CN110263239A - A kind of method, apparatus, storage medium and the computer equipment of invoice identification - Google Patents
A kind of method, apparatus, storage medium and the computer equipment of invoice identification Download PDFInfo
- Publication number
- CN110263239A CN110263239A CN201910469612.8A CN201910469612A CN110263239A CN 110263239 A CN110263239 A CN 110263239A CN 201910469612 A CN201910469612 A CN 201910469612A CN 110263239 A CN110263239 A CN 110263239A
- Authority
- CN
- China
- Prior art keywords
- invoice
- data
- field
- undetermined
- image
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
-
- 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
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/20—Testing patterns thereon
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Character Input (AREA)
Abstract
The present invention provides method, apparatus, storage medium and the computer equipments of a kind of identification of invoice, wherein this method comprises: obtaining the invoice image of target invoice;Identify the invoice information in invoice image, invoice information includes invoice field and invoice data corresponding with invoice field;According to the corresponding relationship between the textview field of invoice validation system and the invoice field of invoice information, invoice data corresponding in invoice information is input in the textview field of invoice validation system, and obtains the verification result of invoice validation system feedback.Which does not need manual verification, can largely save time and the cost of staff, improves the speed and efficiency of verifying true from false of bills.
Description
Technical field
The present invention relates to invoice identification technology field, in particular to a kind of method, apparatus of invoice identification, storage medium and
Computer equipment.
Background technique
Invoice refers to all entity and individual in purchasing and selling commodities, offer or receives service and be engaged in other business activities
In, the business voucher issued and collected is original foundation and the auditing authority, tax authority's examination of law enforcement of accounting
Important evidence.
Currently, with the development of economy, the illegal activities such as invoice fraud, sell-fake-products also increasingly more gets up, in order to verify hair
The ticket true and false, financial staff or everyday consumer need autonomous inquiry invoice information.In traditional mode, when needing to inquire invoice
When the true and false, the taxation website for finding official is generally required, and is manually entered invoice number, hair in the query window of taxation website
The information such as ticket code are inquired, and verify true from false of bills, cumbersome and easy error, when wasting a large amount of manpowers by taxation website
Between, efficiency is lower.
Summary of the invention
To solve the above problems, method, apparatus, storage medium and computer that the present invention provides a kind of invoice identification are set
It is standby.
According to the first aspect of the invention, a kind of invoice knowledge method for distinguishing is provided, comprising:
Obtain the invoice image of target invoice;
Identify the invoice information in the invoice image, the invoice information include invoice field and with the invoice field
Corresponding invoice data;
It, will be described according to the corresponding relationship between the textview field of invoice validation system and the invoice field of the invoice information
Corresponding invoice data is input in the textview field of the invoice validation system in invoice information, and obtains the invoice validation system
The verification result for feedback of uniting.
In one possible implementation, the invoice information in the identification invoice image includes:
Identify data undetermined all in the invoice image, according to the data format of the data undetermined it is determining with it is described
The corresponding one or more invoice fields of data undetermined, and the corresponding one or more of each invoice field is determined respectively
The data undetermined;
When the corresponding data undetermined of the invoice field, using the data undetermined as with the invoice field
Corresponding invoice data;
When the invoice field corresponds to multiple data undetermined, selection one is undetermined from multiple data undetermined
Data are used as effective data undetermined, and using the effectively data undetermined as invoice data corresponding with the invoice field.
In one possible implementation, the data undetermined of selection one from multiple data undetermined are used as and have
Imitating data undetermined includes:
It will have determined that with the data undetermined of invoice field corresponding relationship labeled as identification state;
Reject be in the corresponding multiple data undetermined of the invoice field identification state data undetermined, and from remaining
A data undetermined are chosen in data undetermined as effective data undetermined.
In one possible implementation, the data undetermined of selection one from multiple data undetermined are used as and have
Imitating data undetermined includes:
Using the invoice field of the multiple data undetermined of correspondence as target invoice field, and determine the target invoice word
Position of the corresponding each data undetermined of section in the invoice image;
It identifies invoice text corresponding with the target invoice field in the invoice image, and determines the invoice text
Position in the invoice image;
According to position of the invoice text in the invoice image and each data undetermined in the invoice
Position in image determines that the spacing between the invoice text and the data undetermined, the spacing include line space respectively
And/or column pitch;
Using data undetermined corresponding to the minimum spacing in all spacing as effective data undetermined.
In one possible implementation, the data undetermined of selection one from multiple data undetermined are used as and have
Imitating data undetermined includes:
According to have determined that with the data undetermined of invoice field corresponding relationship and corresponding invoice field, determine relevant mark
Know information;
Using the invoice field of the multiple data undetermined of correspondence as target invoice field, in the target invoice field pair
When in the invoice data answered including the identification information, using the data undetermined to match with the identification information as effectively undetermined
Data.
In one possible implementation, the invoice information in the identification invoice image includes:
Determine effective invoice field needed for invoice validation system;
Identify invoice information relevant to the effective invoice field in the invoice image, the hair in the invoice information
Ticket field is effective invoice field.
In one possible implementation, after the verification result for obtaining the invoice validation system feedback,
This method further include:
When the verification result is to be verified, flag bit is submitted an expense account for invoice information setting, and in the invoice
After the corresponding target invoice of information is submitted an expense account, the reimbursement flag bit of the invoice information is updated.
