CN115292346A

CN115292346A - Automatic data checking method and device based on artificial intelligence and computer equipment

Info

Publication number: CN115292346A
Application number: CN202210939569.9A
Authority: CN
Inventors: 贾林
Original assignee: Shenzhen Qianhai Huanrong Lianyi Information Technology Service Co Ltd
Current assignee: Shenzhen Qianhai Huanrong Lianyi Information Technology Service Co Ltd
Priority date: 2022-08-05
Filing date: 2022-08-05
Publication date: 2022-11-04

Abstract

The application relates to an artificial intelligence technology, and provides an artificial intelligence-based data automatic checking method, an artificial intelligence-based data automatic checking device and computer equipment, wherein the method comprises the steps of checking information of each access item in an acquired access checking item set based on an access checking strategy to obtain an access checking result set; performing content extraction and content verification on the acquired service development item information in the service development verification item set based on the service development verification strategy to obtain a service development verification result set; determining corresponding risk grade values according to the result proportion of the centralized checking of the admission checking results and the result proportion of the centralized checking of the service development checking results; and outputting the risk level value, the admission checking result set and the service development checking result set to a receiving end. The automatic extraction and automatic check of all the check item information included in the check entry item set and the service development check item set are realized, all the check item information does not need to be manually checked, and the information check efficiency is improved.

Description

Data automatic checking method and device based on artificial intelligence and computer equipment

Technical Field

The present application relates to the field of artificial intelligence natural language processing technologies, and in particular, to an artificial intelligence-based method and apparatus for automatically checking data, a computer device, and a storage medium.

Background

At present, data verification is widely applied in many fields, for example, after data uploaded by a user is verified in the financial field, the data can be determined by combining with a data verification result. Currently, when data uploaded by a user (such as a user picture, an invoice and the like) is audited, a system generally performs manual audit after automatically extracting data contents, which causes low data auditing efficiency.

Disclosure of Invention

The embodiment of the application provides an automatic data checking method and device, computer equipment and a storage medium based on artificial intelligence, and aims to solve the problem that in the prior art, the system automatically extracts data contents and then performs manual checking to check the data uploaded by a user, so that the data checking efficiency is low.

In a first aspect, an embodiment of the present application provides an automatic data checking method based on artificial intelligence, which includes:

obtaining an admission checking item set;

checking the information of each admission item in the admission checking item set based on a preset admission checking strategy to obtain an admission checking result set;

acquiring a business development checking item set, wherein the business development checking item set at least comprises a trade contract checking item set;

performing content extraction and content verification on the information of each service development item in the service development verification item set based on a preset service development verification strategy to obtain a service development verification result set;

determining a risk grade value corresponding to the admission checking item set and the service development checking item set according to the result proportion of the centralized checking of the admission checking results and the result proportion of the centralized checking of the service development checking results;

and outputting the risk level value, the admission checking result set and the service development checking result set to a receiving end.

In a second aspect, an embodiment of the present application provides an automatic data checking device based on artificial intelligence, which includes:

a first obtaining unit, configured to obtain an admission check item set;

the first automatic checking unit is used for checking the information of each access item in the access checking item set based on a preset access checking strategy to obtain an access checking result set;

a second obtaining unit, configured to obtain a set of service development check items, where the set of service development check items at least includes a set of trade contract check items

The second automatic checking unit is used for carrying out content extraction and content checking on the information of each service development item in the service development checking item set based on a preset service development checking strategy to obtain a service development checking result set;

a risk level determining unit, configured to determine a risk level value corresponding to the admission check item set and the service development check item set according to the ratio of the admission check result passing centralized check result and the ratio of the service development check result passing centralized check result;

and the result sending unit is used for outputting the risk level value, the admission checking result set and the service development checking result set to a receiving end.

In a third aspect, an embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor, when executing the computer program, implements the artificial intelligence based data automatic checking method according to the first aspect.

In a fourth aspect, the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to execute the artificial intelligence based data automatic checking method according to the first aspect.

The embodiment of the application provides a method, a device and equipment for automatically checking data based on artificial intelligence, which are characterized in that information of each access item in an access checking item set is checked based on a preset access checking strategy to obtain an access checking result set; performing content extraction and content verification on the acquired service development item information in the service development verification item set based on a preset service development verification strategy to obtain a service development verification result set; determining risk grade values corresponding to the admission check item set and the service development check item set according to the result proportion of the centralized check of the admission check results and the result proportion of the centralized check of the service development check results; and outputting the risk level value, the admission checking result set and the service development checking result set to a receiving end. The automatic extraction and automatic check of all the check item information included in the check entry item set and the service development check item set are realized, all the check item information does not need to be manually checked, and the information check efficiency is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a schematic view of an application scenario of an artificial intelligence based automatic data checking method according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of an artificial intelligence based automatic data checking method according to an embodiment of the present disclosure;

FIG. 3 is a schematic block diagram of an apparatus for automatic artificial intelligence-based data verification according to an embodiment of the present application;

fig. 4 is a schematic block diagram of a computer device provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of an artificial intelligence based data automatic checking method according to an embodiment of the present application; fig. 2 is a schematic flowchart of an artificial intelligence based data automatic checking method according to an embodiment of the present application, where the artificial intelligence based data automatic checking method is applied to a server, and the method is executed by application software installed in the server.

