Audit data automatic analysis method and system

Abstract

The invention relates to the technical field of audit data analysis, in particular to an automatic audit data analysis method and system.In the system, an association map analysis module constructs an enterprise association map corresponding to a corresponding data element based on stock equity information in an enterprise to which each data element in audit data belongs; and constructing an enterprise association analysis set corresponding to the enterprise association map. According to the auditing characteristics of the data elements in the to-be-audited data, risk event division is carried out; evaluating the risk tracking difficulty of the audit data of each risk event in the to-be-audited data in combination with the audit risk characteristics of the risk events, the enterprise association maps of the enterprises related to the risk events and the corresponding enterprise association analysis sets; meanwhile, in combination with historical audit results of enterprises related to the risk events, quantitative management of audit priorities of the risk events is realized, a risk event audit sequence of the enterprises is constructed and dynamically updated, effective management of audit data is realized, and audit efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of audit data analysis, and specifically to an automated audit data analysis method and system. Background Art

[0002] With the expansion of enterprise scale and the increase in business complexity, the amount and complexity of data faced by audit work are also rising sharply. Traditional audit methods mainly rely on manual analysis, which is inefficient and error-prone. In addition, the equity correlation relationships among enterprises are intricate, and it is difficult for traditional methods to comprehensively and accurately identify and analyze the impacts of these correlation relationships on audits.

[0003] Existing audit systems usually can only process structured data, lack the ability to process unstructured data, and cannot effectively combine enterprise equity correlation maps for comprehensive analysis; this results in that when determining audit priorities, auditors often rely on experience and intuition, lacking scientific and quantitative bases. Summary of the Invention

[0004] The purpose of the present invention is to provide an automated audit data analysis method and system to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solution: an automated audit data analysis method, the method comprising the following steps: S1. Based on OCR image recognition technology, extract the audit features of each data element in the data to be audited, and generate the risk events to which the audit features of each data element belong; summarize the data elements belonging to the same risk event in the audit data into the same set, and extract the audit risk features of the summary set corresponding to each risk event; S2. Based on the equity information of the enterprises to which each data element in the audit data belongs, construct an enterprise correlation map corresponding to the corresponding data element; construct an enterprise correlation analysis set corresponding to the enterprise correlation map; S3. Obtain the risk events belonging to the same enterprise in the data to be audited, combine the enterprise correlation analysis sets corresponding to the enterprises involved in each risk event respectively, and the audit risk features of the summary set corresponding to the corresponding risk event, to obtain the risk tracking interference evaluation value of the corresponding risk event; and combine the historical audit results of the enterprises involved in the corresponding risk event to generate the audit priority coefficient of the corresponding risk event, and construct the risk event audit sequence of the corresponding enterprise; S4. Real-time feedback the audit results of each risk event to the database, the database retrieves the completed risk events for marking, and updates the risk event audit sequences of each enterprise stored in the current database according to the marked risk events, to obtain the risk event audit sequences of each enterprise that have not been executed.

[0006] Further, the types of data elements in the data to be audited in S1 include transaction invoices and transaction contracts; when extracting the audit features of each data element in the data to be audited based on OCR image recognition technology, through OCR image recognition technology, automatically extract the amount, execution time, transaction fund provider, and transaction executor in the corresponding transaction invoice or transaction contract of the data element as the audit features of the corresponding data element; bind the data elements in the data to be audited of the same enterprise with the same types of data elements, the same transaction fund provider, the same transaction executor, and the time interval between the corresponding execution times less than the preset value, and use the binding result as a whole data element to replace each element in the binding result at the same time. In the audit features corresponding to the obtained whole data element, the transaction fund provider and the transaction executor remain unchanged, the execution time is the average value of the respective execution times of each element in the corresponding binding result, and the amount is the cumulative value of the respective amounts of each element in the corresponding binding result; classify the data elements in the data to be audited with the same amount, transaction fund provider, and transaction executor in the corresponding audit features into the same risk event; the audit risk features of each risk event corresponding to the summary set are the amount, transaction fund provider, and transaction executor in the audit features corresponding to any one element in the corresponding risk event.

