Enterprise risk self-diagnosis method based on big data

Abstract

The invention discloses an enterprise risk self-diagnosis method based on big data, and relates to the technical field of data prediction.The enterprise risk self-diagnosis method comprises the steps that enterprise internal data and competitor external data are collected, and enterprise relative competitive advantages are evaluated regularly; predicting a product sales trend, and analyzing key factors affecting sales; a raw material and product price database is established, historical price changes are recorded, and the influence of the price changes on profits is evaluated; a risk trend is analyzed and predicted by using a time sequence, different responses are triggered according to risk severity, and key risk indexes are monitored in real time. According to the method and the system, the capacity of an enterprise for coping with uncertainty and emergencies is improved, the negative influence of risks on enterprise operation is reduced, and the enterprise can keep business continuity and stability through real-time monitoring and response.

Description

Technical Field

[0001] The present invention relates to the technical field of data prediction, and in particular to an enterprise risk self-diagnosis method based on big data. Background Art

[0002] With the rapid development of information technology and data analysis capabilities, the application of big data in the field of enterprise risk management is becoming more and more extensive. Traditional enterprise risk management methods mainly rely on static financial statement analysis and manual experience judgment, which is difficult to adapt to today's complex and changing business environment.

[0003] In recent years, with the maturity of technologies such as artificial intelligence and machine learning, risk management methods based on big data have gradually become the focus of academic and industry attention. These methods can more comprehensively and timely identify and evaluate various risks faced by enterprises through real-time collection, processing and analysis of massive data, and provide data support for enterprise decision-making. However, existing risk management methods based on big data still have some limitations. Summary of the invention

[0004] In view of the problems existing in the above-mentioned enterprise risk management methods, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to provide an enterprise risk self-diagnosis method with real-time risk monitoring and dynamic response capabilities.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, an embodiment of the present invention provides a method for self-diagnosis of enterprise risks based on big data, which includes collecting internal enterprise data and external competitor data, and regularly evaluating the relative competitive advantages of the enterprise; predicting product sales trends, and analyzing key factors affecting sales; establishing a raw material and product price database, recording historical price changes, and evaluating the impact of price changes on profits; using time series analysis to predict risk trends, and triggering different responses based on the severity of the risk, and monitoring key risk indicators in real time.

[0007] As a preferred solution of the enterprise risk self-diagnosis method based on big data described in the present invention, the evaluation of the relative competitive advantage of the enterprise includes: defining a competitor set C={C1, C2, ..., Ci}, where Ci represents the i-th competitor, and for each competitor Ci, focusing on the following core parameters: market share MS(Ci), product innovation index PI(Ci) and customer satisfaction CS(Ci); defining a time series T={T1, T2, ..., Tj}, where Tj represents the j-th time point; defining a competitive situation set S={S1, S2, S3}, where S1 is an advantageous state, S2 is a balanced state, and S3 is a disadvantageous state; the competitive situation evaluation function is: , in, , , is the weight coefficient, and + 2+ 1=1; according to , establish a mapping relationship: ,in, ∈S; if >Threshold 1, then 1; if the threshold Threshold 1, then 2. If < 2, then 3.

[0008] As a preferred solution of the enterprise risk self-diagnosis method based on big data described in the present invention, the prediction of product sales trend includes: collecting historical sales data, arranging the data in chronological order, ensuring the consistency of time intervals, decomposing the time series using the moving average method, and decomposing the time series into three components: trend, seasonality and random fluctuation: Assume that the time series data is , where U is the time point and the moving average formula is: , in, represents the trend component at time U, 1 represents the size of the moving average window; k is the half-width of the moving average window; h ranges from -k to k, representing the data of k time points forward and backward from the current time point; assuming there is cycles, then the seasonal component By calculating the average value in each cycle and normalizing it, we get: , Random Volatility Component for: , Use the ARIMA model to forecast sales for a certain period in the future, calculate the forecast interval, and provide the uncertainty range of the forecast.

[0009] As a preferred solution of the enterprise risk self-diagnosis method based on big data described in the present invention, the establishment of a raw material and product price database, recording historical price changes, and evaluating the impact of price changes on profits includes the following steps: defining a core parameter set P={P1, P2, P3, P4}, where P1 is the project ID, P2 is the price, P3 is the effective date, and P4 is the project type; the profit calculation function is: when the project ID is raw material: , When the item ID is a product: , in, For sales, For discounts, is the unit cost, is the tax rate and F is the fixed fee.

