Intelligent auditing system and method

Abstract

The invention discloses an intelligent auditing system and method, and relates to the technical field of enterprise internal auditing, and the system comprises an auditing data extraction module which is used for extracting to-be-audited key data from a preset auditing database according to an auditing demand, classifying the to-be-audited key data, and determining multiple types of auditing key data sets; the auditing module is used for carrying out self-analysis and correlation analysis on the multiple types of auditing key data sets and determining a self-analysis result and a correlation analysis result; the exception marking module is used for performing difference exception marking on different types of audit key data sets based on the self-analysis result and the association analysis result, and determining exception data of each type of audit key data set; and the report generation module is used for generating an audit report based on the self-analysis result, the correlation analysis result and the abnormal data of the various types of audit key data sets. The auditing comprehensiveness and accuracy are ensured, the manual operation is reduced, the auditing period is shortened, and the auditing intelligence is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise internal auditing, and in particular to an intelligent auditing system and method. Background Art

[0002] With the rapid development of information technology and the increasing complexity of corporate business, traditional audit methods face many challenges. In today's digital age, enterprises generate massive amounts of data, which contains rich business information and potential risks.

[0003] However, traditional auditing mainly relies on manual operations, which has problems such as low efficiency, prone to errors, and difficulty in comprehensive coverage. Auditors need to spend a lot of time and energy to collect, organize and analyze data, and the audit results may be inaccurate and unintelligent due to human factors. At the same time, the existing intelligent auditing lacks comprehensive data analysis during the audit process, resulting in inaccurate and incomplete audit results. Summary of the Invention

[0004] The present invention provides an intelligent audit system and method, which is used to extract and classify key audit data, thereby improving the reliability of identifying and extracting key audit data, providing reliable data support and convenience for auditing. Secondly, self-analysis and correlation analysis are performed on the classified multi-type audit key data sets, so as to realize audit operations of different dimensions on the multi-type audit key data sets, thereby ensuring the comprehensiveness and accuracy of the audit. Finally, different types of audit key data sets are determined according to the results of self-analysis and correlation analysis, and differential anomaly marking is performed to realize effective determination of abnormal data. At the same time, an audit report is generated according to the self-analysis results, correlation analysis results and abnormal data of each type of audit key data set, thereby realizing effective presentation of audit results, reducing manual operations, shortening the audit cycle and improving the intelligence of the audit.

[0005] The present invention provides an intelligent audit system, comprising:

[0006] The audit data extraction module is used to extract key data to be audited from the preset audit database according to audit requirements, classify the key data to be audited, and determine multiple types of key audit data sets;

[0007] Audit module, used to perform self-analysis and correlation analysis on multiple types of audit key data sets, and determine the self-analysis results and correlation analysis results;

[0008] The anomaly marking module is used to mark the differences and anomalies of different types of audit key data sets based on the self-analysis results and the correlation analysis results, and to determine the abnormal data of each type of audit key data set;

[0009] The report generation module is used to generate audit reports based on self-analysis results, correlation analysis results and abnormal data of various types of audit key data sets.

[0010] Preferably, in the intelligent audit system, the audit data extraction module includes:

[0011] An audit requirement reading unit is used to parse the audit requirements input by the user terminal and determine the audit objectives;

[0012] A data retrieval unit is used to retrieve corresponding target source data from the database based on the audit target;

[0013] The data processing unit is used to read and process the target source data and obtain the key data to be audited based on the processing results;

[0014] The classification unit is used to read the audit type of the key data to be audited, and classify the key data to be audited according to the audit type to obtain multiple types of audit key data sets.

[0015] Preferably, in the intelligent audit system, the audit requirement reading unit includes:

[0016] The field information determination subunit is used to read the audit requirements, determine the field information of the audit requirements, and filter symbol characters in the field information;

[0017] The field information division sub-unit is used to divide the field information according to the symbol characters to obtain multiple sub-field information and, at the same time, obtain the preset audit vocabulary library;

[0018] The valid field determination subunit is used to input multiple field information into the audit vocabulary library for semantic matching and determine the valid field of each subfield information;

[0019] The audit target determination subunit is used to integrate the valid fields in each subfield information and use the integrated result as the audit target.

