CN110147981A - Contract Risk checking method, device and terminal device based on text analyzing - Google Patents
Contract Risk checking method, device and terminal device based on text analyzing Download PDFInfo
- Publication number
- CN110147981A CN110147981A CN201910293568.XA CN201910293568A CN110147981A CN 110147981 A CN110147981 A CN 110147981A CN 201910293568 A CN201910293568 A CN 201910293568A CN 110147981 A CN110147981 A CN 110147981A
- Authority
- CN
- China
- Prior art keywords
- contract
- risk
- clause
- word
- text
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012550 audit Methods 0.000 claims abstract description 58
- 230000011218 segmentation Effects 0.000 claims abstract description 50
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 9
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000032258 transport Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services; Handling legal documents
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The present invention is suitable for field of artificial intelligence, provide a kind of Contract Risk checking method, device and terminal device based on text analyzing, the described method includes: the contract audit request that receiving terminal apparatus is sent, the contract audit request includes contract type information and multiple contract page pictures;Character recognition is carried out to multiple contract page pictures, obtains a contract text;Word segmentation processing is carried out to the contract text, obtains word segmentation processing as a result, the word segmentation processing result includes multiple keywords;Each keyword is matched with preset risk word, if successful match, it is determined that the contract terms where the keyword of successful match are risk contract clause;Risk auditing result is generated, the risk auditing result includes the risk contract clause.The present invention improves contract audit efficiency, improves user experience.
Description
Technical field
The invention belongs to field of artificial intelligence more particularly to a kind of Contract Risk audit sides based on text analyzing
Method, device and terminal device.
Background technique
Contract is widely used in each neck in production and living because it is with extremely strong restraining force and flexible flexibility
Domain, a complete contract are made of the contract terms of several clear rights and obligations, contract terms it is rigorous whether directly affect
A validity of contract and feasibility.Thus, the risk audit of contract is particularly important.
Currently, relying primarily on the risk audit that legal professionals carry out contract terms, on the one hand, legal professionals'
Professional knowledge and career experience have direct influence to the accuracy of auditing result, there is stronger subjectivity;On the other hand, manually
Audit contract terms bring huge workload to legal professionals one by one, and review efficiency is low.And for nonlegal profession
For people, it is even more difficult incomparable for carrying out the risk audit of contract terms, as a consequence it is hardly possible to be completed.
Summary of the invention
In view of this, the Contract Risk checking method and terminal that the embodiment of the invention provides a kind of based on text analyzing are set
It is standby, to solve the problem of that the risk audit intelligence of contract terms of the existing technology lowly affects review efficiency.
The first aspect of the embodiment of the present invention provides a kind of Contract Risk checking method based on text analyzing, comprising:
The contract audit request that receiving terminal apparatus is sent, contract audit request include contract type information and multiple
Contract page picture;
Character recognition is carried out to multiple contract page pictures, obtains a contract text;
Word segmentation processing is carried out to the contract text, obtains word segmentation processing as a result, the word segmentation processing result includes multiple
Keyword;
Each keyword is matched with preset risk word, if successful match, it is determined that successful match
Contract terms where keyword are risk contract clause;
When the matching of all keywords and preset risk word in the word segmentation processing result terminates, generation risk is audited
As a result, the risk auditing result includes the risk contract clause.
The second aspect of the embodiment of the present invention provides a kind of Contract Risk audit device based on text analyzing, comprising:
Receiving unit, for the contract audit request that receiving terminal apparatus is sent, the contract audit request includes contract
Type information and multiple contract page pictures;
Character recognition unit obtains a contract text for carrying out character recognition to multiple contract page pictures;
Word segmentation processing unit obtains word segmentation processing as a result, the participle for carrying out word segmentation processing to the contract text
Processing result includes multiple keywords;
Risk matching unit, for each keyword to be matched with preset risk word, if successful match,
Contract terms where then determining the keyword of successful match are risk contract clause;
Generation unit, for the matching knot when all keywords and preset risk word in the word segmentation processing result
Beam generates risk auditing result, and the risk auditing result includes the risk contract clause
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory and processor, described to deposit
The computer program that can be run on the processor is stored in reservoir, when the processor executes the computer program,
Realize following steps:
The contract audit request that receiving terminal apparatus is sent, contract audit request include contract type information and multiple
Contract page picture;
Character recognition is carried out to multiple contract page pictures, obtains a contract text;
Word segmentation processing is carried out to the contract text, obtains word segmentation processing as a result, the word segmentation processing result includes multiple
Keyword;
Each keyword is matched with preset risk word, if successful match, it is determined that successful match
Contract terms where keyword are risk contract clause;
When the matching of all keywords and preset risk word in the word segmentation processing result terminates, generation risk is audited
As a result, the risk auditing result includes the risk contract clause
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the computer program realizes following steps when being executed by processor:
The contract audit request that receiving terminal apparatus is sent, contract audit request include contract type information and multiple
Contract page picture;
Character recognition is carried out to multiple contract page pictures, obtains a contract text;
Word segmentation processing is carried out to the contract text, obtains word segmentation processing as a result, the word segmentation processing result includes multiple
Keyword;
Each keyword is matched with preset risk word, if successful match, it is determined that successful match
Contract terms where keyword are risk contract clause;
When the matching of all keywords and preset risk word in the word segmentation processing result terminates, generation risk is audited
As a result, the risk auditing result includes the risk contract clause.