[0010] As a preferred solution of the enterprise risk self-diagnosis method based on big data described in the present invention, wherein: the project ID is one of the raw material ID or the product ID; the project type is raw material or product.

[0011] As a preferred solution of the enterprise risk self-diagnosis method based on big data described in the present invention, the risk trend prediction using time series analysis includes: , collect historical data to form a time series: , using the ARIMA time series model The prediction of time units is returned as a sequence of predicted values ​​Fi={Fi,1,Fi,2,...,Fi, } and prediction intervals: , , in, is an autoregressive polynomial of order p, is a moving average polynomial with order q, and B is the lag operator; is the value of the time series data at time t; d is the number of differences; is the white noise error term; the prediction value formula is: , in, At time t+ The predicted value of is a constant term; the obtained predicted values ​​are sorted by time and input into the predicted value sequence respectively; the prediction interval is calculated based on the standard error of the predicted value, and the upper and lower bounds are given: , in, is the standard error of the prediction; is the critical value of the standard normal distribution.

[0012] As a preferred solution of the enterprise risk self-diagnosis method based on big data described in the present invention, wherein: triggering different responses according to the severity of the risk includes: defining a risk level set L={L1, L2, L3, L4}, representing low risk, medium risk, high risk and extremely high risk respectively, calculating the proportional difference between the current value Ki and the predicted value Fi as the risk score, assigning the risk score to different risk levels, and giving corresponding responses for different risk levels.

[0013] In a second aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the enterprise risk self-diagnosis method based on big data as described in the first aspect of the present invention is implemented.

[0014] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the enterprise risk self-diagnosis method based on big data as described in the first aspect of the present invention.

[0015] The beneficial effects of the present invention are that, through comprehensive data collection and analysis, the present invention enables enterprises to adjust their business strategies in a timely manner to cope with market changes, thereby maintaining a leading position in the competition; and by predicting product sales trends and other operations, accurate prediction of future market demand is achieved, which can help enterprises maintain stability in market fluctuations and avoid economic losses caused by imbalances in supply and demand. The risk management method of the present invention improves the ability of enterprises to cope with uncertainty and emergencies, reduces the negative impact of risks on enterprise operations, and through real-time monitoring and response, enterprises can maintain business continuity and stability, thereby enhancing market competitiveness and customer trust. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 This is a flow chart of the enterprise risk self-diagnosis method based on big data. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0020] Example 1 Reference Figure 1 , which is the first embodiment of the present invention, and provides a method for self-diagnosis of enterprise risks based on big data, comprising the following steps: S1: Collect internal data of the enterprise and external data of competitors, monitor and analyze the changes in market share of the enterprise and competitors in real time, and regularly evaluate the relative competitive advantages of the enterprise.

[0021] S1.1: Collect data in real time.

[0022] Regularly obtain sales, customer, financial and other data from the company's internal system, collect external data such as competitor public information, industry news, social media comments, etc.; use natural language processing (NLP) technology to extract key information from unstructured data.

[0023] Specifically, the collected unstructured data, such as news articles, social media comments, etc., are processed using natural language processing (NLP) technology.

[0024] We developed a crawler using the Scrapy framework to crawl the websites of major competitors on a regular basis every day to collect data such as product information and price changes. In order to avoid IP being blocked, we used proxy pool technology to randomly select proxy IPs for each request.

[0025] S1.2: Assess the company's relative competitive advantages.

[0026] Define the competitor set C={C1,C2,...,Ci}, where Ci represents the i-th competitor. For each competitor Ci, pay attention to the following core parameters: market share MS(Ci), product innovation index PI(Ci) and customer satisfaction CS(Ci); define the time series T={T1,T2,...,Tj}, where Tj represents the j-th time point; define the competition situation set S={S1,S2,S3}, where: S1 is the dominant state, S2 is the balanced state, and S3 is the disadvantageous state.

[0027] The competition situation evaluation function is: , in, , , is the weight coefficient, and + 2+ 1=1; according to , establish a mapping relationship: ,in, ∈S; if >Threshold 1, then 1; if the threshold Threshold 1, then 2. If < 2, then 3.

[0028] This will help us gain a general understanding of the company's competitive intensity and its main competitors, which will facilitate further analysis.

[0029] Collect comprehensive data on the company and its main competitors, apply competitive situation assessment functions, score the company and its competitors, compare the company's competitive intensity with that of its main competitors, and identify strengths and weaknesses.

[0030] S2: Predict product sales trends and analyze key factors affecting sales.