[0020] Preferably, in the intelligent audit system, the data retrieval unit includes:

[0021] The format conversion subunit is used to read the audit target and determine the data format of the source data stored in the database. At the same time, the format of the audit target is converted according to the data format of the source data.

[0022] A first extraction subunit is used to input the audit target after format conversion into the database for correlation matching, and to perform a first extraction of source data with a correlation greater than a preset correlation threshold in the database;

[0023] The second extraction subunit is used to determine the target range of the extracted source data according to the audit objectives, and to perform a second extraction on the source data whose correlation is greater than a preset correlation threshold according to the target range, and to determine the target source data based on the second extraction result.

[0024] Preferably, in the intelligent audit system, the data processing unit includes:

[0025] A data format determination subunit is used to read the target source data and determine the data format of the target source data;

[0026] Data format conversion subunit, used for:

[0027] Read the format conversion strategy table;

[0028] Among them, the format conversion strategy table contains conversion strategies for different data formats;

[0029] Match the data format of the target source data in the format conversion strategy table, and determine a target data conversion strategy that is consistent with the data format of the target source data based on the matching result;

[0030] Performing format conversion on the target source data according to the target data conversion strategy to obtain first target source data;

[0031] The sub-unit for determining key data to be audited is used to:

[0032] Acquire the semantic structure of the first target source data, and semantically split the first target source data according to the semantic structure to obtain a plurality of sub-first target source data;

[0033] determining a structural attribute of each sub-first target source data, and extracting valid data from each sub-first target source data according to the structural attribute;

[0034] Integrate the valid data of each sub-first target source data to obtain the second target source data;

[0035] Among them, the second target source data is the key data to be audited.

[0036] Preferably, in the intelligent audit system, the audit module includes:

[0037] A data reading unit is used to read the audit key data set corresponding to each type respectively, and perform data mapping of each type of audit key data set in a preset rectangular coordinate system;

[0038] A discrete point determination unit, for obtaining, based on the data mapping result, discrete points corresponding to the audit key data of each type in a preset rectangular coordinate system;

[0039] Data curve acquisition unit, used for:

[0040] Determine the data envelope of the audit key data based on the position of the discrete points in the preset rectangular coordinate system, and at the same time, connect the discrete points;

[0041] Smoothing the connected discrete points based on the data envelopment to obtain the data curves corresponding to each type of audit key data set;

[0042] Curve analysis unit for:

[0043] Read the data curve, determine the data vertices of the data curve, and split the data curve according to the data vertices to obtain multiple data curve segments;

[0044] Calculating the data curvature corresponding to each data curve segment, and determining the data transformation trend and data transformation rate of each data curve segment according to the data curvature of each data curve segment;

[0045] Self-analyzing unit for:

[0046] Read the security data attributes of each type of audit key data set, and determine the standard range interval, data transformation rate threshold, and standard data transformation trend corresponding to each type based on the security data attributes;

[0047] Compare the data range, data conversion trend, and data conversion rate of each data curve segment with the standard range, data conversion rate threshold, and standard data conversion trend of the corresponding type to determine the data state of each data curve segment;

[0048] Wherein, when the data range interval of a data curve segment does not belong to the standard range interval, or the data transformation trend does not belong to the standard data transformation trend, or the data transformation rate is greater than the data transformation rate threshold, the data status of the data curve segment is an audit failure status;

[0049] Otherwise, the data status of the data curve segment is audit qualified.

[0050] Summarize the data status of each data curve segment to determine the self-analysis results of each type of audit key data set;

[0051] The correlation analysis unit is used to obtain the correlation relationship between each type of audit key data set, and perform correlation analysis on each type of audit key data set according to the correlation relationship to obtain the correlation analysis result.

[0052] Preferably, in the intelligent audit system, the correlation analysis unit includes:

[0053] The influence standard determination subunit is used to retrieve the association relationship between each type of audit key data set and determine the influence standard of the data change trend of each type of data curve on the change trend of other types of data curves based on the association relationship;

[0054] The association analysis result generation subunit is used to:

[0055] Read the data curves corresponding to each type of audit key data set, determine the change trend of each data curve, and make a first record of the data curves that do not meet the impact criteria, and at the same time, make a second record of the data curves that meet the impact criteria;

[0056] Generate an association analysis result based on the first recording result and the second recording result.

