Enterprise financial management system based on financial information processing

Abstract

The invention discloses an enterprise financial management system based on financial information processing, which relates to the technical field of financial management, is used for solving the problem of risk assessment misjudgment caused by financial data volume reduction and financial risk and controllable force change, and comprises the steps of collecting historical data, determining financial data types and enterprise risk assessment indexes according to the historical data, and determining the financial data types and the enterprise risk assessment indexes. Setting a statistical deadline, collecting enterprise data and financial change data within the statistical deadline, integrating the enterprise data and the financial change data, analyzing the controllability of different types of financial data by using a hierarchical anomaly detection method, and collecting environmental data when the controllability degree of the financial data is low. Constructing a support vector machine model by integrating the controllability degree of the financial data and the environmental data, evaluating financial risk changes according to an output result of the support vector machine model, adjusting risk evaluation indexes according to the financial risk changes, performing simulation testing, and collecting feedback data; the statistical deadline is dynamically planned according to the feedback data, so that the risk assessment index is adjusted more timely, and the decision-making strain is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of financial management, and more specifically, to an enterprise financial management system based on financial information processing. Background Art

[0002] Financial management technology is a technology that improves the financial management level and operating efficiency of an enterprise. It is widely used in the daily operations, strategic decision-making and risk control of an enterprise. The application of financial management technology in risk control can more accurately predict project risks, reduce the risks caused by changes in financial data, and ensure the smooth progress of the project.

[0003] The prior art has the following deficiencies: Generally, when the amount of corporate financial data decreases, the financial risk assessment and control capabilities will also decrease. When the risk assessment indicators do not change, it will lead to misreporting of corporate financial risks and difficulties in corporate turnover. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an enterprise financial management system based on financial information processing, which adjusts the risk assessment indicators by analyzing the risks and controllability decline of financial data to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: An enterprise financial management system based on financial information processing, comprising: a data acquisition module, a data analysis module, a risk assessment module and an adjustment feedback module, and signal connections between the modules; The data acquisition module is used to collect various analytical data in the system and send the collected analytical data to different modules for processing; The data analysis module is used to determine and record the types of financial data and risk assessment indicators, analyze the controllability of the overall financial data, and send the judgment results of the controllability of the overall financial data to the risk assessment module; The risk assessment module is used to assess the change of financial risk. If the change of financial risk is too high, the risk assessment index will be adjusted and the adjustment signal will be transmitted to the adjustment feedback module; The adjustment feedback module is used to receive the adjustment signal, collect feedback data, and dynamically plan the statistical period according to the feedback data.

[0006] In a preferred embodiment, the various analytical data collected by the data collection module include historical data, enterprise data, financial change data and environmental data. The data collection module sets a statistical period when collecting enterprise data and financial change data, and collects enterprise data and financial change data within the statistical period.

[0007] In a preferred embodiment, the historical data includes financial data tags and initial risk assessment indicators; the enterprise data is the project change amount; the financial change data is the change amount of various financial data; The data analysis module determines and records the types of financial data and risk assessment indicators based on historical data, and uses the layered anomaly detection method to analyze the controllability of the overall financial data after preprocessing the enterprise data and financial change data.

[0008] In a preferred embodiment, the data analysis module uses the hierarchical anomaly detection method to analyze the controllability of the overall financial data. The specific steps are as follows: Divide the changes in various types of financial data into layers; set controllability thresholds for each layer based on the project changes; mark and count the financial data that exceeds the controllability threshold as abnormal; set abnormal data thresholds; and determine the controllability of the overall financial data based on the comparison of the statistics of the abnormally marked financial data with the abnormal data thresholds.

[0009] In a preferred embodiment, the environmental data is the change in similar enterprise projects. The risk assessment module constructs a support vector machine model based on the controllability of the financial data and the environmental data, and assesses the change in financial risk based on the output of the support vector machine model.

[0010] In a preferred embodiment, the risk assessment module constructs a support vector machine model in the following steps: Step S1: Set input and output; Step S2: Select a kernel function to calculate the training result; Step S3: Divide the training set and the test set and perform training through the kernel function; Step S4: Set the loss function to converge the kernel function training result.

