Document auditing method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of data auditing, and discloses a receipt auditing method and device, computer equipment and a storage medium. According to the to-be-audited order of the to-be-audited document under multiple auditing regulations, in the process of executing the auditing operation on the to-be-audited document, due to the fact that the target applicant is supported to modify the to-be-audited data having problems in real time, the target applicant can know the abnormal to-be-audited data in time in the auditing process of the target auditing regulations, and the auditing efficiency of the to-be-audited document is improved. And the abnormal information of the to-be-audited data is not known after the audit is finished. And meanwhile, the next auditing action does not need to be continuously executed after each auditing problem is modified, so that the average consumed time of single auditing is shortened.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data auditing, in particular to a bill auditing method and device, a computer device and a storage medium. BACKGROUND

[0002] Bill auditing is a further auditing and confirmation of the accuracy of a bill after the bill is saved. As a core business link in the financial, tax, supply chain and other industries, the efficiency and accuracy of bill auditing directly affect the operating cost and risk control ability of an enterprise.

[0003] In related technologies, if a bill has multiple auditing problems, the applicant needs to modify each auditing problem before the auditing action can continue, resulting in a long average time for a single audit and poor modification real-time performance. SUMMARY

[0004] Therefore, the present application provides a bill auditing method and device, a computer device and a storage medium to solve the problem of a long average time for a single audit and poor modification real-time performance.

[0005] In a first aspect, the present application provides a bill auditing method, which comprises:

[0006] obtaining a to-be-audited order of the to-be-audited bill under multiple auditing regulations;

[0007] obtaining an auditing performance value of the to-be-audited bill of the target applicant under the target auditing regulation of the current item;

[0008] performing an auditing operation on the to-be-audited bill according to the to-be-audited order of the to-be-audited bill under the multiple auditing regulations and the auditing performance value of the to-be-audited bill of the target applicant under the target auditing regulation of the current item, and initiating a modification prompt instruction of the to-be-audited bill to the target applicant multiple times until the to-be-audited bill is audited under the multiple auditing regulations, wherein the modification prompt instruction is used to instruct the target applicant to modify the to-be-audited bill according to the auditing requirements of the target auditing regulation.

[0009] In the process of performing an auditing operation on the to-be-audited bill according to the to-be-audited order of the to-be-audited bill under the multiple auditing regulations, the present embodiment supports the target applicant to modify the to-be-audited data in real time, so that the target applicant can learn about the abnormal to-be-audited data in time during the auditing process under the target auditing regulation, and does not need to wait until the auditing is completed to know the abnormal information of the to-be-audited data. In addition, the present embodiment does not need to wait for each auditing problem to be modified before continuing to perform the next auditing action, thereby reducing the average time length of a single audit.

[0010] In some optional embodiments, the auditing operation is performed on the to-be-audited document according to the to-be-audited order of the to-be-audited document under the plurality of auditing provisions, and the modification prompt instruction of the to-be-audited document is initiated to the target applicant multiple times until the auditing of the to-be-audited document under the plurality of auditing provisions is completed, comprising:

[0011] When the auditing performance value of the to-be-audited document by the target applicant under the current target auditing provision is less than the preset threshold, the modification prompt instruction of the to-be-audited document under the current target auditing provision is initiated to the target applicant, and the auditing operation is performed on the next target auditing provision until the auditing of the to-be-audited document under the plurality of auditing provisions is completed;

[0012] When the auditing performance value of the to-be-audited document by the target applicant under the current target auditing provision is not less than the preset threshold, it is determined that the to-be-audited document meets the auditing requirement under the current target auditing provision, and the auditing operation is performed on the next target auditing provision until the auditing of the to-be-audited document under the plurality of auditing provisions is completed.

[0013] The embodiment compares the auditing performance value of the to-be-audited document by the target applicant under the current target auditing provision with the preset threshold, performs the auditing operation on the to-be-audited document according to the to-be-audited order of the to-be-audited document under the plurality of auditing provisions, which not only ensures efficient auditing of the to-be-audited document, but also ensures that the target applicant can modify the to-be-audited document in real time and reduces the average duration of single auditing.

[0014] In some optional embodiments, the to-be-audited order of the to-be-audited document under the plurality of auditing provisions is obtained, and the method comprises:

[0015] The to-be-audited document of the target applicant under the target auditing provision and a plurality of historical auditing documents of the to-be-audited document are obtained, wherein the target auditing provision is each auditing provision of the plurality of auditing provisions;

[0016] The auditing performance value of the plurality of historical auditing documents by the target applicant under the target auditing provision is obtained;

[0017] Based on a plurality of coordinate points of the auditing performance value of the plurality of historical auditing documents under a preset coordinate system, the auditing distinct value of the plurality of historical auditing documents of the target applicant under the target auditing provision is determined, wherein the horizontal coordinate value of each coordinate point represents the historical auditing order of each historical auditing document, the vertical coordinate value of each coordinate point represents the auditing performance value of each historical auditing document, and the historical auditing order of each historical auditing document is determined by the auditing performance value of the historical auditing document;

[0018] The to-be-audited order of the to-be-audited document under the target auditing provision is determined according to the auditing distinct value of the plurality of historical auditing documents of the target applicant under the target auditing provision.

[0019] According to the audit distinctness value of the multiple historical audit documents of the target applicant under the target audit regulation, the audit order of the to-be-audited document under the target audit regulation is determined to be associated with the audit performance value of the multiple historical audit documents. Finally, the audit order determined by the embodiment under the target audit regulation can flexibly adapt to the audit order of the to-be-audited document of different target applicants under different target audit regulations, and thus is beneficial to prioritizing the to-be-audited document with higher risk, and improves the flexibility and efficiency of the to-be-audited document audit.

[0020] In some optional embodiments, the audit distinctness value of the multiple historical audit documents of the target applicant under the target audit regulation is determined based on multiple coordinate points of the audit performance value of the multiple historical audit documents in a preset coordinate system, and the method comprises the following steps:

[0021] The number of the multiple coordinate points in the preset coordinate system is marked as n;

[0022] n-1 audit performance change line segments are determined from the n coordinate points in the preset coordinate system, and each audit performance change line segment is connected by two adjacent coordinate points;

[0023] An audit performance change curve is formed by the n-1 audit performance change line segments, and a starting endpoint and an ending endpoint are determined from the audit performance change curve;

[0024] A closed figure is constructed in the preset coordinate system according to the audit performance change curve, the starting endpoint and the ending endpoint;

[0025] The total area of the closed figure is calculated;

[0026] The comprehensive change slope of the n-1 audit performance change line segments is calculated, and the comprehensive change slope is calculated by summing the target slope of each audit performance change line segment;

[0027] The audit distinctness value of the multiple historical audit documents of the target applicant under the target audit regulation is calculated according to the comprehensive change slope and the total area of the closed figure.