According to the second aspect of the invention, a kind of device of invoice identification is provided, comprising:
Image collection module, for obtaining the invoice image of target invoice;
Identification module, the invoice information in the invoice image for identification, the invoice information include invoice field and
Invoice data corresponding with the invoice field;
Authentication module, for according to pair between the textview field of invoice validation system and the invoice field of the invoice information
It should be related to, invoice data corresponding in the invoice information is input in the textview field of the invoice validation system, and is obtained
The verification result of the invoice validation system feedback.
In terms of according to the third of the application, a kind of computer readable storage medium is provided, being stored thereon with computer can
Reading instruction, the computer-readable instruction realize above-mentioned steps when being executed by processor.
According to the 4th of the application the aspect, a kind of computer equipment is provided, including memory, processor and be stored in
On reservoir and the computer-readable instruction that can run on a processor, the processor execute real when the computer-readable instruction
Existing above-mentioned steps.
Method, apparatus, storage medium and the computer equipment of a kind of invoice identification provided in an embodiment of the present invention, can be right
Invoice carries out automatic identification, and identifies invoice field and invoice data in invoice image, later automatically fills out invoice data
Enter into invoice validation system and inquiring and authenticating, and the available verifying knot to invoice validation system feedback are carried out to true from false of bills
Fruit, so as to automatically determine true from false of bills.Which does not need manual verification, can largely save staff time and
Cost improves the speed and efficiency of verifying true from false of bills.Meanwhile passing through the effective invoice field of determination, it is possible to reduce image recognition
Treating capacity, improve recognition efficiency.By way of identifying invoice data first, the accuracy of identification is further increased;And it is first
The invoice field that data undetermined may belong to first is judged based on the data format of data undetermined, later again based on invoice text into
Row correction, can more accurately determine invoice data corresponding with target invoice field.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by written explanation
Specifically noted structure is achieved and obtained in book, claims and attached drawing.
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example to be used to explain the present invention together, not be construed as limiting the invention.In the accompanying drawings:
Fig. 1 is a kind of flow diagram of invoice knowledge method for distinguishing in the embodiment of the present invention;
Fig. 2 is the flow diagram that the invoice information in invoice image is identified in the embodiment of the present invention;
Fig. 3 is a kind of schematic diagram of form of expression of invoice image in the embodiment of the present invention;
Fig. 4 is a kind of first structure diagram of the device of invoice identification in the embodiment of the present invention;
Fig. 5 is a kind of second structural schematic diagram of the device of invoice identification in the embodiment of the present invention;
Fig. 6 is the structural schematic diagram that the computer equipment of invoice recognition methods is executed in the embodiment of the present invention.
Specific embodiment
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein
Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
A kind of invoice provided in an embodiment of the present invention knows method for distinguishing, shown in Figure 1, comprising:
Step 101: obtaining the invoice image of target invoice.
In the embodiment of the present invention, target invoice is the invoice for needing to identify verifying, that is, needs to verify the true of the target invoice
It is pseudo-.Specifically, the invoice image of target invoice can be obtained by way of scanning;Alternatively, if the target invoice is electronics hair
Ticket, can be by the corresponding image of electronic invoice directly as invoice image.
Step 102: the invoice information in identification invoice image, invoice information includes invoice field and opposite with invoice field
The invoice data answered.
In the embodiment of the present invention, after getting invoice image, that is, invoice field and the phase in invoice image may recognize that
The invoice data answered identifies the invoice information in invoice image.Wherein it is possible to identify invoice based on image recognition technology
Invoice information in image, for example it is based on OCR (Optical Character Recognition, optical character identification) technology
Deng.
In the embodiment of the present invention, invoice field includes that invoice codes, invoice number, date of making out an invoice, amount issued (are free of
Tax), check code, purchaser's title, purchaser's Taxpayer Identification Number, seller title, in seller Taxpayer Identification Number etc.
One or more, invoice data is the corresponding data of invoice field.For example, " invoice number " that invoice field is 8, phase
Corresponding invoice data is " 12345678 ".
Step 103:, will according to the corresponding relationship between the textview field of invoice validation system and the invoice field of invoice information
Corresponding invoice data is input in the textview field of invoice validation system in invoice information, and obtains invoice validation system feedback
Verification result.
In the embodiment of the present invention, invoice validation system is the system or official's platform that can verify true from false of bills, such as state
Shui Ju official website etc..Textview field is the control of invoice validation system, the textview field in the present embodiment be specifically as follows uniline or
The Input of multirow.The corresponding invoice field of each textview field, for facilitating user to submit corresponding invoice data, into
And inquiry true from false of bills can be enabled a user to.In the embodiment of the present invention, after identifying invoice field and invoice data, if
It can determine the corresponding relationship between the textview field of the invoice validation system and invoice field, it can be by corresponding invoice data certainly
Dynamic filling verifies the target invoice by the invoice validation system into corresponding textview field, and available to hair
The verification result of ticket verifying system feedback.If the invoice data submitted automatically is correctly, invoice validation system feeds back the mesh
Mark invoice is the verification result of legalized invoice;Conversely, invoice validation system feeds back the verifying knot that the target invoice is illegal invoice
Fruit.
Optionally, due to that can include much information in invoice, but invoice validation system be only needed when verifying true from false of bills
User is wanted to submit the partial information of invoice, therefore step 102 " the invoice letter in identification invoice image in the embodiment of the present invention
Breath " specifically includes:
Determine effective invoice field needed for invoice validation system;It identifies relevant to effective invoice field in invoice image
Invoice information, the invoice field in invoice information are effective invoice field.
