Enterprise operation risk assessment method, device and system

Abstract

The invention relates to the technical field of enterprise operation risk management, and discloses an enterprise operation risk assessment method, device and system. Comprising a data acquisition module, a data preprocessing and feature engineering module, a risk assessment model construction module, a risk assessment and analysis module and a risk early warning and decision support module, wherein the data acquisition module is used for constructing a multi-source data system based on internal data and external data of an enterprise; the data preprocessing and feature engineering module is used for cleaning and standardizing the collected internal data and external data of the enterprise; the risk assessment model construction module is used for constructing an enterprise operation risk assessment model based on a quantitative analysis model and a qualitative analysis method; the risk assessment and analysis module is used for assessing the enterprise operation risk level in real time according to the enterprise operation risk assessment model; and the risk early warning and decision support module is used for setting an early warning threshold value, and monitoring and triggering early warning in real time according to the enterprise operation risk level. And comprehensive evaluation of the enterprise operation risk is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise operation risk management, and in particular to an enterprise operation risk assessment method, device and system. Background Art

[0002] In a rapidly changing business environment, the management of business risks has become the key to the sustainable development and stable operation of enterprises. Business risks involve many aspects, including financial risks, market risks, operational risks, human resource risks, etc. These risks not only come from various aspects of internal business management, but are also affected by external factors such as the macroeconomic environment, industry policies, and market competition. Therefore, how to comprehensively and accurately assess business risks, provide timely warnings and provide decision-making support has become an important topic in enterprise management and research.

[0003] Traditional enterprise operation risk assessment relies on financial statement analysis and empirical judgment, which has obvious limitations. First, financial statement data has a lag and cannot reflect the current operation status and market changes of the enterprise in a timely manner; second, relying solely on financial data ignores the impact of non-financial factors on enterprise operation risk, such as employee satisfaction, production efficiency, market share, etc.; third, the lack of systematic risk assessment models and tools makes it difficult to conduct quantitative analysis and dynamic monitoring of enterprise operation risks.

[0004] With the development of big data, artificial intelligence and machine learning technologies, new ideas and methods have been provided for enterprise operation risk assessment. By integrating multi-source data inside and outside the enterprise and using technical means such as data preprocessing, feature engineering, and model building, a more comprehensive and accurate enterprise operation risk assessment system can be built. However, most of the risk assessment systems in existing technologies focus on single-dimensional data analysis and lack the fusion and in-depth mining of multi-source data; the risk assessment model is too simple and cannot fully reflect the complexity and dynamics of enterprise operation risks; the early warning and decision support functions are not perfect and it is difficult to meet the actual management needs of enterprises. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of the prior art and provide an enterprise operation risk assessment system, including a data acquisition module, a data preprocessing and feature engineering module, a risk assessment model building module, a risk assessment and analysis module, and a risk warning and decision support module: The data acquisition module is used to build a multi-source data system based on internal enterprise data and external data; the internal enterprise data includes financial data, human resources data, production and operation data, and sales data; the external enterprise data includes macroeconomic data, industry data, market data, and policy and regulatory data; The data preprocessing and feature engineering module is used to clean and standardize the collected internal and external data of the enterprise, and extract key feature variables based on the standardized data and the enterprise's business risk assessment needs; The risk assessment model building module is used to build an enterprise operation risk assessment model based on quantitative analysis models and qualitative analysis methods; The risk assessment and analysis module is used to assess the enterprise's operating risk level in real time according to the enterprise operating risk assessment model, and obtain the contribution of enterprise operating risk factors and risk distribution; Risk warning and decision support module: set warning thresholds, monitor in real time and trigger warnings based on the business risk level of the enterprise.

[0006] Preferably, the data acquisition module includes: an internal financial data acquisition unit, an internal non-financial data acquisition unit and an external data acquisition unit; The internal financial data acquisition unit is used to obtain the balance sheet, income statement, cash flow statement from the enterprise financial system, and extract debt repayment ability, profitability, operating capacity and cash flow indicators; The internal non-financial data collection unit is used to obtain employee structure, equipment utilization, and sales order data from human resources, production operations, and sales management respectively; The external data collection unit is used to collect macroeconomic, industry, market and policy and regulatory data.