[0057] Preferably, in the intelligent audit system, the abnormality marking module includes:

[0058] An abnormal data determination unit, configured to determine the location of abnormal data in the audit key data set based on the self-analysis result and the correlation analysis result;

[0059] The marking unit is used to obtain the marking method of each type, and mark the abnormal data positions in the corresponding audit key data set according to the marking method of each type, and extract the abnormal data of each type of audit key data set according to the abnormal marking results.

[0060] Preferably, in the intelligent audit system, the report generation module includes:

[0061] The encryption unit is used to obtain the browsing authority of the audit report after the audit report is generated, and to encrypt the audit report according to the browsing authority to obtain the encrypted audit report;

[0062] The transmission and display unit is used to transmit the encrypted audit report to the user terminal, and when the user terminal successfully decrypts the encrypted audit report, the audit report is visually displayed based on the user terminal.

[0063] The present invention provides an intelligent audit method, comprising:

[0064] Step 1: Extract key data to be audited from the preset audit database according to audit requirements, classify the key data to be audited, and determine multiple types of key audit data sets;

[0065] Step 2: Conduct self-analysis and correlation analysis on multiple types of audit key data sets to determine the self-analysis results and correlation analysis results;

[0066] Step 3: Based on the self-analysis results and the correlation analysis results, different types of audit key data sets are marked with different anomalies to determine the abnormal data of each type of audit key data set;

[0067] Step 4: Generate an audit report based on the self-analysis results, correlation analysis results, and abnormal data of various types of audit key data sets.

[0068] Compared with the prior art, the present invention has the following beneficial effects: by extracting and classifying key audit data, the reliability of identifying and extracting key audit data is improved, and reliable data support and convenience are provided for auditing; secondly, self-analysis and correlation analysis are performed on the classified multi-type audit key data sets, and audit operations of different dimensions are performed on the multi-type audit key data sets, thereby ensuring the comprehensiveness and accuracy of the audit; finally, different types of audit key data sets are determined according to the results of self-analysis and correlation analysis, and differential anomaly marking is performed, thereby effectively determining abnormal data; at the same time, an audit report is generated according to the self-analysis results, correlation analysis results and abnormal data of each type of audit key data set, thereby achieving effective presentation of the audit results, reducing manual operations, shortening the audit cycle, and improving the intelligence of the audit.

[0069] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0071] Figure 1 This is a structural diagram of an intelligent audit system in an embodiment of the present invention;

[0072] Figure 2 This is a structural diagram of an audit data extraction module in an intelligent audit system in an embodiment of the present invention;

[0073] Figure 3 This is a structural diagram of an audit module in an intelligent audit system in an embodiment of the present invention;

[0074] Figure 4 This is a structural diagram of an abnormality marking module in an intelligent audit system in an embodiment of the present invention;

[0075] Figure 5 This is a structural diagram of a report generation module in an intelligent audit system in an embodiment of the present invention;

[0076] Figure 6 The figure is a flow chart of an intelligent audit method in an embodiment of the present invention. DETAILED DESCRIPTION

[0077] The following will be combined with the accompanying 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 embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0078] Example:

[0079] It should be noted that the terms "including" and "having" in the embodiments of the present invention and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or devices.

[0080] Example 1:

[0081] This embodiment provides an intelligent audit system, such as Figure 1 Shown, including:

[0082] The audit data extraction module is used to extract key data to be audited from the preset audit database according to audit requirements, classify the key data to be audited, and determine multiple types of key audit data sets;

[0083] Audit module, used to perform self-analysis and correlation analysis on multiple types of audit key data sets, and determine the self-analysis results and correlation analysis results;

[0084] The anomaly marking module is used to mark the differences and anomalies of different types of audit key data sets based on the self-analysis results and the correlation analysis results, and to determine the abnormal data of each type of audit key data set;

[0085] The report generation module is used to generate audit reports based on self-analysis results, correlation analysis results and abnormal data of various types of audit key data sets.

[0086] In this embodiment, the audit requirements are known in advance, including the types of projects that need to be audited and the audit standards.

