CN110378343A - A kind of finance reimbursement data processing method, apparatus and system - Google Patents
A kind of finance reimbursement data processing method, apparatus and system Download PDFInfo
- Publication number
- CN110378343A CN110378343A CN201910681472.0A CN201910681472A CN110378343A CN 110378343 A CN110378343 A CN 110378343A CN 201910681472 A CN201910681472 A CN 201910681472A CN 110378343 A CN110378343 A CN 110378343A
- Authority
- CN
- China
- Prior art keywords
- reimbursement
- image
- data
- image slice
- processing
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
This specification embodiment discloses a kind of finance reimbursement data processing method, apparatus and system, and the method includes obtaining the reimbursement voucher image of reimbursement application to be processed;Image cutting processing is carried out to the reimbursement voucher image according to determining reimbursement key area, obtains the corresponding image slice of the reimbursement key area;Pictograph identifying processing is carried out to the image slice, obtains the corresponding substructuring data of the image slice;The corresponding substructuring data of each image slice of the reimbursement application to be processed are integrated, the structural data of the reimbursement application to be processed is formed, the structural data is verified according to default verification rule;The corresponding image slice of substructuring data that preset requirement is unsatisfactory in check results is transferred, to be modified processing to the structural data.Using each embodiment of this specification, the efficiency of finance reimbursement data processing can be increased substantially, the workload of financial staff is reduced.
Description
Technical field
The present invention relates to computer data processing technology fields, particularly, be related to it is a kind of finance reimbursement data processing method,
Apparatus and system.
Background technique
During finance reimbursement, need to handle the reimbursement voucher of vast number, such as the mono- all kinds of reimbursements of invoice, pos with
Card.Financial staff needs that big workload is spent to check all kinds of reimbursement voucher data, it is also desirable to which manual entry is a large amount of
Reimbursement information so that entirely reimbursement process complexity it is cumbersome, workload is huge.Therefore, the art need one kind can be more
Add efficient finance reimbursement data processing method.
Summary of the invention
This specification embodiment is designed to provide a kind of finance reimbursement data processing method, apparatus and system, can be with
The efficiency for increasing substantially finance reimbursement data processing, reduces the workload of financial staff.
It includes under type realization such as that this specification, which provides a kind of finance reimbursement data processing method, apparatus and system:
A kind of finance reimbursement data processing method, comprising:
Obtain the reimbursement voucher image of reimbursement application to be processed;
Image cutting processing is carried out to the reimbursement voucher image according to determining reimbursement key area, obtains the reimbursement
The corresponding image slice of key area;
Pictograph identifying processing is carried out to the image slice, obtains the corresponding substructuring number of the image slice
According to;
The corresponding substructuring data of each image slice of the reimbursement application to be processed are integrated, formed it is described to
The structural data of processing reimbursement application verifies the structural data according to default verification rule;
The corresponding image slice of substructuring data that preset requirement is unsatisfactory in check results is transferred, to the structure
Change data and is modified processing.
It is described that image is carried out to the reimbursement voucher image in another embodiment of the method that this specification provides
Cutting processing, comprising:
Type identification processing is carried out to the reimbursement voucher image, obtains the type of credentials of the reimbursement voucher image;
The corresponding image segmentation algorithm of the reimbursement voucher image is determined according to the type of credentials, is cut using described image
Algorithm is divided to carry out image cutting processing to the reimbursement voucher image.
In another embodiment of the method that this specification provides, the default verification rule of the basis is to the structure
Change data to be verified, comprising:
The reimbursement type for obtaining the reimbursement application to be processed, determines the reimbursement voucher image according to the reimbursement type
Corresponding verification rule;
The structural data is verified according to the corresponding verification rule.
It is described that pictograph is carried out to the image slice in another embodiment of the method that this specification provides
Identifying processing obtains the corresponding substructuring data of the image slice, comprising:
If image slice recognition failures, using the image slice of recognition failures as to amended record image slice;
Described distribute to amended record image slice at least two amended record terminals is subjected to amended record processing, is obtained described to amended record
The corresponding at least two amended records data of image slice;
Consistency desired result is carried out at least two amended records data, when check results are met the requirements, by the amended record
Data are as the substructuring data to amended record image slice.
In another embodiment of the method that this specification provides, the method also includes:
The corresponding structural data of image slice and image slice for the reimbursement application to be processed that audit is passed through updates
To reimbursement sample set;
Using updated reimbursement sample set to image cutting processing and the corresponding machine learning of pictograph identifying processing
Model is updated processing.
On the other hand, this specification also provides a kind of finance reimbursement data processing equipment, and described device includes:
Data acquisition module, for obtaining the reimbursement voucher image of reimbursement application to be processed;
Image cutting module, for carrying out image cutting to the reimbursement voucher image according to determining reimbursement key area
Processing obtains the corresponding image slice of the reimbursement key area;
Picture recognition module obtains the image slice for carrying out pictograph identifying processing to the image slice
Corresponding substructuring data;
Data check module, for by it is described it is to be processed reimbursement application the corresponding substructuring data of each image slice into
Row integration forms the structural data of the reimbursement application to be processed, according to default verification it is regular to the structural data into
Row verification;
Data transfer module, for transferring the corresponding image of substructuring data for being unsatisfactory for preset requirement in check results
Slice, to be modified processing to the structural data.
In another embodiment for the described device that this specification provides, described image cutting module includes:
Type of credentials determination unit obtains the reimbursement for carrying out type identification processing to the reimbursement voucher image
The type of credentials of certificate image;
Image cutting unit, for determining that the corresponding image cutting of the reimbursement voucher image is calculated according to the type of credentials
Method carries out image cutting processing to the reimbursement voucher image using described image segmentation algorithm.
In another embodiment for the described device that this specification provides, the data check module includes:
Rule determination unit is verified, for obtaining the reimbursement type of the reimbursement application to be processed, according to the reimbursement class
Type determines the corresponding verification rule of the reimbursement voucher image;
Data check unit, for being verified according to the corresponding verification rule to the structural data.
In another embodiment for the described device that this specification provides, described image identification module includes:
Judging unit, for judge image slice whether recognition failures, if image slice recognition failures, by recognition failures
Image slice be used as to amended record image slice;
Amended record unit, for described distribute to amended record image slice at least two amended record terminals to be carried out amended record processing,
It obtains described to the corresponding at least two amended records data of amended record image slice;
Verification unit, for carrying out consistency desired result at least two amended records data, when check results are met the requirements
When, using the amended record data as the substructuring data to amended record image slice.