[0007] Preferably, the data preprocessing and feature engineering module includes a data cleaning unit, a data standardization unit, and a feature extraction and selection unit; The data cleaning unit is used to process outliers and missing values ​​in the collected data, including using historical data comparison to process outliers; using industry mean filling or regression prediction to fill missing values; The data standardization unit is used to unify the dimensions of the collected data through the Z-score standardization method and standardize the collected data; The feature extraction and selection unit is used to screen out key risk features in the standardized data through principal component analysis.

[0008] Preferably, the risk assessment model construction module is used to construct an enterprise operation risk assessment model based on a quantitative analysis model and a qualitative analysis method, and includes: Taking financial indicators, market indicators, and macroeconomic indicators as independent variables and the comprehensive score of enterprise operating risk as the dependent variable, the model is trained through historical data, the regression coefficient of each variable is determined, and a risk prediction model is established; Risk assessment is performed through a neural network model, by setting the input layer nodes to the number of key indicators after feature selection, the hidden layer determines the number of layers and nodes based on experience and trial and error, and the output layer is the enterprise's operating risk level; The financial indicators include debt-paying ability, profitability, and operating capacity; the market indicators include market share and sales growth rate; and the macroeconomic indicators include GDP growth rate and inflation rate.

[0009] Preferably, the risk assessment and analysis module is used to assess the enterprise's operating risk level in real time according to the enterprise operating risk assessment model, and obtain the contribution of enterprise operating risk factors and risk distribution, including: The real-time assessment unit outputs the enterprise's current risk score or level; the risk factor analysis unit obtains the contribution of the enterprise's operating risk factors through model weights and sensitivity analysis; the risk distribution visualization unit generates a risk heat map to display the risk distribution.

[0010] Preferably, the risk warning and decision support module includes: a threshold setting unit, a real-time monitoring unit, and a decision support unit; The threshold setting unit is used to set multi-level warning thresholds based on historical data and industry standards; the real-time monitoring unit is used to connect to the enterprise information system, dynamically track risk indicators and trigger warnings; the decision support unit is used to provide risk avoidance, reduction, transfer or acceptance strategies and resource allocation suggestions.

[0011] An enterprise operation risk assessment device, applied to the enterprise operation risk assessment system, comprises: a data acquisition module, a preprocessing module, a communication module, a storage unit, a data processing module and a visualization module; The data acquisition module, preprocessing module, communication module, storage unit and visualization module are respectively connected to the data processing module.

[0012] A method for assessing business operation risk, applied to the above-mentioned device for assessing business operation risk, comprises the following steps: Step 1: Collect and integrate multi-source data from inside and outside the enterprise to build a multi-source data system; Step 2: Clean, standardize and extract features of the collected multi-source data to obtain key feature variables; Step 3: Construct a risk assessment model integrating quantitative and qualitative methods; Step 4: Using the constructed risk assessment model to assess the enterprise's operating risk level and obtain risk factors based on key characteristic variables; Step 5: Monitor the enterprise's operating risk level and obtained risk factors in real time according to the set early warning threshold.

[0013] Furthermore, the construction of the risk assessment model integrating quantitative and qualitative aspects includes: Train multiple linear regression models or neural network models for quantitative prediction; construct a judgment matrix and calculate the weights of qualitative factors through the hierarchical analysis method; and weightedly integrate the fuzzy comprehensive evaluation method with the quantitative model results.

[0014] The beneficial effects of the present invention are: integrating multi-source data inside and outside the enterprise, including financial data, human resources data, production and operation data, sales data, as well as macroeconomic data, industry data, market data, and policy and regulatory data, to achieve a comprehensive assessment of the enterprise's operating risks.