As shown in fig. 2, the method includes steps S101 to S106.

S101, an admission check item set is obtained.

In this embodiment, a server is used as an execution subject to describe the technical solution. After a user uploads an admission check item set including multiple items of admission item information (the types of the admission item information at least include text-type admission check items, image-type admission check items, and the like), the uploaded multiple items of admission item information need to be automatically checked in a server to obtain a check result, and the obtained check result can also be quickly converted into a risk level value to be used for determining the risk level of the user.

S101, checking the information of each admission item in the admission check item set based on a preset admission check strategy to obtain an admission check result set.

In this embodiment, in order to more clearly understand the technical solution of the present application, a detailed description is given below of a process of performing automatic checking on multiple items of admission item information in a server. According to the method, by taking information verification and risk level determination of enterprise users in an intelligent financial scene as an example, a server firstly obtains an admission verification item set comprising a plurality of items of admission item information. Wherein, the admission checking item set at least comprises a text type admission checking item set and an image type admission checking item set. And the server checks the text admission checking item set based on the text checking strategy in the admission checking strategy, and checks the image admission checking item set based on the image checking strategy in the admission checking strategy.

In one embodiment, step S102 includes:

determining a text type admission checking item set and an image type admission checking item set in the admission checking item set based on the acquired admission checking item set;

based on a text checking strategy in the admission checking strategies, performing data matching on each text admission checking item information in the text admission checking item set and a preset database to obtain a first admission checking result set corresponding to the text admission checking item set;

based on the image checking strategy in the admission checking strategies, performing text comparison on the identification content of each image admission checking item information in the image admission checking item set with a preset database to obtain a second admission checking result set corresponding to the image admission checking item set;

and combining the obtained first admission checking result set and the second admission checking result set to obtain the admission checking result set.

In this embodiment, in order to determine the checking result of each piece of admission checking item information in the admission checking item set more quickly, it is necessary to initially classify each piece of admission checking item information, that is, to classify the piece of admission checking item information of a text type into a text type admission checking item set, and to classify the admission checking items of an image type into an image type admission checking item set. When initially classifying the admission check item information, specifically referring to a file name suffix of each admission check item information, and if the file name suffix of the admission check item information is a png, ipeg, pdf and other image file suffixes, dividing the admission check item information into an image admission check item set; and if the file name suffix of the admission checking item information is a text file suffix such as txt, docx, xls and the like, dividing the admission checking item information into a text type admission checking item set.

After the admission checking item set is divided into a text type admission checking item set and an image type admission checking item set, the text type admission checking item set and the image type admission checking item set are automatically checked respectively.

The method comprises the steps that a text type admittance checking item set is checked, core operation is that each text type admittance checking item information in the text type admittance checking item set is subjected to data matching with a preset database (wherein the preset database is a local database local to a server and/or a non-local third-party database of the server), namely a text checking strategy in admittance checking strategies is used for comparing the text type admittance checking item information with data in the preset database, and if the text type admittance checking item information is consistent with the data in the preset database, the text type admittance checking item information is checked to be passed; if the text type access checking item information is inconsistent with the data in the preset database, the text type access checking item information is represented to be not checked.

The text type admission checking item set at least comprises a legal mobile phone real name authentication item, a legal evidence number authentication item, an authorized mobile phone real name authentication item, an authorized certificate number authentication item, an enterprise business and business checking four-factor checking item, an enterprise business and business checking three-factor checking item and an authorized human face recognition authentication item, and also comprises authentication item values respectively corresponding to the authentication items.

The automatic verification realization process of the real-name authentication item of the mobile phone of the legal person is to obtain a real-name authentication identification value of the mobile phone of the legal person to determine an automatic verification result of the real-name authentication identification value, if the real-name authentication identification value of the mobile phone of the legal person is 1, the mobile phone of the legal person passes the real-name authentication and the corresponding automatic verification result after the automatic verification of the server is passed, and the system time for automatically verifying the real-name authentication item of the mobile phone of the legal person is combined with the automatic verification result to obtain the automatic verification information (namely, the automatic verification information comprises the automatic verification result and the automatic verification system time) of the real-name authentication item of the mobile phone of the legal person.

The automatic checking of the evidence number authentication item of the legal person, the real-name authentication item of the mobile phone of the authorized person and the certificate number authentication item of the authorized person can refer to the automatic checking implementation process of the real-name authentication item of the legal person, namely, the automatic checking information of the evidence number authentication of the legal person is determined by the evidence number authentication identification value of the legal person, the automatic checking information of the real-name authentication item of the mobile phone of the authorized person is determined by the real-name authentication identification value of the mobile phone of the authorized person, and the automatic checking information of the certificate number authentication item of the authorized person is determined by the certificate number authentication identification value of the authorized person.

The four-element enterprise business checking in the four-element enterprise business checking project refers to consistency verification of enterprise names, unified social credit codes, legal representative names and legal representative identity numbers. The method comprises the steps that a server communicates with a third-party server to obtain data in a third-party database, then enterprise names, unified social credit codes, legal representative names and legal representative identity numbers are compared with data in the third-party database one by one, if the enterprise names, the unified social credit codes, the legal representative names and the legal representative identity numbers are the same as the data in the third-party database, corresponding automatic checking results are passed, and system time for automatically checking the enterprise industrial and commercial four-element checking project is combined with the automatic checking results to obtain automatic checking information (including the automatic checking results and the automatic checking system time) of the enterprise industrial and commercial four-element checking project.

The enterprise business and business inspection three-element inspection project comprises the steps of enterprise business and business inspection, wherein the enterprise business and business inspection three-element inspection in the enterprise business and business inspection project refers to the consistency verification of enterprise names, unified social credit codes and legal representative names. The method comprises the steps that a server communicates with a third-party server to obtain data in a third-party database, then enterprise names, unified social credit codes and legal representative names are compared with the data in the third-party database one by one, if the enterprise names, the unified social credit codes and the legal representative names are the same as the data in the third-party database, corresponding automatic checking results are checked to be passed, and system time for automatically checking enterprise business checking three-element checking projects is combined with the automatic checking results to obtain automatic checking information (including the automatic checking results and the automatic checking system time) of the enterprise business checking three-element checking projects.

The automatic checking of the face recognition authentication item of the authorized person is realized by obtaining a face recognition identification value of the authorized person to determine an automatic checking result, if the face recognition identification value of the authorized person is 1, the face recognition of the authorized person is passed, the corresponding automatic checking result is passed after the automatic checking of the server, and the system time for automatically checking the face recognition authentication item of the authorized person is combined with the automatic checking result to obtain the automatic checking information (including the automatic checking result and the automatic checking system time) of the face recognition authentication item of the authorized person.

In an embodiment, the performing text comparison between the identification content of the information of each image type admission check item in the image type admission check item set and a preset database based on an image check policy in the admission check policies to obtain a second admission check result set corresponding to the image type admission check item set includes:

acquiring the ith image class admission check item information in the image class admission check item set; wherein, the initial value of i is 1, the value range of i is [1, N ], and N represents the total number of the image class admission checking item information in the image class admission checking item set;

acquiring an ith identification content corresponding to the ith image class admission checking item information based on an OCR image identification model;

performing text comparison on the ith identification content and corresponding data in a preset database to obtain a checking result corresponding to the ith identification content; if the ith identification content is the same as the corresponding data in the preset database, determining that the checking result corresponding to the ith identification content is checked to be passed, and if the ith identification content is different from the corresponding data in the preset database, determining that the checking result corresponding to the ith identification content is checked to be not passed;

increasing i by 1 to update the value of i;

if i does not exceed N, returning to the step of obtaining the ith image class admission checking item information in the image class admission checking item set;

and if i exceeds N, obtaining a checking result corresponding to the 1 st identification content to a checking result corresponding to the Nth identification content to form a second admission checking result set.

In this embodiment, an image admission check item set is checked, and a core operation is to sequentially perform image recognition, text extraction (e.g., image recognition and text extraction are performed on image admission check item information through an OCR image recognition model) and text comparison with a preset database on each image admission check item information (generally, an image, such as a business license image and an authorization book image, etc.) in the image admission check item set, that is, an image check policy in the admission check policies is used to sequentially perform image recognition, text extraction and text comparison with the preset database on the image admission check item information, and if a text obtained by image admission check item information recognition is consistent with corresponding data in the preset database, it indicates that the image admission check item information passes the check; and if the text obtained by identifying the image type admission checking item information is inconsistent with the data in the preset database, indicating that the image type admission checking item information is not checked.

For example, one piece of image class admission checking item information in the image class admission checking item set is a business license image admission checking item, and mainly identifies identification values corresponding to an enterprise name, a unified social credit code, a legal representative, a registration address and a business license validity period, for example, the identification value of the enterprise name is XX1 technology limited company, the system value of the enterprise name corresponding to the preset database is XX1 technology limited company, and if the two data are consistent, the checking of the item of the enterprise name is passed; the identification value of the validity period of the business license is 12/2030, the corresponding system value of the validity period of the business license in the preset database is 12/2030 and 11/11, and the data of the two are consistent, which indicates that the item of the business name is not checked. The business license image admission checking item can be guaranteed to pass the checking only if the identification values corresponding to the identification enterprise name, the unified social credit code, the legal representative, the registration address and the business license validity period are the same as the corresponding system values in the preset database, and the business license image admission checking item is regarded as failing to pass the checking as long as one identification value corresponding to the identification enterprise name, the unified social credit code, the legal representative, the registration address and the business license validity period is different from the corresponding system value in the preset database. Therefore, the admittance checking item set is checked at least from the perspective of text type and image type, and the final checking result of the admittance checking item set can be determined quickly and accurately.

S103, acquiring a service development and verification item set, wherein the service development and verification item set at least comprises a trade contract verification item set.

In this embodiment, after the verification of the information of each admission item in the admission verification item set is completed, the information of each service development item in the service development verification item set needs to be further verified, so that the server needs to further obtain a service development verification item set at least including the trade contract verification item set to be verified.

S104, based on a preset service development checking strategy, performing content extraction and content checking on the information of each service development item in the service development checking item set to obtain a service development checking result set.

In this embodiment, after the server obtains the service development and verification item set, it may further perform verification on information of each service development item in the service development and verification item set, mainly perform verification on the service development and verification item set, which includes at least a trade contract verification item. Of course, if the admission check item set further includes non-trade contract check items (such as creditor enterprise check items, comprehensive check items, and the like), the non-trade contract check items are mainly text information, so the check process may refer to a check process for a text admission check item set.

In one embodiment, step S104 includes:

determining a trade contract checking item set and a non-trade contract checking item set in the service development checking item set based on the acquired service development checking item set;

based on a trade contract checking strategy in the business development checking strategy, contract extraction data obtained by extracting the content of each trade contract checking item information in the trade contract checking item set is compared with trade contract data in a preset database, so as to obtain a first business development checking result set corresponding to the trade contract checking item set;

if the non-trade contract checking item set is determined to be a non-empty set, comparing the state value of each piece of non-trade contract checking item information in the non-trade contract checking item set with an item expected state value based on a state value checking strategy in the service development checking strategy to obtain a second service development checking result set corresponding to the non-trade contract checking item set;

and combining the obtained first service development checking result set and the second service development checking result set to obtain the service development checking result set.

In this embodiment, in order to more quickly determine the checking result of the information of each service development checking item in the service development checking item set, it is necessary to initially classify the information of each service development checking item, divide the information of the checking item belonging to the trade contract into the trade contract checking item set, and uniformly divide the information of the checking item not belonging to the trade contract into the non-trade contract checking item set. After the above division, there may be a case where the trade contract checking item set is not an empty set and the non-trade contract checking item set is an empty set, or a case where the trade contract checking item set is not an empty set and the non-trade contract checking item set is not an empty set. When the trade contract checking item set is not an empty set and the non-trade contract checking item set is an empty set, only the trade contract checking item set needs to be automatically checked; when the trade contract checking item set is not an empty set and the non-trade contract checking item set is not an empty set, not only the trade contract checking item set needs to be automatically checked, but also the non-trade contract checking item set needs to be automatically checked.

When the trade contract check item set is checked, contract extraction data obtained by extracting the content of trade contract check item information in the trade contract check item set is compared with trade contract data in a preset database, and if the contract extraction data is completely consistent with the trade contract data in the preset database, the trade contract check item information is checked to be passed; and if the contract extraction data is inconsistent with the trade contract data in the preset database, the trade contract checking item information is not checked.

If the non-trade contract checking item set is determined to be a non-empty set, when the non-trade contract checking item set is checked, comparing the state value of each piece of non-trade contract checking item information with an item expected state value, and if the state value of the non-trade contract checking item information is the same as the item expected state value, indicating that the non-trade contract checking item information passes checking; if the state value of the non-trade contract check item information is different from the expected state value of the item, the non-trade contract check item information is not checked. For example, one non-trade contract checking item included in the set of non-trade contract checking items is a change in a business name, a status value of the change in the business name is unchanged, an item expected status value of the change in the business name is unchanged, and if the two items are identical, the information on the non-trade contract checking item indicating the change in the business name is checked.

In an embodiment, the comparing contract extraction data obtained by extracting content of information of each trade contract checking item in the trade contract checking item set with trade contract data in a preset database to obtain a first service development checking result set corresponding to the trade contract checking item set includes:

acquiring information of a jth trade contract checking item in the trade contract checking item set; wherein the initial value of j is 1, the numeric area of j is [1, M ], M represents the total number of the trade contract checking item information in the trade contract checking item set;

splitting a jth trade contract file corresponding to the jth trade contract checking item information to obtain a specific page set included in the jth trade contract file;

correspondingly extracting key elements and key element values in a specific page set in the jth trade contract document to obtain contract extraction data of the jth trade contract document;

comparing the contract extraction data of the jth trade contract file with trade contract data in a preset database to obtain a checking result corresponding to the jth trade contract file; if the contract extraction data of the jth trade contract file is the same as the trade contract data in the preset database, determining that the checking result corresponding to the jth trade contract file is passed, and if the contract extraction data of the jth trade contract file is not the same as the trade contract data in the preset database, determining that the checking result corresponding to the jth trade contract file is not passed;

increasing j by 1 to update the value of j;

if j does not exceed M, returning to execute the step of obtaining the information of the jth trade contract checking item in the trade contract checking item set;

and if j exceeds M, acquiring a checking result corresponding to the 1 st trade contract document to a checking result corresponding to the Mth trade contract document to form a first service development checking result set.

In this embodiment, a specific checking process is described by taking a trade contract checking item set in the service development checking item set as an example, and more specifically, a specific checking process is described by taking a jth trade contract document corresponding to the jth trade contract checking item information as an example. Since the jth trade contract document generally includes a specific page set composed of key pages such as a contract cover, a contract first page, a contract price page, a contract construction period page, a payment method page, a contract effective page, and a contract signing page, it is necessary to split the jth trade contract document into a plurality of single-page documents, and then screen out the contract cover, the contract first page, the contract price page, the contract construction period page, the payment method page, the contract effective page, and the contract signing page from the plurality of single-page documents.