[0007] Further, the method steps for constructing the enterprise association graph corresponding to the corresponding data element in S2 are specifically as follows: S21. Obtain the summary set of the enterprise names to which each data element in the audit data belongs, denoted as QS ; obtain the equity information in the enterprise name to which each data element in the audit data belongs, and denote the equity information in the enterprise name to which the i th data element in the audit data belongs as G i , where G i is a set, and each element in the set corresponds to a shareholder name, and the shareholders include individuals or enterprises; S22. Denote the array obtained by summarizing the enterprise name to which the i th data element in the audit data belongs and each element in G i as H i ; add the enterprise name to which the i th data element in the audit data belongs to an empty set to obtain the set Q i ; regard each element in H i as a graph node, and regard each element in G i as being respectively associated with thei Connect the i th data element to obtain the initial knowledge graph corresponding to the P i th data element in the audit data, denoted as G i ; Take each element in j as a reference node of the j -level graph, and the initial value of is 1; P i , Q i and the reference node of the j -level graph, and jump to step S24; S24. Analyze each reference node of the j -level graph one by one. Denote the a th reference node of the j -level graph as GR （i，j，a） ; Obtain the summary set of each element in QS and the equity information corresponding to it, which contains GR （i，j，a） and the corresponding enterprises do not belong to Q i , denoted as M （i，j，a） ; S25. If M （i，j，a） is an empty set, stop analyzing the a th reference node of the j -level graph; If M （i，j，a） is not an empty set, obtain the equity information corresponding to each element in M （i，j，a） . Connect each element in the obtained equity information with the corresponding element in M （i，j，a） to get the knowledge graph, and use the splicing result with P i as the new P i ; Add the corresponding elements in M （i，j，a） to Q i to get the new Q i ; Take any element in the equity information corresponding to each element in M （i，j，a） as a reference node of the next-level graph; and add 1 to the corresponding value of j as the new jValue; Jump to step S23 for iteration; S25. Obtain the i corporate association graph corresponding to the P i th data element in the data to be audited after all the graph reference nodes corresponding to the i th data element in the data to be audited stop analyzing; Use the set composed of all the enterprise names and shareholder names involved in the corporate association graph as the corporate association analysis set corresponding to the corresponding corporate association graph.

[0008] Furthermore, the calculation formula for the risk tracking interference evaluation value of the corresponding risk event obtained in S3 is as follows: ; Wherein, RP （k，g） represents the risk tracking interference evaluation value of the k th risk event of the g th enterprise in the data to be audited; Num （k，g） represents the number of each enterprise involved in the audit risk characteristics of the k th risk event of the g th enterprise in the data to be audited; COM （k，g，d） represents the corporate association graph complexity coefficient of the k th enterprise involved in the audit risk characteristics of the g th risk event of the d th enterprise in the data to be audited; ; Level （k，g，d） represents the maximum level number of the graph reference nodes in the corporate association graph of the k th enterprise involved in the audit risk characteristics of the g th risk event of the d th enterprise in the data to be audited; B （k，g，d） represents the maximum value of the number of graph reference nodes at each level in the corporate association graph of the k th enterprise involved in the audit risk characteristics of the g th risk event of the d th enterprise in the data to be audited; W （k，g，d） represents the k th enterprise involved in the audit risk characteristics of the g th risk event of the dThe number of elements in the enterprise association analysis set corresponding to an enterprise; r Indicates a preset first weight coefficient; β Indicates a preset second weight coefficient.

[0009] Further, the calculation formula for generating the audit priority coefficient of the corresponding risk event in S3 is as follows: ; Wherein, F （k，g） Indicates the k th enterprise to which the to-be-audited data belongs, and the g th audit priority coefficient of the risk event; E （k，g） Indicates the k th enterprise, and the total number of risk events with unqualified internal audit results in the historical audit results of each enterprise included in the enterprise association analysis set corresponding to the g th risk event involved by the enterprise; ES （k，g） Indicates the k th enterprise, and the total number of risk events that have completed the audit in the historical audit results of each enterprise included in the enterprise association analysis set corresponding to the g th risk event involved by the enterprise, and ES （k，g） > 0; μ Indicates a preset constant; The audit sequence of risk events of the corresponding enterprise is the sorting result of each risk event in the corresponding enterprise in descending order of the audit priority coefficient.

[0010] Further, the specific execution process in S4 includes: The updated result of the audit sequence of risk events of each enterprise is the audit sequence composed of the remaining risk events after removing the risk events marked in the database from the audit sequence of risk events of the corresponding enterprise.

