Enterprise financial information risk management method and system based on cloud platform

Abstract

The invention discloses an enterprise financial information risk management method and system based on a cloud platform, and relates to the technical field of financial information risk management.The enterprise financial information risk management method based on the cloud platform specifically comprises the steps that 1, characteristic values of enterprise financial information are collected and preliminarily processed, and the processed characteristic values are sent to the cloud platform; the method comprises the steps of 1, determining various characteristic values of enterprise financial data, 2, analyzing and determining limit indexes of various characteristic values of the enterprise financial data, and establishing a prediction model of various characteristic values of the enterprise financial data, and 3, setting risk degree values based on the limit indexes of various characteristic values of the enterprise financial data, and comprehensively predicting the risk degree values of a time period to realize risk management of the enterprise financial information. According to the method, potential financial risks are found in time by monitoring and predicting enterprise financial data characteristic values in real time, the efficiency and accuracy of risk management are improved, and powerful support is provided for decisions such as investment strategy making and financial structure optimization by means of data analysis and prediction models of the cloud platform.

Description

Technical Field

[0001] The present invention belongs to the technical field of financial information risk management, and specifically relates to a cloud platform-based enterprise financial information risk management method and system. Background Art

[0002] In corporate management, the management and analysis of financial information is a crucial link. The traditional way of processing financial information mainly relies on manual collection, collation and analysis, which is not only inefficient but also easily affected by human factors, leading to doubts about the accuracy and reliability of data. With the rapid development of information technology, especially the application of cloud computing and big data technology, the way of processing corporate financial information is undergoing profound changes.

[0003] As an efficient and flexible information processing platform, the cloud platform can provide enterprises with powerful data storage, processing and analysis capabilities. Through the cloud platform, enterprises can achieve real-time monitoring, early warning and analysis of financial information, thereby improving the efficiency and accuracy of financial management. Therefore, it is urgent to give full play to the advantages of the cloud platform in financial information processing, solve the problems of collecting, processing and predicting the characteristic values ​​of financial information, and propose a method for enterprise financial information risk management based on the cloud platform. Summary of the invention

[0004] The purpose of the present invention is to provide a cloud platform-based enterprise financial information risk management method and system to solve the technical problems in the prior art that the accuracy and reliability of data are questioned due to low efficiency and susceptibility to human factors.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: The enterprise financial information risk management method based on cloud platform includes: Step 1: Collect and preliminarily process the characteristic values ​​of the enterprise's financial information, and send the processed characteristic values ​​to the cloud platform; The characteristic values ​​of enterprise financial information include enterprise asset data, liability data, account operation data and transaction data. Among them, enterprise asset data refers to the increase or decrease of enterprise assets including cash, bank deposits, fixed assets, technology value and long-term investment between different time periods; enterprise liability data refers to the increase or decrease of enterprise liabilities including short-term loans, long-term loans and bonds payable between different time periods; enterprise account operation data refers to the specific operation data of enterprise accounts generated by changes in enterprise account balances and account authority adjustments between different time periods; enterprise transaction data refers to the specific transaction data generated by the business of the enterprise itself between different time periods, including sales revenue, procurement costs, investment and financing activities, tax payment, asset disposal, borrowing and repayment; Step 2: Analyze and determine the limiting indicators of various characteristic values ​​of enterprise financial data, and establish a prediction model for various characteristic values ​​of enterprise financial data; Step 3: Set the risk level value based on the limiting indicators of various characteristic values ​​of the enterprise's financial data, comprehensively predict the risk level value of the time period, and realize the risk management of the enterprise's financial information. Furthermore, the characteristic values ​​of the enterprise financial information are collected and preliminarily processed. The specific method is as follows: The time period is divided into units of time T. Through the financial monitoring platform, the scope and objectives of financial monitoring in each time period are clarified, including determining the financial modules to be monitored. With the help of the monitoring systems deployed in various financial modules and accounts within the enterprise, real-time monitoring of financial data within the monitoring scope of each time period is realized, and the financial information set in each time period is obtained. Key features are extracted from the real-time monitored financial data in the order of time periods. The specific operation method is to set a time node every t minutes in a time period. A time period contains h time nodes, that is, the time node set in each time period is {1, ..., x, ..., h}, where x represents the xth time node in the time period. Whenever a time node is reached, the real-time monitored financial data is collected once, and then the key features of each collected data are determined. These key features include: account balance changes, capital flow direction, transaction type and amount, so as to obtain the characteristic values ​​of the enterprise financial data in each time period.