Splitting a jth trading contract file corresponding to the jth trading contract check item information to obtain a specific page set included in the jth trading contract file, wherein the splitting includes:

splitting a jth trade contract file corresponding to the jth trade contract checking item information according to pages to obtain a jth initial single-page file set;

if the page number sequence of the single-page documents in the jth initial single-page document set is 1, the page number sequence is used as a contract cover in the jth initial single-page document set;

if the single-page file in the jth initial single-page file set comprises a contract name, a first party name and a second party name, the single-page file is taken as a contract home page in the jth initial single-page file set;

if the single page document in the jth initial single page document set comprises the contract amount, the contract amount is taken as a contract price page in the jth initial single page document set;

if the single-page file in the jth initial single-page file set comprises a contract period, taking the contract period as a contract period page in the jth initial single-page file set;

if the single page file in the jth initial single page file set comprises the payment mode, the payment mode is used as the payment mode page in the jth initial single page file set;

if the single-page file in the jth initial single-page file set comprises a contract effective date, taking the single-page file as a contract effective page in the jth initial single-page file set;

and if the single-page document in the jth initial single-page document set comprises a official seal image, the single-page document is taken as a contract signing page in the jth initial single-page document set.

In this embodiment, since the trading contract documents are generally stored in the server in the form of pdf scanned pieces, the jth trading contract document corresponding to the jth trading contract check item information may be split by page to obtain a jth initial single-page document set. Then, based on the specific content of each page, page types can be accurately classified, for example, the first page of a common jth initial single-page document set is a contract cover, the second page of the document is often a contract first page and includes key contents such as a contract name, a first party name and a second party name in the contract first page, the document including contract amount in the following page is a contract price page, the document including contract period is a contract period page, the document including payment mode is a payment mode page, the document including contract effective date is a contract effective page, and the document including official seal image is a contract signing page. Therefore, after the contract document is split and the single page content is identified, the type of each page can be identified quickly, so that the core elements and the content of the page can be extracted more accurately.

And S105, determining a risk grade value corresponding to the admission checking item set and the service development checking item set according to the admission checking result centralized checking passing result ratio and the service development checking result centralized checking passing result ratio.

In this embodiment, after the admission check result set and the service development check result set are obtained, the ratio of the passing results of the centralized check of the admission check results and the ratio of the passing results of the centralized check of the service development check results may be accurately obtained. And when the ratio of the two verification passing results is obtained, performing operations such as weighted summation and the like to obtain the risk level value. Therefore, based on the mode of the result proportion passing through the statistical checking, the risk grade value can be intuitively and quickly converted.

In one embodiment, step S105 includes:

acquiring the total number of the admission checking results in the admission checking result set and the first total number of the admission checking results with checking passing results in the admission checking result set, and determining the proportion of the first checking passing results according to the proportion of the first total number and the total number of the admission checking results;

acquiring the total number of the service development checking results in the service development checking result set and a second total number of the service development checking results with checking passing results in the service development checking result set, and determining a second checking passing result ratio according to the ratio of the second total number to the total number of the service development checking results;

and acquiring a first weight value corresponding to the first verification passing result proportion, acquiring a second weight value corresponding to the second verification passing result proportion, and summing a first product of the first verification passing result proportion and the first weight value and a second product of the second verification passing result proportion and the second weight value to obtain the risk level value.

In this embodiment, since the admission check result is concentrated with admission check results corresponding to check-passing results and also with admission check results corresponding to check-failing results, the total number of the admission check results and the first total number of the admission check results having the check-passing results are counted, and the first total number is divided by the total number of the admission check results to obtain a first check-passing result ratio.

Similarly, since the service development and verification result is concentrated with the result that the service development and verification result corresponds to the verification passing result and the result that the service development and verification result corresponds to the verification failing result, a second total number of the service development and verification results which are concentrated with the verification passing result in the service development and verification result is counted, and the second total number is divided by the total number of the service development and verification results to obtain a second verification passing result ratio.

As a first weight value corresponding to the first verification passing result proportion may be preset in the server, and a second weight value corresponding to the second verification passing result proportion may be set, the first verification passing result proportion and the second verification passing result proportion are subjected to weighted summation, and the risk level value may be obtained. Therefore, the risk assessment is carried out by referring to the multi-dimensional data, and the risk grade value can be obtained more reasonably and accurately.

S106, outputting the risk level value, the admission checking result set and the service development checking result set to a receiving end.

In this embodiment, after obtaining the risk level values corresponding to the admission check item set and the service development check item set in the server, the information (specifically, the risk level values, the admission check result set, and the service development check result set) needs to be sent to the receiving end that sends the information corresponding to the admission check item set and the service development check item set, and then the risk level values, the admission check result set, and the service development check result set are displayed on the display interface of the receiving end.

The method realizes automatic extraction and automatic checking of all the checking item information included in the entry checking item set and the service development checking item set, does not need to manually check all the checking item information, and improves the information checking efficiency.

The embodiment of the application further provides an artificial intelligence based automatic data checking device, and the artificial intelligence based automatic data checking device is used for executing any embodiment of the artificial intelligence based automatic data checking method. Specifically, referring to fig. 3, fig. 3 is a schematic block diagram of an artificial intelligence based data automatic checking apparatus 100 according to an embodiment of the present application.

As shown in fig. 3, the apparatus 100 for automatically checking data based on artificial intelligence includes a first obtaining unit 101, a first automatic checking unit 102, a second obtaining unit 103, a second automatic checking unit 104, a risk level determining unit 105, and a result transmitting unit 106.

A first obtaining unit 101, configured to obtain a set of admission check items.

In this embodiment, a server is used as an execution subject to describe the technical solution. After a user uploads an admission check item set including multiple items of admission item information (the types of the admission item information at least include text admission check items, image admission check items and the like), the uploaded multiple items of admission item information need to be automatically checked in a server to obtain a check result, and the obtained check result can be quickly converted into a risk level value to be used for determining the risk level of the user.

And the first automatic checking unit 102 is configured to check information of each admission item in the admission check item set based on a preset admission check policy to obtain an admission check result set.

In an embodiment, the first automatic checking unit 102 is specifically configured to:

determining a text type admission check item set and an image type admission check item set in the admission check item set based on the acquired admission check item set;

based on a text verification strategy in the admission verification strategies, performing data matching on each text admission verification item information in the text admission verification item set and a preset database to obtain a first admission verification result set corresponding to the text admission verification item set;

based on an image checking strategy in the admission checking strategies, performing text comparison on the identification content of each image admission checking item information in the image admission checking item set with a preset database to obtain a second admission checking result set corresponding to the image admission checking item set;

In this embodiment, in order to determine the checking result of each admission check item information in the admission check item set more quickly, it is necessary to initially classify each admission check item information, that is, to divide the admission check item information of a text type into a text type admission check item set, and to divide the admission check item of an image type into an image type admission check item set. When initially classifying the admission checking item information, specifically referring to a file name suffix of each admission checking item information, and if the file name suffix of the admission checking item information is a png, ipeg, pdf and other image file suffixes, dividing the admission checking item information into an image admission checking item set; and if the file name suffix of the admission checking item information is a text file suffix such as txt, docx, xls and the like, dividing the admission checking item information into a text type admission checking item set.

The automatic checking of the legal person evidence number authentication item, the authorized person mobile phone real name authentication item and the authorized person certificate number authentication item can refer to the automatic checking implementation process of the legal person mobile phone real name authentication item, namely, the automatic checking information of legal person evidence number authentication is determined by the legal person evidence number authentication identification value, the automatic checking information of the authorized person mobile phone real name authentication item is determined by the authorized person mobile phone real name authentication identification value, and the automatic checking information of the authorized person certificate number authentication item is determined by the authorized person certificate number authentication identification value.

The enterprise business-to-business checking three-element checking project of the enterprise business-to-business checking three-element checking project refers to consistency verification of enterprise names, unified social credit codes and legal representative names. The method specifically comprises the steps that a server communicates with a third-party server to obtain data in a third-party database, then enterprise names, unified social credit codes and legal representative names are compared with the data in the third-party database one by one, if the enterprise names, the unified social credit codes and the legal representative names are the same as the data in the third-party database, corresponding automatic checking results are checked to be passed, and system time for automatically checking the enterprise industrial and commercial checking three-element checking project is combined with the automatic checking results to obtain automatic checking information (including the automatic checking results and the automatic checking system time) of the enterprise industrial and commercial checking three-element checking project.

acquiring an ith identification content corresponding to the ith image type admission checking item information based on an OCR image identification model;

increasing i by 1 to update the value of i;

if i does not exceed N, returning to execute the step of obtaining the ith image class access checking item information in the image class access checking item set;

For example, one piece of image type admission check item information in the image type admission check item set is a business license image admission check item, and mainly identifies the identification values corresponding to the enterprise name, the unified social credit code, the legal representative, the registration address and the validity period of the business license, if the identification value of the enterprise name is XX1 technology limited company, the system value corresponding to the enterprise name in the preset database is XX1 technology limited company, and if the two data are consistent, the checking of the item of the enterprise name is passed; the identification value of the validity period of the license is 2030, 12 and 12 days, the corresponding system value of the validity period of the license in the preset database is 2030, 12 and 11 days, and if the two data are consistent, the verification of the item of the enterprise name is failed. The business license image admission checking item can be guaranteed to pass the checking only if the identification values corresponding to the identification enterprise name, the unified social credit code, the legal representative, the registration address and the business license validity period are the same as the corresponding system values in the preset database, and the business license image admission checking item is regarded as failing to pass the checking as long as one identification value corresponding to the identification enterprise name, the unified social credit code, the legal representative, the registration address and the business license validity period is different from the corresponding system value in the preset database. Therefore, the admittance checking item set is checked at least from the perspective of text type and image type, and the final checking result of the admittance checking item set can be determined quickly and accurately.

A second obtaining unit 103, configured to obtain a set of business development check items, where the set of business development check items at least includes a set of trade contract check items.

And a second automatic checking unit 104, configured to perform content extraction and content checking on the service development item information in the service development checking item set based on a preset service development checking policy, so as to obtain a service development checking result set.

In this embodiment, after the server obtains the service development verification item set, the server may also verify information of each service development item in the service development verification item set, and mainly verify that the service development verification item set at least includes a trade contract verification item. Of course, if the admission check item set further includes non-trade contract check items (such as creditor enterprise check items, comprehensive check items, and the like), the non-trade contract check items are mainly text information, so the check process may refer to a check process for a text admission check item set.

In an embodiment, the second automatic checking unit 104 is specifically configured to:

determining a trade contract checking item set and a non-trade contract checking item set in the business development checking item set based on the acquired business development checking item set;

if the non-trade contract checking item set is determined to be a non-empty set, comparing the state value of each piece of non-trade contract checking item information in the non-trade contract checking item set with an item expected state value based on a state value checking strategy in the business developing checking strategy to obtain a second business developing checking result set corresponding to the non-trade contract checking item set;

and combining the acquired first service development and verification result set and the acquired second service development and verification result set to obtain the service development and verification result set.

In this embodiment, in order to more quickly determine the checking result of the information of each service development checking item in the service development checking item set, it is necessary to initially classify the information of each service development checking item, divide the information of the checking item belonging to the trade contract into the trade contract checking item set, and uniformly divide the information of the checking item not belonging to the trade contract into the non-trade contract checking item set. After the above division, it may happen that the trade contract checking item set is not an empty set and the non-trade contract checking item set is an empty set, or that the trade contract checking item set is not an empty set and the non-trade contract checking item set is not an empty set. When the trade contract checking item set is not an empty set and the non-trade contract checking item set is an empty set, only the trade contract checking item set needs to be automatically checked; when the trade contract checking item set is not an empty set and the non-trade contract checking item set is not an empty set, not only the trade contract checking item set but also the non-trade contract checking item set need to be automatically checked.

If the non-trade contract checking item set is determined to be a non-empty set, when the non-trade contract checking item set is checked, comparing the state value of each piece of non-trade contract checking item information with an item expected state value, and if the state value of the non-trade contract checking item information is the same as the item expected state value, indicating that the non-trade contract checking item information passes checking; if the state value of the non-trade contract check item information is different from the expected state value of the item, the non-trade contract check item information is not checked. For example, one non-trade contract checking item included in the set of non-trade contract checking items is a change in the name of the business, and the status value of the change in the name of the business is unchanged, while the item expected status value of the change in the name of the business is unchanged, and if the two are identical, the non-trade contract checking item information indicating the change in the name of the business is checked.

In an embodiment, the comparing contract extraction data obtained by extracting content of each trade contract checking item information in the trade contract checking item set with trade contract data in a preset database to obtain a first service development checking result set corresponding to the trade contract checking item set includes:

comparing the contract extraction data of the jth trade contract file with trade contract data in a preset database to obtain a checking result corresponding to the jth trade contract file; if the contract extraction data of the jth trade contract document is the same as the trade contract data in the preset database, determining that the checking result corresponding to the jth trade contract document is passed, and if the contract extraction data of the jth trade contract document is not the same as the trade contract data in the preset database, determining that the checking result corresponding to the jth trade contract document is failed to check;

increasing j by 1 to update the value of j;

In this embodiment, a specific checking process is described by taking a trade contract checking item set in a service development checking item set as an example, and more specifically, a jth trade contract document corresponding to the jth trade contract checking item information is taken as an example to describe the specific checking process. Since the jth trade contract document generally includes a specific page set composed of key pages such as a contract cover, a contract first page, a contract price page, a contract construction period page, a payment method page, a contract effective page, and a contract signing page, it is necessary to split the jth trade contract document into a plurality of single-page documents, and then screen out the contract cover, the contract first page, the contract price page, the contract construction period page, the payment method page, the contract effective page, and the contract signing page from the plurality of single-page documents.

if the single-page file in the jth initial single-page file set comprises a contract name, a name of a first party and a name of a second party, the single-page file is used as a contract home page in the jth initial single-page file set;

and if the single-page document in the jth initial single-page document set comprises a official seal image, the single-page document is used as a contract signing page in the jth initial single-page document set.

In this embodiment, since the trade contract documents are generally stored in the server in the form of pdf scan pieces, the jth trade contract document corresponding to the jth trade contract checking item information may be split by page to obtain a jth initial single-page document set. And then, based on the specific content of each page, the page types of the pages can be accurately classified, for example, the first page of a common jth initial single-page file set is a contract cover, the second page of the file is often a contract first page and includes key contents such as contract names, first party names and second party names in the contract first page, the file including the contract amount in the following page is a contract price page, the file including the contract period is a contract period page, the file including the payment mode is a payment mode page, the file including the contract effective date is a contract effective page, and the file including the official seal image is a contract signing page. Therefore, after the contract document is split and the contents of the single page are identified, the type of each page can be quickly identified, so that the core elements and the contents of the page can be more accurately extracted.

A risk level determining unit 105, configured to determine a risk level value corresponding to the admission check item set and the service development check item set according to the ratio of the admission check result passing centralized check result and the ratio of the service development check result passing centralized check result.

In this embodiment, after the admission check result set and the service development check result set are obtained, the ratio of the passing results of the centralized check of the admission check results and the ratio of the passing results of the centralized check of the service development check results may be accurately obtained. And when the proportion of the two checking passing results is obtained, performing operations such as weighted summation and the like to obtain the risk grade value. Therefore, based on the mode of the result proportion of the statistical verification, the risk level value can be intuitively and quickly converted.

In an embodiment, the risk level determination unit 105 is specifically configured to:

As a first weight value corresponding to the first verification passing result proportion and a second weight value corresponding to the second verification passing result proportion may be preset in the server, and the first verification passing result proportion and the second verification passing result proportion are subjected to weighted summation, so as to obtain the risk level value. Therefore, the risk assessment is carried out by referring to the multi-dimensional data, and the risk grade value can be obtained more reasonably and accurately.

A result sending unit 106, configured to output the risk level value, the admission check result set, and the service development check result set to a receiving end.

The device realizes automatic extraction and automatic checking of all the checking item information included in the entry checking item set and the service development checking item set, all the checking item information does not need to be checked manually, and the information checking efficiency is improved.

The above-mentioned artificial intelligence-based data automatic checking apparatus can be implemented in the form of a computer program, which can be run on a computer device as shown in fig. 4.

Referring to fig. 4, fig. 4 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server or a server cluster. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.

Referring to fig. 4, the computer apparatus 500 includes a processor 502, a memory, which may include a storage medium 503 and an internal memory 504, and a network interface 505 connected by a device bus 501.

The storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032, when executed, causes the processor 502 to perform an artificial intelligence based data auto-verification method.

The processor 502 is used to provide computing and control capabilities that support the operation of the overall computer device 500.

The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 can be caused to execute an artificial intelligence based data auto-verification method.

The network interface 505 is used for network communication, such as providing transmission of data information. Those skilled in the art will appreciate that the configuration shown in fig. 4 is a block diagram of only a portion of the configuration associated with aspects of the present application, and is not intended to limit the computing device 500 to which aspects of the present application may be applied, and that a particular computing device 500 may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

The processor 502 is configured to run the computer program 5032 stored in the memory to implement the artificial intelligence based data automatic checking method disclosed in the embodiment of the present application.

Those skilled in the art will appreciate that the embodiment of a computer device illustrated in fig. 4 does not constitute a limitation on the specific construction of the computer device, and that in other embodiments a computer device may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor, and in such embodiments, the structures and functions of the memory and the processor are consistent with those of the embodiment shown in fig. 4, which are not described herein again.

It should be understood that in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium may be a nonvolatile computer-readable storage medium or a volatile computer-readable storage medium. The computer readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the artificial intelligence based data auto-verification method disclosed in the embodiments of the present application.

It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described devices, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. Those of ordinary skill in the art will appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, device and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only a logical division, and there may be other divisions when the actual implementation is performed, or units having the same function may be grouped into one unit, for example, a plurality of units or components may be combined or may be integrated into another device, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electrical, mechanical or other form of connection.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the elements may be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a backend server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk.

While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An artificial intelligence based automatic data checking method is characterized by comprising the following steps:

obtaining an admission checking item set;

acquiring a service development and verification item set, wherein the service development and verification item set at least comprises a trade contract verification item set;

2. The method for automatically checking data based on artificial intelligence according to claim 1, wherein the checking the information of each admission item in the admission check item set based on a preset admission check policy to obtain an admission check result set comprises:

3. The method for automatically checking data based on artificial intelligence according to claim 2, wherein the text comparison of the identification content of each image type admission check item information in the image type admission check item set with a preset database based on an image check policy in the admission check policies to obtain a second admission check result set corresponding to the image type admission check item set comprises:

increasing i by 1 to update the value of i;

4. The method for automatically checking data based on artificial intelligence of claim 1, wherein the performing content extraction and content check on the obtained information of each service development item in the service development check item set based on a preset service development check strategy to obtain a service development check result set comprises:

5. The method for automatically checking data based on artificial intelligence according to claim 4, wherein said extracting contract data obtained by extracting contents of each trade contract check item in said trade contract check item set and comparing the extracted contract data with trade contract data in a preset database to obtain a first service development check result set corresponding to said trade contract check item set comprises:

acquiring information of a jth trade contract checking item in the trade contract checking item set; wherein the initial value of j is 1, the numeric area of j is [1, M ], and M represents the total number of the trade contract checking item information in the trade contract checking item set;

splitting a jth trading contract file corresponding to the jth trading contract check item information to obtain a specific page set included in the jth trading contract file;

increasing j by 1 to update the value of j;

6. The artificial intelligence based data automatic checking method according to claim 5, wherein the specific page set of the jth trade contract document includes a cover page, a contract first page, a contract price page, a contract construction period page, a payment method page, a contract validation page and a contract signing page, and the splitting of the jth trade contract document corresponding to the jth trade contract checking item information to obtain the specific page set included in the jth trade contract document includes:

splitting a jth trading contract file corresponding to the jth trading contract check item information according to pages to obtain a jth initial single-page file set;

if the single page file in the jth initial single page file set comprises the contract amount, the contract amount is used as a contract price page in the jth initial single page file set;

if the single page file in the jth initial single page file set comprises the payment mode, the single page file is taken as a payment mode page in the jth initial single page file set;

7. The method of claim 1, wherein the determining a risk level value corresponding to the set of admission check items and the set of service development check items according to the ratio of the results of centralized check of admission check items and the ratio of the results of centralized check of service development check items comprises:

8. An automatic data checking device based on artificial intelligence is characterized by comprising:

a first obtaining unit, configured to obtain an admission check item set;

a second obtaining unit, configured to obtain a set of business development verification items, where the set of business development verification items at least includes a set of trade contract verification items

a risk level determining unit, configured to determine a risk level value corresponding to the admission check item set and the service development check item set according to the admission check result centralized check passing result ratio and the service development check result centralized check passing result ratio;

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the artificial intelligence based data auto-verification method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, causes the processor to execute the artificial intelligence based data auto-verification method according to any one of claims 1 to 7.