CN110070264A - Contract evaluation method, platform, equipment and readable storage medium storing program for executing - Google Patents
Contract evaluation method, platform, equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN110070264A CN110070264A CN201910205782.5A CN201910205782A CN110070264A CN 110070264 A CN110070264 A CN 110070264A CN 201910205782 A CN201910205782 A CN 201910205782A CN 110070264 A CN110070264 A CN 110070264A
- Authority
- CN
- China
- Prior art keywords
- contract
- clause
- exceptional
- evaluated
- terms
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 84
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 28
- 239000013598 vector Substances 0.000 claims description 116
- 239000011159 matrix material Substances 0.000 claims description 30
- 238000005520 cutting process Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 238000003066 decision tree Methods 0.000 claims description 12
- 239000003795 chemical substances by application Substances 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012550 audit Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- SBNFWQZLDJGRLK-UHFFFAOYSA-N phenothrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=CC=CC(OC=2C=CC=CC=2)=C1 SBNFWQZLDJGRLK-UHFFFAOYSA-N 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of contract evaluation methods, including the exceptional clause in determination contract terms to be evaluated;Stop words filter operation is carried out to the exceptional clause, to obtain exceptional clause information;Based on exceptional clause information, the corresponding target contract terms of exceptional clause are determined in contract terms database, and the score information of the exceptional clause is determined based on target contract terms;The corresponding contract evaluating template of contract to be evaluated is obtained, and fills contract evaluating template based on contract terms to be evaluated;According to the score information of exceptional clause, the score value of contract to be evaluated is calculated based on filled contract evaluating template.The invention also discloses a kind of contract evaluation platform, equipment and readable storage medium storing program for executing.The present invention is handled contract text by the data processing technique based on matching tree, the score value of contract to be evaluated is accurately obtained with specific reference to contract terms database, and then realize the overall evaluation to contract to be evaluated.
Description
Technical field
The present invention relates to data processing field more particularly to a kind of contract evaluation method, platform, equipment and readable storage mediums
Matter.
Background technique
With the rapid development of economic society, inevitably contact contract is literary in work and life for everyone
This, for example, employ registration, rent is sought in house to let, house, second-hand house dealing, out on tours etc..The counterpart of contract both wrapped
Individual is included, also including business entity etc..The form of contract text had both included instant hand-writing contract, also included that counterpart is quasi- in advance
The model agreements got ready.Especially each in face of house deal intermediary, tourist service company, house lease intermediary etc.
When kind mechanism, the not very fair contract item of some couples of users can be hidden in model agreements since these mechanisms are intentional or unintentional
Money.The contract text not reasonable in face of these, most users are difficult to all find the unreasonable clause in these texts, from
It and is that user brings many potential threats and loss.
Currently, focusing on contract terms generation mostly in existing contract analysis scheme or document, utilizing contract template skill
Art helps user to generate blank form contract.And it is directed to the discriminance analysis of contract terms, single contract terms are often directed to, to contract
Whole availability is not analyzed, it is difficult to identify the unreasonable risk information in contract text, contract terms is caused to be deposited
In potential risks.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of contract evaluation method, platform, equipment and readable storage medium storing program for executing, it is intended to
Solve the technical issues of existing contract identifies the unreasonable risk information being difficult to out in contract text.
To achieve the above object, the present invention provides a kind of contract evaluation method, and the contract evaluation method includes following step
It is rapid:
The contract terms to be evaluated of contract to be evaluated are obtained, and determine the exceptional clause in the contract terms to be evaluated;
Based on default stop words, stop words filter operation is carried out to the exceptional clause, to obtain exceptional clause information;
Based on the exceptional clause information, the corresponding target contract of the exceptional clause is determined in contract terms database
Clause, and determine based on the target contract terms score information of the exceptional clause;
The corresponding contract evaluating template of the contract to be evaluated is obtained, and based on described in the contract terms filling to be evaluated
Contract evaluating template;
According to the score information of the exceptional clause, based on the filled contract evaluating template be calculated it is described to
The score value of evaluation contract.
Further, it is based on the exceptional clause information, it is described that the exceptional clause is determined in contract terms database
The step of corresponding target contract terms includes:
Word-based vector model is trained the exceptional clause information, corresponding to obtain the exceptional clause information
Term vector;
The corresponding sentence vector of the exceptional clause is determined based on the term vector;
Based on the default sentence vector for presetting contract terms in the sentence vector and the contract terms database, meter
Calculate the similarity between the exceptional clause and each default contract terms;
Based on the similarity, the corresponding target contract terms of the exceptional clause are determined in contract terms database.
Further, described the step of determining the exceptional clause corresponding sentence vector based on the term vector, includes:
The similarity between the term vector and the term vector in matched sentences subvector is calculated, is generated based on the similarity
Similar word matrix, wherein the element of every a line in the similar word matrix is in same term vector and matched sentences subvector
Similarity between term vector, the element of each column is the term vector and matched sentences of same exceptional clause in the similar word matrix
The similarity between term vector in subvector;
Maximum similarity in each column element based on the similar word matrix generates the sentence vector.
Further, described to be based on the similarity, determine that the exceptional clause is corresponding in contract terms database
The step of target contract terms includes:
The corresponding maximum similarity of the exceptional clause is determined based on the similarity;
By the corresponding default contract terms of the maximum similarity, as the corresponding exceptional clause of the maximum similarity
Target contract terms.
Further, the contract terms to be evaluated for obtaining contract to be evaluated, and determine the contract terms to be evaluated
In exceptional clause the step of include:
Text cutting is carried out to the contract to be evaluated, to obtain the contract terms of the contract to be evaluated;
Cleaning operation is carried out to the contract terms of the contract to be evaluated, removes the repetition clause in the contract terms,
To obtain the contract terms to be evaluated;
Based on the clause theme of the contract terms to be evaluated, by agent model to contract terms to be evaluated progress time
It goes through, with the exceptional clause in the determination contract terms to be evaluated.
Further, described the step of obtaining the contract to be evaluated corresponding contract evaluating template, includes:
Obtain the contract main body of the contract to be evaluated;
Contract evaluating template is determined based on the contract main body and the contract terms to be evaluated.
