CN107145814A - invoice input method, invoice input device and terminal - Google Patents
invoice input method, invoice input device and terminal Download PDFInfo
- Publication number
- CN107145814A CN107145814A CN201710256064.1A CN201710256064A CN107145814A CN 107145814 A CN107145814 A CN 107145814A CN 201710256064 A CN201710256064 A CN 201710256064A CN 107145814 A CN107145814 A CN 107145814A
- Authority
- CN
- China
- Prior art keywords
- invoice
- image
- terminal
- information
- typing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/00—Commerce
- G06Q30/04—Billing or invoicing
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9554—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL] by using bar codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- 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
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- 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
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/412—Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
Abstract
The present invention proposes a kind of invoice input method, invoice input device and terminal, wherein, the invoice input method includes：First terminal generates the identification code for data transfer when receiving the signal of typing invoice, so that invoice image is sent to the first terminal by second terminal by scanning the identification code；The invoice image sent from the second terminal is received, the invoice information in the invoice image is identified；The invoice information is entered into invoice input system.Pass through technical scheme, it is possible to achieve large batch of invoice typing, and the invoice can be the invoice with Quick Response Code or bar code, can also be the invoice without Quick Response Code or bar code.
Description
Technical field
The present invention relates to field of terminal technology, in particular to a kind of invoice input method, a kind of invoice input device
With a kind of terminal.
Background technology
The pattern of the existing typing invoice of enterprise is：In the manual typing invoice of computer end；In the manual typing of mobile phone terminal, voice
Invoice Quick Response Code, bar code typing are swept in typing.
The shortcoming of the existing typing invoice of enterprise is：Use manual typing invoice, it is easy to occur inputing by mistake, omit in invoice
The situation of appearance, especially when need typing invoiced amount it is more when, carry out manual labor's consumption required for manual typing invoice
Take than larger；Use voice typing invoice, although reduce the time of manual typing, but still need typing one by one, it is impossible to be real
Existing large batch of data inputting；Existing mobile phone scanning recognition invoice information is just in the hair with Quick Response Code or bar code
Ticket, Rapid input invoice can not be realized for the invoice without Quick Response Code or bar code.
Therefore, how to realize that large batch of invoice typing turns into technical problem urgently to be resolved hurrily.
The content of the invention
The present invention is based on above mentioned problem, it is proposed that a kind of new technical scheme, it is possible to achieve large batch of invoice record
Enter, and the invoice can be the invoice with Quick Response Code or bar code, can also be without Quick Response Code or bar code
Invoice.
In view of this, the first aspect of the present invention proposes a kind of invoice input method, including：First terminal is being received
During the signal of typing invoice, the identification code for data transfer is generated, so that second terminal will be sent out by scanning the identification code
Ticket image is sent to the first terminal；The invoice image sent from the second terminal is received, the hair is identified
Invoice information in ticket image；The invoice information is entered into invoice input system.
In the technical scheme, second terminal is sent to first terminal by scanning identification code by invoice image, and first eventually
The invoice information in automatic identification invoice image is held, and the invoice information is entered into invoice input system, this programme is avoided
By the way of invoice information typing one by one, it is adaptable to large batch of invoice typing, invoice typing can be effectively improved
Efficiency.And the invoice of typing can be the invoice with Quick Response Code or bar code, can also be without Quick Response Code or
The invoice of bar code.
In the above-mentioned technical solutions, it is preferable that the identification code generated for data transfer, specifically include：Obtain institute
State IP (agreement interconnected between InternetProtocol, network) address that first terminal receives the webpage of the invoice image
Data Transport Protocol between information and the first terminal and the second terminal；According to the IP address information and the number
According to host-host protocol, the web page interlinkage of data transfer is generated；The generation identification code corresponding with the web page interlinkage.
In the technical scheme, second terminal is by scanning the IP that Quick Response Code can obtain the webpage of invoice image to be received
Address information and Data Transport Protocol, second terminal are based on the Data Transport Protocol, it is possible to by the invoice figure in second terminal
As being sent to first terminal, it is to avoid reveal company information during invoice image is transmitted.