In embodiments of the present invention, it by obtaining multiple contract page pictures and contract type, is generated and is closed based on character recognition
Same text, then word segmentation processing is carried out to contract text, so that it is determined that whether there is risk word in contract text, generate contract wind
Dangerous auditing result, so that user does not have to the manual examination and verification particulars of a contract again, in the premise of input contract page picture and contract type
Under, the intelligentized generation Contract Risk auditing result of energy greatly increases contract audit efficiency, improves user experience
Degree.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is a kind of structural representation of Contract Risk auditing system based on text analyzing provided in an embodiment of the present invention
Figure;
Fig. 2 is a kind of specific implementation stream of Contract Risk checking method based on text analyzing provided in an embodiment of the present invention
Cheng Tu;
Fig. 3 is a kind of step 202 of Contract Risk checking method based on text analyzing provided in an embodiment of the present invention
Specific implementation flow chart;
Fig. 4 is the specific implementation of another Contract Risk checking method based on text analyzing provided in an embodiment of the present invention
Flow chart;
Fig. 5 is the specific implementation of another Contract Risk checking method based on text analyzing provided in an embodiment of the present invention
Flow chart;
Fig. 6 is the specific implementation of another Contract Risk checking method based on text analyzing provided in an embodiment of the present invention
Flow chart;
Fig. 7 is a kind of structural representation of Contract Risk audit device based on text analyzing provided in an embodiment of the present invention
Figure;
Fig. 8 is the schematic diagram of terminal device provided in an embodiment of the present invention.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Fig. 1 shows the interaction signal of the Contract Risk auditing system provided in an embodiment of the present invention based on text analyzing
Figure.Contract Risk auditing system includes terminal device 100 and server 200.Terminal device 100 is interacted with server 200 with reality
Existing Contract Risk audit.Terminal device 100 and server 200 communicate to connect.As the user of terminal device 100, opens and log in
The default application of terminal device 100 shoots contract page picture by camera, and selects contract type by user interface, eventually
Contract page picture and contract type information are sent to server 200 by end equipment 100, server 200 based on contract page picture and
Contract type information carries out risk audit to contract automatically, that is to say, that no longer user is needed manually to examine treaty content
The process of automation completing Contract Risk and auditing is substantially increased contract audit efficiency, provided for user by core, server
It is convenient.
As shown in Figure 1, terminal device 100 is smart phone, in other embodiments of the present invention, terminal device can also be
Desktop computer, tablet computer, personal digital assistant (PDA) or wearable device etc..Server 200 can also be that other have meter
The terminal device of calculation ability, for example, desktop computer, tablet computer or PAD etc..It should be noted that being merely illustrative shown in Fig. 1
Illustrate, cannot be construed to concrete restriction of the invention.
The implementation process of Fig. 2 shows the provided in an embodiment of the present invention Contract Risk checking method based on text analyzing,
The Contract Risk checking method process includes step S201 to S205.The Contract Risk checking method be applicable to contract into
The situation of row risk audit.The Contract Risk checking method is executed by Contract Risk audit device, the Contract Risk audit dress
It sets and is configured at server 200 shown in FIG. 1, can be implemented by software and/or hardware.The specific implementation principle of each step is as follows.
S201, the contract audit request that receiving terminal apparatus is sent, the contract audit request includes contract type information
With multiple contract page pictures.
Wherein, installing terminal equipment has default application, which can be contract audit application, and user passes through unlatching
The default application is interacted with server to complete the audit of the risk of contract.Default application can be web application, or
Terminal applies, the present invention are not especially limited this.
In embodiments of the present invention, the installing terminal equipment has camera, and terminal device is shot each by camera
The contract page picture of contract page, thus, contract page picture is to be shot by the camera of terminal device to each contract page
The photo of acquisition.
Illustratively, in a certain user interface of default application, the user of terminal device can upload contract page picture, this
Outside, user is also an option that contract type, so that the contract audit for carrying contract page picture and contract type information be requested
It is sent to server, so that the server receives the request, to complete the audit of Contract Risk.Wherein, contract class
Type information is the type of contract, is selected on the terminal device by user.For example, house purchase contract or commodity contract etc..
That is, server is according to the institute received after terminal device sends contract audit and requests to server
Contract audit request is stated, subsequent audit step is carried out, to generate Contract Risk auditing result.
S202 carries out character recognition to multiple contract page pictures, obtains a contract text.
In the embodiment of the present invention, server carries out character knowledge to multiple contract page pictures using character recognition technology
Not, a contract text is obtained.Wherein, character recognition technology can be optical character identification ((Optical Character
Recognition, OCR) technology etc..
Optionally, as an embodiment of the present invention, step 202 includes: to carry out character knowledge to each contract page picture
Do not obtain corresponding contract Ziwen sheet, according to the page number recognition result in each contract Ziwen sheet, to multiple contract Ziwen sheets into
Row sequence obtains a contract text.
In the embodiment of the present invention, character recognition is carried out using character recognition technology pairing same page picture, obtains contract Ziwen
This.Contract Ziwen sheet is ranked up according to page number sequence, obtains a contract text.
Optionally, as another embodiment of the present invention, as shown in figure 3, step 202 includes: step 301 to 302.
S301 pre-processes each contract page picture, obtains pretreatment picture.
Wherein, there is difference to acquisition parameters such as the shooting angle of each contract page picture due to user, thus shoot
Contract page position included by the contract page picture come or size be not identical.In addition, different users is set due to the terminal used
Standby not identical, the format of captured contract page picture is also not quite similar.Therefore, in the embodiment of the present invention, first to each contract
Page picture is pre-processed, to reduce the noise data amount of subsequent processing, improves recognition efficiency.
Specifically, step 301 includes: that each contract page picture is converted into preset format, cuts off each conjunction
Background parts in same page picture in addition to contract page, and the size of the contract page picture after each excision background parts is adjusted,
Obtain pretreatment picture of the same size.
It should be noted that preset format can be jpg format, or jpeg or gif or png or bmp format
Deng the present invention is not especially limited this.
S302 carries out character recognition to each pretreatment picture and obtains corresponding contract Ziwen sheet, according to each conjunction
With the page number recognition result in Ziwen sheet, multiple contract Ziwens are originally ranked up to obtain a contract text.
In the embodiment of the present invention, character recognition is carried out to pretreatment picture using character recognition technology, obtains contract Ziwen
This.Contract Ziwen sheet is ranked up according to page number sequence, obtains a contract text.
S203 carries out word segmentation processing to the contract text, obtains word segmentation processing as a result, the word segmentation processing result includes
Multiple keywords.
In embodiments of the present invention, the segmenting method based on string matching, the segmenting method based on understanding can be used
Or word segmentation processing is carried out to contract text based on the segmenting method of statistics.It will be understood by those skilled in the art that existing participle
Method may be incorporated for the present invention, and the present invention is not specifically limited this.
After the progress character recognition of pairing same page picture obtains contract text, word segmentation processing is carried out to contract text, is obtained
To a series of corresponding keywords of the contract text, i.e., multiple keywords, that is, word segmentation processing result.
Optionally, in other embodiments of the present invention, after word segmentation processing, stop words can be first removed, then obtains institute
State a series of corresponding keywords of contract text.The accuracy that can be improved participle is handled in this way, to further increase subsequent
The accuracy of Contract Risk audit.
S204 matches each keyword with preset risk word, if successful match, it is determined that matching at
Contract terms where the keyword of function are risk contract clause.
In embodiments of the present invention, risk word is provided by senior lawyer, generally includes multiple, is pre-stored in
In the database of server.
After obtaining word segmentation processing result, by each keyword and wind in a series of corresponding keywords of contract text
Dangerous word match, if when keyword and the success of some risk word match, it is determined that the conjunction where the keyword of successful match
It is risk contract clause with clause.
That is, illustrating this contract terms when in contract terms including risk word, there are risks, need at this time
Contract of record risk position, so that user pays close attention to these risk clauses in subsequent process.
S205 generates wind when the matching of all keywords and preset risk word in the word segmentation processing result terminates
Dangerous auditing result, the risk auditing result include the risk contract clause.
In embodiments of the present invention, when each keyword and risk word in a series of corresponding keywords of contract text
Language matching terminates, then generates risk auditing result, the risk auditing result includes risk contract clause.
It is understood that risk auditing result includes risk contract clause, user can be made to pay close attention to these wind
Dangerous clause, adjusts, to avoid losing.
Optionally, in other embodiments of the present invention, the risk auditing result is pushed into terminal device, so that handy
Risk auditing result is intuitively checked at family.Illustratively, risk auditing result is risk clause list.
In embodiments of the present invention, it by obtaining multiple contract page pictures and contract type, is generated and is closed based on character recognition
Same text, then word segmentation processing is carried out to contract text, so that it is determined that whether there is risk word in contract text, generate contract wind
Dangerous auditing result, so that user does not have to the manual examination and verification particulars of a contract again, in the premise of input contract page picture and contract type
Under, the intelligentized generation Contract Risk auditing result of energy greatly increases contract audit efficiency, improves user experience
Degree.
Optionally, on the basis of above-mentioned embodiment illustrated in fig. 2, as shown in figure 4, further including step after step s 204
Rapid 206.
S206 matches each keyword in the risk contract clause with preset important word, if matching
Success, it is determined that the risk contract clause is important contract terms;If matching unsuccessful, it is determined that the risk contract clause
For insignificant contract terms.
Wherein, each contract includes multiple contract terms, and the significance level of each contract terms is different, thus, in determination
It whether there is key contracts clause in the risk contract clause in contract and then determining risk clause out, more for last output
Risk auditing result accurately quantitatively and/or qualitatively is added to be provided with niche plinth.
