WO2019227576A1

WO2019227576A1 - Invoice verification method and apparatus, computer device, and storage medium

Info

Publication number: WO2019227576A1
Application number: PCT/CN2018/094362
Authority: WO
Inventors: 潘庚生
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-05-31
Filing date: 2018-07-03
Publication date: 2019-12-05
Also published as: CN108960058B; CN108960058A

Abstract

Disclosed is an invoice verification method. The verification method comprises: constructing a blacklist library, the blacklist library comprising black name supplier information; when a verification request sent by a client is obtained, obtaining supplier information on an invoice to be verified from the verification request, the supplier information comprising an identification-version field and an entry-version field of the supplier; performing fuzzy searching in the blacklist library by means of the identification-version field to obtain black name supplier information associated with the supplier information; on the basis of the black name supplier information associated with the supplier information, performing matching processing by respectively using the entry-version field and the identification-version field as a fixed word group, and generating a verification result according to the matching processing; and sending the verification result to the client, so that the client receives and outputs the verification result. The present application solves the existing problem of being unable to verify a supplier when payment is performed on the supplier, and improves the verification accuracy.

Description

Invoice verification method, device, computer equipment and storage medium

This application is based on a Chinese invention patent application filed on May 31, 2018 with the application number 201810551153.3 and entitled "Invoice Verification Method, Device, Computer Equipment and Storage Medium" and claims its priority.

Technical field

The present application relates to the field of communication technologies, and in particular, to an invoice verification method, device, computer equipment, and storage medium.

Background technique

When an enterprise performs a payment operation with a supplier, employees in the financial department usually manually review the information on the invoice, but cannot verify the supplier on the ticket. They can learn the potential risks of the supplier and provide early warning. The risk of reimbursement can easily lead to the loss of corporate funds.

Summary of the Invention

The embodiments of the present application provide an invoice verification method, device, computer equipment, and storage medium to solve the problem that the supplier cannot be verified when performing a payment operation with the supplier at present.

An invoice verification method includes:

Building a blacklist library, which includes blackname vendor information;

When the verification request sent by the client is obtained, the supplier information on the invoice to be verified is obtained from the verification request, and the supplier information includes an identification version field and an entry version field of the supplier;

Perform a fuzzy search in the blacklist database through the identification version field to obtain black name supplier information associated with the supplier information;

Based on the black name supplier information associated with the supplier information, the matching process is performed using the input version field and the identification version field as fixed phrases, and a verification result is generated based on the black name supplier information obtained by the matching process. ;

Sending the verification result to the client, so that the client receives and outputs the verification result.

Further, performing the fuzzy search in the blacklist database through the identification version field to obtain the black name supplier information associated with the supplier information includes:

Perform word segmentation processing on the identification version field, and obtain keywords in the supplier information according to a result of the word segmentation processing;

The black name supplier information including the keywords is acquired from the black list database based on the SQL language to obtain the black name supplier information associated with the supplier information.

Perform word segmentation processing on the identification version field, and word segmentation processing on each black name supplier information in the black list library;

For each black name supplier information and identification version field to be compared, according to the result of word segmentation processing, generate a word segmentation sequence corresponding to the black name supplier information and identification version field to be compared;

Generating a word frequency vector corresponding to the black name supplier information to be compared and a word frequency vector corresponding to the recognition version field according to the word segmentation sequence;

Calculating the cosine similarity between the word frequency vector corresponding to the black name supplier information to be compared and the word frequency vector corresponding to the recognition version field;

Obtain black name supplier information whose cosine similarity is greater than or equal to a preset similarity threshold.

Further, the black name supplier information associated with the supplier information is used to perform matching processing using the input version field and the identification version field as fixed phrases, respectively, and the black name supplier obtained according to the matching processing. Information generation verification results include:

Performing a first matching process on the black name supplier information associated with the input version field and the supplier information, and performing a second match on the black name supplier information associated with the identification version field and the supplier information Matching processing

If the black name supplier information, the input version field, and the identification version field obtained by the two matching processes are all the same, generate a verification result according to the black name supplier information obtained by the first matching process or the second matching process;

If the black name supplier information obtained by the two matching processes is different, a verification result is generated according to the black name supplier information obtained by the second matching process.

Further, the constructing a blacklist library includes:

Obtain black-named user information from a preset credit system, and use the black-named user information as black-name supplier information to add to the blacklist database; and / or

According to the transaction bad debt records between the related suppliers, the suppliers whose transaction bad debts reach the preset amount threshold and the aging reaches the preset aging threshold are selected as black name supplier information and added to the blacklist database.

Further, the constructing the blacklist library further includes:

Introduce a controlling relationship between enterprises;

For each black name supplier information in the black list database, the holding company corresponding to each black name supplier is obtained from the controlling relationship, and the holding company is added to the black list database as the black name supplier information.

An invoice checking device includes:

A building module for building a blacklist library that includes blackname vendor information;

An obtaining module, configured to obtain the supplier information on the invoice to be verified from the verification request when the verification request sent by the client is obtained, where the supplier information includes an identification version field of the supplier and an entry Version field

A fuzzy search module, configured to perform a fuzzy search in a blacklist database through an identification version field to obtain black name supplier information associated with the supplier information;

A matching module, configured to perform matching processing using the input version field and the identification version field as fixed phrases based on the black name supplier information associated with the supplier information, and according to the black name supplier obtained by the matching processing Information generation verification results;

A sending module is configured to send the verification result to a client, so that the client receives and outputs the verification result.

