CN110109918A - For verifying the method, apparatus, equipment and computer storage medium of list data - Google Patents
For verifying the method, apparatus, equipment and computer storage medium of list data Download PDFInfo
- Publication number
- CN110109918A CN110109918A CN201810105169.1A CN201810105169A CN110109918A CN 110109918 A CN110109918 A CN 110109918A CN 201810105169 A CN201810105169 A CN 201810105169A CN 110109918 A CN110109918 A CN 110109918A
- Authority
- CN
- China
- Prior art keywords
- numerical value
- predetermined relationship
- field
- fields
- identified
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Character Discrimination (AREA)
Abstract
According to the exemplary embodiment of present disclosure, provide a kind of for verifying the method, apparatus, equipment and computer storage medium of list data.Specifically, a kind of method for verifying list data is provided, comprising: obtain form image, the table in form image includes multiple fields and numerical value corresponding with each field in multiple fields;Based on form image, each field in multiple fields and corresponding numerical value are identified;Predetermined relationship related at least some of multiple fields field is obtained, predetermined relationship indicates the incidence relation between numerical value corresponding at least some fields;And whether verification numerical value corresponding at least some fields meets predetermined relationship.According to the exemplary embodiment of present disclosure, additionally provide for verifying the corresponding device of list data, equipment and computer storage medium.
Description
Technical field
Embodiment of the disclosure relates generally to field of image recognition, and more particularly, to one kind for verifying table
Method, apparatus, equipment and the computer storage medium of data.
Background technique
Table is the format of a kind of effectively management and group organization data, and for a long time, paper list has been widely used in
Every field.In order to assist office automation, needs that existing paper list is scanned or taken pictures, form the table of electronic form
Image.Then Table recognition is carried out, to carry out subsequent processing.In field of image recognition, the correct table identified in image and
Its content important in inhibiting.For example, for financial institution, it is correct to identify such as balance sheet, cash flow statement, benefit
The enterprise financial report of profit table etc facilitates the management state for comprehensively disclosing enterprise, and then facilitates in credit examination & approval and its
Working efficiency is improved in his decision.
At present in field of image recognition, OCR (Optical Character Recognition, optics are depended on
Character recognition) technology identifies the table in image.Pass through image preprocessing, image segmentation, character recognition, recognition result processing
Recognition result can be obtained etc. a series of processes.However, since that there are pixels is lower, figure for a part of parts of images or image
Situations such as piece obscures causes the partial data in table to identify wrong;Or there are mistakes for initial data in image itself.This
A little problems all need especially to pay close attention in subsequent processing, manually verify table number if fully relied in subsequent processing
According to recognition result, then workload is huge, and the accuracy and integrality that verify can not be guaranteed.This is affected
Application effect of the OCR technique in table automatic identification.
It especially include the table of multiple numerical value, between at least some of table project for some type of table
There are incidence relations.Accordingly, it is desirable to provide a kind of can verify table number using the incidence relation between project each in table
According to method.
Summary of the invention
According to the example embodiment of present disclosure, provide a kind of for verifying the scheme of list data.
In the first aspect of present disclosure, a kind of method for verifying list data is provided.Specifically, the party
Method includes: acquisition form image, and the table in form image includes multiple fields and opposite with each field in multiple fields
The numerical value answered;Based on form image, each field in multiple fields and corresponding numerical value are identified;In acquisition and multiple fields
The related predetermined relationship of at least some fields, predetermined relationship indicate that the association between numerical value corresponding at least some fields is closed
System;And whether verification numerical value corresponding at least some fields meets predetermined relationship.
In in the second aspect of the present disclosure, provide a kind of for verifying the device of list data.Specifically, the dress
Setting includes: image collection module, and image collection module is configured as obtaining form image, and the table in form image includes multiple
Field and numerical value corresponding with each field in multiple fields;Table recognition module, Table recognition module are configured as base
Each field and corresponding numerical value in multiple fields are identified in form image;Relation acquisition module, Relation acquisition module are matched
It is set to acquisition predetermined relationship related at least some of multiple fields field, predetermined relationship indicates and at least some field phases
Incidence relation between corresponding numerical value;And data check module, data check module be configured as verification with it is at least some
Whether the corresponding numerical value of field meets predetermined relationship.
In the third aspect of present disclosure, a kind of equipment, including one or more processors are provided;And storage
Device, for storing one or more programs, when one or more programs are executed by one or more processors so that one or
The method that multiple processors realize the first aspect according to present disclosure.
