CN110728566B - Data processing method and device in reimbursement file, computer equipment and storage medium - Google Patents
Data processing method and device in reimbursement file, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110728566B CN110728566B CN201910876220.3A CN201910876220A CN110728566B CN 110728566 B CN110728566 B CN 110728566B CN 201910876220 A CN201910876220 A CN 201910876220A CN 110728566 B CN110728566 B CN 110728566B
- Authority
- CN
- China
- Prior art keywords
- sum
- bill
- processed
- reimbursement
- amount
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a data processing method, a device, computer equipment and a storage medium in the reimbursement file, wherein the method comprises the following steps: the method comprises the steps of obtaining documents to be processed and various documents to be processed corresponding to the documents to be processed, extracting total amount of the documents in the documents to be processed and total amount of the documents in the documents to be processed, obtaining digital fuzzy documents in the documents to be processed when the sum of the total amount of the documents is different from the total amount of the documents, obtaining a similar amount set corresponding to the total amount of the documents of the digital fuzzy documents, and iteratively updating the total amount of the documents of the digital fuzzy documents until the updated sum of the total amount of the documents is the same as the total amount of the documents. In the whole process, fuzzy recognition is carried out on the amount numbers which cannot be clearly recognized in the reimbursement file according to the rule that the total amount in the document is equal to the sum of the subentry amounts in each bill to be processed, the amount numbers are iteratively updated according to the similar amount sets corresponding to the fuzzy recognition results, and finally data processing in the reimbursement file is accurately and efficiently completed.
Description
Technical Field
The present application relates to the field of bill management technologies, and in particular, to a method and an apparatus for processing data in a reimbursement file, a computer device, and a storage medium.
Background
Reimbursement management is becoming more and more important as an important component of enterprise (organization) management.
The conventional reimbursement management adopts the mode that information such as pictures, money amount and characters of bills and receipts are manually input into an reimbursement management system, the reimbursement management system can simply collect and count the data and then manually check the data, or the reimbursement management system automatically identifies the data and runs based on pre-programmed software to obtain a data processing result in an reimbursement file, and the data processing result can be directly similar results such as the approval of reimbursement money amount, the approval of an reimbursement process and the like.
Although the mode can realize reimbursement management, the premise is that data related to the amount of money on the reimbursement file is clear, and in the face of the situation that data of a part of the amount of money in the reimbursement file is not clear, the amount of money cannot be accurately recorded into the reimbursement management system, so that the reimbursement file cannot be accurately processed by the scheme.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for processing data in an accurate reimbursement file.
A method of processing data in a reimbursement file, the method comprising:
acquiring a document to be processed and various documents to be processed corresponding to the document to be processed;
extracting the total bill sum in the bills to be processed and the bill sum in each bill to be processed;
when the sum of the bills is different from the total sum of the bills, acquiring digital fuzzy bills in the bills to be processed;
carrying out image recognition on the digital fuzzy bill to obtain a similar sum set corresponding to the bill sum of the digital fuzzy bill;
and sequentially selecting the sum of the similar sum set, and iteratively updating the bill sum of the digital fuzzy bills until the updated sum of the bill sums is the same as the total bill sum.
In one embodiment, the sequentially selecting the amounts in the similar amount set, and iteratively updating the bill amounts of the digital fuzzy bills until the sum of the updated bill amounts is the same as the total amount of the bills, further includes:
extracting keywords carried by the digital fuzzy bill, wherein the keywords comprise bill type keywords and address keywords;
inquiring a verification amount set corresponding to the keyword;
sequentially selecting the sum of the similar sum of money in the set, and iteratively updating the bill sum of the digital fuzzy bill until the updated sum of the bill sum is the same as the total bill sum, wherein the step of iteratively updating the bill sum comprises the following steps:
sequentially selecting the amount in the similar amount set, iteratively updating the bill amount of the digital fuzzy bill until the sum of the updated bill amounts is the same as the total amount of the bills, and recording the amount correspondingly selected when iteration is stopped;
outputting a value check result when the recorded value belongs to a subset of the verification value set.
In one embodiment, querying the set of verification amounts corresponding to the keyword comprises:
sending a query request carrying the keyword to a third-party database, and querying the amount by the third-party database according to the keyword to obtain a verification amount set;
and receiving the verification amount set fed back by the third-party database.
In one embodiment, when the sum of the bills is different from the total sum of the bills, acquiring the digital fuzzy bill in the to-be-processed bill comprises the following steps:
when the sum of the bill sum is different from the total bill sum, checking the bill sums one by one;
when the number in each bill to be processed is unclear, classifying the recognized unclear number into a fuzzy recognition number set;
and searching the bill to be processed to which each digit in the fuzzy recognition digit set belongs to obtain a digital fuzzy bill.
In one embodiment, the data processing method in the reimbursement file further includes:
and when the number in the bill to be processed is clear and the bill sum is matched with the gold amount in the bill to be processed, feeding back a finishing message of sum matching in the reimbursement file.
