CN108960223A - The method for automatically generating voucher based on bill intelligent recognition - Google Patents
The method for automatically generating voucher based on bill intelligent recognition Download PDFInfo
- Publication number
- CN108960223A CN108960223A CN201810483413.8A CN201810483413A CN108960223A CN 108960223 A CN108960223 A CN 108960223A CN 201810483413 A CN201810483413 A CN 201810483413A CN 108960223 A CN108960223 A CN 108960223A
- Authority
- CN
- China
- Prior art keywords
- voucher
- bill
- templates
- key message
- voucher templates
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- 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
- G06Q40/123—Tax preparation or submission
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Technology Law (AREA)
- Character Input (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention provides a kind of method for automatically generating voucher based on bill intelligent recognition, itself the following steps are included: S1, by bill upload carry out intelligent recognition, key message is extracted, and classification processing is carried out to bill according to the key message extracted, and key message is made to be associated with and store with bill;S2, in voucher templates system, preset voucher templates database, the source of voucher templates mainly includes that manually generated, system generates and false form conversion generates;S3, matching template generate voucher;S4, scrip is handled manually.The present invention is arranged by the electronic data that intelligent recognition is got and is saved, establish index relative, according to classification and matching voucher templates, generate accurately and effectively credential information, and credential information is associated with original document, to reduce the workload of accountant, working efficiency is improved, it will meter personnel free from many and diverse invoice ocean.
Description
Technical field
The present invention relates to bill intelligent recognition fields, automatically generate voucher based on bill intelligent recognition more particularly to one kind
Method.
Background technique
In present electronic information, the method that processing bill generates voucher, is all to carry out original document by accounting
Manual arranging, then work out voucher in systems, not only workload is especially big for such way, but also is easy to appear mistake
Accidentally, it needs accounting repeatedly to check, leverages working efficiency.Especially in some medium-sized or small-sized enterprise, due to
Lack outstanding accounting, the problem for being very easy to occur in accounting voucher processing.
Constantly bringing forth new ideas and popularizing with Internet technology, artificial intelligence have obtained further extensively in computer field
Attention, more and more industries start to be that enterprise creates value, and obtains in the identification of bill more next with artificial intelligence
More it is widely applied.Bill barcode scanning identification based on artificial intelligence technology (intelligent recognition) can carry out the bill space of a whole page automatic
Identification made breakthrough progress, and make it possible that ticket contents become electronic data, to achieve the purpose that intelligently to keep accounts.
However the processing for these electronic data after identification, how to be converted into accurate and effective financial data becomes new problem.
Summary of the invention
In order to overcome the drawbacks of the prior art, the present invention provides a kind of side that voucher is automatically generated based on bill intelligent recognition
Method is arranged by the electronic data that intelligent recognition is got and is saved, establishes index relative, raw according to classification and matching voucher templates
It is associated at accurately and effectively credential information, and by credential information with original document, to reduce the workload of accountant, improves
Working efficiency, it will meter personnel free from many and diverse invoice ocean.
Specifically, the present invention provides a kind of method for automatically generating voucher based on bill intelligent recognition comprising following step
It is rapid:
S1, in voucher templates system, preset voucher templates form voucher templates database, and the source of voucher templates is main
It is generated including system, the conversion of manually generated and false form, the method that system generates voucher templates is according to bill type, quotient
Product attribute, abstract and currency be created that thousands of a voucher templates and import voucher templates system, manually generated voucher templates
Method is the voucher templates that user is special according to the business rule of oneself supplement increase in use, false form conversion life
Method at voucher templates is that the false form in use process is converted into voucher templates;
S2, by bill upload carry out intelligent recognition, extract key message, and according to the key message extracted to bill into
Row classification processing, and be associated with key message with bill and be stored in voucher templates system, key message database is formed, is made
Key message is associated with bill method particularly includes: and an invoice is uploaded, and generates bill unique identifier in upload procedure,
And intelligent recognition is carried out to this invoice, it extracts after key message is corresponded with bill unique identifier and deposits from invoice
In voucher templates, the key message includes bill type, beneficiary, paying party, detail of making out an invoice and the amount of money for storage;
S3, matching template generate voucher, specifically includes the following steps:
Bill electronic data and voucher templates are matched, generate final voucher by voucher templates: first according to bill
Point data extract key message, the key message includes bill type and company's information, then true according to key message
The type of booking evidence and the data environment of the bill, and in the data environment based on the type of the bill and the bill and step S1
The key message database of generation carries out retrieval comparison, and is selected in the voucher templates database in S2 according to comparison result pair
The voucher templates answered are as final voucher;
S4, manual processing, manual intervention: handle manually scrip, if credential information is errorless, be adjusted to formally with
Card;If credential information is inaccurate, voucher is modified, generates formal voucher.After generating formal voucher, according to bill electric information
A new voucher templates are generated with voucher subject;
S5, the bill for generating voucher templates is labeled as having identified.