In the fourth aspect of present disclosure, a kind of computer-readable medium is provided, is stored thereon with computer journey
Sequence realizes the method for the first aspect according to present disclosure when the program is executed by processor.
It should be appreciated that content described in Summary is not intended to limit the pass of the embodiment of present disclosure
Key or important feature, it is also non-for limiting the scope of the disclosure.The other feature of present disclosure will be retouched by below
It states and is easy to understand.
Detailed description of the invention
It refers to the following detailed description in conjunction with the accompanying drawings, the above and other feature, advantage of each embodiment of present disclosure
And aspect will be apparent.In the accompanying drawings, the same or similar appended drawing reference indicates the same or similar element, in which:
Fig. 1 schematically shows the example table that may include in form image;
Fig. 2 shows the streams according to the exemplary method for verifying list data of the exemplary embodiment of present disclosure
Cheng Tu;
Fig. 3 shows schematic according to one that identification mistake is wherein not present of the exemplary embodiment of present disclosure
Recognition result;
Fig. 4 is shown schematically to be known according to one for wherein there is identification mistake of the exemplary embodiment of present disclosure
Other result;
Fig. 5 diagrammatically illustrates the device for verifying list data of the exemplary embodiment according to present disclosure
Block diagram;And
Fig. 6 shows the block diagram that can implement the calculating equipment of multiple embodiments of present disclosure.
Specific embodiment
The embodiment of present disclosure is more fully described below with reference to accompanying drawings.Although being shown in the disclosure in attached drawing
The some embodiments of appearance, it should be understood that, present disclosure can be realized by various forms, and should not be by
It is interpreted as being limited to embodiments set forth here, providing these embodiments on the contrary is in order to more thorough and be fully understood by the disclosure
Content.It should be understood that the being given for example only property of accompanying drawings and embodiments of present disclosure acts on, it is not intended to limit the disclosure
The protection scope of content.
In the description of the embodiment of present disclosure, term " includes " and its similar term should be understood as open packet
Contain, i.e., " including but not limited to ".Term "based" should be understood as " being based at least partially on ".Term " one embodiment " or
" embodiment " should be understood as " at least one embodiment ".Term " first ", " second " etc. may refer to different or phase
Same object.Hereafter it is also possible that other specific and implicit definition.
In current field of image recognition, the table in image is identified by means of OCR technique.Due to image slices
The low reason of element, while it being limited to the technical bottleneck of image recognition, recognition result is inevitably present some identification mistakes.It is right
In the extremely important situation of data accuracy (such as, for enterprise financial report), need wrong probability occur as far as possible
It is reduced to minimum.If manually verified to recognition result, workload is huge, and accuracy is not high.
In order at least be partially solved the problems in prior art, the embodiment of present disclosure proposes a kind of use
In the scheme of verification list data, to reduce the workload of manual review in subsequent process.The embodiment of present disclosure utilizes
Incidence relation in data form between numerical value corresponding with each project verifies relevant item and its corresponding numerical value, will
The result of verification is supplied in visual form subsequent reviewing officer.For example, in enterprise financial report, each accounting item
Between there are Articulation.Add " the owner as the amount of money number of " assets " section now is equal to the amount of money number of " debt " section now
The amount of money number of Total Equity " section now.Therefore, it is possible to based on " assets ", " debt " and " owner's equity is total ", section is now
Number relationship, to determine the table content of extraction with the presence or absence of mistake.
In this way, it is possible to substantially reduce the workload of manual review and adjustment, Table recognition is improved in related fields
Application effect.Hereinafter, some example implementations of the embodiment of present disclosure will be described referring to figs. 1 to Fig. 6.
Fig. 1 schematically shows the example table 100 that may include in form image.As shown in Figure 1, " XX table "
It can indicate the gauge outfit of example table 100, that is, the title of example table 100, for example, certain 2017 annual balance sheet of company
Deng.Table main part can have multiple fields and numerical value corresponding with each field in these fields.Shown in Fig. 1
Example table 100 have 10 fields, that is, field 1 to field 10;Each field has corresponding numerical value, that is, numerical value
1 to numerical value 10.In Fig. 1, each numerical value is corresponding with the field in cell before it, and indicates that the field is had
Attribute value having or associated with the field etc..