[0006] Furthermore, the limiting indicators of various characteristic values ​​of enterprise financial data are analyzed and determined. The specific method is as follows: Filter the historical time periods where the enterprise's financial information has experienced risks, analyze the characteristic values ​​of the historical enterprise's financial data within such historical time periods, and combine the relevant financial rules and restriction attributes of each financial module and account of the enterprise. These restriction attributes include: enterprise asset flow restrictions, enterprise liability change restrictions, enterprise account operation restrictions, and enterprise transaction type restrictions. Obtain restriction indicators for various characteristic values ​​of the enterprise's financial data. The restriction indicators for various characteristic values ​​of the enterprise's financial data are expressed as various restrictions set by the enterprise or relevant departments on various characteristic values ​​of the enterprise's financial data within a time period. The restriction set is obtained as ,in represents the i-th restriction index on the characteristic value of the enterprise's financial data, a represents a total of a restriction indexes. When the characteristic values ​​of various types of enterprise financial data at a certain time point do not exceed the restriction index in the restriction set, it means that the enterprise's financial information at that time point is risk-free; Furthermore, a prediction model for various characteristic values ​​of corporate financial data is established. The specific method is as follows: Using the formula Denote the polynomial prediction model, where QM represents the polynomial prediction model for the financial data of type M enterprises, and QM(x + 1) represents the predicted value of the financial data of type M enterprises at time node x + 1. Denote the model coefficients, x is the independent variable represented by the time node used, and k is the highest order of the polynomial prediction model. According to the changing trend of the eigenvalue of the financial data of type M enterprises at each time node within the historical time period, initially estimate the reasonable range of the coefficients. Through the least squares method, use the eigenvalue of the financial data of type M enterprises at each time node within the historical time period to fit the polynomial model, and obtain the coefficient value that minimizes the prediction error. Start from the low order and gradually increase the order of the polynomial. For the polynomial model of each order, use the data of the first n time nodes in each historical time period to predict the data value of the (n + 1)-th time node, where n is a positive integer and 1 < n + 1 < h. Set the prediction accuracy index. According to the prediction accuracy index, select the order with the smallest prediction accuracy index as the order of the polynomial model, and finally obtain the polynomial model with coefficients fitted and order determined.

[0007] Furthermore, set the prediction accuracy index. The specific method is as follows: Use the formula Denote the prediction accuracy index, where k represents the order of the polynomial model, g represents a total of g historical time periods are predicted, i represents the i-th historical time period, mes(k, i) represents using the polynomial model of order k to predict the i-th historical time period, the mean square error between the predicted value and the true value, rmes(k, i) represents using the polynomial model of order k to predict the i-th historical time period, the root mean square error between the predicted value and the true value, mae(k, i) represents using the polynomial model of order k to predict the i-th historical time period, the mean absolute error between the predicted value and the true value. Denote the weight coefficient of the mean square error. Denote the weight coefficient of the root mean square error. Denote the weight coefficient of the mean absolute error.

[0008] Furthermore, set the risk degree value based on the limit index of various eigenvalue of the enterprise financial data. The specific method is as follows: Use the formula represents the risk level index, where j represents the jth type of the characteristic value of the enterprise financial data, x represents the xth time node, h represents a time period including h time nodes, Y represents the risk level index, b(j) represents the restriction index corresponding to the characteristic value of the jth type of enterprise financial data, a(j, x) represents the degree of deviation of the characteristic value of the jth type of enterprise financial data at the xth time node from its corresponding restriction index, f(j) represents the weight coefficient of the characteristic value of the jth type of enterprise financial data, and c is a constant value.

[0009] Furthermore, the degree of deviation includes: Using the formula Indicates the degree of deviation, a(j, x) represents the degree of deviation of the characteristic value of the j-th type of enterprise financial data at the x-th time node with respect to its corresponding restriction index, j represents the j-th type of the characteristic value of the enterprise financial data, x represents the x-th time node, b(j) represents the restriction index corresponding to the characteristic value of the j-th type of enterprise financial data, and v(j, x) represents the predicted value of the characteristic value of the j-th type of enterprise financial data at the x-th time node.