[0011] An automated audit data analysis system, the system includes the following modules: An audit risk feature extraction module, which extracts the audit features of each data element in the to-be-audited data based on OCR image recognition technology and generates the risk events to which the audit features of each data element belong; aggregates the data elements belonging to the same risk event in the audit data into the same set, and extracts the audit risk features of the summary set corresponding to each risk event; The associated graph analysis module constructs an enterprise associated graph corresponding to each data element based on the equity information in the enterprises to which each data element in the audit data belongs; constructs an enterprise association analysis set corresponding to the enterprise associated graph; The audit sequence analysis module obtains each risk event belonging to the same enterprise in the data to be audited, combines the enterprise association analysis sets respectively corresponding to the enterprises involved in each risk event, and the audit risk characteristics of the corresponding summary set of the corresponding risk event, to obtain the risk tracking interference evaluation value of the corresponding risk event; and combines the historical audit results of the enterprises involved in the corresponding risk event to generate the audit priority coefficient of the corresponding risk event, and constructs the risk event audit sequence of the corresponding enterprise; The audit sequence update management module feeds back the audit results for each risk event to the database in real time. The database retrieves the completed risk events for marking, and updates the risk event audit sequences of each enterprise stored in the current database according to the marked risk events, to obtain the risk event audit sequences of each enterprise that have not been executed.

[0012] Further, the audit sequence analysis module includes a risk tracking interference evaluation unit, an audit priority coefficient calculation unit, and a risk event audit sequence construction unit, The risk tracking interference evaluation unit obtains each risk event belonging to the same enterprise in the data to be audited, combines the enterprise association analysis sets respectively corresponding to the enterprises involved in each risk event, and the audit risk characteristics of the corresponding summary set of the corresponding risk event, to obtain the risk tracking interference evaluation value of the corresponding risk event; The audit priority coefficient calculation unit combines the historical audit results of the enterprises involved in the corresponding risk event to generate the audit priority coefficient of the corresponding risk event; The risk event audit sequence construction unit constructs the risk event audit sequence of the corresponding enterprise according to the obtained result of the audit priority coefficient calculation unit.

[0013] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The present invention divides risk events according to the audit characteristics of data elements in the data to be audited; and combines the audit risk characteristics of risk events, the enterprise associated graph of the enterprises involved in the risk events, and their corresponding enterprise association analysis sets to evaluate the risk tracking difficulty of the audit data of each risk event in the data to be audited; at the same time, combines the historical audit results of the enterprises involved in the risk events to realize the quantitative management of the audit priority of risk events, constructs and dynamically updates the risk event audit sequences of enterprises, realizes the effective management of audit data, and improves audit efficiency and audit accuracy. Description of the Drawings

[0014] The accompanying drawings are used to provide a further understanding of the present invention and form a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the accompanying drawings: Figure 1 is a schematic structural diagram of an automated audit data analysis system of the present invention; Figure 2 is a schematic flowchart of an automated audit data analysis method of the present invention. Detailed implementation manners

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0016] Please refer to Figure 1 , the present invention provides a technical solution: an automated audit data analysis system, the system includes the following modules: An audit risk feature extraction module, which extracts the audit features of each data element in the data to be audited based on the OCR image recognition technology and generates the risk events to which the audit features of each data element belong; summarizes the data elements belonging to the same risk event in the audit data into the same set, and extracts the audit risk features of the summary set corresponding to each risk event; An association graph analysis module, which constructs an enterprise association graph corresponding to the corresponding data element based on the equity information in the enterprise to which each data element in the audit data belongs; constructs an enterprise association analysis set corresponding to the enterprise association graph; An audit sequence analysis module, which includes a risk tracking interference evaluation unit, an audit priority coefficient calculation unit, and a risk event audit sequence construction unit, The risk tracking interference evaluation unit obtains the risk events belonging to the same enterprise in the data to be audited, combines the enterprise association analysis sets corresponding to the enterprises involved in each risk event respectively, and the audit risk features of the summary set corresponding to the corresponding risk event, to obtain the risk tracking interference evaluation value of the corresponding risk event; The audit priority coefficient calculation unit generates the audit priority coefficient of the corresponding risk event in combination with the historical audit results of the enterprises involved in the corresponding risk event; The risk event audit sequence construction unit constructs the risk event audit sequence of the corresponding enterprise according to the obtained result of the audit priority coefficient calculation unit; An audit sequence update management module, which feeds back the audit results for each risk event to the database in real time. The database retrieves the completed risk events for marking, and updates the risk event audit sequences of each enterprise stored in the current database based on the marked risk events to obtain the risk event audit sequences that have not been executed for each enterprise.