[0011] In a preferred embodiment, when adjusting the initial risk assessment index, the risk assessment module sets an adjustment ratio based on the enterprise data and the financial change data, and uses the product of the initial risk assessment index and the adjustment ratio as the adjusted risk assessment index.

[0012] In a preferred embodiment, after receiving the adjustment signal, the adjustment feedback module performs a simulation test to collect feedback data and dynamically plans the statistical period. When performing the simulation test, the adjustment feedback module sets the period ratio according to the test results, and uses the product of the previous statistical period and the period ratio as the updated statistical period.

[0013] In a preferred embodiment, the specific steps of adjusting the simulation test in the feedback module are as follows: Set the sample time according to the last statistical period; record the number of data marked as abnormal in the last statistical period, and collect the same financial data within the sample time to count the number of data marked as abnormal; compare the number of data marked as abnormal during the sample time with the number of data marked as abnormal in the last statistical period, set the period ratio and update the statistical period.

[0014] The technical effects and advantages of the enterprise financial management system based on financial information processing of the present invention are as follows: The present invention collects historical data, determines the types of financial data and enterprise risk assessment indicators based on the historical data, sets a statistical period, collects enterprise data and financial change data within the statistical period, analyzes the controllability of different types of financial data by combining the enterprise data and the financial change data, collects environmental data when the controllability of financial data is low, evaluates financial risk changes by combining the controllability of financial data and environmental data, adjusts risk assessment indicators according to financial risk changes, collects feedback data, and dynamically plans the statistical period based on the feedback data. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention is a schematic diagram of the structure of an enterprise financial management system based on financial information processing.

[0016] Figure 2 The present invention is a flow chart of an enterprise financial management system based on financial information processing. DETAILED DESCRIPTION

[0017] 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.

[0018] The present invention collects historical data, determines the types of financial data and enterprise risk assessment indicators based on the historical data, sets a statistical period, collects enterprise data and financial change data within the statistical period, analyzes the controllability of different types of financial data by combining the enterprise data and the financial change data, collects environmental data when the controllability of financial data is low, evaluates financial risk changes by combining the controllability of financial data and environmental data, adjusts risk assessment indicators based on financial risk changes, collects feedback data, and dynamically plans the statistical period based on the feedback data so as to adjust risk assessment indicators more timely, thereby improving decision-making adaptability.

[0019] Examples, such as Figure 1 and Figure 2As shown, an enterprise financial management system based on financial information processing includes: a data acquisition module, a data analysis module, a risk assessment module and an adjustment feedback module, and the modules are connected by signals.

[0020] The functions of each module are as follows: The data acquisition module is used to collect various analytical data in the system and send the collected analytical data to different modules for processing. The analytical data includes historical data, enterprise data, financial change data and environmental data. Historical data includes financial data labels and initial risk assessment indicators; enterprise data is the project change amount; financial change data is the change amount of various financial data; environmental data is the change amount of similar enterprise projects.

[0021] The data analysis module is used to receive historical data, enterprise data and financial change data, determine the type of financial data and initial risk assessment indicators based on the historical data and record them, pre-process the enterprise data and financial change data, and use the layered anomaly detection method to analyze the controllability of the overall financial data, and send the judgment result of the controllability of the overall financial data to the risk assessment module.

[0022] The risk assessment module is used to receive the controllability judgment results and environmental data, build a support vector machine model based on the controllability of financial data and environmental data, and evaluate the change of financial risk according to the output results of the support vector machine model. If the financial risk change is too high, the initial risk assessment indicator will be adjusted and the adjustment signal will be transmitted to the adjustment feedback module.

[0023] The adjustment feedback module is used to receive adjustment signals and collect feedback data, dynamically plan the statistical period based on the feedback data, and re-collect enterprise data and financial change data based on the statistical period to analyze the importance of various financial data.

[0024] It should be noted that historical data can be obtained by accessing the company's historical database, corporate data and financial change data can be collected by accessing the company's database, environmental data can usually be collected by accessing the regular financial reports of similar projects of other listed companies, and feedback data is the adjustment indicator test results of the simulation test after the adjustment feedback module receives the adjustment signal.