On the other hand, this specification also provides a kind of finance reimbursement data processing equipment, including processor and for storing
The memory of processor-executable instruction, when described instruction is executed by the processor realize the following steps are included:
Obtain the reimbursement voucher image of reimbursement application to be processed;
Image cutting processing is carried out to the reimbursement voucher image according to determining reimbursement key area, obtains the reimbursement
The corresponding image slice of key area;
Pictograph identifying processing is carried out to the image slice, obtains the corresponding substructuring number of the image slice
According to;
The corresponding substructuring data of each image slice of the reimbursement application to be processed are integrated, formed it is described to
The structural data of processing reimbursement application verifies the structural data according to default verification rule;
The corresponding image slice of substructuring data that preset requirement is unsatisfactory in check results is transferred, to the structure
Change data and is modified processing.
On the other hand, this specification also provides a kind of finance reimbursement data processing system, and the system comprises at least one
Processor and the memory for storing computer executable instructions, the processor are realized above-mentioned any one when executing described instruction
The step of a embodiment the method.
Finance the reimbursement data processing method, apparatus and system that this specification one or more embodiment provides, Ke Yitong
Image cutting processing is carried out to reimbursement voucher after first, the corresponding image slice of reimbursement key area is obtained, it is then possible to again to each
Image slice carries out Text region, forms structural data.Later, structural data can be carried out certainly based on preset rules again
Dynamicization verification can transfer the amended record that corresponding image slice quickly realizes information to the problematic data of checked result,
To increase substantially information checking and check the efficiency of amended record processing.Meanwhile due to can use image slice when amended record
It realizes, therefore amended record can also be carried out using third-party form is contracted out to, without having to worry about information leakage, guaranteeing information peace
On the basis of full property, the efficiency of finance reimbursement data processing is further increased, the workload of financial staff is reduced.
Detailed description of the invention
In order to illustrate more clearly of this specification embodiment or technical solution in the prior art, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
The some embodiments recorded in this specification, for those of ordinary skill in the art, in not making the creative labor property
Under the premise of, it is also possible to obtain other drawings based on these drawings.In the accompanying drawings:
Fig. 1 is a kind of flow diagram for finance reimbursement data processing method embodiment that this specification provides;
Fig. 2 is the finance reimbursement data processing method flow diagram in one embodiment that this specification provides;
Fig. 3 is a kind of modular structure schematic diagram for finance reimbursement data processing equipment embodiment that this specification provides;
Fig. 4 is the modular structure signal of the finance reimbursement data processing system in another embodiment that this specification provides
Figure;
Fig. 5 is the structural schematic diagram of the image processing module in another embodiment that this specification provides;
Fig. 6 is the structural schematic diagram of the finance reimbursement module in another embodiment that this specification provides;
Fig. 7 is the structural schematic diagram of the depth excavation module in another embodiment that this specification provides.
Specific embodiment
In order to make those skilled in the art more fully understand the technical solution in this specification, below in conjunction with this explanation
Attached drawing in book one or more embodiment carries out the technical solution in this specification one or more embodiment clear, complete
Site preparation description, it is clear that described embodiment is only specification a part of the embodiment, instead of all the embodiments.Based on saying
Bright book one or more embodiment, it is obtained by those of ordinary skill in the art without making creative efforts all
The range of this specification example scheme protection all should belong in other embodiments.
During finance reimbursement, need to handle the reimbursement voucher of vast number, such as the mono- all kinds of reimbursements of invoice, pos with
Card.Financial staff needs that big workload is spent to check all kinds of reimbursement voucher data, it is also desirable to which manual entry is a large amount of
Reimbursement information so that entirely reimbursement process complexity it is cumbersome, workload is huge.
Correspondingly, this specification embodiment provides a kind of finance reimbursement data processing method, it can be by first to reimbursement
Voucher carries out image cutting processing, obtains the corresponding image slice of reimbursement key area, it is then possible to again to each image slice into
Row Text region forms structural data.Later, automation verification can be carried out to structural data based on preset rules again,
To the problematic data of checked result, the amended record that corresponding image slice quickly realizes information can be transferred, thus substantially
Degree improves information checking and checks the efficiency of amended record processing.Meanwhile being realized when amended record due to can use image slice, because
This can also carry out amended record using third-party form is contracted out to, without having to worry about information leakage, in the base of ensuring information security property
On plinth, the efficiency of finance reimbursement data processing is further increased, the workload of financial staff is reduced.
Fig. 1 is a kind of finance reimbursement data processing method embodiment flow diagram that this specification provides.Although
Present description provides as the following examples or method operating procedure shown in the drawings or apparatus structure, but it is based on routine or nothing
Need creative labor may include more in the method or device or part merge after less operating procedure or mould
Module unit.In the step of there is no necessary causalities in logicality or structure, the execution sequences of these steps or device
Modular structure is not limited to this specification embodiment or execution shown in the drawings sequence or modular structure.The method or module knot
Device in practice, server or the end product of structure in application, can according to embodiment or method shown in the drawings or
Modular structure carry out sequence execution or it is parallel execute (such as parallel processor or multiple threads environment, even include
The implementation environment of distributed treatment, server cluster).
Specific one embodiment is as shown in Figure 1, the finance that this specification provides submit an expense account a reality of data processing method
It applies in example, the method may include:
S0: the reimbursement voucher image of reimbursement application to be processed is obtained.
The reimbursement voucher image of available reimbursement application to be processed.The reimbursement voucher image may include to reimbursement with
The image data that obtains of modes such as card scanning or shooting, reimbursement voucher such as may include various types of invoices, POS mono-.
User can fill in the scanning or shooting that transfer corresponding equipment when reimbursement application and carry out reimbursement voucher, can also will be preparatory
It has scanned or filmed reimbursement voucher image is uploaded, formed the reimbursement voucher image file of reimbursement application to be processed,
It is stored in file server.
S2: image cutting processing is carried out to the reimbursement voucher image according to determining reimbursement key area, described in acquisition
Submit an expense account the corresponding image slice of key area;
The reimbursement key area can for the corresponding region of content of interest in reimbursement application, the date of such as making out an invoice, the amount of money,
The corresponding region such as account.Such as reimbursement key area can be determined by analyzing the content of interest of reimbursement application to be processed,
It can also apply for content of interest by a kind of reimbursement of comprehensive analysis, predefine certain one kind reimbursement and apply for report of interest
Sell key area.
After obtaining the corresponding reimbursement voucher image of reimbursement application, signature analysis first can be carried out to reimbursement voucher image, it is right
Each reimbursement key area carries out Primary Location, it is then possible to be reported according to pre-set image segmentation algorithm to reimbursement voucher image
Pin key area accurately extracts, and obtains in reimbursement voucher image and respectively submits an expense account the corresponding image slice of key area.