Further, the matching module includes:

A matching unit, configured to perform a first matching process on the black name supplier information associated with the entry version field and the supplier information, and provide a black name supply associated with the identification version field and the supplier information Quotient information performs a second matching process;

The first generating unit is configured to generate a calibration according to the black name supplier information obtained by the first matching process or the second matching process if the black name supplier information obtained by the two matching processes, the input version field, and the identification version field are the same Test results

The second generating unit is configured to generate a verification result according to the black name supplier information obtained by the second matching process if the black name supplier information obtained by the two matching processes is different.

A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the following steps are implemented:

Building a blacklist library, which includes blackname vendor information;

One or more non-volatile readable storage media storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the following steps:

Building a blacklist library, which includes blackname vendor information;

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below. Other features and advantages of the application will become apparent from the description, the drawings, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solutions of the embodiments of the present application more clearly, the drawings used in the description of the embodiments of the application will be briefly introduced below. Obviously, the drawings in the following description are just some embodiments of the application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a schematic diagram of an application environment of an invoice verification method according to an embodiment of the present application; FIG.

2 is a flowchart of an invoice verification method according to an embodiment of the present application;

3 is a flowchart of step S203 in the invoice verification method according to an embodiment of the present application;

4 is a flowchart of step S203 in the invoice verification method according to an embodiment of the present application;

5 is a flowchart of step S204 in the invoice verification method according to an embodiment of the present application;

6 is a principle block diagram of an invoice verification device in an embodiment of the present application;

FIG. 7 is a schematic diagram of a computer device in an embodiment of the present application.

Detailed ways

In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

The invoice verification method provided in the embodiment of the present application can be applied in the application environment as shown in FIG. 1, including a client and a server, where the client communicates with the server through a network. The client may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers. The client and server jointly complete the verification of the information on the invoice. The server is used to construct and manage a blacklist database, perform operations of adding, deleting, and modifying the black name information on the record in the blacklist database, and perform a blacklist verification analysis in response to a verification request from the client. The client is used to initiate a verification request, and output and display the verification result obtained from the server. In the embodiment of the present application, the verification is a verification of the supplier information on the invoice, and the blacklist database includes a plurality of black name supplier information.

In one embodiment, as shown in FIG. 2, an invoice verification method is provided. The method is applied to the server in FIG. 1 as an example, and includes the following steps:

In step S201, a blacklist library is constructed, and the blacklist library includes black name supplier information.

Here, the embodiment of the present application constructs a blacklist library on the server side in advance, and improves the data source of the blackname supplier information in the blacklist library to improve the data reliability of the blacklist library and enrich the data in the blacklist library. Types, providing a more comprehensive verification service.

Optionally, as a preferred example of the present application, the step S201 may include:

The black name user information is obtained from a preset credit system, and the black name user information is added to the black list database as black name supplier information.

The preset credit system includes, but is not limited to, a national credit system, a banking system, and a credit reporting agency. The embodiment of the present application directly obtains black-named user information from the national credit system, banking system, and credit reporting agencies. Each black-named user information includes, but is not limited to, black-name supplier names and records of black-related behaviors. This includes, but is not limited to, the reasons for black sex and the time when black sex acts occurred.

In this example, the data sources of the constructed blacklist database include data from the national credit system, banking system, and credit reporting agencies. The data of the blacklist database is highly reliable and the data types are complete, which is conducive to providing more comprehensive information. Calibration services.

As another preferred example of the present application, the step S201 may further include:

Here, the embodiment of the present application may also filter black-named supplier information based on the bad debts of the transaction from the big data accumulated by the enterprise itself. First, obtain the associated supplier with bad transactions from big data, then compare the amount of bad transactions with the preset amount threshold, compare the age of the bad transactions with the preset age threshold, if the bad debts in the transaction When the amount is greater than or equal to the preset amount threshold and the aging is greater than or equal to the preset aging threshold, the associated supplier is used as black name supplier information and added to the black list database. The preset amount threshold and the preset aging threshold are both parameters for judging whether a supplier corresponding to a transaction bad debt is a blacklist. The preset amount threshold is a blacklisted transaction for a supplier corresponding to a transaction bad debt. The lower limit of the amount, and the preset aging threshold is the lower limit of the aging that the supplier corresponding to the transaction bad debt is a blacklist.

Introduce a controlling relationship between enterprises;

Here, the controlling relationship refers to a relationship between enterprises that controls other enterprises by holding a certain number of shares. The holding relationship may be stored in a mapping table. Exemplarily, it is assumed that the company M in the holding relationship is the holding company of the company N. If the company M exists in the blacklist supplier information of the blacklist database, then by querying the holding relationship, it can be obtained that the company M is the holding of the company N Company, then the company N is also used as the black name supplier information and added to the black list database, thereby further expanding the data amount of the black name information in the black list database, which is beneficial to achieve a more comprehensive verification To improve the ability of financial risk management and control.