In any of the above-described technical scheme, it is preferable that the invoice information identified in the invoice image, specific bag
Include：Dividing processing is carried out to the invoice image, to extract the text filed image in the invoice image；Using convolution god
The text filed image is identified through network, to identify the invoice information in the text filed image.
In the technical scheme, the invoice information in text filed image, Ke Yizhi are identified using convolutional neural networks
Connect and input original invoice image, it is not necessary to which region detection and division are carried out to invoice image.Moreover, above scheme can be recognized
Go out hand-written invoice information.
The invoice information identified includes but is not limited to one below or a variety of combinations：Invoice codes, invoice number, open
Ticket date, the amount of money of making out an invoice, the amount of tax to be paid, purchaser's title, pin side's title, cargo measurement unit, quantity of goods.
In any of the above-described technical scheme, it is preferable that described to carry out dividing processing to the invoice image, to extract
The text filed image in invoice image is stated, is specifically included：The colored invoice image clustering is obtained by k-means algorithms
To the image of single backcolor；Binaryzation and zone location are carried out to the image of single backcolor, to obtain doubtful text
Region；The doubtful text filed coordinate is mapped in the invoice image of colour and carries out dividing processing, to be partitioned into
The text filed image.
In the technical scheme, by being clustered to invoice image, binaryzation and zone location, it can be gone out with Direct Recognition
Invoice information, it is not necessary to use specific invoice scanner, accuracy of identification is high, and speed is fast, facilitates large batch of invoice typing.
In any of the above-described technical scheme, it is preferable that described that the invoice information is entered into invoice input system, tool
Body includes：Invoice model is selected for the invoice information；The invoice information is imported into the invoice model；It will be imported with
The invoice model of the invoice information is uploaded in the invoice input system.
In the technical scheme, by for invoice information select invoice model, for example, selection VAT invoice model or
The model of person's common invoice, it is to avoid user before typing is manually classified invoice, even if VAT invoice and common
Invoice, which is mixed, can also recognize, further ensure that the efficiency of invoice typing.
In any of the above-described technical scheme, it is preferable that after the invoice information is imported into the invoice model,
Also include：According to the invoice model, invoice voucher is generated；And/or delete the invoice image.
In the technical scheme, by generating invoice voucher, the invoice voucher can be for carrying out financial verification, can also
Printed on webpage and do financial analysis, form etc..Furthermore it is also possible to delete invoice image, it is to avoid in invoice image takes
Deposit, so as to improve memory usage.
The second aspect of the present invention proposes a kind of invoice input device, for first terminal, the invoice input device
Including：First generation unit, for when receiving the signal of typing invoice, generating the identification code for data transfer, for
Second terminal is sent to the first terminal by scanning the identification code by invoice image；Recognition unit, comes from for receiving
The invoice image that the second terminal is sent, identifies the invoice information in the invoice image；Typing unit, for inciting somebody to action
The invoice information is entered into invoice input system.
In the technical scheme, second terminal is sent to first terminal by scanning identification code by invoice image, and first eventually
The invoice information in automatic identification invoice image is held, and the invoice information is entered into invoice input system, this programme is avoided
By the way of invoice information typing one by one, it is adaptable to large batch of invoice typing, invoice typing can be effectively improved
Efficiency.And the invoice of typing can be the invoice with Quick Response Code or bar code, can also be without Quick Response Code or
The invoice of bar code.
In the above-mentioned technical solutions, it is preferable that first generation unit includes：Subelement is obtained, it is described for obtaining
First terminal is received between the IP address information and the first terminal and the second terminal of the webpage of the invoice image
Data Transport Protocol；Subelement is generated, for according to the IP address information and the Data Transport Protocol, generating data transfer
Web page interlinkage；The generation subelement is additionally operable to, and generates the identification code corresponding with the web page interlinkage.
In the technical scheme, second terminal is by scanning the IP that Quick Response Code can obtain the webpage of invoice image to be received
Address information and Data Transport Protocol, second terminal are based on the Data Transport Protocol, it is possible to by the invoice figure in second terminal
As being sent to first terminal, it is to avoid reveal company information during invoice image is transmitted.