In the embodiment of the present invention, effective invoice field is that invoice validation system verifies required field when true from false of bills,
When identifying invoice information in a step 102 at this time, it is only necessary to identify effective invoice field and corresponding invoice data.Example
Such as, invoice validation system needs user to provide three invoice fields when verifying invoice: invoice codes, invoice number and issuing gold
Volume, i.e., effective invoice field includes invoice codes, invoice number and amount issued, when identifying the invoice information of target invoice,
It only needs to identify invoice data corresponding with invoice codes, invoice number and amount issued.By determining effectively hair
Ticket field, it is possible to reduce the treating capacity of image recognition improves recognition efficiency.
A kind of invoice provided in an embodiment of the present invention knows method for distinguishing, can carry out automatic identification to invoice, and identify
Invoice data is filled into invoice validation system true to invoice by invoice field and invoice data in invoice image automatically later
Puppet carries out inquiring and authenticating, and the available verification result to invoice validation system feedback, true so as to automatically determine invoice
It is pseudo-.Which does not need manual verification, can largely save time and the cost of staff, improves the speed of verifying true from false of bills
Degree and efficiency.Meanwhile passing through the effective invoice field of determination, it is possible to reduce the treating capacity of image recognition improves recognition efficiency.
On the basis of the above embodiments, shown in Figure 2 in order to more accurately identify invoice information, on
Stating step 102 " invoice information in identification invoice image " includes:
Step 1021: all data undetermined in identification invoice image, according to the data format of data undetermined determine with to
Fixed number determines the corresponding one or more indefinite numbers of each invoice field according to corresponding one or more invoice fields respectively
According to.
Invoice data and corresponding invoice are determined in the embodiment of the present invention by way of identifying invoice data first
Field.Since the invoice data in invoice is usually to be made of number, i.e., " invoice data " in the present embodiment refers to wrapping
Data containing number;For example, the invoice data of corresponding " amount issued " is " 100.00 " or " $100.00 ", correspondence " issues day
The invoice data of phase " is " on January 1st, 2018 " or " 2018/1/1 " etc..Under normal circumstances, number is identified based on image recognition technology
Accuracy when word is higher, and in the present embodiment by way of identifying invoice data first, the accuracy of identification can be improved.
Specifically, the data undetermined are to wrap firstly the need of the data undetermined identified in invoice image in the present embodiment
Data containing number;Since the corresponding invoice data of invoice fields different in invoice generally has specific format, the present embodiment
The middle data format according to data undetermined can determine that the data undetermined may correspond to which or which invoice field, that is, can determine
The corresponding one or more invoice fields of data undetermined.Wherein, the data format of data undetermined refer to the data digit,
Intrinsic form of expression of data etc..For example, 12 invoice codes (invoice codes of VAT invoice before are 10), 8
The invoice number of position, " X X month X day " format, " X-X-X " format or " X/X/X " format are made out an invoice the date, " $XXX " format or
The amount issued etc. of " XX.XX member " format.For example, the number that invoice number is 8, phone (such as complaint telephone etc.) is also 8
The number of position, if some data undetermined is " 12345678 ", the data " 12345678 " undetermined and " invoice number " and " electricity
Words " are corresponding, i.e., " 12345678 " may be invoice number, it is also possible to phone.
It meanwhile as described above, between the data undetermined in the present embodiment and invoice field being one-to-one or one-to-many
Corresponding relationship, correspondingly, be also possible to one-to-one or one-to-many corresponding relationship between invoice field and data undetermined, i.e., one
Invoice field may correspond to a data undetermined, it is also possible to corresponding multiple data undetermined.For example, the data lattice with 8 bit digitals
The data undetermined of formula include " 12345678 " and " 87654321 ", corresponding two data undetermined of invoice field " invoice number "
" 12345678 " and " 87654321 ", i.e. invoice number may be 12345678, it is also possible to 87654321.
It should be noted that " data undetermined " and " invoice data " in the present embodiment be same data in different time points
Two address.Specifically, " data undetermined " refer to the data for most starting to identify from invoice image, do not know also at this time
Road should " data undetermined " which corresponding invoice field;And " invoice data " refers to knowing the data of which corresponding invoice field,
I.e. if it is known which invoice field is some data correspond to, then the data are known as " invoice data ".For example, being identified from invoice image
Data " 12345678 " out, then the data " 12345678 " are known as " data undetermined " at this time, if determining the corresponding " hair of the data later
This field of ticket number ", then the data " 12345678 " are known as " invoice data " at this time.
Step 1022: when the corresponding data undetermined of invoice field, using data undetermined as corresponding with invoice field
Invoice data.
Step 1023: when invoice field corresponds to multiple data undetermined, an indefinite number is chosen from multiple data undetermined
According to as effective data undetermined, and will effective data undetermined as invoice data corresponding with invoice field.
In the embodiment of the present invention, if invoice field and data undetermined are one-to-one relationships, can directly determine this to
Fixed number is according to as invoice data corresponding with invoice field.When invoice field corresponds to multiple data undetermined, can therefrom select
Take a data undetermined as invoice data corresponding with the invoice field.
Specifically, above-mentioned steps 1023 " choosing a data undetermined from multiple data undetermined as effective data undetermined "
Include:
Step A1: it will have determined that with the data undetermined of invoice field corresponding relationship labeled as identification state.