[0015] Through data preprocessing and feature engineering modules, the collected data is cleaned, standardized and feature extracted, which improves the accuracy and availability of the data. At the same time, the integration of quantitative and qualitative risk assessment models fully considers the complexity and dynamics of corporate operating risks and improves the accuracy of risk assessment.

[0016] The present invention can evaluate the business risk level of an enterprise in real time, dynamically track risk indicators, and provide timely decision support once an early warning is triggered, thereby helping the enterprise to respond to risks in a timely manner and reduce losses.

[0017] Through the risk distribution visualization unit, risk heat maps and other intuitive displays of risk assessment results are generated, allowing enterprise managers to clearly understand the risk distribution of various departments and business links of the enterprise, providing strong support for risk management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the principle of an enterprise operation risk assessment system; Figure 2 It is a schematic diagram of the principle of a device for assessing enterprise operation risk; Figure 3 The figure is a flow chart of a business risk assessment method. DETAILED DESCRIPTION

[0019] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0020] The features and performance of the present invention are further described in detail below in conjunction with the embodiments.

[0021] like Figure 1 As shown, an enterprise operation risk assessment system includes a data acquisition module, a data preprocessing and feature engineering module, a risk assessment model building module, a risk assessment and analysis module, and a risk warning and decision support module: The data acquisition module is used to build a multi-source data system based on internal enterprise data and external data; the internal enterprise data includes financial data, human resources data, production and operation data, and sales data; the external enterprise data includes macroeconomic data, industry data, market data, and policy and regulatory data; The data preprocessing and feature engineering module is used to clean and standardize the collected internal and external data of the enterprise, and extract key feature variables based on the standardized data and the enterprise's business risk assessment needs; The risk assessment model building module is used to build an enterprise operation risk assessment model based on quantitative analysis models and qualitative analysis methods; The risk assessment and analysis module is used to assess the enterprise's operating risk level in real time according to the enterprise operating risk assessment model, and obtain the contribution of enterprise operating risk factors and risk distribution; Risk warning and decision support module: set warning thresholds, monitor in real time and trigger warnings based on the business risk level of the enterprise.

[0022] The data acquisition module includes: an internal financial data acquisition unit, an internal non-financial data acquisition unit and an external data acquisition unit; The internal financial data acquisition unit is used to obtain the balance sheet, income statement, cash flow statement from the enterprise financial system, and extract debt repayment ability, profitability, operating capacity and cash flow indicators; The internal non-financial data collection unit is used to obtain employee structure, equipment utilization, and sales order data from human resources, production operations, and sales management respectively; The external data collection unit is used to collect macroeconomic, industry, market and policy and regulatory data.

[0023] The data preprocessing and feature engineering module includes a data cleaning unit, a data standardization unit, and a feature extraction and selection unit; The data cleaning unit is used to process outliers and missing values ​​in the collected data, including using historical data comparison to process outliers; using industry mean filling or regression prediction to fill missing values; The data standardization unit is used to unify the dimensions of the collected data through the Z-score standardization method and standardize the collected data; The feature extraction and selection unit is used to screen out key risk features in the standardized data through principal component analysis.

[0024] The risk assessment model construction module is used to construct an enterprise operation risk assessment model based on a quantitative analysis model and a qualitative analysis method, including: Taking financial indicators, market indicators, and macroeconomic indicators as independent variables and the comprehensive score of enterprise operating risk as the dependent variable, the model is trained through historical data, the regression coefficient of each variable is determined, and a risk prediction model is established; Risk assessment is performed through a neural network model, by setting the input layer nodes to the number of key indicators after feature selection, the hidden layer determines the number of layers and nodes based on experience and trial and error, and the output layer is the enterprise's operating risk level; The financial indicators include debt-paying ability, profitability, and operating capacity; the market indicators include market share and sales growth rate; and the macroeconomic indicators include GDP growth rate and inflation rate.

