A visualization method and system based on audit data

Abstract

The present invention relates to the field of data processing technology, and in particular to a visualization method and system based on audit data. The method includes the steps of: obtaining the degree of disorder of data in the audit data sequence according to the maximum value points and the minimum value points in the audit data sequence; obtaining the initial possibility that each extreme value point in the audit data sequence is a segmentation point according to the degree of disorder, clustering all extreme value points in the audit data sequence, dividing the obtained cluster clusters into first category cluster clusters, second category cluster clusters and third category cluster clusters, setting the extreme value points in the first category cluster clusters as segmentation points; obtaining the second possibility that each extreme value point in the third category cluster cluster is a segmentation point, and obtaining the segmentation point based on the second possibility; performing spline regression on the audit data sequence according to all the segmentation points to realize the visualization of the audit data. The present invention improves the rationality of the selection of segmentation points, so that the obtained fitting curve reflects the changing trend of the audit data more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a visualization method and system based on audit data. Background Art

[0002] The visualization of audit data can help auditors understand the distribution and changing trends of audit data, and can assist auditors in grasping the future development trends of data. Therefore, in order to meet the needs of audit work, it is necessary to visualize audit data to facilitate auditors to access and view it.

[0003] The patent document with the authorization announcement number CN108090323B currently discloses a wind power curve fitting method based on infinite mixed Gaussian and spline regression, including the steps of data preprocessing, constructing a robust spline regression model, optimizing the robust spline regression model using variational Bayesian, and deriving a power curve and a probabilistic power curve.

[0004] Usually, the spline regression algorithm is used to fit the audit data to obtain the fitting curve, and then the audit data is visualized. The implementation of the spline regression algorithm requires setting the segmentation points of the spline function in the audit data to cope with the complexity of the nonlinear relationship. However, the unreasonable setting of the segmentation points of the spline function will make the obtained fitting curve not accurately reflect the changing trend of the audit data, which will affect the auditor's analysis of the audit data. Summary of the invention

[0005] In order to solve the technical problem that unreasonable setting of segmentation points of spline function will make the obtained fitting curve not accurately reflect the changing trend of audit data, which will affect the auditors' analysis of audit data, the present invention provides a visualization method and system based on audit data.

[0006] In a first aspect, the present invention provides a visualization method based on audit data, which adopts the following technical solution:

[0007] A visualization method based on audit data, comprising the steps of:

[0008] Collect audit data sequence; obtain the initial possibility of each extreme point in the audit data sequence as a segmentation point , Represents the initial possibility that the i-th extreme point is a segmentation point; Represents the degree of disorder of the data in the audit data sequence; Represents the number of data that each data in the left window of the i-th extreme point is larger than its previous data; Represents the number of data that each data in the right window of the i-th extreme point is larger than the previous data; Represents the number of data in the right window of the i-th extreme point; Represents the mean of all data in the right window and the left window of the i-th extreme point; Represents the value of the i-th extreme point; represent and The maximum value in ;

[0009] According to the initial possibility, all extreme points in the audit data sequence are clustered to obtain the first category clustering cluster and the third category clustering cluster, and the extreme points in the first category clustering cluster are set as segmentation points; the second possibility that each extreme point in the third category clustering cluster is a segmentation point is obtained; based on the second possibility, the segmentation points are obtained; spline regression is performed on the audit data sequence according to all the segmentation points to realize the visualization of the audit data.

[0010] The innovation of the present invention lies in obtaining the initial possibility of each extreme point in the audit data sequence being a segmentation point according to the changing trend of each extreme point and the surrounding data, and then determining the segmentation point position according to the initial possibility of the extreme point being a segmentation point, so that the extreme points in the audit data sequence that are more suitable as segmentation points can be screened out, avoiding the situation in which the fitting curve due to unreasonable segmentation point setting does not accurately reflect the changing trend of the audit data, which can help auditors to perform audit data analysis to a certain extent; further, the initial possibility of each extreme point in the audit data sequence being a segmentation point is corrected using the degree of clutter of the data in the audit data sequence, avoiding setting too many segmentation points and reducing the risk of over-fitting of the curve.

[0011] Preferably, the process of obtaining the disorder degree of data in the audit data sequence includes:

[0012] Obtain the maximum and minimum points in the audit data sequence;

[0013] ;

[0014] In the formula, Represents the degree of disorder of the data in the audit data sequence; Represents the number of maximum points in the sequence in the audit data; Represents the number of minimum value points in the audit data sequence; Represents the number of data in the audit data sequence; Represents the average value of all maximum points in the audit data sequence; Represents the average value of all minimum points in the audit data sequence; exp() represents the exponential function with a natural constant as the base.

[0015] This facilitates the subsequent use of the clutter of the data in the audit data sequence to correct the initial possibility of each extreme point in the audit data sequence being a segmentation point, avoids setting too many segmentation points, and reduces the risk of curve overfitting.

[0016] Preferably, the step of obtaining the maximum value point and the minimum value point in the audit data sequence includes:

[0017] Use the peak detection algorithm to obtain the maximum and minimum points in the audit data sequence.

[0018] This facilitates the subsequent analysis of extreme points and the acquisition of reasonable segmentation points among the extreme points.

[0019] Preferably, the process of obtaining the left window of the extreme point includes:

[0020] The number of window data is preset as T, and the T data on the left side of each extreme point in the audit data sequence are used as the left window of each extreme point in the audit data sequence.

[0021] Preferably, the process of acquiring the right window of the extreme point includes:

[0022] The number of window data is preset as T, and the T data on the right side of each extreme point in the audit data sequence are used as the right window of each extreme point in the audit data sequence.

[0023] Preferably, the obtaining of the first category cluster and the third category cluster includes:

[0024] The number of clusters is preset. According to the preset number of clusters and the initial possibility that all extreme points in the audit data sequence are segmentation points, all extreme points in the audit data sequence are clustered using the K-means clustering algorithm to obtain each cluster. The average value of the initial possibility that all extreme points in each cluster are segmentation points is obtained, and the cluster with the largest average value is recorded as the first category cluster; the cluster with the middle average value is recorded as the third category cluster.

[0025] After clustering all extreme points in the audit data sequence, some accurate segmentation points can be screened out, and then the remaining extreme points can be analyzed.

[0026] Preferably, the second possibility of obtaining each extreme point in the third category cluster as a segmentation point includes:

[0027] ;

[0028] In the formula, Represents the second possibility that the jth extreme point in the third category cluster is a segmentation point; Represents the mean of the initial likelihood that all extreme points in the first category cluster are segmentation points; Represents the mean of the initial likelihood that all extreme points in the second category cluster are segmentation points; Represents the initial possibility that the jth extreme point in the third category cluster is a segmentation point; exp() represents an exponential function with a natural constant as the base.

[0029] Preferably, obtaining segmentation points based on the second possibility includes:

[0030] A second possibility threshold T2 is preset. If the second possibility that the j-th extreme point in the third category cluster is a segmentation point is greater than or equal to the second possibility threshold T2, the j-th extreme point in the third category cluster is set as a segmentation point to obtain all segmentation points.

[0031] The obtained segmentation points are more reasonable, so that the obtained fitting curve can accurately reflect the changing trend of the audit data and improve the accuracy of the auditors' analysis of the audit data.

[0032] Preferably, the acquisition of audit data sequence includes:

[0033] Any dimension of audit data in the database is recorded as target data; in the database, all target data are obtained in chronological order, and all the target data are formed into a sequence, which is recorded as an audit data sequence.

[0034] In a second aspect, the present invention provides a visualization system based on audit data, which adopts the following technical solution:

[0035] A visualization system based on audit data includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned visualization method based on audit data is implemented.

[0036] By adopting the above technical solution, the above-mentioned visualization method based on audit data is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0037] The present invention has the following technical effects: the purpose of the present invention is to obtain the initial possibility that each extreme point in the audit data sequence is a segmentation point according to the changing trend of each extreme point and its surrounding data, and then determine the segmentation point position according to the initial possibility that the extreme point is a segmentation point, so that the extreme points in the audit data sequence that are more suitable as segmentation points can be screened out, avoiding the situation where the fitting curve caused by unreasonable segmentation point setting does not accurately reflect the changing trend of the audit data, and facilitating the subsequent spline regression of the audit data based on reasonable segmentation points, so that the obtained fitting curve can better reflect the changing trend of the audit data, which can help auditors to analyze the audit data to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0039] Figure 1 It is a method flow chart of a visualization method based on audit data in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0041] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0042] The embodiment of the present invention discloses a visualization method based on audit data, referring to Figure 1 , comprising steps S1 to S3:

[0043] S1: Collect audit data sequence.

[0044] In the embodiment of the present invention, any dimension data of the audit data in the database is recorded as target data; in the database, all target data are obtained in chronological order, and all the target data are formed into a sequence, which is recorded as an audit data sequence; and the audit data sequence is subjected to operations of removing duplicate values, filling in missing values, and correcting abnormal values;

[0045] Among them, this embodiment uses a hash algorithm to identify duplicate values ​​and remove duplicate values; uses a mode statistic value filling method to fill missing values; uses a mean value correction method to correct outliers; this embodiment does not limit the methods of removing duplicate values, filling missing values, and correcting outliers, and implementers can choose the methods of removing duplicate values, filling missing values, and correcting outliers according to actual conditions.

[0046] S2: Obtain the maximum and minimum points in the audit data sequence, and obtain the degree of disorder of the data in the audit data sequence based on the maximum and minimum points; obtain the initial possibility that each extreme point in the audit data sequence is a segmentation point based on the degree of disorder of the data in the audit data sequence and the difference in the increasing situation of the data on both sides of each extreme point in the audit data sequence.

[0047] It should be noted that, in general, a spline regression algorithm is used to fit the audit data to obtain a fitting curve, thereby realizing the visualization of the audit data. The implementation of the spline regression algorithm requires setting segmentation points of the spline function in the audit data to cope with the complexity of the nonlinear relationship. However, the unreasonable setting of the segmentation points of the spline function will make the obtained fitting curve not accurately reflect the changing trend of the audit data, which will affect the auditors' analysis of the audit data. Therefore, the purpose of the present invention is to obtain reasonable segmentation points in the audit data.

[0048] Step S2 includes steps S20 and S21, which are specifically as follows:

[0049] S20: Obtain the maximum value points and the minimum value points in the audit data sequence, and obtain the degree of disorder of the data in the audit data sequence according to the maximum value points and the minimum value points.

[0050] It should be noted that due to the certain fluctuations in the data in the audit data sequence, the data will also produce a certain degree of chaotic changes on the basis of a certain overall trend in the process of changing according to the trend, and this chaotic change will affect the selection of segmentation points. Therefore, the present invention first obtains the extreme points in the audit data sequence, and then analyzes the degree of chaos of the data in the audit data sequence according to the extreme points.

[0051] In the embodiment of the present invention, a peak detection algorithm is used to obtain the maximum value points and the minimum value points in the audit data sequence.

[0052] Get the level of chaos in the audit data sequence:

[0053] ;

[0054] In the formula, Represents the degree of disorder of the data in the audit data sequence; Represents the number of maximum points in the sequence in the audit data; Represents the number of minimum value points in the audit data sequence; Represents the number of data in the audit data sequence; Represents the average value of all maximum points in the audit data sequence; Represents the average value of all minimum points in the audit data sequence; exp() represents an exponential function with a natural constant as the base; It represents the ratio of the data except the extreme points in the audit data sequence to all the data. The larger its value is, the more obvious the change trend of the data in the audit data sequence is, the less chaotic the data is, and the smaller its value is, the less obvious the change trend of the data in the audit data sequence is, the more chaotic the data is, and the greater the chaotic degree of the data in the audit data sequence is. Represents the relative size of the gap between the average level of the maximum value points and the average level of the minimum value points in the audit data sequence. The larger the value is, the greater the gap between the average level of the maximum value points and the average level of the minimum value points in the data is, and the more likely there is a significant fluctuation in the data, that is, the greater the degree of disorder of the data in the audit data sequence; The smaller the value, the closer the gap between the average level of the maximum value points and the average level of the minimum value points in the data is, which means that the fluctuation in the data is less significant and the data in the audit data sequence is less cluttered.

[0055] S21: According to the degree of disorder of the data in the audit data sequence and the difference in the increasing situation of the data on both sides of each extreme point in the audit data sequence, the initial possibility of each extreme point in the audit data sequence being a segmentation point is obtained.

[0056] It should be noted that when performing spline regression on audit data, audit data with obvious changes are usually selected as segmentation points. The extreme points in the audit data sequence obtained in the above steps have relatively obvious changes. Therefore, it is possible to determine whether to set the extreme point as a segmentation point based on the gap between each extreme point in the audit data sequence and its nearby data. Therefore, the present invention analyzes each extreme point in the audit data sequence and its nearby data to obtain the initial possibility that each extreme point in the audit data sequence is a segmentation point.

[0057] In an embodiment of the present invention, the T data on the left side of each extreme point in the audit data sequence are used as the left window of each extreme point in the audit data sequence, and the T data on the right side of each extreme point in the audit data sequence are used as the right window of each extreme point in the audit data sequence. It should be noted that the preset number of window data T=50. In other embodiments, the implementer can preset the value of the number of window data T according to the specific implementation situation.

[0058] Get the initial probability of each extreme point in the audit data sequence being a segmentation point:

[0059] ;

[0060] In the formula, Represents the initial possibility that the i-th extreme point in the audit data sequence is a segmentation point; Represents the degree of disorder of the data in the audit data sequence; Represents the number of data that are larger than the previous data in the left window of the i-th extreme point in the audit data sequence; Represents the number of data that are larger than the previous data in the right window of the i-th extreme point in the audit data sequence; Represents the number of data in the right window of the ith extreme value point in the audit data sequence; it should be noted that the number of data in the right window of the ith extreme value point in the audit data sequence is consistent with the number of data in the left window; Represents the mean of all data in the right window and the left window of the i-th extreme point in the audit data sequence; Represents the value of the i-th extreme point in the audit data sequence; represent and The maximum value in The values ​​of are normalized;

[0061] Represents the difference in the increasing situation of the data on both sides of the ith extreme point in the audit data sequence. The smaller its value is, the smaller the difference between the increasing situation of the data on both sides of the ith extreme point in the audit data sequence is, that is, the data on both sides of the ith extreme point in the audit data sequence have a more uniform linear change trend. At this time, the initial possibility that the ith extreme point in the audit data sequence is a segmentation point is smaller; the larger its value is, the larger the difference between the increasing situation of the data on both sides of the ith extreme point in the audit data sequence is, that is, the linear change trend of the data on both sides of the ith extreme point in the audit data sequence is inconsistent. At this time, the initial possibility that the ith extreme point in the audit data sequence is a segmentation point is greater; Represents the gap between the ith extreme point in the audit data sequence and the data nearby. The larger the value, the more prominent the ith extreme point is compared with the data points nearby, indicating that the data on both sides of the ith extreme point are more likely to have different change trends. Therefore, in order to achieve higher fitting accuracy of the subsequent fitted curve, the initial possibility that the ith extreme point in the audit data sequence is a segmentation point is greater.

[0062] It is known that the greater the degree of disorder in the audit data sequence, the more extreme points will be obtained. In order to avoid setting too many segmentation points and reduce the risk of overfitting of the curve, it is necessary to use the degree of disorder of the data in the audit data sequence to The value of The bigger the The value of is adjusted downward so that The smaller the value of .

[0063] S3: Cluster all extreme points in the audit data sequence, divide the obtained clusters into first category clusters, second category clusters and third category clusters, set the extreme points in the first category clusters as segmentation points; obtain the second possibility that each extreme point in the third category cluster is a segmentation point, and obtain the segmentation point based on the second possibility; perform spline regression on the audit data sequence according to all segmentation points to realize the visualization of the audit data.

[0064] Step S3 includes steps S30 and S31, which are specifically as follows:

[0065] S30: Cluster all extreme points in the audit data sequence, divide the obtained clusters into first category clusters, second category clusters and third category clusters, set the extreme points in the first category clusters as segmentation points; obtain the second possibility that each extreme point in the third category cluster is a segmentation point, and obtain the segmentation point based on the second possibility.

[0066] It should be noted that the fitting effect of the spline regression algorithm on audit data depends on the selection of data segmentation points. If the segmentation points are not selected reasonably, the spline regression will not be able to fit the various data segments generated by the segmentation points well. Therefore, in order to select more suitable segmentation points, the present invention determines the segmentation points based on the initial possibility that each extreme point in the audit data sequence is a segmentation point.

[0067] In an embodiment of the present invention, according to the preset number of clusters and the initial possibility that all extreme points in the audit data sequence are segmentation points, the K-means clustering algorithm is used to cluster all extreme points in the audit data sequence to obtain each cluster, and the average value of the initial possibility that all extreme points in each cluster are segmentation points is obtained. The cluster with the largest average value is recorded as the first category cluster, and the extreme points in the first category cluster are set as segmentation points; the cluster with the smallest average value is recorded as the second category cluster; and the cluster with an average value in the middle is recorded as the third category cluster.

[0068] Preset number of clusters In other embodiments, the implementer may preset the number of clusters according to the specific implementation method. The value of .

[0069] Get the second probability that each extreme point in the third category cluster is a segmentation point:

[0070] ;

[0071] In the formula, Represents the second possibility that the jth extreme point in the third category cluster is a segmentation point; Represents the mean of the initial likelihood that all extreme points in the first category cluster are segmentation points; Represents the mean of the initial likelihood that all extreme points in the second category cluster are segmentation points; represents the initial possibility that the jth extreme point in the third category cluster is a segmentation point; exp() represents an exponential function with a natural constant as the base; Represents the difference between the initial possibility that the jth extreme point in the third category cluster is a segmentation point and the average of the initial possibilities that all extreme points in the first category cluster are segmentation points. The smaller the value, the closer the jth extreme point in the third category cluster is to the average level of the first category cluster, that is, the jth extreme point in the third category cluster shows more significant changes or fluctuations around it, and at this time, the second possibility that the jth extreme point in the third category cluster is a segmentation point is greater; Used for The values ​​are normalized.

[0072] A second possibility threshold T2 is preset. If the second possibility that the j-th extreme point in the third category cluster is a segmentation point is greater than or equal to the second possibility threshold T2, the j-th extreme point in the third category cluster is set as a segmentation point to obtain all segmentation points. In an embodiment of the present invention, the second possibility threshold T2=0.65 is preset. In other embodiments, the implementer may preset the value of the second possibility threshold T2 according to the specific implementation method.

[0073] S31: Perform spline regression on the audit data based on all segmentation points to achieve visualization of the audit data.

[0074] In an embodiment of the present invention, spline regression is performed on the audit data based on the acquired segmentation points to obtain a spline regression result, and the audit data is visualized based on the spline regression result.

[0075] An embodiment of the present invention further discloses a visualization system based on audit data, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a visualization method based on audit data according to the present invention is implemented.

[0076] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0077] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0078] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0079] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A visualization method based on audit data, characterized in that: Includes steps: Collect audit data sequence; obtain the initial possibility of each extreme point in the audit data sequence as a segmentation point , Represents the initial possibility that the i-th extreme point is a segmentation point; Represents the degree of disorder of the data in the audit data sequence; Represents the number of data that each data in the left window of the i-th extreme point is larger than its previous data; Represents the number of data that each data in the right window of the i-th extreme point is larger than the previous data; Represents the number of data in the right window of the i-th extreme point; Represents the mean of all data in the right window and the left window of the i-th extreme point; Represents the value of the i-th extreme point; represent and The maximum value in ; Clustering all extreme value points in the audit data sequence according to the initial possibility to obtain first category clustering clusters and third category clustering clusters, including: The number of clusters is preset. According to the preset number of clusters and the initial possibility that all extreme points in the audit data sequence are segmentation points, all extreme points in the audit data sequence are clustered using the K-means clustering algorithm to obtain each cluster. The average value of the initial possibility that all extreme points in each cluster are segmentation points is obtained, and the cluster with the largest average value is recorded as the first category cluster; the cluster with the middle average value is recorded as the third category cluster; The extreme points in the first category clusters are set as segmentation points; the second possibility that each extreme point in the third category cluster is a segmentation point is obtained; based on the second possibility, the segmentation points are obtained; and spline regression is performed on the audit data sequence according to all the segmentation points to realize the visualization of the audit data.

2. A visualization method based on audit data according to claim 1, characterized in that: The process of obtaining the disorder degree of data in the audit data sequence includes: Obtain the maximum and minimum points in the audit data sequence; ； In the formula, Represents the degree of disorder of the data in the audit data sequence; Represents the number of maximum points in the sequence in the audit data; Represents the number of minimum value points in the audit data sequence; Represents the number of data in the audit data sequence; Represents the average value of all maximum points in the audit data sequence; Represents the average value of all minimum points in the audit data sequence; exp() represents the exponential function with a natural constant as the base.

3. A visualization method based on audit data according to claim 2, characterized in that: The step of obtaining the maximum value point and the minimum value point in the audit data sequence includes: Use the peak detection algorithm to obtain the maximum and minimum points in the audit data sequence.

4. A visualization method based on audit data according to claim 1, characterized in that: The process of obtaining the left window of the extreme point includes: The number of window data is preset as T, and the T data on the left side of each extreme point in the audit data sequence are used as the left window of each extreme point in the audit data sequence.

5. The visualization method based on audit data according to claim 1 is characterized in that: The process of obtaining the right window of the extreme point includes: The number of window data is preset as T, and the T data on the right side of each extreme point in the audit data sequence are used as the right window of each extreme point in the audit data sequence.

6. A visualization method based on audit data according to claim 1, characterized in that: The second possibility of obtaining each extreme point in the third category cluster as a segmentation point includes: ； In the formula, Represents the second possibility that the jth extreme point in the third category cluster is a segmentation point; Represents the mean of the initial likelihood that all extreme points in the first category cluster are segmentation points; Represents the mean of the initial likelihood that all extreme points in the second category cluster are segmentation points; Represents the initial possibility that the jth extreme point in the third category cluster is a segmentation point; exp() represents an exponential function with a natural constant as the base.

7. The visualization method based on audit data according to claim 1 is characterized in that: The acquiring of segmentation points based on the second possibility includes: A second possibility threshold T2 is preset. If the second possibility that the j-th extreme point in the third category cluster is a segmentation point is greater than or equal to the second possibility threshold T2, the j-th extreme point in the third category cluster is set as a segmentation point to obtain all segmentation points.

8. The visualization method based on audit data according to claim 1 is characterized in that: The acquisition audit data sequence includes: Any dimension of audit data in the database is recorded as target data; in the database, all target data are obtained in chronological order, and all the target data are formed into a sequence, which is recorded as an audit data sequence.

9. A visualization system based on audit data, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a visualization method based on audit data according to any one of claims 1 to 8 is implemented.

Images