[0087] In this embodiment, the preset audit database is set in advance and is used to store various types of data to be audited, such as financial revenue and expenditure data, corporate debt data, and operating activity data.

[0088] In this embodiment, the key data to be audited may be data related to audit requirements retrieved from a preset audit database.

[0089] In this embodiment, the audit key data set may be a result obtained by extracting key information from the audit key data and performing data classification.

[0090] In this embodiment, the self-analysis may be to analyze the value range and data change of each type of audit key data set.

[0091] In this embodiment, the correlation analysis may be a comprehensive analysis of the correlation relationships and mutual restrictions between different types of audit key data sets, in order to comprehensively analyze the relative change trends and other characteristics between different types of audit key data sets.

[0092] In this embodiment, the difference anomaly mark can be the abnormal data (data that is obviously inconsistent with business activities or financial revenue and expenditure, etc.) existing in different types of audit key data sets determined based on the self-analysis results and the correlation analysis results, and each category of abnormal data is marked in a different format or method.

[0093] The working principle and beneficial effects of the above technical solution are: by extracting and classifying key audit data, the reliability of identifying and extracting key audit data is improved, providing reliable data support and convenience for auditing; secondly, self-analysis and correlation analysis are performed on the classified multi-type audit key data sets, so as to realize audit operations of different dimensions on multi-type audit key data sets, thereby ensuring the comprehensiveness and accuracy of the audit; finally, different types of audit key data sets are determined according to the results of self-analysis and correlation analysis and differential anomaly marking is performed, so as to realize effective determination of abnormal data; at the same time, an audit report is generated according to the self-analysis results, correlation analysis results and abnormal data of various types of audit key data sets, thereby realizing effective presentation of audit results, reducing manual operations, shortening the audit cycle and improving the intelligence of the audit.

[0094] Example 2:

[0095] Based on Example 1, this example provides an audit data extraction module, such as Figure 2 As shown, including:

[0096] An audit requirement reading unit is used to parse the audit requirements input by the user terminal and determine the audit objectives;

[0097] A data retrieval unit is used to retrieve corresponding target source data from the database based on the audit target;

[0098] The data processing unit is used to read and process the target source data and obtain the key data to be audited based on the processing results;

[0099] The classification unit is used to read the audit type of the key data to be audited, and classify the key data to be audited according to the audit type to obtain multiple types of audit key data sets.

[0100] Example 3:

[0101] Based on Example 2, this embodiment provides an audit requirement reading unit, including:

[0102] The field information determination subunit is used to read the audit requirements, determine the field information of the audit requirements, and filter symbol characters in the field information;

[0103] The field information division sub-unit is used to divide the field information according to the symbol characters to obtain multiple sub-field information and, at the same time, obtain the preset audit vocabulary library;

[0104] The valid field determination subunit is used to input multiple field information into the audit vocabulary library for semantic matching and determine the valid field of each subfield information;

[0105] The audit target determination subunit is used to integrate the valid fields in each subfield information and use the integrated result as the audit target.

[0106] Example 4:

[0107] Based on Example 2, this embodiment provides a data retrieval unit, including:

[0108] The format conversion subunit is used to read the audit target and determine the data format of the source data stored in the database. At the same time, the format of the audit target is converted according to the data format of the source data.

[0109] A first extraction subunit is used to input the audit target after format conversion into the database for correlation matching, and to perform a first extraction of source data with a correlation greater than a preset correlation threshold in the database;

[0110] The second extraction subunit is used to determine the target range of the extracted source data according to the audit objectives, and to perform a second extraction on the source data whose correlation is greater than a preset correlation threshold according to the target range, and to determine the target source data based on the second extraction result.

[0111] Example 5:

[0112] Based on Example 2, this embodiment provides a data processing unit, including:

[0113] A data format determination subunit is used to read the target source data and determine the data format of the target source data;

[0114] Data format conversion subunit, used for:

[0115] Read the format conversion strategy table;

[0116] Among them, the format conversion strategy table contains conversion strategies for different data formats;

[0117] Match the data format of the target source data in the format conversion strategy table, and determine a target data conversion strategy that is consistent with the data format of the target source data based on the matching result;

[0118] Performing format conversion on the target source data according to the target data conversion strategy to obtain first target source data;

[0119] The sub-unit for determining key data to be audited is used to:

[0120] Acquire the semantic structure of the first target source data, and semantically split the first target source data according to the semantic structure to obtain a plurality of sub-first target source data;

[0121] determining a structural attribute of each sub-first target source data, and extracting valid data from each sub-first target source data according to the structural attribute;

[0122] Integrate the valid data of each sub-first target source data to obtain the second target source data;

[0123] Among them, the second target source data is the key data to be audited.