In any of the above-described technical scheme, it is preferable that the recognition unit includes：Subelement is extracted, for the hair
Ticket image carries out dividing processing, to extract the text filed image in the invoice image；Subelement is recognized, for using volume
The text filed image is identified product neutral net, to identify that the invoice in the text filed image is believed
Breath.
In the technical scheme, the invoice information in text filed image, Ke Yizhi are identified using convolutional neural networks
Connect and input original invoice image, it is not necessary to which region detection and division are carried out to invoice image.Moreover, above scheme can be recognized
Go out hand-written invoice information.
In any of the above-described technical scheme, it is preferable that the extraction subelement is specifically for passing through k-means algorithms pair
The colored invoice image clustering obtains the image of single backcolor, the image of single backcolor is carried out binaryzation and
Zone location, it is doubtful text filed to obtain, the doubtful text filed coordinate is mapped to the invoice image of colour
Middle carry out dividing processing, to be partitioned into the text filed image.
In the technical scheme, by being clustered to invoice image, binaryzation and zone location, it can be gone out with Direct Recognition
Invoice information, it is not necessary to use specific invoice scanner, accuracy of identification is high, and speed is fast, facilitates large batch of invoice typing.
In any of the above-described technical scheme, it is preferable that the typing unit includes：Subelement is selected, for for the hair
Ticket information selects invoice model；Subelement is imported, for the invoice information to be imported into the invoice model；Upload son single
Member, for the invoice model for being imported with the invoice information to be uploaded in the invoice input system.
In the technical scheme, by for invoice information select invoice model, for example, selection VAT invoice model or
The model of person's common invoice, it is to avoid user before typing is manually classified invoice, even if VAT invoice and common
Invoice, which is mixed, can also recognize, further ensure that the efficiency of invoice typing.
In any of the above-described technical scheme, it is preferable that also include：Second generation unit, for according to the invoice model,
Generate invoice voucher；And/or unit is deleted, for deleting the invoice image.
In the technical scheme, by generating invoice voucher, the invoice voucher can be for carrying out financial verification, can also
Printed on webpage and do financial analysis, form etc..Furthermore it is also possible to delete invoice image, it is to avoid in invoice image takes
Deposit, so as to improve memory usage.
The third aspect of the present invention proposes a kind of terminal, including the invoice typing any one of above-mentioned technical proposal
Device, therefore, the terminal have and above-mentioned technical proposal any one of invoice input device identical technique effect,
This is repeated no more.
Pass through technical scheme, it is possible to achieve large batch of invoice typing, and the invoice can have two
The invoice of code or bar code is tieed up, the invoice without Quick Response Code or bar code is can also be.
Brief description of the drawings
Fig. 1 shows the schematic flow sheet of invoice input method according to an embodiment of the invention；
Fig. 2 shows the structural representation of invoice input device according to an embodiment of the invention；
Fig. 3 shows the structural representation of terminal according to an embodiment of the invention.
Embodiment
It is below in conjunction with the accompanying drawings and specific real in order to which the above objects, features and advantages of the present invention can be more clearly understood that
Mode is applied the present invention is further described in detail.It should be noted that in the case where not conflicting, the implementation of the application
Feature in example and embodiment can be mutually combined.
Many details are elaborated in the following description to facilitate a thorough understanding of the present invention, still, the present invention may be used also
Implemented with being different from other modes described here using other, therefore, protection scope of the present invention is not by described below
Specific embodiment limitation.
Fig. 1 shows the schematic flow sheet of invoice input method according to an embodiment of the invention.
As shown in figure 1, invoice input method according to an embodiment of the invention, including：
Step 102, first terminal generates the identification code for data transfer when receiving the signal of typing invoice, with
For second terminal the first terminal is sent to by scanning the identification code by invoice image.
Wherein, the identification code can be Quick Response Code, can also be bar code.
Step 104, the invoice image sent from the second terminal is received, is identified in the invoice image
Invoice information.