In one embodiment of this specification, type identification processing first can be carried out to the reimbursement voucher image, obtained
Then the type of credentials of the reimbursement voucher image determines the corresponding figure of the reimbursement voucher image according to the type of credentials
As segmentation algorithm, image cutting processing is carried out to the reimbursement voucher image using described image segmentation algorithm.
It can classify in advance to reimbursement voucher, the reimbursement voucher with similar features is divided into one kind, it then, can
To construct corresponding image segmentation algorithm for every a kind of reimbursement voucher.It, can be first to reimbursement voucher shadow in practical application scene
As carrying out type identification, type of credentials belonging to reimbursement voucher image is determined.It is then possible to according to the corresponding image of type of credentials
Segmentation algorithm carries out the positioning of key area accurate coordinate to reimbursement voucher image, carries out image cutting processing according to position coordinates,
The corresponding image of each reimbursement key area is extracted, the corresponding image slice of each reimbursement key area is obtained.
There are many kinds of the types of reimbursement voucher, and there may be certain for the reimbursement key area of different types of reimbursement voucher
Otherness.If invoice and the mono- amount of money of POS, specific location of the receiver information in voucher are there may be biggish otherness,
The accurate positionin of reimbursement critical zone locations coordinate is directly carried out by way of key message signature analysis, it is understood that there may be identification
The problem of inaccuracy.By first classifying to reimbursement voucher, the building of image segmentation algorithm is carried out respectively, then, using each
The corresponding image segmentation algorithm of type carries out image cutting processing, can be further improved the extraction of reimbursement voucher image key area
Accuracy, and then improve reimbursement voucher in key message extract accuracy.
In practical application, user may deposit the image scan of multiple reimbursement vouchers into an image file
It stores up, in some embodiments of this specification, before image cutting processing, first reimbursement voucher image can also be located in advance
Reason, extracts the corresponding image of each reimbursement voucher, as the reimbursement voucher image.The voucher of each reimbursement voucher image is determined again
Type, according to type of credentials to reimbursement voucher image carry out image cutting processing, can be further improved key area extract with
And the efficiency and accuracy of cutting processing.
S4: pictograph identifying processing is carried out to the image slice, obtains the corresponding substructuring of the image slice
Data.
Pictograph identification can be carried out to image slice, obtain the corresponding substructuring data of image slice.Structuring
Data may include can be carried out by relevant database by two-dimentional table structure come the data of logical expression and realization storage and
Management.Text region processing is carried out to image, the text or digital information in image can be extracted, it is then possible to will know
Not Chu text or digital information according to its distribution characteristics and grammar property in image, be stored as structural data,
In order to the subsequent analysis and processing of data.
Carrying out pictograph identifying processing to image slice can will identify that successful text, number are deposited if identifying successfully
Storage is the form of structural data, is stated for the ease of distinguishing, can be by the corresponding knot of image slice in this specification embodiment
Structure data definition is substructuring data.
In another embodiment of this specification, if image slice recognition failures, the image of recognition failures can be cut
Piece is used as to amended record image slice;Described distribute to amended record image slice at least two amended record terminals is subjected to amended record processing,
It obtains described to the corresponding at least two amended records data of amended record image slice;Consistency is carried out at least two amended records data
Verification, when check results are met the requirements, using the amended record data as the substructuring data to amended record image slice.
When carrying out pictograph identification to image slice, it can such as identify the content in image slice, then be identified
While data, the recognition confidence of identification data can also be obtained;If the content in image slice could not identify, then can obtain
Obtain the result prompt such as content recognition failure.In some embodiments, recognition confidence can be lower than to preset threshold or interior
Hold image slice of the image slice that could not be identified as recognition failures, to carry out amended record processing.
It is then possible to will be distributed to amended record image slice to amended record terminal, to carry out amended record processing.During amended record, by
Image slice is only externally shown in amended record terminal, does not show complete reimbursement voucher image, and therefore, amended record operation can also adopt
With the mode of outsourcing, without having to worry about information leakage.Such as, can by third party staff using amended record terminal to image slice into
Row amended record processing, the amended record data of the available third party staff's input of amended record terminal, so as to guarantee information peace
On the basis of full property, the workload of financial staff is greatly lowered.
In some embodiments, it can also will be distributed to amended record image slice at least two amended record terminals, to be mended
Record processing, can obtain at least two amended record data, it is then possible to carry out consistency school at least two amended records data again
It tests.It is accomplished manually since amended record generallys use, amended record process is dull and data volume is larger, is easy that there are amended record data inputting mistakes
The problem of, amended record processing is carried out compared with by way of two records one, can be further improved the accuracy of data amended record.
S6: the corresponding substructuring data of each image slice of the reimbursement application to be processed are integrated, institute is formed
The structural data for stating reimbursement application to be processed verifies the structural data according to default verification rule.
Image recognition processing is carried out using reimbursement voucher image of the above-described embodiment to reimbursement application to be processed, and to identification
After problematic image slice carries out amended record processing, the substructuring number of each image slice in reimbursement application to be processed can be obtained
According to.It is then possible to by it is to be processed reimbursement application the corresponding substructuring data of each image slice comb, organize the formation of to
The structural data of processing reimbursement application.
It can use default verification rule and automation verification carried out to the structural data of reimbursement application to be processed, with verifying
The accuracy of the structural data finally obtained.For example, it is bright to verify each receiver information in structural data, the amount of money
Carefully, whether all kinds of reimbursement information such as amount of money total value are consistent with the information filled in expense report.The default verification rule can lead to
The data filled in the structural data and expense report of analysis of history reimbursement application are crossed to determine.
In one embodiment of this specification, the reimbursement type of the reimbursement application to be processed can be first obtained, according to institute
It states reimbursement type and determines the corresponding verification rule of the reimbursement voucher image, it is then possible to according to the corresponding verification rule
The structural data is verified.
Reimbursement application may include a variety of reimbursement types, such as may include business trip reimbursement/reimbursement for a business trip, procurement contract reimbursement, product testing
A variety of mode classifications such as reimbursement.It can classify in advance to reimbursement application, obtain a variety of reimbursement types of reimbursement application, classification
Mode be referred to the reimbursement process in existing reimbursement system progress, can also be with sets itself, here without limitation.Then,
It can analyze the corresponding structural data distribution characteristics of each reimbursement type, determine each reimbursement in such a way that such as artificial intelligence learns
The corresponding verification rule of type.In practical application scene, reimbursement to be processed is applied, can first obtain or discriminance analysis is true
Then its fixed corresponding reimbursement type verifies structural data according to the corresponding verification rule of the reimbursement type, obtains
Check results.