For example, example table 100 can be table relevant to temperature, field 1 to field 9 can respectively indicate certain office
One floor of building to nine floor room temperature.In such a table, field 1 can be " one layer ", and numerical value 1 (can unit: be taken the photograph for " 26 "
Family name's degree can not include in the cell where numerical value 1);Field 2 can be " two layers ", and numerical value 2 can be " 28 ";Word
Section 10 can be one layer to nine layers of average room temperature, and numerical value 10 can be expressed as (numerical value 1+ numerical value 2+ ...+numerical value 9)/
9.For another example, in the case where example table 100 is balance sheet, field 1 can respectively indicate different accounting to field 10
Subject, numerical value 1 to numerical value 10 can indicate corresponding amount of money number.For example, field 1 can be " money-capital ", and numerical value 1 can
Think the amount of money for the money-capital that enterprise of filling in a form is possessed, for example 100 (Wan Yuan).Similar to above-described temperature table, respectively
May exist predetermined relationship between a field.
Although it will be appreciated by those skilled in the art that example table shown in fig. 1 100 have the five-element four arrange layout,
It is that can be applied to that there is any table being suitably laid out according to the method and apparatus of present disclosure embodiment.In addition, though
Each field is shown in example table 100 only has a corresponding numerical value, but the field in table also can have more than one
A correspondence numerical value, such as 2 or 3.In addition, table may be used also other than title, field, numerical value shown in Fig. 1
To include sundry item, organization unit, establishment date etc..
The detailed process of verification list data is described below in conjunction with Fig. 2.Fig. 2 shows the examples according to present disclosure
Property embodiment for verify list data exemplary method 200 flow chart.It should be appreciated that method 200 can be applied to it
In between each project with any table of incidence relation.
210, form image is obtained, the table (for example, example table 100) in the form image includes multiple fields
(for example, field 1 to field 10) and numerical value corresponding with each field in multiple fields (for example, numerical value 1 to numerical value 10).
Form image can be by reading local data base acquisition, can be via network real-time reception, can be related work
Server is uploaded to as personnel or calculates equipment.Form image can be scanning or generation of taking pictures, and form image
Format can be any computer-readable format.Embodiment of the disclosure is not limited in this respect.
220, based on acquired form image, the table that the form image is included, including the multiple words of identification are identified
Each field and corresponding numerical value in section.In some embodiments, it can use OCR technique to identify the word in form image
Section and numerical value.The process of identification may include image preprocessing, image segmentation, character recognition, recognition result processing etc., and right
The various characters such as text, number, System Partition character are identified.After recognition, by each field and its corresponding number
Value is associated, and is stored in association in such as database, can also be temporarily stored in the caching for calculating equipment.
230, predetermined relationship related at least some of multiple fields field is obtained.With sample table shown in FIG. 1
For lattice 100, available predetermined relationship relevant to field 1, field 3 and field 5.Predetermined relationship can be mathematical operation pass
System, can also be with logical relation.For example, can there is such as " numerical value 1+ numerical value 2 " " numerical value 5 " should be equal to example table 100
Predetermined relationship;Or " numerical value 1+ numerical value 2 " should be greater than the predetermined relationship of " numerical value 5 ";" numerical value 1* numerical value 2 " should be equal to
The predetermined relationship of " numerical value 5 ".
In some embodiments, predetermined relationship is related with form types.For example, can be according to usual in a certain form types
Incidence relation between the project being related to and these projects makes a reservation for predetermined relationship relevant to the table of the type in advance.?
In some embodiments, predetermined relationship can be stored in relationship library, then according to the form types for the table to be verified come
Retrieval relationship library, to obtain predetermined relationship.In some embodiments, for the table to be verified, there are multiple pre-
Relationship is determined, then then can successively obtain these predetermined relationships.
Hereinafter, only pre- between projects to provide in table with the financial statement of three types common in financial industry
Determine the specific example of relationship.Table 1 to table 3 is predetermined relationship in balance sheet, profit and loss statement and cash flow statement respectively (in wealth
Business field, commonly known as Articulation).As shown in table 1, there are at least 13 predetermined relationships in balance sheet, for example, compiling
Number for 2 predetermined relationship indicate with " long-term investment " corresponding numerical value plus numerical value corresponding with " cost-book value differentials " should equal to
" long-term investment is total " corresponding numerical value.For example, in the case where the table identified is balance sheet, it can be based on " money
Producing liability account " this form types retrieves relationship library, to obtain as described in table 1 13 predetermined relationships.