Step 106, the invoice information is entered into invoice input system.
In the technical scheme, second terminal is sent to first terminal by scanning identification code by invoice image, and first eventually
The invoice information in automatic identification invoice image is held, and the invoice information is entered into invoice input system, this programme is avoided
By the way of invoice information typing one by one, it is adaptable to large batch of invoice typing, invoice typing can be effectively improved
Efficiency.And the invoice of typing can be the invoice with Quick Response Code or bar code, can also be without Quick Response Code or
The invoice of bar code.
In the above-mentioned technical solutions, it is preferable that the identification code generated for data transfer, specifically include：Obtain institute
Between the IP address information and the first terminal and the second terminal of stating the webpage of the first terminal reception invoice image
Data Transport Protocol；According to the IP address information and the Data Transport Protocol, the web page interlinkage of data transfer is generated；It is raw
Into the identification code corresponding with the web page interlinkage.
In the technical scheme, second terminal is by scanning the IP that Quick Response Code can obtain the webpage of invoice image to be received
Address information and Data Transport Protocol, second terminal are based on the Data Transport Protocol, it is possible to by the invoice figure in second terminal
As being sent to first terminal, it is to avoid reveal company information during invoice image is transmitted.
For example, first terminal currently shows the interface of invoice typing, there are two kinds of typing modes on the interface, one kind is manual
The mode of input, another is the mode of scanning record.If the mode that user selects scanning record is detected, by the IP of webpage
Address information and ColoradoFTP (the File Transfer Protocol, file biography that wireless data transmission function can be realized
Defeated agreement) an integrated data transfer web page interlinkage, generate corresponding with web page interlinkage Quick Response Code, and the Quick Response Code is shown
On the interface of invoice typing.Second terminal scans the Quick Response Code, and the information in Quick Response Code is read by coding rule.Due to two
Carry ColoradoFTP wireless data transmission protocols in dimension code, ColoradoFTP agreements have more rapidly, it is reliable and expansible
Carry out wireless data transmission the characteristics of, so invoice figure to be logged can be directly selected after the complete Quick Response Code of scanning input
Picture, and the invoice image is sent to first terminal.
In any of the above-described technical scheme, it is preferable that the invoice information identified in the invoice image, specific bag
Include：Dividing processing is carried out to the invoice image, to extract the text filed image in the invoice image；Using convolution god
The text filed image is identified through network, to identify the invoice information in the text filed image.
In the technical scheme, the invoice information in text filed image, Ke Yizhi are identified using convolutional neural networks
Connect and input original invoice image, it is not necessary to which region detection and division are carried out to invoice image.Moreover, above scheme can be recognized
Go out hand-written invoice information.
The invoice information identified includes but is not limited to one below or a variety of combinations：Invoice codes, invoice number, open
Ticket date, the amount of money of making out an invoice, the amount of tax to be paid, purchaser's title, pin side's title, cargo measurement unit, quantity of goods.
In any of the above-described technical scheme, it is preferable that described to carry out dividing processing to the invoice image, to extract
The text filed image in invoice image is stated, is specifically included：The colored invoice image clustering is obtained by k-means algorithms
To the image of single backcolor；Binaryzation and zone location are carried out to the image of single backcolor, to obtain doubtful text
Region；The doubtful text filed coordinate is mapped in the invoice image of colour and carries out dividing processing, to be partitioned into
The text filed image.
In the technical scheme, by being clustered to invoice image, binaryzation and zone location, it can be gone out with Direct Recognition
Invoice information, it is not necessary to use specific invoice scanner, accuracy of identification is high, and speed is fast, facilitates large batch of invoice typing.
In any of the above-described technical scheme, it is preferable that step 106 is specifically included：Invoice mould is selected for the invoice information
Type；The invoice information is imported into the invoice model；The invoice model for being imported with the invoice information is uploaded
Into the invoice input system.
In the technical scheme, by for invoice information select invoice model, for example, selection VAT invoice model or
The model of person's common invoice, it is to avoid user before typing is manually classified invoice, even if VAT invoice and common
Invoice, which is mixed, can also recognize, further ensure that the efficiency of invoice typing.