[0028] The embodiment constructs a closed graph through the coordinate points in the preset coordinate system, calculates the total area of the closed graph, and calculates the comprehensive change slope of the audit performance change curve formed by the plurality of coordinate points, so that the audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation are finally obtained, and the subsequent further accurate audit order of the to-be-audited document under the target audit regulation is facilitated.

[0029] In some optional embodiments, the closed graph is constructed under the preset coordinate system according to the audit performance change curve, the starting endpoint and the ending endpoint, and the closed graph comprises:

[0030] a first perpendicular line segment is drawn from the starting endpoint to a horizontal coordinate axis under the preset coordinate system, and a second perpendicular line segment is drawn from the ending endpoint to a vertical coordinate axis under the preset coordinate system;

[0031] The closed graph formed by the first perpendicular line segment, the second perpendicular line segment, the horizontal coordinate axis and the audit performance change curve is constructed under the preset coordinate system.

[0032] The embodiment constructs the closed graph under the preset coordinate system, and facilitates the further calculation of the audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation.

[0033] In some optional embodiments, the audit performance values of the plurality of historical audit documents of the target applicant under the target audit regulation are obtained, and the method comprises:

[0034] At least one audit feature corresponding to each historical audit document is extracted, and the audit feature comprises: a field integrity audit feature, a format compliance audit feature and a cross-field logic consistency audit feature.

[0035] The at least one audit feature is input into a target audit model for prediction to obtain the audit performance values of the plurality of historical audit documents of the target applicant, wherein the target audit model is a pre-trained neural network model.

[0036] The embodiment trains the at least one audit feature through the target audit model, and facilitates the further accurate obtaining of the audit performance values of the plurality of historical audit documents of the target applicant.

[0037] In some optional embodiments, the to-be-audited order of the to-be-audited document under the target audit regulation is determined according to the audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation, and the method comprises:

[0038] The audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation are sorted in descending order to obtain a historical audit order of the plurality of historical audit documents under the target audit regulation.

[0039] According to the historical auditing sequence of the plurality of historical auditing documents under the target auditing regulation, a to-be-audited sequence of the to-be-audited document is determined.

[0040] According to the above embodiment, the auditing difference values of the plurality of historical auditing documents of the target applicant under the target auditing regulation are sorted in descending order, and the historical auditing document with a higher risk level is sorted in the front. Since the to-be-audited document is of the same type as the historical auditing document, the to-be-audited document with a higher risk level is also sorted in the front. Finally, the to-be-audited document with a higher risk level is audited preferentially.

[0041] In a second aspect, the embodiment provides a document auditing device, and the device comprises:

[0042] An auditing sequence acquisition module is configured to acquire a to-be-audited sequence of the to-be-audited document under a plurality of auditing regulations;

[0043] A current performance acquisition module is configured to acquire an auditing performance value of the target applicant for the to-be-audited document under the current target auditing regulation;

[0044] An auditing document modification module is configured to perform an auditing operation on the to-be-audited document through the to-be-audited sequence of the to-be-audited document under the plurality of auditing regulations according to the auditing performance value of the target applicant for the to-be-audited document under the current target auditing regulation, and to initiate a modification prompt instruction of the to-be-audited document to the target applicant for multiple times until the to-be-audited document is audited under the plurality of auditing regulations, wherein the modification prompt instruction is configured to instruct the target applicant to modify the to-be-audited document according to the auditing requirements of the target auditing regulation.

[0045] In a third aspect, the embodiment provides a computer device, and the computer device comprises:

[0046] A memory and a processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the document auditing method of the first aspect or any of the corresponding embodiments thereof.

[0047] In a fourth aspect, the embodiment provides a computer readable storage medium, and the computer readable storage medium stores computer instructions, and the computer instructions are executed to perform the document auditing method of the first aspect or any of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0049] Figure 1 is a flowchart of a document review sequence determination method according to an embodiment of the present application;

[0050] Figure 2 is a flowchart of another document review sequence determination method according to an embodiment of the present application;

[0051] Figure 3 is a schematic diagram of forming a closed figure based on coordinate points in a preset coordinate system according to an embodiment of the present application;

[0052] Figure 4 is a flowchart of a document review sequence determination method according to an embodiment of the present application;

[0053] Figure 5 is a flowchart of a document review method according to an embodiment of the present application;

[0054] Figure 6 is a structural block diagram of a document review sequence determination device according to an embodiment of the present application;

[0055] Figure 7 is a hardware structure schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0057] According to an embodiment of the present application, a document review sequence determination method embodiment is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a group of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0058] The present embodiment provides a bill auditing method, which can be applied to computer devices such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 1 The flowchart of the bill auditing method according to the present embodiment is shown in FIG. 1, which includes the following steps: Figure 1

[0059] In step S101, the order of the bill to be audited under the multiple auditing regulations is obtained.

[0060] The order of the bill to be audited is the priority order of the bill to be audited.

[0061] In step S102, the auditing performance value of the target applicant to the bill to be audited under the target auditing regulation of the current item is obtained.

[0062] As described above, the multiple auditing regulations include auditing regulation A, auditing regulation B, auditing regulation C, and auditing regulation D, wherein the target auditing regulation can be A, B, C, or D. The target auditing regulation of the current item can be auditing regulation C, and the target auditing regulation of the next item can be auditing regulation D.

[0063] Further, the method for obtaining the auditing performance value of the target applicant to the bill to be audited under the target auditing regulation of the current item is the same as the method for obtaining the auditing performance value of the target applicant to the multiple historical auditing bills under the target auditing regulation, which will not be described herein.