In the embodiment of the present invention, data undetermined for part can uniquely determine invoice corresponding with the data undetermined
Field, such data undetermined are " having determined that the data undetermined with invoice field corresponding relationship ", this thing can be by the indefinite number
According to labeled as identification state.Wherein, the data undetermined determined in step 1022 are " to have determined that and invoice field corresponding relationship
Data undetermined ".For example, the data format on date is issued as " xx xx month xx day " or " xx/xx/xx ", and invoice image
In only one data fit undetermined this issue the data format on date, then the data undetermined are the corresponding invoice of invoice image
Data, at this time can be by the data undetermined labeled as identification state.
Step A2: reject be in the corresponding multiple data undetermined of invoice field identification state data undetermined, and from surplus
A data undetermined are chosen in remaining data undetermined as effective data undetermined.
In the embodiment of the present invention, when invoice field corresponds to multiple data undetermined, if some or certain indefinite numbers therein
According to being identification state, then explanation has determined that the corresponding relationship of the data undetermined and other invoice fields, the i.e. indefinite number
According to certain uncorrelated to current invoice field, the data undetermined that such is identification state can be rejected at this time, from remaining
A data undetermined are chosen in data undetermined as effective data undetermined.Wherein, if after rejecting the data undetermined of identification state,
The invoice field is only corresponding with a remaining data undetermined, then remaining unique data undetermined are effective indefinite number
According to.By rejecting the data undetermined of identification state in the present embodiment, can be further improved when choosing effectively data undetermined
Accuracy.
Optionally, since invoice type is relatively more, such as common invoice, VAT invoice etc., and every kind of invoice there is also
A variety of groups, for example VAT invoice includes again: VAT invoice, value-added tax common invoice, the unified hair of motor vehicle sale
Ticket, used car sale uniform invoice, carrying trade VAT invoice etc., and there are also quota invoice, universal machines to dismiss ticket
Deng the nominal value size of every kind of invoice and typesetting are distinct, and it is tired to lead to identify that the invoice information in invoice image exists
It is difficult.In order to overcome the problems referred above, in the embodiment of the present invention, above-mentioned steps 1023 " choose an indefinite number from multiple data undetermined
According to as effective data undetermined " include:
Step B1: using the invoice field of the multiple data undetermined of correspondence as target invoice field, and target invoice word is determined
Position of the corresponding each data undetermined of section in invoice image.
Step B2: invoice text corresponding with target invoice field in identification invoice image, and determine that invoice text is being sent out
Position in ticket image.
In the embodiment of the present invention, if some invoice field corresponds to multiple data undetermined, in order to facilitate subsequent descriptions, by the hair
Ticket field is known as target invoice field.Meanwhile data undetermined are the data identified from invoice image, data undetermined are located at hair
Specific position in ticket image can also determine each data undetermined corresponding with the target invoice field in invoice image at this time
In position.For example, establishing two-dimensional coordinate system for invoice image, which can be described in the form of coordinate points at this time
Position, such as using the coordinate of the point in the data lower left corner undetermined as the position of the data undetermined, or by the data undetermined
Central point position of the coordinate as the data undetermined.
In addition, when identifying invoice information, identifying invoice data first in the embodiment before above-mentioned;Due to each
The invoice field that invoice includes is known, even identical, the invoice field in the invoice information identified in the present embodiment
It is the determination according to the invoice data identified, not by image recognition technology, Direct Recognition is come out from invoice image
's.Likewise, the target invoice field is not that Direct Recognition comes out from invoice image yet.But in the present embodiment,
It is which invoice field in order to which correctly determining invoice data is corresponding, based on the hair in image recognition technology identification invoice image
Ticket text, which is invoice field identify from invoice image, textual form, if the hair identified
Ticket text is corresponding with the target invoice field, it is determined that the position of the invoice text in invoice image.Wherein it is determined that invoice
Text is similar with the process of above-mentioned " determining position of the data undetermined in invoice image " in the position in invoice image, herein not
It repeats.
Step B3: according to invoice text in the position of position and each data undetermined in invoice image in invoice image
It sets, determines the spacing between invoice text and data undetermined respectively, spacing includes line space and/or column pitch.
Step B4: using data undetermined corresponding to the minimum spacing in all spacing as effective data undetermined.
Both in the embodiment of the present invention, according to the position of invoice text and data undetermined in invoice image, can determine
Line space or column pitch in invoice image.Specifically, a kind of form of expression of invoice image is shown in Figure 3, in Fig. 3 with
Invoice image includes four invoice texts and three data instance explanations undetermined.
In the embodiment of the present invention, the line space between invoice text and data undetermined refers to the position coordinates of invoice text
With the difference of the position coordinates of data undetermined on y direction;Correspondingly, the column pitch between invoice text and data undetermined
Difference of the position coordinates of the position coordinates and data undetermined that refer to invoice text in X direction.Line space is smaller, says
The bright invoice text and data undetermined more may be in same a line;Column pitch is smaller, which is more possible to data undetermined
In same row.As shown in figure 3, line space between invoice text a and data undetermined 1 is smaller, invoice text d and data 1 undetermined,
2, the column pitch between 3 is smaller.
If the line space or column pitch between invoice text and data undetermined are that the invoice text is relevant with other all
The smallest in spacing between data undetermined, then the line space or column pitch are minimum spacing, corresponding with the minimum spacing
Data undetermined and the invoice text are very likely located at same a line or same row, the corresponding data undetermined of the minimum spacing and the hair
Ticket text is corresponding relationship, at this time can will using data undetermined corresponding to the minimum spacing in all spacing as effectively
Data undetermined.As shown in figure 3, if the corresponding invoice text of target invoice field is invoice text a, with the target invoice field pair
The data undetermined answered include data 1 undetermined, data undetermined 2, data undetermined 3;Invoice text a and data 1 undetermined known at this time it
Between there is minimum spacing (minimum line space), at this time can be by data 1 undetermined as the corresponding effective indefinite number of invoice text a
According to.