Optionally, in the embodiment of the present application, the blacklist library may be deployed on a cloud platform, so as to provide data services to internal enterprises and external enterprises, and implement a SAAS service model.

In step S202, when the verification request sent by the client is obtained, the supplier information on the invoice to be verified is obtained from the verification request, and the supplier information includes the identification version field of the supplier and the entry. Edition field.

Here, the supplier identification field refers to the supplier information obtained by image recognition of the invoice image information, and the entry version field refers to the supplier information obtained by manual entry. During the payment transaction, the user can enter the supplier information on the invoice face of the invoice to be verified on the client, and upload the invoice image information by scanning with a scanner. The client or server on the client side receives the supplier information and obtains the entry version field of the supplier; and performs OCR identification on the invoice image information to obtain the supplier information on the invoice face, that is, the supplier's identification version Field. A verification request is then generated based on the supplier's identification version field and the entry version field, and the verification request is sent to the server to initiate a verification process for the invoice to be verified.

Correspondingly, after obtaining the verification request sent by the client, the server parses the verification request, and obtains the supplier information on the invoice to be verified, including the identification version field and the entry version field of the supplier.

In step S203, a fuzzy search is performed in the blacklist database through the identification version field to obtain black name supplier information associated with the supplier information.

Here, because the input version field is prone to input errors, the accuracy of the identification version field is higher than the input version field. When verifying the supplier information on the verification invoice, the embodiment of the present application first uses the identification version field as a verification object, and performs a fuzzy search on the identification version field in a blacklist database. Optionally, the fuzzy search may be split according to the identification version field, and the keywords in the search term are used as search terms to perform a logical AND operation to obtain the black name supplier information associated with the identification version field from a blacklist database. The black-name supplier information with low reference meaning is initially filtered out.

In step S204, based on the black name supplier information associated with the supplier information, a matching process is performed using the input version field and the identification version field as fixed phrases, respectively, and the black name supplier obtained according to the matching process The information generates a verification result.

After the fuzzy search is completed, based on the results obtained by the fuzzy search, the input version field and the identification version field are used as verification objects, respectively, to perform accurate matching processing. The precise matching process refers to using the input version field and the identification version field as fixed search phrases, performing a logical AND operation, and obtaining the input version field or the input version field from the associated black name supplier information. Black name supplier information with exactly the same identification field.

Here, in the embodiment of the present application, the input version field and the identification version field are respectively used as a fixed phrase to perform a matching process, and then generate a verification result based on the two matching processes, which is beneficial to improving the accuracy of the matching process and further improving supply Verification accuracy of business information.

In step S205, the verification result is sent to the client, so that the client receives and outputs the verification result.

In the embodiment of the present application, the verification result includes a conclusion of whether it is a blacklist and a name of the blacklist. The conclusion of whether it is a blacklist includes: the supplier information on the invoice to be verified is a blacklist, the supplier information on the invoice to be verified is not a blacklist, and the supply on the invoice to be verified The business information is suspected blacklist. The name of the blacklist is the blacklisted vendor information in the blacklist library that matches the check. The embodiment of the present application further sends the verification result to the client, so that the client receives and outputs the verification result, and at the same time as completing the blacklist verification, the SAAS (Software- as-a-Service (software as a service) service, which can provide black name verification services to internal and external enterprises.

In an embodiment, the fuzzy search may be performed based on a structured query language SQL. As shown in FIG. 3, in step S203, that is, performing a fuzzy search in the blacklist database through the identification version field to obtain the black name supplier information associated with the supplier information includes the following steps:

In step S301, word segmentation processing is performed on the identification version field, and keywords in the supplier information are acquired according to a result of the word segmentation processing.

Here, the supplier information is usually the company name, such as XX (city) XX Technology Co., Ltd. The embodiment of the present application constructs a word segmentation meta database in advance, and uses the word segmentation meta database to store the word segmentation rules and standard information on the region, company name, and company form on which the word segmentation process is based. Wherein, the word segmentation rule refers to a rule defined according to whether a company name includes specified characteristic characters, and the specified characteristic characters include, but are not limited to, for example, "province", "city", "technology", "clothing", " Information Technology "," Communication "," Limited Liability Company "," Company Limited ". Each segmentation rule corresponds to a different segmentation procedure. When word segmentation processing is performed on the recognition version field, the position where the characteristic character appears is obtained according to the word segmentation rule, and information before the characteristic character or between two characteristic characters is intercepted to obtain several word segmentation. Exemplarily, for example, the information between "province" and "city" is intercepted, and the information between "city" and "limited liability company" is intercepted. Then, the intercepted information is compared with the standard information in the segmentation meta database to identify the attributes of each segmentation, that is, whether the segmentation is a regional noun, a company name, or a company form, which further ensures the accuracy of the segmentation. For example, as described above, after comparing the intercepted information between "province" and "city" with standard information, the intercepted information can be identified as a regional noun, and can be specifically identified as a municipal-level region; After the information between the intercepted "city" and "limited liability company" is compared with the standard information, the intercepted information can be identified as the company name. Optionally, in the embodiment of the present application, a company name is used as a keyword, that is, a participle whose attribute is a company name is used as a keyword.

In step S302, the black name supplier information including the keywords is acquired from the black list database based on the SQL language to obtain black name supplier information associated with the supplier information.

After the keywords are obtained, the embodiment of the present application sets a specified SQL statement based on the keywords. Exemplarily, the specified SQL statement may be:

SELECT (XX field) FROM (XX table) WHERE (XX field) LIKE (XX condition).

Here, the embodiment of the present application sets a LIKE condition according to the keywords. To match characters of any type and any length, for Chinese fields, two percent signs (%%) can be used. such as:

Assuming that the identification version field of the supplier information of the invoice to be verified is "Ping An Technology Co., Ltd.", and the keyword obtained through word segmentation processing is "Ping An Technology", the SQL statement can be set to:

select * from flow_supplier where the supplier name is like '% 平安科技%';

Here, the flow_supplier indicates the black name supplier information list in the blacklist library, and the suppliername indicates the black name supplier name. According to the above SQL statement, the flow_supplier table name in the suppliername contains "safety" "Technology" records are all queried out to complete a fuzzy search to obtain a name similar to the identification version field, that is, all black name supplier information that includes the word "Ping An Technology" in the identification version field.

In the embodiment of the present application, the black name supplier information associated with the identification version field is obtained from the black list database through a fuzzy search, and the black name supplier information with a lower reference meaning is preliminarily filtered, which is helpful to improve the verification. Efficiency and accuracy; and SQL language is highly non-procedural, which effectively reduces development costs.

In one embodiment, a fuzzy search may be performed based on a cosine similarity algorithm. As shown in FIG. 4, in step S203, that is, performing a fuzzy search in the blacklist database through the identification version field to obtain the black name supplier information associated with the supplier information includes the following steps:

In step S401, word segmentation processing is performed on the identification version field, and word segmentation processing is performed on each black name supplier information in the black list database.

In the embodiment of the present application, the supplier information is usually a company name, such as XX (City) YY Technology Co., Ltd. The word segmentation here refers to segmenting the Chinese character sequence into meaningful words. For example, the above-mentioned XX (city) YY Technology Co., Ltd. is divided into "XX, YY, Technology, Co., Ltd.". Optionally, the manner of word segmentation includes, but is not limited to, a word segmentation method based on string matching, a word segmentation method based on understanding, and a word segmentation method based on statistics.

In step S402, for each black name supplier information and identification version field to be compared, a word segmentation sequence corresponding to the black name supplier information and identification version field to be compared is generated according to the result of the word segmentation processing.

Here, the embodiment of the present application extracts one piece of black name supplier information from the black list database without replacement as the black name supplier information to be compared. Generate a corresponding word segmentation sequence according to the black name supplier information to be compared and the identification version field. The word segmentation sequence refers to a sequence composed of the black name supplier information to be compared and the word segmentation included in the identification field.

Exemplarily, it is assumed that the black name supplier information A to be compared is XX City YY Technology Co., Ltd., and the word segmentation obtained after the word segmentation processing includes XX, City, YY, Technology, Ltd .; the identification version field B is XXYY Technology Limited Companies, the word segmentation obtained after the word segmentation processing includes XX, YY, technology, limited company. The word segmentation corresponding to the black name supplier information to be compared and the identification version field is combined to obtain the word segmentation sequence corresponding to the black name supplier information A and the identification version field B to be compared: XX, city, YY, Technology Co., Ltd.

In step S403, a word frequency vector corresponding to the black name supplier information to be compared and a word frequency vector corresponding to the recognition version field are generated according to the word segmentation sequence.

In the embodiment of the present application, the word frequency refers to the number of times each participle appears in the identification version field or the black name supplier information to be compared. As mentioned above, the participle "XX" appears in the black name supplier information A or the identification version field B that are to be compared, and the number of occurrences is 1. The participle "city" is in the black name to be compared. The number of occurrences in the supplier information A is 1, the number of occurrences in the identification version field B is 0, and so on.

After obtaining the word frequency of each participle in the identification version field / to-be-compared black name supplier information, the word frequency is combined according to the word segmentation sequence to obtain the identification version field / to-be-compared black name supplier information Corresponding word frequency vector. The word frequency vector represents a feature vector of the identified version field / to be compared black name supplier information, and each word frequency in the vector represents a corresponding segmentation contribution to the identified version field / to be compared black name supplier information. degree.

Exemplarily, as described above, the word segmentation sequences corresponding to the black name supplier information A and the identification version field B to be compared are: XX, city, YY, technology, and company limited. The word frequency vector corresponding to the black name supplier information A to be compared is (1,1,1,1,1), and the word frequency vector corresponding to the recognition version field B is (1,0,1,1,1) .

In step S404, the cosine similarity between the word frequency vector corresponding to the black name supplier information to be compared and the word frequency vector corresponding to the recognition version field is calculated.