Wherein, invoice model is the model of form, i.e., invoice model is to store invoice information in table form,
When invoice information is imported into invoice model, table match is carried out automatically, the relevant position that invoice information is imported into form.
And the invoice model can be changed, user can change invoice according to the actual demand of oneself, so as to avoid the letter of typing
Breath is wrong or omits the information of typing.
In any of the above-described technical scheme, it is preferable that after the invoice information is imported into the invoice model,
Also include：According to the invoice model, invoice voucher is generated；And/or delete the invoice image.
In the technical scheme, by generating invoice voucher, the invoice voucher can be for carrying out financial verification, can also
Printed on webpage and do financial analysis, form etc..Furthermore it is also possible to delete invoice image, it is to avoid in invoice image takes
Deposit, so as to improve memory usage.
In addition, after invoice information is imported into invoice model, user, which first carries out the corresponding information of checking of invoice, to be had
Inerrancy, the invoice model after confirmation is errorless further according to selection generates corresponding invoice voucher, then will be imported with invoice information
Invoice model is uploaded in invoice input system.
Fig. 2 shows the structural representation of invoice input device according to an embodiment of the invention.
As shown in Fig. 2 invoice input device 200 according to an embodiment of the invention, for first terminal, the hair
Ticket input device 200 includes：First generation unit 202, recognition unit 204 and typing unit 206.
First generation unit 202, for when receiving the signal of typing invoice, generating the mark for data transfer
Code, so that invoice image is sent to the first terminal by second terminal by scanning the identification code；Recognition unit 204, is used
In receiving the invoice image from second terminal transmission, the invoice information in the invoice image is identified；Typing
Unit 206, for the invoice information to be entered into invoice input system.
In the technical scheme, second terminal is sent to first terminal by scanning identification code by invoice image, and first eventually
The invoice information in automatic identification invoice image is held, and the invoice information is entered into invoice input system, this programme is avoided
By the way of invoice information typing one by one, it is adaptable to large batch of invoice typing, invoice typing can be effectively improved
Efficiency.And the invoice of typing can be the invoice with Quick Response Code or bar code, can also be without Quick Response Code or
The invoice of bar code.
In the above-mentioned technical solutions, it is preferable that first generation unit 202 includes：Subelement 2022 is obtained, for obtaining
The first terminal is taken to receive the IP address information and the first terminal and the second terminal of the webpage of the invoice image
Between Data Transport Protocol；Subelement 2024 is generated, it is raw for according to the IP address information and the Data Transport Protocol
Into the web page interlinkage of data transfer；The generation subelement 2024 is additionally operable to, and generates the mark corresponding with the web page interlinkage
Know code.
In the technical scheme, second terminal is by scanning the IP that Quick Response Code can obtain the webpage of invoice image to be received
Address information and Data Transport Protocol, second terminal are based on the Data Transport Protocol, it is possible to by the invoice figure in second terminal
As being sent to first terminal, it is to avoid reveal company information during invoice image is transmitted.
In any of the above-described technical scheme, it is preferable that the recognition unit 204 includes：Extract subelement 2042, for pair
The invoice image carries out dividing processing, to extract the text filed image in the invoice image；Subelement 2044 is recognized,
For the text filed image to be identified using convolutional neural networks, to identify the institute in the text filed image
State invoice information.
In the technical scheme, the invoice information in text filed image, Ke Yizhi are identified using convolutional neural networks
Connect and input original invoice image, it is not necessary to which region detection and division are carried out to invoice image.Moreover, above scheme can be recognized
Go out hand-written invoice information.
In any of the above-described technical scheme, it is preferable that the extraction subelement 2042 by k-means specifically for being calculated
Method obtains the image of single backcolor to the colored invoice image clustering, and two-value is carried out to the image of single backcolor
Change and zone location, it is doubtful text filed to obtain, the doubtful text filed coordinate is mapped to the invoice of colour
Dividing processing is carried out in image, to be partitioned into the text filed image.