Predetermined relationship in 1 balance sheet of table
Predetermined relationship in profit and loss statement as shown in Table 2 and as shown in table 3 is hereinafter diagrammatically illustrated respectively
Predetermined relationship in cash flow statement, wherein storing 8 and 10 predetermined relationships respectively, meaning is similar with table 1, herein not
It repeats again.
Predetermined relationship in 2 profit and loss statement of table
Predetermined relationship in 3 cash flow statement of table
It will be appreciated by those skilled in the art that although example predetermined relationship given above only includes addition, subtraction, multiplies
Simple calculations such as method, but predetermined relationship also may include more complicated operation relation, so long as operation relation energy
It is enough to be verified in a computing environment.In addition, though example predetermined relationship above only relates to the logics such as " being equal to ", " being greater than ",
But predetermined relationship can also include other logics, "AND", "or" etc..
With continued reference to Fig. 2, process proceeds to 240.240, whether full numerical value corresponding at least some fields is verified
Predetermined relationship acquired in foot.For example, acquired predetermined relationship is the predetermined relationship that number is 2 in table 1 above, that is,
" long-term investment+cost-book value differentials=long-term investment total ", then by the respective value of " long-term investment " that is identified with identified
The respective value of " cost-book value differentials " be added, then determine whether the result being added is equal to " long-term investment total " identified
Respective value.
If predetermined relationship is not satisfied, process proceeds to 250.It is involved in 250, unsatisfied predetermined relationship
All fields be identified.Still by taking the predetermined relationship that number is 2 in table 1 as an example, if " long-term investment+cost-book value differentials=length
Phase investment is total " this predetermined relationship is not satisfied, then " long-term investment ", " cost-book value differentials ", " long-term investment is total " this three
A field is identified.
If predetermined relationship is satisfied, can determine whether there is also the predetermined relationships not verified for the table.?
In the case where the predetermined relationship not verified, process returns to step 230, obtains the predetermined relationship not verified and is verified;
There is no the predetermined relationship not verified, process continues to follow-up process.
In some embodiments, after list data identifies and verifies, the Output of for ms that can will be identified.For example,
The document (such as Excel document) comprising identified table can be generated, and be highlighted in the document (or with other
Mode highlights) each field for being identified in step 250, such as it is highlighted " long-term investment ", " cost-book value differentials ", " long
Phase investment is total ".In such embodiments, subsequent reviewing officer can pay special attention to the field and its correspondence being highlighted
The correctness of numerical value, and the field for not being highlighted and its corresponding numerical value then can be without reviews, or suitably put
The requirement of pine review.
In some embodiments, the table identified can also be exported in real time, such as related work people can be output to
In the display equipment of member.And notice is exported while output formats, indicates which of the table to relevant staff
Doubtful data, such as prompting can be provided by providing the mode of field text (such as, " long-term investment "), finger can also be passed through
Show that the mode for the data specific location (such as, the 2nd row the 3rd arrange) in the table that leaves a question open provides prompting.
Different recognition results is schematically described below with reference to Fig. 3 and Fig. 4.Fig. 3 is shown according to present disclosure
Exemplary embodiment wherein there is no identification mistake a schematic recognition result.In this example, it is assumed that Fig. 3 and figure
Table shown in 4 should meet following predetermined relationship:
1) " field A+ field B=field C ";And
2) " field C+ field D=field E "
In Fig. 3, the data in table 300 identified meet the two predetermined relationships.In some embodiments, make a reservation for
Relationship includes one or more input items associated at least some fields and output item, and predetermined relationship instruction is one or more
Mathematical operation relationship between input item and output item.In above-described predetermined relationship 1) in, field A and field B indicate defeated
Enter item, and field C indicates output item;In above-described predetermined relationship 2) in, field C and field D expression input item, and field
E indicates output item.
Hereinafter, will be with predetermined relationship 1) it is how example description determines whether to meet predetermined relationship.Firstly, based on
The associated numerical value of one or more input items and predetermined relationship, determine numerical value associated with output item.For table 3,2
+ 3=5 can determine that numerical value associated with output item is 5 at this time.At this time due to identified from form image and output item
Associated numerical value is also 5, thus the numerical value determined and the numerical value phase associated with output item identified from form image
Match.It can determine that predetermined relationship is satisfied at this time.Similarly, the numerical value in Fig. 3 table meets predetermined relationship 2), thus the table
Pass through verification.