[0031] Preferably, using time series analysis to predict product sales trends includes the following steps: Collect historical sales data, including date, product ID, sales volume, sales amount, etc., arrange the data in chronological order, ensure that the time interval is consistent (such as daily, weekly or monthly), and use the moving average method to decompose the time series into three components: trend, seasonality and random fluctuations. Specifically: Assume that the time series data is , where U is the time point and the moving average formula is: , in, represents the trend component at time U, 1 represents the size of the moving average window; k is the half-width of the moving average window; h ranges from -k to k, representing the data of k time points forward and backward from the current time point.

[0032] Assume that The seasonal component This can be obtained by calculating the average value within each period and normalizing it: , Random Volatility Component is the remainder after subtracting the trend and seasonal components from the actual value: , Use the ARIMA model to make sales forecasts for a certain period in the future (such as the next 12 months), calculate the forecast interval, provide the uncertainty range of the forecast, and use the rolling forecast method to evaluate the forecast accuracy of the model at different time points.

[0033] Furthermore, the stationarity of the time series is tested based on the ADF test. If it is non-stationary, the series is made stationary through methods such as differencing or logarithmic transformation.

[0034] Going a step further, we implemented a decision tree algorithm to analyze the key factors that affect sales: Identify factors that potentially affect sales, such as price, promotions, seasons, competitor behavior, etc., collect relevant data, ensure that they match the time of sales data, merge sales data with influencing factor data, and encode categorical variables (such as one-hot encoding); Divide the data set into a training set (such as 70%) and a test set (such as 30%), select the CART decision tree algorithm, train the decision tree model on the training set, calculate the importance contribution of each feature to the model prediction, select the top N as the key factors affecting sales, and adjust the weight of step S1.2 based on this key influencing factor.

[0035] Optionally, create an interactive dashboard to display demand changes and early warning information for each product line, including integrating sales forecast results, actual sales data, and key influencing factor data, creating sales trend charts that display historical sales, forecast sales, and forecast ranges, and displaying product line comparison charts, such as stacked bar charts or heat maps.

[0036] S3: Establish a database of raw material and product prices, record historical price changes, and evaluate the impact of price changes on profits.

[0037] Specifically, define the core parameter set P={P1,P2,P3,P4}, where: P1 is the project ID (can be the raw material ID or product ID), P2 is the price, P3 is the effective date, and P4 is the project type (raw material or product); the profit calculation function is: When the item ID is a raw material: , When the item ID is a product: , in, For sales, For discounts, is the unit cost, is the tax rate and F is the fixed fee.

[0038] Furthermore, we conduct price-profit sensitivity analysis and give the best price recommendation: Based on experience, a price range is selected for analysis, such as ±20% of the current price. Within the selected range, the price P2 is gradually adjusted by a small amount (such as 1%). For each price point, the corresponding profit is calculated, the potential impact of price changes on sales volume Q is analyzed, and a price-profit curve is drawn to find the price point that maximizes profit, and specific price adjustment suggestions are made. Among them, considering factors such as long-term customer relationships and market share, it may be necessary to weigh the maximum profit against other goals, and consider the competitive advantage evaluation results in the optimal price recommendation.

[0039] S4: Use time series analysis to predict risk trends, trigger different responses based on risk severity, and monitor key risk indicators in real time.

[0040] Specifically, a key risk indicator set K={K1, K2, ..., Km} is set, where each Ki represents a key risk indicator, for example, K1 is the accounts receivable turnover rate, K2 is the inventory turnover rate, K3 is the cash flow ratio, K4 is the customer satisfaction CS(Ci), etc.; for each , collect historical data to form a time series: , using the ARIMA time series model The prediction of time units is returned as a sequence of predicted values ​​Fi={Fi,1,Fi,2,...,Fi, } and prediction intervals: Specifically, if the data is not stationary, a difference operation is performed to make it stationary. After determining that it is stationary, appropriate ARIMA model parameters p, d, q are selected. The formula is as follows: , , in, is an autoregressive polynomial of order p, is a moving average polynomial with order q, and B is the lag operator; is the value of the time series data at time t; d is the number of differences; is the white noise error term; The predicted value formula is: , in, At time t+ The predicted value of is a constant term; the obtained predicted values ​​are sorted by time and input into the predicted value sequence respectively; the prediction interval is calculated based on the standard error of the predicted value, and the upper and lower bounds are given: , in, is the standard error of the prediction; is the critical value of the standard normal distribution.