Preferably, the first similarity threshold and the second similarity threshold are previously provided in voucher templates database.
Preferably, retrieval in step S3 compare specifically includes the following steps:
The similarity mode of S31, text: the key message of extraction is subjected to characters matching, key message can form one
New character strings are compared by new character string and existing key message in the key message database of voucher templates system
Compared with confirming its similarity, and voucher templates corresponding to the highest key message of the similarity stored in selecting system are stand-by
Template;
S32, the similarity that step S31 is obtained is compared with the first similarity threshold and the second similarity threshold,
If the similarity is higher than the first similarity threshold, choosing the stand-by template is final voucher,
If lower than the first similarity threshold and being greater than or equal to the second similarity threshold, electronic data is generated one
False form and scrip are classified as first kind false form and scrip, enter step S4;
If the similarity be lower than the second similarity threshold, equally by electronic data generate a false form and temporarily with
Card, but need that the false form and scrip is marked, it is classified as the second class false form and scrip, is entered step
S4。
Preferably, text matching rule is by each Chinese character according to phonetic, four corner braces, font and pen in step S31
The mode for drawing number is converted to form a new character string.
Preferably, system generates voucher templates in step S2 method particularly includes: system is according to bill type, commodity category
Property, abstract and currency generate a voucher templates, after generating formal voucher templates, by the information extraction of the voucher templates
It is matched out with the information of the voucher templates in system, the voucher templates of information generation is ignored if successful match,
A new voucher templates are generated if matching is unsuccessful to be stored.
Preferably, scrip template generation voucher templates in step S2 method particularly includes: scrip template source
In scrip, scrip is manually adjusted, generates a formal voucher after having adjusted, asks the user whether to delete scrip
Template if it is deletes false form, if it is not, then the false form can be converted to one newly according to the formal voucher of generation
Voucher templates stored.
Preferably, the information of voucher templates includes subject information, summary info and billing information.
It preferably, is that bill passes through intelligence knowledge according to the specific method that the point data of bill extracts key message in step S3
Information classification, and the key message of the corresponding classification of classification information assembling defined according to system are not obtained afterwards.
Preferably, the first similarity threshold is 85-95% in step S32, and the second similarity threshold is 65-75%.
Compared with prior art, the invention has the following advantages:
The electronic data that the present invention is got by intelligent recognition, which arranges, to be saved, and index relative is established, according to classification and matching with
Template is demonstrate,proved, accurately and effectively credential information is generated, and credential information is associated with original document, to reduce the work of accountant
It measures, improves working efficiency, it will meter personnel free from many and diverse invoice ocean.
Accountant can generate voucher templates during identifying bill, and call directly in work later
For the voucher templates of the bill type, and during identifying bill, constantly study generates new voucher templates, expands
Voucher templates in system template library.
The invention proposes a kind of new methods for generating voucher, and which solve the walls of this field puzzlement technical staff
It builds, artificial intelligence is added to accountant and is made in the method for voucher, working efficiency is increased.
Detailed description of the invention
Fig. 1 is workflow schematic diagram of the invention;
Fig. 2 is the schematic diagram of bank slip recognition classification in the embodiment of the present invention;
Fig. 3 is the schematic diagram of matched voucher templates in the embodiment of the present invention;
Fig. 4 is the schematic diagram that invoice is marked in the embodiment of the present invention;
Fig. 5 is the schematic diagram of storing bill information in the embodiment of the present invention.
Specific embodiment
Below with reference to the attached drawing exemplary embodiment that the present invention will be described in detail, feature and aspect.It is identical attached in attached drawing
Icon note indicates element functionally identical or similar.Although the various aspects of embodiment are shown in the attached drawings, unless special
It does not point out, it is not necessary to attached drawing drawn to scale.
Specifically, the present invention provides a kind of method for automatically generating voucher based on bill intelligent recognition, as shown in Figure 1, its
The following steps are included:
S1, in voucher templates system, preset voucher templates form voucher templates database, and the source of voucher templates is main
It is generated including system, the conversion of manually generated and false form.
It is thousands of to be created that according to bill type, item property, abstract and currency that system generates the method for voucher templates
A voucher templates simultaneously import voucher templates system, and the method for manually generated voucher templates is in the total user of use process according to oneself
Business rule supplement increase special voucher templates, the method that false form conversion generates voucher templates is will be in use process
False form be converted into voucher templates.