In the embodiment of the present application, a cosine similarity algorithm (cosine similarity) is used to calculate an angle cosine value between two word frequency vectors to obtain a similarity between the identification version field and the black name supplier information to be compared, thereby The comparison between the identification version field and each black name supplier information in the black list database is converted into calculating the similarity between the two word frequency vectors. It is assumed that the black name supplier information to be compared corresponds to a word frequency vector P, the identification version field corresponds to a word frequency vector Q, and the cosine similarity calculation formula is:

Among them, P _i represents the word frequency corresponding to the i-th participle in the word frequency vector P, Q _i represents the word frequency corresponding to the i-th participle in the word frequency vector Q, and n represents the total number of participles in the word segmentation sequence.

In step S405, the black name supplier information whose cosine similarity is greater than or equal to a preset similarity threshold is acquired.

According to the cosine theorem, when the cosine of the included angle of the two vectors is 1, the value of the included angle θ is 0, indicating that the two word frequency vectors are the same, that is, the identification field and the black name supplier information to be compared. Are the same; the smaller the cosine of the included angle, the greater the value of the included angle θ, the more unrelated the two word frequency vectors; if the cosine of the included angle is 0, it means that the two word frequency vectors are orthogonal, and the included angle θ The value is 90 degrees, and the identification field is not related to the black name supplier information to be compared. In view of this, in the embodiment of the present application, a preset similarity threshold is preset, an error space is reserved, and then the similarity calculated in step S304 is compared with the preset similarity threshold to filter out greater than or equal to the preset similarity. Threshold similarity; the black name supplier information to be compared corresponding to the similarity is recorded as the associated black name supplier information, thereby completing a fuzzy search of the black name supplier information, filtering out the low reference meaning The black name supplier information is beneficial to improve the efficiency and accuracy of the check; and the cosine similarity algorithm effectively avoids that the fields with the same meaning are considered to be dissimilar when the length or order is inconsistent, simple and fast. Speed and accuracy are high.

In an embodiment, as shown in FIG. 5, the black name supplier information associated with the supplier information based on the supplier information described in step S204 performs matching processing using the input version field and the identification version field as fixed phrases, respectively. And generating a verification result based on the black name supplier information obtained by the matching process includes:

In step S501, a first matching process is performed on black name supplier information associated with the input version field and the supplier information, and black name supply associated with the identification version field and the supplier information is performed. The quotient information performs a second matching process.

As described above, the black name supplier information associated with the supplier information is the black name supplier information related to the supplier information on the invoice to be verified, which is obtained through the fuzzy search performed in step S203. In order to further improve the accuracy of the verification, the embodiment of the present application uses multiple matching, and performs a matching process using the input version field and the identification version field as fixed phrases, that is, the input version field is related to the supplier information. The first matching of the black name supplier information is performed to obtain the black name supplier information that is the same as the entry version field; and the black name supplier information that associates the identification version field with the supplier information is performed. The second matching is to obtain the black name supplier information that is the same as the identification version field. Then, a verification result is generated based on the two matchings to improve the accuracy of the matching process and further improve the verification accuracy of the supplier information.

In step S502, if the black name supplier information obtained by the two matching processes, the input version field and the identification version field are all the same, a verification result is generated according to the black name supplier information obtained by the first matching process or the second matching process. .

Here, the embodiment of the present application compares the black name supplier information obtained by the two matching processes; if the black name supplier information obtained by the first matching process is the same as the black name supplier information obtained by the second matching process At the same time, the black name supplier information, the input version field, and the identification version field obtained by the two matching processes are compared. If the black name supplier information, the input version field, and the identification version field obtained by the two matching processing are all compared, The same, it is confirmed that the supplier information on the invoice to be verified belongs to the blacklist, and a verification result is generated. As mentioned earlier, the verification result includes the conclusion of whether it is a blacklist and the name of the blacklist. Here, the verification result may be: the supplier information on the invoice to be verified is a black list, and the name of the black list is XXX (based on the black name supplier information obtained by matching).

In step S503, if the black name supplier information obtained by the two matching processes is not the same, a verification result is generated based on the black name supplier information obtained by the second matching process.

Optionally, if the black name supplier information obtained in the first matching process is different from the black name supplier information obtained in the second matching process, it is confirmed that the supplier information on the invoice to be verified is suspected black List and generate verification results. Here, the verification result may be: the supplier information on the invoice to be verified is a suspected blacklist, and the name of the blacklist is XXX (the black name supplier information obtained by the second match); to inform the user There is a black name supplier similar to the supplier information on the invoice to be verified, and it is confirmed.

Exemplarily, it is assumed that the black name supplier information associated with the supplier includes China XX Technology Co., Ltd., China XX Insurance Co., Ltd., China (XX) Technology Co., Ltd., and the like. In scenario 1, the input version field obtained by manually entering the supplier information is China XX Insurance Co., Ltd., and the identification version field obtained by identifying the supplier information through OCR technology is China XX Insurance Co., Ltd. The black name supplier information obtained from the second matching process is China XX Insurance Co., Ltd., and it is consistent with the entry version field and the identification version field. Then confirm that the supplier information on the invoice to be verified belongs to the black list. Generate a verification result, for example, the supplier information on the invoice to be verified is a blacklist, and the name of the blacklist is China XX Insurance Co., Ltd. In scenario two, the input version field obtained by manually entering the supplier information is China XX Technology Co., Ltd., and the identification version field obtained by identifying the supplier information by OCR technology is China (XX) Technology Co., Ltd. The black name supplier information is China XX Technology Co., Ltd., and the second matching black name supplier information is China Technology Co., Ltd., confirm that the supplier information on the invoice to be verified belongs to a suspected blacklist, and generate a check. As a result, for example, the supplier information on the invoice to be verified is a suspected blacklist, and the name of the blacklist is China Science and Technology Co., Ltd. Please confirm.

