trend deviation data.

[0070] Embodiment 2

[0071] Based on the same inventive concept as the intelligent decision-making method based on digital benefit evaluation in the aforementioned embodiment, Figure 4 As shown, the present application provides an intelligent decision-making system based on digital benefit evaluation, the system comprising:

[0072] A digital topology network determination module 10, which is used to perform correlation assessment on multiple data systems, interconnect data islands, and determine a digital topology network;

[0073] A channel connection establishment module 20, wherein the channel connection establishment module 20 establishes a channel connection between each data port and a third-party platform based on the digital topology network, wherein the third-party platform is provided with an intelligent decision-making model;

[0074] A data transmission module 30, the data transmission module 30 is used to read the pre-decision task, traverse the digital topology network to determine the target data system, integrate the task source data and transmit it to the third-party platform;

[0075] An impact characteristic value screening module 40, wherein the impact characteristic value screening module 40 is used to read market driving factors and quantitative variables and screen decision-making impact characteristic values;

[0076] A target decision-making scheme determining module 50, which is an intelligent decision-making model based on the third-party platform, performs single-item evaluation and collaborative evaluation on the task source data in combination with the decision-influencing characteristic value, determines the data evaluation result and makes an intelligent decision to determine the target decision-making scheme;

[0077] Deviation data feedback module 60, the deviation data feedback module 60 is used to delegate execution of the target decision plan, track and monitor in real time and make deviation decisions, and feedback trend deviation data;

[0078] The data calibration and compensation module 70 is used to combine the intelligent decision model to perform calibration compensation on the target decision plan based on the trend deviation data, determine the scenario decision compensation plan and update it.

[0079] Furthermore, the system includes:

[0080] The digital topology network generation module is used to associate and identify the multiple data systems based on system correlation to determine a first interconnection layer; associate and identify the multiple data systems based on data correlation to determine a second interconnection layer, wherein the data correlation evaluation criteria at least include sequential impact association and co-frequency impact association; and fuse the first interconnection layer and the second interconnection layer to generate the digital topology network.

[0081] Furthermore, the system includes:

[0082] The task source data determination module is used to perform data sensitivity analysis on the task source data and mark multi-level sensitive data groups; for the multi-level sensitive data groups, match the data encryption method in combination with the key database and perform sensitive data processing to determine the encrypted sensitive data; based on the encrypted sensitive data, replace the multi-level sensitive data group to determine the adjusted task source data.

[0083] Furthermore, the system includes:

[0084] The preprocessing source data determination module is used to identify the data volume of the task source data and determine whether the processing time limit constraint is met; if not, balance the data value and processing efficiency and determine the preprocessing standard based on the data volume; based on the preprocessing standard, extract effective data information and normalize the task source data to determine the preprocessing source data.

[0085] Furthermore, the system includes:

[0086] A collaborative evaluation result determination module, wherein the intelligent decision-making model includes a data evaluation layer and a decision analysis layer; based on the data evaluation layer, the pre-processed source data is identified, and a single data evaluation is performed based on the belonging data system to determine the single evaluation result; the data association identifier based on the digital topology network is identified, and a data collaborative evaluation is performed based on the data correlation assessment standard to determine the collaborative evaluation result; the single evaluation result and the collaborative evaluation result are added to the data evaluation result.

[0087] Furthermore, the system includes:

[0088] The task decision module is used to predict the market trend in a predetermined time zone and determine the trend prediction result; based on the decision-influencing characteristic value, the trend prediction result is compensated and adjusted to determine the compensation prediction trend; the data evaluation result is transferred to the decision analysis layer, and the task decision is made with the compensation prediction trend as a constraint to determine the target decision plan.

[0089] Furthermore, the system includes:

[0090] The trend deviation data acquisition module is used to execute the target decision plan, synchronously monitor and determine the real-time response data; divide the plan execution range into time and space grids, read and integrate grid monitoring data; identify the grid monitoring data, perform deviation trend analysis on single grid data, and determine multiple single analysis results; combine the multiple single analysis results to determine the deviation decision result; and filter the data in the deviation decision result that does not meet the deviation tolerance interval as the trend deviation data.