[0064] In step S103, according to the auditing performance value of the target applicant to the bill to be audited under the target auditing regulation of the current item, the auditing operation of the bill to be audited is performed through the order of the bill to be audited under the multiple auditing regulations, and the modification prompt instruction of the bill to be audited is initiated to the target applicant multiple times until the auditing of the bill to be audited under the multiple auditing regulations is completed, wherein the modification prompt instruction is used to instruct the target applicant to modify the bill to be audited according to the auditing requirements of the target auditing regulation.

[0065] In the bill auditing process, if the bill has multiple auditing problems, the applicant needs to modify each auditing problem before the auditing operation can be continued, which leads to a long average time for single auditing, and therefore, the real-time performance of the method for modifying the bill to be audited is poor.

[0066] ​In view of this, the embodiment supports the target applicant to modify the problematic to-be-audited data in real time in the process of performing the auditing operation on the to-be-audited document according to the to-be-audited order of the to-be-audited document under the multiple auditing provisions, so as to ensure that the target applicant can learn about the abnormal to-be-audited data in time in the auditing process under the target auditing provision, and does not have to wait until the auditing is completed to learn about the abnormal information of the to-be-audited data. In addition, the embodiment does not need to wait for each auditing problem to be modified before continuing to perform the next auditing action, thereby reducing the average time length of single auditing.

[0067] In some specific embodiments, the above step S103 includes:

[0068] Step a1, when the auditing performance value of the target applicant to the to-be-audited document under the current target auditing provision is less than the preset threshold value, the modification prompt instruction of the to-be-audited document under the current target auditing provision is initiated to the target applicant, and the auditing operation is performed on the next target auditing provision until the to-be-audited document is completed under the multiple auditing provisions.

[0069] The preset threshold value can be flexibly set according to the actual situation. For example, the preset threshold value is 0.5, the current target auditing provision is C, the next target auditing provision is D, and the auditing performance value of the target applicant to the to-be-audited document under the current target auditing provision C is 0.45, which is less than the preset threshold value 0.5. The modification prompt instruction of the to-be-audited data is initiated to the target applicant, and this way is continued until the to-be-audited data is completed under the multiple auditing provisions.

[0070] Step a2, when the auditing performance value of the target applicant to the to-be-audited document under the current target auditing provision is not less than the preset threshold value, it is determined that the to-be-audited document under the current target auditing provision meets the auditing requirement, and the auditing operation is performed on the next target auditing provision until the to-be-audited document is completed under the multiple auditing provisions.

[0071] On the basis of the above example, the auditing performance value of the target applicant to the to-be-audited document under the current target auditing provision C is 0.56, which is greater than the preset threshold value 0.5, indicating that the current to-be-audited data is not abnormal, and the auditing of the next to-be-audited document is continued until the to-be-audited document is completed under the multiple auditing provisions.

[0072] In the embodiment, a document auditing method is provided, which can be used for computer equipment such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 2is a flowchart of a document review sequence determination method according to an embodiment of the present application, as shown in Figure 2 The flowchart includes the following steps:

[0073] In step S201, a target applicant's to-be-reviewed document under a target review regulation and a plurality of historical review documents of the to-be-reviewed document are obtained, wherein the target review regulation is each review regulation of a plurality of review regulations.

[0074] The target applicant can be any applicant applying for a to-be-reviewed document, for example, the target applicant includes but is not limited to an applicant applying for an invoice, an account opening, a registered account, and the like. The plurality of review regulations include a review regulation A, a review regulation B, a review regulation C, and a review regulation D, wherein the target review regulation can be A or B or C or D.

[0075] The to-be-reviewed document is a document requested to be reviewed by an applicant. The historical review document is a plurality of historical review documents of the to-be-reviewed document completed by the target applicant in the past. Therefore, the to-be-reviewed document and the historical review document are of the same type. The type of the to-be-reviewed document and the historical review document includes but is not limited to a historical invoice, a historical registered account, a historical registered housing, a historical reimbursement, and the like.

[0076] In a specific example, obtaining the target applicant's to-be-reviewed document under the target review regulation and the plurality of historical review documents of the to-be-reviewed document includes:

[0077] In step b1, a request instruction package of the to-be-reviewed document initiated by the target applicant is received, and the request instruction package is loaded with identification information of the target applicant.

[0078] In step b2, according to the identification information of the target applicant, the plurality of historical review documents of the to-be-reviewed document are obtained.

[0079] In step S202, the target applicant's review performance value for the plurality of historical review documents under the target review regulation is obtained.

[0080] The review performance value is the target applicant's different review performance for field integrity, format compliance, cross-field logic consistency, and the like under the target review regulation.

[0081] The embodiment can preferentially use a pre-trained target review model to further obtain the target applicant's review performance value for the plurality of historical review documents under the target review regulation, thereby achieving the purpose of accurately extracting the review performance value of the plurality of historical review documents.

[0082] In step S203, based on the plurality of coordinate points of the audit performance values of the plurality of historical audit documents in the preset coordinate system, the audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation are determined, wherein the horizontal coordinate value of each coordinate point represents the historical audit order of each historical audit document, the vertical coordinate value of each coordinate point represents the audit performance value of each historical audit document, and the historical audit order of each historical audit document is determined by the audit performance value of the historical audit document.

[0083] In a specific example, the audit performance values of the plurality of historical audit documents of the target applicant under the target audit regulation are sorted in descending order to obtain the historical audit orders of the plurality of historical audit documents under the target audit regulation; and the historical audit order of each historical audit document is sorted in a preset coordinate system in ascending order.

[0084] The greater the audit performance value of the plurality of historical audit documents of the target applicant under the target audit regulation, the more unstable the historical performance of the target applicant on the documents, and the higher the sorting of the historical audit documents. The historical audit order of the historical audit document corresponding to the audit performance value of the historical audit document sorted in the front in the preset coordinate system is sorted in the front, which means that the historical audit document can be audited first.

[0085] Specifically, the preset coordinate system can be a rectangular coordinate system. In the rectangular coordinate system, the horizontal coordinate value of each coordinate point represents the historical audit order of each historical audit document. The historical audit order of each historical audit document is labeled in ascending order on the X-axis of the rectangular coordinate system, and the audit performance value corresponding to each label is taken as the parameter value of the Y-axis. The audit performance value corresponding to each label is marked in the form of a coordinate point in the rectangular coordinate system, and a plurality of coordinate points are marked, and the number of the plurality of coordinate points is n.