The embodiment of the present application improves the accuracy of the matching process by setting a double matching process, thereby improving the accuracy of checking the supplier information.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

In one embodiment, an invoice verification device is provided, and the invoice verification device corresponds to the invoice verification method in the embodiment described above. As shown in FIG. 6, the invoice verification device includes a construction module, an acquisition module, a fuzzy search module, a matching module, and a sending module. The detailed description of each function module is as follows:

A building module 61, configured to build a blacklist library, where the blacklist library includes black name supplier information;

The obtaining module 62 is configured to obtain the supplier information on the invoice to be verified from the verification request when the verification request sent by the client is obtained, where the supplier information includes an identification version field of the supplier and Entry field

A fuzzy search module 63, configured to perform a fuzzy search in a blacklist database through an identification version field to obtain black name supplier information associated with the supplier information;

A matching module 64 is configured to perform matching processing based on the black name supplier information associated with the supplier information, respectively, using the input version field and the identification version field as fixed phrases, and supply the black name based on the matching processing. Business information to generate verification results;

The sending module 65 is configured to send the verification result to the client, so that the client receives and outputs the verification result.

Optionally, the fuzzy search module 63 includes:

A keyword obtaining unit 631, configured to perform word segmentation processing on the identification version field, and obtain keywords in the supplier information according to a result of the word segmentation processing;

The SQL search unit 632 is configured to obtain black name supplier information including the keywords from the black list database based on the SQL language, so as to obtain black name supplier information associated with the supplier information.

Optionally, the fuzzy search module 63 includes:

The word segmentation processing unit 633 is configured to perform word segmentation processing on the identification version field and word segmentation processing on each black name supplier information in the blacklist database;

Word segmentation sequence generating unit 634, for each black name supplier information and identification version field to be compared, according to the result of word segmentation processing, generate a word segmentation sequence corresponding to the black name supplier information and identification version field ;

A word frequency vector generating unit 635, configured to generate a word frequency vector corresponding to the black name supplier information to be compared and a word frequency vector corresponding to a recognition version field according to the word segmentation sequence;

A similarity calculation unit 636, configured to calculate a cosine similarity between the word frequency vector corresponding to the black name supplier information to be compared and the word frequency vector corresponding to the recognition version field;

The obtaining unit 637 is configured to obtain black name supplier information whose cosine similarity is greater than or equal to a preset similarity threshold.

Optionally, the matching module 64 includes:

A matching unit 641, configured to perform a first matching process on the black name supplier information associated with the input version field and the supplier information, and the black name associated with the identification version field and the supplier information Supplier information performs a second matching process;

A first generating unit 642 is configured to generate the black name supplier information, the input version field, and the identification version field obtained by the two matching processes according to the black name supplier information obtained by the first matching process or the second matching process. Verification result

The second generating unit 643 is configured to generate a verification result according to the black name supplier information obtained by the second matching process if the black name supplier information obtained by the two matching processes is different.

Optionally, the building module 61 includes:

A first construction unit 611, configured to obtain black name user information from a preset credit system, and add the black name user information to the black list database as black name supplier information; and / or

The second constructing unit 612 is configured to filter suppliers whose transaction bad debts reach a preset amount threshold and the aging reaches a preset aging threshold according to the transaction bad debt records between related suppliers, and add the information as black name supplier information. To the blacklist library.

Optionally, the building module 61 further includes:

The third constructing unit 613 is used for importing the holding relationship between enterprises; for each black name supplier information in the black list database, obtaining the holding company corresponding to each black name supplier from the holding relationship, The holding company is added to the blacklist database as the black name supplier information.

For the specific limitation of the invoice verification device, please refer to the limitation on the invoice verification method described above, which will not be repeated here. Each module in the above-mentioned invoice verification device may be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the hardware in or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 7. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in a non-volatile storage medium. The database of the computer equipment is used to store black name supplier information and perform operations of adding, deleting, and modifying the black name supplier information on file. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instructions are executed by a processor to implement an invoice verification method.

In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor. When the processor executes the computer-readable instructions, the implementation is as shown in FIG. 2 to FIG. 5 the steps described in any of the embodiments. In one embodiment, a computer-readable storage medium is provided, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor, the steps shown in any one of the embodiments of FIG. 2 to FIG. 5 are implemented. A person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by using computer-readable instructions to instruct related hardware. The computer-readable instructions can be stored in a non-volatile computer. In the readable storage medium, the computer-readable instructions, when executed, may include the processes of the embodiments of the methods described above. Wherein, any reference to the storage, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile storage. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

Those skilled in the art can clearly understand that, for the convenience and brevity of the description, only the above-mentioned division of functional units and modules is used as an example. In practical applications, the above functions can be assigned by different functional units, Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.

