CN115689786A - Financial reimbursement checking method, medium, equipment and system based on industry characteristics - Google Patents

Abstract

The invention relates to a financial reimbursement checking method, medium, equipment and system based on industry characteristics, wherein an industry characteristic library is established, enterprise multidimensional data are extracted, the industry characteristics are matched, a rule table is established, a financial reimbursement system is set based on the rule table, personnel reimbursement data are obtained and reimbursement checking is carried out, and reimbursement behaviors which do not meet requirements are processed; the realization of the medium and the equipment is achieved based on the method; the system comprises a background management unit, a communication unit, an input unit, a primary screening unit, a checking unit and a notification unit, wherein the background management unit establishes a rule table and configures rules, the communication unit updates an industry feature library, the input unit inputs personnel reimbursement data, the primary screening unit performs primary screening on the reimbursement data, the checking unit performs checking based on the configured rules, and the notification unit notifies whether reimbursement checking is passed or not. The invention can not only check and check the validity of the bill, but also can speculate the possibility of the bill being false and screen the bill in doubt; the implementation of the financial reimbursement system of an enterprise and the standardization of the reimbursement system are facilitated, the auditing pressure is reduced, the enterprise compliance is improved, and the enterprise competitiveness is improved.

Description

Financial reimbursement checking method, medium, equipment and system based on industry characteristics

Technical Field

The invention relates to the technical field of mode identification methods or devices, in particular to a financial reimbursement checking method, medium, equipment and system based on industrial characteristics.

Background

The reimbursement is a process of listing the received money or the balance account and reporting the upper-level reimbursement, and is an important link in the operation process of an enterprise. Along with the development of enterprises and the continuous increase of the number of employees, the financial account reporting problem is increasingly highlighted.

Among the prior art, financial reimbursement generally adopts artifical hand to fill out reimbursement or electronic reimbursement, and there is the combination of these two kinds of reimbursement forms certainly, and no matter which all needs financial staff to check the reimbursement document that reimbursement personnel filled in and the validity of checking the bill, still has other problems when whole reimbursement flow is loaded down with trivial details, include:

(1) The method comprises the following steps of (1) making a fake bill, wherein the fake bill is divided into a fake bill and a fake invoice;

(2) The bill is inconsistent with the actual reimbursement content or is in error in detail;

(3) The number of the bills exceeds the rated number of the enterprises;

(4) The ticket may conflict or not match the business's claim of reimbursement allowance.

These problems will actually slow down the financial process, and also present a great risk to the financial staff to review, which may even become a taint in the operation of the enterprise.

Disclosure of Invention

The invention solves the problems in the prior art and provides a financial reimbursement checking method, medium, equipment and system based on industrial characteristics.

The technical scheme adopted by the invention is that the financial reimbursement checking method based on the industry characteristics comprises the following steps:

step 1: establishing an industry feature library based on the big data;

and 2, step: extracting multidimensional data from any enterprise, matching the industry characteristics and establishing a rule table;

and 3, step 3: setting a financial reimbursement system based on the rule table;

and 4, step 4: and acquiring personnel reimbursement data, performing reimbursement checking, and processing the reimbursement behaviors which do not meet the requirements.

Preferably, in the step 1, the industry feature library performs oriented data mining by using compliance enterprises disclosed in big data; the method comprises the steps of integrating public financial reimbursement data of all compliance enterprises in the same industry, merging data with consistency and uniformly marking reference labels, and manually marking characteristic labels on data without consistency.

Preferably, a differentiation model is established based on the industry feature library, the model comprises one or more nodes, any one corresponding node is a cluster of the same industry, and a node label is the reference label;

and establishing a sub-differential tree structure in any node, wherein the sub-differential tree structure comprises one or more sub-nodes, and any sub-node is an enterprise or a cluster of the enterprise corresponding to different feature labels.

Preferably, in the step 2, feature data is extracted from any enterprise, the industry is judged, and a reference label is searched and corresponds to any node;

if the current node has a child node, searching a feature label based on the feature data, and if the current node has the child node, corresponding to the child node;

and searching financial reimbursement data published by the compliance enterprise based on the nodes or the sub-nodes in the industry feature library, and establishing a rule table, wherein the rule table is configured with a plurality of reimbursement item rules.

Preferably, in the step 4, the personnel reimbursement data is obtained, if the personnel reimbursement data is form data and a corresponding bill picture, the personnel reimbursement data is entered for preliminary screening, and if not, the personnel reimbursement data is returned.