In the present embodiment, invoice field corresponding with data undetermined is determined by minimum spacing, is adapted to difference
Invoice pattern.Meanwhile machine dismiss ticket invoice text may not go together with data undetermined, possibly even wrong row (similar Fig. 3 institute
Show), for example amount issued printed to date a line of making out an invoice;If directly being closed according to the position between invoice data and invoice text
System is to determine field corresponding to the data undetermined, then there may be erroneous judgements.The number of data undetermined is primarily based in the present embodiment
The invoice field that data undetermined may belong to is judged according to format, is corrected again based on invoice text later, it can be more quasi-
Really determine invoice data corresponding with target invoice field.
It should be noted that " the invoice text d " of the multiple data undetermined of correspondence in Fig. 3 is usually " amount of money ", accordingly
Invoice text a and b are article of consumption respectively, for example are " mobile phone " and " computer " respectively, then corresponding data 1 undetermined are exactly mobile phone
Price, data 2 undetermined are the prices of computer.But " amount issued " in invoice field is actually total amount, if invoice
Text c is " total amount ", then and the corresponding data 3 undetermined of invoice text c are only invoice data corresponding with amount issued.At this time
Can be by " invoice text c " as invoice text corresponding with " target invoice field ", namely which data undetermined only considered
It is minimum with the line space or column pitch of invoice text c.
In addition, invoice includes many numbers, i.e., data undetermined, such as invoice codes, invoice number, invoice, check code
Etc. corresponding number;Invoice be directly write exactly number meaning, such as " invoice number: 12345678 ", and some only
There are a number, such as " 12345678 ", not writing this number exactly is " invoice number ".That is, the invoice data in invoice
It is than more complete, and invoice text may be imperfect.Alternatively, the same invoice field may be different in different invoices
The form of expression, i.e., different invoice text, such as " invoice number " this invoice field, the specific manifestation in invoice image
Form (i.e. invoice text) may be " invoice number ", it is also possible to " No. ".Invoice data is first identified in the present embodiment, later
Corresponding invoice field is determined again, even if the invoice field in invoice is imperfect, can also clearly and completely be determined all
Invoice information.
On the basis of the above embodiments, above-mentioned steps 1023 " choose a data undetermined to make from multiple data undetermined
For effective data undetermined " include:
Step C1: it according to having determined that and the data undetermined of invoice field corresponding relationship and corresponding invoice field, determines
Relevant identification information.
Step C2: using the invoice field of the multiple data undetermined of correspondence as target invoice field, in target invoice field pair
When in the invoice data answered including identification information, using the data undetermined to match with identification information as effective data undetermined.
In the embodiment of the present invention, it can identify that other are unidentified according to the invoice data and invoice field that have identified
Invoice data.Specifically, determining relevant identification information according to the invoice data and invoice field that identify, basis should later
Identification information identifies the corresponding data undetermined of target invoice field.Wherein, which is specifically as follows date information, position
Set relationship etc..For example, the format on date of generally making out an invoice is special, it is easier to identify, is identifying date of making out an invoice corresponding invoice
After data, that is, it can determine the time (i.e. identification information) made out an invoice;And in invoice codes the 6th~7 expression of years code (such as
18 indicate 2018), can be chosen at this time according to the time on date of making out an invoice the 6th~7 of data undetermined be the time to
Fixed number is according to as effective data undetermined.Alternatively, the identification information can be positional relationship.For example, general invoice codes and invoice
The neighbouring arrangement of number can be using 8 bit digitals below invoice codes as invoice number after identifying invoice codes.
Optionally, with the prevalence of electronic invoice, invoice, which easily exists, repeats the case where submitting an expense account.To solve this problem, at this
In embodiment, after step 103 " verification result for obtaining invoice validation system feedback ", this method further include: when verifying is tied
Fruit is to submit an expense account flag bit when being verified for invoice information setting, and after the corresponding target invoice of invoice information is submitted an expense account, more
The reimbursement flag bit of new invoice information.
In the embodiment of the present invention, invoice database can establish, can also be deposited according to the invoice information that invoice image recognition goes out
Storage is every invoice information setting reimbursement flag bit in database, for example do not submit an expense account invoice letter in the invoice database
The reimbursement flag bit of breath is 0, and the reimbursement flag bit for having submitted an expense account invoice information is 1.It can determine and be somebody's turn to do according to the reimbursement flag bit
Whether the corresponding invoice of invoice information has been submitted an expense account, so as to avoid repeating submitting an expense account.
A kind of invoice provided in an embodiment of the present invention knows method for distinguishing, can carry out automatic identification to invoice, and identify
Invoice data is filled into invoice validation system true to invoice by invoice field and invoice data in invoice image automatically later
Puppet carries out inquiring and authenticating, and the available verification result to invoice validation system feedback, true so as to automatically determine invoice
It is pseudo-.Which does not need manual verification, can largely save time and the cost of staff, improves the speed of verifying true from false of bills
Degree and efficiency.Meanwhile passing through the effective invoice field of determination, it is possible to reduce the treating capacity of image recognition improves recognition efficiency.Pass through
The mode for identifying invoice data first, further increases the accuracy of identification;And the data format for being primarily based on data undetermined is come
Judge the invoice field that data undetermined may belong to, is corrected, can more accurately be determined based on invoice text again later
Invoice data corresponding with target invoice field.