Preferably, system generates voucher templates in step S1 method particularly includes: system is according to bill type, commodity category
Property, abstract and currency generate a voucher templates, after generating formal voucher templates, by the information extraction of the voucher templates
It is matched out with the information of the voucher templates in system, the voucher templates of letter generation is ignored if successful match, such as
Fruit match it is unsuccessful, generate a new voucher templates stored.
Preferably, the information of voucher templates includes subject information, summary info and billing information.Voucher templates can be
Sale voucher, the buying voucher or other vouchers etc. of accountant's needs.
Preferably, scrip template generation voucher templates in step S1 method particularly includes: scrip template source
In scrip, scrip is manually adjusted, generates a formal voucher after having adjusted, asks the user whether to delete scrip
Template if it is deletes false form, if it is not, then the false form can be converted to one newly according to the formal voucher of generation
Voucher templates the step of being stored, generating new voucher templates and system the step of generating voucher templates as, in life
After formal voucher templates, the information of the voucher templates is extracted and the progress of the information of the voucher templates in system
Match, the voucher templates of letter generation are ignored if successful match, generates a new voucher templates if matching is unsuccessful
It is stored.
S2, by bill upload carry out intelligent recognition, extract key message, and according to the key message extracted to bill into
Row classification processing is associated with key message with bill and is stored in voucher templates system, forms key message database.
Keep key message associated with bill method particularly includes: to upload an invoice, and generate bill in upload procedure
Unique identifier, carries out intelligent recognition to this invoice, and key message is extracted from invoice and bill unique identifier carries out one
It is stored in voucher templates corresponding with the bill type after one correspondence.
The key message includes bill type, beneficiary, paying party, detail of making out an invoice and the amount of money.
When specifically used, bill is uploaded to system, and intelligent recognition is carried out to bill after the completion of upload, to ticket
During carrying out intelligent recognition, the key message of bill, and the bill key message obtained according to identification can be accessed
Classify to key message, to classify to bill itself, and key message is associated with bill and is stored in voucher
In template system, key message database is formed.Voucher templates can be sales template or the template that keeps accounts etc..
The intelligent recognition of bill, which can be taken, carries out the mixed mode swept to bill, extract the key message of bill, mixed to sweep
It is described that steps are as follows:
1, after intelligent identifying system learns a plurality of types of bills, the key message of all types of bills is carried out
It stores, identify the different key message of all types of bills and dismisses ticket and quota invoice definition of keywords for Bank bills, machine,
By constantly study storage during scanning bill, bill key message database, bill key message database packet are established
Include recognition sequence list, Keyword List, key message list and corresponding bill type list, Keyword List, key
Information list and corresponding bill type list are one-to-one.
Specifically, described in the following table of bill key message database:
Specific learning process is to scan a large amount of bills, and the key message of bill is distinguished, and the key of bill is believed
Breath is associated with actual bill type, and is directed to certain specific invoice definition of keywords, such as Bank bills, machine are dismissed
Ticket and quota invoice, this few class invoice define keyword in learning process, and keyword is corresponding with key message,
When identification, as long as pickup can be scanned to keyword, the key message of needs can be extracted from keyword.In other words, it is
Comprising the key message needed in the keyword that certain bills define, keyword is arrived as long as can scan, it will be able in keyword
Obtain the key message that keyword includes.The study of database is based on largely scanning, in practical applications, can also be direct
Define above-mentioned list, implant data library or increase further types of invoice type implant data library.
2, the scanning of various mixing bills is become by electronic edition image by scanner, is uploaded to intelligent identifying system and obtains pass
Key word, for the picture for tilting and rotating, intelligent identifying system automatic identification is simultaneously corrected.Electronic edition image can be color image
It is also possible to black white image.
3, the key message or keyword of the information and storage obtained to obtained electronic edition image according to scanning compare
It is right, the bill type of the bill is obtained, comparison sequence is carried out according to the sequence of recognition sequence list, if bill type is increment
Tax invoice, then checked, and is such as checked successfully, then examination result is back to intelligent recognition terminal and shown, such as examination is lost
It loses, is then classified as the invoice checking wrong class;If bill type is the invoice type except VAT invoice, by the invoice
Invoice type return directly to intelligent recognition terminal and shown, if the invoice type of the invoice can not be identified, by institute
Stating can not identify that the invoice of invoice type is classified as not identifying class and returns to recognition result.VAT invoice includes that value-added tax is common
Invoice, roll type bill, motor vehicle invoice, value-added tax ordinary electronic invoice and VAT invoice.
The keyword or key message defined before being to the information that obtained electronic edition image is obtained according to scanning, sweeps
Retouch to obtain mainly comprising the following steps for information and the two dimensional code of the invoice of scanning positioned, and to the content of two dimensional code storage inside into
The parsing of row two dimensional code, obtains information hiding inside two dimensional code, is compared after obtaining the information according to corresponding sequence, judges
The invoice type of invoice.