Further, the score information according to the exceptional clause is based on the filled contract evaluating template
The step of score value of the contract to be evaluated is calculated include:
The missing item of the contract to be evaluated is determined based on the contract evaluating template and the contract terms to be evaluated
Money;
The filled contract evaluating template is based on according to institute's scoring information and the missing clause to be calculated
The score value;
Based on the exceptional clause information, the corresponding violation information of the exceptional clause is determined by decision-tree model;
The evaluation information of the contract to be evaluated is generated based on the violation information and institute's scoring information, and sends institute
Evaluation information and missing clause are stated to the corresponding terminal of the contract to be evaluated.
In addition, to achieve the above object, the present invention also provides a kind of contract evaluation platform, the contract evaluation platform packet
It includes:
Module is obtained, for obtaining the contract terms to be evaluated of contract to be evaluated, and determines the contract terms to be evaluated
In exceptional clause;
Filtering module, it is different to obtain for carrying out stop words filter operation to the exceptional clause based on default stop words
Normal clause information;
Determining module, for determining the corresponding target contract terms of the exceptional clause in contract terms database, and
The score information of the exceptional clause is determined based on the target contract terms;
Module is filled, for obtaining the corresponding contract evaluating template of the contract to be evaluated, and is based on the conjunction to be evaluated
The contract evaluating template is filled with clause;
Computing module is based on the filled contract evaluating template for the score information according to the exceptional clause
The score value of the contract to be evaluated is calculated.
In addition, to achieve the above object, the present invention also provides a kind of contract valuator device, the contract valuator device packet
It includes: memory, processor and being stored in the contract assessment process that can be run on the memory and on the processor, it is described
Contract assessment process realizes the step of contract evaluation method above-mentioned when being executed by the processor.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Contract assessment process is stored on storage medium, the contract assessment process realizes contract evaluation above-mentioned when being executed by processor
The step of method.
The present invention is determined in the contract terms to be evaluated by obtaining the contract terms to be evaluated of contract to be evaluated
Exceptional clause carries out stop words filter operation to the exceptional clause then based on default stop words, to obtain exceptional clause letter
Breath is then based on the exceptional clause information, and the corresponding target contract of the exceptional clause is determined in contract terms database
Clause, and determine based on the target contract terms score information of the exceptional clause, then obtain the contract to be evaluated
Corresponding contract evaluating template, and the contract evaluating template is filled based on the contract terms to be evaluated, finally according to
The scoring of the contract to be evaluated is calculated based on the filled contract evaluating template for the score information of exceptional clause
Value is handled contract text by the data processing technique based on matching tree, accurate with specific reference to contract terms database
The score value of contract to be evaluated is obtained, and then realizes the overall evaluation to contract to be evaluated, to excavate in contract to be evaluated not
Reasonable terms, to reduce potential threat caused by contract to be evaluated and loss.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of contract valuator device in hardware running environment that the embodiment of the present invention is related to;
Fig. 2 is the flow diagram of contract evaluation method first embodiment of the present invention;
Fig. 3 is that the exceptional clause information is based in contract evaluation method second embodiment of the present invention, described in contract item
The refinement flow diagram for the step of corresponding target contract terms of the exceptional clause are determined in money database;
Fig. 4 is to determine that the exceptional clause is corresponding based on the term vector in contract evaluation method 3rd embodiment of the present invention
Sentence vector the step of refinement flow diagram;
Fig. 5 is that the similarity is based in contract evaluation method fourth embodiment of the present invention, in contract terms database
The refinement flow diagram for the step of determining the exceptional clause corresponding target contract terms;
Fig. 6 is the contract terms to be evaluated that contract to be evaluated is obtained in the 5th embodiment of contract evaluation method of the present invention, and
The refinement flow diagram for the step of determining the exceptional clause in the contract terms to be evaluated;
Fig. 7 is to obtain the corresponding contract of the contract to be evaluated in contract evaluation method sixth embodiment of the present invention to evaluate mould
The refinement flow diagram of the step of plate;
Fig. 8 is in the 7th embodiment of contract evaluation method of the present invention according to the score information of the exceptional clause, based on filling out
The refinement flow diagram for the step of score value of the contract to be evaluated is calculated in the contract evaluating template after filling;
Fig. 9 is the functional block diagram of one embodiment of contract evaluation platform of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 is the structure of contract valuator device in hardware running environment that the embodiment of the present invention is related to
Schematic diagram.
Contract valuator device of the embodiment of the present invention may include: processor 1001, such as CPU, network interface 1004, user
Interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing the connection between these components
Communication.User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional user
Interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 optionally may include having for standard
Line interface, wireless interface (such as WI-FI interface).Memory 1005 can be high speed RAM memory, be also possible to stable storage
Device (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processing
The storage device of device 1001.
Contract is evaluated it will be understood by those skilled in the art that contract valuator device structure shown in Fig. 1 is not constituted
The restriction of equipment may include perhaps combining certain components or different component cloth than illustrating more or fewer components
It sets.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage medium
Believe module, Subscriber Interface Module SIM and contract assessment process.
In contract valuator device shown in Fig. 1, network interface 1004 is mainly used for connecting background server, takes with backstage
Business device carries out data communication;User interface 1003 is mainly used for connecting client (user terminal), carries out data communication with client;
And processor 1001 can be used for calling the contract assessment process stored in memory 1005, and execute following contract evaluation method
Each embodiment in operation.
The present invention also provides a kind of contract evaluation methods, are contract evaluation method first of the present invention implementation referring to Fig. 2, Fig. 2
The flow diagram of example.
In the present embodiment, which includes:
Step S100 obtains the contract terms to be evaluated of contract to be evaluated, and determines in the contract terms to be evaluated
Exceptional clause;
In the present embodiment, the contract text evaluated can be uploaded to conjunction by mobile terminal or PC by user
Same evaluation platform, for example, contract text is uploaded to contract evaluation platform by the APP by mobile terminal.
When receiving contract to be evaluated, contract evaluation platform carries out text cutting to the contract to be evaluated, to be somebody's turn to do
The contract terms to be evaluated of contract to be evaluated, wherein if the contract to be evaluated is the contract dataset of picture format, first to contract
Data carry out OCR and identify to obtain contract text, then carry out text cutting, for example, being carried out using existing text cutting algorithm
Text cutting, to ensure that the data after cutting are a complete contract terms, for example, including one in the data after cutting
Fullstop.