There are biggish othernesses for each corresponding structural data feature of reimbursement type, by elder generation according to each reimbursement class
The structured data feature of type determines corresponding verification rule, then, recycles corresponding verification rule to carry out structural data quasi-
True property verification, can be further improved the efficiency and accuracy of checking treatment.
S8: the corresponding image slice of substructuring data that preset requirement is unsatisfactory in check results is transferred, to described
Structural data is modified processing.
When check results all meet preset requirement, such as each receiver information, amount of money detail, all kinds of reimbursements of amount of money total value
When information is consistent with the information filled in expense report, verification can be prompted to pass through, it is then possible to enter payment reimbursement in next step
Link.
The data of preset requirement are unsatisfactory for if there is check results, such as exist with the information on request slip it is inconsistent or
When the data of missing, the structural data for being unsatisfactory for requiring can be shown, is reviewed for financial staff.Some embodiment party
In formula, the corresponding image slice of substructuring data for being unsatisfactory for requiring can be transferred according to the operation of financial staff, to carry out
Information verification and amended record processing.For example, if it is certain receiver information, there are problems, can transfer the receiver information pair
The image slice answered, to carry out information verification and amended record processing;It goes wrong, then can transfer if it is reimbursed sum total value
Image slice related with the amount of money, to carry out amount information verification and amended record processing.
In above-mentioned treatment process, problematic structural data can be carried out using image slice by financial staff preliminary
Verification, then, then by financial staff to the data progress amended record processing wrong to information using amended record terminal.In order to further mention
Image slice to amended record can also be used the form of outsourcing, third party is transferred to carry out amended record processing by high efficiency.If there is
Loss of learning and the case where can not transfer corresponding image slice again, can also only be carried out by financial staff according to reimbursement voucher image
The verification of full dose information and amended record processing, to guarantee the safety of information.
After the completion of structural data calibration link, financial staff can further be audited reimbursement application, and can lead to
It crosses and checks slice and structural data, whether check image recognition result is correct, can also check that whole certificate images carry out people
Work audit.If financial staff has found that image recognition result is wrong, can be by being repaired according to image slice to structural data
It just, can also be according to certificate image typing structural data, it is ensured that the correctness of data.After financial audit passes through, single-turn is submitted an expense account
Enter payment flow and carry out automatic reimbursement payment, do not pass through such as, then retract applicant's modification processing, alternatively, terminating reimbursement process.
It is then possible to which reimbursement data and its certificate image that audit is passed through are filed, file store is formed, is analyzed for data
And it excavates, such as analysis processing timeliness, reimbursed sum statistics, reimbursement statistic of classification.At the same time it can also which the shadow passed through will be audited
Picture and its structural data further promote the accuracy that image identifies for machine learning module progress deep learning.It is based on
Above-mentioned implement scene, in another embodiment of this specification, the method can also include:
The corresponding structural data of image slice and image slice for the reimbursement application to be processed that audit is passed through updates
To reimbursement sample set;
Using updated reimbursement sample set to image cutting processing and the corresponding machine learning of pictograph identifying processing
Model is updated processing.
Fig. 2 indicates a kind of flow diagram for finance reimbursement data processing method that this specification provides.As shown in Fig. 2,
In one application scenarios of this specification, the finance reimbursement data processing method be may include steps of:
S01: the reimbursement voucher that reimbursement personnel prepare is obtained;
S02: scanning and store to reimbursement voucher using voucher scan module, obtains reimbursement voucher image;
S03: to the processing of certificate image type identification, image cutting processing and Text region:
301: being classified using image recognition machine learning model to certificate image, in being paid close attention in sorted image
The picture region of appearance is sliced, and image slice file is saved as;
302: pictograph identification being carried out to image slice, obtains the corresponding substructuring data of image slice;
S04: the image slice of recognition failures is judged whether there is;
S05: if there is the image slice of recognition failures, then amended record is carried out to image slice;
It is lower than the image slice of threshold value for the failure of identification content or recognition confidence, it can be there are two amended record terminal
The typing for being sliced upper content is completed, only amended record is consistent just thinks that (two one schools of record) is completed in amended record.Due to the shadow being only sliced
Picture improves the speed of typing, and can be contracted out to third party and carry out amended record without worrying information leakage.
S06: structural data is verified using default verification rule;
It can be directed to different reimbursement types, different verification rules is designed and structural data is verified.
S07: financial staff's audit;
Financial staff audits automatic Verification as a result, simultaneously can be by checking slice and structural data, check image identification knot
Whether fruit is correct, can also check that whole certificate images carry out manual examination and verification.
S08: the data of image identification mistake are judged whether there is;
S09: if it does, Credential data can be filled according to image slice or image supplement;
S10: judge whether finance audit and pass through, rescaned if not, can retract, or directly disagree termination stream
Journey;
S11: if it is, the data that audit is passed through carry out subsequent processing:
S12: reimbursement payment is carried out according to the data that audit passes through;
S13: the data that audit passes through are updated to sample set, to carry out image recognition machine study;
S14: carrying out reimbursement archive for the data that audit passes through, and to be used for subsequent data analysis, such as handles timeliness, report
Gold-sprinkled volume statistics, reimbursement statistic of classification etc..
This specification said one or multiple embodiments, by by reimbursement voucher scan-image, content recognition, automatically
The methods of auditing rule verification can effectively improve the efficiency of finance reimbursement audit.When carrying out amended record for problematic data,
Because can only see the part of voucher during amended record, whole image can not be seen, so that amended record operation can also be contracted out to third party
It carries out, without worrying information leakage, the workload of financial staff is greatly lowered.At the same time it can also which the number passed through will be examined
According to as the image recognition data marked, processing is updated to image recognition machine learning model, further increases image
The accuracy of identification.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Specifically it is referred to
The description of aforementioned relevant treatment related embodiment, does not do repeat one by one herein.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
This specification one or more embodiment provide finance reimbursement data processing method, can by first to reimbursement with
Card carries out image cutting processing, the corresponding image slice of reimbursement key area is obtained, it is then possible to carry out again to each image slice
Text region forms structural data.Later, automation verification can be carried out to structural data based on preset rules again, it is right
The problematic data of checked result can transfer the amended record that corresponding image slice quickly realizes information, thus significantly
It improves information checking and checks the efficiency of amended record processing.Meanwhile being realized when amended record due to can use image slice,
Amended record can also be carried out using third-party form is contracted out to, without having to worry about information leakage, on the basis of ensuring information security property
On, the efficiency of finance reimbursement data processing is further increased, the workload of financial staff is reduced.