Preferably, step 3 specifically includes the following steps:
31, key message is directly extracted to obtained electronic edition image, if it directly can extract key message first
The value-added tax scanned in the key message list stored in obtained key message and bill key message database is commonly sent out
Ticket, roll type bill, motor vehicle invoice or VAT invoice key message column compare, if the invoice belongs to increment
Tax common invoice, roll type bill, motor vehicle invoice or VAT invoice, then checked, and hair is returned if checking successfully
Fare ticket type type and the corresponding key message of the invoice type, such as examination failure, then be classified as the invoice to check wrong class and return to knowledge
Other result;If key message cannot be extracted directly, carry out keyword extraction and obtained according to the keyword extracted to be somebody's turn to do
The corresponding key message of keyword simultaneously enters step 32;
32, by the bank money in the Keyword List stored in the keyword extracted and bill key message database
Key column compare, if the invoice belongs to bank money, according to the key for including in keyword recognition keyword
Information, surrender of bills type and corresponding key message enter step 33 if the invoice is not belonging to bank money;
33, the machine in the Keyword List stored in the keyword extracted and bill key message database is dismissed into ticket
Key column compare, if the invoice, which belongs to machine, dismisses ticket, according to the key for including in keyword recognition keyword
Information, surrender of bills type and corresponding key message enter step 34 if the invoice, which is not belonging to machine, dismisses ticket;
34, by the quota invoice in the Keyword List stored in the keyword extracted and bill key message database
Key column compare, if the invoice belongs to quota invoice, according to the key for including in keyword recognition keyword
Information, surrender of bills type and corresponding key message enter step 35 if the invoice is not belonging to quota invoice;
If 35, can not identify the invoice type of the invoice, the invoice that can not identify invoice type is classified as nothing
Method identification class simultaneously returns to recognition result.
4, to can not identify class or the tax bureau examination mistake invoice be recognized after image procossing, described image
The method of processing is determined according to unrecognized concrete reason, locking key message position is specifically included, according to pixel
The coordinate of point carries out stripping and slicing, eliminates red chapter, removal lines or carries out machine learning training to incomplete number.
S3, matching template generate voucher, specifically includes the following steps:
Bill electronic data and voucher templates are matched, generate final voucher by voucher templates: first according to bill
Point data extract key message, the point data of bill is obtained by the two dimensional code of scanning bill, and the key message includes bill
Then type and company's information determine the type of bill and the data environment of the bill according to key message, and are based on the ticket
According to type and the bill data environment and step S1 in the key message database that generates carry out retrieval and compare, and according to than
Select corresponding voucher templates as final voucher in voucher templates database in S2 result.
It preferably, is that bill passes through intelligence knowledge according to the specific method that the point data of bill extracts key message in step S3
Information classification, and the key message of the corresponding classification of classification information assembling defined according to system are not obtained afterwards.
Bill can determine whether the key message of data classification, data during intelligent recognition.It is right by these information
Matching template afterwards.
Preferably, retrieval in step S3 compare specifically includes the following steps:
The similarity mode of S31, text: the key message of extraction is subjected to characters matching, key message can form one
New character strings are compared by new character string and existing key message in the key message database of voucher templates system
Compared with confirming its similarity, and voucher templates corresponding to the highest key message of the similarity stored in selecting system are stand-by
Template.
S32, the similarity that step S31 is obtained is compared with the first similarity threshold and the second similarity threshold,
If the similarity is higher than the first similarity threshold, choosing the stand-by template is final voucher.
If lower than the first similarity threshold and being greater than or equal to the second similarity threshold, electronic data is generated one
False form and scrip are classified as first kind false form and scrip, enter step S4.
If the similarity be lower than the second similarity threshold, equally by electronic data generate a false form and temporarily with
Card, but need that the false form and scrip is marked, it is classified as the second class false form and scrip, is entered step
S4。
Preferably, text matching rule is by each Chinese character according to phonetic, four corner braces, font and pen in step S31
The mode for drawing number is converted to form a new character string.
Preferably, the first similarity threshold is 85-95% in step S32, and the second similarity threshold is 65-75%.It is being
System is initial in use, the first similarity threshold is 85%, and the second similarity threshold is 65%, generates the mistake of voucher in continuous identification
Cheng Zhong, system constantly learn, and the first similarity threshold and the second similarity threshold are increased also with the quantity that voucher generates.
S4, manual processing, manual intervention: handle manually scrip, if credential information is errorless, be adjusted to formally with
Card;If credential information is inaccurate, voucher is modified, generates formal voucher.After generating formal voucher, according to bill electric information
A new voucher templates are generated with voucher subject.