In embodiments of the present invention, important word is provided by senior lawyer, generally includes multiple, is pre-stored in
In the database of server.After determining risk contract clause, by each keyword in risk contract clause and preset
Important word match illustrate that the contract terms are important clause if keyword and when some important word successful match, from
And whether determined finally based on this with the presence of important clause risk, obtain more accurate Contract Risk auditing result.
On this basis, step 205 includes step 207.
S207 generates the risk clause list being combined by the risk contract clause, and marks the risk contract item
The key contracts clause and/or insignificant contract terms in money.
Illustratively, key contracts clause is only marked in risk clause list, it is to be understood that can also mark non-
Key contracts clause can also mark key contracts clause and insignificant contract terms simultaneously.By being arranged in risk contract clause
Key contracts clause and insignificant contract terms are distinguished in table, the precision that a more step improves auditing result, thus into
One step improves user experience.
Fig. 5 shows the realization of another Contract Risk checking method based on text analyzing provided in an embodiment of the present invention
Process, the Contract Risk checking method are further improved on the basis of Fig. 2 embodiment carries out Qualitative risk audit, are realized
A kind of quantitative Contract Risk checking method.As shown in figure 5, the process includes step S501 to S506.It should be noted that
The embodiment is repeated no more with Fig. 2 embodiment something in common, in place of the corresponding description for referring to Fig. 2 embodiment.
S501, the contract audit request that receiving terminal apparatus is sent, the contract audit request includes contract type information
With multiple contract page pictures.
S502 carries out character recognition to multiple contract page pictures, obtains a contract text.
S503 carries out word segmentation processing to the contract text, obtains word segmentation processing as a result, the word segmentation processing result includes
Multiple keywords.
S504 matches each keyword with preset risk word, if successful match, it is determined that matching at
Contract terms where the keyword of function are risk contract clause.
S505 obtains risk score corresponding with the preset successful keyword of risk word match;Obtain contractual revenue.
Wherein, it is preset with risk score corresponding with each risk word, risk more Risks score is higher, when some pass
Key word and the success of risk word match, then obtain the corresponding risk score of risk word, that is to say, that it is corresponding to obtain keyword
Risk score.
Contractual revenue can be uploaded to server for the user of terminal device, or be obtained according to Text region result
It arrives, the present invention is not specifically limited in this embodiment.
It should be noted that obtaining risk score can carry out simultaneously with contractual revenue is obtained, can also successively carry out, this
Invention is not especially limited the chronological order of the two.
S506 calculates the Contract Risk value according to the risk score and the contractual revenue.
According to formulaCalculate Contract Risk value.
Wherein, n is the total quantity with the preset successful keyword of risk word match;RiskScoreiFor with it is preset
The corresponding risk score of the successful keyword of risk word match;ContractRevenue is contractual revenue.When contractual revenue
When unit is member, the reaction of Contract Risk value is every corresponding degree of risk of income for generating 1 yuan.
In embodiments of the present invention, a kind of quantitative Contract Risk checking method is realized, user can be allowed more intuitive
The height for knowing Contract Risk, improve precision, to preferably instruct subsequent user behavior, avoid losing, improve
User experience.
Fig. 6 shows the realization of another Contract Risk checking method based on text analyzing provided in an embodiment of the present invention
Process, the Contract Risk checking method are further improved on the basis of Fig. 4 embodiment carries out Qualitative risk audit, are realized
A kind of quantitative Contract Risk checking method.As shown in fig. 6, the process includes step S601 to S607.It should be noted that
The embodiment is repeated no more with Fig. 4 embodiment something in common, in place of the corresponding description for referring to Fig. 4 embodiment.
S601, the contract audit request that receiving terminal apparatus is sent, the contract audit request includes contract type information
With multiple contract page pictures.
S602 carries out character recognition to multiple contract page pictures, obtains a contract text.
S603 carries out word segmentation processing to the contract text, obtains word segmentation processing as a result, the word segmentation processing result includes
Multiple keywords.
S604 matches each keyword with preset risk word, if successful match, it is determined that matching at
Contract terms where the keyword of function are risk contract clause.
S605 matches each keyword in the risk contract clause with preset important word, if matching
Success, it is determined that the risk contract clause is important contract terms;If matching unsuccessful, it is determined that the risk contract clause
For insignificant contract terms.
S606 obtains risk score corresponding with the preset successful keyword of risk word match;Obtain key contracts
Clause and the corresponding weight coefficient of insignificant contract terms;Obtain contractual revenue.
Wherein, it is preset with risk score corresponding with each risk word, risk more Risks score is higher, when some pass
Key word and the success of risk word match, then obtain the corresponding risk score of risk word, that is to say, that it is corresponding to obtain keyword
Risk score.Also, corresponding weight coefficient is respectively provided with for key contracts clause and insignificant contract terms, works as weight
Coefficient is bigger, it is meant that the significance level of contract terms is higher.
Contractual revenue can be uploaded to server for the user of terminal device, or be obtained according to Text region result
It arrives.
It should be noted that obtaining risk score, weight coefficient can carry out simultaneously with this three of contractual revenue is obtained,
It successively can successively carry out, also may be performed simultaneously two of them, the present invention does not limit the chronological order of three specifically
It is fixed.
S607 calculates the Contract Risk value according to the risk score, the weight coefficient and the contractual revenue.
According to formulaCalculate Contract Risk value.
Wherein, n is the total quantity with the preset successful keyword of risk word match;RiskScoreiFor with it is preset
The corresponding risk score of the successful keyword of risk word match;ClauseScoreiFor the weight system of the risk contract clause
Number;ContractRevenue is contractual revenue.When the unit of contractual revenue is member, the reaction of Contract Risk value is every generation 1
Yuan the corresponding degree of risk of income.
Illustratively, the weight coefficient ClauseScore of key contracts clausei1 is taken, the weight system of insignificant contract terms
Number ClauseScoreiTake 0.5.Alternatively, fixed weight coefficient can be preset for insignificant contract terms, and for every
A different key contracts clause, presets different weight coefficients.The present invention is not especially limited this.
In embodiments of the present invention, a kind of quantitative Contract Risk checking method is realized, user can be allowed more intuitive
The height for knowing Contract Risk, improve the precision of Contract Risk audit, to preferably instruct subsequent user behavior,
It avoids losing, improves user experience.
Corresponding to the Contract Risk checking method described in foregoing embodiments based on text analyzing, Fig. 7 shows the present invention
Embodiment provide based on text analyzing Contract Risk audit device structural block diagram, for ease of description, illustrate only with
The relevant part of the embodiment of the present invention.
Referring to Fig. 7, Contract Risk audit device includes:
Receiving unit 71, for the contract audit request that receiving terminal apparatus is sent, the contract audit request includes closing
Same type information and multiple contract page pictures;
Character recognition unit 72 obtains a contract text for carrying out character recognition to multiple contract page pictures;
Word segmentation processing unit 73 obtains word segmentation processing as a result, described point for carrying out word segmentation processing to the contract text
Word processing result includes multiple keywords;
Risk matching unit 74, for each keyword to be matched with preset risk word, if matching at
Function, it is determined that the contract terms where the keyword of successful match are risk contract clause;
Generation unit 75, for the matching knot when all keywords and preset risk word in the word segmentation processing result
Beam generates risk auditing result, and the risk auditing result includes the risk contract clause.
Optionally, the generation unit 75 is specifically used for:
Obtain risk score corresponding with the preset successful keyword of risk word match;Obtain contractual revenue;
The Contract Risk value is calculated according to the risk score and the contractual revenue.
Optionally, which audits device further include:
Important matching unit 76, by the risk contract clause each keyword and preset important word carry out
Match, if successful match, it is determined that the risk contract clause is important contract terms;If matching unsuccessful, it is determined that the wind
Dangerous contract terms are insignificant contract terms.
Optionally, the generation unit 75 is specifically used for:
Obtain risk score corresponding with the preset successful keyword of risk word match;Obtain key contracts clause and
The corresponding weight coefficient of insignificant contract terms;Obtain contractual revenue;
The Contract Risk value is calculated according to the risk score, the weight coefficient and the contractual revenue.
Further, the Contract Risk value is calculated according to the following formula:
Wherein, n is the total quantity with the preset successful keyword of risk word match;RiskScoreiFor with it is preset
The corresponding risk score of the successful keyword of risk word match;ClauseScoreiFor the weight system of the risk contract clause
Number, the weight coefficient of the key contracts clause are greater than the weight coefficient of the insignificant contract terms;ContractRevenue
For contractual revenue.
Optionally, character recognition unit 72 are specifically used for:
Each contract page picture is pre-processed, pretreatment picture is obtained;
Character recognition is carried out to each pretreatment picture and obtains corresponding contract Ziwen sheet, according to each contract Ziwen
Page number recognition result in this, is originally ranked up multiple contract Ziwens to obtain a contract text.
Optionally, described that each contract page picture is pre-processed, obtain pretreatment picture, comprising:
Each contract page picture is converted into preset format, cut off in each contract page picture except contract page with
Outer background parts, and the size of the contract page picture after each excision background parts is adjusted, obtain pretreatment of the same size
Picture.
In embodiments of the present invention, it by obtaining multiple contract page pictures and contract type, is generated and is closed based on character recognition
Same text, then word segmentation processing is carried out to contract text, so that it is determined that whether there is risk word in contract text, generate contract wind
Dangerous auditing result, so that user does not have to the manual examination and verification particulars of a contract again, in the premise of input contract page picture and contract type
Under, the intelligentized generation Contract Risk auditing result of energy greatly increases contract audit efficiency, improves user experience
Degree.Further, a kind of quantitative Contract Risk checking method is provided, can allow user is more intuitive to know Contract Risk
Height, improve Contract Risk audit precision avoid losing to preferably instruct subsequent user behavior.
Fig. 8 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in figure 8, the terminal of the embodiment is set
Standby 8 include: processor 80, memory 81 and are stored in the meter that can be run in the memory 81 and on the processor 80
Calculation machine program 82, such as Contract Risk review procedure.The processor 80 is realized above-mentioned each when executing the computer program 82
Step in a Contract Risk checking method embodiment based on text analyzing, such as step 201 shown in Fig. 2 is to 205.Or
Person, the processor 80 realize the function of each module/unit in above-mentioned each Installation practice when executing the computer program 82,
Such as the function of unit 71 to 75 shown in Fig. 7.
Illustratively, the computer program 82 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 81, and are executed by the processor 80, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 82 in the terminal device 8 is described.
The terminal device 8 can be server, desktop PC, notebook, palm PC and cloud server etc.
Calculate equipment.The terminal device may include, but be not limited only to, processor 80, memory 81.Those skilled in the art can manage
Solution, Fig. 8 is only the example of terminal device 8, does not constitute the restriction to terminal device 8, may include more or more than illustrating
Few component perhaps combines certain components or different components, such as the terminal device can also be set including input and output
Standby, network access equipment, bus etc..
Alleged processor 80 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 81 can be the internal storage unit of the terminal device 8, such as the hard disk or interior of terminal device 8
It deposits.The memory 81 is also possible to the External memory equipment of the terminal device 8, such as be equipped on the terminal device 8
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 81 can also both include the storage inside list of the terminal device 8
Member also includes External memory equipment.The memory 81 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 81 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of Contract Risk checking method based on text analyzing characterized by comprising
The contract audit request that receiving terminal apparatus is sent, the contract audit request includes contract type information and multiple contracts
Page picture;
Character recognition is carried out to multiple contract page pictures, obtains a contract text;
Word segmentation processing is carried out to the contract text, obtains word segmentation processing as a result, the word segmentation processing result includes multiple keys
Word;
Each keyword is matched with preset risk word, if successful match, it is determined that the key of successful match
Contract terms where word are risk contract clause;
When the matching of all keywords and preset risk word in the word segmentation processing result terminates, generation risk audit is tied
Fruit, the risk auditing result include the risk contract clause.
2. Contract Risk checking method as described in claim 1, which is characterized in that the keyword institute of the determining successful match
Contract terms be risk contract clause after, further includes:
Each keyword in the risk contract clause is matched with preset important word, if successful match, really
The fixed risk contract clause is important contract terms;If matching unsuccessful, it is determined that the risk contract clause is insignificant
Contract terms;
Correspondingly, the generation risk auditing result, comprising:
The risk clause list being combined by the risk contract clause is generated, and is marked described in the risk contract clause
Key contracts clause and/or insignificant contract terms.
3. Contract Risk checking method as described in claim 1, which is characterized in that the generation risk auditing result, comprising:
Obtain risk score corresponding with the preset successful keyword of risk word match;Obtain contractual revenue;
The Contract Risk value is calculated according to the risk score and the contractual revenue.
4. Contract Risk checking method as claimed in claim 2, which is characterized in that the generation risk auditing result, comprising:
Obtain risk score corresponding with the preset successful keyword of risk word match;Obtain key contracts clause and non-heavy
Want the corresponding weight coefficient of contract terms;Obtain contractual revenue;
The Contract Risk value is calculated according to the risk score, the weight coefficient and the contractual revenue.
5. Contract Risk checking method as claimed in claim 4, which is characterized in that it is described according to the risk factor, it is described
Weight coefficient and the contractual revenue calculate the Contract Risk value, comprising:
The Contract Risk value is calculated according to the following formula:
Wherein, n is the total quantity with the preset successful keyword of risk word match;RiskScoreiFor with preset risk
The corresponding risk score of the successful keyword of word match;ClauseScoreiFor the weight coefficient of the risk contract clause,
The weight coefficient of the key contracts clause is greater than the weight coefficient of the insignificant contract terms;ContractRevenue is
Contractual revenue.
6. Contract Risk checking method as described in claim 1, which is characterized in that it is described to multiple contract page pictures into
Line character identification, obtains a contract text, comprising:
Each contract page picture is pre-processed, pretreatment picture is obtained;
Character recognition is carried out to each pretreatment picture and obtains corresponding contract Ziwen sheet, according in each contract Ziwen sheet
Page number recognition result, multiple contract Ziwens are originally ranked up to obtain a contract text.
7. Contract Risk checking method as claimed in claim 6, which is characterized in that described to be carried out in advance to each contract page picture
Processing obtains pretreatment picture, comprising:
Each contract page picture is converted into preset format, is cut off in each contract page picture in addition to contract page
Background parts, and the size of the contract page picture after each excision background parts is adjusted, obtain pretreatment picture of the same size.
8. a kind of Contract Risk based on text analyzing audits device characterized by comprising
Receiving unit, for the contract audit request that receiving terminal apparatus is sent, the contract audit request includes contract type
Information and multiple contract page pictures;
Character recognition unit obtains a contract text for carrying out character recognition to multiple contract page pictures;
Word segmentation processing unit obtains word segmentation processing as a result, the word segmentation processing for carrying out word segmentation processing to the contract text
It as a result include multiple keywords;
Risk matching unit, for matching each keyword with preset risk word, if successful match, really
Contract terms where determining the keyword of successful match are risk contract clause;
Generation unit, it is raw for terminating when the matching of all keywords and preset risk word in the word segmentation processing result
At risk auditing result, the risk auditing result includes the risk contract clause.
9. a kind of terminal device, including memory and processor, it is stored with and can transports on the processor in the memory
Capable computer program, which is characterized in that when the processor executes the computer program, realize such as claim 1 to 7 times
The step of Contract Risk checking method described in one.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the Contract Risk audit of any one of such as claim 1 to 7 of realization the method when the computer program is executed by processor
The step of method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910293568.XA CN110147981A (en) | 2019-04-12 | 2019-04-12 | Contract Risk checking method, device and terminal device based on text analyzing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910293568.XA CN110147981A (en) | 2019-04-12 | 2019-04-12 | Contract Risk checking method, device and terminal device based on text analyzing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110147981A true CN110147981A (en) | 2019-08-20 |
Family
ID=67588272
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910293568.XA Pending CN110147981A (en) | 2019-04-12 | 2019-04-12 | Contract Risk checking method, device and terminal device based on text analyzing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110147981A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110705265A (en) * | 2019-08-27 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Contract clause risk identification method and device |
CN110826321A (en) * | 2019-09-19 | 2020-02-21 | 平安科技(深圳)有限公司 | Contract file risk checking method and device, computer equipment and storage medium |
CN111275410A (en) * | 2020-02-29 | 2020-06-12 | 重庆百事得大牛机器人有限公司 | Remote interaction method for remote counselor of enterprise |
CN111311451A (en) * | 2020-02-29 | 2020-06-19 | 重庆百事得大牛机器人有限公司 | Remote interaction management system for corporate counselor services |
CN111368521A (en) * | 2020-02-29 | 2020-07-03 | 重庆百事得大牛机器人有限公司 | Management method for legal advisor service |
CN111753090A (en) * | 2020-06-30 | 2020-10-09 | 北京来也网络科技有限公司 | Document auditing method, device, equipment and medium based on RPA and AI |
CN112950017A (en) * | 2021-02-26 | 2021-06-11 | 云账户技术(天津)有限公司 | Contract risk identification method and device and electronic equipment |
CN112950170A (en) * | 2020-06-19 | 2021-06-11 | 支付宝(杭州)信息技术有限公司 | Auditing method and device |
CN113780038A (en) * | 2020-06-10 | 2021-12-10 | 深信服科技股份有限公司 | Picture auditing method and device, computing equipment and storage medium |
CN113779640A (en) * | 2021-09-01 | 2021-12-10 | 北京橙色云科技有限公司 | Contract signing method, contract signing device and storage medium |
US11494720B2 (en) | 2020-06-30 | 2022-11-08 | International Business Machines Corporation | Automatic contract risk assessment based on sentence level risk criterion using machine learning |
CN116485587A (en) * | 2023-04-21 | 2023-07-25 | 深圳润高智慧产业有限公司 | Community service acquisition method, community service providing method, electronic device and storage medium |
CN117252690A (en) * | 2023-11-17 | 2023-12-19 | 杭州钱袋数字科技有限公司 | Loan contract online signing method and system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103366231A (en) * | 2012-03-29 | 2013-10-23 | 上海天闻律师事务所 | Contract risk information automatic processing method and device |
US20140053069A1 (en) * | 2012-08-16 | 2014-02-20 | Sap Ag | Identifying and mitigating risks in contract document using text analysis with custom high risk clause dictionary |
CN107608958A (en) * | 2017-09-07 | 2018-01-19 | 湖南湘君奕成信息技术有限公司 | Contract text risk information method for digging and system based on clause unified Modeling |
CN108519972A (en) * | 2018-03-26 | 2018-09-11 | 北京北大英华科技有限公司 | A kind of legal risk determination method, device and the computer equipment of contract terms |
CN108763499A (en) * | 2018-05-30 | 2018-11-06 | 平安科技(深圳)有限公司 | Calling quality detecting method, device, equipment and storage medium based on intelligent sound |
CN109192202A (en) * | 2018-09-21 | 2019-01-11 | 平安科技(深圳)有限公司 | Voice safety recognizing method, device, computer equipment and storage medium |
CN109543516A (en) * | 2018-10-16 | 2019-03-29 | 深圳壹账通智能科技有限公司 | Signing intention judgment method, device, computer equipment and storage medium |
-
2019
- 2019-04-12 CN CN201910293568.XA patent/CN110147981A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103366231A (en) * | 2012-03-29 | 2013-10-23 | 上海天闻律师事务所 | Contract risk information automatic processing method and device |
US20140053069A1 (en) * | 2012-08-16 | 2014-02-20 | Sap Ag | Identifying and mitigating risks in contract document using text analysis with custom high risk clause dictionary |
CN107608958A (en) * | 2017-09-07 | 2018-01-19 | 湖南湘君奕成信息技术有限公司 | Contract text risk information method for digging and system based on clause unified Modeling |
CN108519972A (en) * | 2018-03-26 | 2018-09-11 | 北京北大英华科技有限公司 | A kind of legal risk determination method, device and the computer equipment of contract terms |
CN108763499A (en) * | 2018-05-30 | 2018-11-06 | 平安科技(深圳)有限公司 | Calling quality detecting method, device, equipment and storage medium based on intelligent sound |
CN109192202A (en) * | 2018-09-21 | 2019-01-11 | 平安科技(深圳)有限公司 | Voice safety recognizing method, device, computer equipment and storage medium |
CN109543516A (en) * | 2018-10-16 | 2019-03-29 | 深圳壹账通智能科技有限公司 | Signing intention judgment method, device, computer equipment and storage medium |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110705265A (en) * | 2019-08-27 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Contract clause risk identification method and device |
CN110826321A (en) * | 2019-09-19 | 2020-02-21 | 平安科技(深圳)有限公司 | Contract file risk checking method and device, computer equipment and storage medium |
CN111275410A (en) * | 2020-02-29 | 2020-06-12 | 重庆百事得大牛机器人有限公司 | Remote interaction method for remote counselor of enterprise |
CN111311451A (en) * | 2020-02-29 | 2020-06-19 | 重庆百事得大牛机器人有限公司 | Remote interaction management system for corporate counselor services |
CN111368521A (en) * | 2020-02-29 | 2020-07-03 | 重庆百事得大牛机器人有限公司 | Management method for legal advisor service |
CN111368521B (en) * | 2020-02-29 | 2023-04-07 | 重庆百事得大牛机器人有限公司 | Management method for legal advisor service |
CN113780038A (en) * | 2020-06-10 | 2021-12-10 | 深信服科技股份有限公司 | Picture auditing method and device, computing equipment and storage medium |
CN112950170A (en) * | 2020-06-19 | 2021-06-11 | 支付宝(杭州)信息技术有限公司 | Auditing method and device |
US11494720B2 (en) | 2020-06-30 | 2022-11-08 | International Business Machines Corporation | Automatic contract risk assessment based on sentence level risk criterion using machine learning |
CN111753090A (en) * | 2020-06-30 | 2020-10-09 | 北京来也网络科技有限公司 | Document auditing method, device, equipment and medium based on RPA and AI |
CN112950017A (en) * | 2021-02-26 | 2021-06-11 | 云账户技术(天津)有限公司 | Contract risk identification method and device and electronic equipment |
CN113779640A (en) * | 2021-09-01 | 2021-12-10 | 北京橙色云科技有限公司 | Contract signing method, contract signing device and storage medium |
CN116485587A (en) * | 2023-04-21 | 2023-07-25 | 深圳润高智慧产业有限公司 | Community service acquisition method, community service providing method, electronic device and storage medium |
CN116485587B (en) * | 2023-04-21 | 2024-04-09 | 深圳润高智慧产业有限公司 | Community service acquisition method, community service providing method, electronic device and storage medium |
CN117252690A (en) * | 2023-11-17 | 2023-12-19 | 杭州钱袋数字科技有限公司 | Loan contract online signing method and system |
CN117252690B (en) * | 2023-11-17 | 2024-02-23 | 杭州钱袋数字科技有限公司 | Loan contract online signing method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110147981A (en) | Contract Risk checking method, device and terminal device based on text analyzing | |
CN110163478B (en) | Risk examination method and device for contract clauses | |
CN109479061A (en) | Compliance violates detection | |
CN108153901A (en) | The information-pushing method and device of knowledge based collection of illustrative plates | |
CN109345282A (en) | A kind of response method and equipment of business consultation | |
CN107924679A (en) | Delayed binding during inputting understanding processing in response selects | |
US10678786B2 (en) | Translating search queries on online social networks | |
CN107491534A (en) | Information processing method and device | |
CN110674255B (en) | Text content auditing method and device | |
CN107111725A (en) | Private information is protected in input understanding system | |
CN106874253A (en) | Recognize the method and device of sensitive information | |
CN104346418A (en) | Anonymizing Sensitive Identifying Information Based on Relational Context Across a Group | |
CN105122935A (en) | Improved media sharing techniques | |
AU2019204444B2 (en) | System and method for enrichment of ocr-extracted data | |
CN110489345A (en) | A kind of collapse polymerization, device, medium and equipment | |
WO2022134360A1 (en) | Word embedding-based model training method, apparatus, electronic device, and storage medium | |
CN108170759A (en) | Method, apparatus, computer equipment and the storage medium of tip-offs about environmental issues processing | |
CN104572847B (en) | A kind of method and device of photo name | |
CN109741086A (en) | A kind of generation method and equipment of computation model | |
CN110069698A (en) | Information-pushing method and device | |
CN108255602A (en) | Task combined method and terminal device | |
CN112468658B (en) | Voice quality detection method and device, computer equipment and storage medium | |
CN107992523A (en) | The function choosing-item lookup method and terminal device of mobile application | |
CN109241722A (en) | For obtaining method, electronic equipment and the computer-readable medium of information | |
US20130151519A1 (en) | Ranking Programs in a Marketplace System |
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 |