Based on finance reimbursement data processing method described above, this specification one or more embodiment also provides one kind
Finance reimbursement data processing equipment.The device may include the system for having used this specification embodiment the method, soft
Part (application), module, component, server etc. simultaneously combine the necessary device for implementing hardware.Based on same innovation thinking, this explanation
The device in one or more embodiments that book embodiment provides is as described in the following examples.The reality solved the problems, such as due to device
Existing scheme is similar to method, therefore the implementation of the specific device of this specification embodiment may refer to the implementation of preceding method, weight
Multiple place repeats no more.Used below, the software of predetermined function and/or hard may be implemented in term " unit " or " module "
The combination of part.Although device described in following embodiment is preferably realized with software, hardware or software and hardware
The realization of combination be also that may and be contemplated.Specifically, Fig. 3 indicates a kind of finance reimbursement data processing that specification provides
The modular structure schematic diagram of Installation practice, as shown in figure 3, the apparatus may include:
Data acquisition module 102 can be used for obtaining the reimbursement voucher image of reimbursement application to be processed;
Image cutting module 104 can be used for carrying out the reimbursement voucher image according to determining reimbursement key area
Image cutting processing obtains the corresponding image slice of the reimbursement key area;
Picture recognition module 106 can be used for carrying out pictograph identifying processing to the image slice, obtain the shadow
As being sliced corresponding substructuring data;
Data check module 108 can be used for the corresponding minor structure of each image slice of the reimbursement application to be processed
Change data to be integrated, the structural data of the reimbursement application to be processed is formed, according to default verification rule to the structure
Change data to be verified;
Data transfer module 110, can be used for transferring the substructuring data pair that preset requirement is unsatisfactory in check results
The image slice answered, to be modified processing to the structural data.
In another embodiment of this specification, described image cutting module 104 may include:
Type of credentials determination unit can be used for carrying out type identification processing to the reimbursement voucher image, described in acquisition
The type of credentials of reimbursement voucher image;
Image cutting unit can be used for determining that the corresponding image of the reimbursement voucher image is cut according to the type of credentials
Divide algorithm, image cutting processing is carried out to the reimbursement voucher image using described image segmentation algorithm.
In another embodiment of this specification, the data check module 108 may include:
Rule determination unit is verified, can be used for obtaining the reimbursement type of the reimbursement application to be processed, according to the report
Pin type determines the corresponding verification rule of the reimbursement voucher image;
Data check unit can be used for verifying the structural data according to the corresponding verification rule.
In another embodiment of this specification, described image identification module 106 may include:
Judging unit can be used for judging whether recognition failures will identify image slice if image slice recognition failures
The image slice of failure is used as to amended record image slice;
Amended record unit can be used for carrying out described distribute to amended record image slice at least two amended record terminals at amended record
Reason obtains described to the corresponding at least two amended records data of amended record image slice;
Verification unit can be used for carrying out consistency desired result at least two amended records data, when check results meet
It is required that when, using the amended record data as the substructuring data to amended record image slice.
It should be noted that device described above can also include other embodiment party according to the description of embodiment of the method
Formula.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
This specification one or more embodiment provide finance reimbursement data processing equipment, can by first to reimbursement with
Card carries out image cutting processing, the corresponding image slice of reimbursement key area is obtained, it is then possible to carry out again to each image slice
Text region forms structural data.Later, automation verification can be carried out to structural data based on preset rules again, it is right
The problematic data of checked result can transfer the amended record that corresponding image slice quickly realizes information, thus significantly
It improves information checking and checks the efficiency of amended record processing.Meanwhile being realized when amended record due to can use image slice,
Amended record can also be carried out using third-party form is contracted out to, without having to worry about information leakage, on the basis of ensuring information security property
On, the efficiency of finance reimbursement data processing is further increased, the workload of financial staff is reduced.
Method or apparatus described in above-described embodiment that this specification provides can realize that business is patrolled by computer program
It collects and records on a storage medium, the storage medium can be read and be executed with computer, realize this specification embodiment institute
The effect of description scheme.Therefore, this specification also provide it is a kind of finance reimbursement data processing equipment, including processor and storage at
Manage device executable instruction memory, when described instruction is executed by the processor realization the following steps are included:
Obtain the reimbursement voucher image of reimbursement application to be processed;
Image cutting processing is carried out to the reimbursement voucher image according to determining reimbursement key area, obtains the reimbursement
The corresponding image slice of key area;
Pictograph identifying processing is carried out to the image slice, obtains the corresponding substructuring number of the image slice
According to;
The corresponding substructuring data of each image slice of the reimbursement application to be processed are integrated, formed it is described to
The structural data of processing reimbursement application verifies the structural data according to default verification rule;
The corresponding image slice of substructuring data that preset requirement is unsatisfactory in check results is transferred, to the structure
Change data and is modified processing.
The storage medium may include the physical unit for storing information, usually by after information digitalization again with benefit
The media of the modes such as electricity consumption, magnetic or optics are stored.It may include: that letter is stored in the way of electric energy that the storage medium, which has,
The device of breath such as, various memory, such as RAM, ROM;The device of information is stored in the way of magnetic energy such as, hard disk, floppy disk, magnetic
Band, core memory, magnetic bubble memory, USB flash disk;Using optical mode storage information device such as, CD or DVD.Certainly, there are also it
Readable storage medium storing program for executing of his mode, such as quantum memory, graphene memory etc..
It should be noted that equipment described above can also include other embodiment party according to the description of embodiment of the method
Formula.Concrete implementation mode is referred to the description of related method embodiment, does not repeat one by one herein.
Finance described in above-described embodiment submit an expense account data processing equipment, can be by first carrying out image cutting to reimbursement voucher
Processing obtains the corresponding image slice of reimbursement key area and is formed it is then possible to carry out Text region to each image slice again
Structural data.Later, automation verification can be carried out to structural data based on preset rules again, it is problematic to checked result
Data, can transfer corresponding image slice come quickly realize the amended record of information, thus increase substantially information checking with
And the efficiency of verification amended record processing.Meanwhile being realized when amended record due to can use image slice, outsourcing can also be used
Amended record, which is carried out, to third-party form on the basis of ensuring information security property, further increases wealth without having to worry about information leakage
The efficiency of business reimbursement data processing, reduces the workload of financial staff.