The false form and scrip of the first kind are than more complete, and the accuracy of the information matches such as subject, abstract is high, user
Modify small part information.And the false form and scrip information accuracy of the second class are generally lower, need to modify
Place is more, and user oneself is needed to adjust subject, abstract, even amount information.
S5, the bill for generating voucher templates is labeled as having identified.
Example is embodied
Step 1: bill is uploaded by online accounting voucher first, such as third class bank receipt bill;
Step 2: upload bill can be browsed in systems after the completion of bill uploads.
Step 3: by intelligent recognition, the billing information identified.The categorized completion in identification process, it is specific to know
Other classification is referred to Fig. 2.
Step 4: the Credential data generated, matches voucher templates, matched voucher mould by the classification information identified
Plate is referring to Fig. 3.
Step 5: being to have identified by the coupon identification after generation voucher, label result is referring to fig. 4.
It is stored in and the ticket Step 6: being extracted from invoice after key message is corresponded with bill unique identifier
According in the corresponding voucher templates of type, referring to Fig. 5.
The electronic data that the present invention is got by intelligent recognition, which arranges, to be saved, and index relative is established, according to classification and matching with
Template is demonstrate,proved, accurately and effectively credential information is generated, and credential information is associated with original document, to reduce the work of accountant
It measures, improves working efficiency, it will meter personnel free from many and diverse invoice ocean.
Accountant can generate voucher templates during identifying bill, and call directly in work later
For the voucher templates of the bill type, and during identifying bill, constantly study generates new voucher templates, expands
Voucher templates in system template library.
Finally, it should be noted that above-described embodiments are merely to illustrate the technical scheme, rather than to it
Limitation;Although the present invention is described in detail referring to the foregoing embodiments, those skilled in the art should understand that:
It can still modify to technical solution documented by previous embodiment, or to part of or all technical features into
Row equivalent replacement;And these modifications or substitutions, it does not separate the essence of the corresponding technical solution various embodiments of the present invention technical side
The range of case.
Claims (9)
1. a kind of method for automatically generating voucher based on bill intelligent recognition, it is characterised in that: itself the following steps are included:
S1, in voucher templates system, preset voucher templates form voucher templates database, and the source of voucher templates mainly includes
System generates, manually generated and false form is converted, and the method that system generates voucher templates is according to bill type, commodity category
Property, abstract and currency be created that thousands of a voucher templates and import voucher templates system, the method for manually generated voucher templates
It is supplemented for user in use according to the business rule of oneself and increases special voucher templates and be stored in voucher templates system
In system, the method that false form conversion generates voucher templates is that the false form in use process is converted into voucher templates and is deposited
Storage is in voucher templates system;
S2, bill is uploaded to progress intelligent recognition, extracts key message, and divide bill according to the key message extracted
Class processing, and be associated with key message with bill and be stored in voucher templates system, key message database is formed, key is made
Information is associated with bill method particularly includes: uploads an invoice, and generates bill unique identifier in upload procedure, and right
This invoice carries out intelligent recognition, extracts after key message is corresponded with bill unique identifier and is stored in from invoice
In voucher templates, the key message includes bill type, beneficiary, paying party, detail of making out an invoice and the amount of money;
S3, matching template generate voucher, specifically includes the following steps:
Bill electronic data and voucher templates are matched, generate final voucher by voucher templates: first according to the point of bill
Data extract key message, and the key message includes bill type and company's information, then determines ticket according to key message
According to type and the bill data environment, and generated in the data environment based on the type of the bill and the bill and step S1
Key message database carry out retrieval comparison, and selected in the voucher templates database in S2 according to comparison result corresponding
Voucher templates are as final voucher;
Manual intervention: S4, manual processing handle manually scrip if credential information is correct and are adjusted to formal voucher;
If credential information is inaccurate, voucher is modified, generates formal voucher.After generating formal voucher, according to bill electric information and
Voucher subject generates a new voucher templates;
S5, the bill for generating voucher templates is labeled as having identified.
2. the method according to claim 1 for automatically generating voucher based on bill intelligent recognition, it is characterised in that: voucher mould
The first similarity threshold and the second similarity threshold are previously provided in plate database.
3. the method according to claim 1 for automatically generating voucher based on bill intelligent recognition, it is characterised in that: step S3
In retrieval compare specifically includes the following steps:
The similarity mode of S31, text: the key message of extraction is subjected to characters matching, key message can form a new word
Symbol string, is compared by new character string with existing key message in the key message database of voucher templates system, really
Recognize its similarity, and voucher templates corresponding to the highest key message of the similarity stored in selecting system are stand-by template;
S32, the similarity that step S31 is obtained is compared with the first similarity threshold and the second similarity threshold, if
The similarity is higher than the first similarity threshold, then choosing the stand-by template is final voucher,
If lower than the first similarity threshold and being greater than or equal to the second similarity threshold, electronic data is generated one temporarily
Template and scrip are classified as first kind false form and scrip, enter step S4;
If the similarity is lower than the second similarity threshold, electronic data is equally generated into a false form and scrip,
But the false form and scrip is marked in needs, is classified as the second class false form and scrip, enters step S4.