[0025] The risk assessment and analysis module is used to assess the enterprise's operating risk level in real time according to the enterprise operating risk assessment model, and obtain the contribution of enterprise operating risk factors and risk distribution, including: The real-time assessment unit outputs the enterprise's current risk score or level; the risk factor analysis unit obtains the contribution of the enterprise's operating risk factors through model weights and sensitivity analysis; the risk distribution visualization unit generates a risk heat map to display the risk distribution.

[0026] The risk warning and decision support module includes: a threshold setting unit, a real-time monitoring unit, and a decision support unit; The threshold setting unit is used to set multi-level warning thresholds based on historical data and industry standards; the real-time monitoring unit is used to connect to the enterprise information system, dynamically track risk indicators and trigger warnings; the decision support unit is used to provide risk avoidance, reduction, transfer or acceptance strategies and resource allocation suggestions.

[0027] like Figure 2 As shown, an enterprise operation risk assessment device is applied to the enterprise operation risk assessment system, comprising: a data acquisition module, a preprocessing module, a communication module, a storage unit, a data processing module and a visualization module; The data acquisition module, preprocessing module, communication module, storage unit and visualization module are respectively connected to the data processing module.

[0028] like Figure 3 As shown, a method for assessing business risk is applied to the above-mentioned device for assessing business risk, and comprises the following steps: Step 1: Collect and integrate multi-source data from inside and outside the enterprise to build a multi-source data system; Step 2: Clean, standardize and extract features of the collected multi-source data to obtain key feature variables; Step 3: Construct a risk assessment model integrating quantitative and qualitative methods; Step 4: Using the constructed risk assessment model to assess the enterprise's operating risk level and obtain risk factors based on key characteristic variables; Step 5: Monitor the enterprise's operating risk level and obtained risk factors in real time according to the set early warning threshold.

[0029] The construction of the risk assessment model integrating quantitative and qualitative aspects includes: Train multiple linear regression models or neural network models for quantitative prediction; construct a judgment matrix and calculate the weights of qualitative factors through the hierarchical analysis method; and weightedly integrate the fuzzy comprehensive evaluation method with the quantitative model results.

[0030] Specifically, the present invention provides an enterprise operation risk assessment system, comprising: Data collection module: used to build a multi-source data system based on internal and external data of the enterprise. Internal data of the enterprise includes financial data, human resources data, production operation data, and sales data.

[0031] Financial data: Obtain balance sheets, income statements, and cash flow statements from the company's financial system, and extract debt-paying ability, profitability, operating capacity, and cash flow indicators.

[0032] Human resource data includes employee structure, employee satisfaction, training records, etc. Production operation data includes equipment utilization, production efficiency, inventory levels, etc.

[0033] Sales data: sales orders, market share, sales growth rate, etc. Enterprise external data includes macroeconomic data, industry data, market data, and policy and regulatory data. Macroeconomic data: GDP growth rate, inflation rate, unemployment rate, etc. Industry data: industry growth rate, industry profit margin, competitor analysis, etc. Market data: changes in market demand, consumer behavior, market price fluctuations, etc. Policy and regulatory data: relevant laws and regulations, policy changes, etc.

[0034] The data collection module includes an internal financial data collection unit, an internal non-financial data collection unit and an external data collection unit, which are respectively used to collect the above-mentioned types of data.

[0035] Data preprocessing and feature engineering module: used to clean and standardize collected internal and external enterprise data.

[0036] Data cleaning unit: handle outliers and missing values, use historical data comparison to handle outliers, and use industry mean filling or regression prediction to fill missing values.

[0037] Data standardization unit: The dimension of collected data is unified through the Z-score standardization method, and the collected data is standardized.

[0038] Feature extraction and selection unit: Use principal component analysis (PCA), correlation analysis and other methods to screen out key risk features in standardized data and provide input for subsequent model construction.

[0039] Risk assessment model building module: Build an enterprise operation risk assessment model based on quantitative analysis models and qualitative analysis methods.