[0010] Furthermore, the present invention also proposes a cloud platform-based enterprise financial information risk management system, which is applied to the artificial intelligence-based network security risk prediction method, including: The enterprise financial data collection and processing module is used to collect the characteristic values ​​of the enterprise financial information, perform preliminary processing on the collected characteristic values ​​of the enterprise financial information, and send the processed characteristic values ​​to the cloud platform; The enterprise financial data prediction model establishment module is used to analyze and determine the limiting indicators of various characteristic values ​​of enterprise financial data and establish prediction models for various characteristic values ​​of enterprise financial data; The financial information risk management module sets the risk level value based on the limiting indicators of various characteristic values ​​of the enterprise's financial data, comprehensively predicts the risk level value of the time period, and realizes the risk management of the enterprise's financial information.

[0011] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention analyzes the characteristic values ​​of corporate financial data in the historical time period, combines relevant financial rules and restriction attributes, establishes restriction indicators for various characteristic values ​​of corporate financial data, and uses a polynomial prediction model to fit and predict corporate financial data in the historical time period, thereby obtaining a polynomial model with coefficient fitting and determined order, and predicting future financial data based on current data, thereby helping to timely discover potential risks and take corresponding measures; 2. The present invention realizes a quantitative assessment of the risk level of enterprise financial information based on the predicted values ​​of various characteristic values ​​of enterprise financial data in the next time period, combined with restriction indicators and risk level indicators. According to the risk preference and risk management objectives of the enterprise, a threshold value of the risk level indicator is set to judge whether the current risk level of enterprise financial information is acceptable and whether risk management measures need to be taken, which helps to improve the scientificity, systematicness and effectiveness of enterprise risk management. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings 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 paying creative work.

[0013] Figure 1 A step diagram of a method for risk management of enterprise financial information based on a cloud platform is shown; Figure 2 The flowchart of the enterprise financial information risk management system based on the cloud platform is shown. DETAILED DESCRIPTION

[0014] 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.

[0015] Embodiment 1: Figure 1 The enterprise financial information risk management method based on the cloud platform shown in the figure specifically includes the following steps: Step 1: Collect and preliminarily process the characteristic values ​​of the enterprise's financial information, and send the processed characteristic values ​​to the cloud platform.

[0016] The time period is divided into units of time T. Through the financial monitoring platform, the scope and objectives of financial monitoring in each time period are clarified, including determining the financial modules to be monitored, such as corporate income, cost, profit, cash flow and specific financial indicators. With the help of the monitoring system deployed in various financial modules and accounts within the enterprise, the real-time monitoring of financial data within the monitoring scope of each time period is realized, and the financial information set in each time period is obtained. The key features are extracted from the real-time monitored financial data in the order of time periods. The specific operation method is to set a time node every t minutes in a time period. A time period contains h time nodes, that is, the time node set in each time period is {1, ..., x, ..., h}, where x represents the xth time node in the time period. Whenever a time node is reached, the real-time monitored financial data is collected once, and then the key features of each collected data are determined. These key features include: account balance changes, capital flow direction, transaction type and amount, and the characteristic values ​​of the enterprise financial data in each time period are obtained. The characteristic values ​​of the enterprise financial data include the enterprise asset data, enterprise liability data, enterprise account operation data and enterprise transaction data in each time period; Among them, enterprise asset data refers to the increase or decrease of enterprise assets including cash, bank deposits, fixed assets, technology value, and long-term investments between different time periods; Enterprise debt data refers to the changes in enterprise debt, including short-term loans, long-term loans and debts payable, between different time periods; Enterprise account operation data refers to the specific operation data of enterprise accounts generated by changes in enterprise account balances and account authority adjustments between different time periods; Enterprise transaction data refers to the specific transaction data generated by the enterprise's own business between different time periods, including sales revenue, procurement costs, investment and financing activities, tax payment, asset disposal, borrowing and repayment.

[0017] The extracted eigenvalues ​​are cleaned, sorted and formatted to ensure data consistency and readability, and the preprocessed eigenvalues ​​are uploaded to the enterprise financial data monitoring cloud platform for subsequent data analysis and decision support.

[0018] Step 2: Analyze and determine the limiting indicators of various characteristic values ​​of enterprise financial data, and establish prediction models for various characteristic values ​​of enterprise financial data.