[0017] As Figure 2 shown, an automated audit data analysis method, the method comprising the following steps: S1. Extract the audit features of each data element in the data to be audited based on OCR image recognition technology, and generate the risk events to which the audit features of each data element belong; aggregate the data elements belonging to the same risk event in the audit data into the same set, and extract the audit risk features of the corresponding aggregated set for each risk event; In S1, the types of data elements in the data to be audited include transaction invoices and transaction contracts; when extracting the audit features of each data element in the data to be audited based on OCR image recognition technology, the amount, execution time, transaction fund provider, and transaction executor in the corresponding transaction invoice or transaction contract of the data element are automatically extracted by OCR image recognition technology as the audit features of the corresponding data element; bind the data elements in the data to be audited of the same enterprise with the same type of data element, the same transaction fund provider, the same transaction executor, and the time interval between the corresponding execution times less than the preset value, and use the binding result as a whole data element to replace each element in the binding result at the same time. In the audit features corresponding to the obtained whole data element, the transaction fund provider and the transaction executor remain unchanged, the execution time is the average value of the execution times corresponding to each element in the corresponding binding result, and the amount is the cumulative value of the amounts corresponding to each element in the corresponding binding result; classify the data elements with the same amount, transaction fund provider, and transaction executor in the corresponding audit features in the data to be audited into the same risk event; the audit risk features of the corresponding aggregated set for each risk event are the amount, transaction fund provider, and transaction executor in the audit features corresponding to any one element in the corresponding risk event.

[0018] S2. Based on the equity information in the enterprise to which each data element in the audit data belongs, construct an enterprise association graph corresponding to the corresponding data element; construct an enterprise association analysis set corresponding to the enterprise association graph; The method steps for constructing the enterprise association graph corresponding to the corresponding data element in S2 are specifically as follows: S21. Obtain the aggregated set of the enterprise names to which each data element in the audit data belongs, denoted as QS ; obtain the equity information in the enterprise names to which each data element in the audit data belongs, and for thei The equity information in the enterprise name to which a data element belongs is recorded as G i , where the G i is a set, and each element in the set corresponds to a shareholder name, and the shareholders include individuals or enterprises; S22. The array obtained by summarizing the enterprise name to which the i th data element in the audit data belongs and each element in the G i is recorded as H i ; The enterprise name to which the i th data element in the audit data belongs is added to an empty set to obtain the set Q i ; Each element in the H i is used as a graph node, and each element in the G i is connected to the i th data element in the audit data respectively, and the initial knowledge graph corresponding to the i th data element in the audit data is obtained, and is recorded as P i ; Each element in the G i is used as a graph reference node of the j th level respectively, and the initial value of the j is 1; S23. Receive P i , Q i and the graph reference node of the j th level, and jump to step S24; S24. Analyze each graph reference node of the j th level one by one, and record the a th graph reference node of the j th level as GR （i，j，a） ; Obtain the summary set of each enterprise in the QS whose equity information contains GR （i，j，a） and the corresponding enterprise does not belong to Q i , and is recorded as M （i，j，a） ; S25. If the M （i，j，a） is an empty set, stop analyzing the a th graph reference node of the j th level; If M （i，j，a） is not an empty set, then obtain M （i，j，a） the equity information corresponding to each element in, and connect each element in the obtained equity information with M （i，j，a） the knowledge graph obtained by connecting the corresponding elements in respectively, and the splicing result with P i is used as the new P i ; Add the corresponding elements in M （i，j，a） to Q i to obtain the new Q i ; Use any one element in the equity information corresponding to each element in M （i，j，a） as a reference node for the next-level graph; And add 1 to the corresponding value of j as the new j value; Jump to step S23 for iteration; S25. Obtain the i after the analysis of each graph reference node corresponding to the P i th data element in the data to be audited stops, and the enterprise association graph corresponding to the i th data element in the data to be audited; Use the set composed of all enterprise names and shareholder names involved in the enterprise association graph as the enterprise association analysis set corresponding to the corresponding enterprise association graph.