The method flow of invoice identification is described in detail above, this method can also be realized by corresponding device, below
The structure and function of the device is discussed in detail.
A kind of device of invoice identification provided in an embodiment of the present invention, it is shown in Figure 4, comprising:
Image collection module 41, for obtaining the invoice image of target invoice;
Identification module 42, the invoice information in the invoice image, the invoice information include invoice field for identification
With invoice data corresponding with the invoice field;
Authentication module 43, for according between the textview field of invoice validation system and the invoice field of the invoice information
Invoice data corresponding in the invoice information is input in the textview field of the invoice validation system, and obtains by corresponding relationship
Take the verification result of the invoice validation system feedback.
On the basis of the above embodiments, the identification module 42 includes:
All data undetermined in recognition unit, with the identification invoice image, according to the data lattice of the data undetermined
The determining one or more invoice fields corresponding with the data undetermined of formula, and determine that each invoice field is corresponding respectively
The one or more data undetermined;
First determination unit is used for when the corresponding data undetermined of the invoice field, by the data undetermined
As invoice data corresponding with the invoice field;
Second determination unit, for when the invoice field corresponds to multiple data undetermined, from multiple described undetermined
Data undetermined are chosen in data as effective data undetermined, and will effective data undetermined as with the invoice field
Corresponding invoice data.
On the basis of the above embodiments, second determination unit chosen from multiple data undetermined one it is undetermined
Data include: as effective data undetermined
It will have determined that with the data undetermined of invoice field corresponding relationship labeled as identification state;
Reject be in the corresponding multiple data undetermined of the invoice field identification state data undetermined, and from remaining
A data undetermined are chosen in data undetermined as effective data undetermined.
On the basis of the above embodiments, second determination unit chosen from multiple data undetermined one it is undetermined
Data include: as effective data undetermined
Using the invoice field of the multiple data undetermined of correspondence as target invoice field, and determine the target invoice word
Position of the corresponding each data undetermined of section in the invoice image;
It identifies invoice text corresponding with the target invoice field in the invoice image, and determines the invoice text
Position in the invoice image;
According to position of the invoice text in the invoice image and each data undetermined in the invoice
Position in image determines that the spacing between the invoice text and the data undetermined, the spacing include line space respectively
And/or column pitch;
Using data undetermined corresponding to the minimum spacing in all spacing as effective data undetermined.
On the basis of the above embodiments, second determination unit chosen from multiple data undetermined one it is undetermined
Data include: as effective data undetermined
According to have determined that with the data undetermined of invoice field corresponding relationship and corresponding invoice field, determine relevant mark
Know information;
Using the invoice field of the multiple data undetermined of correspondence as target invoice field, in the target invoice field pair
When in the invoice data answered including the identification information, using the data undetermined to match with the identification information as effectively undetermined
Data.
On the basis of the above embodiments, the identification module 42 identifies that the invoice information in the invoice image includes:
Determine effective invoice field needed for invoice validation system;
Identify invoice information relevant to the effective invoice field in the invoice image, the hair in the invoice information
Ticket field is effective invoice field.
On the basis of the above embodiments, shown in Figure 5, which further includes mark module 44;
After the verification result that the authentication module 43 obtains the invoice validation system feedback, the mark module 44
For: when the verification result is to be verified, flag bit is submitted an expense account for invoice information setting, and in the invoice information
After corresponding target invoice is submitted an expense account, the reimbursement flag bit of the invoice information is updated.
A kind of device of invoice identification provided in an embodiment of the present invention, can carry out automatic identification to invoice, and identify
Invoice data is filled into invoice validation system true to invoice by invoice field and invoice data in invoice image automatically later
Puppet carries out inquiring and authenticating, and the available verification result to invoice validation system feedback, true so as to automatically determine invoice
It is pseudo-.Which does not need manual verification, can largely save time and the cost of staff, improves the speed of verifying true from false of bills
Degree and efficiency.Meanwhile passing through the effective invoice field of determination, it is possible to reduce the treating capacity of image recognition improves recognition efficiency.Pass through
The mode for identifying invoice data first, further increases the accuracy of identification;And the data format for being primarily based on data undetermined is come
Judge the invoice field that data undetermined may belong to, is corrected, can more accurately be determined based on invoice text again later
Invoice data corresponding with target invoice field.
The embodiment of the present application also provides a kind of computer readable storage medium, the computer-readable recording medium storage
There is computer-readable instruction, it includes the program for executing above-mentioned invoice recognition methods, the computer-readable instruction is executable
Method in above-mentioned any means embodiment.
Wherein, the computer readable storage medium can be any usable medium that computer can access or data are deposited
Store up equipment, including but not limited to magnetic storage (such as floppy disk, hard disk, tape, magneto-optic disk (MO) etc.), optical memory (example
Such as CD, DVD, BD, HVD) and semiconductor memory (such as ROM, EPROM, EEPROM, nonvolatile memory (NAND
FLASH), solid state hard disk (SSD)) etc..
Fig. 6 shows a kind of structural block diagram of computer equipment of another embodiment of the invention.The computer is set
Standby 1100 can be the host server for having computing capability, personal computer PC or portable portable computer or
Terminal etc..The specific embodiment of the invention does not limit the specific implementation of computer equipment.