When getting contract terms to be evaluated, determine that the exceptional clause in the contract terms to be evaluated specifically first obtains
The clause theme for taking contract terms to be evaluated traverses contract terms to be evaluated by agent model based on clause theme,
With the exceptional clause in the determination contract terms to be evaluated.
It should be noted that agent model includes the clause theme of a plurality of default exceptional clause, by being based on clause theme
The agent model is traversed, can determine the exceptional clause in contract terms to be evaluated roughly.
Step S200 carries out stop words filter operation to the exceptional clause, to obtain abnormal item based on default stop words
Money information;
In the present embodiment, when determining exceptional clause, based on default stop words, stop words filtering is carried out to exceptional clause
Operation obtains exceptional clause information, i.e. deactivating in the exceptional clause after removal cleaning to adjust the stop words in exceptional clause
Word specifically traverses exceptional clause, if existing in the exceptional clause currently traversed consistent with the stop words in default deactivated dictionary
Word, then will be removed in the exceptional clause currently traversed with the consistent word of stop words in default deactivated dictionary.Wherein, this is default
It deactivates in dictionary and is stored with default stop words, which includes the exclusive stop words without legal sense, and packet
Include the conventional stop words including conjunction, preposition etc..
Step S300 is based on the exceptional clause information, determines that the exceptional clause is corresponding in contract terms database
Target contract terms, and determine based on the target contract terms score information of the exceptional clause;
In the present embodiment, when getting exceptional clause information, exceptional clause pair is determined in contract terms database
The target contract terms answered specifically determine the sentence vector of exceptional clause according to exceptional clause information, according to based on the sentence
The default sentence vector that contract terms are preset in vector and contract terms database, calculates exceptional clause and each default contract
Similarity between clause, and the corresponding target contract terms of exceptional clause are determined according to similarity, it specifically, will be with abnormal item
Similarity between money meets the default contract terms of preset condition as the target contract terms, and is based on target contract terms
It determines the score information of exceptional clause, i.e., determines the score information of the exceptional clause according to the score information of target contract terms.
Step S400 obtains the corresponding contract evaluating template of the contract to be evaluated, and is based on the contract item to be evaluated
Money fills the contract evaluating template;
In the present embodiment, it can first determine the contract main body of contract to be evaluated, be based on the contract main body and exceptional clause
It determines contract evaluating template, and according to the main body of each clause information and the main body of contract evaluating template, each clause is believed
Breath is filled to contract evaluating template.
Specifically, can first based on contract main body determines target contract evaluating template, target contract evaluating template include it is more
When a, according to exceptional clause (including missing clause) and the corresponding rule of exceptional clause, selected in target contract evaluating template
The contract evaluating template of definitive application is selected, for example, the clause theme of contract evaluating template includes the clause theme of exceptional clause.
Step S500 is calculated according to the score information of the exceptional clause based on the filled contract evaluating template
Obtain the score value of the contract to be evaluated.
In the present embodiment, in the score information for getting exceptional clause, based on filled contract evaluating template
Calculation obtains the score value of contract to be evaluated, specifically, the total score of the contract evaluating template can be preset, and is evaluated according to the contract
Contract terms quantity averagely total score in template, obtains the best result of each contract terms, based on the best result and different
The score information of normal clause, calculates the scoring of each exceptional clause, and the scoring based on exceptional clause calculates the contract to be evaluated
Score value, wherein other contract terms in contract to be evaluated in addition to exceptional clause can be calculated according to best result.
For example, the contract to be evaluated includes 10 contract terms to be evaluated, and 3 therein are exceptional clause, abnormal
The score information of clause is respectively 2,3,3;If the contract evaluating template includes 10 contract terms, the full marks of each contract terms
For 10 points (i.e. the scoring of normal contract clause is 10 points), then the score value of the contract to be evaluated is 7*10+2+3+3=78;If
The contract evaluating template includes 20 contract terms, then showing the contract to be evaluated, there are 10 missing clauses, wherein Ge Gehe
Full marks with clause are 5 points (i.e. the scoring of normal contract clause is 5 points), and the score value of the contract to be evaluated is 7*5+2+3+3
=43.
It should be noted that needing to create contract terms database before carrying out contract evaluation, specifically, receive simultaneously
Contract terms information and contract evaluating template are stored, which includes: abnormal contract terms, abnormal contract terms
Score value and normal contract clause, normal contract clause score value.
For the contract of different subjects, contract evaluating template include the contract of the theme necessary contract terms that are included with
And the contract terms presence pair in optional contract terms, necessity contract terms and optional contract terms and contract terms information
It should be related to.
Wherein, abnormal contract terms include missing clause and risk clause, and missing clause refers to the clause lacked in contract,
For example, the necessary contract terms in missing contract evaluating template;Risk clause refers to that the clause might have risk;Risk clause
It include the information such as corresponding risk class (score information), amending advice with missing clause.
For abnormal contract terms, the main body of abnormal contract terms is extracted, and obtains the corresponding mark of abnormal contract terms
Sign information, the articles of law that the unavailable information of the label information and the contract terms mainly violate.Getting abnormal contract
When the main body of clause, according to articles of law involved in abnormal contract terms, the LDA (theme for being directed to articles of law granularity is established
Model).
LR model (logistic regression) also can be used to be trained contract terms information, by the marking of contract terms information
As a result it is mapped in the section of 0-1, for example, scoring is 80 (hundred-mark system), then after training for a certain contract terms information
Score value is 0.8.Wherein, LR model is feature to be carried out linear combination, then combined result is led on the basis of linear regression
Cross one layer of sigmoid Function Mapping at the result is that 1 or 0 probability, Logic Regression Models are a disaggregated models, to generation
The result is that 0 or 1 probability is modeled, likelihood function is maximized by using the method for maximal possibility estimation, using in gradient
The method risen obtains making the maximum parameter of likelihood function.Wherein, if there is the clause of multiple marking results, then by multiple marking
As a result final marking result of the mean value as the clause.
For each contract terms information, based on default stop words, stop words filter operation is carried out to contract terms information,
Word-based vector model is trained filtered contract terms information, to obtain the corresponding term vector of contract terms information;
The similarity between the term vector of the term vector and contract terms information in matched sentences subvector is calculated, it is raw based on the similarity
At similar word matrix, wherein the element of every a line in the similar word matrix is in same term vector and matched sentences subvector
Term vector between similarity, the element of each column is term vector and the matching of same exceptional clause in the similar word matrix
The similarity between term vector in sentence vector;Maximum similarity in each column element based on the similar word matrix,
The sentence vector is generated, and then obtains the sentence vector of each clause in contract terms information, finally by contract terms information
Contract terms number is generated using the corresponding sentence vector of contract terms information as default sentence vector as default contract terms
According to library.