[0040] Quantitative analysis model: Multiple linear regression model: Financial indicators, market indicators, and macroeconomic indicators are used as independent variables, and the comprehensive score of business risk is used as the dependent variable. The model is trained through historical data to determine the regression coefficient of each variable.

[0041] Neural network model: The input layer nodes are set to the number of key indicators after feature selection, the number of layers and nodes in the hidden layer is determined based on experience and trial and error, and the output layer is the enterprise's operating risk level.

[0042] Qualitative analysis method: Analytical hierarchy process (AHP): Construct a judgment matrix and calculate the weight of each qualitative factor.

[0043] Fuzzy comprehensive evaluation method: qualitative factors are weighted and integrated with quantitative model results to obtain comprehensive risk assessment results.

[0044] Risk assessment and analysis module: Based on the enterprise operation risk assessment model, the enterprise operation risk level is assessed in real time to obtain the contribution of enterprise operation risk factors and risk distribution.

[0045] Real-time assessment unit: outputs the current risk score or level of the enterprise. Risk factor analysis unit: obtains the contribution of enterprise operating risk factors through model weight and sensitivity analysis and identifies key risk points.

[0046] Risk distribution visualization unit: Generates a risk heat map to display the risk distribution of each department and business link of the enterprise.

[0047] Risk warning and decision support module: set warning thresholds, monitor in real time and trigger warnings according to the enterprise's operating risk level. Threshold setting unit: set multi-level warning thresholds based on historical data and industry standards. Real-time monitoring unit: connect to the enterprise information system, dynamically track risk indicators, and trigger warnings when exceeding the warning threshold. Decision support unit: provide risk avoidance, reduction, transfer or acceptance strategies based on risk assessment results.

[0048] An enterprise operation risk assessment device, applied to the above-mentioned enterprise operation risk assessment system, comprises: Data acquisition module: used to collect internal and external data of the enterprise. Preprocessing module: cleans, standardizes and extracts features of data. Communication module: realizes communication and data transmission between the device and other parts of the system. Storage unit: stores collected data, processed data and model parameters. Visualization module: generates risk heat maps, reports, etc. to intuitively display risk assessment results.

[0049] A method for assessing business risk, applied to the above-mentioned business risk assessment device, comprises the following steps: Collect and integrate multi-source data from inside and outside the enterprise to build a multi-source data system.

[0050] The collected multi-source data is cleaned, standardized and feature extracted to obtain key feature variables.

[0051] Construct a risk assessment model that integrates quantitative and qualitative methods, including training a multivariate linear regression model or a neural network model for quantitative prediction, constructing a judgment matrix through the hierarchical analysis method and calculating the weights of qualitative factors, and weighted integration of the fuzzy comprehensive evaluation method and the quantitative model results.

[0052] Through the constructed risk assessment model, the business risk level of the enterprise is evaluated based on key characteristic variables, and the contribution of risk factors and risk distribution are obtained.

[0053] Based on the set early warning threshold, the business risk level and risk factors of the enterprise are monitored in real time, and once the early warning is triggered, timely decision support is provided.

[0054] Example: In order to comprehensively improve its business risk management capabilities, a certain smart manufacturing company decided to adopt the enterprise business risk assessment system, device and method proposed in the present invention.

[0055] Internal financial data collection unit: Automatically extract the balance sheet, income statement, and cash flow statement of the past five years from the ERP system of Smart Manufacturing Co., Ltd., and calculate debt-paying ability ratios (such as current ratio, quick ratio), profitability ratios (such as gross profit margin, net profit margin), operating ability ratios (such as inventory turnover rate, accounts receivable turnover rate) and cash flow indicators (such as net cash flow generated by operating activities).

[0056] Internal non-financial data collection unit: collects employee structure data (such as department distribution, job level), employee satisfaction survey results, and employee training records through the HR management system; obtains data such as equipment utilization, production efficiency, inventory levels, etc. from the production management system; the sales department provides sales order records, market share reports and annual sales growth rate.