In one embodiment, when the sum of the bill amounts is different from the total bill amount, the checking the bill amounts one by one includes:
and when the sum of the bill sum is different from the total bill sum, checking whether the decimal point position identification error exists in the bill sum.
In one embodiment, the data processing in the reimbursement file further includes:
identifying the identity of the reimburser corresponding to the reimbursement file;
inquiring the reimbursement grade corresponding to the identity of the reimbursement personnel;
acquiring a subentry amount reimbursement threshold value and a total amount reimbursement threshold value corresponding to the reimbursement grade;
and performing reimbursement verification according to the updated sum of each bill, the total sum of the bills, the acquired itemized sum reimbursement threshold value and the acquired total sum reimbursement threshold value.
An apparatus for processing data in a reimbursement file, the apparatus comprising:
the acquiring module is used for acquiring the bills to be processed and the bills to be processed corresponding to the bills to be processed;
the extraction module is used for extracting the total bill sum in the bills to be processed and the bill sum in each bill to be processed;
the fuzzy identification module is used for acquiring digital fuzzy bills in the bills to be processed when the sum of the bills is different from the total sum of the bills;
the fuzzy processing module is used for carrying out image recognition on the digital fuzzy bill to obtain a similar amount set corresponding to the bill amount of the digital fuzzy bill;
and the iteration updating module is used for sequentially selecting the sum of the similar sum set and iteratively updating the bill sum of the digital fuzzy bill until the sum of the updated bill sums is the same as the total bill sum.
A computer device comprising a memory storing a computer program and a processor executing the computer program with the steps of the method as described above.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method as described above.
The data processing method, the device, the computer equipment and the storage medium in the reimbursement file acquire the documents to be processed and the bills to be processed corresponding to the documents to be processed, extract the total sum of the documents in the documents to be processed and the sum of the bills in the documents to be processed, acquire the digital fuzzy bills in the bills to be processed when the sum of the sums of the bills is different from the total sum of the documents, acquire the similar sum set corresponding to the sum of the bills of the digital fuzzy bills, and iteratively update the sum of the bills of the digital fuzzy bills until the updated sum of the sums of the bills is the same as the total sum of the documents. In the whole process, fuzzy recognition is carried out on the amount numbers which cannot be clearly recognized in the reimbursement file according to the rule that the total amount in the document is equal to the sum of the subentry amounts in each bill to be processed, the amount numbers are iteratively updated according to the similar amount sets corresponding to the fuzzy recognition results, and finally data processing in the reimbursement file is accurately and efficiently completed.
Drawings
FIG. 1 is a diagram of an application environment for a method for processing data in an reimbursement file in one embodiment;
FIG. 2 is a flow diagram that illustrates a method for processing data in an reimbursement file, according to one embodiment;
FIG. 3 is a flowchart illustrating a method for processing data in an reimbursement file in another embodiment;
FIG. 4 is a flow chart illustrating a method for processing data in an reimbursement file in one example of an application;
FIG. 5 is a block diagram of a data processing apparatus in an reimbursement file in one embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The data processing method in the reimbursement file can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 uploads an reimbursement file to the server 104, wherein the reimbursement file specifically comprises bills and bills, the server 104 acquires the bills to be processed and the bills to be processed corresponding to the bills to be processed, extracts the total amount of the bills in the bills to be processed and the amount of the bills in the bills to be processed, acquires the digital fuzzy bills in the bills to be processed when the sum of the amounts of the bills is different from the total amount of the bills, acquires a similar amount set corresponding to the amount of the bills of the digital fuzzy bills, iteratively updates the amount of the bills of the digital fuzzy bills until the updated sum of the amounts of the bills is the same as the total amount of the bills, the server 104 can sum up the finally updated amounts of the bills according to the types of the bills to obtain the amounts of the branches, pushes the amounts of the branches, the names thereof and the total amount to the terminal 102, and displays the amounts of the branches to the user by the terminal 102. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a method for processing data in an reimbursement file is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
s100: and acquiring the bills to be processed and the bills to be processed corresponding to the bills to be processed.
The reimbursement documents include tickets and vouchers, which include invoices, entrance tickets, airline tickets, bus tickets, and the like. The bills carry corresponding amount numbers, and the bills also carry keywords of the types, such as service bills, catering bills, tickets and the like, and may also carry address keywords, which are commonly found on the tickets, air tickets and the like, such as Beijing-Wuhan second-class seat high-speed railway tickets, on which the amount numbers 585 Yuan, the type keywords 'high-speed second-class seat tickets' and the address keywords 'Beijing' and 'Wuhan' are carried. The bill is the bill filled by the reimburser, the sum of money on the bill is matched with the sum of money on the bill under normal conditions, and the reimburser audits the bill and the bill data given by the reimburser. Here, the amount in the reimbursement file is preferentially paid attention for the subsequent amount audit. Generally, the reimbursement files can be uploaded to a server in a picture form, a user can take pictures of bills and upload the pictures of the bills and the bills to the server through a terminal, the server can identify the reimbursement files in the picture form to obtain the amount data carried in the files, and particularly, the amount of money can be identified based on an optical character identification technology.