[0086] Further, the audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation are determined based on the n coordinate points of the audit performance values of the plurality of historical audit documents in the preset coordinate system.

[0087] In step S204, the audit order of the to-be-audited document under the target audit regulation is determined according to the audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation.

[0088] In a specific example, the audit order of the plurality of historical audit documents under the target audit regulation is determined according to the audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation, including:

[0089] Step c1, the audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation are sorted in descending order, and the audit order of the to-be-audited document under the target audit regulation is obtained.

[0090] Step c2, the audit order of the to-be-audited document is determined according to the historical audit order of the plurality of historical audit documents under the target audit regulation.

[0091] For example, the audit difference value of the historical invoicing document of the target applicant 1 under the target audit regulation A is 0.33, the audit difference value of the historical registration document of the target applicant 1 under the target audit regulation A is 0.55, and the audit difference value of the historical reimbursement document of the target applicant 1 under the target audit regulation A is 0.57.

[0092] For example, the audit difference values 0.57, 0.55, 0.33 of the plurality of historical audit documents of the target applicant 1 under the target audit regulation A are sorted in descending order, and the audit order of the plurality of historical audit documents under the target audit regulation A is determined as follows: the audit order of the historical reimbursement document is first, the audit order of the historical registration document is second, and the audit order of the historical invoicing document is third.

[0093] Since the historical audit document is a historical audit document of the to-be-audited document, the type of the historical audit document is the same as the type of the to-be-audited document. Based on the above example, when the type of the to-be-audited document is a reimbursement document, the audit order of the to-be-audited document is first; when the type of the to-be-audited document is a registration document, the audit order of the to-be-audited document is second; and when the type of the to-be-audited document is an invoicing document, the audit order of the to-be-audited document is third.

[0094] The greater the audit difference value, the greater the fluctuation of the target applicant's performance on the historical audit document under the target regulation, which also means that the risk of the to-be-audited document is greater. Therefore, the audit difference values of the plurality of historical audit documents of the target applicant under the target audit regulation are sorted in descending order, the historical audit document with a higher risk level is sorted in front, and since the to-be-audited document and the historical audit document are of the same type, the to-be-audited document with a higher risk level is also sorted in front, which is finally beneficial to preferentially auditing the to-be-audited document with a higher risk.

[0095] In summary, since the audit distinct values of the plurality of historical audit documents of the target applicant under the target audit regulation are associated with the audit performance values of the plurality of historical audit documents, the audit order of the to-be-audited document under the target audit regulation is determined according to the audit distinct values of the plurality of historical audit documents of the target applicant under the target audit regulation, and is associated with the audit performance values of the plurality of historical audit documents. Finally, the to-be-audited order determined by the embodiment under the target audit regulation can flexibly adapt to the to-be-audited order of the to-be-audited document of different target applicants under each audit regulation by considering the audit performance of the plurality of historical audit documents of the target applicant under the target audit regulation, thereby facilitating the priority audit of the to-be-audited document with higher risk and improving the flexibility and efficiency of the to-be-audited document audit.

[0096] In the embodiment, a document audit order determination method is provided, which can be used for computer equipment such as mobile phones, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 3 is a flowchart of the document audit order determination method according to the embodiment of the application, as shown in Figure 3 S203, the audit distinct values of the plurality of historical audit documents of the target applicant under the target audit regulation are determined based on the plurality of coordinate points of the audit performance values of the plurality of historical audit documents in the preset coordinate system, comprising:

[0097] S2031, the number of the plurality of coordinate points in the preset coordinate system is marked as n.

[0098] S2032, n-1 audit performance change line segments are determined from the n coordinate points in the preset coordinate system, and each audit performance change line segment is connected by two adjacent coordinate points.

[0099] As shown in Figure 4 , the preset coordinate system is a rectangular coordinate system, n coordinate points are marked in the rectangular coordinate system, and n-1 audit performance change line segments are determined, and the audit performance change line segment OC is connected by two adjacent coordinate points.

[0100] S2033, the audit performance change curve is formed by the n-1 audit performance change line segments, and the starting endpoint and the ending endpoint are determined from the audit performance change curve.

[0101] In Figure 4 , the audit performance change curve L is formed by the n-1 audit change line segments, and the starting endpoint E and the ending endpoint N are determined from the audit performance change curve L.

[0102] S2034, the closed figure is constructed in the preset coordinate system according to the audit performance change curve, the starting endpoint and the ending endpoint.

[0103] In a specific example, the step S2034 of constructing the closed figure in the preset coordinate system according to the audit performance change curve, the starting endpoint and the ending endpoint comprises:

[0104] The step d1 comprises drawing a first perpendicular segment from the starting endpoint to a horizontal coordinate axis in the preset coordinate system, and drawing a second perpendicular segment from the ending endpoint to a vertical coordinate axis in the preset coordinate system.

[0105] In the specific example, the first perpendicular segment m1 is drawn from the starting endpoint to a horizontal coordinate axis (X-axis) in a rectangular coordinate system, and the second perpendicular segment m2 is drawn from the ending endpoint to a vertical coordinate axis (Y-axis) in the rectangular coordinate system. Figure 4 The step d2 comprises constructing, in the preset coordinate system, a closed figure formed by the first perpendicular segment, the second perpendicular segment, the horizontal coordinate axis and the audit performance change curve.

[0106] In the specific example, the first perpendicular segment m1, the second perpendicular segment m2, the horizontal coordinate axis (X-axis), the vertical coordinate axis (Y-axis) and the audit performance change curve form a closed figure M in the rectangular coordinate system.

[0107] Figure 4 The step S2035 comprises calculating a total area of the closed figure.

[0108] The total area of the closed figure is determined by the shape of the closed figure. For example, when the closed figure is a trapezoid, the total area of the closed trapezoid is calculated according to the calculation formula of the area of the trapezoid; when the closed figure is a rectangle, the total area of the rectangle is calculated according to the calculation formula of the area of the rectangle; when the closed figure can be divided into multiple regular figures, the total sum of each regular figure is calculated.

[0109] The step S2036 comprises calculating a comprehensive change slope of the n-1 audit performance change segments, and the comprehensive change slope is calculated by summing up the target slopes of each audit performance change segment.

[0110] For example, in the specific example, the target slope of the audit change segment OC is represented by OC k .