This specification also provides a kind of finance reimbursement data processing system, and the system can submit an expense account number for individually finance
According to processing system, can also apply in a variety of computer data processing systems.The system can be individual server,
It also may include the server set for having used one or more the methods or one or more embodiment devices of this specification
Group, system (including distributed system), software (application), practical operation device, logic gates device, quantum computer etc. are simultaneously
In conjunction with the necessary terminal installation for implementing hardware.The finance reimbursement data processing system may include at least one processor with
And the memory of storage computer executable instructions, the processor realized when executing described instruction it is above-mentioned any one or it is more
The step of method described in a embodiment.
Fig. 4 indicates a kind of finance reimbursement data processing system structural schematic diagram that this specification provides.As shown in figure 4, should
System may include that voucher scan module, image processing module, finance reimbursement module and depth excavate module.Voucher scan module
After being scanned to reimbursement voucher, certificate image can be sent to image processing module.The mould of Fig. 5 expression image processing module
Block structure schematic diagram, as shown in figure 5, the image processing module may include image identification module, image cutting module and benefit
Record module.Image identification module, image cutting module can carry out image cutting and image recognition processing to certificate image, for
The image of recognition failures can use amended record module and carry out amended record processing.
Certificate image and structural data can be sent to finance reimbursement module by image processing module.Fig. 6 indicates finance
The modular structure schematic diagram of module is submitted an expense account, as shown in fig. 6, the finance reimbursement module may include auditing rule engine, finance
Audit engine, payment module and financial amended record module.Auditing rule engine can carry out certificate image and structural data
Verification, financial audit module can audit check results, and if there is wrong data, then financial amended record module can be with
Amended record processing is carried out to wrong data.When structural data is without mistake, then it can be transferred to payment module and carry out reimbursement processing.
Meanwhile image processing module and finance reimbursement module can also be reported by certificate image, structural data and by finance
Pin data are sent to depth and excavate module.Fig. 7 indicates that depth excavates the modular structure schematic diagram of module, as shown in fig. 7, the depth
It may include reimbursement file store, depth excavation module and machine learning module that degree, which excavates module,.Examining the data that pass through can be with
As the image recognition data marked, automaton study is carried out, further increases image recognition accuracy, while can be with
Reimbursement file store is improved, for data analysis mining.
It should be noted that system described above can also include others according to the description of method or Installation practice
Embodiment, concrete implementation mode are referred to the description of related method embodiment, do not repeat one by one herein.
Finance described in above-described embodiment submit an expense account data processing system, can be by first carrying out image cutting to reimbursement voucher
Processing obtains the corresponding image slice of reimbursement key area and is formed it is then possible to carry out Text region to each image slice again
Structural data.Later, automation verification can be carried out to structural data based on preset rules again, it is problematic to checked result
Data, can transfer corresponding image slice come quickly realize the amended record of information, thus increase substantially information checking with
And the efficiency of verification amended record processing.Meanwhile being realized when amended record due to can use image slice, outsourcing can also be used
Amended record, which is carried out, to third-party form on the basis of ensuring information security property, further increases wealth without having to worry about information leakage
The efficiency of business reimbursement data processing, reduces the workload of financial staff.
It should be noted that this specification device or system described above according to the description of related method embodiment also
It may include other embodiments, concrete implementation mode is referred to the description of embodiment of the method, does not go to live in the household of one's in-laws on getting married one by one herein
It states.All the embodiments in this specification are described in a progressive manner, and same and similar part is mutual between each embodiment
Mutually referring to each embodiment focuses on the differences from other embodiments.Especially for hardware+program
For class, storage medium+program embodiment, since it is substantially similar to the method embodiment, so be described relatively simple, it is related
Place illustrates referring to the part of embodiment of the method.
This specification embodiment is not limited to comply with standard data model/template or this specification embodiment institute
The case where description.It is modified slightly in certain professional standards or the practice processes for using customized mode or embodiment to describe
Embodiment also may be implemented above-described embodiment it is identical, it is equivalent or it is close or deformation after it is anticipated that implementation result.Using these
The embodiment of the acquisitions such as modification or deformed data acquisition, storage, judgement, processing mode, still may belong to this specification
Optional embodiment within the scope of.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, vehicle-mounted human-computer interaction device, cellular phone, camera phone, smart phone, individual
Digital assistants, media player, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or
The combination of any equipment in these equipment of person.
For convenience of description, it is divided into various modules when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each module can be realized in the same or multiple software and or hardware when specification one or more, it can also be with
The module for realizing same function is realized by the combination of multiple submodule or subelement etc..Installation practice described above is only
It is only illustrative, for example, in addition the division of the unit, only a kind of logical function partition can have in actual implementation
Division mode, such as multiple units or components can be combined or can be integrated into another system or some features can be with
Ignore, or does not execute.Another point, shown or discussed mutual coupling, direct-coupling or communication connection can be logical
Some interfaces are crossed, the indirect coupling or communication connection of device or unit can be electrical property, mechanical or other forms.
It is also known in the art that other than realizing controller in a manner of pure computer readable program code, it is complete
Entirely can by by method and step carry out programming in logic come so that controller with logic gate, switch, specific integrated circuit, programmable
Logic controller realizes identical function with the form for being embedded in microcontroller etc..Therefore this controller is considered one kind
Hardware component, and the structure that the device for realizing various functions that its inside includes can also be considered as in hardware component.Or
Person even, can will be considered as realizing the device of various functions either the software module of implementation method can be hardware again
Structure in component.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method or equipment of element.
It will be understood by those skilled in the art that this specification one or more embodiment can provide as method, system or calculating
Machine program product.Therefore, this specification one or more embodiment can be used complete hardware embodiment, complete software embodiment or
The form of embodiment combining software and hardware aspects.Moreover, this specification one or more embodiment can be used at one or
It is multiple wherein include computer usable program code computer-usable storage medium (including but not limited to magnetic disk storage,
CD-ROM, optical memory etc.) on the form of computer program product implemented.
This specification one or more embodiment can computer executable instructions it is general on
It hereinafter describes, such as program module.Generally, program module includes executing particular task or realization particular abstract data type
Routine, programs, objects, component, data structure etc..This this specification one can also be practiced in a distributed computing environment
Or multiple embodiments, in these distributed computing environments, by being held by the connected remote processing devices of communication network
Row task.In a distributed computing environment, program module can be located at the local and remote computer including storage equipment
In storage medium.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ",
The description of " specific example " or " some examples " etc. means specific features described in conjunction with this embodiment or example, structure, material
Or feature is contained at least one embodiment or example of this specification.In the present specification, to the signal of above-mentioned term
Property statement must not necessarily be directed to identical embodiment or example.Moreover, specific features, structure, material or the spy of description
Point may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other,
Those skilled in the art can be by different embodiments or examples described in this specification and different embodiments or examples
Feature is combined.