The computer equipment 1100 includes at least one processor (processor) 1110, communication interface
(Communications Interface) 1120, memory (memory array) 1130 and bus 1140.Wherein, processor
1110, communication interface 1120 and memory 1130 complete mutual communication by bus 1140.
Communication interface 1120 with network element for communicating, and wherein network element includes such as Virtual Machine Manager center, shared storage.
Processor 1110 is for executing program.Processor 1110 may be a central processor CPU or dedicated collection
At circuit ASIC (Application Specific Integrated Circuit), or it is arranged to implement the present invention
One or more integrated circuits of embodiment.
Memory 1130 is for storing computer-readable instruction.Memory 1130 may include high speed RAM memory, can also
It can further include nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.Memory 1130
It is also possible to memory array.Memory 1130 is also possible to by piecemeal, and described piece can be combined into virtually by certain rule
Volume.The instruction that memory 1130 stores can be executed by processor 1110, so that processor 1110 is able to carry out above-mentioned any means
Method in embodiment.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of invoice knows method for distinguishing characterized by comprising
Obtain the invoice image of target invoice;
Identify the invoice information in the invoice image, the invoice information includes invoice field and opposite with the invoice field
The invoice data answered;
According to the corresponding relationship between the textview field of invoice validation system and the invoice field of the invoice information, by the invoice
Corresponding invoice data is input in the textview field of the invoice validation system in information, and it is anti-to obtain the invoice validation system
The verification result of feedback.
2. the method according to claim 1, wherein the invoice information packet in the identification invoice image
It includes:
Identify data undetermined all in the invoice image, according to the data format of the data undetermined it is determining with it is described undetermined
The corresponding one or more invoice fields of data, and determined described in the corresponding one or more of each invoice field respectively
Data undetermined;
When the corresponding data undetermined of the invoice field, using the data undetermined as opposite with the invoice field
The invoice data answered;
When the invoice field corresponds to multiple data undetermined, a data undetermined are chosen from multiple data undetermined
As effective data undetermined, and using the effectively data undetermined as invoice data corresponding with the invoice field.
3. according to the method described in claim 2, it is characterized in that, the selection one from multiple data undetermined is undetermined
Data include: as effective data undetermined
It will have determined that with the data undetermined of invoice field corresponding relationship labeled as identification state;
Reject be in the corresponding multiple data undetermined of the invoice field identification state data undetermined, and from remaining undetermined
A data undetermined are chosen in data as effective data undetermined.
4. according to the method described in claim 2, it is characterized in that, the selection one from multiple data undetermined is undetermined
Data include: as effective data undetermined
Using the invoice field of the multiple data undetermined of correspondence as target invoice field, and determine the target invoice field pair
Each of answer position of the data undetermined in the invoice image;
It identifies invoice text corresponding with the target invoice field in the invoice image, and determines the invoice text in institute
State the position in invoice image;
According to position of the invoice text in the invoice image and each data undetermined in the invoice image
In position, determine the spacing between the invoice text and the data undetermined respectively, the spacing include line space and/or
Column pitch;
Using data undetermined corresponding to the minimum spacing in all spacing as effective data undetermined.
5. according to the method described in claim 2, it is characterized in that, the selection one from multiple data undetermined is undetermined
Data include: as effective data undetermined
According to have determined that with the data undetermined of invoice field corresponding relationship and corresponding invoice field, determine relevant mark letter
Breath;
It is corresponding in the target invoice field using the invoice field of the multiple data undetermined of correspondence as target invoice field
When in invoice data including the identification information, using the data undetermined to match with the identification information as effective indefinite number
According to.
6. the method according to claim 1, wherein the invoice information packet in the identification invoice image
It includes:
Determine effective invoice field needed for invoice validation system;
Identify invoice information relevant to the effective invoice field in the invoice image, the invoice word in the invoice information
Section is effective invoice field.
7. -6 any method according to claim 1, which is characterized in that obtain the invoice validation system feedback described
Verification result after, further includes:
When the verification result is to be verified, flag bit is submitted an expense account for invoice information setting, and in the invoice information
After corresponding target invoice is submitted an expense account, the reimbursement flag bit of the invoice information is updated.
8. a kind of device of invoice identification characterized by comprising
Image collection module, for obtaining the invoice image of target invoice;
Identification module, the invoice information in the invoice image for identification, the invoice information include invoice field and with institute
State the corresponding invoice data of invoice field;
Authentication module, for according to the corresponding pass between the textview field of invoice validation system and the invoice field of the invoice information
System, invoice data corresponding in the invoice information is input in the textview field of the invoice validation system, and described in acquisition
The verification result of invoice validation system feedback.
9. a kind of computer readable storage medium, is stored thereon with computer-readable instruction, which is characterized in that the computer can
The step of method described in any one of claims 1 to 7 is realized when reading instruction is executed by processor.