[0111] For example, in the specific example, the target slope of the audit change segment OC is represented by OC k . Figure 4

[0112] In the specific example, the target slope of the audit change segment OC is represented by OC k . The sum of the target slopes of the n-1 audit performance change segments is calculated to obtain the comprehensive change slope Slcoy of the n-1 audit performance change segments.

[0113] The sum of the target slopes of the n-1 audit performance change segments is calculated to obtain the comprehensive change slope Slcoy of the n-1 audit performance change segments.

[0114] The sum of the target slopes of the n-1 audit performance change segments is calculated to obtain the comprehensive change slope Slcoy of the n-1 audit performance change segments.Step S2037, according to the comprehensive change slope and the total area of the closed figure, the audit difference value of the target applicant under the target audit regulation is calculated.

[0115] The comprehensive change slope is denoted by SICOY, and the total area of the closed figure is denoted by HKBm. The audit difference value of the target applicant under the target audit regulation is calculated by the following formula:

[0116]

[0117] In the embodiment, the audit difference value of the target applicant under the target audit regulation is determined by the above-mentioned manner, which is beneficial to further accurately and flexibly determine the to-be-audited order of the to-be-audited document under the target audit regulation, and expose the to-be-audited document with higher risk in advance, so as to finally achieve the priority audit of the to-be-audited document with higher risk.

[0118] In some specific embodiments, as shown in Figure 5 The step S202 of obtaining the audit performance value of the target applicant under the target audit regulation includes:

[0119] Step S2021, at least one audit feature corresponding to each historical audit document is extracted, and the audit feature includes: field integrity audit feature, format compliance audit feature, and cross-field logic consistency audit feature.

[0120] Step S2022, at least one audit feature is input into the target audit model for prediction to obtain the audit performance value of the target applicant under the target audit regulation, wherein the target audit model is a pre-trained neural network model.

[0121] For example, the target applicant 1 under the target audit regulation A has multiple historical audit documents, including historical billing document 11, historical billing document 12, historical registration document 21, and historical reimbursement document 31. The historical audit documents in this embodiment are pre-processed historical audit documents.

[0122] In a specific example, step S2022, the field integrity audit feature corresponding to each historical audit document is extracted, including:

[0123] Step e1, the mandatory field attribute list of each historical audit document is obtained, and the mandatory field attribute list includes a plurality of mandatory field attributes.

[0124] For example, for a historical billing document, the mandatory field attribute list of the historical billing document is obtained, and the mandatory field attribute list includes but is not limited to: invoice code, billing date, amount, and buyer name.

[0125] Step e2, extract the Boolean vector of each mandatory field attribute in the mandatory field attribute list of each historical audit document.

[0126] For example, for each historical audit document, if there is a mandatory field attribute, the field is marked as 1, otherwise, it is marked as 0, and then a Boolean vector is generated.

[0127] Step e3, encode the Boolean vector of each mandatory field attribute in the mandatory field attribute list of each historical audit document to obtain the field encoding result of the historical audit document.

[0128] When the historical audit document is a historical billing document, the historical billing document is encoded by the One-Hot encoding network or the Embedding encoding network, and the encoding result obtained is: for example, the historical billing document = (1, 0, 0). When the historical audit document is a historical reimbursement document, the historical reimbursement document = (0, 1, 0). Therefore, by encoding each historical audit document, the embodiment can solve the problem of differences in mandatory fields of different types of documents.

[0129] Step e4, according to the business rules, assign weights to the plurality of mandatory field attributes, and obtain the field integrity audit features corresponding to each historical audit document.

[0130] When the historical audit document is a historical billing document, the mandatory field attribute is a billing code, and the weight of the "billing code" is 10. The mandatory field attribute is a billing address, and the weight of the "billing address" is 5. When the mandatory field attribute is missing, the influence degree of the optional field attribute can be calculated according to the weight, and the influence degree is used for audit result scoring.

[0131] In another specific example, step S2022, extract the format compliance audit features corresponding to each historical audit document, including:

[0132] Step f1, identify a plurality of text field attributes of each historical audit document.

[0133] The plurality of text attributes includes but is not limited to date, mailbox, code, etc. In the specific identification of the plurality of text field attributes, the plurality of text field attributes can be obtained by regular matching.

[0134] For example, regular expressions such as date format ^\d{4}-\d{2}-\d{2}$, email format ^[\w.-]+@[\w.-]+\.\w+$, etc. are written according to the format rule; regular matching is performed on the field value, and matching is successful = 1, and failure = 0, and then the format compliance text features are generated.

[0135] For example, the field value "2025 / 04 / 22" matches the date regular expression fails, and the match fails = 0; "2025-04-22" matches successfully, and the match fails = 1.

[0136] Step f2, define the label of each text field attribute of each historical audit document.

[0137] For example, "date" = 01, "mailbox" = 02, "invoice code" = 03.

[0138] Step f3, encode the label of each text field attribute of each historical audit document to obtain the label encoding result of the historical audit document.

[0139] By using a One-Hot encoding network or an Embedding encoding network, the label of each text field attribute of each historical audit document is converted into a vector, thereby solving the difference in cross-field format rules.

[0140] Step f4, according to the label encoding result of each historical audit document, determine whether the current data amount of each historical audit document is equal to the preset data amount.

[0141] Step f5, mark the historical audit document whose current data amount is not equal to the preset data amount as abnormal data;

[0142] Step f6, the historical audit document whose current data amount is equal to the preset data amount is taken as the format compliance audit feature corresponding to each historical audit document.

[0143] For example, when the historical audit document is a historical invoicing document, the preset data amount is 12 characters, and the preset data amount can be flexibly set according to the actual situation. If the current data amount of the historical invoicing document is not equal to 12 characters, the historical invoicing document is marked as abnormal data.

[0144] In another specific example, step S2012, extracting the format compliance audit feature corresponding to each historical audit document further includes:

[0145] Step g1, identify a plurality of numerical field attributes of each historical audit document, the plurality of numerical field attributes including: integer field attributes and decimal field attributes.

[0146] Step g2, according to the decimal field attribute of each historical audit document, determine whether the number of digits after the decimal point in the decimal field meets the requirements.