The above-mentioned embodiments are only used to describe the technical solution of the present application, but not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still implement the foregoing implementations. The technical solutions described in the examples are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in Within the scope of this application.

Claims

An invoice verification method, comprising:

Building a blacklist library, which includes blackname vendor information;

When the verification request sent by the client is obtained, the supplier information on the invoice to be verified is obtained from the verification request, and the supplier information includes an identification version field and an entry version field of the supplier;

Perform a fuzzy search in the blacklist database through the identification version field to obtain black name supplier information associated with the supplier information;

Based on the black name supplier information associated with the supplier information, the matching process is performed using the input version field and the identification version field as fixed phrases, and a verification result is generated based on the black name supplier information obtained by the matching process. ;

Sending the verification result to the client, so that the client receives and outputs the verification result.
The invoice verification method according to claim 1, wherein the performing a fuzzy search in a blacklist database through the identification version field to obtain the black name supplier information associated with the supplier information comprises:

Perform word segmentation processing on the identification version field, and obtain keywords in the supplier information according to a result of the word segmentation processing;

The black name supplier information including the keywords is acquired from the black list database based on the SQL language to obtain the black name supplier information associated with the supplier information.
The invoice verification method according to claim 1, wherein the performing a fuzzy search in a blacklist database through the identification version field to obtain the black name supplier information associated with the supplier information comprises:

Perform word segmentation processing on the identification version field, and word segmentation processing on each black name supplier information in the black list library;

For each black name supplier information and identification version field to be compared, according to the result of word segmentation processing, generate a word segmentation sequence corresponding to the black name supplier information and identification version field to be compared;

Generating a word frequency vector corresponding to the black name supplier information to be compared and a word frequency vector corresponding to the recognition version field according to the word segmentation sequence;

Calculating the cosine similarity between the word frequency vector corresponding to the black name supplier information to be compared and the word frequency vector corresponding to the recognition version field;

Obtain black name supplier information whose cosine similarity is greater than or equal to a preset similarity threshold.
The invoice verification method according to any one of claims 1 to 3, wherein the black name supplier information associated based on the supplier information uses the entry version field and the identification version field respectively as Performing a matching process on a fixed phrase, and generating a verification result based on the black name supplier information obtained by the matching process includes:

Performing a first matching process on the black name supplier information associated with the input version field and the supplier information, and performing a second match on the black name supplier information associated with the identification version field and the supplier information Matching processing

If the black name supplier information, the input version field, and the identification version field obtained by the two matching processes are all the same, generate a verification result according to the black name supplier information obtained by the first matching process or the second matching process;

If the black name supplier information obtained by the two matching processes is different, a verification result is generated according to the black name supplier information obtained by the second matching process.
The invoice verification method according to claim 1, wherein the constructing a blacklist library comprises:

Obtain black-named user information from a preset credit system, and use the black-named user information as black-name supplier information to add to the blacklist database; and / or

According to the transaction bad debt records between the related suppliers, the suppliers whose transaction bad debts reach the preset amount threshold and the aging reaches the preset aging threshold are selected as black name supplier information and added to the blacklist database.
The invoice verification method according to claim 5, wherein the building a blacklist database further comprises:

Introduce a controlling relationship between enterprises;

For each black name supplier information in the black list database, the holding company corresponding to each black name supplier is obtained from the controlling relationship, and the holding company is added to the black list database as the black name supplier information.
An invoice verification device, characterized in that it includes:

A building module for building a blacklist library that includes blackname vendor information;

An obtaining module, configured to obtain the supplier information on the invoice to be verified from the verification request when the verification request sent by the client is obtained, where the supplier information includes an identification version field of the supplier and an entry Version field

A fuzzy search module, configured to perform a fuzzy search in a blacklist database through an identification version field to obtain black name supplier information associated with the supplier information;

A matching module, configured to perform matching processing using the input version field and the identification version field as fixed phrases based on the black name supplier information associated with the supplier information, and according to the black name supplier obtained by the matching processing Information generation verification results;

A sending module is configured to send the verification result to a client, so that the client receives and outputs the verification result.
The invoice verification device according to claim 7, wherein the fuzzy search module comprises:

A keyword acquisition unit, configured to perform word segmentation processing on the identification version field, and obtain a keyword in the supplier information according to a result of the word segmentation processing;

A SQL search unit is configured to obtain black name supplier information including the keywords from the black list database based on the SQL language to obtain black name supplier information associated with the supplier information.
The invoice verification device according to claim 7 or 8, wherein the matching module comprises:

A matching unit, configured to perform a first matching process on the black name supplier information associated with the entry version field and the supplier information, and provide a black name supply associated with the identification version field and the supplier information Quotient information performs a second matching process;

The first generating unit is configured to generate a calibration according to the black name supplier information obtained by the first matching process or the second matching process if the black name supplier information obtained by the two matching processes, the input version field, and the identification version field are the same Test results

The second generating unit is configured to generate a verification result according to the black name supplier information obtained by the second matching process if the black name supplier information obtained by the two matching processes is different.
The invoice verification device according to claim 7, wherein the building module comprises:

A first construction unit, configured to obtain black name user information from a preset credit system, and add the black name user information as black name supplier information to a black list database; and / or

