Business analysis aided decision-making method and system based on big data

Abstract

The invention provides a business analysis aided decision-making method and system based on big data. Wherein real-time data streams from different sources are integrated to form continuous data input streams; dynamically constructing a real-time monitoring model reflecting a service state based on the data input stream, the real-time monitoring model being used for capturing a service state change; when the real-time monitoring model identifies that the service state of the specific service is changed, triggering a scene analysis mechanism so as to evaluate the development trend of the specific service through the scene analysis mechanism, and generating a corresponding scene report; according to the scene report, a preset strategy generation algorithm is applied, and the strategy generation algorithm generates action suggestions adapted to the specific service according to optimal action paths under different scenes; and providing the action suggestions to a decision support interface to assist a decision maker in quickly responding to business changes. According to the technical scheme provided by the invention, the decision-making efficiency and the service response speed are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of intelligent decision support systems, and in particular to a business analysis and decision support method and system based on big data. Background Art

[0002] As application scenarios and technical requirements become increasingly complex, modern enterprises face the challenge of quickly responding to market changes and changes in internal operating status in the fierce market competition.

[0003] There are already some solutions on the market that meet the above needs. For example, business intelligence platforms can connect different data sources and provide basic data visualization tools, while advanced analytical tools can perform predictive modeling based on historical data to provide companies with insights into future trends.

[0004] However, these existing solutions still have obvious limitations: data sources are diverse and in different formats, and existing tools are difficult to efficiently process heterogeneous data, resulting in a long data preparation phase. Many so-called "real-time" analyses can only achieve quasi-real-time or periodic updates, which cannot fully meet the company's demand for instant information. Data processing, model building, and decision-making recommendation generation still require a lot of manual intervention, which increases costs and limits the flexibility and response speed of the system.

[0005] Therefore, developing a new intelligent decision support system that can overcome the above-mentioned defects is of great significance to improving the decision-making efficiency and market competitiveness of enterprises. Summary of the invention

[0006] The embodiments of the present application provide a business analysis decision-making assistance method and system based on big data, which are used to solve the problems of low decision-making efficiency and slow business response speed in the prior art.

[0007] In a first aspect, an embodiment of the present application provides a business analysis decision-making assistance method based on big data, comprising: Integrate real-time data streams from different sources to form a continuous data input flow; Based on the data input stream, dynamically construct a real-time monitoring model reflecting the business status, wherein the real-time monitoring model is used to capture business status changes; When the real-time monitoring model identifies a change in the business status of a specific business, a scenario analysis mechanism is triggered to evaluate the development trend of the specific business through the scenario analysis mechanism and generate a corresponding scenario report; Based on the scenario report, a preset strategy generation algorithm is applied, wherein the strategy generation algorithm generates action suggestions adapted to the specific business according to the optimal action paths under different scenarios; The action suggestions are provided to a decision support interface to assist decision makers in responding quickly to business changes.

[0008] In a second aspect, an embodiment of the present application provides a business analysis and decision support system based on big data, including: Integration module, used to integrate real-time data streams from different sources to form a continuous data input flow; A construction module, used to dynamically construct a real-time monitoring model reflecting the business status based on the data input stream, wherein the real-time monitoring model is used to capture business status changes; An analysis module, configured to trigger a scenario analysis mechanism when the real-time monitoring model identifies a change in the business status of a specific business, so as to evaluate the development trend of the specific business through the scenario analysis mechanism and generate a corresponding scenario report; A generation module, configured to apply a preset strategy generation algorithm based on the scenario report, wherein the strategy generation algorithm generates action suggestions adapted to the specific business based on the optimal action paths under different scenarios; A module is provided for providing the action suggestions to a decision support interface to assist decision makers in quickly responding to business changes.

[0009] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a business analysis decision support method based on big data as described in any one of the first aspects.

[0010] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a business analysis and decision support method based on big data as described in any one of the first aspects.

[0011] In an embodiment of the present application, real-time data streams from different sources are integrated to form a continuous data input stream; based on the data input stream, a real-time monitoring model reflecting the business status is dynamically constructed, and the real-time monitoring model is used to capture changes in the business status; when the real-time monitoring model identifies changes in the business status of a specific business, a scenario analysis mechanism is triggered to evaluate the development trend of the specific business through the scenario analysis mechanism and generate a corresponding scenario report; based on the scenario report, a preset strategy generation algorithm is applied, and the strategy generation algorithm generates action recommendations that are suitable for the specific business based on the optimal action path under different scenarios; the action recommendations are provided to a decision support interface to assist decision makers in quickly responding to business changes.

[0012] The business analysis and decision-making assistance method based on big data in this application integrates multi-source real-time data streams, dynamically builds a real-time monitoring model, captures business status changes in real time, and evaluates business development trends through a scenario analysis mechanism to generate action recommendations adapted to specific businesses. A comprehensive and real-time business status monitoring model is also constructed through data fusion and machine learning technology, which can accurately capture business changes and trigger scenario analysis in a timely manner. The scenario analysis mechanism simulates different scenarios, evaluates business development trends, and generates detailed reports to help decision makers fully understand market changes and potential risks, and formulate response strategies in advance. This not only improves the real-time and accuracy of decision-making, but also reduces decision-making risks and enhances the resilience and competitiveness of enterprises.

[0013] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] Figure 1 A flowchart of a business analysis and decision-making assistance method based on big data provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a business analysis and decision support system based on big data provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0017] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[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 those skilled in the art without creative work are within the scope of protection of this application.

[0019] Figure 1 A flowchart of a business analysis and decision-making assistance method based on big data is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes: 101. Integrate real-time data streams from different sources to form a continuous data input stream; In this step, the data can come from internal enterprise systems (such as ERP, CRM, etc.), external APIs (such as social media, weather services, etc.), and IoT devices (such as sensors). Real-time data means that the data is transmitted from the source to the processing system almost instantly with very low latency. Continuous data input stream refers to an uninterrupted flow of data, which can continuously provide the latest information to the back-end system.