[0124] Example 6:

[0125] Based on Example 1, this example provides an audit module, such as Figure 3 Shown, including:

[0126] A data reading unit is used to read the audit key data set corresponding to each type respectively, and perform data mapping of each type of audit key data set in a preset rectangular coordinate system;

[0127] A discrete point determination unit, for obtaining, based on the data mapping result, discrete points corresponding to the audit key data of each type in a preset rectangular coordinate system;

[0128] Data curve acquisition unit, used for:

[0129] Determine the data envelope of the audit key data based on the position of the discrete points in the preset rectangular coordinate system, and at the same time, connect the discrete points;

[0130] Smoothing the connected discrete points based on the data envelopment to obtain the data curves corresponding to each type of audit key data set;

[0131] Curve analysis unit for:

[0132] Read the data curve, determine the data vertices of the data curve, and split the data curve according to the data vertices to obtain multiple data curve segments;

[0133] Calculating the data curvature corresponding to each data curve segment, and determining the data transformation trend and data transformation rate of each data curve segment according to the data curvature of each data curve segment;

[0134] Self-analyzing unit for:

[0135] Read the security data attributes of each type of audit key data set, and determine the standard range interval, data transformation rate threshold, and standard data transformation trend corresponding to each type based on the security data attributes;

[0136] Compare the data range, data conversion trend, and data conversion rate of each data curve segment with the standard range, data conversion rate threshold, and standard data conversion trend of the corresponding type to determine the data state of each data curve segment;

[0137] Wherein, when the data range interval of a data curve segment does not belong to the standard range interval, or the data transformation trend does not belong to the standard data transformation trend, or the data transformation rate is greater than the data transformation rate threshold, the data status of the data curve segment is an audit failure status;

[0138] Otherwise, the data status of the data curve segment is audit qualified.

[0139] Summarize the data status of each data curve segment to determine the self-analysis results of each type of audit key data set;

[0140] The correlation analysis unit is used to obtain the correlation relationship between each type of audit key data set, and perform correlation analysis on each type of audit key data set according to the correlation relationship to obtain the correlation analysis result.

[0141] Example 7:

[0142] Based on Example 6, this embodiment provides an association analysis unit, including:

[0143] The influence standard determination subunit is used to retrieve the association relationship between each type of audit key data set and determine the influence standard of the data change trend of each type of data curve on the change trend of other types of data curves based on the association relationship;

[0144] The association analysis result generation subunit is used to:

[0145] Read the data curves corresponding to each type of audit key data set, determine the change trend of each data curve, and make a first record of the data curves that do not meet the impact criteria, and at the same time, make a second record of the data curves that meet the impact criteria;

[0146] Generate an association analysis result based on the first recording result and the second recording result.

[0147] Example 8:

[0148] Based on Example 1, this example provides an abnormality marking module, such as Figure 4 Shown, including:

[0149] An abnormal data determination unit, configured to determine the location of abnormal data in the audit key data set based on the self-analysis result and the correlation analysis result;

[0150] The marking unit is used to obtain the marking method of each type, and mark the abnormal data positions in the corresponding audit key data set according to the marking method of each type, and extract the abnormal data of each type of audit key data set according to the abnormal marking results.

[0151] Example 9:

[0152] Based on Example 1, this example provides a report generation module, such as Figure 5 Shown, including:

[0153] The encryption unit is used to obtain the browsing authority of the audit report after the audit report is generated, and to encrypt the audit report according to the browsing authority to obtain the encrypted audit report;

[0154] The transmission and display unit is used to transmit the encrypted audit report to the user terminal, and when the user terminal successfully decrypts the encrypted audit report, the audit report is visually displayed based on the user terminal.