[0019] Through the enterprise financial data monitoring cloud platform, historical time periods where risks have occurred in enterprise financial information are screened, and the characteristic values ​​of historical enterprise financial data in such historical time periods are analyzed. Combined with the relevant financial rules and restriction attributes of each enterprise's financial modules and accounts, these restriction attributes include: enterprise asset flow restrictions, enterprise liability change restrictions, enterprise account operation restrictions, and enterprise transaction type restrictions, obtain restriction indicators for various characteristic values ​​of enterprise financial data, that is, when a certain type of characteristic value in the enterprise's financial data in a certain time period exceeds the restriction indicator corresponding to this type of characteristic value, there is a risk of enterprise financial information in this time period. With the help of the monitoring system deployed in various financial modules and accounts within the enterprise, real-time monitoring of financial data within the monitoring range of each time period is realized, and enterprise financial data within each time period is obtained; Among them, the restriction index of various characteristic values ​​of enterprise financial data is expressed as various restrictions set by enterprises or relevant departments on various characteristic values ​​of enterprise financial data within a period of time, and the restriction set is obtained as ,in represents the i-th restriction index on the characteristic value of the enterprise's financial data, a represents a total of a restriction indexes. When the characteristic values ​​of various types of enterprise financial data at a certain time point do not exceed the restriction index in the restriction set, it means that the enterprise's financial information at that time point is risk-free; The characteristic values ​​of various types of enterprise financial data at each time node in the historical time period are obtained. For the characteristic values ​​of enterprise financial data of type M, the true value of the characteristic values ​​of the enterprise financial data of this type in the historical time period is determined, thereby establishing a polynomial prediction model for the financial data of type M enterprises. The specific formula of the polynomial prediction model is as follows: ; Where QM represents the polynomial prediction model for the financial data of M-type enterprises, QM(x+1) represents the predicted value of the financial data of M-type enterprises at time node x+1, represents the model coefficient, x is the independent variable represented by the time node, and k is the highest order of the polynomial prediction model.

[0020] According to the changing trend of the characteristic values ​​of the financial data of M-type enterprises at each time node in the historical time period, the reasonable range of the coefficient is preliminarily estimated. Through the least squares method, the characteristic values ​​of the financial data of M-type enterprises at each time node in the historical time period are used to fit the polynomial model to find the coefficient value that minimizes the prediction error; Starting from the lower order, gradually increase the order of the polynomial. For each polynomial model of a certain order, use the data of the first n time nodes in each historical time period to predict the data value of the (n + 1)-th time node, where n is a positive integer and 1 < n + 1 < h. Then compare the predicted value with the true value, and set the prediction accuracy index by integrating the mean square error index, root mean square error index, and mean absolute error index. The specific formula is as follows: ; Among them, k represents the order of the polynomial model, g represents the total number of historical time periods for prediction, i represents the i-th historical time period, mes(k, i) represents the mean square error between the predicted value and the true value when using the polynomial model of order k to predict the i-th historical time period, rmes(k, i) represents the root mean square error between the predicted value and the true value when using the polynomial model of order k to predict the i-th historical time period, mae(k, i) represents the mean absolute error between the predicted value and the true value when using the polynomial model of order k to predict the i-th historical time period. represents the weight coefficient of the mean square error, represents the weight coefficient of the root mean square error, represents the weight coefficient of the mean absolute error.

[0021] According to the prediction accuracy index, select the order with the smallest prediction accuracy index as the order of the polynomial model, and finally obtain the polynomial model with coefficients fitted and order determined.

[0022] Step 3: Set the risk degree value based on the limit indicators of various eigenvalue features of the enterprise financial data, and integrate the risk degree values of the prediction time period to achieve the risk management of the enterprise financial information.

[0023] Use the polynomial model with coefficients fitted and order determined to predict various eigenvalue features of the enterprise financial data based on the data of the current time period, and obtain the predicted values of the enterprise asset data, enterprise liability data, enterprise account operation data, and enterprise transaction data in the next time period. Represent the types of enterprise financial data eigenvalue features with numbers, where different numbers represent different types of enterprise financial data eigenvalue features. Compare with the limit set, and determine the risk degree index according to the different types of eigenvalue features of the enterprise financial data and their corresponding limit indicators at different time nodes. The specific calculation formula of the risk degree index is as follows: ; Among them, j represents the jth type of the characteristic value of the enterprise financial data, x represents the xth time node, h represents a time period including h time nodes, Y represents the risk level index, b(j) represents the restriction index corresponding to the characteristic value of the jth type of enterprise financial data, a(j, x) represents the degree of deviation of the characteristic value of the jth type of enterprise financial data at the xth time node from its corresponding restriction index, f(j) represents the weight coefficient of the characteristic value of the jth type of enterprise financial data, c is a constant value, and c=1 is set in this embodiment.