[0020] In the embodiments of the present application, data integration tools or platforms are used to connect various data sources, collect data through API calls, message queues, etc., and integrate them into a unified data stream. This usually requires solving problems such as data format conversion, data cleaning, and data verification to ensure the quality and availability of data.

[0021] 102. Based on the data input stream, dynamically construct a real-time monitoring model reflecting the business status, wherein the real-time monitoring model is used to capture changes in the business status; In this step, the real-time monitoring model is a mathematical or computational model that can be updated in real time according to changes in input data, aiming to accurately reflect the current state of the business. Business state changes refer to any significant changes in business operations, such as sales fluctuations, changes in inventory levels, changes in customer behavior patterns, etc.

[0022] In the embodiment of the present application, machine learning algorithms and data analysis techniques are used to dynamically adjust model parameters according to information in real-time data streams to ensure that the model can reflect changes in business status in a timely manner. This process may involve technologies such as feature selection, model training, and online learning.

[0023] Optionally, the step 102 of dynamically constructing a real-time monitoring model reflecting the business status based on the data input stream includes: integrating the data input stream using data fusion technology to construct a data lake; based on the data lake, dynamically constructing a real-time monitoring model reflecting the business status using a machine learning algorithm, and the real-time monitoring model is used to extract key indicators from the data lake to accurately capture changes in business status.

[0024] Data fusion technology: refers to the integration of data from different sources to eliminate redundancy and contradictions and improve data consistency and accuracy. In this scenario, data fusion technology is used to integrate real-time data streams from different sources into a unified data set.

[0025] Data lake: It is a large warehouse that stores all the raw data of an enterprise. These data can be structured (such as database tables), semi-structured (such as XML, JSON files) or unstructured (such as text, pictures). The data in the data lake can be used for subsequent data processing, analysis and mining.

[0026] Machine learning algorithms: are algorithms that learn patterns from data and make predictions or decisions based on them. In this scenario, machine learning algorithms are used to extract key indicators from the data lake and build real-time monitoring models that can reflect changes in business status.

[0027] Key indicators: refers to important data points that can directly or indirectly reflect the business status. For example, in the field of energy and electricity, power generation, power consumption, grid frequency, etc. are all key indicators.

[0028] First, collect real-time data from various data sources through APIs, message queues, and other means, and then use data fusion technology to integrate these data together to ensure data consistency and integrity. Store the fused data on a platform that can efficiently process a large amount of heterogeneous data, namely the data lake. In this process, it is necessary to consider the security, scalability, and access performance of the data. Based on the data in the data lake, select appropriate machine learning algorithms (such as time series analysis, regression analysis, etc.) to build a real-time monitoring model. During the model training process, it is necessary to continuously adjust the parameters to ensure that the model can accurately extract key indicators from the data lake and reflect changes in business status. Finally, deploy the trained model to the production environment, receive new data from the data lake in real time, and dynamically update the model based on this data to capture changes in business status in a timely manner. At the same time, a monitoring system needs to be established to ensure the performance and stability of the model.

[0029] In the embodiment of this application, it is assumed that the State Grid Corporation of China needs to monitor the balance of power supply and demand across the country in real time to ensure the stable operation of the power grid and optimize the allocation of power resources. Faced with massive amounts of power generation, transmission, distribution and power consumption data, traditional data processing methods can no longer meet the needs.

[0030] First, real-time power data, including power generation, power consumption, grid frequency, voltage level, etc., are collected from various substations, power plants, smart meters, etc. Data fusion technology is used to process this data to ensure data consistency and accuracy. Secondly, the processed data is stored in the data lake for subsequent analysis. The data lake needs to be highly scalable and able to support PB-level data storage and processing. Then, time series analysis and anomaly detection algorithms are used to extract key indicators from the data lake, such as power supply and demand ratio, grid frequency fluctuations, etc., to build a model that can monitor the balance of power supply and demand in real time. The model is trained with historical data so that it can accurately predict future power supply and demand. Finally, the model is deployed to the real-time monitoring system of the State Grid, which receives new data from the data lake in real time and dynamically updates the model prediction results. If the model detects signs of imbalance in power supply and demand, the early warning mechanism is immediately triggered to notify the relevant person in charge to take measures. At the same time, the model performance is regularly evaluated to ensure that it is always in the best condition.

[0031] 103. When the real-time monitoring model identifies a change in the business status of a specific business, a scenario analysis mechanism is triggered to evaluate the development trend of the specific business through the scenario analysis mechanism and generate a corresponding scenario report; In this step, scenario analysis refers to a forecasting method that simulates different future scenarios to evaluate potential outcomes and help understand the impact of business changes. Scenario reports are documents generated based on the results of scenario analysis to show the possibility of business development under different assumptions.

[0032] In the embodiment of the present application, once the real-time monitoring model detects a significant change in the business status, the scenario analysis process will be automatically started. The process may include setting multiple assumptions, running the simulation model, and then generating a scenario report based on the simulation results for further analysis.

[0033] Optionally, in step 103, when the real-time monitoring model identifies a change in the business status of a specific business, a scenario analysis mechanism is triggered to evaluate the development trend of the specific business through the scenario analysis mechanism, and a corresponding scenario report is generated, including: when the real-time monitoring model identifies a change in the business status of a specific business, a scenario analysis mechanism is triggered; according to the change in the business status of the specific business, different scenarios are simulated, and the development trend of the specific business under different scenarios is evaluated to obtain a scenario evaluation result, and the different scenarios at least include market shrinkage, intensified competition, and policy changes; based on the scenario evaluation results, a corresponding scenario report is generated, and the scenario report includes an evaluation of the development trend of the specific business under the corresponding scenario, identification of potential risk points, and recommendations for response strategies.