It should be noted that the method for determination of the sentence vector of the contract terms information and the sentence vector of exceptional clause are true
It is similar to determine mode, is not repeating herein.
The contract evaluation method that the present embodiment proposes by obtaining the contract terms to be evaluated of contract to be evaluated, and determines
Exceptional clause in the contract terms to be evaluated carries out stop words mistake to the exceptional clause then based on default stop words
Filter operation is then based on the exceptional clause information to obtain exceptional clause information, in contract terms database described in determination
The corresponding target contract terms of exceptional clause, and determine based on the target contract terms score information of the exceptional clause,
Then the corresponding contract evaluating template of the contract to be evaluated is obtained, and fills the contract based on the contract terms to be evaluated
Evaluating template is calculated finally according to the score information of the exceptional clause based on the filled contract evaluating template
The score value of the contract to be evaluated is handled contract text by the data processing technique based on matching tree, specific root
The score value of contract to be evaluated is accurately obtained according to contract terms database, and then realizes the overall evaluation to contract to be evaluated, with
The unreasonable clause in contract to be evaluated is excavated, to reduce potential threat caused by contract to be evaluated and loss.
Based on first embodiment, the second embodiment of contract evaluation method of the present invention is proposed, referring to Fig. 3, in the present embodiment
In, step S300 includes:
Step S310, word-based vector model are trained the exceptional clause information, to obtain the exceptional clause
The corresponding term vector of information;
Step S320 determines the corresponding sentence vector of the exceptional clause based on the term vector;
Step S330, based on the default sentence for presetting contract terms in the sentence vector and the contract terms database
Subvector calculates the similarity between the exceptional clause and each default contract terms;
Step S340 is based on the similarity, and the corresponding target of the exceptional clause is determined in contract terms database
Contract terms.
In the present embodiment, when getting exceptional clause information, word-based vector model (Distributed
Representation), exceptional clause information is trained, to obtain the corresponding term vector of exceptional clause information, the word to
Amount is vector corresponding to each word in exceptional clause information.The term vector model mainly use CBOW and SKIP assume into
Row training, it is identifiable that the unrecognized word of computer in the contract terms after adjusting stop words is converted into computer
Vector;For example, being trained using Word2Vec to the contract terms after adjusting stop words, which is for generating word
The neural network model of vector, including CBOW and SKIP two ways.
When getting the corresponding term vector of exceptional clause information, based on term vector determine the corresponding sentence of exceptional clause to
Amount, specifically, the term vector for being based respectively on each clause in exceptional clause determines the corresponding sentence vector of the clause.
Then based on the default sentence vector for presetting contract terms in sentence vector and contract terms database, calculate different
Similarity between normal clause and each default contract terms specifically successively calculates the sentence vector of clause in exceptional clause
With the similarity between each default sentence vector, i.e. cosine value between the sentence vector and each default sentence vector.
When phase knowledge and magnanimity are calculated, it is based on the similarity, determines that exceptional clause is corresponding in contract terms database
Target contract terms.Specifically, it is first determined the corresponding maximum similarity of each exceptional clause, and by each maximum
The corresponding default contract terms of similarity, the target contract terms as the corresponding exceptional clause of the maximum similarity;Alternatively,
Exceptional clause is traversed, for each of exceptional clause clause, successively determines phase corresponding to the exceptional clause currently traversed
Like in degree, if there are the phase knowledge and magnanimity that similarity is greater than preset threshold, and if it exists, then by the similar of the exceptional clause currently traversed
In degree, the corresponding default contract terms of maximum similarity are as target contract terms, if it does not exist, it is determined that is currently traversed is different
Normal clause is without exception, i.e., the exceptional clause currently traversed is available normal contract clause.
Further, in other embodiments, step S330 includes: to pass through Tf-idf based on the exceptional clause information
Algorithm calculates the Tf-idf value between the exceptional clause and each default contract terms;It will be pre- in each Tf-idf value
If the maximum Tf-idf value of quantity, target sentences vector is used as in the default sentence vector of corresponding default contract terms;
Based on the sentence vector and the target sentences vector, the exceptional clause is calculated, it is corresponding with the target sentences vector
Target contract terms between similarity.
In the present embodiment, when getting sentence vector, it is primarily based on exceptional clause information, by Tf-idf algorithm,
The Tf-idf value calculated between the exceptional clause and the default contract terms specifically successively traverses exceptional clause, for
The exceptional clause currently traversed then traverses default contract terms, calculates the exceptional clause letter of the exceptional clause currently traversed
Each word in breath, and the Tf value and idf value between the default contract terms that currently traverse, and calculate the Tf value of each word
With the product of idf value, finally using the mean value of the corresponding Tf value of each word and the product of idf value as the exception currently traversed
Tf-idf value between clause and the default contract terms currently traversed.
Default contract terms, the default contract terms currently traversed are then traversed, and traverse the exception currently traversed
Each word in the clause information of clause calculates the Tf value between the word currently traversed and the default contract terms currently traversed
And idf value, the product of Tf value and idf value is calculated, when each word traversal is completed in clause information, calculates each word pair
The mean value of the product of the Tf value and idf value answered, with the default contract terms for obtaining the exceptional clause currently traversed with currently traversing
Between Tf-idf value.When default contract terms traverse completion, the exceptional clause and each default contract that are currently traversed
Tf-idf value between clause, exceptional clause traverse complete when, obtain each exceptional clause respectively with each default contract item
Tf-idf value between money.
It should be noted that Tf value refers to the frequency that some given word occurs in this document, Tf value is should
Frequency of occurrence of the word in default contract terms, divided by the sum of the frequency of occurrence of all words in default contract terms.Idf value
Specifically: the total quantity of default contract terms takes divided by the number for the default contract terms for including the word, then by obtained quotient
Denary logarithm obtains.
It, will be pre- in each Tf-idf value when getting the Tf-idf value between exceptional clause and the default contract terms
If the maximum Tf-idf value of quantity, target sentences vector is used as in the default sentence vector of corresponding default contract terms,
And it is based on the sentence vector and the target sentences vector, and exceptional clause is calculated, it is corresponding with the target sentences vector
Similarity between target contract terms, and then the similarity calculation number of contract terms to be evaluated can be reduced, it improves similar
Spend the efficiency calculated.
The contract evaluation method that the present embodiment proposes, instructs the exceptional clause information by word-based vector model
Practice, to obtain the corresponding term vector of the exceptional clause information, then determines that the exceptional clause is corresponding based on the term vector
Sentence vector, then based in the sentence vector and the contract terms database preset contract terms default sentence
Vector calculates the similarity between the exceptional clause and each default contract terms, is then based on the similarity,
The corresponding target contract terms of the exceptional clause are determined in contract terms database, can accurately be determined successively according to similarity
Target contract terms corresponding to clause, and then the accuracy evaluated exceptional clause is improved, improve the effect of contract evaluation
Rate and accuracy.
Based on second embodiment, the 3rd embodiment of contract evaluation method of the present invention is proposed, referring to Fig. 4, in the present embodiment
In, step S320 includes:
Step S321 calculates the similarity between the term vector and the term vector in matched sentences subvector, based on described
Similarity generates similar word matrix, wherein the element of every a line in the similar word matrix is same term vector and matched sentences
The similarity between term vector in subvector, in the similar word matrix element of each column be same exceptional clause word to
The similarity between term vector in amount and matched sentences subvector;
Step S322, the maximum similarity in each column element based on the similar word matrix, generate the sentence to
Amount.
In the present embodiment, in the term vector for determining exceptional clause, matched sentences subvector is obtained, wherein the matching sentence
The sentence vector that vector is made of pre-set each word, the element of the matched sentences subvector are each word in vocabulary
Term vector, the matched sentences subvector be M dimensional vector, M be vocabulary length, that is, vocabulary in word quantity, for example, M is
100000, that is, the quantity of word corresponding to the matched sentences subvector, wherein the word in vocabulary is can in contract text
Can occur all words (can for except conjunction, preposition and without the word of legal sense in addition to word).
When getting matched sentences subvector, the phase between the term vector and the term vector in matched sentences subvector is calculated
Like degree, similar word matrix is generated based on the similarity, wherein the element of every a line in the similar word matrix is same word
The similarity between term vector in vector and matched sentences subvector, the element of each column is same different in the similar word matrix
The similarity between term vector in the term vector and matched sentences subvector of normal clause.The similar word matrix is M*N matrix,
In, M is the length of vocabulary, and N is the word quantity in number, that is, exceptional clause information of similar word.Then it is based on similar word matrix
Each column element in maximum similarity, generate the sentence vector
Specifically, exceptional clause can be successively traversed, determines word in the exceptional clause information of the exceptional clause currently traversed
Quantity, the quantity of the word is the columns N in similar word matrix, calculate matched sentences subvector in term vector with current time
Similarity between the corresponding term vector of the exceptional clause gone through generates the similar of the exceptional clause currently traversed based on the similarity
Word matrix, wherein the element of every a line in the similar word matrix is the corresponding all term vectors of exceptional clause currently traversed
In the same term vector and matched sentences subvector in term vector between similarity.In the abnormal item currently traversed
When the similar word matrix of money, it is respectively compared the element of each column in the similar word matrix, with the maximum of each column element of determination
Similarity, and using the maximum similarity of each column as the element of an one-dimensional vector, which as currently traverses different
The sentence vector of normal clause.
The contract evaluation method that the present embodiment proposes, by calculating term vector and the term vector in matched sentences subvector
Between similarity, based on the similarity generate similar word matrix, each column element then based on the similar word matrix
In maximum similarity, generate the sentence vector, the sentence vector of exceptional clause accurately obtained according to similar word matrix, so as to
In can according to sentence vector accurately determine successively clause corresponding to target contract terms, and then improve to exceptional clause carry out
The accuracy of evaluation improves the efficiency and accuracy of contract evaluation.
Based on second embodiment, the fourth embodiment of contract evaluation method of the present invention is proposed, referring to Fig. 5, in the present embodiment
In, step S340 includes:
Step S341 determines the corresponding maximum similarity of the exceptional clause based on the similarity;
Step S342, it is corresponding as the maximum similarity by the corresponding default contract terms of the maximum similarity
The target contract terms of exceptional clause.
In the present embodiment, when obtaining the similarity between exceptional clause and the default contract terms, to similarity
It is compared, the corresponding maximum similarity of the exceptional clause is determined based on similarity, and maximum similarity is corresponding default
Contract terms, the target contract terms as the corresponding exceptional clause of the maximum similarity;If the exceptional clause be it is a plurality of,
Exceptional clause is successively traversed, determines the corresponding maximum similarity of exceptional clause currently traversed, and the maximum similarity is corresponding
Target contract terms of the default contract terms as the exceptional clause currently traversed.
It in other embodiments, can be first successively true for each of exceptional clause clause by traversing exceptional clause
In similarity corresponding to the exceptional clause traversed before settled, if there are the phase knowledge and magnanimity that similarity is greater than preset threshold, if depositing
Then by the similarity of the exceptional clause currently traversed, the corresponding default contract terms of maximum similarity are as target contract
Clause, if it does not exist, it is determined that the exceptional clause currently traversed is without exception, i.e., the exceptional clause currently traversed is available normal
Contract terms.
The contract evaluation method that the present embodiment proposes, by determining that each exceptional clause is corresponding based on the similarity
Maximum similarity, it is corresponding as the maximum similarity by the corresponding default contract terms of each maximum similarity
The target contract terms of exceptional clause can accurately determine the corresponding target contract terms of exceptional clause according to maximum similarity,
Further increase the accuracy of contract evaluation.
Based on first embodiment, the 5th embodiment of contract evaluation method of the present invention is proposed, referring to Fig. 6, in the present embodiment
In, step S100 includes:
Step S110 carries out text cutting to the contract to be evaluated, to obtain the contract terms of the contract to be evaluated;
Step S120 carries out cleaning operation to the contract terms of the contract to be evaluated, removes in the contract terms
Clause is repeated, to obtain the contract terms to be evaluated;
Step S130, based on the clause theme of the contract terms to be evaluated, by agent model to contract item to be evaluated
Money is traversed, with the exceptional clause in the determination contract terms to be evaluated.
In the present embodiment, when receiving contract to be evaluated, contract evaluation platform carries out text to the contract to be evaluated
The contract terms of contract to be evaluated to obtain the contract terms to be evaluated of the contract to be evaluated, are then carried out cleaning behaviour by cutting
Make, the repetition clause in contract terms is removed, to obtain contract terms to be evaluated, wherein if the contract to be evaluated is picture lattice
The contract dataset of formula then first carries out OCR to contract dataset and identifies to obtain contract text, then carries out text cutting, for example, using
Existing text cutting algorithm carries out text cutting, to ensure that the data after cutting are a complete contract terms, for example,
It include a fullstop in data after cutting.
When getting contract terms to be evaluated, the clause theme of contract terms to be evaluated is obtained, it is logical based on clause theme
It crosses agent model to traverse contract terms to be evaluated, with the exceptional clause in the determination contract terms to be evaluated.Specifically
Ground, if the clause theme of a certain contract terms to be evaluated is consistent with the clause theme in agent model, the contract item to be evaluated
Money is exceptional clause.
The contract evaluation method that the present embodiment proposes, by carrying out text cutting to the contract to be evaluated, to obtain
The contract terms of contract to be evaluated are stated, cleaning operation then is carried out to the contract terms of the contract to be evaluated, removes the conjunction
Clause with the repetition clause in clause, to obtain the contract terms to be evaluated, then based on the contract terms to be evaluated
Theme traverses contract terms to be evaluated by agent model, with the abnormal item in the determination contract terms to be evaluated
Money can accurately determine its exceptional clause according to contract to be evaluated, improve the screening efficiency of exceptional clause, further improve
The efficiency and accuracy rate of contract evaluation.
Based on first embodiment, the sixth embodiment of contract evaluation method of the present invention is proposed, referring to Fig. 7, in the present embodiment
In, step S400 includes:
Step S410 obtains the contract main body of the contract to be evaluated;
Step S420 determines contract evaluating template based on the contract main body and the contract terms to be evaluated.
In the present embodiment, the contract main body for obtaining contract to be evaluated is determined based on the contract main body and exceptional clause
Contract evaluating template, specifically, can first based on contract main body determines target contract evaluating template, in target contract evaluating template packet
When including multiple, according to contract terms to be evaluated, exceptional clause and the corresponding rule of exceptional clause, in target contract evaluating template
The contract evaluating template of middle selection definitive application, for example, including whole contract terms to be evaluated in target contract evaluating template
Clause theme.
The contract evaluation method that the present embodiment proposes, by the contract main body for obtaining the contract to be evaluated;Then it is based on
The contract main body and the contract terms to be evaluated determine contract evaluating template, can accurately determine contract evaluating template,
And then improve the efficiency of contract evaluation.
Based on the above embodiment, the 7th embodiment for proposing contract evaluation method of the present invention, referring to Fig. 8, in the present embodiment
In, step S500 includes:
Step S510 determines the contract to be evaluated based on the contract evaluating template and the contract terms to be evaluated
Missing clause;
Step S520 is based on the filled contract evaluating template according to institute's scoring information and the missing clause
The score value is calculated;
Step S530 is based on the exceptional clause information, determines that the exceptional clause is corresponding by decision-tree model and disobeys
Advise information;
Step S540 generates the evaluation letter of the contract to be evaluated based on the violation information and institute's scoring information
Breath, and the evaluation information and missing clause are sent to the corresponding terminal of the contract to be evaluated.
In the present embodiment, contract evaluating template includes necessary contract terms that the contract of the theme is included and optional
Contract terms, when getting contract evaluating template, according to clause corresponding to the necessary contract terms of the contract evaluating template
Theme and the clause theme of contract terms to be evaluated determine the missing clause of contract to be evaluated, if contract terms to be evaluated
It include clause theme corresponding to all necessary contract terms in clause theme, then there is no missing items for the contract to be evaluated
Money, otherwise, in the clause theme of the contract terms to be evaluated it is not to be covered necessity contract terms corresponding to clause theme, be scarce
The clause theme of clause is lost, and then determines the missing clause of contract to be evaluated.Then, according to score information and missing clause base
The score value is calculated in the filled contract evaluating template.
It should be noted that in other embodiments, contract terms database also may include the sentence of normal contract clause
The information such as vector.The score information processing mode that exceptional clause can be used obtains normal contract clause in contract terms to be evaluated
The score information of (can be with contract terms), so according to the score information of normal contract clause, the score information of exceptional clause, lack
Clause is lost, the score value, specific calculation and aforesaid way are calculated based on the filled contract evaluating template
It is similar, it is not repeating herein.
Based on the exceptional clause information, the corresponding violation information of the exceptional clause is determined by decision-tree model, and
Generate the evaluation information of the contract to be evaluated based on violation information and institute's scoring information, and send the evaluation information with
And missing clause, to the corresponding terminal of the contract to be evaluated, which can show the evaluation information and missing clause, so that
User understands potential risk present in the contract to be evaluated in time, avoids causing damages for user.
Specifically, for exceptional clause, in order to enhance the solution to model property released, rule is taken to combine the decision tree mould of decision tree
Type, in decision-tree model, can be obtained by training it is some about contract is available and not available path, according to not available road
Diameter, which determines, determines not available rule.Specifically, the decision node in decision-tree model is the contract terms after adjusting cleaning
Each word, the decision-tree model include leaf node and non-leaf nodes (including root node), and non-leaf nodes is each
Rule of judgment corresponding to a word (whether be specifically as follows includes the word), leaf node is conclusion, which includes should
Contract terms not available rule corresponding when available or unavailable and unavailable;In decision-tree model, for each
Exceptional clause, by the exceptional clause for exceptional clause information in word traverse decision-tree model, obtain each conjunction
With contract corresponding to clause is available or not available path, the non-leaf nodes in the available path or not available path is
Rule of judgment corresponding to each of exceptional clause information word is not available path in the path for obtaining exceptional clause
When, using rule corresponding to the leaf node in the not available path as the rule of the contract terms, for example, not available rule
It is then the contract because violating xxxx, xxxx, leads to xxxx risk, final system determines that contract is unavailable, the not available rule
As violation information.
Further, the score value of contract to be evaluated and evaluation information can also be audited, and auditing result is anti-
It feeds user (transmitting terminal of contract to be evaluated), wherein when contract to be evaluated is unavailable, which includes above-mentioned judgement
Not available rule.
In addition, for auditing result (including the score value after contract audit to be evaluated and the evaluation information after audit, each
The score value of a contract terms and corresponding evaluation information), contract of novation clause database, using evaluation data as training data
It is trained, and carries out model iteration, make model accuracy rate and accuracy can be by continuous iteration.
The contract evaluation method that the present embodiment proposes, by being based on the contract evaluating template and the target contract item
Money determines the missing clause of the contract to be evaluated, after being based on filling then according to institute's scoring information and the missing clause
The contract evaluating template score value is calculated, then be based on the exceptional clause information, pass through decision-tree model
Determine the corresponding violation information of the exceptional clause, be then based on the violation information and institute's scoring information generate it is described to
The evaluation information of evaluation contract, and send the evaluation information and missing clause to the corresponding terminal of the contract to be evaluated,
The evaluation result of contract to be evaluated can be fed back to terminal for user's access, so that user understands the contract to be evaluated in time
Potential risk, avoid causing damages for user.
It is the functional block diagram of one embodiment of contract evaluation platform of the present invention referring to Fig. 9, Fig. 9.
In the present embodiment, contract evaluation platform includes:
Module 10 is obtained, for obtaining the contract terms to be evaluated of contract to be evaluated, and determines the contract item to be evaluated
Exceptional clause in money;
Filtering module 20, for carrying out stop words filter operation to the exceptional clause based on default stop words, to obtain
Exceptional clause information;
Determining module 30, for determining the corresponding target contract terms of the exceptional clause in contract terms database,
And the score information of the exceptional clause is determined based on the target contract terms;
Module 40 is filled, for obtaining the corresponding contract evaluating template of the contract to be evaluated, and based on described to be evaluated
Contract terms fill the contract evaluating template;
Computing module 50 evaluates mould based on the filled contract for the score information according to the exceptional clause
The score value of the contract to be evaluated is calculated in plate.
It should be noted that each embodiment of contract evaluation platform and each embodiment of said contract evaluation method are basic
Identical, in this not go into detail.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with contract assessment process, conjunction as described in any one of above-mentioned is realized when the contract assessment process is executed by processor
The step of with evaluation method.
Each embodiment base of computer readable storage medium specific embodiment of the present invention and the above order drainage processing method
This is identical, and in this not go into detail.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of contract evaluation method, which is characterized in that the contract evaluation method the following steps are included:
The contract terms to be evaluated of contract to be evaluated are obtained, and determine the exceptional clause in the contract terms to be evaluated;
Based on default stop words, stop words filter operation is carried out to the exceptional clause, to obtain exceptional clause information;
Based on the exceptional clause information, the corresponding target contract item of the exceptional clause is determined in contract terms database
Money, and determine based on the target contract terms score information of the exceptional clause;
The corresponding contract evaluating template of the contract to be evaluated is obtained, and fills the contract based on the contract terms to be evaluated
Evaluating template;
According to the score information of the exceptional clause, it is calculated based on the filled contract evaluating template described to be evaluated
The score value of contract.
2. contract evaluation method as described in claim 1, which is characterized in that it is based on the exceptional clause information, it is described to close
With the determination exceptional clause in clause database, the step of corresponding target contract terms, includes:
Word-based vector model is trained the exceptional clause information, with obtain the corresponding word of the exceptional clause information to
Amount;
The corresponding sentence vector of the exceptional clause is determined based on the term vector;
Based on the default sentence vector for presetting contract terms in the sentence vector and the contract terms database, institute is calculated
State the similarity between exceptional clause and each default contract terms;
Based on the similarity, the corresponding target contract terms of the exceptional clause are determined in contract terms database.
3. contract evaluation method as claimed in claim 2, which is characterized in that described to determine the exception based on the term vector
The step of clause corresponding sentence vector includes:
The similarity between the term vector and the term vector in matched sentences subvector is calculated, is generated based on the similarity similar
Word matrix, wherein the element of every a line in the similar word matrix be word in same term vector and matched sentences subvector to
Similarity between amount, in the similar word matrix element of each column be same exceptional clause term vector with match sentence to
The similarity between term vector in amount;
Maximum similarity in each column element based on the similar word matrix generates the sentence vector.
4. contract evaluation method as claimed in claim 2, which is characterized in that it is described to be based on the similarity, in contract terms
The step of corresponding target contract terms of the exceptional clause are determined in database include:
The corresponding maximum similarity of the exceptional clause is determined based on the similarity;
Target by the corresponding default contract terms of the maximum similarity, as the corresponding exceptional clause of the maximum similarity
Contract terms.
5. contract evaluation method as described in claim 1, which is characterized in that the contract to be evaluated for obtaining contract to be evaluated
Clause, and the step of determining the exceptional clause in the contract terms to be evaluated includes:
Text cutting is carried out to the contract to be evaluated, to obtain the contract terms of the contract to be evaluated;
Cleaning operation is carried out to the contract terms of the contract to be evaluated, the repetition clause in the contract terms is removed, to obtain
Obtain the contract terms to be evaluated;
Based on the clause theme of the contract terms to be evaluated, contract terms to be evaluated are traversed by agent model, with
Determine the exceptional clause in the contract terms to be evaluated.
6. contract evaluation method as described in claim 1, which is characterized in that described to obtain the corresponding conjunction of the contract to be evaluated
Include: with the step of evaluating template
Obtain the contract main body of the contract to be evaluated;
Contract evaluating template is determined based on the contract main body and the contract terms to be evaluated.
7. such as contract evaluation method as claimed in any one of claims 1 to 6, which is characterized in that described according to the exceptional clause
Score information, the step of score value of the contract to be evaluated is calculated based on the filled contract evaluating template packet
It includes:
The missing clause of the contract to be evaluated is determined based on the contract evaluating template and the contract terms to be evaluated;
According to institute's scoring information and the missing clause be based on the filled contract evaluating template be calculated it is described
Score value;
Based on the exceptional clause information, the corresponding violation information of the exceptional clause is determined by decision-tree model;
The evaluation information of the contract to be evaluated is generated based on the violation information and institute's scoring information, and is commented described in transmission
Valence information and missing clause are to the corresponding terminal of the contract to be evaluated.
8. a kind of contract evaluation platform, which is characterized in that the contract evaluation platform includes:
Module is obtained, for obtaining the contract terms to be evaluated of contract to be evaluated, and is determined in the contract terms to be evaluated
Exceptional clause;
Filtering module, for stop words filter operation being carried out to the exceptional clause, to obtain abnormal item based on default stop words
Money information;
Determining module for determining the corresponding target contract terms of the exceptional clause in contract terms database, and is based on
The target contract terms determine the score information of the exceptional clause;
Module is filled, for obtaining the corresponding contract evaluating template of the contract to be evaluated, and is based on the contract item to be evaluated
Money fills the contract evaluating template;
Computing module is calculated for the score information according to the exceptional clause based on the filled contract evaluating template
Obtain the score value of the contract to be evaluated.
9. a kind of contract valuator device, which is characterized in that the contract valuator device includes: memory, processor and is stored in
On the memory and the contract assessment process that can run on the processor, the contract assessment process is by the processor
The step of contract evaluation method as described in any one of claims 1 to 7 is realized when execution.
10. a kind of computer readable storage medium, which is characterized in that be stored with contract on the computer readable storage medium and comment
Valence program realizes the contract evaluation as described in any one of claims 1 to 7 when the contract assessment process is executed by processor
The step of method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910205782.5A CN110070264A (en) | 2019-03-16 | 2019-03-16 | Contract evaluation method, platform, equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910205782.5A CN110070264A (en) | 2019-03-16 | 2019-03-16 | Contract evaluation method, platform, equipment and readable storage medium storing program for executing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110070264A true CN110070264A (en) | 2019-07-30 |
Family
ID=67365325
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910205782.5A Pending CN110070264A (en) | 2019-03-16 | 2019-03-16 | Contract evaluation method, platform, equipment and readable storage medium storing program for executing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110070264A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111046934A (en) * | 2019-12-04 | 2020-04-21 | 中国建设银行股份有限公司 | Method and device for identifying soft clauses of SWIFT message |
CN112949273A (en) * | 2021-03-04 | 2021-06-11 | 长沙市到家悠享网络科技有限公司 | Electronic contract signing method and device, electronic equipment and computer readable medium |
Citations (5)
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 |
CN106844544A (en) * | 2016-12-30 | 2017-06-13 | 全民互联科技(天津)有限公司 | A kind of contract terms Risk Identification Method and system |
CN108399482A (en) * | 2018-01-17 | 2018-08-14 | 阿里巴巴集团控股有限公司 | Appraisal procedure, device and the electronic equipment of contract |
CN108830443A (en) * | 2018-04-19 | 2018-11-16 | 出门问问信息科技有限公司 | A kind of contract review method and device |
CN109447105A (en) * | 2018-09-10 | 2019-03-08 | 平安科技(深圳)有限公司 | Contract audit method, apparatus, computer equipment and storage medium |
-
2019
- 2019-03-16 CN CN201910205782.5A patent/CN110070264A/en active Pending
Patent Citations (5)
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 |
CN106844544A (en) * | 2016-12-30 | 2017-06-13 | 全民互联科技(天津)有限公司 | A kind of contract terms Risk Identification Method and system |
CN108399482A (en) * | 2018-01-17 | 2018-08-14 | 阿里巴巴集团控股有限公司 | Appraisal procedure, device and the electronic equipment of contract |
CN108830443A (en) * | 2018-04-19 | 2018-11-16 | 出门问问信息科技有限公司 | A kind of contract review method and device |
CN109447105A (en) * | 2018-09-10 | 2019-03-08 | 平安科技(深圳)有限公司 | Contract audit method, apparatus, computer equipment and storage medium |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111046934A (en) * | 2019-12-04 | 2020-04-21 | 中国建设银行股份有限公司 | Method and device for identifying soft clauses of SWIFT message |
CN111046934B (en) * | 2019-12-04 | 2024-04-09 | 中国建设银行股份有限公司 | SWIFT message soft clause recognition method and device |
CN112949273A (en) * | 2021-03-04 | 2021-06-11 | 长沙市到家悠享网络科技有限公司 | Electronic contract signing method and device, electronic equipment and computer readable medium |
CN112949273B (en) * | 2021-03-04 | 2024-04-26 | 长沙市到家悠享网络科技有限公司 | Electronic contract signing method, device, electronic equipment and computer readable medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022141861A1 (en) | Emotion classification method and apparatus, electronic device, and storage medium | |
CN103679462B (en) | A kind of comment data treating method and apparatus, a kind of searching method and system | |
US9245252B2 (en) | Method and system for determining on-line influence in social media | |
CN109783632A (en) | Customer service information-pushing method, device, computer equipment and storage medium | |
JP6506439B1 (en) | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM | |
CN108280104A (en) | The characteristics information extraction method and device of target object | |
CN110096681A (en) | Contract terms analysis method, device, equipment and readable storage medium storing program for executing | |
CN109299258A (en) | A kind of public sentiment event detecting method, device and equipment | |
CN107704512A (en) | Financial product based on social data recommends method, electronic installation and medium | |
CN108694647A (en) | A kind of method for digging and device of trade company's rationale for the recommendation, electronic equipment | |
CN103440242A (en) | User search behavior-based personalized recommendation method and system | |
WO2014107441A2 (en) | Social media impact assessment | |
CN110134845A (en) | Project public sentiment monitoring method, device, computer equipment and storage medium | |
CN107368521B (en) | Knowledge recommendation method and system based on big data and deep learning | |
CN107688870A (en) | A kind of the classification factor visual analysis method and device of the deep neural network based on text flow input | |
CN108734327A (en) | A kind of data processing method, device and server | |
CN108572988A (en) | A kind of house property assessment data creation method and device | |
CN111221881B (en) | User characteristic data synthesis method and device and electronic equipment | |
CN110070264A (en) | Contract evaluation method, platform, equipment and readable storage medium storing program for executing | |
CN115392237A (en) | Emotion analysis model training method, device, equipment and storage medium | |
CN107464019A (en) | A kind of financial events method for early warning | |
CN110083809A (en) | Contract terms similarity calculating method, device, equipment and readable storage medium storing program for executing | |
Gerlich et al. | Artificial intelligence as toolset for analysis of public opinion and social interaction in marketing: identification of micro and nano influencers | |
CN104572613A (en) | Data processing device, data processing method and program | |
CN112163098A (en) | Knowledge graph creating method and device, storage medium and server |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190730 |
|
WD01 | Invention patent application deemed withdrawn after publication |