The foregoing is merely the embodiments of this specification, are not limited to this specification.For art technology
For personnel, this specification can have various modifications and variations.It is all made any within the spirit and principle of this specification
Modification, equivalent replacement, improvement etc., should be included within the scope of the claims of this specification.
Claims (11)
1. a kind of finance reimbursement data processing method characterized by comprising
Obtain the reimbursement voucher image of reimbursement application to be processed;
Image cutting processing is carried out to the reimbursement voucher image according to determining reimbursement key area, it is crucial to obtain the reimbursement
The corresponding image slice in region;
Pictograph identifying processing is carried out to the image slice, obtains the corresponding substructuring data of the image slice;
The corresponding substructuring data of each image slice of the reimbursement application to be processed are integrated, are formed described to be processed
The structural data for submitting an expense account application verifies the structural data according to default verification rule;
The corresponding image slice of substructuring data that preset requirement is unsatisfactory in check results is transferred, to the structuring number
It is handled according to being modified.
2. the method according to claim 1, wherein described carry out at image cutting the reimbursement voucher image
Reason, comprising:
Type identification processing is carried out to the reimbursement voucher image, obtains the type of credentials of the reimbursement voucher image;
The corresponding image segmentation algorithm of the reimbursement voucher image is determined according to the type of credentials, is calculated using described image cutting
Method carries out image cutting processing to the reimbursement voucher image.
3. the method according to claim 1, wherein the default verification rule of the basis is to the structural data
It is verified, comprising:
The reimbursement type for obtaining the reimbursement application to be processed, determines that the reimbursement voucher image is corresponding according to the reimbursement type
Verification rule;
The structural data is verified according to the corresponding verification rule.
4. the method according to claim 1, wherein described carry out at pictograph identification the image slice
Reason, obtains the corresponding substructuring data of the image slice, comprising:
If image slice recognition failures, using the image slice of recognition failures as to amended record image slice;
Described distribute to amended record image slice at least two amended record terminals is subjected to amended record processing, is obtained described to amended record image
It is sliced corresponding at least two amended records data;
Consistency desired result is carried out at least two amended records data, when check results are met the requirements, by the amended record data
As the substructuring data to amended record image slice.
5. method according to claim 1-4, which is characterized in that the method also includes:
The image slice for the reimbursement application to be processed that audit passes through and the corresponding structural data of image slice are updated to report
Sell sample set;
Using updated reimbursement sample set to image cutting processing and the corresponding machine learning model of pictograph identifying processing
It is updated processing.
6. a kind of finance reimbursement data processing equipment, which is characterized in that described device includes:
Data acquisition module, for obtaining the reimbursement voucher image of reimbursement application to be processed;
Image cutting module, for being carried out at image cutting according to determining reimbursement key area to the reimbursement voucher image
Reason obtains the corresponding image slice of the reimbursement key area;
It is corresponding to obtain the image slice for carrying out pictograph identifying processing to the image slice for picture recognition module
Substructuring data;
Data check module, it is whole for carrying out the corresponding substructuring data of each image slice of the reimbursement application to be processed
It closes, forms the structural data of the reimbursement application to be processed, school is carried out to the structural data according to default verification rule
It tests;
Data transfer module, are unsatisfactory for the corresponding image of substructuring data of preset requirement in check results for transferring and cut
Piece, to be modified processing to the structural data.
7. device according to claim 6, which is characterized in that described image cutting module includes:
Type of credentials determination unit obtains the reimbursement voucher for carrying out type identification processing to the reimbursement voucher image
The type of credentials of image;
Image cutting unit, for determining the corresponding image segmentation algorithm of the reimbursement voucher image according to the type of credentials,
Image cutting processing is carried out to the reimbursement voucher image using described image segmentation algorithm.
8. device according to claim 6, which is characterized in that the data check module includes:
Rule determination unit is verified, it is true according to the reimbursement type for obtaining the reimbursement type of the reimbursement application to be processed
Determine the corresponding verification rule of the reimbursement voucher image;
Data check unit, for being verified according to the corresponding verification rule to the structural data.
9. device according to claim 6, which is characterized in that described image identification module includes:
Judging unit, for judge image slice whether recognition failures, if image slice recognition failures, by the shadow of recognition failures
As slice is as to amended record image slice;
Amended record unit is obtained for described distribute to amended record image slice at least two amended record terminals to be carried out amended record processing
It is described to the corresponding at least two amended records data of amended record image slice;
Verification unit, will when check results are met the requirements for carrying out consistency desired result at least two amended records data
The amended record data are as the substructuring data to amended record image slice.
10. a kind of finance reimbursement data processing equipment, which is characterized in that including processor and for the executable finger of storage processor
The memory of order, when described instruction is executed by the processor realize the following steps are included:
Obtain the reimbursement voucher image of reimbursement application to be processed;
Image cutting processing is carried out to the reimbursement voucher image according to determining reimbursement key area, it is crucial to obtain the reimbursement
The corresponding image slice in region;
Pictograph identifying processing is carried out to the image slice, obtains the corresponding substructuring data of the image slice;
The corresponding substructuring data of each image slice of the reimbursement application to be processed are integrated, are formed described to be processed
The structural data for submitting an expense account application verifies the structural data according to default verification rule;
The corresponding image slice of substructuring data that preset requirement is unsatisfactory in check results is transferred, to the structuring number
It is handled according to being modified.