[0034] Real-time monitoring model: A method based on machine learning or statistical analysis that can monitor changes in business status in real time and issue alerts when anomalies or significant changes are detected.

[0035] Scenario Analysis: A forecasting method that helps decision makers understand the impact of business changes by simulating different future scenarios to evaluate potential outcomes.

[0036] Scenario Assessment Results: Assessment results of specific business development trends under different assumptions, including positive and negative possibilities.

[0037] Scenario report: A document generated based on scenario assessment results, used to demonstrate the possibilities, potential risks and response strategies for business development under different scenarios.

[0038] First, when the real-time monitoring model detects a significant change in the business status of a specific business, the scenario analysis mechanism is automatically triggered. Secondly, different future scenarios are designed and simulated according to the specific circumstances of the business status change. These scenarios include at least market shrinkage, intensified competition, policy changes, etc. Then, in each simulated scenario, the development trend of the specific business is evaluated, including changes in key indicators such as revenue, market share, and cost. Finally, based on the results of the scenario evaluation, a detailed scenario report is generated. The report should include an evaluation of the business development trend in each scenario, the identification of potential risk points, and corresponding response strategy recommendations.

[0039] In the embodiment of the present application, it is assumed that the State Grid Corporation needs to monitor the balance of power supply and demand in real time to ensure the stable operation of the power grid. When an imbalance in power supply and demand or a change in the market environment is detected, scenario analysis is needed to evaluate future development trends and formulate response strategies.

[0040] First, the State Grid uses a real-time monitoring model to monitor the balance of electricity supply and demand across the country, including key indicators such as power generation, power consumption, and grid frequency. When the model detects an imbalance in power supply and demand (such as a sudden surge in power consumption in a certain area or a sharp drop in power generation), the scenario analysis mechanism is automatically triggered. Then assume that the economic recession leads to a decrease in industrial and residential power consumption. Assume that new competitors enter the market and provide cheaper or more efficient power solutions. If the current conditions require an increase in the proportion of renewable energy use. Then evaluate the changes in the State Grid's revenue, market share, and operating costs in the event of an economic recession. For example, a decrease in power consumption may lead to a decrease in revenue, but operating costs may also decrease. Evaluate the changes in the State Grid's market share and customer satisfaction after new competitors enter the market. For example, competitors offering cheaper electricity prices may attract some users to switch networks. Evaluate the impact of existing environmental protection requirements on the State Grid, including the costs and benefits of investing in renewable energy projects. For example, increasing the use of renewable energy may increase operating costs. Further generate scenario reports, which describe in detail the development trends of the State Grid in each scenario, including changes in key indicators such as revenue, market share, and operating costs. Identify the risk points that may be faced in each scenario, such as market shrinkage may lead to tight cash flow, and intensified competition may lead to customer loss. Propose response strategies for each scenario, such as: optimizing cost structure and improving operational efficiency; developing new value-added services and increasing revenue sources; strengthening technology research and development and improving service quality; carrying out marketing activities and enhancing brand influence.

[0041] 104. Based on the scenario report, a preset strategy generation algorithm is applied, wherein the strategy generation algorithm generates action suggestions adapted to the specific business according to the optimal action paths under different scenarios; In this step, the strategy generation algorithm refers to an algorithm that generates a series of recommended actions based on given inputs (such as data in a scenario report) to guide business decisions. The optimal action path is the sequence of actions that can bring the greatest benefit or the least loss in a given scenario.

[0042] In the embodiment of the present application, based on the various possible situations provided by the scenario report, an optimization algorithm, a decision tree or other suitable algorithm is used to evaluate the potential action plans under each scenario, and ultimately determine the action recommendations that are most conducive to achieving the business goals.

[0043] Optionally, in step 104, based on the scenario report, a preset strategy generation algorithm is applied, and the strategy generation algorithm generates action recommendations suitable for the specific business according to the optimal action paths under different scenarios, including: converting key information in the scenario report into structured data, and sending the structured data as input to a preset strategy generation algorithm, so that the strategy generation algorithm evaluates the plan details of the alternative action plan under the corresponding scenario according to the structured data to obtain an evaluation result, wherein the action plan includes an action path, and the plan details include at least plan cost, plan benefit and plan risk; according to the evaluation result, calculating the plan score of the alternative action plan under the scenario corresponding to the structured data; selecting the alternative action plan with the highest plan score as the optimal action plan, and the optimal action path corresponding to the optimal action plan can achieve the best balance among the plan cost, the plan benefit and the plan risk; and generating action recommendations suitable for the specific business according to the optimal action path.

[0044] Scenario report: A document generated based on the scenario analysis mechanism, which contains an assessment of business development trends under different scenarios, identification of potential risk points, and preliminary response strategy recommendations.

[0045] Structured data: Convert key information in a scenario report into a format that can be processed by a computer, usually stored in a table or database.

[0046] Strategy generation algorithm: An algorithm that evaluates alternative action plans under different scenarios based on input structured data and selects the optimal action path.

[0047] Plan details: The specific details of each alternative course of action, including the cost, benefits, and risks of the plan.

[0048] Plan score: A score given after a comprehensive evaluation of plan costs, plan benefits and plan risks, used to select the best action plan.

[0049] Optimal action path: Among all alternative action plans, the action path corresponding to the plan with the highest score can achieve the best balance between costs, benefits and risks.

[0050] First, the key information in the scenario report (such as the evaluation results under scenarios such as market shrinkage, intensified competition, and policy changes) is converted into structured data for computer processing. Then the structured data is sent as input to the preset strategy generation algorithm. Secondly, the strategy generation algorithm evaluates the details of each alternative action plan (plan cost, plan benefit, plan risk) based on the input structured data to obtain the evaluation results. Further, based on the evaluation results, the comprehensive score of each alternative action plan is calculated. The score calculation can be based on weighted average or other multi-criteria decision-making methods. Then the alternative action plan with the highest score is selected as the optimal action plan, which can achieve the best balance between cost, benefit and risk. Finally, based on the optimal action path, action recommendations adapted to specific businesses are generated for reference and execution by decision makers.