S200: and extracting the total amount of the bills in the bills to be processed and the amount of the bills in each bill to be processed.
In general, a pending document corresponds to a plurality of pending notes, as an offer may involve a plurality or types of notes. The total amount and the total reimbursement amount corresponding to the reimbursement event of this time are filled in the bill, the bill to be processed also carries the bill amount of each bill, for example, in a certain business trip expense reimbursement event, the business trip reimbursement bill is filled with 1000 yuan, the bill to be processed comprises 500 yuan of train tickets, 100 yuan of taxi tickets, 200 yuan of lodging and 200 yuan of catering, and the step is to identify the 1000 yuan, 500 yuan, 100 yuan, 200 yuan and 200 yuan.
S300: and when the sum of the bill sum is different from the total bill sum, acquiring the digital fuzzy bill in each bill to be processed.
Normally, the sum of the sub-amounts of the bills in the reimbursement document should be equal to the total amount of the bills, if there is inequality, it may be that the number of the partial amount identified in step S200 is obtained by fuzzy identification, and at this time, the fuzzy-identified digital fuzzy bill needs to be searched. Taking the example that the reimbursement file uploaded by the first customer comprises a ticket, an accommodation invoice, a catering invoice, an entrance ticket and a receipt, the server executes the step S200 to identify and obtain the ticket 200, the accommodation invoice 200, the catering invoice 100 and the entrance ticket 50, the total amount recorded in the receipt is 560 yuan, the total amount is unequal to the sum of the ticket 200, the accommodation invoice 200, the catering invoice 100 and the entrance ticket 50, the server searches for the reimbursement file to which fuzzy identification numbers belong in the reimbursement file, the step S200 is specifically searched for executing fuzzy identification on the number identification in the entrance ticket, and the searched digital fuzzy bill is the entrance ticket.
S400: and carrying out image recognition on the digital fuzzy bill to obtain a similar sum set corresponding to the bill sum of the digital fuzzy bill.
And (5) carrying out image recognition algorithm processing on the digital fuzzy bill obtained in the step (S400) to obtain a similar number set corresponding to all possible fuzzy recognition numbers. In short, like numbers are grouped to include all possible numbers for ambiguous recognition. Continuing with the case of the user a as an example, the server performs fuzzy recognition on the uploaded entrance ticket picture, and the server preferably selects the number 50 obtained by the fuzzy recognition, so that the amount of the number obtained in step S200 is 50 yuan, and when the sum of the itemized amounts is found to be inconsistent with the total amount in step S400, the server finds the entrance ticket picture again, performs image recognition algorithm processing on the entrance ticket picture to obtain possibly similar numbers such as 0, 50, 60, 30, 90, 40 and the like, and the similar numbers form a similar number set. The image recognition algorithm may specifically include, but is not limited to, GAN (generic adaptive Network, generating countermeasure Network), GNN (graph Neural Network), RNN (Recurrent Neural Network), and other algorithms.
S500: and sequentially selecting the sum of the similar sum set, and iteratively updating the bill sum of the digital fuzzy bill until the sum of the updated bill sum is the same as the total bill sum.
And (4) randomly selecting different numbers from the similar amount set obtained in the step (S400) to iteratively update the amount numbers until the sum of the updated bill amounts is the same as the total amount of the bill, which indicates that the currently selected number is the number which needs to be accurately recorded. Continuing with the above example, after several iterations, the server finds that when the sum of the bills is equal to the total amount at 60, i.e. the currently identified amount number is correct, and the server can continue to check whether the amounts of the bills and the reimbursement document match and check to obtain an amount check result. Optionally, the server may further perform other reimbursement auditing items, such as reimbursement personnel identity auditing, reimbursement level auditing corresponding to reimbursement personnel identity, reimbursement authority auditing, reimbursement amount auditing at corresponding levels, reimbursement period auditing, and so on.
The data processing method in the reimbursement file comprises the steps of obtaining documents to be processed and all documents to be processed corresponding to the documents to be processed, extracting total sum of the documents in the documents to be processed and sum of the documents in the documents to be processed, obtaining digital fuzzy documents in the documents to be processed when sum of the documents is different from the total sum of the documents, obtaining a similar sum set corresponding to the sum of the documents of the digital fuzzy documents, and iteratively updating the sum of the documents of the digital fuzzy documents until the sum of the updated sum of the documents is the same as the total sum of the documents. In the whole process, fuzzy recognition is carried out on the amount numbers which cannot be clearly recognized in the reimbursement file according to the rule that the total amount in the document is equal to the sum of the subentry amounts in each bill to be processed, the amount numbers are iteratively updated according to the similar amount sets corresponding to the fuzzy recognition results, and finally data processing in the reimbursement file is accurately and efficiently completed.