10. a kind of computer equipment, including memory and processor, the memory are stored with computer-readable instruction, special
Sign is that the processor realizes the step of any one of claims 1 to 7 the method when executing the computer-readable instruction
Suddenly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910469612.8A CN110263239B (en) | 2019-05-31 | 2019-05-31 | Invoice identification method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910469612.8A CN110263239B (en) | 2019-05-31 | 2019-05-31 | Invoice identification method and device, storage medium and computer equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110263239A true CN110263239A (en) | 2019-09-20 |
CN110263239B CN110263239B (en) | 2023-08-22 |
Family
ID=67916338
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910469612.8A Active CN110263239B (en) | 2019-05-31 | 2019-05-31 | Invoice identification method and device, storage medium and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110263239B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111104844A (en) * | 2019-10-12 | 2020-05-05 | 中国平安财产保险股份有限公司 | Multi-invoice information input method and device, electronic equipment and storage medium |
CN111932766A (en) * | 2020-08-11 | 2020-11-13 | 上海眼控科技股份有限公司 | Invoice verification method and device, computer equipment and readable storage medium |
CN112085885A (en) * | 2020-09-24 | 2020-12-15 | 理光图像技术(上海)有限公司 | Ticket recognition device and ticket information management system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013111782A (en) * | 2011-11-25 | 2013-06-10 | National Printing Bureau | Printed matter capable of distinguishing authenticity |
CN105046553A (en) * | 2015-07-09 | 2015-11-11 | 胡昭 | Cloud intelligent invoice recognition inspection system and method based on mobile phone |
CN105528604A (en) * | 2016-01-31 | 2016-04-27 | 华南理工大学 | Bill automatic identification and processing system based on OCR |
CN108122139A (en) * | 2016-11-29 | 2018-06-05 | 阿里巴巴集团控股有限公司 | A kind of invoice data processing method, equipment and system |
CN109472918A (en) * | 2018-10-12 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Invoice validation method, financing checking method, device, equipment and medium |
CN109800747A (en) * | 2018-12-14 | 2019-05-24 | 平安科技(深圳)有限公司 | Medical invoice recognition methods, user equipment, storage medium and device |
-
2019
- 2019-05-31 CN CN201910469612.8A patent/CN110263239B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013111782A (en) * | 2011-11-25 | 2013-06-10 | National Printing Bureau | Printed matter capable of distinguishing authenticity |
CN105046553A (en) * | 2015-07-09 | 2015-11-11 | 胡昭 | Cloud intelligent invoice recognition inspection system and method based on mobile phone |
CN105528604A (en) * | 2016-01-31 | 2016-04-27 | 华南理工大学 | Bill automatic identification and processing system based on OCR |
CN108122139A (en) * | 2016-11-29 | 2018-06-05 | 阿里巴巴集团控股有限公司 | A kind of invoice data processing method, equipment and system |
CN109472918A (en) * | 2018-10-12 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Invoice validation method, financing checking method, device, equipment and medium |
CN109800747A (en) * | 2018-12-14 | 2019-05-24 | 平安科技(深圳)有限公司 | Medical invoice recognition methods, user equipment, storage medium and device |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111104844A (en) * | 2019-10-12 | 2020-05-05 | 中国平安财产保险股份有限公司 | Multi-invoice information input method and device, electronic equipment and storage medium |
CN111104844B (en) * | 2019-10-12 | 2023-11-14 | 中国平安财产保险股份有限公司 | Multi-invoice information input method and device, electronic equipment and storage medium |
CN111932766A (en) * | 2020-08-11 | 2020-11-13 | 上海眼控科技股份有限公司 | Invoice verification method and device, computer equipment and readable storage medium |
CN112085885A (en) * | 2020-09-24 | 2020-12-15 | 理光图像技术(上海)有限公司 | Ticket recognition device and ticket information management system |
Also Published As
Publication number | Publication date |
---|---|
CN110263239B (en) | 2023-08-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108734528A (en) | A kind of electronic invoice keeps accounts method automatically | |
CN109377342A (en) | Bill processing method, device, computer equipment and storage medium | |
CN109325729A (en) | A kind of method and server generating electronic contract | |
CN110263239A (en) | A kind of method, apparatus, storage medium and the computer equipment of invoice identification | |
CN107798596A (en) | Credit card fabrication method, apparatus, computer equipment and readable storage medium storing program for executing | |
CN106980995A (en) | A kind of identification of electronic invoice layout files and checking method and relevant apparatus | |
US11663592B2 (en) | Automatic transaction-based verification of account ownership | |
CN109194771A (en) | A kind of neocaine bids to host method, apparatus, server and storage medium | |
CN106504097A (en) | A kind for the treatment of method and apparatus of assets information | |
WO2020233402A1 (en) | Accounts payable order validation method, apparatus and device, and storage medium | |
CN103942677A (en) | Transaction payment method and system, and POS machine | |
CN107679060A (en) | Method for inquiring status, device, user terminal and the storage medium of electronic insurance policy | |
CN102044091A (en) | Self-service ticketing system | |
AU2020313995A1 (en) | Asset verification systems and/or methods | |
CN110110223A (en) | Information recommendation method, device, computer equipment and storage medium | |
TWM590271U (en) | Business process system | |
CN106779743A (en) | Sincere Classified Protection, device and service end | |
CN105205706A (en) | Invoice query method and device | |
CN103761646A (en) | Method for recognizing and verifying electronic consumption voucher on POS machine through mobile phone number | |
CN109409875A (en) | A kind of bill method of calibration, device and electronic equipment | |
CN110138707A (en) | Method, client, application and the electronic equipment of data interaction | |
WO2007030980A1 (en) | A method and system to prevent fraudulent ticket (paper or electronic) by using non-contact public transportation ic card as an identity proof to authenticate the legitimacy of the ticket holder | |
CN106251127A (en) | The online recharge method of a kind of smart card and equipment | |
CN105741169A (en) | Device, method and system for paying tax through bank card | |
CN111367776A (en) | Recording method, device, equipment and storage medium of resource transfer service |
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 |