[0051] In the embodiment of the present application, it is assumed that when the State Grid Corporation detects an imbalance in electricity supply and demand or a change in the market environment, it needs to formulate an optimal response strategy through scenario analysis and strategy generation algorithms to ensure the stable operation of the power grid and the sustainable development of the company.

[0052] The What-If Scenario Report contains the following information: Market shrinkage: electricity consumption decreased by 10%, and revenue decreased by 8%. Intensified competition: market share decreased by 5%, and customer satisfaction decreased by 10%. Policy changes: the proportion of renewable energy use needs to be increased, and the initial investment increased by 20%. Structured data: The above information is converted into structured data, as shown in Table 1 below: Table 1: scene Changes in electricity consumption Changes in income Market share changes Changes in customer satisfaction Changes in initial investment Shrinking market -10% -8% 0% 0% 0% Intensified competition 0% 0% -5% -10% 0% Policy changes 0% 0% 0% 0% +20% The above structured data is input into the preset strategy generation algorithm.

[0053] Evaluate alternative courses of action: Plan A optimizes the cost structure and reduces operating costs by 10%. Plan cost: -10%, plan benefit: +5%, plan risk: low.

[0054] Plan B: Develop new value-added services and increase revenue by 5%. Plan cost: +5%, Plan benefit: +5%, Plan risk: medium.

[0055] Plan C: Strengthen technology research and development and improve service quality. Plan cost: +10%, plan benefit: +8%, plan risk: medium.

[0056] Plan D: Carry out marketing activities to enhance brand influence. Plan cost: +15%, Plan benefit: +10%, Plan risk: high.

[0057] Plan E: Actively invest in renewable energy projects. Plan cost: +20%, Plan benefit: +15%, Plan risk: medium.

[0058] Plan F: Strengthen communication with the government and understand policy trends. Plan cost: +5%, plan benefit: +5%, plan risk: low.

[0059] Assume that the calculation formula for the solution score is: Solution score = 0.5*(solution benefit)-0.3*(solution cost)-0.2*(solution risk) Calculate the score for each solution: Plan A: 0.5*5%-0.3*(-10%)-0.2*low=2.5%+3%-0.2*1=5.3% Plan B: 0.5*5%-0.3*5%-0.2*medium=2.5%-1.5%-0.2*2=0.6% Solution C: 0.5*8%-0.3*10%-0.2*medium=4%-3%-0.2*2=0.6% Solution D: 0.5*10%-0.3*15%-0.2*high=5%-4.5%-0.2*3=0.4% Plan E: 0.5*15%-0.3*20%-0.2*medium=7.5%-6%-0.2*2=1.1% Plan F: 0.5*5%-0.3*5%-0.2*low=2.5%-1.5%-0.2*1=0.8% Select the best action plan based on the score: Plan A (5.3%) Plan C (0.6%) Plan F (0.8%) Generate action suggestions, optimize the cost structure, and reduce operating costs by 10%. Strengthen technology research and development to improve service quality. Strengthen communication with the government and understand policy trends.

[0060] 105. Providing the action suggestions to a decision support interface to assist decision makers in quickly responding to business changes.

[0061] In this step, the decision support interface refers to a user interface or API that presents key information and support materials to decision makers to help them make better decisions. The action recommendations are specific implementation plans or measures designed to solve the identified problems or take advantage of the discovered opportunities.

[0062] In the embodiment of the present application, the action recommendations derived from the strategy generation algorithm are presented to the decision maker in an easy-to-understand manner through the decision support interface. This may include charts, reports, dashboards, etc., with the aim of enabling the decision maker to quickly grasp the core information and respond quickly. In addition, the interface should also support a feedback mechanism to allow the decision maker to evaluate and adjust the recommendations.

[0063] Optionally, the step 105 of providing the action recommendations to a decision support interface to assist decision makers in quickly responding to business changes includes: designing and implementing a user-friendly decision support interface, which is capable of receiving and displaying action recommendations for the specific business generated by the policy generation algorithm, while supporting interactive operations of decision makers; allowing the decision makers to provide instant feedback on the action recommendations through the decision support interface.

[0064] Decision support interface: A user interface or API that presents key information and supporting materials to decision makers to help them make better decisions. The interface should be highly user-friendly and interactive.

[0065] Action recommendations: Specific execution plans or measures generated by the strategy generation algorithm to address identified problems or exploit discovered opportunities.

[0066] Interactive operations: Decision makers can perform operations through the decision support interface, such as viewing detailed information, modifying suggestions, adding comments, etc.

[0067] Instant feedback: Decision makers can evaluate and provide feedback on action suggestions on the decision support interface, and this feedback can be used to optimize future decision-making processes.

[0068] First, design an intuitive and easy-to-use user interface to ensure that decision makers can quickly find the information they need. This includes functions such as displaying action suggestions, viewing detailed information, modifying suggestions, adding comments, and submitting feedback. Then use modern front-end frameworks (such as React, Vue, etc.) to develop the user interface. Build a back-end service that is responsible for receiving action suggestions from the strategy generation algorithm and passing this data to the front-end. Secondly, the back-end service receives action suggestions from the strategy generation algorithm and stores them in the database. The front-end interface obtains action suggestions from the back-end and displays them to decision makers in the form of a list or card. Further, decision makers can click on the action suggestion to view detailed plan details (such as plan cost, plan benefit, plan risk, etc.). Decision makers can modify the action suggestion, add their own opinions, or adjust the plan. Add comments: Decision makers can add comments to record their own thinking and decision-making process. Finally, decision makers can submit evaluations and feedback on the action suggestions through the interface. The back-end service receives feedback and stores it in the database for subsequent analysis and optimization.