Fig. 4 is shown schematically to be known according to one for wherein there is identification mistake of the exemplary embodiment of present disclosure
Other result.Table in Fig. 3 and Fig. 4 belongs to same type, predetermined relationship having the same, and difference and is in two tables
Numerical value it is different.In Fig. 4, the predetermined relationship of " field A+ field B=field C " is satisfied, and " field C+ field D=field
The predetermined relationship of E " is not satisfied, therefore three fields involved in the predetermined relationship are identified, in the recognition result of output
In be highlighted and (shown in such as Fig. 4 with ellipse).
Although it will be appreciated by those skilled in the art that in this disclosure, to involved in unsatisfied predetermined relationship
And all fields be identified, it is also possible to further be modified embodiment, such as can use multiple predetermined
Relationship carries out cross check, to exclude the identified field of some scripts, further decreases the workload of subsequent review.
After using list data verification is carried out according to the method for present disclosure embodiment, user is by tying identification
The preview of fruit, can be according to being highlighted in the prompt or document exported, to be checked table, be adjusted.Pass through
Increase the verifying function according to predetermined relationship in Table recognition, further improves Table recognition technology (such as, based on OCR
Table recognition) application effect in table automatic identification.
Fig. 5 diagrammatically illustrates the device for being used to verify list data of the exemplary embodiment according to present disclosure
500 block diagram.Specifically, which includes: image collection module 510, and image collection module 510 is configured as acquisition table
Table images, the table in form image includes multiple fields and numerical value corresponding with each field in multiple fields;Table
Identification module 520, Table recognition module 520 are configured as identifying each field and the correspondence in multiple fields based on form image
Numerical value;Relation acquisition module 530, Relation acquisition module 530 are configured as obtaining and at least some of multiple fields field
Related predetermined relationship, predetermined relationship indicate the incidence relation between numerical value corresponding at least some fields;And data
Correction verification module 540, data check module 540 be configured as corresponding at least some fields numerical value of verification whether meet it is predetermined
Relationship.
In some embodiments, device 500 further includes field identification module 550, and field identification module 550 is configured as:
It is unsatisfactory for predetermined relationship in response to numerical value corresponding at least some fields, identifies each field at least some fields.
In some embodiments, device 500 further includes document creation module 560, and document creation module 560 is configured as:
Generate the document comprising identified table;And it is highlighted each word in at least some fields identified in a document
Section.
In some embodiments, device 500 further includes Output of for ms module 570, and Output of for ms module 570 is configured as:
Export identified table;And output notice, the notice indicate that identified field is unsatisfactory for predetermined relationship.
In some embodiments, Relation acquisition module 530 is also configured to the form types based on table, acquisition and table
The corresponding relationship library of lattice type;And predetermined relationship is determined based on relationship library.
In some embodiments, predetermined relationship includes one or more input item associated at least some fields and defeated
Item out, and predetermined relationship indicates the mathematical operation relationship between one or more input items and output item.
In some embodiments, data check module 540 is also configured to based on associated with one or more input items
Numerical value and predetermined relationship, determine associated with output item numerical value;It is identified in response to determining numerical value and from form image
Numerical value associated with output item match, determine that predetermined relationship is satisfied;And in response to determining numerical value and from table
The numerical value associated with output item identified in image does not match that, determines that predetermined relationship is not satisfied.
According to the exemplary embodiment of present disclosure, a kind of equipment, including one or more processors are provided;And
Storage device, for storing one or more programs.When one or more programs are executed by one or more processors, so that
One or more processors are realized according to disclosed method.
According to the exemplary embodiment of present disclosure, a kind of computer-readable medium is provided, is stored thereon with calculating
Machine program is realized when the program is executed by processor according to disclosed method.
Fig. 6 shows the block diagram that can implement the calculating equipment 600 of multiple embodiments of present disclosure.Equipment 600 can
With the calculating equipment of the method for realizing the embodiment for executing present disclosure.As shown, equipment 600 includes central processing
Unit (CPU) 601, can be according to the computer program instructions being stored in read-only memory (ROM) 602 or from storage singly
Member 608 is loaded into the computer program instructions in random access storage device (RAM) 603, to execute various movements appropriate and place
Reason.In RAM 603, it can also store equipment 600 and operate required various programs and data.CPU 601, ROM 602 and RAM
603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to bus 604.