[0024] The specific formula for the degree of deviation is as follows: ; Among them, j represents the j-th type of the characteristic value of the enterprise financial data, x represents the x-th time node, b(j) represents the restriction index corresponding to the characteristic value of the j-th type of enterprise financial data, and v(j, x) represents the predicted value of the characteristic value of the j-th type of enterprise financial data at the x-th time node.

[0025] According to the enterprise's risk preference and risk management objectives, a threshold M of the risk level indicator is set. The threshold M is used to determine whether the current risk level of the enterprise's financial information is acceptable and whether risk management measures need to be taken. When the risk level indicator of the forecast time period exceeds the threshold M, risk management measures are triggered, including: avoiding or reducing risks by adjusting investment strategies and optimizing financial structures, and transferring part of the risks to third parties through insurance, cooperation, etc.; when the risk level indicator of the forecast time period does not exceed the threshold M, it indicates that the current risk level of the enterprise's financial information is within an acceptable range and no intervention is required.

[0026] Embodiment 2: Figure 2 The enterprise financial information risk management system based on the cloud platform shown specifically includes the following contents: an enterprise financial data collection and processing module, an enterprise financial data prediction model establishment module and a financial information risk management module; Among them, the enterprise financial data collection and processing module is used to collect the characteristic values ​​of enterprise financial information, and preliminarily process the collected characteristic values ​​of enterprise financial information, and send the processed characteristic values ​​to the cloud platform, divide the time period into units of time T, and clarify the scope and objectives of financial monitoring in each time period through the financial monitoring platform, including determining the financial modules to be monitored, such as enterprise income, cost, profit, cash flow and specific financial indicators. With the help of the monitoring system deployed in various financial modules and accounts within the enterprise, real-time monitoring of financial data within the monitoring scope of each time period is realized, and the financial information set within each time period is obtained. Key features are extracted from the real-time monitored financial data in the order of time periods. The specific operation method is to set a time node every t minutes in a time period, and a time period contains h time nodes, that is, the time node set in each time period is {1, ..., x, ..., h}, where x represents the xth time node in the time period. Whenever a time node is reached, the real-time monitored financial data is collected, and then the key features of each collected data are determined. These key features include: account balance changes, fund flow direction, transaction type and amount, and the characteristic values ​​of the enterprise financial data in each time period are obtained. The characteristic values ​​of the enterprise financial data include the enterprise asset data, enterprise liability data, enterprise account operation data and enterprise transaction data in each time period; Among them, enterprise asset data refers to the increase or decrease of enterprise assets including cash, bank deposits, fixed assets, technology value, and long-term investments between different time periods; Enterprise debt data refers to the changes in enterprise debt, including short-term loans, long-term loans and debts payable, between different time periods; Enterprise account operation data refers to the specific operation data of enterprise accounts generated by changes in enterprise account balances and account authority adjustments between different time periods; Enterprise transaction data refers to the specific transaction data generated by the enterprise's own business between different time periods, including sales revenue, procurement costs, investment and financing activities, tax payment, asset disposal, borrowing and repayment.

[0027] The extracted eigenvalues ​​are cleaned, sorted and formatted to ensure data consistency and readability, and the preprocessed eigenvalues ​​are uploaded to the enterprise financial data monitoring cloud platform for subsequent data analysis and decision support.