11. a kind of finance reimbursement data processing system, which is characterized in that the system comprises at least one processor and storages
The memory of computer executable instructions, the processor realize any one of the claim 1-5 institute when executing described instruction
The step of stating method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910681472.0A CN110378343A (en) | 2019-07-26 | 2019-07-26 | A kind of finance reimbursement data processing method, apparatus and system |
CN202010068639.9A CN111079755B (en) | 2019-07-26 | 2020-01-21 | Financial reimbursement data processing method, device and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910681472.0A CN110378343A (en) | 2019-07-26 | 2019-07-26 | A kind of finance reimbursement data processing method, apparatus and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110378343A true CN110378343A (en) | 2019-10-25 |
Family
ID=68256219
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910681472.0A Pending CN110378343A (en) | 2019-07-26 | 2019-07-26 | A kind of finance reimbursement data processing method, apparatus and system |
CN202010068639.9A Active CN111079755B (en) | 2019-07-26 | 2020-01-21 | Financial reimbursement data processing method, device and system |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010068639.9A Active CN111079755B (en) | 2019-07-26 | 2020-01-21 | Financial reimbursement data processing method, device and system |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN110378343A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111104853A (en) * | 2019-11-11 | 2020-05-05 | 中国建设银行股份有限公司 | Image information input method and device, electronic equipment and storage medium |
CN111311197A (en) * | 2020-03-05 | 2020-06-19 | 中国工商银行股份有限公司 | Travel data processing method and device |
CN111428633A (en) * | 2020-03-23 | 2020-07-17 | 中国建设银行股份有限公司 | Voucher image processing method, device, equipment and medium |
CN111931666A (en) * | 2020-08-13 | 2020-11-13 | 中国工商银行股份有限公司 | Automatic certificate processing system and method |
CN112766254A (en) * | 2021-01-19 | 2021-05-07 | 中国工商银行股份有限公司 | Automatic testing method and device for voucher information input |
CN114648776A (en) * | 2022-05-24 | 2022-06-21 | 威海海洋职业学院 | Financial reimbursement data processing method and processing system |
CN116186543A (en) * | 2023-03-01 | 2023-05-30 | 深圳崎点数据有限公司 | Financial data processing system and method based on image recognition |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111881881A (en) * | 2020-08-10 | 2020-11-03 | 晶璞(上海)人工智能科技有限公司 | Machine intelligent text recognition credibility judgment method based on multiple dimensions |
CN113239770B (en) * | 2021-04-30 | 2022-12-20 | 国网河北省电力有限公司沧州供电分公司 | Financial statement accounting method |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102156855A (en) * | 2011-03-30 | 2011-08-17 | 信雅达系统工程股份有限公司 | Bank voucher data collection method based on image segmentation |
CN103914907B (en) * | 2014-04-14 | 2016-08-10 | 陕西海基业高科技实业有限公司 | Paper-bill information identification and core calibration system and application process |
CN104751194A (en) * | 2015-04-27 | 2015-07-01 | 陈包容 | Processing method and processing device for financial expense reimbursement |
CN105678612A (en) * | 2015-12-30 | 2016-06-15 | 远光软件股份有限公司 | Mobile terminal original certificate electronic intelligent filling system and method |
CN107507082A (en) * | 2017-07-14 | 2017-12-22 | 太仓诚泽网络科技有限公司 | A kind of business finance submits an expense account system |
WO2019118472A1 (en) * | 2017-12-11 | 2019-06-20 | Walmart Apollo, Llc | System and method for the detection and visualization of reported etics cases within an organization |
CN109887153B (en) * | 2019-02-03 | 2021-08-24 | 国信电子票据平台信息服务有限公司 | Finance and tax processing method and system |
-
2019
- 2019-07-26 CN CN201910681472.0A patent/CN110378343A/en active Pending
-
2020
- 2020-01-21 CN CN202010068639.9A patent/CN111079755B/en active Active
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111104853A (en) * | 2019-11-11 | 2020-05-05 | 中国建设银行股份有限公司 | Image information input method and device, electronic equipment and storage medium |
CN111311197A (en) * | 2020-03-05 | 2020-06-19 | 中国工商银行股份有限公司 | Travel data processing method and device |
CN111428633A (en) * | 2020-03-23 | 2020-07-17 | 中国建设银行股份有限公司 | Voucher image processing method, device, equipment and medium |
CN111931666A (en) * | 2020-08-13 | 2020-11-13 | 中国工商银行股份有限公司 | Automatic certificate processing system and method |
CN111931666B (en) * | 2020-08-13 | 2024-02-13 | 中国工商银行股份有限公司 | Automatic certificate processing system and method |
CN112766254A (en) * | 2021-01-19 | 2021-05-07 | 中国工商银行股份有限公司 | Automatic testing method and device for voucher information input |
CN112766254B (en) * | 2021-01-19 | 2024-02-02 | 中国工商银行股份有限公司 | Automatic test method and device for inputting credential information |
CN114648776A (en) * | 2022-05-24 | 2022-06-21 | 威海海洋职业学院 | Financial reimbursement data processing method and processing system |
CN116186543A (en) * | 2023-03-01 | 2023-05-30 | 深圳崎点数据有限公司 | Financial data processing system and method based on image recognition |
CN116186543B (en) * | 2023-03-01 | 2023-08-22 | 深圳崎点数据有限公司 | Financial data processing system and method based on image recognition |
Also Published As
Publication number | Publication date |
---|---|
CN111079755B (en) | 2021-05-25 |
CN111079755A (en) | 2020-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110378343A (en) | A kind of finance reimbursement data processing method, apparatus and system | |
KR102171220B1 (en) | Character recognition method, device, server and storage medium of claim documents | |
CN110209764B (en) | Corpus annotation set generation method and device, electronic equipment and storage medium | |
US9171072B2 (en) | System and method for real-time dynamic measurement of best-estimate quality levels while reviewing classified or enriched data | |
CN109034069B (en) | Method and apparatus for generating information | |
CA3225621A1 (en) | Ai-augmented auditing platform including techniques for automated document processing | |
US20210366055A1 (en) | Systems and methods for generating accurate transaction data and manipulation | |
CN110688536A (en) | Label prediction method, device, equipment and storage medium | |
Liu et al. | Clustering crowdsourced test reports of mobile applications using image understanding | |
CN110147941A (en) | Content of examination acquisition methods, Stakeholder Evaluation method and device | |
CN114419631A (en) | Network management virtual system based on RPA | |
CN113221918A (en) | Target detection method, and training method and device of target detection model | |
KR102232880B1 (en) | Method for evaluating inspector of crowdsourcing based projects for collecting image or video for artificial intelligence training data generation | |
CN111915186A (en) | Multi-source data management system for city infrastructure construction | |
CN106649121A (en) | Test result analysis method and apparatus | |
CN116453125A (en) | Data input method, device, equipment and storage medium based on artificial intelligence | |
CN111859985B (en) | AI customer service model test method and device, electronic equipment and storage medium | |
CN110309047B (en) | Test point generation method, device and system | |
CN114968816A (en) | Data simulation-based strategy testing method, device, equipment and storage medium | |
CN107403199A (en) | Data processing method and device | |
CN114443493A (en) | Test case generation method and device, electronic equipment and storage medium | |
Johnson et al. | Where does my model underperform? a human evaluation of slice discovery algorithms | |
CN112328787B (en) | Text classification model training method and device, terminal equipment and storage medium | |
CN116340864B (en) | Model drift detection method, device, equipment and storage medium thereof | |
CN112612882B (en) | Review report generation method, device, equipment and storage medium |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191025 |