[0019] S3. Obtain each risk event belonging to the same enterprise in the data to be audited, combine the enterprise association analysis sets corresponding to the enterprises involved in each risk event respectively, and the audit risk characteristics of the corresponding risk event summary set, to obtain the risk tracking interference evaluation value of the corresponding risk event; And combine the historical audit results of the enterprises involved in the corresponding risk event to generate the audit priority coefficient of the corresponding risk event, and construct the risk event audit sequence of the corresponding enterprise; The calculation formula for obtaining the risk tracking interference evaluation value of the corresponding risk event in S3 is as follows: ; Among them, RP （k，g） represents the risk tracking interference evaluation value of the k th risk event of the g th enterprise belonging to the data to be audited; Num （k，g） represents the k th enterprise belonging to the data to be auditedg The number of each enterprise involved in the audit risk characteristics of a risk event; COM （k，g，d） Indicates the k th g th enterprise involved in the audit risk characteristics of the d th risk event of the ; Level （k，g，d） Indicates the k th g th enterprise involved in the audit risk characteristics of the d th risk event of the B （k，g，d） Indicates the k th g th enterprise involved in the audit risk characteristics of the d th risk event of the W （k，g，d） Indicates the k th g th enterprise involved in the audit risk characteristics of the d th risk event of the r Indicates the preset first weight coefficient; β Indicates the preset second weight coefficient.

[0020] The calculation formula for generating the audit priority coefficient of the corresponding risk event in S3 is as follows: ; Among them, F （k，g） Indicates the audit priority coefficient of the k th risk event corresponding to the g th enterprise in the to-be-audited data; E （k，g） Indicates the k th g th risk event corresponding to the ES （k，g） Indicates the k th gThe total number of risk events completed in the historical audit results of each enterprise included in the enterprise association analysis set of the enterprise association graph corresponding to the enterprise involved in each risk event, and ES （k，g） > 0; μ represents a preset constant; The risk event audit sequence of the corresponding enterprise is the arrangement result of each risk event in the corresponding enterprise in descending order of the audit priority coefficient.

[0021] S4. Real-time feedback the audit results of each risk event to the database. The database retrieves the completed risk events for marking, and updates the risk event audit sequences of each enterprise stored in the current database according to the marked risk events, so as to obtain the risk event audit sequences of each enterprise that have not been executed; The specific execution process in S4 includes: The update result of the risk event audit sequence of each enterprise is the audit sequence composed of the remaining risk events after removing the risk events belonging to the marked risk events in the risk event audit sequence of the corresponding enterprise.

[0022] In this embodiment, if there is a transaction transfer between two enterprises, A and B, the transaction contract and transaction invoice corresponding to this transaction transfer between A and B constitute a risk event. This risk event exists in both enterprises A and B at the same time. Therefore, this risk event exists in the risk event audit sequences corresponding to enterprises A and B respectively; if the audit of this risk event in the risk event audit sequence of enterprise A has been completed, the database will mark this risk event, and at the same time update the risk event audit sequences corresponding to enterprises A and B that contain this risk event, and delete this risk event in the risk event audit sequences corresponding to enterprises A and B respectively; therefore, in this process, the execution priority of this risk event in the risk event audit sequence corresponding to enterprise A may remain unchanged, while this risk event has not been executed in the risk event audit sequence corresponding to enterprise B, and the execution priorities of each risk event after the corresponding serial number of this risk event in the risk event audit sequence corresponding to enterprise B have all changed.

[0023] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0024] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An automated analysis method for audit data, characterized in that, The method includes the following steps: S1. Based on OCR image recognition technology, extract the audit features of each data element in the data to be audited, and generate the risk events to which the audit features of each data element belong; aggregate each data element belonging to the same risk event in the audit data into the same set, and extract the audit risk features of the corresponding aggregated set for each risk event; S2. Based on the equity information of each enterprise to which each data element in the audit data belongs, construct an enterprise association graph corresponding to the corresponding data element; construct an enterprise association analysis set corresponding to the enterprise association graph; S3. Obtain each risk event belonging to the same enterprise in the data to be audited. Combine the enterprise association analysis sets corresponding to the enterprises involved in each risk event, and the audit risk characteristics of the corresponding summary set of the corresponding risk event to obtain the risk tracking interference evaluation value of the corresponding risk event; and combine the historical audit results of the enterprises involved in the corresponding risk event to generate the audit priority coefficient of the corresponding risk event, and construct the risk event audit sequence of the corresponding enterprise; S4. Real-time feedback the audit results of each risk event to the database. The database retrieves the completed risk events for marking, and updates the risk event audit sequences of each enterprise stored in the current database according to the marked risk events to obtain the risk event audit sequences of each enterprise that have not been executed.