Preferably, the reimbursement data prescreening comprises the following steps:

step 4.1: acquiring a bill picture, positioning the correct reading direction of the bill picture based on character recognition software, and preprocessing the bill picture;

step 4.2: respectively searching angular points of the table frame from the original point to the lower right and from the farthest point to the upper left by taking the upper left corner of the bill picture as the original point and the lower right corner of the bill picture as the farthest point, and intercepting the table by taking the first searched angular point as a reference; if the form frame is not identified, directly performing the step 4.5;

step 4.3: intercepting intersection points in the table, wherein any intersection point comprises extension lines in multiple directions, and dividing the picture based on the intersection points to obtain one or more classified pictures;

step 4.4: reading information of each classified picture to obtain information of an invoicer and information of a collector, carrying out the next step based on the information obtained by all the classified pictures after checking is accurate, and returning if not;

step 4.5: reading verification information of a bill picture, wherein the verification information comprises an invoice number, a billing date, seal information and region information;

step 4.6: and establishing a table of all read information in the bill picture, carrying out fuzzy matching with the form data, if the information is matched with the form data, primarily screening the reimbursement data, and if the information is not matched with the form data, ending reimbursement checking and returning.

Preferably, the bill which is screened primarily through reimbursement data is subjected to compliance examination with a financial reimbursement system set based on a rule table, and if the bill passes the reimbursement examination, the bill is notified of the unqualified reimbursement behavior.

A computer-readable storage medium having stored thereon an industry-feature-based financial reimbursement checking program that, when executed by a processor, implements the above-described industry-feature-based financial reimbursement checking method.

A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above financial reimbursement checking method based on industry features.

An industry-feature based financial reimbursement verification system, the system comprising:

a background management unit for establishing a rule table and configuring rules;

the communication unit is used for updating the industry feature library;

the input unit is used for inputting personnel reimbursement data;

the primary screening unit is used for carrying out primary screening on reimbursement data of the input personnel reimbursement data;

the checking unit is used for checking the reimbursement information passing the primary screening based on the configured rule;

and the notification unit is used for notifying whether the reimbursement check is passed or not.

The invention relates to a financial reimbursement checking method, medium, equipment and system based on industry characteristics, wherein an industry characteristic library is established based on big data, multidimensional data are extracted from any enterprise, the industry characteristics are matched, a rule table is established, a financial reimbursement system is set based on the rule table, personnel reimbursement data are obtained, reimbursement checking is carried out, and reimbursement behaviors which do not meet requirements are processed; the realization of the medium and the device is achieved based on the method; the system based on the method comprises the steps that a background management unit establishes a rule table and carries out rule configuration, a communication unit updates an industry feature library, an input unit inputs personnel reimbursement data, a primary screening unit carries out primary screening on the input personnel reimbursement data, a checking unit checks reimbursement information passing the primary screening based on a configured rule, and a notification unit notifies whether reimbursement checking is passed or not.

The invention has the advantages that the invention can carry out reimbursement check through the system regardless of manual reimbursement or electronic reimbursement currently, can not only check and check the validity of the bills, but also can conjecture the possibility of the bills being false, and screen out the bills which are not in accordance with the actual reimbursement content or have detail errors, the number of the bills exceeds the rated number of the enterprise, and the bills conflict or mismatch with the items allowed to reimburse by the enterprise; through the screening to these bills, be favorable to enterprise's financial reimbursement system's implementation, the standard of reimbursement system, reduce enterprise's financial staff's pressure of examining and examining simultaneously by a wide margin, promote enterprise's compliance, be favorable to promoting enterprise competitiveness.

Drawings

FIG. 1 is a flow chart of the method of the present invention;

FIG. 2 is a flow chart of the reimbursement data prescreening process of the present invention;

FIG. 3 is a schematic diagram of a reimbursement data prescreening method according to the present invention;

fig. 4 is a schematic diagram of the system structure of the present invention, and the arrow indicates the direction of data or information transmission.

Detailed Description

The present invention is described in further detail with reference to the following examples, but the scope of the present invention is not limited thereto.

As shown in FIG. 1, the invention relates to a financial reimbursement checking method based on industry characteristics, comprising the following steps:

step 1: establishing an industry feature library based on the big data;

in the step 1, the industry feature library carries out directional data mining by compliant enterprises disclosed in big data; the method comprises the steps of integrating public financial reimbursement data of all compliance enterprises in the same industry, merging data with consistency and uniformly marking reference labels, and manually marking characteristic labels on data without consistency.

Establishing a differential model based on the industry feature library, wherein the model comprises one or more nodes, any one corresponding node is a cluster of the same industry, and a node label is the reference label;

a sub-differential tree structure is built in any node, the sub-differential tree structure comprises one or more sub-nodes, and any sub-node corresponds to enterprises with different feature labels or clusters of the enterprises.