As shown in fig. 3, in one embodiment, step S500 further includes:
s420: and extracting keywords carried by the digital fuzzy bill, wherein the keywords comprise bill type keywords and address keywords.
S440: and inquiring a verification amount set corresponding to the keyword.
Step S500 includes:
s520: and sequentially selecting the sum of the similar sum set, iteratively updating the bill sum of the digital fuzzy bill until the sum of the updated bill sum is the same as the total bill sum, and recording the correspondingly selected sum when the iteration is stopped.
S540: when the recorded amount belongs to a subset of the set of verified amounts, the amount check result is output.
The keywords comprise a bill type keyword and an address keyword, the bill type keyword is used for representing a bill type and specifically comprises a ticket, an air ticket, an accommodation, a meal and the like, and the address keyword comprises an origin and a destination on the ticket, the origin and the destination on the air ticket and the like. The server inquires a verification amount number set corresponding to the keywords, the server specifically inquires the verification amount number set by accessing the Internet and a third-party database, for example, the acquired keywords comprise a bill type keyword, a high-speed railway ticket and the like, and an address keyword, Beijing-Wuhan, the server can access a 12306 website to inquire to acquire the corresponding amount number which is 585 yuan, in addition, a possible discount condition exists, other amount numbers can also be provided, the discount condition can also acquire corresponding information after accessing the 12306 website, and the acquired amount numbers form the verification amount number set. And verifying whether the number obtained based on the keyword is accurate or not by carrying the number in the number set of the verified amount, and when the number recorded in the iterative update belongs to the subset of the number set of the verified amount, indicating that the amount number for fuzzy identification is correct at present, and continuing to perform the next verification processing to obtain an amount checking result. In this embodiment, on the basis of the digital scheme obtained by the previous iterative update, a verification amount digital set is obtained by means of keyword query to verify the correctness of the numbers obtained by iterative update, so that the accuracy of amount digital identification and subsequent amount audit in the reimbursement file is further improved.
In one embodiment, querying the verified amount number set corresponding to the keyword comprises:
and sending a query request carrying the keywords to a third-party database, and querying the amount by the third-party database according to the keywords to obtain a verification amount set.
The server can establish connection between the third-party databases and send a query request to the third-party databases, the third-party databases extract keywords carried in the query request when receiving the query request, possible money is obtained based on the keywords, a verification money set is constructed and fed back to the server.
In one embodiment, when the sum of the bill sum is different from the total bill sum, acquiring the digital fuzzy bill in the to-be-processed bill comprises the following steps:
when the sum of the bill sum is different from the total bill sum, checking the bill sums one by one; when the number in each bill to be processed is unclear, classifying the recognized unclear number into a fuzzy recognition number set; and searching the bill to be processed to which each digit in the fuzzy recognition digit set belongs to obtain the digital fuzzy bill.
When the server obtains the sum of the sub-sum of the bills and the total sum of the bills, the server detects whether the sum of the sub-sum of the bills and the total sum of the bills are equal, if the sum of the sub-sum of the bills and the total sum of the bills are not equal, the sum of the bills is indicated to be abnormal, the sum of the bills is further checked one by one, unclear numbers in the sum are collected into a fuzzy recognition number set, a bill to be processed to which each number in the fuzzy recognition number set belongs is searched, and the digital fuzzy bill is obtained. If the number in the reimbursement file is clear and the bill in the reimbursement file is matched with the bill amount, feeding back a message for ending the matching of the bill amount in the reimbursement file.
In one embodiment, when the sum of the sub-amounts in the amount number is not equal to the total amount, checking the numbers in the reimbursement file one by one includes:
when the sum of the bill sum is different from the total bill sum, checking whether the bill sum has a decimal point position identification error.
The presence of a decimal point position recognition error may cause an order of magnitude difference between the recognized number and the correct number, such as a 10-fold difference or a 100-fold difference. For example, when a certain number of ticket amounts in the reimbursement file is 1.68, and the correct number is 16.8, there is a 10-fold difference between the recognition result and the actual result, and when the numbers in the reimbursement file are checked one by one, this situation needs to be checked. Furthermore, when the digits in the reimbursement file are checked to have decimal point position identification errors, the digits need to be corrected to obtain corrected amount digits.
In one embodiment, the data processing in the reimbursement file further includes:
identifying the identity of the reimburser corresponding to the reimbursement file; inquiring the reimbursement grade corresponding to the identity of the reimbursement personnel; acquiring a subentry amount reimbursement threshold value and a total amount reimbursement threshold value corresponding to the reimbursement grade; and performing reimbursement audit according to the updated bill sum, total bill sum, acquired itemized sum reimbursement threshold value and total sum reimbursement threshold value.