In the technical scheme, by being clustered to invoice image, binaryzation and zone location, it can be gone out with Direct Recognition
Invoice information, it is not necessary to use specific invoice scanner, accuracy of identification is high, and speed is fast, facilitates large batch of invoice typing.
In any of the above-described technical scheme, it is preferable that the typing unit 206 includes：Select subelement 2062, for for
The invoice information selects invoice model；Subelement 2064 is imported, for the invoice information to be imported into the invoice model
In；Subelement 2066 is uploaded, for the invoice model for being imported with the invoice information to be uploaded into the invoice typing system
In system.
In the technical scheme, by for invoice information select invoice model, for example, selection VAT invoice model or
The model of person's common invoice, it is to avoid user before typing is manually classified invoice, even if VAT invoice and common
Invoice, which is mixed, can also recognize, further ensure that the efficiency of invoice typing.
In any of the above-described technical scheme, it is preferable that also include：Second generation unit 208, for according to the invoice mould
Type, generates invoice voucher；And/or unit 210 is deleted, for deleting the invoice image.
In the technical scheme, by generating invoice voucher, the invoice voucher can be for carrying out financial verification, can also
Printed on webpage and do financial analysis, form etc..Furthermore it is also possible to delete invoice image, it is to avoid in invoice image takes
Deposit, so as to improve memory usage.
Fig. 3 shows the structural representation of terminal according to an embodiment of the invention.
As shown in figure 3, terminal 300 according to an embodiment of the invention, including any one of above-mentioned technical proposal institute
The invoice input device 200 stated, therefore, the terminal 300 have and the invoice typing dress any one of above-mentioned technical proposal
200 identical technique effects are put, be will not be repeated here.
Technical scheme is described in detail above in association with accompanying drawing, passes through technical scheme, it is possible to achieve
Large batch of invoice typing, and the invoice can be the invoice with Quick Response Code or bar code, can also be without two
Tie up the invoice of code or bar code.
In the present invention, term " first ", " second " are only used for the purpose described, and it is not intended that indicating or implying phase
To importance；Term " multiple " represents two or more.For the ordinary skill in the art, can be according to tool
Body situation understands the concrete meaning of above-mentioned term in the present invention.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (13)
1. a kind of invoice input method, it is characterised in that including：
First terminal generates the identification code for data transfer when receiving the signal of typing invoice, so that second terminal is logical
Over-scan the identification code and invoice image is sent to the first terminal；
The invoice image sent from the second terminal is received, the invoice information in the invoice image is identified；
The invoice information is entered into invoice input system.
2. invoice input method according to claim 1, it is characterised in that the generation is used for the mark of data transfer
Code, is specifically included：
Obtain the first terminal receive the invoice image webpage IP address information and the first terminal and described the
Data Transport Protocol between two terminals；
According to the IP address information and the Data Transport Protocol, the web page interlinkage of data transfer is generated；
The generation identification code corresponding with the web page interlinkage.
3. invoice input method according to claim 1, it is characterised in that the hair identified in the invoice image
Ticket information, is specifically included：
Dividing processing is carried out to the invoice image, to extract the text filed image in the invoice image；
The text filed image is identified using convolutional neural networks, to identify the institute in the text filed image
State invoice information.
4. invoice input method according to claim 3, it is characterised in that described that segmentation portion is carried out to the invoice image
Reason, to extract the text filed image in the invoice image, is specifically included：
The image of single backcolor is obtained to the colored invoice image clustering by k-means algorithms；
Binaryzation and zone location are carried out to the image of single backcolor, it is doubtful text filed to obtain；
The doubtful text filed coordinate is mapped in the invoice image of colour and carries out dividing processing, to be partitioned into
State text filed image.
5. invoice input method according to any one of claim 1 to 4, it is characterised in that described to believe the invoice
Breath is entered into invoice input system, is specifically included：
Invoice model is selected for the invoice information；
The invoice information is imported into the invoice model；
The invoice model for being imported with the invoice information is uploaded in the invoice input system.