[0091] Through the detailed description of the intelligent decision-making method based on digital benefit evaluation mentioned above, those skilled in the art can clearly understand the intelligent decision-making system based on digital benefit evaluation in this embodiment. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0092] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent decision-making method based on digital benefit evaluation, characterized in that: The method comprises: Assess the correlation of multiple data systems, interconnect data islands, and determine the digital topology network; Based on the digital topology network, establishing a channel connection between each data port and a third-party platform, wherein the third-party platform is equipped with an intelligent decision-making model; Read the pre-decision task, traverse the digital topology network to determine the target data system, integrate the task source data and transmit it to the third-party platform; Read market drivers and quantitative variables, and filter decision-making impact feature values; Based on the intelligent decision-making model of the third-party platform and in combination with the decision-influencing characteristic value, the task source data is evaluated individually and collaboratively, the data evaluation results are determined, and intelligent decisions are made to determine the target decision-making plan; Decentralize the execution of the target decision plan, track and monitor in real time, make deviation decisions, and report back trend deviation data; In combination with the intelligent decision model, calibration compensation based on the trend deviation data is performed on the target decision solution, and a scenario decision compensation solution is determined and updated; The said correlation assessment of multiple data systems and interconnection of data islands include: Based on the system correlation, the multiple data systems are associated and identified to determine the first interconnection layer; Based on the data correlation, the multiple data systems are associated and identified to determine the second interconnection layer, wherein the data correlation evaluation criteria at least include sequential impact correlation and same-frequency impact correlation; fusing the first interconnection layer and the second interconnection layer to generate the digital topology network; After integrating the task source data, the following steps are included: Performing data sensitivity analysis on the task source data and marking multi-level sensitive data groups; For the multi-level sensitive data group, matching the data encryption method with the key database and performing sensitive data processing to determine the encrypted sensitive data; Based on the encrypted sensitive data, the multi-level sensitive data group is replaced to determine the adjusted task source data; Before performing single-item evaluation and collaborative evaluation on the task source data, including: Identify the data volume of the task source data and determine whether the processing time limit constraint is met; If not, balance the data value and processing efficiency and determine the preprocessing standard based on the data volume; Based on the preprocessing standard, extracting effective data information and normalizing the task source data to determine the preprocessing source data; Performing single and collaborative evaluations on the task source data, including: Wherein, the intelligent decision-making model includes a data evaluation layer and a decision analysis layer; Based on the data evaluation layer, the pre-processed source data is identified, and a single data evaluation is performed based on the belonging data system to determine the single evaluation result; Identifying a data association identifier based on the digital topology network, performing data collaborative evaluation based on the data relevance evaluation criteria, and determining a collaborative evaluation result; The single evaluation result and the collaborative evaluation result are added to the data evaluation result.

2. The method according to claim 1, characterized in that After adding the single evaluation result and the collaborative evaluation result into the data evaluation result, the method includes: Conduct market trend forecasts in a predetermined time zone and determine trend forecast results; Based on the decision-influencing characteristic value, compensating and adjusting the trend prediction result to determine a compensated prediction trend; The data evaluation result is transferred to the decision analysis layer, and task decision is made to determine the target decision plan based on the compensation prediction trend.

3. The method according to claim 1, characterized in that The real-time tracking and monitoring and deviation decision-making include: Execute the target decision plan and simultaneously monitor and determine real-time response data; Divide the execution scope of the program into time and space grids, and read and integrate grid monitoring data; Identify the grid monitoring data, perform deviation trend analysis on single grid data, and determine multiple single analysis results; Combining the multiple individual analysis results to determine a deviation decision result; The data that does not meet the deviation tolerance interval in the deviation decision results are screened as the trend deviation data.

4. Intelligent decision-making system based on digital benefit evaluation, characterized by: The system comprises: A digital topology network determination module, which is used to perform correlation assessment on multiple data systems, interconnect data islands, and determine a digital topology network; A channel connection establishment module, wherein the channel connection establishment module establishes a channel connection between each data port and a third-party platform based on the digital topology network, wherein the third-party platform is provided with an intelligent decision-making model; A data transmission module, the data transmission module is used to read the pre-decision task, traverse the digital topology network to determine the target data system, integrate the task source data and transmit it to the third-party platform; An impact characteristic value screening module, which is used to read market driving factors and quantitative variables and screen decision-making impact characteristic values; A target decision-making scheme determination module, which is an intelligent decision-making model based on the third-party platform, combines the decision-influencing characteristic value, performs single evaluation and collaborative evaluation on the task source data, determines the data evaluation result and makes an intelligent decision to determine the target decision scheme; A deviation data feedback module, which is used to delegate execution of the target decision-making plan, track and monitor in real time, make deviation decisions, and feedback trend deviation data; A data calibration and compensation module, the data calibration and compensation module is used to perform calibration compensation based on the trend deviation data on the target decision solution in combination with the intelligent decision model, determine the scenario decision compensation solution and update it; A digital topology network generation module is used to associate and identify the multiple data systems based on system correlation to determine a first interconnection layer; associate and identify the multiple data systems based on data correlation to determine a second interconnection layer, wherein the data correlation evaluation criteria at least include sequential impact association and co-frequency impact association; and fuse the first interconnection layer and the second interconnection layer to generate the digital topology network; The task source data determination module is used to perform data sensitivity analysis on the task source data and mark a multi-level sensitive data group; for the multi-level sensitive data group, match the data encryption method in combination with the key database and perform sensitive data processing to determine the encrypted sensitive data; based on the encrypted sensitive data, replace the multi-level sensitive data group to determine the adjusted task source data; A pre-processing source data determination module is used to identify the data volume of the task source data and determine whether the processing time limit constraint is met; if not, the pre-processing standard is determined based on the data volume by balancing the data value and processing efficiency; based on the pre-processing standard, effective data information is extracted and normalized for the task source data to determine the pre-processing source data; A collaborative evaluation result determination module, wherein the intelligent decision-making model includes a data evaluation layer and a decision analysis layer; based on the data evaluation layer, the pre-processed source data is identified, and a single data evaluation is performed based on the belonging data system to determine the single evaluation result; the data association identifier based on the digital topology network is identified, and a data collaborative evaluation is performed based on the data correlation assessment standard to determine the collaborative evaluation result; the single evaluation result and the collaborative evaluation result are added to the data evaluation result.

Images