2. The automated audit data analysis method according to claim 1, characterized in that: In the S1, the types of data elements in the data to be audited include transaction invoices and transaction contracts; based on OCR When extracting the audit features of each data element in the data to be audited through OCR image recognition technology, the amount, execution time, transaction fund provider, and transaction executor in the corresponding transaction invoice or transaction contract of the data element are automatically extracted as the audit features of the corresponding data element; each data element in the data to be audited of the same enterprise with the same type of data element, the same transaction fund provider, the same transaction executor, and the time interval between the corresponding execution times less than the preset value is bound, and the binding result is used as a whole data element to replace each element in the binding result at the same time. Moreover, in the audit features corresponding to the obtained whole data element, the transaction fund provider and the transaction executor remain unchanged, the execution time is the average value of the respective execution times corresponding to each element in the corresponding binding result, and the amount is the cumulative value of the respective amounts corresponding to each element in the corresponding binding result; the data elements in the data to be audited with the same amount, transaction fund provider, and transaction executor in the corresponding audit features are classified into the same risk event; the audit risk features corresponding to each risk event summary set are the amount, transaction fund provider, and transaction executor in the audit features corresponding to any one element in the corresponding risk event.

3. The automated audit data analysis method according to claim 2, wherein: The method steps for constructing the enterprise association graph corresponding to the corresponding data element in S2 are specifically as follows: S21. Obtain the summary set of the enterprise names to which each data element in the audit data belongs, denoted as QS ; obtain the equity information in the enterprise name to which each data element in the audit data belongs, and denote the equity information in the enterprise name of the i th data element in the audit data as G i . The G i is a set, and each element in the set corresponds to a shareholder name, and the shareholders include individuals or enterprises; S22. Denote the array obtained by summarizing the enterprise name to which the i th data element in the audit data belongs and each element in G i as H i ; Add the enterprise name to which the i th data element in the audit data belongs to an empty set to obtain the set Q i ; Take each element in H i as a graph node, and connect each element in G i to the i th data element in the audit data respectively to obtain the initial knowledge graph corresponding to the i th data element in the audit data, denoted as P i ; Take each element in G i as a reference node of the j -level graph respectively, and the initial value of j is 1; S23. Receive P i , Q i and j the reference nodes of the level map, and jump to step S24; S24. Analyze each reference node of the j -level graph spectrum one by one, and denote the a th reference node of the j -level graph spectrum as GR （i，j，a） ; Obtain the aggregated set of each enterprise within QS whose corresponding equity information contains GR （i，j，a） and the corresponding enterprise does not belong to Q i , and denote it as M （i，j，a） ; S25. If M （i，j，a） is an empty set, stop analyzing the reference nodes of the a th j -level graph spectrum; If M （i，j，a） is not an empty set, then obtain M （i，j，a） the equity information corresponding to each element in, and connect each element in the obtained equity information with M （i，j，a） the corresponding elements in to get a knowledge graph, and use the concatenation result of the knowledge graph and P i as the new P i ; add the corresponding elements in M （i，j，a） to Q i to get a new Q i ; use any one element in the equity information corresponding to each element in M （i，j，a） as a reference node for the next-level graph; and add 1 to the corresponding value of j as the new j value; Jump to step S23 for iteration; S25. After all the graph reference nodes corresponding to the i th data element in the data to be audited stop analysis, P i , the enterprise association graph corresponding to the i th data element in the data to be audited; Use the set composed of all enterprise names and shareholder names involved in the enterprise association graph as the enterprise association analysis set corresponding to the corresponding enterprise association graph.