In this embodiment, in addition to processing data in the reimbursement file, an allowable reimbursement amount threshold corresponding to the identity of the reimburser is also audited, so that a more comprehensive and accurate audit result of the reimbursement file is provided. Specifically, the server identifies the identity of the reimbursement staff recorded in the reimbursement file, can query a company (unit) staff management system to obtain reimbursement grades corresponding to the reimbursement staff, wherein the reimbursement grades are preset grades in the staff management system, each staff has a corresponding reimbursement grade which specifically comprises a common staff grade, a supervisor grade, a manager grade, a total supervision grade, a president grade and the like, the server obtains the corresponding reimbursement grades, and then obtains a sublist reimbursement threshold value (such as a lodging reimbursement threshold value and a traffic charge reimbursement threshold value) and a total sum reimbursement threshold value (such as a conference training total sum reimbursement threshold value and the like) corresponding to the reimbursement grades, and performs more comprehensive reimbursement and audit according to the data processing results in the previously obtained reimbursement files and the sublist threshold value and the total sum reimbursement threshold value, to determine whether reimbursement is possible or whether reimbursement at full rate is possible.
To further explain the technical solution of the data processing method in the reimbursement document of the present application and the effect thereof in detail, a specific application example will be described below with reference to fig. 4, and the whole solution includes the following processing steps:
and S1, acquiring the key words and the amount numbers on the bill.
And S2, acquiring the key words and the amount numbers on the bill.
And S3, judging whether the sum of the obtained item sums of the bills is equal to the total sum of the bills, if so, finishing data processing in the reimbursement file, and if not, entering the next step.
And S4, checking the numbers in the reimbursement file one by one, and identifying clear numbers and fuzzy identification numbers in the reimbursement file.
And S5, if the numbers in the reimbursement file are clear and the bill and the receipt numbers are consistent, verifying whether all the numbers are matched completely, and if so, finishing the money amount check.
And S6, if the fuzzy recognition numbers exist in the reimbursement file, classifying the fuzzy recognition numbers into one class (set) to obtain the fuzzy recognition class.
S7, searching original images of the bill corresponding to each number in the fuzzy recognition class, and performing image recognition processing on the original images by adopting algorithms such as GAN, GNN, RNN and the like to obtain a possibly corresponding number set.
And S8, comparing with the unmatched bill and document data sets, eliminating decimal point identification errors, finding out the numbers of the bills and the documents consistent from the number sets obtained in the step S7 until all numbers are matched, and obtaining a money amount auditing result.
And S9, after the amount of money is audited, auditing the reimbursement level information of reimbursers, and feeding back auditing results, wherein the auditing results comprise reimburseable, partial reimbursement, non-reimburseable and the like.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
As shown in fig. 5, the present application further provides an apparatus for processing data in a reimbursement file, the apparatus comprising:
the acquiring module 100 is configured to acquire a document to be processed and each to-be-processed bill corresponding to the document to be processed;
the extraction module 200 is used for extracting the total amount of the bills in the bills to be processed and the amount of the bills in each bill to be processed;
the fuzzy recognition module 300 is used for acquiring digital fuzzy bills in the bills to be processed when the sum of the bills is different from the total sum of the bills;
the fuzzy processing module 400 is used for carrying out image recognition on the digital fuzzy bill to obtain a similar amount set corresponding to the bill amount of the digital fuzzy bill;
and the iteration updating module 500 is used for sequentially selecting the sum of the similar sum set and iteratively updating the bill sum of the digital fuzzy bill until the sum of the updated bill sum is the same as the total bill sum.
The data processing device in the reimbursement file acquires the documents to be processed and the bills to be processed corresponding to the documents to be processed, extracts the total sum of the documents in the documents to be processed and the sum of the bills in the documents to be processed, acquires the digital fuzzy bills in the notes to be processed when the sum of the sums of the bills is different from the total sum of the documents, acquires a similar sum set corresponding to the sum of the bills of the digital fuzzy bills, and iteratively updates the sum of the bills of the digital fuzzy bills until the updated sum of the sums of the bills is the same as the total sum of the documents. In the whole process, fuzzy recognition is carried out on the amount numbers which cannot be clearly recognized in the reimbursement file according to the rule that the total amount in the document is equal to the sum of the subentry amounts in each bill to be processed, the amount numbers are iteratively updated according to the similar amount sets corresponding to the fuzzy recognition results, and finally data processing in the reimbursement file is accurately and efficiently completed.
In one embodiment, the iterative update module 500 is further configured to extract keywords carried by the digital fuzzy bill, where the keywords include a bill type keyword and an address keyword; sequentially selecting the sum of the similar sum set, iteratively updating the bill sum of the digital fuzzy bill until the sum of the updated bill sum is the same as the total bill sum, and recording the correspondingly selected sum when the iteration is stopped; when the recorded amount belongs to a subset of the set of verified amounts, the amount check result is output.
In one embodiment, the iterative update module 500 is further configured to send a query request carrying a keyword to a third-party database, and the third-party database queries the amount of money according to the keyword to obtain a verification amount set; and receiving the verification amount set fed back by the third-party database.