[0147] Step g3, when the number of digits after the decimal point of each historical audit document does not meet the requirements, mark the historical audit document as a first vector;

[0148] Step g4, when the number of digits after the decimal point of each historical audit document meets the requirements, mark the historical audit document as the second vector;

[0149] The first vector is represented by 1, and the second vector is represented by 0. For example, judging the decimal digit compliance, whether the number of digits after the decimal point meets the requirements, when the number of digits after the decimal point meets the requirements, mark 0, otherwise, mark 1.

[0150] Step g5, detecting whether there are abnormal symbols in the multiple numerical field attributes of each historical audit document;

[0151] Step g6, when there are abnormal symbols in the multiple numerical field attributes of each historical audit document, mark the historical audit document as the first vector;

[0152] Step g7, when there are no abnormal symbols in the multiple numerical field attributes of each historical audit document, mark the historical audit document as the second vector;

[0153] For example, when the historical audit document is a historical billing document, when the historical billing document appears “￥” “$” and other non-numeric characters, mark 1, indicating that there are illegal symbols, otherwise, mark 0.

[0154] In another specific example, step S2012, extracting the cross-field logical consistency audit features corresponding to each historical audit document, including:

[0155] Step h1, obtaining multiple numerical fields of each historical audit document;

[0156] Step h2, determining a target numerical field and an associated numerical field of the target numerical field from the multiple numerical fields;

[0157] Step h3, calculating the numerical difference or numerical ratio between the target numerical field and the associated numerical field;

[0158] For example, the historical audit document is a historical billing document, the target numerical field is the total amount, and the sub-item amount is the associated numerical field. The numerical difference between the two is represented as total amount-sub-item amount. When the target numerical field is tax amount and the associated numerical field is amount, the numerical ratio between the two is represented as “tax amount / amount”.

[0159] Step h4, according to whether the numerical difference or numerical ratio between the target numerical field and the associated numerical field meets the preset requirements;

[0160] Step h5, if not, mark the compliance between the target numerical field and the associated numerical field as the first vector.

[0161] Step h6, if yes, mark the compliance between the target value field and the associated value field as the second vector, and perform cross-value field extreme value checking on the target value field to obtain the cross-value field logical consistency audit feature corresponding to each historical audit document;

[0162] For example, the first vector is 1 and the second vector is 0. If the value difference between the target value field and the associated value field is equal to 0, the compliance between the target value field and the associated value field is marked as 0, otherwise, it is marked as 1. If the value ratio between the target value field and the associated value field is within the allowed preset error range, and the value ratio is less than or equal to ≤0.1%, the compliance between the target value field and the associated value field is marked as 0, otherwise, it is marked as 1.

[0163] For example, the total amount of the purchase order is 1000 yuan, and the item sum is 999 yuan. The difference is 1 yuan. If the allowed error is 5 yuan, it is marked as 0, indicating that the difference between the total amount and the item sum is compliant.

[0164] Further, when the value difference or value ratio between the target value field and the associated value field meets the preset requirement, cross-value field extreme value checking is performed on the target value field.

[0165] The target value field is identified to obtain the cross-value field extreme value in the target value field, and then the value of the target value field is further checked for compliance in combination with the cross-value field extreme value. The compliance is marked as the second vector 0, and then the cross-value field logical consistency audit feature corresponding to each historical audit document is obtained. Otherwise, it is marked as the first vector 1, indicating that the value in the target value field exceeds the cross-value field extreme value.

[0166] For example, when the historical audit document is a historical billing document, when the current unit price value is less than or equal to the historical maximum unit price value, it indicates that the cross-value field extreme value checking result of the target value field meets the requirement.

[0167] In another specific example, step S2012, the cross-field logical consistency audit feature corresponding to each historical audit document is extracted, including:

[0168] Step i1, obtaining a plurality of time fields of each historical audit document.

[0169] Step i2, calculating the time difference between each target time in each historical audit document and the preset time;

[0170] Step i3, determining whether the time difference is less than or equal to the preset difference;

[0171] Step i4, if no, determining that the time of each historical audit document is not compliant, and marking it as the first vector.

[0172] Step i5, if yes, determine the time compliance of each historical audit document, and mark as the second vector.

[0173] For example, if the delivery date in the historical audit document is less than or equal to the signing date, mark it as the second vector, and determine that the historical audit document is compliant, otherwise, mark it as the first vector, and determine that the historical audit document is not compliant.

[0174] In another specific example, step S2012, extract the cross-field logical consistency audit features corresponding to each historical audit document, including:

[0175] Step j1, extract a plurality of text field features of each historical audit document;

[0176] Step j2, determine the cross-field logical consistency audit features corresponding to each historical audit document according to the text similarity of each text field feature of each historical audit document.

[0177] Wherein, the text similarity of each text field feature is determined by the text similarity between the text field feature and another text field feature.

[0178] Text field features with a text similarity greater than or equal to a preset threshold are taken as cross-field logical consistency audit features of each text field feature;

[0179] Step j3, discard the text field features with a text similarity less than the preset threshold.

[0180] For example, if the similarity between "Contractor A name" and "Supplier name" is greater than or equal to a preset threshold (90%), it means that the two text features are compliant, otherwise, they are not compliant.

[0181] The target audit model in this embodiment is a pre-trained neural network model, and each historical audit document is a historical audit document collected for each audit regulation, therefore, each audit regulation corresponds to an independently trained deep learning model, and each deep learning model is trained independently to be the corresponding target audit model.

[0182] In a specific training process, the field integrity audit features, the format compliance audit features, and the cross-field logical consistency audit features of the training samples are used to build a deep learning model. The built deep learning model is trained, and in this process, an audit performance value is assigned to each audit feature corresponding to each training sample. The audit performance value is set to a range of 1 to 5. It is important to note that the larger the audit performance value, the more it means that the audit standard is met. Then, the audit features corresponding to the training samples are divided into a training set, a validation set, and a test set according to a specific ratio. The specific division ratio is 60%, 20%, and 20%. Such a division method helps to comprehensively and scientifically train, validate, and finally test the performance of the model, ensuring that the target audit model can accurately evaluate whether the audit standard is met according to the input audit features. After the completion of the data set division, the training set is first used to repeatedly train the target audit model, so that the target audit model learns and masters the internal correlation between the audit features and the audit performance values corresponding to each historical audit document. In the training process, the validation set is used to timely validate the performance of the target audit model in the training stage. According to the validation result, the parameters of the target audit model are adjusted in time, and the structure of the target audit model is optimized, so that it develops in a more accurate and stable direction. When the performance of the target audit model on the training set and the validation set reaches the expected effect, the test set is used to finally test the performance of the target audit model, to test the generalization ability and accuracy of the target audit model on the documents not involved in the training. Finally, a target audit model for auditing field integrity, format compliance, and cross-field logic is successfully built.