Multiple components in equipment 600 are connected to I/O interface 605, comprising: input unit 606, such as keyboard, mouse etc.;
Output unit 607, such as various types of displays, loudspeaker etc.;Storage unit 608, such as disk, CD etc.;And it is logical
Believe unit 609, such as network interface card, modem, wireless communication transceiver etc..Communication unit 609 allows equipment 600 by such as
The computer network of internet and/or various telecommunication networks exchange information/data with other equipment.
Processing unit 601 executes each method as described above and processing, such as method 200.For example, in some implementations
In example, method 200 may be implemented as computer software programs, is tangibly embodied in machine readable media, such as store
Unit 608.In some embodiments, some or all of of computer program can be via ROM 602 and/or communication unit
609 and be loaded into and/or be installed in equipment 600.When computer program loads to RAM 603 and by CPU 601 execute when, can
To execute one or more steps in method as described above 200.Alternatively, in other embodiments, CPU 601 can lead to
It crosses other any modes (for example, by means of firmware) appropriate and is configured as execution method 200.
Function described herein can be executed at least partly by one or more hardware logic components.Example
Such as, without limitation, the hardware logic component for the exemplary type that can be used includes: field programmable gate array (FPGA), dedicated
Integrated circuit (ASIC), Application Specific Standard Product (ASSP), the system (SOC) of system on chip, load programmable logic device
(CPLD) etc..
For implement disclosed method program code can using any combination of one or more programming languages come
It writes.These program codes can be supplied to the place of general purpose computer, special purpose computer or other programmable data processing units
Device or controller are managed, so that program code makes defined in flowchart and or block diagram when by processor or controller execution
Function/operation is carried out.Program code can be executed completely on machine, partly be executed on machine, as stand alone software
Is executed on machine and partly execute or executed on remote machine or server completely on the remote machine to packet portion.
In the context of the disclosure, machine readable media can be tangible medium, may include or is stored for
The program that instruction execution system, device or equipment are used or is used in combination with instruction execution system, device or equipment.Machine can
Reading medium can be machine-readable signal medium or machine-readable storage medium.Machine readable media can include but is not limited to electricity
Son, magnetic, optical, electromagnetism, infrared or semiconductor system, device or equipment or above content any conjunction
Suitable combination.The more specific example of machine readable storage medium includes the electrical connection of line, portable computing based on one or more
Machine disk, hard disk, random access memory (RAM), read-only memory (ROM), Erasable Programmable Read Only Memory EPROM (EPROM or
Flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage facilities or on
State any appropriate combination of content.
Although this should be understood as requiring operating in this way with shown in addition, depicting each operation using certain order
Certain order out executes in sequential order, or requires the operation of all diagrams that should be performed to obtain desired result.
Under certain environment, multitask and parallel processing be may be advantageous.Similarly, although containing several tools in being discussed above
Body realizes details, but these are not construed as the limitation to the scope of the present disclosure.In the context of individual embodiment
Described in certain features can also realize in combination in single realize.On the contrary, in the described in the text up and down individually realized
Various features can also realize individually or in any suitable subcombination in multiple realizations.
Although having used specific to this theme of the language description of structure feature and/or method logical action, answer
When understanding that theme defined in the appended claims is not necessarily limited to special characteristic described above or movement.On on the contrary,
Special characteristic described in face and movement are only to realize the exemplary forms of claims.
Claims (16)
1. a kind of method for verifying list data, comprising:
Obtain form image, the table in the form image include multiple fields and with each field in the multiple field
Corresponding numerical value;
Based on the form image, each field in the multiple field and corresponding numerical value are identified;
Obtain predetermined relationship related at least some of the multiple field field, the predetermined relationship instruction and it is described extremely
Incidence relation between the corresponding numerical value of some fields less;And
Whether verification numerical value corresponding at least some fields meets the predetermined relationship.
2. according to the method described in claim 1, further include:
It is unsatisfactory for the predetermined relationship in response to numerical value corresponding at least some fields, identifies at least some words
Each field in section.
3. according to the method described in claim 2, further include:
Generate the document of the table comprising being identified;And
The each field being highlighted in at least some fields identified within said document.
4. according to the method described in claim 2, further include:
Export the table identified;And
Output notice, the field that the notice instruction is identified are unsatisfactory for the predetermined relationship.
5. according to the method described in claim 1, wherein obtaining related at least some fields in the multiple field
The predetermined relationship include:
Based on the form types of the table, relationship corresponding with form types library is obtained;And
The predetermined relationship is determined based on the relationship library.