[0041] Define the risk level set L = {L1, L2, L3, L4}, representing low risk, medium risk, high risk and extremely high risk respectively, calculate the proportional difference between the current value Ki and the predicted value Fi as the risk score, set a three-level risk threshold, assign the risk score to different risk levels L, that is, return the risk level Lj∈L, and give corresponding responses for different risk levels.

[0042] Furthermore, fuzzy logic is introduced to deal with the uncertainty in risk assessment, including the following: Set up multi-dimensional early warning indicators, including: market share change rate, sales growth rate deviation and price fluctuation range, and develop a rule-based early warning trigger mechanism; implement an automatic upgrade algorithm for early warning levels, and adjust the early warning level according to the duration and severity of the risk.

[0043] Specifically, four warning levels are set for the market share change rate, sales growth rate deviation and price fluctuation range, including: green (normal): no intervention required, yellow (warning): attention required, orange (serious): action required, red (critical): immediate intervention required; if any indicator reaches the yellow level, a yellow warning is triggered; if any indicator reaches the orange level or two indicators reach the yellow level at the same time, an orange warning is triggered; if any indicator reaches the red level or three indicators reach the yellow level at the same time, a red warning is triggered; if the current level lasts for more than the set number of days, it will be upgraded to one level, for example: the yellow warning will be automatically upgraded to orange if it lasts for 7 days; if multiple indicators are at a higher level at the same time, a rapid upgrade may be triggered, for example: two indicators reach orange at the same time, and they are immediately upgraded to red, etc.

[0044] Furthermore, risk response decision support is provided, including: Collect and organize common market risk types, research effective solutions for each risk type, and systematically organize risks and corresponding solutions into a database; analyze emerging risk situations, retrieve similar cases from the case database, sort matching results by similarity, and provide the most relevant historical cases and their response strategies.

[0045] This embodiment also provides a computer device, which is suitable for the enterprise risk self-diagnosis method based on big data, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the enterprise risk self-diagnosis method based on big data proposed in the above embodiment.

[0046] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0047] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the enterprise risk self-diagnosis method based on big data as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0048] In summary, through comprehensive data collection and analysis, the present invention enables enterprises to adjust their business strategies in a timely manner to cope with market changes, thereby maintaining a leading position in the competition; and by predicting product sales trends and other operations, accurate prediction of future market demand is achieved, which can help enterprises maintain stability in market fluctuations and avoid economic losses caused by imbalances in supply and demand. The risk management method of the present invention improves the ability of enterprises to cope with uncertainty and emergencies, reduces the negative impact of risks on enterprise operations, and through real-time monitoring and response, enterprises can maintain business continuity and stability, thereby enhancing market competitiveness and customer trust.

[0049] Example 2 Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the beneficial effects of the present invention, experimental data of an enterprise risk self-diagnosis method based on big data is provided.

[0050] The purpose of this experiment is to collect internal data of the enterprise and external data of competitors, predict product sales trends, establish a database of raw materials and product prices, and use time series analysis to predict risk trends, so as to regularly evaluate the relative competitive advantages of the enterprise, as follows: A company in the field of electronic products is used as the experimental object, and its internal data is collected, including product ID, sales volume, sales revenue, raw material cost, date, etc. At the same time, through public data and market research, relevant data of the company's main competitors, such as market share, sales revenue, product price, etc., are collected.

[0051] After data collection is completed, use the moving average method to smooth the company's sales data, calculate sales trends, analyze key factors affecting sales, such as seasonal changes and promotional activities, and determine seasonal components According to the sales trend and seasonal components, the time series is decomposed into three parts: trend, seasonality and random fluctuation.

[0052] By establishing a raw material and product price database, recording historical price change data, selecting raw material and product price data for the past two years, recording them on a monthly basis, and analyzing the impact of price changes on profits.

[0053] During the risk analysis phase, time series analysis methods are used to predict future risk trends, and different response strategies are developed based on the severity of the risk.

[0054] Establish several key risk indicators (such as supply chain disruptions, changes in market demand, etc.) and monitor these indicators in real time.