[0057] External data collection unit: Use the API interface to obtain macroeconomic data such as GDP growth rate and inflation rate from the National Bureau of Statistics website; obtain industry growth rate, industry profit margin and major competitor analysis through industry research reports; market research companies provide market demand changes, consumer behavior trends and market price fluctuations data; the legal information service platform monitors relevant legal and regulatory updates and policy changes.

[0058] Data cleaning unit: Verify and adjust abnormal values ​​in internal financial data (such as a sudden surge or drop in sales) by comparing with historical data, and fill missing values ​​with industry averages; use regression prediction methods to complete missing macroeconomic indicators in external data.

[0059] Data standardization unit: Z-score standardization method was applied to all data to ensure the comparability of data of different dimensions.

[0060] Feature extraction and selection unit: Use the PCA method to extract the 10 key features that have the greatest impact on operating risk from the standardized data, including net profit margin, current ratio, market share, industry growth rate, etc.

[0061] Quantitative analysis model: Multiple linear regression model: With net profit margin, market share, and GDP growth rate as independent variables and the comprehensive score of business risk as the dependent variable, the model is trained using data from the past three years to determine the regression coefficient of each variable.

[0062] Neural network model: Design a neural network consisting of an input layer (10 nodes), two hidden layers (15 nodes each) and an output layer (1 node, indicating the risk level), use historical data for training, and optimize the model parameters.

[0063] Qualitative analysis methods: Analytic Hierarchy Process (AHP): Construct a judgment matrix to evaluate the relative importance of qualitative factors such as management experience, corporate culture, and policy adaptability, and calculate the weight of each factor.

[0064] Fuzzy comprehensive evaluation method: Combine the qualitative factor weights obtained by AHP with the output results of the quantitative model, and obtain the comprehensive risk assessment results through fuzzy calculation.

[0065] Real-time assessment unit: The system runs automatically every day and outputs the current risk score and level of Smart Manufacturing Co., Ltd. based on the latest data.

[0066] Risk Factor Analysis Unit: Through model weight analysis, it is found that fluctuations in net profit margin and market share contribute the most to business risks of the enterprise and are identified as key risk points.

[0067] Risk distribution visualization unit: Generates a risk heat map to visually show that the production department, sales department, and finance department have higher risk levels.

[0068] Threshold setting unit: Set low-risk, medium-risk and high-risk warning thresholds based on historical data and industry standards.

[0069] Real-time monitoring unit: The system is connected to the enterprise information system to monitor risk indicators in real time. When the net profit margin drops by more than the preset threshold for two consecutive months, an early warning is automatically triggered.

Claims

1. An enterprise operation risk assessment system, characterized in that: It includes data collection module, data preprocessing and feature engineering module, risk assessment model building module, risk assessment and analysis module and risk warning and decision support module: The data acquisition module is used to build a multi-source data system based on internal enterprise data and external data; the internal enterprise data includes financial data, human resources data, production and operation data, and sales data; the external enterprise data includes macroeconomic data, industry data, market data, and policy and regulatory data; The data preprocessing and feature engineering module is used to clean and standardize the collected internal and external data of the enterprise, and extract key feature variables based on the standardized data and the enterprise's business risk assessment needs; The risk assessment model building module is used to build an enterprise operation risk assessment model based on quantitative analysis models and qualitative analysis methods; The risk assessment and analysis module is used to assess the enterprise's operating risk level in real time according to the enterprise operating risk assessment model, and obtain the contribution of enterprise operating risk factors and risk distribution; Risk warning and decision support module: set warning thresholds, monitor in real time and trigger warnings based on the business risk level of the enterprise.

2. The enterprise operation risk assessment system according to claim 1, characterized in that: The data acquisition module includes: an internal financial data acquisition unit, an internal non-financial data acquisition unit and an external data acquisition unit; The internal financial data acquisition unit is used to obtain the balance sheet, income statement, cash flow statement from the enterprise financial system, and extract debt repayment ability, profitability, operating capacity and cash flow indicators; The internal non-financial data collection unit is used to obtain employee structure, equipment utilization, and sales order data from human resources, production operations, and sales management respectively; The external data collection unit is used to collect macroeconomic, industry, market and policy and regulatory data.

3. The enterprise operation risk assessment system according to claim 1, characterized in that: The data preprocessing and feature engineering module includes a data cleaning unit, a data standardization unit, and a feature extraction and selection unit; The data cleaning unit is used to process outliers and missing values ​​in the collected data, including using historical data comparison to process outliers; using industry mean filling or regression prediction to fill missing values; The data standardization unit is used to unify the dimensions of the collected data through the Z-score standardization method and standardize the collected data; The feature extraction and selection unit is used to screen out key risk features in the standardized data through principal component analysis.

4. The enterprise operation risk assessment system according to claim 1, characterized in that: The risk assessment model construction module is used to construct an enterprise operation risk assessment model based on a quantitative analysis model and a qualitative analysis method, including: Taking financial indicators, market indicators, and macroeconomic indicators as independent variables and the comprehensive score of enterprise operating risk as the dependent variable, the model is trained through historical data, the regression coefficient of each variable is determined, and a risk prediction model is established; Risk assessment is performed through a neural network model, by setting the input layer nodes to the number of key indicators after feature selection, the hidden layer determines the number of layers and nodes based on experience and trial and error, and the output layer is the enterprise's operating risk level; The financial indicators include debt-paying ability, profitability, and operating capacity; the market indicators include market share and sales growth rate; and the macroeconomic indicators include GDP growth rate and inflation rate.

5. The enterprise operation risk assessment system according to claim 1, characterized in that: The risk assessment and analysis module is used to assess the enterprise's operating risk level in real time according to the enterprise operating risk assessment model, and obtain the contribution of enterprise operating risk factors and risk distribution, including: The real-time assessment unit outputs the enterprise's current risk score or level; the risk factor analysis unit obtains the contribution of the enterprise's operating risk factors through model weights and sensitivity analysis; the risk distribution visualization unit generates a risk heat map to display the risk distribution.

6. The enterprise operation risk assessment system according to claim 1, characterized in that: The risk warning and decision support module includes: a threshold setting unit, a real-time monitoring unit, and a decision support unit; The threshold setting unit is used to set multi-level warning thresholds based on historical data and industry standards; the real-time monitoring unit is used to connect to the enterprise information system, dynamically track risk indicators and trigger warnings; the decision support unit is used to provide risk avoidance, reduction, transfer or acceptance strategies and resource allocation suggestions.

7. An enterprise operation risk assessment device, characterized in that: An enterprise operation risk assessment system applied to any one of claims 1 to 6, comprising: a data acquisition module, a preprocessing module, a communication module, a storage unit, a data processing module and a visualization module; The data acquisition module, preprocessing module, communication module, storage unit and visualization module are respectively connected to the data processing module.

8. A method for assessing business risk, characterized in that: The enterprise operation risk assessment device as claimed in claim 7 comprises the following steps: Step 1: Collect and integrate multi-source data from inside and outside the enterprise to build a multi-source data system; Step 2: Clean, standardize and extract features of the collected multi-source data to obtain key feature variables; Step 3: Construct a risk assessment model integrating quantitative and qualitative methods; Step 4: Using the constructed risk assessment model to assess the enterprise's operating risk level and obtain risk factors based on key characteristic variables; Step 5: Monitor the enterprise's operating risk level and obtained risk factors in real time according to the set early warning threshold.

9. A method for assessing business risk according to claim 8, characterized in that: The construction of the risk assessment model integrating quantitative and qualitative aspects includes: Train multiple linear regression models or neural network models for quantitative prediction; construct a judgment matrix and calculate the weights of qualitative factors through the hierarchical analysis method; and weightedly integrate the fuzzy comprehensive evaluation method with the quantitative model results.

Images