In one embodiment, the fuzzy recognition module 300 is further configured to check the sum of the bills and the total amount of the document one by one when the sum of the bills and the total amount of the document is different; when the number in each bill to be processed is unclear, classifying the recognized unclear number into a fuzzy recognition number set; and searching the bill to be processed to which each digit in the fuzzy recognition digit set belongs to obtain a digital fuzzy bill.
In one embodiment, the data processing apparatus in the reimbursement file further includes:
and the feedback module is used for feeding back a finishing message of the sum matching in the reimbursement file when the number in the bill to be processed is clear and the sum of the bill is matched with the sum in the bill to be processed.
In one embodiment, the fuzzy recognition module 300 is further configured to check whether a decimal point position recognition error exists in each bill amount when the sum of the bill amounts is different from the total bill amount.
In one embodiment, the data processing apparatus in the reimbursement file further includes:
the reimbursement level auditing module is used for identifying the identity of reimbursers corresponding to the reimbursement files; inquiring the reimbursement grade corresponding to the identity of the reimbursement personnel; acquiring a subentry amount reimbursement threshold value and a total amount reimbursement threshold value corresponding to the reimbursement grade; and performing reimbursement audit according to the updated bill sum, total bill sum, acquired itemized sum reimbursement threshold value and total sum reimbursement threshold value.
For specific limitations of the data processing apparatus in the reimbursement file, reference may be made to the above limitations of the data processing method in the reimbursement file, which are not described herein again. The modules in the data processing device in the reimbursement document can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing preset data related to reimbursement files. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of processing data in a reimbursement file.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring a document to be processed and various documents to be processed corresponding to the document to be processed;
extracting the total amount of the bills in the bills to be processed and the amount of the bills in each bill to be processed;
when the sum of the bill sum is different from the total bill sum, acquiring a digital fuzzy bill in each bill to be processed;
carrying out image recognition on the digital fuzzy bill to obtain a similar amount set corresponding to the bill amount of the digital fuzzy bill;
and sequentially selecting the sum of the similar sum set, and iteratively updating the bill sum of the digital fuzzy bill until the sum of the updated bill sum is the same as the total bill sum.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
extracting keywords carried by the digital fuzzy bill, wherein the keywords comprise bill type keywords and address keywords; inquiring a verification amount set corresponding to the keyword; sequentially selecting the sum of the similar sum set, iteratively updating the bill sum of the digital fuzzy bill until the sum of the updated bill sum is the same as the total bill sum, and recording the correspondingly selected sum when the iteration is stopped; and when the recorded amount belongs to the subset of the verification amount set, outputting an amount check result.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
sending a query request carrying the keywords to a third-party database, and querying the amount by the third-party database according to the keywords to obtain a verification amount set; and receiving the verification amount set fed back by the third-party database.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
when the sum of the bill sum is different from the total bill sum, checking the bill sums one by one; when the number in each bill to be processed is unclear, classifying the recognized unclear number into a fuzzy recognition number set; and searching the bill to be processed to which each digit in the fuzzy recognition digit set belongs to obtain the digital fuzzy bill.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and when the number in the bill to be processed is clear and the bill sum is matched with the gold amount in the bill to be processed, feeding back a finishing message of sum matching in the reimbursement file.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
when the sum of the bill sum is different from the total bill sum, checking whether the bill sum has decimal point position identification error.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
identifying the identity of the reimburser corresponding to the reimbursement file; inquiring the reimbursement grade corresponding to the identity of the reimbursement personnel; acquiring a subentry amount reimbursement threshold value and a total amount reimbursement threshold value corresponding to the reimbursement grade; and performing reimbursement verification according to the updated bill sum, total bill sum, acquired itemized sum reimbursement threshold value and total sum reimbursement threshold value.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a document to be processed and various documents to be processed corresponding to the document to be processed;
extracting the total amount of the bills in the bills to be processed and the amount of the bills in each bill to be processed;
when the sum of the bill sum is different from the total bill sum, acquiring a digital fuzzy bill in each bill to be processed;
carrying out image recognition on the digital fuzzy bill to obtain a similar amount set corresponding to the bill amount of the digital fuzzy bill;
and sequentially selecting the sum of the similar sum set, and iteratively updating the bill sum of the digital fuzzy bill until the sum of the updated bill sum is the same as the total bill sum.
In one embodiment, the computer program when executed by the processor further performs the steps of:
extracting keywords carried by the digital fuzzy bill, wherein the keywords comprise bill type keywords and address keywords; inquiring a verification amount set corresponding to the keyword; sequentially selecting the sum of the similar sum set, iteratively updating the bill sum of the digital fuzzy bills until the sum of the updated bill sum is the same as the total bill sum, and recording the correspondingly selected sum when iteration stops; when the recorded amount belongs to a subset of the set of verified amounts, the amount check result is output.