The second construction unit is used to filter out the suppliers whose transaction bad debts reach the preset amount threshold and the aging reaches the preset aging threshold according to the transaction bad debt records between the associated suppliers, and add them as black name supplier information to Blacklist library.
A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and is characterized in that the processor implements the computer-readable instructions as follows step:

Building a blacklist library, which includes blackname vendor information;

When the verification request sent by the client is obtained, the supplier information on the invoice to be verified is obtained from the verification request, and the supplier information includes an identification version field and an entry version field of the supplier;

Perform a fuzzy search in the blacklist database through the identification version field to obtain black name supplier information associated with the supplier information;

Based on the black name supplier information associated with the supplier information, the matching process is performed using the input version field and the identification version field as fixed phrases, and a verification result is generated based on the black name supplier information obtained by the matching process. ;

Sending the verification result to the client, so that the client receives and outputs the verification result.
The computer device according to claim 11, wherein the performing a fuzzy search in a blacklist database through the identification version field to obtain the black name supplier information associated with the supplier information comprises:

Perform word segmentation processing on the identification version field, and obtain keywords in the supplier information according to a result of the word segmentation processing;

The black name supplier information including the keywords is acquired from the black list database based on the SQL language to obtain the black name supplier information associated with the supplier information.
The computer device according to claim 11 or 12, wherein the black name supplier information associated based on the supplier information performs matching processing using the input version field and the identification version field as fixed phrases, respectively. And generating a verification result based on the black name supplier information obtained by the matching process includes:

Performing a first matching process on the black name supplier information associated with the input version field and the supplier information, and performing a second match on the black name supplier information associated with the identification version field and the supplier information Matching processing

If the black name supplier information, the input version field, and the identification version field obtained by the two matching processes are all the same, generate a verification result according to the black name supplier information obtained by the first matching process or the second matching process;

If the black name supplier information obtained by the two matching processes is not the same, a verification result is generated based on the black name supplier information obtained by the second matching process.
The computer device according to claim 11, wherein the constructing a blacklist library comprises:

Obtain black-named user information from a preset credit system, and use the black-named user information as black-name supplier information to add to the blacklist database; and / or

According to the transaction bad debt records between the related suppliers, the suppliers whose transaction bad debts reach the preset amount threshold and the aging reaches the preset aging threshold are selected as black name supplier information and added to the blacklist database.
The computer device according to claim 14, wherein the constructing a blacklist library further comprises:

Introduce a controlling relationship between enterprises;

For each black name supplier information in the black list database, the holding company corresponding to each black name supplier is obtained from the controlling relationship, and the holding company is added to the black list database as the black name supplier information.
One or more non-volatile readable storage media storing computer readable instructions, characterized in that when the computer readable instructions are executed by one or more processors, the one or more processors are caused to execute The following steps:

Building a blacklist library, which includes blackname vendor information;

When the verification request sent by the client is obtained, the supplier information on the invoice to be verified is obtained from the verification request, and the supplier information includes an identification version field and an entry version field of the supplier;

Perform a fuzzy search in the blacklist database through the identification version field to obtain black name supplier information associated with the supplier information;

Based on the black name supplier information associated with the supplier information, the matching process is performed using the input version field and the identification version field as fixed phrases, and a verification result is generated based on the black name supplier information obtained by the matching process. ;

Sending the verification result to the client, so that the client receives and outputs the verification result.
The non-volatile readable storage medium according to claim 16, wherein the fuzzy search is performed in a blacklist database through the identification version field to obtain black name supplier information associated with the supplier information include:

Perform word segmentation processing on the identification version field, and obtain keywords in the supplier information according to a result of the word segmentation processing;

The black name supplier information including the keywords is acquired from the black list database based on the SQL language to obtain the black name supplier information associated with the supplier information.
The non-volatile readable storage medium according to claim 16 or 17, wherein the black name supplier information associated based on the supplier information includes the entry version field and the identification version field, respectively. Performing a matching process as a fixed phrase, and generating a verification result based on the black name supplier information obtained by the matching process includes:

Performing a first matching process on the black name supplier information associated with the input version field and the supplier information, and performing a second match on the black name supplier information associated with the identification version field and the supplier information Matching processing

If the black name supplier information, the input version field, and the identification version field obtained by the two matching processes are all the same, generate a verification result according to the black name supplier information obtained by the first matching process or the second matching process;

If the black name supplier information obtained by the two matching processes is different, a verification result is generated according to the black name supplier information obtained by the second matching process.
The non-volatile readable storage medium according to claim 16, wherein the constructing a blacklist library comprises:

Obtain black-named user information from a preset credit system, and use the black-named user information as black-name supplier information to add to the blacklist database; and / or

According to the transaction bad debt records between the related suppliers, the suppliers whose transaction bad debts reach the preset amount threshold and the aging reaches the preset aging threshold are selected as black name supplier information and added to the blacklist database.
The non-volatile readable storage medium of claim 19, wherein the constructing a blacklist library further comprises:

Introduce a controlling relationship between enterprises;

For each black name supplier information in the black list database, the holding company corresponding to each black name supplier is obtained from the controlling relationship, and the holding company is added to the black list database as the black name supplier information.