4. the method according to claim 1 for automatically generating voucher based on bill intelligent recognition, it is characterised in that: step
Text matching rule is to convert to form one in the way of phonetic, four corner braces, font and stroke number by each Chinese character in S31
A new character string.
5. the method according to claim 1 for automatically generating voucher based on bill intelligent recognition, it is characterised in that: step S2
Middle system generates voucher templates method particularly includes: system generates one according to bill type, item property, abstract and currency
Voucher templates extract the information of the voucher templates and the voucher templates in system after generating formal voucher templates
Information matched, ignore if successful match the information generation voucher templates, if match it is unsuccessful if generate one
The voucher templates of Zhang Xin are stored.
6. the method according to claim 1 for automatically generating voucher based on bill intelligent recognition, it is characterised in that: step S2
Middle scrip template generation voucher templates method particularly includes: scrip template source manually adjusts and faces in scrip
When voucher, generate a formal voucher after having adjusted, ask the user whether to delete scrip template, if it is delete interim
Template is stored if it is not, then the false form can be converted to a new voucher templates according to the formal voucher of generation.
7. the method according to claim 1 for automatically generating voucher based on bill intelligent recognition, it is characterised in that: voucher mould
The information of plate includes subject information, summary info and billing information.
8. the method according to claim 1 for automatically generating voucher based on bill intelligent recognition, it is characterised in that: step S3
The middle specific method for extracting key message according to the point data of bill is bill by obtaining information classification, and root after intelligent recognition
According to the key message for the corresponding classification of classification information assembling that system defines.
9. the method according to claim 3 for automatically generating voucher based on bill intelligent recognition, it is characterised in that: step
The first similarity threshold is 85-95% in S32, and the second similarity threshold is 65-75%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810483413.8A CN108960223B (en) | 2018-05-18 | 2018-05-18 | Method for automatically generating voucher based on intelligent bill identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810483413.8A CN108960223B (en) | 2018-05-18 | 2018-05-18 | Method for automatically generating voucher based on intelligent bill identification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108960223A true CN108960223A (en) | 2018-12-07 |
CN108960223B CN108960223B (en) | 2020-10-30 |
Family
ID=64499292
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810483413.8A Active CN108960223B (en) | 2018-05-18 | 2018-05-18 | Method for automatically generating voucher based on intelligent bill identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108960223B (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109636557A (en) * | 2018-12-11 | 2019-04-16 | 厦门商集网络科技有限责任公司 | A kind of intelligent classification bookkeeping methods and equipment based on bank slip recognition |
CN109783790A (en) * | 2019-01-23 | 2019-05-21 | 国网山东省电力公司济宁供电公司 | One kind is secondary to pacify ticket generation method and the system of arranging |
CN109858016A (en) * | 2018-12-20 | 2019-06-07 | 航天信息股份有限公司 | A kind of business credential match method |
CN110210470A (en) * | 2019-06-05 | 2019-09-06 | 复旦大学 | Merchandise news image identification system |
CN110245656A (en) * | 2019-05-10 | 2019-09-17 | 上海果藤互联网金融信息服务有限公司 | A kind of bill operation management method and its system |
CN110399463A (en) * | 2019-07-29 | 2019-11-01 | 国网河北省电力有限公司 | The Similarity Match Method and device of work ticket |
CN110399851A (en) * | 2019-07-30 | 2019-11-01 | 广东工业大学 | A kind of image processing apparatus, method, equipment and readable storage medium storing program for executing |
CN110516664A (en) * | 2019-08-16 | 2019-11-29 | 咪咕数字传媒有限公司 | Bank slip recognition method, apparatus, electronic equipment and storage medium |
CN110765749A (en) * | 2019-09-12 | 2020-02-07 | 深圳微企宝计算机系统有限公司 | Method for intelligently generating certificate |
CN110851677A (en) * | 2019-11-18 | 2020-02-28 | 深圳春沐源控股有限公司 | Reimbursement certificate processing method, device, terminal and computer readable storage medium |