[0183] In this embodiment, a document audit order determination device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware or a combination of software and hardware is also possible and contemplated.

[0184] This embodiment provides a document audit order determination device, as shown in Figure 6 , comprising:

[0185] An audit order acquisition module 601 is configured to acquire the audit order of the to-be-audited document under a plurality of audit regulations.

[0186] A current performance acquisition module 602 is configured to acquire an audit performance value of the to-be-audited document by the target applicant under the current target audit regulation.

[0187] The auditing document modification module 603 is configured to perform an auditing operation on the to-be-audited document under the target auditing provision of the current item according to the auditing performance value of the target applicant on the to-be-audited document under the target auditing provision of the current item, and repeatedly initiate a modification prompt instruction of the to-be-audited document to the target applicant until the to-be-audited document is audited under the multiple auditing provisions. The modification prompt instruction is used to instruct the target applicant to modify the to-be-audited document according to the auditing requirement of the target auditing provision.

[0188] In some optional embodiments, the auditing document modification module 603 comprises:

[0189] The auditing document modification submodule is configured to initiate a modification prompt instruction of the to-be-audited document under the target auditing provision of the current item to the target applicant when the auditing performance value of the target applicant on the to-be-audited document under the target auditing provision of the current item is less than the preset threshold, and perform an auditing operation on the target auditing provision of the next item until the to-be-audited document is audited under the multiple auditing provisions.

[0190] The auditing document operation submodule is configured to determine that the to-be-audited document meets the auditing requirement under the target auditing provision of the current item when the auditing performance value of the target applicant on the to-be-audited document under the target auditing provision of the current item is not less than the preset threshold, and perform an auditing operation on the target auditing provision of the next item until the to-be-audited document is audited under the multiple auditing provisions.

[0191] In some optional embodiments, the auditing sequence acquisition module 601 comprises:

[0192] The auditing document acquisition submodule is configured to acquire the to-be-audited document of the target applicant under the target auditing provision and multiple historical auditing documents of the to-be-audited document, wherein the target auditing provision is each auditing provision of the multiple auditing provisions.

[0193] The auditing performance acquisition submodule is configured to acquire the auditing performance value of the target applicant on the multiple historical auditing documents under the target auditing provision.

[0194] The auditing difference determination submodule is configured to determine the auditing difference value of the multiple historical auditing documents of the target applicant under the target auditing provision based on multiple coordinate points of the auditing performance value of the multiple historical auditing documents in a preset coordinate system, wherein the horizontal coordinate value of each coordinate point represents the historical auditing sequence of each historical auditing document, the vertical coordinate value of each coordinate point represents the auditing performance value of each historical auditing document, and the historical auditing sequence of each historical auditing document is determined by the auditing performance value of the historical auditing document.

[0195] The audit order determination sub-module is configured to determine an audit order of the to-be-audited document under the target audit regulation according to the audit difference values of the historical audit documents of the target applicant under the target audit regulation.

[0196] In some optional embodiments, the audit difference determination unit comprises:

[0197] The number marking unit is configured to mark the number of the coordinate points in the preset coordinate system as n.

[0198] The line segment determination unit is configured to determine n-1 audit performance change line segments from the n coordinate points in the preset coordinate system, each audit performance change line segment being formed by connecting two adjacent coordinate points.

[0199] The endpoint determination unit is configured to form an audit performance change curve through the n-1 audit performance change line segments, and determine a starting endpoint and an ending endpoint from the audit performance change curve.

[0200] The graph determination unit is configured to construct a closed graph in the preset coordinate system according to the audit performance change curve, the starting endpoint and the ending endpoint.

[0201] The area calculation unit is configured to calculate a total area of the closed graph.

[0202] The slope calculation unit is configured to calculate a comprehensive change slope of the n-1 audit performance change line segments, the comprehensive change slope being calculated by summing up the target slopes of each audit performance change line segment.

[0203] The difference determination unit is configured to calculate the audit difference values of the historical audit documents of the target applicant under the target audit regulation according to the comprehensive change slope and the total area of the closed graph.

[0204] In some optional embodiments, the graph determination unit comprises:

[0205] The first determination sub-unit is configured to make a first perpendicular line segment from the starting endpoint to a horizontal coordinate axis in the preset coordinate system, and make a second perpendicular line segment from the ending endpoint to a vertical coordinate axis in the preset coordinate system.

[0206] The second determination sub-unit is configured to construct a closed graph formed by the first perpendicular line segment, the second perpendicular line segment, the horizontal coordinate axis and the audit performance change curve in the preset coordinate system.

[0207] In some optional embodiments, the audit performance obtaining sub-module comprises:

[0208] The feature extraction unit is configured to extract at least one audit feature corresponding to each historical audit document, the audit feature comprising: a field integrity audit feature, a format compliance audit feature and a cross-field logic consistency audit feature.

[0209] The feature training unit is used to input at least one audit feature into the target audit model for prediction to obtain the audit performance values ​​of multiple historical audit documents of the target applicant, wherein the target audit model is a pre-trained neural network model.

[0210] In some optional implementations, the review order determination submodule includes:

[0211] The first determining unit is configured to sequentially sort the audit difference values ​​of the target applicant's multiple historical audit documents under the target audit regulations in descending order to obtain a historical audit order of the multiple historical audit documents under the target audit regulations;

[0212] The second determining unit is used to determine the to-be-approved order of the documents to be approved according to the historical approval order of the plurality of historically approved documents under the target approval regulation.

[0213] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0214] The document review device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0215] An embodiment of the present invention further provides a computer device having the above-mentioned document review device.

[0216] See also Figure 7 , Figure 7 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7The processor 10 is taken as an example.

[0217] The processor 10 can be a central processor, a network processor or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic gate array, a generic array logic or any combination thereof.

[0218] The memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0219] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system and application programs required by at least one function. The data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some optional embodiments, the memory 20 can optionally include a memory remotely arranged with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0220] The memory 20 can include a volatile memory, such as a random access memory; the memory can also include a non-volatile memory, such as a flash memory, a hard disk or a solid state disk; the memory 20 can further include a combination of the above kinds of memories.

[0221] The computer device further includes a communication interface 30 for communication of the computer device with other devices or communication networks.

[0222] The embodiments of the present application further provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or be implemented as computer codes stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded through a network and stored in a local storage medium, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component that can store or receive software or computer codes, when the software or computer codes are accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0223] Although the embodiments of the present application are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A document review method, characterized in that: The method comprises: Obtain the order in which documents to be reviewed are reviewed under multiple review regulations; Obtain the target applicant's audit performance value for the document to be audited under the target audit regulations of the current item; According to the audit performance value of the target applicant for the document to be audited under the target audit regulations of the current item, the audit operation is performed on the document to be audited through the audit order of the document to be audited under multiple audit regulations, and modification prompt instructions for the document to be audited are initiated to the target applicant multiple times until the document to be audited completes the audit under the multiple audit regulations, wherein the modification prompt instruction is used to instruct the target applicant to modify the document to be audited in accordance with the audit requirements of the target audit regulations.

2. The document review method according to claim 1, characterized in that: Performing an audit operation on the document to be audited according to the order of the document to be audited under the multiple audit regulations, and sending a modification prompt instruction of the document to be audited to the target applicant multiple times until the document to be audited completes the audit under the multiple audit regulations, including: When the audit performance value of the target applicant for the document to be audited under the current target audit provision is less than a preset threshold, a modification prompt instruction for the document to be audited under the current target audit provision is initiated to the target applicant, and an audit operation is performed on the next target audit provision until the document to be audited is audited under the multiple audit provisions; When the audit performance value of the target applicant for the document to be audited under the target audit regulations of the current item is not less than the preset threshold, it is determined that the document to be audited meets the audit requirements under the target audit regulations of the current item, and the audit operation is performed on the target audit regulations of the next item until the document to be audited completes the audit under the multiple audit fixes.

3. The document review method according to claim 1, characterized in that: Obtain the order in which the documents to be reviewed are reviewed under multiple review regulations, including: Obtaining a target applicant's pending audit documents under a target audit provision and multiple historical audit documents of the pending audit documents, wherein the target audit provision is each audit provision of the multiple audit provisions; Obtain the audit performance values ​​of the target applicant for multiple historical audit documents under the target audit regulations; Determining, based on the audit performance values ​​of the multiple historical audit documents at multiple coordinate points in a preset coordinate system, audit difference values ​​of the multiple historical audit documents of the target applicant under the target audit regulations, wherein the abscissa value of each coordinate point represents the historical audit order of each historical audit document, and the ordinate value of each coordinate point represents the audit performance value of each historical audit document, and the historical audit order of each historical audit document is determined by the audit performance value of the historical audit document; The order of the documents to be reviewed under the target audit regulations is determined according to the audit difference values ​​of multiple historical audit documents of the target applicant under the target audit regulations.

4. The method according to claim 3, characterized in that Based on the audit performance values ​​of the multiple historical audit documents at multiple coordinate points in a preset coordinate system, determining the audit difference values ​​of the multiple historical audit documents of the target applicant under the target audit regulations, including: Mark the number of the plurality of coordinate points in the preset coordinate system as n; Determine n-1 audit performance change line segments from n coordinate points in a preset coordinate system, where each audit performance change line segment is formed by connecting two adjacent coordinate points; Constructing an audit performance change curve through n-1 audit performance change line segments, and determining a starting endpoint and an ending endpoint from the audit performance change curve; Constructing a closed graph in the preset coordinate system according to the audit performance change curve, the starting endpoint and the ending endpoint; Calculating the total area of ​​the closed figure; Calculating the comprehensive change slope of n-1 audit performance change line segments, wherein the comprehensive change slope is calculated by summing the target slope of each audit performance change line segment; According to the comprehensive change slope and the total area of ​​the closed figure, the audit difference values ​​of multiple historical audit documents of the target applicant under the target audit regulations are calculated.

5. The method according to claim 4, characterized in that Constructing a closed graph in the preset coordinate system according to the audit performance change curve, the starting endpoint, and the ending endpoint includes: Draw a first perpendicular line segment from the starting end point to the horizontal coordinate axis of the preset coordinate system, and draw a second perpendicular line segment from the ending end point to the vertical coordinate axis of the preset coordinate system; In the preset coordinate system, a closed figure formed by the first vertical line segment, the second vertical line segment, the horizontal coordinate axis and the audit performance change curve is constructed.

6. The method according to claim 3, characterized in that Obtain the audit performance values ​​of multiple historical audit documents of the target applicant under the target audit regulations, including: Extract at least one audit feature corresponding to each historical audit document, wherein the audit features include: field integrity audit feature, format compliance audit feature, and cross-field logical consistency audit feature; The at least one audit feature is input into the target audit model for prediction to obtain the audit performance values ​​of multiple historical audit documents of the target applicant, wherein the target audit model is a pre-trained neural network model.

7. The method according to claim 3, characterized in that Determining the order of the documents to be reviewed under the target audit regulations according to the audit difference values ​​of multiple historical audit documents of the target applicant under the target audit regulations includes: Sort the audit difference values ​​of multiple historical audit documents of the target applicant under the target audit regulations in descending order to obtain the historical audit order of the multiple historical audit documents under the target audit regulations; The order of the documents to be reviewed is determined according to the order of the historical reviews of the multiple historical reviews under the target review regulations.

8. A document review device, characterized in that: The device comprises: The review order acquisition module is used to obtain the review order of documents to be reviewed under multiple review regulations; The current performance acquisition module is used to obtain the audit performance value of the target applicant on the document to be audited under the target audit regulations of the current item; An audit document modification module is used to perform an audit operation on the document to be audited according to the audit performance value of the target applicant on the document to be audited under the target audit regulations of the current item, and through the order of the document to be audited under multiple audit regulations, and to initiate modification prompt instructions of the document to be audited to the target applicant multiple times until the document to be audited completes the audit under the multiple audit regulations, wherein the modification prompt instruction is used to instruct the target applicant to modify the document to be audited in accordance with the audit requirements of the target audit regulations.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions, wherein the computer instructions are used to execute the document review method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the document review method according to any one of claims 1 to 7.

Images