[0069] In the embodiment of the present application, it is assumed that the State Grid Corporation of China needs a decision support interface to help decision makers quickly respond to imbalances in electricity supply and demand and changes in the market environment and formulate optimal response strategies.

[0070] First, a concise and clear user interface is designed, which mainly includes action suggestion list, detailed information viewing, suggestion modification, annotation and feedback submission modules. All action suggestions generated by the strategy generation algorithm are displayed. Click on the action suggestion to display detailed solution details, including solution cost, solution benefit, solution risk, etc. Decision makers can edit the action suggestion, add their own opinions or adjust the solution. Decision makers can add comments to record their thinking and decision-making process. Decision makers can submit comments and feedback on the action suggestion. Then, the user interface is developed using the React framework to ensure fast interface response and good user experience. The backend service is built using Node.js and Express frameworks, which is responsible for receiving action suggestions from the strategy generation algorithm and storing these data in the MongoDB database. The backend service further receives action suggestions from the strategy generation algorithm through the API and stores them in the MongoDB database. The front-end interface obtains action suggestions from the backend through the API and displays them in the action suggestion list in the form of cards. Further, the decision maker clicks on the action suggestion card, and the detailed information page pops up, showing detailed information such as solution cost, solution benefit, solution risk, etc. Decision makers can edit the action suggestion, add their own opinions or adjust the solution in the detailed information page. Decision makers can add comments on the details page to record their thinking and decision-making process. Finally, decision makers fill in their evaluation and feedback on the action suggestions on the details page. After clicking the Submit button, the front end sends the feedback data to the back end through the API. The back end service receives the feedback data, stores it in the MongoDB database, and generates a feedback report for subsequent analysis and optimization.

[0071] The decision maker logs in to the decision support interface and enters the main interface. The main interface displays all action suggestions generated by the strategy generation algorithm. Each suggestion is displayed in the form of a card, including a title, a brief description, and the status of the suggestion (pending, reviewed, in progress, etc.). Click on an action suggestion card to pop up the details page, showing detailed information such as the cost, benefit, and risk of the plan. On the details page, the decision maker can edit the action suggestion, add his own opinions, or adjust the plan. The decision maker can add comments on the details page to record his own thinking and decision-making process. The decision maker fills in the evaluation and feedback on the action suggestion on the details page. After clicking the submit button, the feedback data is sent to the backend.

[0072] This application takes into account that in modern business decision-making, especially in the fields of energy, power and industrial information, decision makers need to rely on scientific methods to evaluate different alternative action plans to ensure the effective use of resources and the realization of strategic goals. Traditional decision-making methods often rely on experience and intuition, which may lead to waste of resources or strategic mistakes. Therefore, an algorithm that can systematically evaluate the cost-effectiveness, risk level and market adaptability of alternative action plans becomes particularly important.

[0073] The options are as follows: Optionally, the evaluating the details of the alternative action plans in the corresponding scenario according to the structured data by the strategy generation algorithm to obtain the evaluation result includes: The strategy generation algorithm evaluates the details of the alternative action plan under the corresponding scenario according to the structured data, and calculates the cost-benefit ratio and risk assessment index of the alternative action plan; Calculate a comprehensive score based on the cost-benefit ratio and risk assessment index of the alternative action plan and the obtained market adaptability score of the alternative action plan; Using the comprehensive score as the evaluation result; Among them, the cost-effectiveness ratio Calculated by the following formula: ; in, Indicates The benefits of the alternative action plans, Indicates The cost of the alternative action plan, Indicates The quality of the alternative courses of action, is a benchmark solution quality, is a tuning parameter used to control the impact of solution quality on the cost-effectiveness ratio. Indicates The implementation time of the alternative action plan, is a benchmark implementation time, is a tuning parameter used to control the effect of implementation time on the cost-effectiveness ratio; Among them, the risk assessment index Calculated by the following formula: ; in, Indicates The alternative action plan is The scores on the risk factors Indicates The average score of all risk factors for the alternative action plans. Indicates The weight of the risk factors, represents the number of risk factors, Indicates The ideal score for each risk factor is is a penalty factor that increases the risk of deviation from the ideal score, is an additional penalty factor that increases the risk of exceeding the ideal score; Among them, the comprehensive score Calculated by the following formula: ; in They are the weights of cost-effectiveness ratio, risk assessment index and market adaptability. Indicates The market suitability score of the alternative action plans, is a benchmark market fitness score, It is a tuning parameter used to control the impact of market adaptability on the comprehensive score.

[0074] The design of this strategy generation algorithm aims to provide decision makers with a quantitative tool to help them comprehensively evaluate alternative action plans from multiple dimensions, so as to make more scientific and reasonable decisions. The algorithm calculates the cost-effectiveness ratio (CER), risk assessment index (RAI) and market adaptability score of each alternative action plan, and finally obtains a comprehensive score as the basis for selecting the best plan.

[0075] Cost-effectiveness ratio ( ) is an important indicator to measure the economic value of a project or solution. The design introduces the solution quality ( ) and implementation time ( ) factors to more fully reflect the actual benefits of the program. Adjustment parameters and Allowing adjustment of the degree to which quality and time affect cost-effectiveness makes the assessment more flexible.

[0076] Risk Assessment Index ( ) is an integral part of the decision-making process. By calculating the difference in scores of different risk factors and their weights, plus penalties for deviations from the ideal state, potential risks can be effectively identified and quantified. This can help decision makers better understand the challenges that each option may face.

[0077] Market suitability score: Market suitability refers to whether a solution can successfully gain recognition and support in the market. Incorporating market suitability into the overall score calculation helps ensure that the selected solution is not only technically feasible, but also has the potential to succeed commercially.

[0078] (Scheme Benefits) and (Scheme cost) is usually determined through detailed financial analysis and market research. For example, in the energy and power industry, the benefits can be estimated by predicting future electricity price changes, cost savings, etc., while the costs include the direct investment of the project, operation and maintenance expenses, etc.

[0079] (quality of the programme) and (Implementation time) The quality of the plan can be determined through expert review or comparison with historical data, while the implementation time is estimated based on the complexity of the project and available resources.

[0080] (Risk Factor Score), (Risk factor weight), (Ideal score) These parameters need to be determined through risk assessment meetings, inviting experts in related fields to score and discuss. The ideal score can be set based on industry standards or past experience.

[0081] (Market adaptability score) can be obtained through market survey questionnaires, competitive product analysis, etc.

[0082] Adjustment parameters (such as ) These parameters usually need to be set through trial and error or empirical values ​​based on historical data to ensure the accuracy and practicality of the model.

[0083] In the embodiment of this application, it is assumed that a power company in a certain region of the State Grid needs to ensure stable operation of the power grid during the peak period of winter power consumption and quickly respond to sudden failures. The company decides to introduce a decision support system to optimize the evaluation results of alternative action plans and improve the scientificity and rationality of decision-making.

[0084] First, the decision support system is integrated with the existing power dispatching system, fault monitoring system and customer service system to ensure real-time data transmission. Sensors and monitoring equipment are used to collect real-time grid operation data, including current, voltage, temperature, etc., and record the benefits, costs, quality, implementation time and risk factor scores of all alternative action plans.

[0085] Secondly, based on historical data, set the quality of the benchmark solution , Benchmark implementation time and benchmark market fitness scores Using the formula Calculate the cost-effectiveness ratio of each alternative action plan. Based on the CER value, select the alternative action plan with the highest cost-effectiveness ratio to ensure efficient operation during the peak electricity consumption period in winter and reduce power outages.

[0087] Further, based on historical data, set the ideal score for each risk factor Using the formula Calculate the risk assessment index for each alternative action plan. Based on the RAI value, select the alternative action plan with the lowest risk assessment index to ensure that the risk can be minimized when dealing with unexpected failures.

[0088] Finally, according to the company's strategy and historical data, the weights of cost-effectiveness ratio, risk assessment index and market adaptability are set. . Use the formula: Calculate the overall score for each alternative course of action. The alternative action plan with the highest comprehensive score is selected to ensure efficient and safe operation during the peak electricity consumption period in winter while meeting market demand.

[0089] By optimizing the selection of alternative action plans, the grid's operating efficiency during the winter peak electricity consumption period has been significantly improved, reducing the occurrence of power outages. By optimizing risk management, the company can more effectively reduce risks when dealing with sudden failures and improve system stability. By optimizing market adaptability, the company can better meet customer needs during the winter peak electricity consumption period and improve customer satisfaction.

[0090] This application takes into account that in modern enterprises and organizations, efficient decision support systems are essential to improve operational efficiency, reduce risks and enhance competitiveness. Especially in the fields of energy and power (such as State Grid) and industrial information technology (Industry Information Technology), since these industries usually involve large amounts of data processing, complex process management and rapid response requirements, a system that can effectively convey action suggestions and quickly respond to decision makers' feedback is particularly important.

[0091] The options are as follows: Optionally, it also includes: The decision support interface uses the following calculation formula to optimize the efficiency of conveying action suggestions: ; in, Indicates the efficiency index of the communication of action suggestions, Indicates the actual delivery time. Indicates the scheduled delivery time. is a positive proportional constant used to adjust the rate of change of the transmission efficiency index. Indicates The acceptance score of the action proposal, is a baseline acceptance score, is a tuning parameter used to control the impact of acceptance score on communication efficiency. Indicates The priority rating of the action recommendations, is a baseline priority score, It is a tuning parameter used to control the impact of priority rating on communication efficiency; The decision support interface uses the following calculation formula to optimize the decision maker feedback response time of action suggestions: ; in, Indicates the user feedback response time, Indicates The response time of the decision maker feedback, represents the number of times the decision maker gives feedback, represents the average response time of all decision makers’ feedback, is a tuning parameter used to increase the impact of response time fluctuations on the overall response time. Indicates Satisfaction ratings from decision makers, is a baseline satisfaction score, is a tuning parameter used to control the impact of satisfaction ratings on decision makers’ feedback response time. is an additional tuning parameter used to increase the impact of satisfaction ratings.

[0092] This formula is designed to quantify and optimize two key indicators of the decision support system through mathematical models: the communication efficiency of action suggestions (CEI) and the user feedback response time (UFRT). These two indicators directly affect the quality and speed of decision-making, and thus affect the operating efficiency and service level of the entire system.

[0093] (The difference between the actual delivery time and the scheduled delivery time) This part can evaluate the difference between the actual communication time and the scheduled communication time, thereby measuring the timeliness of communication. The Sigmoid function is used here. As the actual communication time deviates from the scheduled time, the value of this part will gradually decrease, indicating that the communication efficiency is reduced.

[0094] Acceptability score of action proposal This part reflects the impact of the acceptance of the action suggestion on the communication efficiency. If a suggestion is more acceptable, its communication efficiency will be higher. The Sigmoid function is also used. As the acceptance score increases, the value of this part will also increase.

[0095] Priority rating of action recommendations This part considers the impact of the priority of the action suggestion on its communication efficiency. High-priority suggestions should be communicated to relevant personnel more quickly to ensure the timely delivery of important information. This part also uses the Sigmoid function form. The higher the priority score, the larger the value of this part.

[0096] UFRT (average response time) Represents the average of all feedback response times, which is a basic indicator for measuring system response speed.

[0097] Response time volatility This part is used to evaluate the stability of the response time. The greater the fluctuation of the response time, the larger the value of this part, which means that the response consistency of the system is poor.

[0098] Satisfaction ratings from decision makers This part considers the decision maker's satisfaction with the system feedback. A higher satisfaction score means a better user experience, which will help improve user trust and the overall evaluation of the system. Using the Sigmoid function form, the value of this part increases when the satisfaction score exceeds the baseline value.

[0099] and : The actual delivery time and the scheduled delivery time can be directly obtained from the system log or timestamp.

[0100] and : The acceptance scores of action suggestions can be collected through questionnaires, user feedback, or the system's built-in evaluation mechanism, while the baseline acceptance scores are determined based on historical data.

[0101] and : Priority scores are usually set automatically by an expert team or algorithm in a decision support system, and benchmark priority scores are also based on historical data or industry standards.

[0102] and : The response time of each decision maker's feedback can be directly obtained from the system records, and the average response time is the arithmetic mean of all response times.

[0103] and : Satisfaction scores can also be collected through user feedback or dedicated satisfaction surveys, while benchmark satisfaction scores are determined based on industry standards or historical data.

[0104] In the embodiment of this application, it is assumed that a power company in a certain region of the State Grid needs to ensure stable operation of the power grid during the peak period of electricity consumption in summer and quickly respond to sudden failures. The company decides to introduce a decision support system to optimize the efficiency of conveying action suggestions and the response time of decision makers' feedback.

[0105] First, the decision support system is integrated with the existing power dispatching system, fault monitoring system and customer service system to ensure real-time data transmission. Sensors and monitoring equipment are used to collect real-time grid operation data, including current, voltage, temperature, etc., and record the communication time of all action suggestions and the decision maker's feedback time. Secondly, according to historical data, a scheduled communication time is set. and baseline acceptance scores , Baseline Priority Scoring .

[0106] Using the formula Calculate the communication efficiency index of each action suggestion. According to the CEI value, adjust the communication method of the action suggestion, such as through SMS, email, phone and other channels at the same time, to ensure that high-priority and highly accepted suggestions can be communicated to relevant personnel as soon as possible. Then, after each decision maker's feedback, record the response time And calculate the average response time .

[0107] Using the formula Calculate the user feedback response time. Based on the UFRT value, optimize the decision maker's feedback mechanism, such as quickly responding to common problems through an intelligent customer service system, reducing manual intervention, and improving response speed and satisfaction.

[0109] Finally, by optimizing the communication strategy, the efficiency of action suggestions was significantly improved, ensuring that timely measures could be taken during peak power consumption periods and avoiding multiple power outages. By optimizing the feedback mechanism, the decision maker's feedback response time was greatly shortened, improving customer satisfaction and reducing the complaint rate.

[0110] Figure 2 A schematic diagram of the structure of a business analysis and decision support system based on big data is provided for the embodiment of the present application. Figure 2 As shown, the system includes: An integration module 21, used to integrate real-time data streams from different sources to form a continuous data input stream; A construction module 22, configured to dynamically construct a real-time monitoring model reflecting the business status based on the data input stream, wherein the real-time monitoring model is used to capture business status changes; The analysis module 23 is used to trigger the scenario analysis mechanism when the real-time monitoring model identifies a change in the business state of a specific business, so as to evaluate the development trend of the specific business through the scenario analysis mechanism and generate a corresponding scenario report; A generating module 24, configured to apply a preset strategy generating algorithm according to the scenario report, wherein the strategy generating algorithm generates action suggestions adapted to the specific business according to the optimal action paths under different scenarios; A module 25 is provided, which is used to provide the action suggestion to a decision support interface to assist decision makers to quickly respond to business changes.

[0111] Figure 2 The business analysis and decision support system based on big data can be executed Figure 1 The implementation principle and technical effect of the business analysis and decision-making assistance method based on big data described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the business analysis and decision-making assistance system based on big data in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0112] In one possible design, Figure 2 The business analysis and decision support system based on big data in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0113] The processing component 32 is used to: integrate real-time data streams from different sources to form a continuous data input stream; based on the data input stream, dynamically construct a real-time monitoring model that reflects the business status, and the real-time monitoring model is used to capture business status changes; when the real-time monitoring model identifies changes in the business status of a specific business, trigger a scenario analysis mechanism to evaluate the development trend of the specific business through the scenario analysis mechanism and generate a corresponding scenario report; based on the scenario report, apply a preset strategy generation algorithm, and the strategy generation algorithm generates action recommendations that are suitable for the specific business based on the optimal action path under different scenarios; provide the action recommendations to a decision support interface to assist decision makers in quickly responding to business changes.

[0114] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0115] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0116] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0117] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0118] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0119] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0120] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a business analysis and decision-making assistance method based on big data.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0122] The system embodiment described above is merely illustrative, wherein 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 they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0123] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these 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 application.

Claims

1. A business analysis and decision-making assistance method based on big data, characterized in that: include: Integrate real-time data streams from different sources to form a continuous data input flow; Based on the data input stream, dynamically construct a real-time monitoring model reflecting the business status, wherein the real-time monitoring model is used to capture business status changes; When the real-time monitoring model identifies a change in the business status of a specific business, a scenario analysis mechanism is triggered to evaluate the development trend of the specific business through the scenario analysis mechanism and generate a corresponding scenario report; Based on the scenario report, a preset strategy generation algorithm is applied, wherein the strategy generation algorithm generates action suggestions adapted to the specific business according to the optimal action paths under different scenarios; The action suggestions are provided to a decision support interface to assist decision makers in responding quickly to business changes.

2. The method according to claim 1, characterized in that The dynamically building a real-time monitoring model reflecting the business status based on the data input stream includes: Using data fusion technology to integrate the data input streams and build a data lake; Based on the data lake, a real-time monitoring model that reflects the business status is dynamically constructed using a machine learning algorithm. The real-time monitoring model is used to extract key indicators from the data lake to accurately capture changes in the business status.

3. The method according to claim 1, characterized in that When the real-time monitoring model identifies a change in the business status of a specific business, a scenario analysis mechanism is triggered to evaluate the development trend of the specific business through the scenario analysis mechanism and generate a corresponding scenario report, including: When the real-time monitoring model identifies a change in the business status of a specific business, a scenario analysis mechanism is triggered; According to the changes in the business status of the specific business, different scenarios are simulated, and the development trend of the specific business under different scenarios is evaluated to obtain scenario evaluation results, where the different scenarios at least include market shrinkage, intensified competition, and policy changes; A corresponding scenario report is generated based on the scenario assessment result, and the scenario report includes an assessment of the development trend of a specific business under the corresponding scenario, identification of potential risk points, and suggestions for response strategies.

4. The method according to claim 1, characterized in that The method of applying a preset strategy generation algorithm based on the scenario report, wherein the strategy generation algorithm generates action suggestions adapted to the specific business according to the optimal action paths under different scenarios, includes: Convert key information in the scenario report into structured data, and send the structured data as input to a preset strategy generation algorithm, so that the strategy generation algorithm evaluates the details of the alternative action plan under the corresponding scenario according to the structured data to obtain an evaluation result, wherein the action plan includes an action path, and the plan details at least include plan cost, plan benefit, and plan risk; Calculating, based on the evaluation results, the solution scores of the alternative action solutions in the scenario corresponding to the structured data; Select the alternative action plan with the highest plan score as the optimal action plan, and the optimal action path corresponding to the optimal action plan can achieve the best balance among the cost of the plan, the benefit of the plan and the risk of the plan; An action suggestion adapted to the specific business is generated according to the optimal action path.

5. The method according to claim 4, characterized in that Providing the action suggestions to the decision support interface to assist decision makers in quickly responding to business changes includes: Design and implement a user-friendly decision support interface, which can receive and display action suggestions for the specific business generated by the strategy generation algorithm, and support interactive operations of decision makers; The decision maker is allowed to provide instant feedback on the action suggestions through the decision support interface.

6. The method according to claim 4, characterized in that The strategy generation algorithm evaluates the details of the alternative action plan under the corresponding scenario according to the structured data to obtain an evaluation result, including: The strategy generation algorithm evaluates the details of the alternative action plan under the corresponding scenario according to the structured data, and calculates the cost-benefit ratio and risk assessment index of the alternative action plan; Calculate a comprehensive score based on the cost-benefit ratio and risk assessment index of the alternative action plan and the obtained market adaptability score of the alternative action plan; Using the comprehensive score as the evaluation result; Among them, the cost-effectiveness ratio Calculated by the following formula: ； in, Indicates The benefits of the alternative action plans, Indicates The cost of the alternative action plan, Indicates The quality of the alternative courses of action, is a benchmark solution quality, is a tuning parameter used to control the impact of solution quality on the cost-effectiveness ratio. Indicates The implementation time of the alternative action plan, is a benchmark implementation time, is a tuning parameter used to control the effect of implementation time on the cost-effectiveness ratio; Among them, the risk assessment index Calculated by the following formula: ； in, Indicates The alternative action plan is The scores on the risk factors Indicates The average score of the alternative action plans on all risk factors. Indicates The weight of the risk factors, represents the number of risk factors, Indicates The ideal score for each risk factor is is a penalty factor that increases the risk of deviation from the ideal score, is an additional penalty factor that increases the risk of exceeding the ideal score; Among them, the comprehensive score Calculated by the following formula: ； in They are the weights of cost-effectiveness ratio, risk assessment index and market adaptability. Indicates The market suitability score of the alternative action plans, is a benchmark market fitness score, It is a tuning parameter used to control the impact of market adaptability on the comprehensive score.

7. The method according to claim 5, characterized in that Also includes: The decision support interface uses the following calculation formula to optimize the efficiency of conveying action suggestions: ； in, Indicates the efficiency index of the communication of action suggestions, Indicates the actual delivery time. Indicates the scheduled delivery time. is a positive proportional constant used to adjust the rate of change of the transmission efficiency index. Indicates The acceptance score of the action proposal, is a baseline acceptance score, is a tuning parameter used to control the impact of the acceptance score on the communication efficiency. Indicates The priority rating of the action recommendations, is a baseline priority score, It is a tuning parameter used to control the impact of priority score on communication efficiency; The decision support interface uses the following calculation formula to optimize the decision maker feedback response time of action suggestions: ； in, Indicates the user feedback response time, Indicates The response time of the decision maker feedback, represents the number of times the decision maker gives feedback, represents the average response time of all decision makers’ feedback, is a tuning parameter used to increase the impact of response time fluctuations on the overall response time. Indicates Satisfaction ratings from decision makers, is a baseline satisfaction score, is a tuning parameter used to control the impact of satisfaction ratings on decision makers’ feedback response time. is an additional tuning parameter used to increase the impact of satisfaction ratings.

8. A business analysis and decision support system based on big data, characterized in that: include: Integration module, used to integrate real-time data streams from different sources to form a continuous data input flow; A construction module, used to dynamically construct a real-time monitoring model reflecting the business status based on the data input stream, wherein the real-time monitoring model is used to capture changes in the business status; An analysis module, configured to trigger a scenario analysis mechanism when the real-time monitoring model identifies a change in the business status of a specific business, so as to evaluate the development trend of the specific business through the scenario analysis mechanism and generate a corresponding scenario report; A generation module, configured to apply a preset strategy generation algorithm based on the scenario report, wherein the strategy generation algorithm generates action suggestions adapted to the specific business based on the optimal action paths under different scenarios; A module is provided for providing the action suggestions to a decision support interface to assist decision makers in quickly responding to business changes.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a business analysis decision-making support method based on big data as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a business analysis and decision-making assistance method based on big data is implemented as described in any one of claims 1 to 7.

Images