6. invoice input method according to claim 5, it is characterised in that the invoice information is being imported into the hair
After in ticket model, in addition to：
According to the invoice model, invoice voucher is generated；And/or
Delete the invoice image.
7. a kind of invoice input device, for first terminal, it is characterised in that the invoice input device includes：
First generation unit, for when receiving the signal of typing invoice, generating the identification code for data transfer, for
Two terminals are sent to the first terminal by scanning the identification code by invoice image；
Recognition unit, for receiving the invoice image sent from the second terminal, is identified in the invoice image
Invoice information；
Typing unit, for the invoice information to be entered into invoice input system.
8. invoice input device according to claim 7, it is characterised in that first generation unit includes：
Subelement is obtained, for obtaining the IP address information and described that the first terminal receives the webpage of the invoice image
Data Transport Protocol between one terminal and the second terminal；
Subelement is generated, for according to the IP address information and the Data Transport Protocol, generating the webpage chain of data transfer
Connect；
The generation subelement is additionally operable to, and generates the identification code corresponding with the web page interlinkage.
9. invoice input device according to claim 7, it is characterised in that the recognition unit includes：
Subelement is extracted, for carrying out dividing processing to the invoice image, to extract the text area in the invoice image
Area image；
Subelement is recognized, for the text filed image to be identified using convolutional neural networks, to identify the text
The invoice information in local area area image.
10. invoice input device according to claim 9, it is characterised in that the extraction subelement specifically for,
The image of single backcolor is obtained to the colored invoice image clustering by k-means algorithms,
Binaryzation and zone location are carried out to the image of single backcolor, it is doubtful text filed to obtain,
The doubtful text filed coordinate is mapped in the invoice image of colour and carries out dividing processing, to be partitioned into
State text filed image.
11. the invoice input device according to any one of claim 7 to 10, it is characterised in that the typing unit bag
Include：
Subelement is selected, for selecting invoice model for the invoice information；
Subelement is imported, for the invoice information to be imported into the invoice model；
Subelement is uploaded, for the invoice model for being imported with the invoice information to be uploaded into the invoice input system
In.
12. invoice input device according to claim 11, it is characterised in that also include：
Second generation unit, for according to the invoice model, generating invoice voucher；And/or
Unit is deleted, for deleting the invoice image.
13. a kind of terminal, it is characterised in that including：Invoice input device as any one of claim 7 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710256064.1A CN107145814A (en) | 2017-04-19 | 2017-04-19 | invoice input method, invoice input device and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710256064.1A CN107145814A (en) | 2017-04-19 | 2017-04-19 | invoice input method, invoice input device and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107145814A true CN107145814A (en) | 2017-09-08 |
Family
ID=59774291
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710256064.1A Pending CN107145814A (en) | 2017-04-19 | 2017-04-19 | invoice input method, invoice input device and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107145814A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108268641A (en) * | 2018-01-18 | 2018-07-10 | 大象慧云信息技术有限公司 | Invoice information recognition methods and invoice information identification device, equipment and storage medium |
| CN109685477A (en) * | 2018-12-28 | 2019-04-26 | 北京爱康鼎科技有限公司 | Accounting process systems and processing method |
| CN109887202A (en) * | 2019-02-22 | 2019-06-14 | 北京航天泰坦科技股份有限公司 | The tax control tray of built-in enhancing module |
| CN110427851A (en) * | 2019-07-23 | 2019-11-08 | 上海易点时空网络有限公司 | The processing method and device of data, electronic equipment |
| 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 |
| CN111144416A (en) * | 2019-12-25 | 2020-05-12 | 中国联合网络通信集团有限公司 | Information processing method and device |