In the invention, the industry feature library carries out directional data mining by compliance enterprises disclosed in big data, ensures that the data corresponding to each industry is forward data, and has guiding significance and value; on the premise, the financial reimbursement data of the official business of all compliance enterprises in the same industry are integrated, the data with consistency are merged and uniformly labeled with reference labels, for example, the industry directly identified by a local management department (directly associated with bills), and the data without consistency are labeled with artificial characteristic labels, for example, the service industry needs to be divided into technical service, labor service and the like; and establishing a differential model on the basis, wherein the differential model comprises one or more nodes, a sub-differential tree structure is established under each node, the nodes correspond to industries, and the sub-nodes correspond to enterprises with different characteristics under each industry.

In the invention, the differential model is a decentralized structure, the sub-differential tree structure is a tree structure, and the father node is a node in the differential model.

In the invention, after the industry feature library is established, some illegal issuing enterprises can be marked and set with warnings, and on the premise, if the issuing party of the ticket is the marked enterprises, the illegal issuing enterprises are directly regarded as unqualified reimbursement behaviors and are processed.

Step 2: extracting multidimensional data from any enterprise, matching the industry characteristics and establishing a rule table;

in the step 2, extracting characteristic data of any enterprise, judging the industry to which the enterprise belongs, searching a reference label and corresponding to any node;

if the current node has a child node, searching a feature label based on the feature data, and if the current node has the child node, corresponding to the child node;

and searching financial reimbursement data published by the compliance enterprise based on the nodes or the sub-nodes in the industry feature library, and establishing a rule table, wherein the rule table is configured with a plurality of reimbursement item rules.

And step 3: and setting a financial reimbursement system based on the rule table.

In the invention, characteristic data is extracted from an enterprise, the characteristic data comprises but is not limited to industrial and commercial record information, keywords can be extracted from the record information so as to judge the industry to which the characteristic data belongs, and a benchmark tag is searched through the industry and corresponds to a node.

In the invention, after the nodes are corresponded, all characteristics of the industry corresponding to the current nodes are obtained, in order to better obtain the characteristics, whether the current nodes have child nodes or not needs to be judged, the characteristic labels are searched based on the characteristic data, and if the current nodes have child nodes, the current nodes correspond to the child nodes.

In the invention, after the judgment of the industry is finished, the financial reimbursement data corresponding to the compliance enterprise public notice can be based on the node or the sub-node, and a rule table configured with reimbursement item rules is established through the data; the rule table can extract reimbursement data of a compliance enterprise, realize output of the formatted rule table through remote control of a tax department, and set an alarm value.

And 4, step 4: and acquiring personnel reimbursement data, performing reimbursement checking, and processing the reimbursement behaviors which do not meet the requirements.

In the step 4, personnel reimbursement data is obtained, if the personnel reimbursement data are form data and corresponding bill pictures, the personnel reimbursement data are screened for the first time, and if not, the personnel reimbursement data are returned.

As shown in fig. 2, the reimbursement data prescreening includes the following steps:

step 4.1: acquiring a bill picture, positioning the correct reading direction of the bill picture based on character recognition software, and preprocessing the bill picture;

step 4.2: respectively searching angular points of the table frame from the original point to the lower right and from the farthest point to the upper left by taking the upper left corner of the bill picture as the original point and the lower right corner of the bill picture as the farthest point, and intercepting the table by taking the respectively searched first angular point as a reference; if the form frame is not identified, directly performing the step 4.5;

step 4.3: intercepting intersection points in the table, wherein any intersection point comprises extension lines in multiple directions, and dividing the picture based on the intersection points to obtain one or more classified pictures;

step 4.4: reading information of each classified picture to obtain invoicer information and invoicer information, performing the next step based on the information obtained by all classified pictures after checking is accurate, and returning if not;

step 4.5: reading verification information of a bill picture, wherein the verification information comprises an invoice number, a billing date, seal information and region information;

step 4.6: and establishing a table of all read information in the bill picture, carrying out fuzzy matching with the form data, if the information is matched with the form data, primarily screening the reimbursement data, and if the information is not matched with the form data, ending reimbursement checking and returning.

In the invention, the personnel reimbursement data is pre-checked, generally, a simple form can be provided for filling data, which is a content easily understood by the technical personnel in the field, and the technical personnel in the field can continuously need to realize on platforms such as small programs, nails and the like; however, if the personnel reimbursement data only includes form data, the personnel reimbursement data does not accord with reimbursement regulations, and the personnel reimbursement data enters into the initial screening of reimbursement data by matching with corresponding bill pictures.