6. according to the method described in claim 1, wherein the predetermined relationship includes associated at least some fields
One or more input items and output item, the predetermined relationship indicate between one or more of input items and the output item
Mathematical operation relationship.
7. according to the method described in claim 6, wherein whether verification numerical value corresponding at least some fields meets
The predetermined relationship includes:
Based on numerical value associated with one or more of input items and the predetermined relationship, determination is related to the output item
The numerical value of connection;
The numerical value phase associated with the output item identified in response to the determining numerical value and from the form image
Match, determines that the predetermined relationship is satisfied;And
The numerical value associated with the output item identified in response to the determining numerical value and from the form image not phase
Matching, determines that the predetermined relationship is not satisfied.
8. a kind of for verifying the device of list data, comprising:
Image collection module is configured as obtaining form image, the table in the form image include multiple fields and with institute
State the corresponding numerical value of each field in multiple fields;
Table recognition module, is configured as: being based on the form image, identifies each field and the correspondence in the multiple field
Numerical value;
Relation acquisition module is configured as obtaining predetermined relationship related at least some of the multiple field field, institute
State the incidence relation between predetermined relationship instruction numerical value corresponding at least some fields;And
Data check module, is configured as whether verification numerical value corresponding at least some fields meets the predetermined pass
System.
9. device according to claim 8 further includes field identification module, the field identification module is configured as: being rung
The corresponding numerical value of at least some fields described in Ying Yuyu is unsatisfactory for the predetermined relationship, identifies at least some fields
Each field.
10. device according to claim 9 further includes document creation module, the document creation module is configured as:
Generate the document of the table comprising being identified;And
The each field being highlighted in at least some fields identified within said document.
11. device according to claim 9 further includes Output of for ms module, the Output of for ms module is configured as:
Export the table identified;And
Output notice, the field that the notice instruction is identified are unsatisfactory for the predetermined relationship.
12. device according to claim 8, wherein the Relation acquisition module is also configured to
Based on the form types of the table, relationship corresponding with form types library is obtained;And
The predetermined relationship is determined based on the relationship library.
13. device according to claim 8, wherein the predetermined relationship includes associated at least some fields
One or more input items and output item, the predetermined relationship indicate between one or more of input items and the output item
Mathematical operation relationship.
14. device according to claim 13, wherein the data check module is also configured to
Based on numerical value associated with one or more of input items and the predetermined relationship, determination is related to the output item
The numerical value of connection;
The numerical value phase associated with the output item identified in response to the determining numerical value and from the form image
Match, determines that the predetermined relationship is satisfied;And
The numerical value associated with the output item identified in response to the determining numerical value and from the form image not phase
Matching, determines that the predetermined relationship is not satisfied.
15. a kind of equipment, the equipment include:
One or more processors;And
Storage device, for storing one or more programs, when one or more of programs are by one or more of processing
Device executes, so that one or more of processors realize method according to any one of claims 1-7.
16. a kind of computer readable storage medium is stored thereon with computer program, realization when described program is executed by processor
Method according to any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810105169.1A CN110109918A (en) | 2018-02-02 | 2018-02-02 | For verifying the method, apparatus, equipment and computer storage medium of list data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810105169.1A CN110109918A (en) | 2018-02-02 | 2018-02-02 | For verifying the method, apparatus, equipment and computer storage medium of list data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110109918A true CN110109918A (en) | 2019-08-09 |
Family
ID=67483118
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810105169.1A Pending CN110109918A (en) | 2018-02-02 | 2018-02-02 | For verifying the method, apparatus, equipment and computer storage medium of list data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110109918A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111611990A (en) * | 2020-05-22 | 2020-09-01 | 北京百度网讯科技有限公司 | Method and device for identifying table in image |