[0025] After receiving the historical data, the data analysis module records the initial risk assessment indicators of the enterprise and classifies the financial data according to the financial data tags. When receiving enterprise data and financial change data, the data analysis module sets a statistical period, that is, randomly selects a period of time as the receiving time, and receives the enterprise data and financial change data within the receiving time.

[0026] It needs to be explained that enterprise data refers to the change in project data, financial change data refers to the change in various types of financial data, and the data collection module only collects the number of projects and various types of financial data.

[0027] The data analysis module needs to pre-process the enterprise data and financial change data when receiving them. The specific steps are as follows: The receiving time is divided into two periods from the midpoint, marked as the upper half receiving time and the lower half receiving time respectively. The number of projects and the amount of various financial data received are received at the two end times respectively, and the number of projects and the amount of various financial data received in the two periods are subtracted respectively to obtain the project change amount and the change amount of various financial data. The change amount of various financial data is arranged from small to large and merged into a financial change data set. Different controllability thresholds are set for different types of financial data based on the project change amount and the financial change data set, and the controllability of the overall financial data is evaluated by comparing the change amount of various financial data with the controllability threshold.

[0028] Different controllability thresholds can be set using the layered threshold method. The financial change data set is divided into N small data sets, and each small data set is used as a layer. The same controllability threshold is set for each layer of data, and the data in each small data set is compared with the controllability threshold of the corresponding layer. The data with a value exceeding the controllability threshold is marked as abnormal.

[0029] When setting the controllability threshold, you can set it according to the amount of change in the project, and calculate the average value of each small data set and mark it as , marking the project changes as , calculate the controllability threshold of each layer, and the formula can be: ,in is the controllability threshold of the corresponding layer, is the corresponding layer number, Adjust the parameters for the corresponding layer threshold.

[0030] The data analysis module uses the hierarchical anomaly detection method to analyze the controllability of the overall financial data. The specific steps are as follows: Set trigger conditions and abnormal data thresholds.

[0031] Count the abnormal marks and sum the data marked abnormally in each layer to get the total abnormal data.

[0032] Controllability judgment: Compare the sum of abnormal data with the abnormal data threshold. When the sum of abnormal data is lower than the abnormal data threshold, the overall financial data is judged to be highly controllable; when the sum of abnormal data is higher than the abnormal data threshold, the overall financial data is judged to be low controllable.

[0033] When the overall financial data is highly controllable, the changes in financial data are within the tolerable range, and there is no need to adjust the initial risk assessment indicators; when the overall financial data is low in controllability, the calculation result obtained by dividing the sum of abnormal data by the abnormal data threshold minus 1 is used as the abnormal overload coefficient, and multiple groups of N values ​​are set to divide the financial change data set into different numbers of small data sets. Similarly, the abnormal overload coefficients are calculated separately, and the calculated abnormal overload coefficients are merged into the abnormal overload data set. The overall financial data controllability judgment result and the abnormal overload data set are sent to the risk assessment module.

[0034] It should be noted that the number of small and medium data sets, the corresponding layer threshold adjustment parameters and the abnormal data threshold can be set according to the actual situation. For example, the financial change data set is divided into three small data sets, that is, three layers of controllability thresholds are set accordingly. According to the size relationship of each layer of data, it is set to 0.55, 0.5, and 0.45 respectively. If there are 10 types of data in the financial change data set, the abnormal data threshold can be set to 6, and so on. This is not analyzed here.

[0035] The risk assessment module responds based on the received controllability judgment result of the overall financial data. If the judgment result is that the overall financial data is highly controllable, the initial risk assessment indicator will continue to be used. If the judgment result is that the overall financial data is low in controllability, the environmental data transmitted by the receiving data acquisition module will be normalized and then the support vector machine model will be constructed based on the abnormal overload data set to evaluate changes in financial risks.

[0036] When the environmental data is normalized, the collected n similar enterprise projects are processed in the same way to obtain n similar enterprise project changes. The n similar enterprise project changes are normalized and merged into a project change data set. The normalization formula can be: ,in is the result after the corresponding data is normalized. is the change in similar enterprise projects, is the minimum value of the change in n similar enterprise projects, It is the maximum value among the changes of n similar enterprise projects.