CN111178238A (en) * | 2019-12-25 | 2020-05-19 | 未鲲(上海)科技服务有限公司 | Certificate testing method, device, equipment and computer readable storage medium |
CN111210328A (en) * | 2019-12-31 | 2020-05-29 | 航天信息股份有限公司 | Voucher generation method and device, storage medium and electronic equipment |
CN111275037A (en) * | 2020-01-09 | 2020-06-12 | 上海知达教育科技有限公司 | Bill identification method and device |
CN111401002A (en) * | 2020-03-11 | 2020-07-10 | 山东浪潮通软信息科技有限公司 | Method, device and computer storage medium for automatically identifying PDF electronic receipt information |
CN111666885A (en) * | 2020-06-08 | 2020-09-15 | 成都知识视觉科技有限公司 | Template construction and matching method for medical document structured knowledge extraction |
CN111680983A (en) * | 2020-06-15 | 2020-09-18 | 山东理工职业学院 | Automatic accounting document generating device for database |
CN111783703A (en) * | 2020-07-07 | 2020-10-16 | 常州市第三人民医院 | Intelligent identification and automatic generation system and method for paper bills |
CN115311651A (en) * | 2022-10-12 | 2022-11-08 | 泰安协同软件有限公司 | Real estate voucher data acquisition and arrangement method |
CN116561602A (en) * | 2023-07-10 | 2023-08-08 | 三峡高科信息技术有限责任公司 | Automatic sales material matching method for sales cost transfer |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020143621A1 (en) * | 2001-03-30 | 2002-10-03 | Donnelly Dennis P. | System and method for transferring credits as an incentive for prompt payment |
WO2014052572A1 (en) * | 2012-09-28 | 2014-04-03 | Order Inn, Inc. | Method and system for offering combinations of goods and services for purchase and controlling expenses |
CN103761599A (en) * | 2013-12-23 | 2014-04-30 | 远光软件股份有限公司 | Method and device for generating compensating vouchers of internal transaction businesses |
CN105095842A (en) * | 2014-05-22 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying information of bill |
CN107423731A (en) * | 2017-04-06 | 2017-12-01 | 云南小鹰科技有限公司 | The data processing method and system of aviation document |
-
2018
- 2018-05-18 CN CN201810483413.8A patent/CN108960223B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020143621A1 (en) * | 2001-03-30 | 2002-10-03 | Donnelly Dennis P. | System and method for transferring credits as an incentive for prompt payment |
WO2014052572A1 (en) * | 2012-09-28 | 2014-04-03 | Order Inn, Inc. | Method and system for offering combinations of goods and services for purchase and controlling expenses |
CN103761599A (en) * | 2013-12-23 | 2014-04-30 | 远光软件股份有限公司 | Method and device for generating compensating vouchers of internal transaction businesses |
CN105095842A (en) * | 2014-05-22 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for identifying information of bill |
CN107423731A (en) * | 2017-04-06 | 2017-12-01 | 云南小鹰科技有限公司 | The data processing method and system of aviation document |
Non-Patent Citations (2)
Title |
---|
WANG HONG等: "The Research of Output and Authentication Methods of Digital Bills Based on the Fusion of Identity Information", 《IEEE》 * |
李春梅等: "具有QoS约束的语义Web服务发现的研究", 《计算机科学》 * |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109636557A (en) * | 2018-12-11 | 2019-04-16 | 厦门商集网络科技有限责任公司 | A kind of intelligent classification bookkeeping methods and equipment based on bank slip recognition |
CN109858016A (en) * | 2018-12-20 | 2019-06-07 | 航天信息股份有限公司 | A kind of business credential match method |
CN109783790A (en) * | 2019-01-23 | 2019-05-21 | 国网山东省电力公司济宁供电公司 | One kind is secondary to pacify ticket generation method and the system of arranging |
CN110245656A (en) * | 2019-05-10 | 2019-09-17 | 上海果藤互联网金融信息服务有限公司 | A kind of bill operation management method and its system |
CN110245656B (en) * | 2019-05-10 | 2021-02-02 | 上海果藤互联网金融信息服务有限公司 | Bill operation management method and system |
CN110210470A (en) * | 2019-06-05 | 2019-09-06 | 复旦大学 | Merchandise news image identification system |
CN110399463A (en) * | 2019-07-29 | 2019-11-01 | 国网河北省电力有限公司 | The Similarity Match Method and device of work ticket |
CN110399851A (en) * | 2019-07-30 | 2019-11-01 | 广东工业大学 | A kind of image processing apparatus, method, equipment and readable storage medium storing program for executing |
CN110399851B (en) * | 2019-07-30 | 2022-02-15 | 广东工业大学 | Image processing device, method, equipment and readable storage medium |
CN110516664A (en) * | 2019-08-16 | 2019-11-29 | 咪咕数字传媒有限公司 | Bank slip recognition method, apparatus, electronic equipment and storage medium |
CN110765749A (en) * | 2019-09-12 | 2020-02-07 | 深圳微企宝计算机系统有限公司 | Method for intelligently generating certificate |
CN110851677A (en) * | 2019-11-18 | 2020-02-28 | 深圳春沐源控股有限公司 | Reimbursement certificate processing method, device, terminal and computer readable storage medium |