[0155] Example 10:

[0156] This embodiment provides an intelligent audit method, such as Figure 6 Shown, including:

[0157] Step 1: Extract key data to be audited from the preset audit database according to audit requirements, classify the key data to be audited, and determine multiple types of key audit data sets;

[0158] Step 2: Conduct self-analysis and correlation analysis on multiple types of audit key data sets to determine the self-analysis results and correlation analysis results;

[0159] Step 3: Based on the self-analysis results and the correlation analysis results, different types of audit key data sets are marked with different anomalies to determine the abnormal data of each type of audit key data set;

[0160] Step 4: Generate an audit report based on the self-analysis results, correlation analysis results, and abnormal data of various types of audit key data sets.

[0161] Since the intelligent audit method is a method corresponding to the intelligent audit system of the embodiment of the present invention, and the principle of solving the problem by this method is similar to that of the intelligent audit system, the implementation of the intelligent audit method can refer to the implementation process of the above-mentioned system embodiment, and the repeated parts will not be repeated.

[0162] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0163] The above embodiments are intended only to illustrate the technical concepts and features of the present invention. Their purpose is to enable those skilled in the art to understand the contents of the present invention and implement them accordingly. They are not intended to limit the scope of protection of the present invention. Any equivalent changes or modifications made based on the essence of the present invention are intended to be covered by the scope of protection of the present invention.

Claims

1. An intelligent audit system, characterized in that: include: The audit data extraction module is used to extract key data to be audited from the preset audit database according to audit requirements, classify the key data to be audited, and determine multiple types of key audit data sets; Audit module, used to perform self-analysis and correlation analysis on multiple types of audit key data sets, and determine the self-analysis results and correlation analysis results; The anomaly marking module is used to mark the differences and anomalies of different types of audit key data sets based on the self-analysis results and the correlation analysis results, and to determine the abnormal data of each type of audit key data set; The report generation module is used to generate audit reports based on self-analysis results, correlation analysis results and abnormal data of various types of audit key data sets.

2. The intelligent audit system according to claim 1, characterized in that: Audit data extraction module, including: An audit requirement reading unit is used to analyze the audit requirements input by the user terminal and determine the audit objectives; A data retrieval unit is used to retrieve corresponding target source data from the audit database based on the audit target; The data processing unit is used to read and process the target source data and obtain the key data to be audited based on the processing results; The classification unit is used to read the audit type of the key data to be audited, and classify the key data to be audited according to the audit type to obtain multiple types of audit key data sets.

3. The intelligent audit system according to claim 2, characterized in that: Audit requirement reading unit, including: The field information determination subunit is used to read the audit requirements, determine the field information of the audit requirements, and filter symbol characters in the field information; The field information division sub-unit is used to divide the field information according to the symbol characters to obtain multiple sub-field information and, at the same time, obtain the preset audit vocabulary library; The valid field determination subunit is used to input multiple field information into the audit vocabulary library for semantic matching and determine the valid field of each subfield information; The audit target determination subunit is used to integrate the valid fields in each subfield information and use the integrated result as the audit target.

4. The intelligent audit system according to claim 2, characterized in that: Data retrieval unit, including: The format conversion subunit is used to read the audit target and determine the data format of the source data stored in the audit database. At the same time, the format of the audit target is converted according to the data format of the source data. A first extraction subunit is used to input the audit target after format conversion into the audit database for correlation matching, and to perform a first extraction of source data with a correlation greater than a preset correlation threshold in the audit database; The second extraction subunit is used to determine the target range of the extracted source data according to the audit objectives, and to perform a second extraction on the source data whose correlation is greater than a preset correlation threshold according to the target range, and to determine the target source data based on the second extraction result.

5. The intelligent audit system according to claim 2, characterized in that: Data processing unit, including: A data format determination subunit is used to read the target source data and determine the data format of the target source data; A data format conversion subunit, used for reading the format conversion strategy table; Among them, the format conversion strategy table contains conversion strategies for different data formats; Match the data format of the target source data in the format conversion strategy table, and determine a target data conversion strategy that is consistent with the data format of the target source data based on the matching result; Performing format conversion on the target source data according to the target data conversion strategy to obtain first target source data; The sub-unit for determining key data to be audited is used to: Acquire the semantic structure of the first target source data, and semantically split the first target source data according to the semantic structure to obtain a plurality of sub-first target source data; determining a structural attribute of each sub-first target source data, and extracting valid data from each sub-first target source data according to the structural attribute; Integrate the valid data of each sub-first target source data to obtain the second target source data; Among them, the second target source data is the key data to be audited.