In the invention, for obtaining the bill picture, based on the character recognition software, the correct reading direction of the bill picture is positioned, and the bill picture is preprocessed, including but not limited to adjusting the bill picture according to the public length-width ratio; here, it is necessary to separately distinguish partial toll invoices, and in general, the toll invoices have characteristics different from those of a common invoice, such as a large difference in aspect ratio.

In the invention, the bill generally has a table structure, and if the bill does not have the table structure, other information is directly read; for the bill with a table structure, firstly, the table is cut out independently, more intersection points often exist in the table of the bill, namely, a sub-table frame in the table, and the intersection points can be used for dividing pictures (at least 3 intersection points) to obtain classified pictures; as shown in fig. 3, information including, but not limited to, the name of the purchaser, taxpayer identification number, address, phone, account number, and the like, such as the name of goods or taxed labor, service, and the like, may be obtained, and based on these classified pictures, the information of the invoicing party and the information of the collection party may be obtained; the existing bill format may change continuously with the regularization and generalization of bills, but the reading of the method extracts sub-form frames in sequence, so the read information has continuity in general.

Firstly, checking whether an invoice collector is an enterprise main body and whether an invoice issuer is consistent with form data, and acquiring information acquired by all classified pictures after confirming that the invoice collector is correct, wherein the information is the first part of information; and then, reading the verification information of the bill picture, including but not limited to the invoice number, the invoicing date, the seal information and the region information, and also reading direct identification such as a two-dimensional code and the like as the information of the second part.

In the invention, the information of the first part and the information of the second part are tabulated and are subjected to fuzzy matching with form data, and if the first part and the second part are matched, the report data is primarily screened; the fuzzy matching means that, for example, when the business trip time in the current personnel reimbursement data is 2 days, the business trip area is A, and the lodging bills exist in the bill information of the table and the address of the invoicing party is A, the fuzzy matching is satisfied; for example, if the business trip time in the current personnel reimbursement data is 1 day, the business trip area is the local area, and the lodging bills exist in the bill information of the building table, fuzzy matching cannot be met, reimbursement verification is finished, and reimbursement personnel are required to modify the content.

And for the bill which passes the primary screening of reimbursement data, carrying out compliance examination on the bill and a financial reimbursement system set based on the rule table, and if the bill passes reimbursement verification, otherwise, notifying the reimbursement behavior which does not meet the requirements.

In the invention, for the bill passing through the primary screening, compliance examination needs to be carried out again through a financial reimbursement system; the compliance examination includes whether the violation banquet is present, the bill is a fake bill, the false invoice is suspected, the reimbursement amount of the bill item exceeds the rated amount of the enterprise, the bill item conflicts with or does not match the items allowed to be reimbursed by the enterprise, even if the invoker is a blacklist enterprise in the tax system, and the declaration behavior which is not in accordance with the requirement is notified.

The present invention also relates to a computer-readable storage medium having stored thereon an industry-trait-based financial reimbursement checking program that, when executed by a processor, implements the above-described industry-trait-based financial reimbursement checking method.

The invention also relates to a computer device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the financial reimbursement checking method based on the industry characteristics.

In order to realize the content, the invention also provides a computer readable storage medium and computer equipment, which realize the efficient audit of the historical medical insurance fund data and the effective alarm of the newly entered medical insurance fund data.

As shown in fig. 4, the present invention also relates to a financial reimbursement checking system based on industry features, the system comprising:

the background management unit is used for establishing a rule table and carrying out rule configuration;

the communication unit is used for updating the industry feature library;

the input unit is used for inputting personnel reimbursement data;

the primary screening unit is used for carrying out primary screening on reimbursement data of the input personnel reimbursement data;

the checking unit is used for checking the reimbursement information passing through the primary screening based on the configured rule;

and the notification unit is used for notifying whether the reimbursement check is passed or not.

In the invention, an application example is provided;

an enterprise inputs basic enterprise information into a background management unit, the background management unit extracts characteristic data, industry matching is carried out, financial reimbursement data published by a compliance enterprise is searched based on nodes or sub-nodes, a rule table is established, and a plurality of reimbursement item rules are configured in the rule table;

when the reimbursement items are processed each time, the background management unit is accessed to the Internet through the communication unit to update the industry feature library, particularly to obtain blacklist enterprises;

the reimbursement personnel input personnel reimbursement data through the input unit;

the primary screening unit performs primary screening on reimbursement data of the entered personnel by using a reimbursement data primary screening method, and returns reimbursement affairs which obviously do not meet the requirements;

the checking unit checks the reimbursement information primarily screened by the primary screening unit based on the configured rules, and the checking is associated with the industry feature library;

for the reimbursement items failed by the primary screening unit and/or the checking unit, the notification unit notifies that the information should be given if necessary, such as obviously submitting false bills.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. A financial reimbursement checking method based on industry characteristics is characterized by comprising the following steps: the method comprises the following steps:

step 1: establishing an industry feature library based on big data;

step 2: extracting multi-dimensional data from any enterprise, matching industrial characteristics and establishing a rule table;

and step 3: setting a financial reimbursement system based on the rule table;

and 4, step 4: and acquiring personnel reimbursement data, performing reimbursement check, and processing the reimbursement behaviors which do not meet the requirements.