[0037] The risk assessment module uses the abnormal overload data set and the project change data set as input variables to build a support vector machine model. The support vector machine trains the data set and converges the calculation results. The converged results are used as the evaluation threshold. When the support vector machine receives the current enterprise's project change amount and abnormal overload coefficient, it compares them with the evaluation threshold and outputs the evaluation result. The specific steps are as follows: Step S1, taking the abnormal overload dataset and the project change dataset as input features, and taking the financial risk change as the output result.

[0038] Step S2, select a kernel function to transform the input features into vectors. The kernel function is not unique. In this example, the radial basis function is used as an example, and its feature transformation expression is: ,in is the calculation result after the support vector machine is trained on the data set, y is an abnormal overload coefficient randomly selected from the abnormal overload data set, x is a data randomly selected from the project change data set, e is the natural base number, is a hyperparameter that can be used to adjust the width of the kernel function.

[0039] Step S3, divide the training set and the test set, randomly divide the abnormal overload data set and the project change data set into training sets and test sets with different proportions, randomly select a set of data from the training set and the test set respectively to perform calculations through the kernel function, and obtain the calculation results of the training set and the test set. The proportion of dividing the training set and the test set is randomly allocated, for example, the ratio of the training set to the test set is divided into 6:4, that is, the abnormal overload data set and the project change data set are divided according to the ratio of 6:4.

[0040] Step S4, select a loss function to converge the calculation results after the support vector machine is trained on the data set. In this example, the hinge loss function is used to converge the calculation results. The expression of the hinge loss function is: ,in, is the kernel function loss, Compute results for the test set, is the calculation result of the training set. According to the kernel function loss, the calculation result of the support vector machine after training the data set is converged, and its convergence formula is: , the final result after convergence as the evaluation threshold.

[0041] Step S4, the support vector machine receives the current enterprise's project change amount, normalizes it, combines it with the abnormal overload coefficient, and compares the calculated result with the evaluation threshold. When the calculated result is lower than the evaluation threshold, the assessed financial risk change is low, and the support vector machine output result is low risk; when the calculated result is higher than the evaluation threshold, the assessed financial risk change is high, and the support vector machine output result is high risk.

[0042] When the support vector machine output result is low risk, the smaller the project change or abnormal overload coefficient, the less the initial risk assessment indicator needs to be adjusted; when the support vector machine data result is high risk, the larger the project change or abnormal overload coefficient, the more the initial risk assessment indicator needs to be adjusted. The risk assessment module transmits the adjustment signal to the adjustment feedback module for subsequent processing.

[0043] It should be noted that the kernel function and loss function in the support vector machine are not unique and can be selected and adjusted according to actual conditions. This example only takes the radial basis function and hinge loss function as examples.

[0044] The risk assessment module adjusts the initial risk assessment index according to the abnormal overload coefficient of the current enterprise. Due to the high change in financial risk and the small amount of financial data, the initial risk assessment index needs to be lowered, and the adjustment ratio is set according to the abnormal overload coefficient. The formula can be: ,in is the adjustment ratio, d is the risk reduction parameter, y is the abnormal overload coefficient, and the product of the initial risk assessment index and the adjustment ratio is taken as the adjusted risk assessment index: , is the adjusted risk assessment indicator, It is an initial risk assessment indicator.

[0045] It should be noted that the risk reduction parameters can be set according to actual conditions. For example, if d=1 and y=0.25, the adjustment ratio T=0.8, which will not be elaborated here.

[0046] After receiving the adjustment signal, the adjustment feedback module performs a simulation test to collect feedback data and dynamically plan the statistical period. The specific steps are as follows: Select the same time interval as the statistical period as the sample time, set the initial risk assessment index to the adjusted risk assessment index, collect various financial data within the sample time, and similarly calculate the change in various financial data with the data analysis module, and mark the abnormal data according to the controllability threshold. , mark the abnormal data counted in the previous statistical period as When abnormal data increases, the controllability of the overall financial data decreases, and the statistical period needs to be shortened; when abnormal data decreases, the controllability of the overall financial data increases, and the statistical period can be extended.

[0047] According to the abnormal data changes, the period ratio is set to update the statistical period, and the update formula can be: ,in For the updated statistical period, For the last statistical period, is the term ratio, and its size can be set to .

[0048] It should be noted that there is no unique method for setting the term ratio. In this example, all parameters involved in the formula have been normalized or regarded as de-normalized values ​​for calculation.

[0049] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0050] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0051] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0052] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0053] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An enterprise financial management system based on financial information processing, characterized in that: include: Data acquisition module, data analysis module, risk assessment module and adjustment feedback module, and signal connections between modules; The data acquisition module is used to collect various analytical data in the system and send the collected analytical data to different modules for processing; The data analysis module is used to determine and record the types of financial data and risk assessment indicators, analyze the controllability of the overall financial data, and send the judgment results of the controllability of the overall financial data to the risk assessment module; The risk assessment module is used to assess the change of financial risk. If the change of financial risk is too high, the risk assessment index will be adjusted and the adjustment signal will be transmitted to the adjustment feedback module; The adjustment feedback module is used to receive the adjustment signal, collect feedback data, and dynamically plan the statistical period according to the feedback data.

2. The enterprise financial management system based on financial information processing according to claim 1, characterized in that: The various analytical data collected by the data collection module include historical data, enterprise data, financial change data and environmental data. The data collection module sets a statistical period when collecting enterprise data and financial change data, and collects enterprise data and financial change data within the statistical period.

3. According to the enterprise financial management system based on financial information processing as described in claim 2, it is characterized by: Historical data includes financial data labels and initial risk assessment indicators; enterprise data is the amount of project changes; financial change data is the amount of changes in various types of financial data; The data analysis module determines and records the types of financial data and risk assessment indicators based on historical data, pre-processes the enterprise data and financial change data, and uses the layered anomaly detection method to analyze the controllability of the overall financial data.

4. According to the enterprise financial management system based on financial information processing as described in claim 3, it is characterized by: The data analysis module uses the hierarchical anomaly detection method to analyze the controllability of the overall financial data. The specific steps are as follows: Divide the changes in various types of financial data into layers; set controllability thresholds for each layer based on the project changes; mark and count the financial data that exceeds the controllability threshold as abnormal; set abnormal data thresholds; and determine the controllability of the overall financial data based on the comparison of the statistics of the abnormally marked financial data with the abnormal data thresholds.

5. According to the enterprise financial management system based on financial information processing as described in claim 2, it is characterized by: Environmental data refers to the changes in similar enterprise projects. The risk assessment module builds a support vector machine model based on the controllability of financial data and environmental data, and evaluates changes in financial risks based on the output results of the support vector machine model.

6. The enterprise financial management system based on financial information processing according to claim 5, characterized in that: The steps for building a support vector machine model in the risk assessment module are as follows: Step S1: Set input and output; Step S2: Select a kernel function to calculate the training result; Step S3: Divide the training set and the test set and perform training through the kernel function; Step S4: Set the loss function to converge the kernel function training result.

7. The enterprise financial management system based on financial information processing according to claim 1 is characterized by: When the risk assessment module adjusts the initial risk assessment index, it sets the adjustment ratio based on the enterprise data and financial change data, and uses the product of the initial risk assessment index and the adjustment ratio as the adjusted risk assessment index.

8. The enterprise financial management system based on financial information processing according to claim 2 is characterized by: After receiving the adjustment signal, the adjustment feedback module performs a simulation test to collect feedback data and dynamically plan the statistical period. When performing the simulation test, the adjustment feedback module sets the period ratio according to the test results, and takes the product of the previous statistical period and the period ratio as the updated statistical period.

9. The enterprise financial management system based on financial information processing according to claim 8, characterized in that: The specific steps for adjusting the simulation test in the feedback module are as follows: Set the sample time according to the last statistical period; record the number of data marked as abnormal in the last statistical period, and collect the same financial data within the sample time to count the number of data marked as abnormal; compare the number of data marked as abnormal during the sample time with the number of data marked as abnormal in the last statistical period, set the period ratio and update the statistical period.

Images