CN111178238A (en) * | 2019-12-25 | 2020-05-19 | 未鲲(上海)科技服务有限公司 | Certificate testing method, device, equipment and computer readable storage medium |
CN111210328A (en) * | 2019-12-31 | 2020-05-29 | 航天信息股份有限公司 | Voucher generation method and device, storage medium and electronic equipment |
CN111275037A (en) * | 2020-01-09 | 2020-06-12 | 上海知达教育科技有限公司 | Bill identification method and device |
CN111275037B (en) * | 2020-01-09 | 2021-06-08 | 上海知达教育科技有限公司 | Bill identification method and device |
CN111401002A (en) * | 2020-03-11 | 2020-07-10 | 山东浪潮通软信息科技有限公司 | Method, device and computer storage medium for automatically identifying PDF electronic receipt information |
CN111666885A (en) * | 2020-06-08 | 2020-09-15 | 成都知识视觉科技有限公司 | Template construction and matching method for medical document structured knowledge extraction |
CN111680983A (en) * | 2020-06-15 | 2020-09-18 | 山东理工职业学院 | Automatic accounting document generating device for database |
CN111783703A (en) * | 2020-07-07 | 2020-10-16 | 常州市第三人民医院 | Intelligent identification and automatic generation system and method for paper bills |
CN111783703B (en) * | 2020-07-07 | 2024-01-26 | 常州市第三人民医院 | Intelligent recognition and electronic certificate automatic generation system and method for paper bill |
CN115311651A (en) * | 2022-10-12 | 2022-11-08 | 泰安协同软件有限公司 | Real estate voucher data acquisition and arrangement method |
CN115311651B (en) * | 2022-10-12 | 2023-08-08 | 泰安协同软件有限公司 | Real estate certificate data acquisition and arrangement method |
CN116561602A (en) * | 2023-07-10 | 2023-08-08 | 三峡高科信息技术有限责任公司 | Automatic sales material matching method for sales cost transfer |
CN116561602B (en) * | 2023-07-10 | 2023-09-19 | 三峡高科信息技术有限责任公司 | Automatic sales material matching method for sales cost transfer |
Also Published As
Publication number | Publication date |
---|---|
CN108960223B (en) | 2020-10-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108960223A (en) | The method for automatically generating voucher based on bill intelligent recognition | |
CN109887153B (en) | Finance and tax processing method and system | |
US10783367B2 (en) | System and method for data extraction and searching | |
CN106485243B (en) | A kind of bank slip recognition error correction method and device | |
US9552516B2 (en) | Document information extraction using geometric models | |
JP5090369B2 (en) | Automated processing using remotely stored templates (method for processing forms, apparatus for processing forms) | |
US20140153830A1 (en) | Systems, methods and computer program products for processing financial documents | |
US20140153787A1 (en) | Systems, methods and computer program products for determining document validity | |
US10963692B1 (en) | Deep learning based document image embeddings for layout classification and retrieval | |
US8326041B2 (en) | Machine character recognition verification | |
CN109034727A (en) | Self-service electronic government affairs processing method | |
CN110046978A (en) | Intelligent method of charging out | |
US20100202698A1 (en) | Systems, methods, and computer program products for determining document validity | |
CN108363943B (en) | Customs clearance robot based on intelligent recognition technology | |
WO2019157029A1 (en) | System and method for classifying images of an evidence | |
US11501344B2 (en) | Partial perceptual image hashing for invoice deconstruction | |
JP6357621B1 (en) | Accounting processing apparatus, accounting processing system, accounting processing method and program | |
CN103336983A (en) | Bar-code-based bill generation system and recognition method thereof | |
CN112508011A (en) | OCR (optical character recognition) method and device based on neural network | |
CN110197140B (en) | Material auditing method and equipment based on character recognition | |
CN111462388A (en) | Bill inspection method and device, terminal equipment and storage medium | |
CN114529933A (en) | Contract data difference comparison method, device, equipment and medium | |
CN107563689A (en) | Use bar code management system and method | |
CN111860450A (en) | Ticket recognition device and ticket information management system | |
CN111768565A (en) | Method for identifying and post-processing invoice codes in value-added tax invoices |
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 | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: 501-018, floor 5, No. 15, wanquanzhuang Road, Haidian District, Beijing 100089 Patentee after: Dajingfang Network Technology Co.,Ltd. Address before: 100000 405, No. 15, wanquanzhuang Road, Haidian District, Beijing Patentee before: BEIJING DAZHANGFANG NETWORK TECHNOLOGY Co.,Ltd. |