2. The financial reimbursement checking method based on industry features of claim 1, wherein: in the step 1, the industry feature library carries out directional data mining by compliant enterprises disclosed in big data; the method comprises the steps of integrating public financial reimbursement data of all compliance enterprises in the same industry, merging data with consistency and uniformly marking reference labels, and manually marking characteristic labels on data without consistency.

3. An industry feature based financial reimbursement verification method according to claim 2, further comprising: establishing a differential model based on the industry feature library, wherein the model comprises one or more nodes, any one corresponding node is a cluster of the same industry, and a node label is the reference label;

a sub-differential tree structure is built in any node, the sub-differential tree structure comprises one or more sub-nodes, and any sub-node corresponds to enterprises with different feature labels or clusters of the enterprises.

4. An industry feature based financial reimbursement verification method according to claim 3 and wherein: in the step 2, feature data is extracted from any enterprise, the industry is judged, and a reference label is searched and corresponds to any node;

if the current node has a child node, searching a feature label based on the feature data, and if the current node has the child node, corresponding to the child node;

and searching financial reimbursement data published by the compliance enterprise based on the nodes or the sub-nodes in the industry feature library, and establishing a rule table, wherein the rule table is configured with a plurality of reimbursement item rules.

5. The method of claim 1, wherein the method comprises: in the step 4, personnel reimbursement data is obtained, if the personnel reimbursement data are form data and corresponding bill pictures, the personnel reimbursement data are screened for the first time, and if not, the personnel reimbursement data are returned.

6. The financial reimbursement checking method based on industry features of claim 5, wherein: the reimbursement data primary screening method comprises the following steps:

step 4.1: acquiring a bill picture, positioning the correct reading direction of the bill picture based on character recognition software, and preprocessing the bill picture;

step 4.2: respectively searching angular points of the table frame from the original point to the lower right and from the farthest point to the upper left by taking the upper left corner of the bill picture as the original point and the lower right corner of the bill picture as the farthest point, and intercepting the table by taking the respectively searched first angular point as a reference; if the form frame is not identified, directly performing the step 4.5;

step 4.3: intercepting intersection points in the table, wherein any intersection point comprises extension lines in multiple directions, and segmenting the picture based on the intersection points to obtain one or more classified pictures;

step 4.4: reading information of each classified picture to obtain information of an invoicer and information of a collector, carrying out the next step based on the information obtained by all the classified pictures after checking is accurate, and returning if not;

step 4.5: reading verification information of a bill picture, wherein the verification information comprises an invoice number, a billing date, seal information and region information;

step 4.6: and establishing a table of all read information in the bill picture, carrying out fuzzy matching with the form data, if the information is matched with the form data, primarily screening the reimbursement data, and if the information is not matched with the form data, ending reimbursement checking and returning.

7. An industry feature based financial reimbursement verification method according to claim 6, further comprising: and for the bill which passes the primary screening of reimbursement data, carrying out compliance examination on the bill and a financial reimbursement system set based on the rule table, and if the bill passes reimbursement verification, otherwise, notifying the reimbursement behavior which does not meet the requirements.

8. A computer-readable storage medium, characterized in that: the financial reimbursement checking program comprises an industrial characteristic-based financial reimbursement checking program stored on the computer readable medium, and the program is executed by a processor to realize the above-mentioned industrial characteristic-based financial reimbursement checking method.

9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein: when the processor executes the program, the financial reimbursement checking method based on the industry characteristics is realized.

10. The utility model provides a financial reimbursement checking system based on trade characteristics which characterized in that: the system comprises:

a background management unit for establishing a rule table and configuring rules;

the communication unit is used for updating the industry feature library;

the input unit is used for inputting personnel reimbursement data;

the primary screening unit is used for carrying out primary screening on reimbursement data of the input personnel reimbursement data;

the checking unit is used for checking the reimbursement information passing the primary screening based on the configured rule;

and the notification unit is used for notifying whether the reimbursement check is passed or not.

Images