[0055] The following are the sales and price data of a certain model of smartphone of the electronic product enterprise in different time periods, as well as the historical records of raw material and product prices. The specific data are as follows: Table 1 date Product ID Sales volume (units) Sales (yuan) Raw material cost (yuan) Competitor sales (RMB) market share(%) 2023-08 SMG123A 1537 3038250 1512340 2837640 30.5 2023-09 SMG123A 1418 2828450 1425670 2745610 28.7 2023-10 SMG123A 1623 3237425 1634820 2923750 29.8 2023-11 SMG123A 1574 3138600 1572130 2789450 28.9 2023-12 SMG123A 1712 3426250 1663980 3032840 31.3 2024-01 SMG123A 1685 3372950 1628370 2957640 31.7 As can be seen from the table above, by comparing the sales and market share of enterprises in different months, we can find the fluctuation of market share and the trend of sales. The overall market share shows an upward fluctuation trend, indicating that the competitive advantage of enterprises is gradually increasing. This comprehensive data collection and comparison helps enterprises to adjust their strategies in time and maintain their competitive advantage.

[0056] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for self-diagnosis of enterprise risks based on big data, characterized by: include: Collect internal data of the enterprise and external data of competitors to regularly evaluate the relative competitive advantages of the enterprise; Predict product sales trends and analyze key factors affecting sales; Establish a database of raw material and product prices, record historical price changes, and evaluate the impact of price changes on profits; Use time series analysis to predict risk trends, trigger different responses based on risk severity, and monitor key risk indicators in real time.

2. The enterprise risk self-diagnosis method based on big data according to claim 1, characterized in that: The assessment of the relative competitive advantages of an enterprise includes: Define the competitor set C={C1,C2,...,Ci}, where Ci represents the i-th competitor. For each competitor Ci, focus on the following core parameters: market share MS(Ci), product innovation index PI(Ci) and customer satisfaction CS(Ci); Define the time series T={T1,T2,...,Tj}, where Tj represents the jth time point; Define the competitive situation set S = {S1, S2, S3}, where S1 is the dominant state, S2 is the balanced state, and S3 is the disadvantageous state; The competition situation evaluation function is: , in, , , is the weight coefficient, and + 2+ 1=1; according to , establish a mapping relationship: ,in, ∈S; if >Threshold 1, then 1; if the threshold Threshold 1, then 2. If < 2, then 3.

3. The enterprise risk self-diagnosis method based on big data according to claim 2, characterized in that: The predicted product sales trends include: Collect historical sales data, arrange the data in chronological order, ensure that the time intervals are consistent, and use the moving average method to decompose the time series into three components: trend, seasonality, and random fluctuations: Assume that the time series data is , where U is the time point and the moving average formula is: , in, represents the trend component at time U, 1 represents the size of the moving average window; k is the half-width of the moving average window; h ranges from -k to k, representing the data of k time points forward and backward from the current time point; Assume that cycles, then the seasonal component By calculating the average value in each cycle and normalizing it, we get: , Random Volatility Component for: , Use the ARIMA model to forecast sales for a certain period in the future.

4. The enterprise risk self-diagnosis method based on big data according to claim 3, characterized in that: The establishment of a raw material and product price database, recording historical price changes, and evaluating the impact of price changes on profits includes the following steps: Define the core parameter set P = {P1, P2, P3, P4}, where P1 is the project ID, P2 is the price, P3 is the effective date, and P4 is the project type; The profit calculation function is: When the item ID is a raw material: , When the item ID is a product: , in, For sales, For discounts, is the unit cost, is the tax rate and F is the fixed fee.

5. The enterprise risk self-diagnosis method based on big data according to claim 4, characterized in that: The project ID is one of the raw material ID or the product ID; The item type is either raw material or product.

6. The enterprise risk self-diagnosis method based on big data according to claim 5, characterized in that: The use of time series analysis to predict risk trends includes: For each key risk indicator , collect historical data to form a time series: , using the ARIMA time series model The prediction of time units is returned as a sequence of predicted values ​​Fi={Fi,1,Fi,2,...,Fi, } and prediction intervals: , , in, is an autoregressive polynomial of order p, is a moving average polynomial with order q, and B is the lag operator; is the value of the time series data at time t; d is the number of differences; is the white noise error term; The predicted value formula is: , in, At time t+ The predicted value of is a constant term; The obtained predicted values ​​are sorted by time and input into the predicted value sequence respectively; The prediction interval is calculated based on the standard error of the predicted value, and the upper and lower bounds of the prediction interval are: , in, is the standard error of the prediction; is the critical value of the standard normal distribution.

7. The enterprise risk self-diagnosis method based on big data according to claim 6, characterized in that: The triggering of different responses according to the severity of the risk includes: Define the risk level set L={L1,L2,L3,L4}, which represent low risk, medium risk, high risk and extremely high risk respectively. Calculate the proportional difference between the current value Ki and the predicted value Fi as the risk score, assign the risk score to different risk levels, and give corresponding responses for different risk levels.

Images