| CN114415911A (en) * | 2021-12-24 | 2022-04-29 | 珠海大横琴科技发展有限公司 | Data entry method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103078868A (en) * | 2013-01-15 | 2013-05-01 | 广州多益网络科技有限公司 | Application method and system of two-dimension code |
| US20140089313A1 (en) * | 2009-01-27 | 2014-03-27 | Stephen J. Brown | Semantic note taking system |
| CN105139128A (en) * | 2015-08-26 | 2015-12-09 | 潘伟骏 | Remote accounting processing method and system |
-
2017
- 2017-04-19 CN CN201710256064.1A patent/CN107145814A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140089313A1 (en) * | 2009-01-27 | 2014-03-27 | Stephen J. Brown | Semantic note taking system |
| CN103078868A (en) * | 2013-01-15 | 2013-05-01 | 广州多益网络科技有限公司 | Application method and system of two-dimension code |
| CN105139128A (en) * | 2015-08-26 | 2015-12-09 | 潘伟骏 | Remote accounting processing method and system |
Non-Patent Citations (1)
| Title |
|---|
| 张凯歌: "基于K-means和神经网络算法的图像文字提取与识别", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108268641A (en) * | 2018-01-18 | 2018-07-10 | 大象慧云信息技术有限公司 | Invoice information recognition methods and invoice information identification device, equipment and storage medium |
| CN109685477A (en) * | 2018-12-28 | 2019-04-26 | 北京爱康鼎科技有限公司 | Accounting process systems and processing method |
| CN109887202A (en) * | 2019-02-22 | 2019-06-14 | 北京航天泰坦科技股份有限公司 | The tax control tray of built-in enhancing module |
| CN109887202B (en) * | 2019-02-22 | 2021-04-06 | 北京航天泰坦科技股份有限公司 | Tax control disk with built-in reinforced module |
| CN110427851A (en) * | 2019-07-23 | 2019-11-08 | 上海易点时空网络有限公司 | The processing method and device of data, electronic equipment |
| 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 |
| CN111144416A (en) * | 2019-12-25 | 2020-05-12 | 中国联合网络通信集团有限公司 | Information processing method and device |
| CN114415911A (en) * | 2021-12-24 | 2022-04-29 | 珠海大横琴科技发展有限公司 | Data entry method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107145814A (en) | invoice input method, invoice input device and terminal | |
| CN103914907B (en) | Paper-bill information identification and core calibration system and application process | |
| CN106228675A (en) | The method and apparatus identifying true from false of bills | |
| CN103745186B (en) | The processing method and communication terminal of 2 D code information | |
| US8964211B2 (en) | Document processing apparatus, document processing method, document processing system, and computer readable medium for transmitting document information according to a rule selected on the basis of position information | |
| CN104158889B (en) | Card information querying method and Cloud Server | |
| CN103412877A (en) | Method and device for transmitting picture | |
| CN108875757A (en) | A kind of signal auditing method, server and system | |
| CN104200361A (en) | Automatic two-dimension code generation based mobile banking payment system and payment method | |
| CN104683935B (en) | Communication system, communication device and communication connecting method | |
| CN107113614B (en) | Method and system for remotely handling SIM card | |
| CN104732182A (en) | Two-dimension-code-based communication method on webpage | |
| CN105915740A (en) | Image Forming Apparatus, Image Forming System, And Non-Transitory Computer Readable Medium Storing Program | |
| CN1700646B (en) | Device and method for utilizing a scannable URL (universal resource locator) | |
| CN104200252B (en) | A kind of function logic jump method, client and system based on barcode data | |
| CN108335369A (en) | A kind of passenger station system of real name verification ticket-checking system | |
| CN205318553U (en) | Data processing device and system and printer | |
| RU2492521C2 (en) | Method and means for delivering, handling and using coded information | |
| CN102694936B (en) | Control method and apparatus for composite scanning device and composite scanning system | |
| CN104616183B (en) | Network trading identification system, client and discrimination method | |
| CN206431680U (en) | A kind of rapid safety Claims Resolution system for identity code barcode scanning of being traced to the source based on product false proof | |
| CN108647570A (en) | Zebra line detecting method, device and computer readable storage medium | |
| JP5246364B1 (en) | Information processing system and program | |
| JP2009048297A (en) | Affiliate subscription promotion server and system | |
| CN109840507A (en) | Mobile administrative law enforcement method, apparatus and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170908 |
|
| RJ01 | Rejection of invention patent application after publication |