CN112905090A (en) * | 2021-02-08 | 2021-06-04 | 北京字跳网络技术有限公司 | Spreadsheet processing method, device, terminal and storage medium |
CN117556078A (en) * | 2024-01-11 | 2024-02-13 | 北京极致车网科技有限公司 | Visual vehicle registration certificate file management method and device and electronic equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101661512A (en) * | 2009-09-25 | 2010-03-03 | 万斌 | System and method for identifying traditional form information and establishing corresponding Web form |
US20150278593A1 (en) * | 2014-03-31 | 2015-10-01 | Abbyy Development Llc | Data capture from images of documents with fixed structure |
CN105022829A (en) * | 2015-07-30 | 2015-11-04 | 四川长虹电器股份有限公司 | System and method for processing data |
CN107392260A (en) * | 2017-06-08 | 2017-11-24 | 中国民生银行股份有限公司 | The wrong scaling method and device of a kind of character identification result |
CN107463921A (en) * | 2017-08-21 | 2017-12-12 | 深圳微众税银信息服务有限公司 | A kind of reference mandate validation verification method and system |
-
2018
- 2018-02-02 CN CN201810105169.1A patent/CN110109918A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101661512A (en) * | 2009-09-25 | 2010-03-03 | 万斌 | System and method for identifying traditional form information and establishing corresponding Web form |
US20150278593A1 (en) * | 2014-03-31 | 2015-10-01 | Abbyy Development Llc | Data capture from images of documents with fixed structure |
CN105022829A (en) * | 2015-07-30 | 2015-11-04 | 四川长虹电器股份有限公司 | System and method for processing data |
CN107392260A (en) * | 2017-06-08 | 2017-11-24 | 中国民生银行股份有限公司 | The wrong scaling method and device of a kind of character identification result |
CN107463921A (en) * | 2017-08-21 | 2017-12-12 | 深圳微众税银信息服务有限公司 | A kind of reference mandate validation verification method and system |
Non-Patent Citations (1)
Title |
---|
袁新程: "ExceI表格数据校验二法", 《电脑应用》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111611990A (en) * | 2020-05-22 | 2020-09-01 | 北京百度网讯科技有限公司 | Method and device for identifying table in image |
CN111611990B (en) * | 2020-05-22 | 2023-10-31 | 北京百度网讯科技有限公司 | Method and device for identifying tables in images |
CN112905090A (en) * | 2021-02-08 | 2021-06-04 | 北京字跳网络技术有限公司 | Spreadsheet processing method, device, terminal and storage medium |
CN117556078A (en) * | 2024-01-11 | 2024-02-13 | 北京极致车网科技有限公司 | Visual vehicle registration certificate file management method and device and electronic equipment |
CN117556078B (en) * | 2024-01-11 | 2024-03-29 | 北京极致车网科技有限公司 | Visual vehicle registration certificate file management method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108170759B (en) | Complaint case processing method and device, computer equipment and storage medium | |
CN110750654A (en) | Knowledge graph acquisition method, device, equipment and medium | |
CN107437219A (en) | The voucher generation method and device of a kind of business paper | |
CN110109918A (en) | For verifying the method, apparatus, equipment and computer storage medium of list data | |
US20220171967A1 (en) | Model-independent confidence values for extracted document information using a convolutional neural network | |
CN111949550B (en) | Method, device, equipment and storage medium for automatically generating test data | |
CN114863439B (en) | Information extraction method, information extraction device, electronic equipment and medium | |
CN115547466A (en) | Medical institution registration and review system and method based on big data | |
CN113255496A (en) | Financial expense reimbursement management method based on block chain technology | |
CN115563271A (en) | Artificial intelligence accounting data entry method, system, equipment and storage medium | |
CN114444465A (en) | Information extraction method, device, equipment and storage medium | |
CN117114901A (en) | Method, device, equipment and medium for processing insurance data based on artificial intelligence | |
CN117273968A (en) | Accounting document generation method of cross-business line product and related equipment thereof | |
CN111400187A (en) | Parameter dynamic verification system and method based on customized data source | |
CN117033431A (en) | Work order processing method, device, electronic equipment and medium | |
US11966970B2 (en) | Method and system for performing income analysis from source documents | |
CN115880703A (en) | Form data processing method and device, electronic equipment and storage medium | |
CN114861622A (en) | Documentary credit generating method, documentary credit generating device, documentary credit generating equipment, storage medium and program product | |
CN115510188A (en) | Text keyword association method, device, equipment and storage medium | |
WO2018206819A1 (en) | Data storage method and apparatus | |
CN110334328B (en) | Automatic generation method and device for object list based on machine learning | |
CN114187081A (en) | Estimated value table processing method and device, electronic equipment and computer readable storage medium | |
CN113822660A (en) | Data processing method and device, electronic equipment and medium | |
CN111552779A (en) | Man-machine conversation method, device, medium and electronic equipment | |
CN117115841A (en) | Table analysis method and device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |