Financial risk online audit supervision method based on big data

Abstract

The invention discloses a financial risk online auditing supervision method based on big data, and relates to the technical field of financial risk auditing, and the method comprises the following steps: 1, determining a basic auditing sequence of various types of financial data; 2, based on a preset period, collecting various types of financial data according to a basic auditing and monitoring sequence every time a period node is reached, obtaining a financial risk judgment value of one type of financial data every time after the financial data of the type is collected, and obtaining the financial risk judgment value of the financial data based on a comparison result of the financial risk judgment value and a threshold value of the financial risk judgment value; according to the method, through the first step and the second step, a reasonable basic auditing supervision sequence can be customized for different types of financial data, multi-dimensional and three-dimensional auditing supervision is carried out on various types of financial data, and the types of financial data with abnormal auditing supervision are marked in time.

Description

Technical Field

[0001] The present invention relates to the technical field of financial risk auditing, and more specifically, to a financial risk online auditing and supervision method based on big data. Background Art

[0002] Online audit and supervision of financial risks is an indispensable part of modern corporate financial management. It uses digital and information technology to conduct real-time, efficient and accurate supervision and audit of corporate financial activities to ensure the authenticity, accuracy and completeness of corporate financial information, thereby reducing financial risks. The current financial risk audit will conduct audit supervision on the corresponding types of financial data based on audit habits. This audit supervision method is relatively rigid and cannot achieve dynamic audit supervision of financial data, and cannot quickly audit abnormal financial data. Summary of the invention

[0003] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an online audit and supervision method for financial risks based on big data.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] The financial risk online audit supervision method based on big data includes the following steps:

[0006] Step 1: Determine the basic review and supervision order for each type of financial data;

[0007] Step 2: Based on the preset cycle, at each cycle node, various types of financial data are collected in the basic review and supervision order. After each type of financial data is collected, the financial risk determination value of this type of financial data is obtained. Based on the comparison result between the financial risk determination value and its threshold, it is determined whether to mark this type of financial data as re-regulatory review and supervision data;

[0008] Step 3: Obtain the re-regulation and supervision value of the re-regulation and supervision data, and based on the comparison result between the re-regulation and supervision value and its threshold, mark the re-regulation and supervision data as linkage supervision data or independent supervision data;

[0009] Step 4: Customize the linkage audit and supervision sequence based on the linkage audit and supervision data, customize the independent audit and supervision sequence based on the independent audit and supervision data, and audit and supervise various types of financial data based on the linkage audit and supervision sequence or the independent audit and supervision sequence.

[0010] Furthermore, the basic review and supervision order of each type of financial data is obtained by: obtaining the total number of re-review and supervision of each type of financial data, sorting all types of financial data in descending order according to the total number of re-review and supervision, and then generating the basic review and supervision order of each type of financial data;

[0011] The total number of re-regulation and supervision is obtained in the following way: summing up the number of times this type of financial data is marked as re-regulation and supervision data before the current time of the system, and obtaining the total number of re-regulation and supervision.

[0012] Furthermore, whenever a type of financial data is collected, a financial risk determination value of the type of financial data is obtained, specifically: a financial risk analysis model of each financial risk type is obtained, and the type of financial data is used as input data of the financial risk analysis model of each financial risk type to obtain a financial risk value of each financial risk type, and a financial risk threshold of each financial risk type is obtained, and the financial risk value of the corresponding financial risk type is compared with the financial risk threshold; when the financial risk value is greater than or equal to the financial risk threshold, the corresponding financial risk type is marked as a high financial risk type, and a financial risk determination record of the type of financial data is generated, and the financial risk determination record includes the type of financial data, the financial risk determination time, and the financial risk determination value.

[0013] Furthermore, the financial risk determination value is obtained in the following manner: obtain all high financial risk types of the financial data of this type, construct a knowledge graph between each financial risk type, compare all high financial risk types in pairs, and when there is a correlation between two high financial risk types in the comparison, increase the number of financial risk linkages by one; when there is no correlation between the two high financial risk types in the comparison, sum the financial risk values ​​of the two high financial risk types to obtain an independent risk sum value, sum all financial risk linkage times to obtain the total number of financial risk linkages, and mark it as Ft, sum all independent risk sum values ​​to obtain the independent risk sum value, and mark it as Hs, and use the formula The financial risk determination value Pd of this type of financial data is obtained, wherein a1 is the total number coefficient of the first financial risk linkage, and a2 is the first independent risk total value coefficient.

[0014] Furthermore, based on the comparison result between the financial risk determination value and its threshold, determine whether to mark this type of financial data as important review and supervision data. Specifically, set a financial risk determination threshold. When the financial risk determination value is greater than or equal to the financial risk determination threshold, mark this type of financial data as important review and supervision data. When the financial risk determination value is less than the financial risk determination threshold, collect subsequent types of financial data in the basic review and supervision order.

[0015] Furthermore, the re-regulation and supervision value of the re-regulation and supervision data is obtained by the following method: the total number of financial risk linkages Ft and the total independent risk value Hs of the re-regulation and supervision data are obtained, and the formula is used The re-regulation and supervision value Cg of the re-regulation and supervision data is obtained, where b1 is the total number coefficient of the second financial risk linkage, and b2 is the total value coefficient of the second independent risk.

[0016] Furthermore, a re-regulation review and supervision threshold is set. When the re-regulation review and supervision value is greater than or equal to the re-regulation review and supervision threshold, the re-regulation review and supervision data is marked as linkage review and supervision data. When the re-regulation review and supervision value is less than the re-regulation review and supervision threshold, the re-regulation review and supervision data is marked as independent review and supervision data.

[0017] Furthermore, when the re-regulation and supervision data is marked as linked supervision data, the remaining types of financial data following the re-regulation and supervision data in the basic supervision sequence are marked as linked financial data, and the total number of financial risk fluctuations and the total number of linked supervision data are obtained and marked as , obtain the total number of financial risk fluctuations and the total number of linkage audits of the linked financial data, and mark them as , using the cosine similarity algorithm to calculate the linkage audit value of the linkage financial data, sorting all the linkage financial data in descending order according to the linkage audit value, generating a linkage audit sequence according to the sorting order, and collecting the linkage financial data according to the linkage audit sequence;

[0018] The total number of financial risk fluctuations is obtained in the following manner: obtain all financial risk determination records of this type of financial data before the current time of the system, sort all financial risk determination records in the order of financial risk determination time, calculate the difference between the financial risk determination values ​​of two adjacent financial risk determination records after sorting and take the absolute value to obtain the financial risk determination variable value, set the financial risk determination threshold variable value, and when the financial risk determination variable value is greater than or equal to the financial risk determination threshold variable value, increase the number of financial risk fluctuations by one, and sum the number of financial risk fluctuations to obtain the total number of financial risk fluctuations;

[0019] The total number of linkage audits and supervisions is obtained in the following manner: the number of times that the type of financial data is marked as linkage audit data before the current time of the system is summed up to obtain the total number of linkage audits and supervisions.

[0020] Furthermore, when the re-regulation and supervision data is marked as independent audit and supervision data, the remaining types of financial data following the re-regulation and supervision data in the basic audit and supervision sequence are marked as independent financial data, and the independent audit and supervision values ​​of the independent financial data are obtained. All independent financial data are sorted in descending order according to the independent audit and supervision value, and an independent audit and supervision sequence is generated in the sorted order, and the independent financial data is collected in the independent audit and supervision sequence.

[0021] Furthermore, the independent audit value is obtained by the following method: obtain all financial risk determination records of this type of financial data before the current time of the system, sum up the financial risk determination values ​​of all financial risk determination records and take the average value to obtain the financial risk determination mean value, which is marked as Lm, obtain the total number of times this type of financial data is marked as independent audit data before the current time of the system, which is marked as Cb, and use the formula The independent audit value Sj of this type of financial data is obtained, where d1 is the mean coefficient of financial risk determination and d2 is the total number coefficient of independent audit data.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] 1. Through step 1 and step 2, the present invention can customize a reasonable basic audit supervision sequence for different types of financial data, conduct multi-dimensional and three-dimensional audit supervision on various types of financial data, and timely mark the types of financial data with abnormal audit supervision;

[0024] 2. Through steps three and four, the present invention can conduct in-depth analysis of financial data of audit supervision abnormality types, and divide the financial data into linked audit supervision data and independent audit supervision data, re-customize a reasonable audit supervision sequence according to different classifications, and dynamically optimize the audit supervision sequence of financial risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flowchart of the online audit supervision method for financial risks based on big data;

[0026] Figure 2 A flowchart for determining whether to mark such financial data as re-regulatory and supervisory data. DETAILED DESCRIPTION

[0027] Reference Figure 1 to Figure 2 The embodiment of the present invention provides a financial risk online audit supervision method based on big data, comprising the following steps:

[0028] Step 1: Determine the basic review and supervision order for each type of financial data;

[0029] The basic review and supervision order of each type of financial data is obtained by the following method: obtaining the total number of re-review and supervision of each type of financial data, sorting all types of financial data in descending order according to the total number of re-review and supervision, and then generating the basic review and supervision order of each type of financial data;

[0030] The total number of re-regulation and supervision is obtained by the following method: summing up the number of times that the type of financial data is marked as re-regulation and supervision data before the current time of the system, and the total number of re-regulation and supervision;

[0031] Step 2: Based on the preset cycle, at each cycle node, various types of financial data are collected in the basic review and supervision order (data is collected according to the type of financial data, such as collecting asset financial data first, and then collecting liability financial data). After each type of financial data is collected, the financial risk analysis model of each financial risk type is obtained (each financial risk type corresponds to a financial risk analysis model, such as a financial risk analysis model for market risk type, a financial risk analysis model for credit risk type, a financial risk analysis model for liquidity risk type, a financial risk analysis model for operational risk type, a financial risk analysis model for legal risk type, etc.) Such financial data are respectively used as input data of the financial risk analysis model of each financial risk type, and the financial risk value of each financial risk type is obtained, and the financial risk threshold of each financial risk type is obtained, and the financial risk value of the corresponding financial risk type is compared with the financial risk threshold. When the financial risk value is greater than or equal to the financial risk threshold, the corresponding financial risk type is marked as a high financial risk type. When the financial risk value is less than the financial risk threshold, no corresponding processing is performed, and a financial risk determination record of such financial data is generated. The financial risk determination record includes the type of financial data, the financial risk determination time (i.e., the time when the financial risk determination record is generated), and the financial risk determination value;

[0032] Set the financial risk determination threshold. The financial risk determination threshold is a system-set threshold that can be modified according to actual needs. When the financial risk determination value is greater than or equal to the financial risk determination threshold, the financial data of this type is marked as re-regulatory and supervisory data. When the financial risk determination value is less than the financial risk determination threshold, subsequent financial data of various types are collected in the basic supervisory order.

[0033] The financial risk determination value is obtained in the following way: obtain all high financial risk types of this type of financial data, construct a knowledge graph between each financial risk type, compare all high financial risk types in pairs, and when there is a correlation between two high financial risk types in the comparison, increase the number of financial risk linkages by one; when there is no correlation between the two high financial risk types in the comparison, sum the financial risk values ​​of the two high financial risk types to obtain an independent risk sum value, sum all financial risk linkage times to obtain the total number of financial risk linkages, and mark it as Ft, sum all independent risk sum values ​​to obtain the independent risk sum value, and mark it as Hs, and use the formula The financial risk determination value Pd of this type of financial data is obtained, where a1 is the total number of times coefficient of the first financial risk linkage, a2 is the total value coefficient of the first independent risk, the value of a1 is 0.67, and the value of a1 is 0.52;

[0034] The various financial risk types are represented in the form of a knowledge graph. For example, the relationships in the knowledge graph represent the associations between the various financial risk types, such as impact relationships, transmission relationships (some financial risk types are conductive, that is, one financial risk type may trigger other financial risk types), etc., to ensure that the knowledge graph can accurately reflect the relationships between the various financial risk types;

[0035] Financial audit refers to the review and evaluation of a company's financial statements, accounting records and financial information to determine their authenticity and accuracy. Depending on the audit purpose, audit object and audit method, financial audit needs to classify financial data into multiple types, and each type of financial data has its specific audit content and focus;

[0036] The classification standards of financial data can be adjusted according to needs. For example, according to the elements of financial statements, financial data can be classified into asset financial data, liability financial data, owner's equity financial data, income financial data, etc.; according to the business process, financial data can be classified into procurement and payment cycle financial data, production and inventory cycle financial data, sales and collection cycle financial data, etc.;

[0037] Taking the financial risk analysis model of market risk type as an example, the financial risk analysis model of market risk type is obtained by the following method: obtaining multiple groups of financial data, each group of financial data can be the same type of financial data or different types of financial data, can be real financial data or virtual financial data, extract market feature data from multiple groups of financial data to obtain multiple groups of market feature data, build a neural network model, use the market feature data as training data of the neural network model, assign financial risk values ​​to the training data, divide the training data into a training set and a validation set according to a set ratio, the set ratio of the training set to the validation set can be adjusted according to actual needs, perform neural network iterative training on the training set and the validation set, and obtain a financial risk analysis model of market risk type, wherein the value of the financial risk value is greater than 0, the larger the value of the financial risk value is, the greater the market risk of the financial data is, and the smaller the value of the financial risk value is, the smaller the market risk of the financial data is;

[0038] The financial risk analysis models of other financial risk types are obtained in the same way as the financial risk analysis models of market risk types. Different financial risk types correspond to an independent financial risk threshold, which is a system-set threshold and can be modified according to actual needs.

[0039] Through steps one and two, the present invention can customize a reasonable basic audit supervision sequence for different types of financial data, conduct multi-dimensional and three-dimensional audit supervision on various types of financial data, and timely mark financial data types with abnormal audit supervision.

[0040] Step 3: Obtain the re-regulation and supervision value of the re-regulation and supervision data, set the re-regulation and supervision threshold, which is the threshold set by the system and can be modified according to actual needs. When the re-regulation and supervision value is greater than or equal to the re-regulation and supervision threshold, the re-regulation and supervision data is marked as linkage supervision data; when the re-regulation and supervision value is less than the re-regulation and supervision threshold, the re-regulation and supervision data is marked as independent supervision data;

[0041] The re-regulation and supervision value of the re-regulation and supervision data is obtained by the following method: obtain the total number of financial risk linkages Ft and the total independent risk value Hs of the re-regulation and supervision data, and use the formula The re-regulation and supervision value Cg of the re-regulation and supervision data is obtained, where b1 is the total number of times of the second financial risk linkage coefficient, b2 is the total value coefficient of the second independent risk, the value of b1 is 0.87, and the value of b2 is 0.96;

[0042] Step 4: When the re-regulation and supervision data is marked as linked supervision data, mark the remaining types of financial data after the re-regulation and supervision data in the basic supervision sequence as linked financial data, obtain the total number of financial risk fluctuations and the total number of linked supervision data, and mark them as , obtain the total number of financial risk fluctuations and the total number of linkage audits of the linked financial data, and mark them as , using the cosine similarity algorithm to calculate the linkage audit value of the linkage financial data, sorting all the linkage financial data in descending order according to the linkage audit value, generating a linkage audit sequence according to the sorting order, and collecting the linkage financial data according to the linkage audit sequence;

[0043] Linked audit value of financial data ;

[0044] The total number of financial risk fluctuations is obtained in the following manner: obtain all financial risk determination records of this type of financial data before the current time of the system, sort all financial risk determination records in the order of financial risk determination time, calculate the difference between the financial risk determination values ​​of two adjacent financial risk determination records after sorting and take the absolute value to obtain the financial risk determination variable value, set the financial risk determination threshold variable value, when the financial risk determination variable value is greater than or equal to the financial risk determination threshold variable value, increase the number of financial risk fluctuations by one, when the financial risk determination variable value is less than the financial risk determination threshold variable value, do not perform corresponding processing, sum the number of financial risk fluctuations to obtain the total number of financial risk fluctuations;

[0045] The total number of linkage audit and supervision is obtained by the following method: the number of times that the type of financial data is marked as linkage audit and supervision data before the current time of the system is summed up to obtain the total number of linkage audit and supervision;

[0046] When the re-regulation and supervision data is marked as independent supervision data, the remaining types of financial data following the re-regulation and supervision data in the basic supervision order are marked as independent financial data, and the independent supervision values ​​of the independent financial data are obtained. All independent financial data are sorted in descending order according to the independent supervision values, and an independent supervision order is generated according to the sorting order. The independent financial data is collected according to the independent supervision order;

[0047] The independent audit value is obtained in the following way: obtain all financial risk determination records of this type of financial data before the current time of the system, sum up the financial risk determination values ​​of all financial risk determination records and take the average value to obtain the financial risk determination mean value, which is marked as Lm, obtain the total number of times this type of financial data is marked as independent audit data before the current time of the system, and mark it as Cb, and use the formula The independent audit value Sj of this type of financial data is obtained, where d1 is the mean coefficient of financial risk determination, d2 is the total number coefficient of independent audit data, the value of d1 is 0.64, and the value of d2 is 0.61.

[0048] Through steps three and four, the present invention can conduct in-depth analysis on financial data of audit supervision abnormality types, and divide the financial data into linked audit supervision data and independent audit supervision data, re-customize a reasonable audit supervision sequence according to different classifications, and dynamically optimize the audit supervision sequence of financial risks.

[0049] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0050] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0051] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0052] Those of ordinary skill in the art will appreciate that the units 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 and design constraints of the technical solution. 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.

[0053] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0054] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0055] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0056] 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.

Claims

1. The financial risk online audit supervision method based on big data is characterized by: The steps include: Step 1: Determine the basic review and supervision order for each type of financial data; Step 2: Based on the preset cycle, at each cycle node, various types of financial data are collected in the basic review and supervision order. After each type of financial data is collected, the financial risk determination value of this type of financial data is obtained. Based on the comparison result between the financial risk determination value and its threshold, it is determined whether to mark this type of financial data as re-regulatory review and supervision data; Step 3: Obtain the re-regulation and supervision value of the re-regulation and supervision data, and based on the comparison result between the re-regulation and supervision value and its threshold, mark the re-regulation and supervision data as linkage supervision data or independent supervision data; Step 4: Customize the linkage audit and supervision sequence based on the linkage audit and supervision data, customize the independent audit and supervision sequence based on the independent audit and supervision data, and audit and supervise various types of financial data based on the linkage audit and supervision sequence or the independent audit and supervision sequence.

2. The method for online audit and supervision of financial risks based on big data according to claim 1 is characterized in that: The basic review and supervision order of each type of financial data is obtained by the following method: obtaining the total number of re-review and supervision of each type of financial data, sorting all types of financial data in descending order according to the total number of re-review and supervision, and then generating the basic review and supervision order of each type of financial data; The total number of re-regulation and supervision is obtained in the following way: summing up the number of times this type of financial data is marked as re-regulation and supervision data before the current time of the system, and obtaining the total number of re-regulation and supervision.

3. The financial risk online audit supervision method based on big data according to claim 1 is characterized in that: Whenever a type of financial data is collected, the financial risk determination value of the type of financial data is obtained, specifically: a financial risk analysis model of each financial risk type is obtained, the type of financial data is used as input data of the financial risk analysis model of each financial risk type, the financial risk value of each financial risk type is obtained, the financial risk threshold of each financial risk type is obtained, the financial risk value of the corresponding financial risk type is compared with the financial risk threshold, when the financial risk value is greater than or equal to the financial risk threshold, the corresponding financial risk type is marked as a high financial risk type, and a financial risk determination record of the type of financial data is generated, the financial risk determination record includes the type of financial data, the financial risk determination time, and the financial risk determination value.

4. The method for online audit and supervision of financial risks based on big data according to claim 3 is characterized in that: The financial risk determination value is obtained in the following way: obtain all high financial risk types of this type of financial data, construct a knowledge graph between each financial risk type, compare all high financial risk types in pairs, and when there is a correlation between two high financial risk types in the comparison, increase the number of financial risk linkages by one; when there is no correlation between the two high financial risk types in the comparison, sum the financial risk values ​​of the two high financial risk types to obtain an independent risk sum value, sum all financial risk linkage times to obtain the total number of financial risk linkages, and mark it as Ft, sum all independent risk sum values ​​to obtain the independent risk sum value, and mark it as Hs, and use the formula The financial risk determination value Pd of this type of financial data is obtained, wherein a1 is the total number coefficient of the first financial risk linkage, and a2 is the first independent risk total value coefficient.

5. The method for online audit and supervision of financial risks based on big data according to claim 1 is characterized in that: Based on the comparison result between the financial risk determination value and its threshold, determine whether to mark this type of financial data as important regulatory review data. Specifically: set a financial risk determination threshold. When the financial risk determination value is greater than or equal to the financial risk determination threshold, mark this type of financial data as important regulatory review data. When the financial risk determination value is less than the financial risk determination threshold, collect subsequent types of financial data in the basic review order.

6. The method for online audit and supervision of financial risks based on big data according to claim 1 is characterized in that: The re-regulation and supervision value of the re-regulation and supervision data is obtained by the following method: obtain the total number of financial risk linkages Ft and the total independent risk value Hs of the re-regulation and supervision data, and use the formula The re-regulation and supervision value Cg of the re-regulation and supervision data is obtained, where b1 is the total number coefficient of the second financial risk linkage, and b2 is the total value coefficient of the second independent risk.

7. The method for online audit and supervision of financial risks based on big data according to claim 1 is characterized in that: Set the re-regulation review and supervision threshold. When the re-regulation review and supervision value is greater than or equal to the re-regulation review and supervision threshold, the re-regulation review and supervision data will be marked as linked review and supervision data. When the re-regulation review and supervision value is less than the re-regulation review and supervision threshold, the re-regulation review and supervision data will be marked as independent review and supervision data.

8. The method for online audit and supervision of financial risks based on big data according to claim 1 is characterized in that: When the re-regulation and supervision data is marked as linkage supervision data, the remaining types of financial data following the re-regulation and supervision data in the basic supervision sequence are marked as linkage financial data, and the total number of financial risk fluctuations and linkage supervision data of the linkage supervision data are obtained and marked as , obtain the total number of financial risk fluctuations and the total number of linkage audits of the linked financial data, and mark them as , using the cosine similarity algorithm to calculate the linkage audit value of the linkage financial data, sorting all the linkage financial data in descending order according to the linkage audit value, generating a linkage audit sequence according to the sorting order, and collecting the linkage financial data according to the linkage audit sequence; The total number of financial risk fluctuations is obtained in the following manner: obtain all financial risk determination records of this type of financial data before the current time of the system, sort all financial risk determination records in the order of financial risk determination time, calculate the difference between the financial risk determination values ​​of two adjacent financial risk determination records after sorting and take the absolute value to obtain the financial risk determination variable value, set the financial risk determination threshold variable value, and when the financial risk determination variable value is greater than or equal to the financial risk determination threshold variable value, increase the number of financial risk fluctuations by one, and sum the number of financial risk fluctuations to obtain the total number of financial risk fluctuations; The total number of linkage audits and supervisions is obtained in the following manner: the number of times that the type of financial data is marked as linkage audit data before the current time of the system is summed up to obtain the total number of linkage audits and supervisions.

9. The method for online audit and supervision of financial risks based on big data according to claim 1 is characterized in that: When the re-regulation and supervision data is marked as independent audit and supervision data, the remaining types of financial data following the re-regulation and supervision data in the basic audit and supervision sequence shall be marked as independent financial data, and the independent audit and supervision values ​​of the independent financial data shall be obtained. All independent financial data shall be sorted in descending order according to the independent audit and supervision value, and an independent audit and supervision sequence shall be generated in the sorted order. The independent financial data shall be collected in the independent audit and supervision sequence.

10. The method for online audit and supervision of financial risks based on big data according to claim 9 is characterized in that: The independent audit value is obtained in the following way: obtain all financial risk determination records of this type of financial data before the current time of the system, sum up the financial risk determination values ​​of all financial risk determination records and take the average value to obtain the financial risk determination mean value, which is marked as Lm, obtain the total number of times this type of financial data is marked as independent audit data before the current time of the system, and mark it as Cb, and use the formula The independent audit value Sj of this type of financial data is obtained, where d1 is the mean coefficient of financial risk determination and d2 is the total number coefficient of independent audit data.

Images