4. The automated audit data analysis method according to claim 3, characterized in that: The calculation formula for obtaining the risk tracking interference evaluation value of the corresponding risk event in S3 is as follows: ； Among them, RP （k，g） represents the risk tracking interference evaluation value of the k th risk event of the g th enterprise in the data to be audited; Num （k，g） represents the number of each enterprise involved in the audit risk characteristics of the k th risk event of the g th enterprise in the data to be audited; COM （k，g，d） represents the enterprise association graph complexity coefficient of the k th enterprise involved in the audit risk characteristics of the g th risk event of the enterprise containing the data to be audited; d th enterprise; ； Level （k，g，d） Indicates the maximum level of the graph reference nodes in the enterprise association graph of the k th enterprise involved in the audit risk characteristics of the g th risk event among the data to be audited; d B （k，g，d） Indicates the maximum number of graph reference nodes at each level in the enterprise association graph of the k th enterprise involved in the audit risk characteristics of the g th risk event among the data to be audited; d W （k，g，d） Indicates the number of elements in the enterprise association analysis set corresponding to the k th enterprise involved in the audit risk characteristics of the g th risk event among the data to be audited; d r Indicates the preset first weight coefficient; β Indicates the preset second weight coefficient.​​​ 5. The automated audit data analysis method according to claim 4, wherein: The calculation formula for generating the audit priority coefficient of the corresponding risk event in S3 is as follows: ； Among them, F （k，g） represents the audit priority coefficient of the k th risk event corresponding to the g th enterprise in the data to be audited; E （k，g） represents the total number of risk events with unqualified audit results in the historical audit results of each enterprise included in the enterprise association analysis set of the enterprise association graph corresponding to the k th enterprise corresponding to the g th risk event; ES （k，g） represents the total number of risk events that have completed audits in the historical audit results of each enterprise included in the enterprise association analysis set of the enterprise association graph corresponding to the k th enterprise corresponding to the g th risk event, and ES （k，g） > 0; μ represents a preset constant; The risk event audit sequence of the corresponding enterprise is the arrangement result of each risk event in the corresponding enterprise in descending order of the audit priority coefficient.

6. The automated audit data analysis method according to claim 1, characterized in that: The specific execution process in S4 includes: The update result of the risk event audit sequence of each enterprise is the audit sequence composed of the remaining risk events after removing the risk events belonging to the marked risk events in the risk event audit sequence of the corresponding enterprise.

7. An automated audit data analysis system, characterized in that, The system includes the following modules: An audit risk feature extraction module, which extracts the audit features of each data element in the data to be audited based on the OCR image recognition technology and generates the risk events to which the audit features of each data element belong; Summarize each data element belonging to the same risk event in the audit data into the same set, and extract the audit risk features of the corresponding summary set of each risk event; An association graph analysis module, which constructs an enterprise association graph corresponding to the corresponding data element based on the equity information of each enterprise to which each data element in the audit data belongs; constructs an enterprise association analysis set corresponding to the enterprise association graph; An audit sequence analysis module, which obtains each risk event belonging to the same enterprise in the data to be audited. Combine the enterprise association analysis sets corresponding to the enterprises involved in each risk event, and the audit risk characteristics of the corresponding summary set of the corresponding risk event to obtain the risk tracking interference evaluation value of the corresponding risk event; Combined with the historical audit results of the enterprises involved in the corresponding risk events, generate the audit priority coefficients of the corresponding risk events, and construct the audit sequence of risk events for the corresponding enterprises; The audit sequence update management module, which will feedback the audit results of each risk event to the database in real time. The database retrieves the completed risk events for marking, and updates the audit sequences of risk events of each enterprise stored in the current database according to the marked risk events to obtain the audit sequences of unexecuted risk events of each enterprise.

8. An automated audit data analysis system according to claim 7, characterized in that: The audit sequence analysis module includes a risk tracking interference assessment unit, an audit priority coefficient calculation unit, and a risk event audit sequence construction unit. The risk tracking interference assessment unit obtains each risk event belonging to the same enterprise in the data to be audited, combines the enterprise correlation analysis sets corresponding to each enterprise involved in each risk event, and the audit risk characteristics of the corresponding summary set of the corresponding risk event, to obtain the risk tracking interference assessment value of the corresponding risk event. The audit priority coefficient calculation unit combines the historical audit results of the enterprises involved in the corresponding risk events to generate the audit priority coefficients of the corresponding risk events. The risk event audit sequence construction unit constructs the audit sequence of risk events for the corresponding enterprises according to the obtained results of the audit priority coefficient calculation unit.

Images