[0028] The enterprise financial data prediction model establishment module is used to analyze and determine the restriction indicators of various characteristic values ​​of enterprise financial data, establish prediction models for various characteristic values ​​of enterprise financial data, screen historical time periods where enterprise financial information has experienced risks through the enterprise financial data monitoring cloud platform, analyze the characteristic values ​​of historical enterprise financial data in such historical time periods, and combine the relevant financial rules and restriction attributes of various financial modules and accounts of the enterprise. These restriction attributes cover: enterprise asset flow restrictions, enterprise liability change restrictions, enterprise account operation restrictions, and enterprise transaction type restrictions. Restriction indicators for various characteristic values ​​of enterprise financial data are obtained, that is, when a certain type of characteristic value in the enterprise financial data in a certain time period exceeds the restriction indicator corresponding to the characteristic value, there is a risk of enterprise financial information in the time period. With the help of the monitoring system deployed in various financial modules and accounts within the enterprise, real-time monitoring of financial data within the monitoring range of each time period is realized, and enterprise financial data within each time period is obtained; Among them, the restriction index of various characteristic values ​​of enterprise financial data is expressed as various restrictions set by enterprises or relevant departments on various characteristic values ​​of enterprise financial data within a period of time, and the restriction set is obtained as ,in represents the i-th restriction index on the characteristic value of the enterprise's financial data, a represents a total of a restriction indexes. When the characteristic values ​​of various types of enterprise financial data at a certain time point do not exceed the restriction index in the restriction set, it means that the enterprise's financial information at that time point is risk-free; The characteristic values ​​of various types of enterprise financial data at each time node in the historical time period are obtained. For the characteristic values ​​of enterprise financial data of type M, the true value of the characteristic values ​​of the enterprise financial data of this type in the historical time period is determined, thereby establishing a polynomial prediction model for the financial data of type M enterprises. The specific formula of the polynomial prediction model is as follows: ; Where QM represents the polynomial prediction model for the financial data of M-type enterprises, QM(x+1) represents the predicted value of the financial data of M-type enterprises at time node x+1, represents the model coefficient, x is the independent variable represented by the time node, and k is the highest order of the polynomial prediction model.

[0029] According to the changing trend of the characteristic values ​​of the financial data of M-type enterprises at each time node in the historical time period, the reasonable range of the coefficient is preliminarily estimated. Through the least squares method, the characteristic values ​​of the financial data of M-type enterprises at each time node in the historical time period are used to fit the polynomial model to find the coefficient value that minimizes the prediction error; Starting from the lower order, gradually increase the order of the polynomial. For each polynomial model of a certain order, use the data of the first n time nodes in each historical time period to predict the data value of the (n + 1)-th time node, where n is a positive integer and 1 < n + 1 < h. Then compare the predicted value with the true value, and set the prediction accuracy index by integrating the mean square error index, root mean square error index, and mean absolute error index. The specific formula is as follows: ; Among them, k represents the order of the polynomial model, g represents the total number of historical time periods for prediction, i represents the i-th historical time period, mes(k, i) represents the mean square error between the predicted value and the true value when using the polynomial model of order k to predict the i-th historical time period, rmes(k, i) represents the root mean square error between the predicted value and the true value when using the polynomial model of order k to predict the i-th historical time period, and mae(k, i) represents the mean absolute error between the predicted value and the true value when using the polynomial model of order k to predict the i-th historical time period. represents the weight coefficient of the mean square error, represents the weight coefficient of the root mean square error, represents the weight coefficient of the mean absolute error.

[0030] According to the prediction accuracy index, select the order with the smallest prediction accuracy index as the order of the polynomial model, and finally obtain the polynomial model with coefficient fitting and determined order.

[0031] The financial information risk management module sets the risk degree value based on the limit indicators of various characteristic values of the enterprise's financial data, integrates the risk degree values of the prediction time period, and realizes the risk management of the enterprise's financial information. Use the polynomial model with coefficient fitting and determined order to predict various characteristic values of the enterprise's financial data based on the data of the current time period, and obtain the predicted values of the enterprise's asset data, liability data, account operation data, and transaction data in the next time period. Represent the types of the characteristic values of the enterprise's financial data with numbers, and different numbers represent different types of characteristic values of the enterprise's financial data. Compare with the limit set, and determine the risk degree index according to the different types of characteristic values of the enterprise's financial data and their corresponding limit indicators at different time nodes. The specific calculation formula of the risk degree index is as follows: ; Among them, j represents the jth type of the characteristic value of the enterprise financial data, x represents the xth time node, h represents a time period including h time nodes, Y represents the risk level index, b(j) represents the restriction index corresponding to the characteristic value of the jth type of enterprise financial data, a(j, x) represents the degree of deviation of the characteristic value of the jth type of enterprise financial data from its corresponding restriction index at the xth time node, f(j) represents the weight coefficient of the characteristic value of the jth type of enterprise financial data, and c is a constant value.

[0032] The specific formula for the degree of deviation is as follows: ; Among them, j represents the j-th type of the characteristic value of the enterprise financial data, x represents the x-th time node, b(j) represents the restriction index corresponding to the characteristic value of the j-th type of enterprise financial data, and v(j, x) represents the predicted value of the characteristic value of the j-th type of enterprise financial data at the x-th time node.

[0033] According to the enterprise's risk preference and risk management objectives, a threshold M of the risk level indicator is set. The threshold M is used to determine whether the current risk level of the enterprise's financial information is acceptable and whether risk management measures need to be taken. When the risk level indicator of the forecast time period exceeds the threshold M, risk management measures are triggered, including: avoiding or reducing risks by adjusting investment strategies and optimizing financial structures, and transferring part of the risks to third parties through insurance, cooperation, etc.; when the risk level indicator of the forecast time period does not exceed the threshold M, it indicates that the current risk level of the enterprise's financial information is within an acceptable range and no intervention is required.

[0034] The above description is only a preferred specific implementation manner 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 scheme and inventive concept 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.

[0035] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A cloud platform-based enterprise financial information risk management method and system, characterized in that: include: Step 1: Collect and preliminarily process the characteristic values ​​of the enterprise's financial information, and send the processed characteristic values ​​to the cloud platform; The characteristic values ​​of enterprise financial information include enterprise asset data, liability data, account operation data and transaction data. Among them, enterprise asset data refers to the increase or decrease of enterprise assets including cash, bank deposits, fixed assets, technology value and long-term investment between different time periods; enterprise liability data refers to the increase or decrease of enterprise liabilities including short-term loans, long-term loans and bonds payable between different time periods; enterprise account operation data refers to the specific operation data of enterprise accounts generated by changes in enterprise account balances and account authority adjustments between different time periods; enterprise transaction data refers to the specific transaction data generated by the business of the enterprise itself between different time periods, including sales revenue, procurement costs, investment and financing activities, tax payment, asset disposal, borrowing and repayment; Step 2: Analyze and determine the limiting indicators of various characteristic values ​​of enterprise financial data, and establish a prediction model for various characteristic values ​​of enterprise financial data; Step 3: Set the risk level value based on the limiting indicators of various characteristic values ​​of the enterprise's financial data, comprehensively predict the risk level value of the time period, and realize the risk management of the enterprise's financial information.

2. The enterprise financial information risk management method and system based on the cloud platform according to claim 1 is characterized in that: Collect and preliminarily process the characteristic values ​​of corporate financial information. The specific method is as follows: The time period is divided into units of time T. Through the financial monitoring platform, the scope and objectives of financial monitoring in each time period are clarified, including determining the financial modules to be monitored. With the help of the monitoring systems deployed in various financial modules and accounts within the enterprise, real-time monitoring of financial data within the monitoring scope of each time period is realized, and the financial information set in each time period is obtained. Key features are extracted from the real-time monitored financial data in the order of time periods. The specific operation method is to set a time node every t minutes in a time period. A time period contains h time nodes, that is, the time node set in each time period is {1, ..., x, ..., h}, where x represents the xth time node in the time period. Whenever a time node is reached, the real-time monitored financial data is collected once, and then the key features of each collected data are determined. These key features include: account balance changes, capital flow direction, transaction type and amount, so as to obtain the characteristic values ​​of the enterprise financial data in each time period.

3. The enterprise financial information risk management method and system based on cloud platform according to claim 1, characterized in that: Analyze and determine the limiting indicators of various characteristic values ​​of corporate financial data. The specific method is: Filter the historical time periods where the enterprise's financial information has experienced risks, analyze the characteristic values ​​of the historical enterprise's financial data within such historical time periods, and combine the relevant financial rules and restriction attributes of each financial module and account of the enterprise. These restriction attributes cover enterprise asset flow restrictions, enterprise liability change restrictions, enterprise account operation restrictions, and enterprise transaction type restrictions. Obtain restriction indicators for various characteristic values ​​of enterprise financial data. The restriction indicators for various characteristic values ​​of enterprise financial data are expressed as various restrictions set by the enterprise or relevant departments on various characteristic values ​​of enterprise financial data within a time period. The restriction set is obtained as ,in It represents the i-th restriction index on the characteristic value of enterprise financial data, a represents a total of a restriction indexes. When the characteristic values ​​of various types of enterprise financial data at a certain time point do not exceed the restriction index in the restriction set, it means that the enterprise financial information at that time point is risk-free.

4. The enterprise financial information risk management method and system based on cloud platform according to claim 1, characterized in that: Establish a prediction model for various characteristic values ​​of corporate financial data. The specific method is: Using the formula represents a polynomial prediction model, where QM represents a polynomial prediction model for the financial data of M-type enterprises, QM(x+1) represents the predicted value of the financial data of M-type enterprises at time node x+1, represents the model coefficient, x is the independent variable represented by the time node, and k is the highest order of the polynomial prediction model; According to the changing trend of the characteristic values ​​of the financial data of M-type enterprises at each time node in the historical time period, the reasonable range of the coefficient is preliminarily estimated. Through the least squares method, the characteristic values ​​of the financial data of M-type enterprises at each time node in the historical time period are used to fit the polynomial model to find the coefficient value that minimizes the prediction error; Starting from the lower order, gradually increase the order of the polynomial. For each polynomial model of a certain order, use the data of the first n time nodes in each historical time period to predict the data value of the (n + 1)-th time node, where n is a positive integer and 1 < n + 1 < h. Set the prediction accuracy index, and according to the prediction accuracy index, select the order with the smallest prediction accuracy index as the order of the polynomial model. Finally, obtain a polynomial model with coefficients fitted and the order determined.

5. The enterprise financial information risk management method and system based on cloud platform according to claim 4 is characterized in that: Set the prediction accuracy index. The specific method is as follows: Using the formula represents the prediction accuracy index, k represents the order of the polynomial model, g represents a total of g historical time periods are predicted, i represents the ith historical time period, mes(k, i) represents the mean square error between the predicted value and the true value when the k-order polynomial model is used to predict the ith historical time period, rmes(k, i) represents the root mean square error between the predicted value and the true value when the k-order polynomial model is used to predict the ith historical time period, mae(k, i) represents the mean absolute error between the predicted value and the true value when the k-order polynomial model is used to predict the ith historical time period, represents the weight coefficient of the mean square error, represents the weight coefficient of the root mean square error, The weight coefficient representing the mean absolute error.

6. The enterprise financial information risk management method and system based on cloud platform according to claim 1, characterized in that: Set the risk level value based on the limit index of various eigenvalue of enterprise financial data. The specific method is as follows: Using the formula represents the risk level index, where j represents the jth type of the characteristic value of the enterprise financial data, x represents the xth time node, h represents a time period including h time nodes, Y represents the risk level index, b(j) represents the restriction index corresponding to the characteristic value of the jth type of enterprise financial data, a(j, x) represents the degree of deviation of the characteristic value of the jth type of enterprise financial data at the xth time node from its corresponding restriction index, f(j) represents the weight coefficient of the characteristic value of the jth type of enterprise financial data, and c is a constant value.

7. The enterprise financial information risk management method and system based on cloud platform according to claim 6 is characterized in that: The degree of deviation, specifically including: Using the formula Indicates the degree of deviation, a(j, x) represents the degree of deviation of the characteristic value of the j-th type of enterprise financial data at the x-th time node with respect to its corresponding restriction index, j represents the j-th type of the characteristic value of the enterprise financial data, x represents the x-th time node, b(j) represents the restriction index corresponding to the characteristic value of the j-th type of enterprise financial data, and v(j, x) represents the predicted value of the characteristic value of the j-th type of enterprise financial data at the x-th time node.

8. An enterprise financial information risk management system based on a cloud platform, applied to the network security risk prediction method based on artificial intelligence according to any one of claims 1 to 7, characterized in that: Including: An enterprise financial data acquisition and processing module, which is used to acquire the eigenvalues of enterprise financial information, preliminarily process the acquired eigenvalues of enterprise financial information, and send the processed eigenvalues to the cloud platform; An enterprise financial data prediction model establishment module, which is used to analyze and determine the limit indexes of various eigenvalues of enterprise financial data and establish a prediction model for various eigenvalues of enterprise financial data; A financial information risk management module, which sets the risk level value based on the limit indexes of various eigenvalues of enterprise financial data, and comprehensively calculates the risk level value of the prediction time period to achieve the risk management of enterprise financial information.

Images