In one embodiment, the computer program when executed by the processor further performs the steps of:
sending a query request carrying the keywords to a third-party database, and querying the amount by the third-party database according to the keywords to obtain a verification amount set; and receiving a verification amount set fed back by the third party database.
In one embodiment, the computer program when executed by the processor further performs the steps of:
when the sum of the bill sum is different from the total bill sum, checking the bill sums one by one; when the number in each bill to be processed is unclear, classifying the recognized unclear number into a fuzzy recognition number set; and searching the bill to be processed to which each digit in the fuzzy recognition digit set belongs to obtain the digital fuzzy bill.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and when the number in the bill to be processed is clear and the bill sum is matched with the gold amount in the bill to be processed, feeding back a finishing message of sum matching in the reimbursement file.
In one embodiment, the computer program when executed by the processor further performs the steps of:
when the sum of the bill sum is different from the total bill sum, checking whether the bill sum has decimal point position identification error.
In one embodiment, the computer program when executed by the processor further performs the steps of:
identifying the identity of the reimburser corresponding to the reimbursement file; inquiring the reimbursement grade corresponding to the identity of the reimbursement personnel; acquiring a subentry amount reimbursement threshold value and a total amount reimbursement threshold value corresponding to the reimbursement grade; and performing reimbursement audit according to the updated bill sum, total bill sum, acquired itemized sum reimbursement threshold value and total sum reimbursement threshold value.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can 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 a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of processing data in a reimbursement file, the method comprising:
acquiring a document to be processed and various documents to be processed corresponding to the document to be processed;
extracting the total bill sum in the bills to be processed and the bill sum in each bill to be processed;
when the sum of the bills is different from the total sum of the bills, acquiring digital fuzzy bills in the bills to be processed;
carrying out image recognition on the digital fuzzy bill to obtain a similar sum set corresponding to the bill sum of the digital fuzzy bill;
and sequentially selecting the sum of the similar sum of money in the set, and iteratively updating the bill sum of the digital fuzzy bill until the updated sum of the bill sum is the same as the total bill sum.
2. The method of claim 1, wherein said sequentially selecting the sum of the similar sum sets, iteratively updating the bill sum of the digitally obfuscated bills until the sum of the updated bill sums is equal to the total bill sum, further comprising:
extracting keywords carried by the digital fuzzy bill, wherein the keywords comprise bill type keywords and address keywords;
inquiring a verification amount set corresponding to the keyword according to the bill type;
sequentially selecting the sum of the similar sum of money in the set, and iteratively updating the bill sum of the digital fuzzy bill until the updated sum of the bill sum is the same as the total bill sum, wherein the step of iteratively updating the bill sum comprises the following steps:
sequentially selecting the amount in the similar amount set, iteratively updating the bill amount of the digital fuzzy bill until the sum of the updated bill amounts is the same as the total amount of the bills, and recording the amount correspondingly selected when iteration is stopped;
outputting a value check result when the recorded value belongs to a subset of the verification value set.
3. The method of claim 2, wherein querying the set of verification amounts corresponding to the keyword comprises:
sending a query request carrying the keyword to a third-party database, and querying the amount by the third-party database according to the keyword to obtain a verification amount set;
and receiving the verification amount set fed back by the third-party database.
4. The method of claim 1, wherein obtaining digitally obscured notes in the pending notes when the sum of the notes is not the same as the total amount of the document comprises:
when the sum of the bill sum is different from the total bill sum, checking the bill sums one by one;
when the number in each bill to be processed is unclear, classifying the recognized unclear number into a fuzzy recognition number set;
and searching the bill to be processed to which each digit in the fuzzy recognition digit set belongs to obtain a digital fuzzy bill.
5. The method of claim 4, further comprising:
and when the number in the bill to be processed is clear and the bill sum is matched with the money sum bill in the bill to be processed, feeding back a finishing message of sum matching in the reimbursement file.
6. The method of claim 4, wherein checking each of the ticket amounts one by one when the sum of each of the ticket amounts is not the same as the total document amount comprises:
and when the sum of the bill sum is different from the total bill sum, checking whether the decimal point position identification error exists in the bill sum.
7. The method of claim 1, further comprising:
identifying the identity of the reimburser corresponding to the reimbursement file;
inquiring the reimbursement grade corresponding to the identity of the reimbursement personnel;
acquiring a subentry amount reimbursement threshold value and a total amount reimbursement threshold value corresponding to the reimbursement grade;
and performing reimbursement verification according to the updated bill sum, the total bill sum, the acquired itemized sum reimbursement threshold value and the total sum reimbursement threshold value.
