Enterprise management system based on big data analysis

Abstract

The invention discloses an enterprise management system based on big data analysis, and the system is characterized in that the system comprises a data collection module, a data preprocessing module, a data storage module, a data analysis module, a management decision module, a risk early warning module, and an intelligent cooperation module; the data acquisition module comprises an internal business data acquisition unit and an external market data acquisition unit, and the internal business data acquisition unit has a function of monitoring staff workflow data in real time; according to the invention, through an innovative data acquisition mode, the internal business data acquisition unit monitors the work flow of employees in real time, and the external market data acquisition unit captures multi-source data such as social media, data sources are comprehensively enriched, so that enterprises can know their own operation and market dynamics in multiple dimensions, and the enterprise management efficiency is improved. And a powerful basis is provided for accurate decision making.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise management systems, and more specifically, to an enterprise management system based on big data analysis. Background Art

[0002] In today's business environment, enterprises are facing increasingly complex internal and external environments and fierce market competition. Traditional enterprise management methods mainly rely on managers' experience and limited data analysis, which can no longer meet the needs of modern enterprises for efficient operation and accurate decision-making.

[0003] From the perspective of internal management, the business processes of enterprises are becoming increasingly complex, involving the collaborative work of multiple departments and links. However, traditional management models often lack real-time monitoring and data analysis of each link in the business process, making it difficult for enterprises to accurately understand the actual operation of the business and to promptly discover bottlenecks and problems in the process. For example, in manufacturing companies, traditional production management mainly relies on manual records and regular statistical reports, which makes it difficult to achieve real-time monitoring and refined management of the production process, resulting in low production efficiency and serious waste of resources.

[0004] In terms of marketing, with the globalization of the market and the diversification of consumer demand, companies need to understand market dynamics and consumer demand more accurately. Traditional market research methods often have limited sample sizes, long data collection cycles, and are difficult to fully cover target customer groups. At the same time, the information from emerging channels such as social media is not fully utilized, and it is impossible to capture consumer feedback and changes in market trends in a timely manner. For example, companies may make mistakes in product development and marketing strategies because they cannot understand consumers' evaluation of products and changes in demand in a timely manner.

[0005] In the field of financial management, traditional financial analysis mainly focuses on post-analysis of financial statements, lacking real-time monitoring and forward-looking forecasting of financial data. It is difficult to provide timely and accurate decision-making support for the company's capital flow, cost control and risk assessment. For example, when facing financial risks, the company may not be able to detect and take effective countermeasures in time, resulting in economic losses.

[0006] From the perspective of the external environment of enterprises, the advent of the big data era has made enterprises face a huge amount of data resources. These data include market data, industry data, competitor data, and macroeconomic data. However, traditional enterprise management systems lack the ability to effectively collect, store, and analyze these big data, and cannot fully tap the potential value in the data. For example, enterprises may not be able to use big data analysis to optimize supply chain management, reduce procurement costs, and improve inventory turnover.

[0007] In addition, with the rapid development of information technology, although the informatization construction of enterprises has achieved certain results, there are often data islands between various information systems, and data cannot be shared and analyzed collaboratively. This also restricts the improvement of enterprise management level. For example, the data between the sales system, production system and financial system of an enterprise cannot be effectively integrated, making it difficult for the enterprise to conduct comprehensive business analysis and decision-making.

[0008] To sum up, the traditional enterprise management methods have obvious deficiencies in data processing and analysis capabilities. There is an urgent need for an enterprise management system based on big data analysis to help enterprises achieve efficient management and accurate decision-making. Summary of the invention

[0009] The present invention proposes an enterprise management system based on big data analysis to solve the problems mentioned in the above-mentioned prior art.

[0010] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solutions: an enterprise management system based on big data analysis, including a data acquisition module, a data preprocessing module, a data storage module, a data analysis module, a management decision module, a risk warning module and an intelligent collaboration module;

[0011] The data collection module is used to collect internal and external data of the enterprise. The data collection module includes an internal business data collection unit and an external market data collection unit. The internal business data collection unit has the function of real-time monitoring of employee workflow data, and the external market data collection unit has the function of social media data capture. Through web crawler technology and natural language processing algorithms, social media comments and user feedback information related to the enterprise can be obtained in real time.

[0012] The data preprocessing module cleans and standardizes the collected data, uses intelligent data cleaning algorithms to identify and remove erroneous and duplicate data, and performs in-depth detection and repair of abnormal data based on the time series characteristics and business logic relevance of the data. For abnormal data fluctuations caused by equipment failure or network delay, the authenticity of the data is determined and corrected by establishing a time series model and a business association rule library. The data preprocessing module can also automatically perform standardized conversion of data formats based on different data types and sources;

[0013] The data analysis module uses big data analysis technology combined with evaluation formulas to conduct in-depth analysis of data. The specific formula is:

[0014]

[0015] Among them, E represents the comprehensive evaluation value of the enterprise, W i represents the weight coefficient of the i-th conventional data indicator, D iRepresents the value of the i-th regular data indicator, P j represents the weight coefficient of the jth innovation data indicator, F j represents the value of the j-th innovation data indicator;

[0016] Introducing deep learning algorithms, and building deep neural network models to extract features and identify patterns in the business and market data of enterprises, in order to discover potential rules and trends hidden in the data. Through deep learning analysis of sales data, we can predict future sales trends and changes in customer demand.

[0017] The management decision-making module formulates corporate strategies based on the analysis results. This module is used to generate regular decision-making recommendation reports and customize personalized decision-making plans, including providing marketing promotion strategies and customer positioning suggestions for the marketing department, and optimizing production processes and inventory management for the production department based on data analysis results. By establishing an enterprise operation simulation model, the effects of different decision-making plans are simulated and predicted before the decision is implemented;

[0018] The risk warning module issues warnings based on risk factors in the analysis data. It identifies the company's reputation risk and internal management risk by analyzing employee behavior data and social media data. When a large number of negative comments about the company's products appear on social media, it can issue reputation risk warnings in a timely manner. When abnormal changes occur in employee workflow data, it determines whether there are internal management problems and issues corresponding warnings. The warning method uses SMS notifications, email reminders, or system pop-ups.

[0019] The intelligent collaboration module is used to promote information exchange and collaboration between departments within the enterprise. By establishing an internal social networking platform and collaboration tools, real-time communication and file sharing between employees can be achieved. The intelligent collaboration module also automatically matches the most suitable collaboration team and partners according to the work tasks and skill characteristics of employees, improving the work efficiency and innovation ability of the enterprise. When a project requires collaboration among multiple departments, the intelligent collaboration module can quickly form a project team based on project requirements and the professional skills of employees, and provide corresponding collaboration tools and communication channels.

[0020] Furthermore, the data collection frequency of the internal business data collection unit is dynamically adjusted according to the busyness of the enterprise business, and the adjustment formula is F int =α+β×B+γ×T peak , where F int represents the frequency of internal data collection, α and β are constant coefficients, B represents the enterprise business busyness index, T peak Represents the business peak adjustment factor. When the business is at its peak, T peak The value is dynamically calculated based on historical data and real-time monitoring data.

[0021] Furthermore, the data preprocessing module adopts an intelligent data cleaning algorithm, and the error data recognition accuracy formula of the algorithm is: Where A represents the accuracy, N correct Indicates the number of incorrect data correctly identified, N total represents the total amount of actual erroneous data, η is the time adjustment coefficient, and ΔT represents the difference between the data processing time and the preset standard time. By introducing the time factor, the algorithm is encouraged to improve the processing speed while ensuring the accuracy.

[0022] Furthermore, the data storage module adopts a distributed storage architecture, and its storage capacity expansion formula is C new =C current +k×T+λ×D growth , where C new Represents the expanded storage capacity, C current represents the current storage capacity, k is the expansion factor, T represents the system running time, λ is the data growth factor, and D growth Indicates the data growth rate and dynamically adjusts the storage capacity based on the actual data growth situation.

[0023] Furthermore, the data analysis module uses machine learning algorithms to perform data mining and trend prediction, and the prediction accuracy improvement formula is P new =P old +l×M+μ×D diversity , where P new represents the improved prediction accuracy, P old represents the original prediction accuracy, l is the improvement coefficient, M represents the optimization degree of the machine learning model, μ is the data diversity coefficient, and D diversity Indicates the diversity index of the data.

[0024] Furthermore, the level of detail of the decision recommendation report generated by the management decision module is proportional to the complexity of the analysis data, and the proportional relationship formula is D level =m×C complex +ν×E importance , where D level Indicates the level of detail of the decision recommendation report, m is the proportionality coefficient, C complex represents the complexity of analyzing data, v is the decision importance coefficient, E importance An indicator that represents the importance of a decision. A decision recommendation report is generated based on data complexity and decision importance.

[0025] Furthermore, the warning sensitivity of the risk warning module is related to the potential impact of the risk factor, and the relevant formula is S sensitivity =n×I impact +ξ×Hhistory , where S sensitivity represents the warning sensitivity, n is the coefficient, I impact represents the potential impact of risk factors, ξ is the historical risk adjustment coefficient, H history It indicates the frequency of historical risk occurrence, comprehensively considers the potential impact of the risk and historical risk situation, and adjusts the warning sensitivity.

[0026] Furthermore, the data collection scope of the external market data collection unit is adaptively adjusted according to the market dynamics of the industry in which the enterprise is located, and the adjustment strategy is based on the formula Where R range Indicates the data collection range, ω is the basic range value, is the adjustment coefficient, M dynamic represents the market dynamics change index, ψ is the competitive pressure coefficient, C competition An indicator of the intensity of industry competition.

[0027] Furthermore, the training speed of the machine learning algorithm is related to the data sample size and computing resources, and the relationship formula is: Where V train Indicates the training speed, S data represents the data sample size, R resource represents the amount of computing resources, δ is the adjustment factor, τ is the algorithm optimization coefficient, A algorithm An indicator that indicates the degree of optimization of a machine learning algorithm.

[0028] Furthermore, the generation time of the decision recommendation report is related to the data processing volume and system performance, and the relevant formula is: Where T generate Indicates the generation time, T base is the base time, Q data Indicates the amount of data processing, P performance represents the system performance index, ρ is the adjustment coefficient, D complexity Represents the data complexity index.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The present invention comprehensively enriches the data sources through innovative data collection methods, including real-time monitoring of employee workflows by internal business data collection units and capture of multi-source data such as social media by external market data collection units, enabling enterprises to understand their own operations and market dynamics in multiple dimensions, providing a strong basis for accurate decision-making.

[0031] The present invention uses an advanced data preprocessing module to achieve efficient cleaning, repair and standardized conversion of data, greatly improving data quality and availability, and laying the foundation for subsequent accurate analysis.

[0032] The present invention introduces a data analysis module based on deep learning and machine learning algorithms to deeply mine the potential patterns and trends in the data, achieve accurate market forecasting and business analysis, and help enterprises plan and respond to changes in advance.

[0033] The present invention generates personalized decision-making plans for different departments and business scenarios through a management decision-making module, and provides a decision-making simulation function to reduce decision-making risks and improve the pertinence and success rate of decisions.

[0034] The present invention comprehensively monitors various risk factors through a risk early warning module, and promptly notifies management personnel to take countermeasures to reduce enterprise risk losses.

[0035] The present invention establishes an internal social network platform and collaboration tools through an intelligent collaboration module, promotes real-time communication, file sharing and efficient collaboration among employees, and stimulates the innovation potential of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a schematic block diagram of the enterprise management system based on big data analysis proposed by the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0039] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, and it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0040] Reference Figure 1 : Enterprise management system based on big data analysis, including data acquisition module, data preprocessing module, data storage module, data analysis module, management decision module, risk warning module and intelligent collaboration module;

[0041] The data collection module is used to collect internal and external data of the enterprise. The data collection module includes an internal business data collection unit and an external market data collection unit. The internal business data collection unit has the function of real-time monitoring of employee workflow data, and the external market data collection unit has the function of social media data capture. Through web crawler technology and natural language processing algorithms, it can obtain social media comments and user feedback information related to the enterprise in real time;

[0042] The data preprocessing module cleans and standardizes the collected data, uses intelligent data cleaning algorithms to identify and remove erroneous and duplicate data, and performs in-depth detection and repair of abnormal data based on the time series characteristics and business logic relevance of the data. For abnormal data fluctuations caused by equipment failure or network delay, the authenticity of the data is determined and corrected by establishing a time series model and a business association rule library. The data preprocessing module can also automatically perform standardized conversion of data formats based on different data types and sources;

[0043] The data analysis module uses big data analysis technology combined with evaluation formulas to conduct in-depth analysis of data. The specific formula is:

[0044]

[0045] Among them, E represents the comprehensive evaluation value of the enterprise, W i represents the weight coefficient of the i-th conventional data indicator, D i Represents the value of the i-th regular data indicator, P jrepresents the weight coefficient of the jth innovation data indicator, F j represents the value of the j-th innovation data indicator;

[0046] Introducing deep learning algorithms, and building deep neural network models to extract features and identify patterns in the business and market data of enterprises, in order to discover potential rules and trends hidden in the data. Through deep learning analysis of sales data, we can predict future sales trends and changes in customer demand.

[0047] The management decision-making module formulates corporate strategies based on the analysis results. This module is used to generate regular decision-making recommendation reports and customize personalized decision-making plans, including providing marketing promotion strategies and customer positioning suggestions for the marketing department, and optimizing production processes and inventory management for the production department based on data analysis results. By establishing an enterprise operation simulation model, the effects of different decision-making plans are simulated and predicted before the decision is implemented;

[0048] The risk warning module issues warnings based on risk factors in the analysis data. It identifies the company's reputation risk and internal management risk by analyzing employee behavior data and social media data. When a large number of negative comments about the company's products appear on social media, it can issue reputation risk warnings in a timely manner. When abnormal changes occur in employee workflow data, it determines whether there are internal management problems and issues corresponding warnings. The warning method uses SMS notifications, email reminders, or system pop-ups.

[0049] The intelligent collaboration module is used to promote information exchange and collaboration between departments within the enterprise. By establishing an internal social networking platform and collaboration tools, real-time communication and file sharing between employees can be achieved. The intelligent collaboration module also automatically matches the most suitable collaboration team and partners according to the work tasks and skill characteristics of employees, improving the work efficiency and innovation ability of the enterprise. When a project requires collaboration among multiple departments, the intelligent collaboration module can quickly form a project team based on project requirements and the professional skills of employees, and provide corresponding collaboration tools and communication channels.

[0050] In the present invention, the data collection frequency of the internal business data collection unit is dynamically adjusted according to the busyness of the enterprise business, and the adjustment formula is F int =α+β×B+γ×T peak , where F int represents the frequency of internal data collection, α and β are constant coefficients, B represents the enterprise business busyness index, T peak Represents the business peak adjustment factor. When the business is at its peak, T peak The value is dynamically calculated based on historical data and real-time monitoring data.

[0051] In the present invention, the data preprocessing module adopts an intelligent data cleaning algorithm, and the error data recognition accuracy formula of the algorithm is: Where A represents the accuracy, N correct Indicates the number of incorrect data correctly identified, N total represents the total amount of actual erroneous data, η is the time adjustment coefficient, and ΔT represents the difference between the data processing time and the preset standard time. By introducing the time factor, the algorithm is encouraged to improve the processing speed while ensuring the accuracy.

[0052] In the present invention, the data storage module adopts a distributed storage architecture, and its storage capacity expansion formula is C new =C current +k×T+λ×D growth , where C new Represents the expanded storage capacity, C current represents the current storage capacity, k is the expansion factor, T represents the system running time, λ is the data growth factor, and D growth Indicates the data growth rate and dynamically adjusts the storage capacity based on the actual data growth situation.

[0053] In the present invention, the data analysis module uses a machine learning algorithm to perform data mining and trend prediction, and its prediction accuracy improvement formula is P new =P old +l×M+μ×D diversity , where P new represents the improved prediction accuracy, P old represents the original prediction accuracy, l is the improvement coefficient, M represents the optimization degree of the machine learning model, μ is the data diversity coefficient, and D diversity Indicates the diversity index of the data.

[0054] In the present invention, the detail of the decision recommendation report generated by the management decision module is proportional to the complexity of the analysis data, and the proportional relationship formula is D level =m×C complex +ν×E importance , where D level Indicates the level of detail of the decision recommendation report, m is the proportionality coefficient, C complex represents the complexity of analyzing data, v is the decision importance coefficient, E importance An indicator that represents the importance of a decision. A decision recommendation report is generated based on data complexity and decision importance.

[0055] In the present invention, the warning sensitivity of the risk warning module is related to the potential impact of the risk factor, and the relevant formula is S sensitivity =n×I impact +ξ×H history , where S sensitivityrepresents the early warning sensitivity, n is the coefficient, I impact represents the potential impact of risk factors, ξ is the historical risk adjustment coefficient, H history It indicates the frequency of historical risk occurrence, comprehensively considers the potential impact of the risk and historical risk situation, and adjusts the warning sensitivity.

[0056] In the present invention, the data collection scope of the external market data collection unit is adaptively adjusted according to the market dynamics of the industry in which the enterprise is located, and the adjustment strategy is based on the formula Where R range Indicates the data collection range, ω is the basic range value, is the adjustment coefficient, M dynamic represents the market dynamics change index, ψ is the competitive pressure coefficient, C competition An indicator of the intensity of industry competition.

[0057] In the present invention, the training speed of the machine learning algorithm is related to the data sample size and computing resources, and the relationship formula is: Where V train Indicates the training speed, S data represents the data sample size, R resource represents the amount of computing resources, δ is the adjustment factor, τ is the algorithm optimization coefficient, A algorithm An indicator that indicates the degree of optimization of a machine learning algorithm.

[0058] In the present invention, the generation time of the decision recommendation report is related to the data processing volume and system performance, and the relevant formula is: Where T generate Indicates the generation time, T base is the base time, Q data Indicates the amount of data processing, P performance represents the system performance index, ρ is the adjustment coefficient, D complexity Represents the data complexity index.

[0059] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An enterprise management system based on big data analysis, characterized in that: It includes data acquisition module, data preprocessing module, data storage module, data analysis module, management decision module, risk warning module and intelligent collaboration module. The data collection module is used to collect internal and external data of the enterprise. The data collection module includes an internal business data collection unit and an external market data collection unit. The internal business data collection unit has the function of real-time monitoring of employee workflow data, and the external market data collection unit has the function of social media data capture. Through web crawler technology and natural language processing algorithms, social media comments and user feedback information related to the enterprise can be obtained in real time; The data preprocessing module cleans and standardizes the collected data, uses intelligent data cleaning algorithms to identify and remove erroneous and duplicate data, and performs in-depth detection and repair of abnormal data based on the time series characteristics and business logic relevance of the data. For abnormal data fluctuations caused by equipment failure or network delay, the authenticity of the data is determined and corrected by establishing a time series model and a business association rule library. The data preprocessing module can also automatically perform standardized conversion of data formats based on different data types and sources; The data analysis module uses big data analysis technology combined with evaluation formulas to conduct in-depth analysis of data. The specific formula is: Among them, E represents the comprehensive evaluation value of the enterprise, W i represents the weight coefficient of the i-th conventional data indicator, D i Represents the value of the i-th regular data indicator, P j represents the weight coefficient of the jth innovation data indicator, F j represents the value of the j-th innovation data indicator; Introducing deep learning algorithms, and building deep neural network models to extract features and identify patterns in the business and market data of enterprises, in order to discover potential rules and trends hidden in the data. Through deep learning analysis of sales data, we can predict future sales trends and changes in customer demand. The management decision-making module formulates corporate strategies based on the analysis results. This module is used to generate regular decision-making recommendation reports and customize personalized decision-making plans, including providing marketing promotion strategies and customer positioning suggestions for the marketing department, and optimizing production processes and inventory management for the production department based on data analysis results. By establishing an enterprise operation simulation model, the effects of different decision-making plans are simulated and predicted before the decision is implemented; The risk warning module issues warnings based on risk factors in the analysis data. It identifies the company's reputation risk and internal management risk by analyzing employee behavior data and social media data. When a large number of negative comments about the company's products appear on social media, it can issue reputation risk warnings in a timely manner. When abnormal changes occur in employee workflow data, it determines whether there are internal management problems and issues corresponding warnings. The warning method uses SMS notifications, email reminders, or system pop-ups. The intelligent collaboration module is used to promote information exchange and collaboration between departments within the enterprise. By establishing an internal social networking platform and collaboration tools, real-time communication and file sharing between employees can be achieved. The intelligent collaboration module also automatically matches the most suitable collaboration team and partners according to the work tasks and skill characteristics of employees, improving the work efficiency and innovation ability of the enterprise. When a project requires collaboration among multiple departments, the intelligent collaboration module can quickly form a project team based on project requirements and the professional skills of employees, and provide corresponding collaboration tools and communication channels.

2. The enterprise management system based on big data analysis according to claim 1, characterized in that: The data collection frequency of the internal business data collection unit is dynamically adjusted according to the busyness of the enterprise business, and the adjustment formula is F int =a+β×B+γ×T peak , where F int represents the frequency of internal data collection, α and β are constant coefficients, B represents the enterprise business busyness index, T peak Represents the business peak adjustment factor. When the business is at its peak, T peak The value is dynamically calculated based on historical data and real-time monitoring data.

3. The enterprise management system based on big data analysis according to claim 1, characterized in that: The data preprocessing module adopts an intelligent data cleaning algorithm, and the error data recognition accuracy formula of the algorithm is: Where A represents the accuracy, N correct Indicates the number of incorrect data correctly identified, N total represents the total amount of actual erroneous data, η is the time adjustment coefficient, and ΔT represents the difference between the data processing time and the preset standard time. By introducing the time factor, the algorithm is encouraged to improve the processing speed while ensuring the accuracy.

4. The enterprise management system based on big data analysis according to claim 1, characterized in that: The data storage module adopts a distributed storage architecture, and its storage capacity expansion formula is C new =C current +k×T+λ×D growth , where C new Represents the expanded storage capacity, C current represents the current storage capacity, k is the expansion factor, T represents the system running time, λ is the data growth factor, and D growth Indicates the data growth rate and dynamically adjusts the storage capacity based on the actual data growth situation.

5. The enterprise management system based on big data analysis according to claim 1, characterized in that: The data analysis module uses machine learning algorithms to perform data mining and trend prediction, and its prediction accuracy improvement formula is P new =P old +l×M+μ×D diversity , where P new represents the improved prediction accuracy, P old represents the original prediction accuracy, l is the improvement coefficient, M represents the optimization degree of the machine learning model, μ is the data diversity coefficient, and D diversity Indicates the diversity index of the data.

6. The enterprise management system based on big data analysis according to claim 1, characterized in that: The level of detail of the decision recommendation report generated by the management decision module is proportional to the complexity of the analyzed data. The proportional relationship formula is D level =m×C complex +v×E importance , where D level Indicates the level of detail of the decision recommendation report, m is the proportionality coefficient, C complex represents the complexity of analyzing data, ν is the decision importance coefficient, E importance An indicator that represents the importance of a decision. A decision recommendation report is generated based on data complexity and decision importance.

7. The enterprise management system based on big data analysis according to claim 1, characterized in that: The warning sensitivity of the risk warning module is related to the potential impact of the risk factor, and its related formula is S sensitivity =n×I impact +ξ×H history , where S sensitivity represents the early warning sensitivity, n is the coefficient, I impact represents the potential impact of risk factors, ξ is the historical risk adjustment coefficient, H history It indicates the frequency of historical risk occurrence, comprehensively considers the potential impact of the risk and historical risk situation, and adjusts the warning sensitivity.

8. The enterprise management system based on big data analysis according to claim 2, characterized in that: The data collection scope of the external market data collection unit is adaptively adjusted according to the market dynamics of the industry in which the enterprise is located, and the adjustment strategy is based on the formula Where R range Indicates the data collection range, ω is the basic range value, is the adjustment coefficient, M dynamic represents the market dynamics change index, ψ is the competitive pressure coefficient, C competition An indicator of the intensity of industry competition.

9. The enterprise management system based on big data analysis according to claim 5, characterized in that: The training speed of the machine learning algorithm is related to the data sample size and computing resources, and the relationship formula is: Where V train Indicates the training speed, S data represents the data sample size, R resource represents the amount of computing resources, δ is the adjustment factor, τ is the algorithm optimization coefficient, A algorithm An indicator that represents the degree of optimization of a machine learning algorithm.

10. The enterprise management system based on big data analysis according to claim 6, characterized in that: The generation time of the decision recommendation report is related to the data processing volume and system performance, and the relevant formula is: Where T generate Indicates the generation time, T base is the base time, Q data Indicates the amount of data processing, P perfomance represents the system performance index, ρ is the adjustment coefficient, D complexity Represents the data complexity index.

Images