6. The intelligent audit system according to claim 1, characterized in that: Audit module, including: A data reading unit is used to read the audit key data set corresponding to each type respectively, and perform data mapping of each type of audit key data set in a preset rectangular coordinate system; A discrete point determination unit, for obtaining, based on the data mapping result, discrete points corresponding to the audit key data of each type in a preset rectangular coordinate system; Data curve acquisition unit, used for: Determine the data envelope of the audit key data based on the position of the discrete points in the preset rectangular coordinate system, and at the same time, connect the discrete points; Smoothing the connected discrete points based on the data envelopment to obtain the data curves corresponding to each type of audit key data set; Curve analysis unit for: Read the data curve, determine the data vertices of the data curve, and split the data curve according to the data vertices to obtain multiple data curve segments; Calculating the data curvature corresponding to each data curve segment, and determining the data transformation trend and data transformation rate of each data curve segment according to the data curvature of each data curve segment; Self-analyzing unit for: Read the security data attributes of each type of audit key data set, and determine the standard range interval, data transformation rate threshold, and standard data transformation trend corresponding to each type based on the security data attributes; Compare the data range, data conversion trend, and data conversion rate of each data curve segment with the standard range, data conversion rate threshold, and standard data conversion trend of the corresponding type to determine the data state of each data curve segment; Wherein, when the data range interval of a data curve segment does not belong to the standard range interval, or the data transformation trend does not belong to the standard data transformation trend, or the data transformation rate is greater than the data transformation rate threshold, the data status of the data curve segment is an audit failure status; Otherwise, the data status of the data curve segment is audit qualified; Summarize the data status of each data curve segment to determine the self-analysis results of each type of audit key data set; The correlation analysis unit is used to obtain the correlation relationship between each type of audit key data set, and perform correlation analysis on each type of audit key data set according to the correlation relationship to obtain the correlation analysis result.

7. The intelligent audit system according to claim 6, characterized in that: Association analysis unit, including: The influence standard determination subunit is used to retrieve the association relationship between each type of audit key data set and determine the influence standard of the data change trend of each type of data curve on the change trend of other types of data curves based on the association relationship; The association analysis result generation subunit is used to: Read the data curves corresponding to each type of audit key data set, determine the change trend of each data curve, and make a first record of the data curves that do not meet the impact criteria, and at the same time, make a second record of the data curves that meet the impact criteria; Generate an association analysis result based on the first recording result and the second recording result.

8. The intelligent audit system according to claim 1, characterized in that: Abnormal marking module, including: An abnormal data determination unit, configured to determine the location of abnormal data in the audit key data set based on the self-analysis result and the correlation analysis result; The marking unit is used to obtain the marking method of each type, and mark the abnormal data positions in the corresponding audit key data set according to the marking method of each type, and extract the abnormal data of each type of audit key data set according to the abnormal marking results.

9. The intelligent audit system according to claim 1, characterized in that: Report generation module, including: The encryption unit is used to obtain the browsing authority of the audit report after the audit report is generated, and to encrypt the audit report according to the browsing authority to obtain the encrypted audit report; The transmission and display unit is used to transmit the encrypted audit report to the user terminal, and when the user terminal successfully decrypts the encrypted audit report, the audit report is visually displayed based on the user terminal.

10. An intelligent audit method, characterized in that: Including steps: Extract key data to be audited from the preset audit database according to audit requirements, classify the key data to be audited, and determine multiple types of key audit data sets; Conduct self-analysis and correlation analysis on multiple types of audit key data sets to determine the self-analysis results and correlation analysis results; Based on the self-analysis results and the correlation analysis results, the different types of audit key data sets are marked with different anomalies to determine the abnormal data of each type of audit key data set; Generate audit reports based on self-analysis results, correlation analysis results, and abnormal data of various types of audit key data sets.

Images