8. An apparatus for processing data in a reimbursement document, the apparatus comprising:
the acquiring module is used for acquiring the bills to be processed and the bills to be processed corresponding to the bills to be processed;
the extraction module is used for extracting the total bill sum in the bills to be processed and the bill sum in each bill to be processed;
the fuzzy identification module is used for acquiring digital fuzzy bills in the bills to be processed when the sum of the bills is different from the total sum of the bills;
the fuzzy processing module is used for carrying out image recognition on the digital fuzzy bill to obtain a similar amount set corresponding to the bill amount of the digital fuzzy bill;
and the iteration updating module is used for sequentially selecting the sum of the similar sum set and iteratively updating the bill sum of the digital fuzzy bill until the sum of the updated bill sums is the same as the total bill sum.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910876220.3A CN110728566B (en) | 2019-09-17 | 2019-09-17 | Data processing method and device in reimbursement file, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910876220.3A CN110728566B (en) | 2019-09-17 | 2019-09-17 | Data processing method and device in reimbursement file, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110728566A CN110728566A (en) | 2020-01-24 |
| CN110728566B true CN110728566B (en) | 2022-08-02 |
Family
ID=69219094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910876220.3A Active CN110728566B (en) | 2019-09-17 | 2019-09-17 | Data processing method and device in reimbursement file, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110728566B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107507018A (en) * | 2017-07-25 | 2017-12-22 | 广州智选网络科技有限公司 | It is a kind of that method, storage device and mobile terminal are checked and write off based on image recognition technology |
| CN107895251A (en) * | 2016-12-24 | 2018-04-10 | 上海壹账通金融科技有限公司 | Data error-correcting method and device |
| CN108573268A (en) * | 2017-03-10 | 2018-09-25 | 北京旷视科技有限公司 | Image-recognizing method and device, image processing method and device and storage medium |
| CN109872444A (en) * | 2019-02-27 | 2019-06-11 | 杭州睿琪软件有限公司 | A kind of bank slip recognition method and device |
| CN109977957A (en) * | 2019-03-04 | 2019-07-05 | 苏宁易购集团股份有限公司 | A kind of invoice recognition methods and system based on deep learning |
-
2019
- 2019-09-17 CN CN201910876220.3A patent/CN110728566B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107895251A (en) * | 2016-12-24 | 2018-04-10 | 上海壹账通金融科技有限公司 | Data error-correcting method and device |
| CN108573268A (en) * | 2017-03-10 | 2018-09-25 | 北京旷视科技有限公司 | Image-recognizing method and device, image processing method and device and storage medium |
| CN107507018A (en) * | 2017-07-25 | 2017-12-22 | 广州智选网络科技有限公司 | It is a kind of that method, storage device and mobile terminal are checked and write off based on image recognition technology |
| CN109872444A (en) * | 2019-02-27 | 2019-06-11 | 杭州睿琪软件有限公司 | A kind of bank slip recognition method and device |
| CN109977957A (en) * | 2019-03-04 | 2019-07-05 | 苏宁易购集团股份有限公司 | A kind of invoice recognition methods and system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110728566A (en) | 2020-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020000688A1 (en) | Financial risk verification processing method and apparatus, computer device, and storage medium | |
| US20210166017A1 (en) | Automatic document source identification systems | |
| WO2020015089A1 (en) | Identity information risk assessment method and apparatus, and computer device and storage medium | |
| CN108876133A (en) | Risk assessment processing method, device, server and medium based on business information | |
| AU2019203697A1 (en) | Intelligent data extraction | |
| WO2021042747A1 (en) | Invoice picture recognition and verification method and system, device, and readable storage medium | |
| US10657530B2 (en) | Automated transactions clearing system and method | |
| CN110489415B (en) | Data updating method and related equipment | |
| CN112882699B (en) | Service processing method, device, equipment and medium based on flow configuration engine | |
| WO2019227577A1 (en) | Invoice authenticity verification method, apparatus, computer device, and storage medium | |
| WO2021164205A1 (en) | Identity identification-based data auditing method and apparatus, and computer device | |
| WO2019227576A1 (en) | Invoice verification method and apparatus, computer device, and storage medium | |
| WO2019019777A1 (en) | Insurance policy premium-withdrawing processing method and apparatus, computer device, and storage medium | |
| CN115601129A (en) | Supply chain financial asset auditing method, device, equipment and medium | |
| CN109214362B (en) | Document processing method and related equipment | |
| US20190294594A1 (en) | Identity Data Enhancement | |
| CN113837584A (en) | Service processing system and abnormal data processing method based on service processing system | |
| CN110489434B (en) | Information processing method and related equipment | |
| CN111126966A (en) | Bill auditing method and device, computer equipment and computer-readable storage medium | |
| CN110728566B (en) | Data processing method and device in reimbursement file, computer equipment and storage medium | |
| CN111400187A (en) | Parameter dynamic verification system and method based on customized data source | |
| US11681966B2 (en) | Systems and methods for enhanced risk identification based on textual analysis | |
| CN110457332B (en) | Information processing method and related equipment | |
| CN109829750B (en) | Public transport transaction information processing method and device and computer equipment | |
| EP4165564A1 (en) | Methods and systems for matching and optimizing technology solutions to requested enterprise products |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |