CN110084105A - Contract documents analysis method, device, computer equipment and storage medium - Google Patents
Contract documents analysis method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110084105A CN110084105A CN201910199015.8A CN201910199015A CN110084105A CN 110084105 A CN110084105 A CN 110084105A CN 201910199015 A CN201910199015 A CN 201910199015A CN 110084105 A CN110084105 A CN 110084105A
- Authority
- CN
- China
- Prior art keywords
- contract
- contract documents
- documents
- dispute
- factor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or 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
- G06V30/40—Document-oriented image-based pattern recognition
Abstract
The embodiment of the invention discloses a kind of contract documents analysis method, device, computer equipment and storage mediums, comprising: obtains the document text of contract documents to be identified；According to preset conversion regime by the document text conversion be array；The array is input in preset text analyzing model；The contract factor of the text analyzing model output is read, and the contract factor is shown according to preset displaying rule.Due to, neural network model with purpose training can accurately extract the key content of contract documents, therefore, most important content in contract documents can be shown to user, avoid user when reading contract documents due to experience deficiency, key content can not be drawn from contract documents, lead to understand contract documents not thorough enough caused error understanding.
Description
Technical field
The present embodiments relate to file process field, especially a kind of contract documents analysis method, device, computer are set
Standby and storage medium.
Background technique
Treaty review is exactly that regulation and the agreement of party audit the particulars of a contract, format as agreed.It wants
How whether examination contract set up or true, how to come into force, whether perhaps come into force has feelings inefficacious undetermined or invalid
How whether shape, contractual right obligation terminate or terminate, which type of contract corresponding contract engagement or clause can generate
Which type of civil contractual relation is consequence can generate, which type of administrative contract relationship, which type of criminal contractual relation.
Expectation with us has much distances.Treaty review have it is very strong professional, it is therefore desirable to have the talent of professional knowledge can
It is answered.
In the prior art, most of users for not knowing about contract knowledge, when facing panoramic contract documents, by
In, contract documents content can not be correctly interpreted, and cause itself lawful right to be unable to get guarantee, or consuming can only be passed through
Manpower and financial resources seeks that there is the personage of relevant knowledge deposit to seek advice from.Therefore, in the prior art, the interpretation of treaty review according to
It is old to need one kind for partially facilitate the people for enjoying professional person and teaching by the professional person with relevant knowledge
The more means of popularization interpret contract documents.
Summary of the invention
The embodiment of the present invention provides a kind of key content by identification contract documents, passes through brief and concise displaying
The key content of contract documents reaches contract documents analysis method, the device, calculating for quickly and accurately parsing contract documents purpose
Machine equipment and storage medium.
In order to solve the above technical problems, the technical solution that the embodiment of the invention uses is: providing a kind of conjunction
With file analysis method, comprising:
Obtain the document text of contract documents to be identified；
According to preset conversion regime by the document text conversion be array；
The array is input in preset text analyzing model, wherein the text analyzing model is preparatory
Training to convergence state is used to carry out text information the neural network model of contract factor extraction, and the contract factor is expression contract
The key message of file content purport；
The contract factor of the text analyzing model output is read, and according to preset displaying rule to the contract factor
It is shown.
Optionally, the contract factor for reading the text analyzing model output, and it is right according to preset displaying rule
After the contract factor is shown, further includes:
According to preset search rule by the contract factor section Content Transformation be retrieval type；
It is retrieved, is searched and the contract documents in preset legal precedent database using the retrieval type as search condition
Example file with the identical agreement origin of an incident includes the dispute origin of an incident in the example file wherein.
Optionally, when the example file is multiple, described using the retrieval type is search condition in preset legal precedent
It is retrieved, is searched after there is the identical example file for arranging the origin of an incident with the contract documents in database, further includes:
Multiple example files are counted using the dispute origin of an incident as qualifications；
According to statistical result calculate each dispute classification shared by percentage；
The dissension risk of the contract documents is predicted according to percentage shared by each dispute classification.
Optionally, the percentage according to shared by each dispute classification carries out the dissension risk of the contract documents pre-
After survey, further includes:
Obtain the contract factor that the dispute origin of an incident is characterized in the example file；
It is retrieved in the contract documents using the contract factor as search condition, obtains and made in the contract documents
The restriction clause of the about described dispute origin of an incident；
Restriction clause progress differentiation is shown.
Optionally, described to be retrieved in the contract documents using the contract factor as search condition, described in acquisition
Before the restriction clause for restricting the dispute origin of an incident in contract documents, further includes:
It is retrieved in the contract documents using the contract factor as search condition, to judge in the contract documents
Whether there is the restriction clause for restricting the dispute origin of an incident；
When not having the restriction clause for restricting the dispute origin of an incident in the contract documents, preset first warning is extracted
Information is simultaneously shown；Otherwise, then confirm and obtain the restriction clause；Wherein, first information warning is for prompting user
There are legal risks in contract documents.
Optionally, described to be retrieved in the contract documents using the contract factor as search condition, to judge
It states in contract documents after whether there is the restriction clause for restricting the dispute origin of an incident, further includes:
When not having the restriction clause for restricting the dispute origin of an incident in the contract documents, in preset policy database
Middle retrieval has the supplementary provision of mapping relations with the contract factor, wherein includes the supplement item in the supplementary provision
Writing position of the money in the contract documents；
The supplementary provision is written into the contract documents according to said write position, and confirms the supplementary provision
For the restriction clause of the dispute origin of an incident.
Optionally, before the document text for obtaining contract documents to be identified, further includes:
Obtain the document picture of the contract documents；
The document picture is converted into document text according to preset picture and text conversion regime.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of contract documents analytical equipment, comprising:
Module is obtained, for obtaining the document text of contract documents to be identified；
Conversion module is used to according to preset conversion regime be array by the document text conversion；
Processing module, for the array to be input in preset text analyzing model, wherein the text point
Analyse model be in advance training to convergence state be used for text information carry out the extraction of the contract factor neural network model, contract because
Son is the key message of expression contract documents content purport；
Execution module, for reading the contract factor of the text analyzing model output, and according to preset displaying rule
The contract factor is shown.
Optionally, the contract documents analytical equipment further include:
First transform subblock, for being retrieved the contract factor section Content Transformation according to preset search rule
Formula；
First processing submodule, for being examined in preset legal precedent database using the retrieval type as search condition
Rope searches the example file for having the identical agreement origin of an incident with the contract documents wherein, includes dispute thing in the example file
By.
Optionally, when the example file is multiple, the contract documents analytical equipment further include:
First statistic submodule, for being counted using the dispute origin of an incident as qualifications to multiple example files；
First computational submodule, for according to statistical result calculate each dispute classification shared by percentage；
First implementation sub-module, for the percentage according to shared by each dispute classification to the dispute wind of the contract documents
It is predicted danger.
Optionally, the contract documents analytical equipment further include:
First acquisition submodule, for obtaining the contract factor for characterizing the dispute origin of an incident in the example file；
Second processing submodule, for being retrieved in the contract documents using the contract factor as search condition,
Obtain the restriction clause that the dispute origin of an incident is restricted in the contract documents；
First display sub-module, for showing restriction clause progress differentiation.
Optionally, the contract documents analytical equipment further include:
First searches submodule, for being retrieved in the contract documents using the contract factor as search condition,
To judge whether there is the restriction clause for restricting the dispute origin of an incident in the contract documents；
Second implementation sub-module, for when the restriction clause for not having the restriction dispute origin of an incident in the contract documents
When, it extracts preset first information warning and is shown；Otherwise, then confirm and obtain the restriction clause；Wherein, described first
There are legal risks for prompting in user's contract documents for information warning.
Optionally, the contract documents analytical equipment further include:
Second searches submodule, for when the restriction clause for not having the restriction dispute origin of an incident in the contract documents
When, the supplementary provision that there are mapping relations with the contract factor is retrieved in preset policy database, wherein the supplement
It include writing position of the supplementary provision in the contract documents in clause；
Third implementation sub-module, for the supplementary provision to be written to the contract documents according to said write position
In, and confirm that the supplementary provision is the restriction clause of the dispute origin of an incident.
Optionally, the contract documents analytical equipment further include:
Second acquisition submodule, for obtaining the document picture of the contract documents；
Third handles submodule, for the document picture to be converted to document text according to preset picture and text conversion regime
This.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of computer equipment, including memory and processing
Device is stored with computer-readable instruction in the memory, when the computer-readable instruction is executed by the processor, so that
The processor executes the step of contract documents analysis method described above.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of storage Jie for being stored with computer-readable instruction
Matter, when the computer-readable instruction is executed by one or more processors, so that one or more processors execute above-mentioned institute
The step of stating contract documents analysis method.
The beneficial effect of the embodiment of the present invention is: by by the document text conversion of contract documents be can be by neural network
The array of model identification, then by training to convergent neural network model to contract documents can be characterized in array
The data of key content carry out classification extraction, form the contract factor of contract documents, finally, the contract factor is carried out editor's exhibition
Show.Due to, the neural network model with purpose training can accurately extract the key content of contract documents, therefore,
Most important content in contract documents can be shown to user, avoid user when reading contract documents due to experience deficiency, it cannot
It is enough that key content is drawn from contract documents, lead to understand contract documents not thorough enough caused error understanding.Meanwhile by
In the extraction of key point content is equivalent to the outline for foring contract documents before user reads contract documents, enables users to
Enough purport contents for more accurately understanding contract documents, achieving the effect that duplicate to teach in professional understands.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the basic procedure schematic diagram of contract documents of embodiment of the present invention analysis method；
Fig. 2 is the flow diagram that the embodiment of the present invention retrieves same type example file by the contract factor；
Fig. 3 is the flow diagram that the embodiment of the present invention is predicted by result of the example file to contract documents；
Fig. 4 is the stream that the embodiment of the present invention searches corresponding restriction clause in contract documents by the contract factor of the dispute origin of an incident
Journey schematic diagram；
Fig. 5 is that there are the flow diagrams of legal risk for warning of embodiment of the present invention user's contract documents；
Fig. 6 is the flow diagram that completion of the embodiment of the present invention restricts clause；
Fig. 7 is the flow diagram that the embodiment of the present invention converts contract documents format；
Fig. 8 is contract documents of embodiment of the present invention analytical equipment basic structure schematic diagram；
Fig. 9 is computer equipment of embodiment of the present invention basic structure block diagram.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.
In some processes of the description in description and claims of this specification and above-mentioned attached drawing, contain according to
Multiple operations that particular order occurs, but it should be clearly understood that these operations can not be what appears in this article suitable according to its
Sequence is executed or is executed parallel, and serial number of operation such as 101,102 etc. is only used for distinguishing each different operation, serial number
It itself does not represent and any executes sequence.In addition, these processes may include more or fewer operations, and these operations can
To execute or execute parallel in order.It should be noted that the description such as " first " herein, " second ", is for distinguishing not
Same message, equipment, module etc., does not represent sequencing, does not also limit " first " and " second " and be different type.
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those skilled in the art's every other implementation obtained without creative efforts
Example, shall fall within the protection scope of the present invention.
Those skilled in the art of the present technique are appreciated that " terminal " used herein above, " terminal device " both include wireless communication
The equipment of number receiver, only has the equipment of the wireless signal receiver of non-emissive ability, and including receiving and emitting hardware
Equipment, have on bidirectional communication link, can execute two-way communication reception and emit hardware equipment.This equipment
It may include: honeycomb or other communication equipments, shown with single line display or multi-line display or without multi-line
The honeycomb of device or other communication equipments；PCS (Personal Communications Service, PCS Personal Communications System), can
With combine voice, data processing, fax and/or communication ability；PDA (Personal Digital Assistant, it is personal
Digital assistants), it may include radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, day
It goes through and/or GPS (Global Positioning System, global positioning system) receiver；Conventional laptop and/or palm
Type computer or other equipment, have and/or the conventional laptop including radio frequency receiver and/or palmtop computer or its
His equipment." terminal " used herein above, " terminal device " can be it is portable, can transport, be mounted on the vehicles (aviation,
Sea-freight and/or land) in, or be suitable for and/or be configured in local runtime, and/or with distribution form, operate in the earth
And/or any other position operation in space." terminal " used herein above, " terminal device " can also be communication terminal, on
Network termination, music/video playback terminal, such as can be PDA, MID (Mobile Internet Device, mobile Internet
Equipment) and/or mobile phone with music/video playing function, it is also possible to the equipment such as smart television, set-top box.
It is the basic procedure schematic diagram of the present embodiment contract documents analysis method referring specifically to Fig. 1, Fig. 1.
As shown in Figure 1, a kind of contract documents analysis method, comprising:
S1100, the document text for obtaining contract documents to be identified；
The both sides of contract documents cooperation or number side reach to ensure respective legitimate rights and interests through both sides or number side's joint consultation
After consensus, the written material of signing.Contract is one kind of title document.After contract documents generate or upload, obtain
Take the document text for recording contract documents content, wherein document text is the editable text envelope for recording contract documents content
Breath.
In some embodiments, when contract documents are with picture format, by image processing techniques, such as OCR, will scheme
Piece format is converted into editable font format, and the font after conversion is then replicated in generation document text in ineffective law, rule, etc. sheet.
S1200, according to preset conversion regime by the document text conversion be array；
After having read contract documents, contract documents are converted into array by matlab software application.Its
In, each word or word of contract documents are constituted, an element for replacing with array, and the row of element are mapped
Column order is consistent with the arrangement order of contract documents.
S1300, the array is input in preset text analyzing model, wherein the text analyzing model
To train to convergence state the neural network model for being used to carry out text information the extraction of the contract factor in advance, the contract factor is table
Up to the key message of contract documents content purport；
In present embodiment, the keyword in contract documents is extracted by text resolution model, text resolution mould
Type is preparatory training to convergence state, for carrying out the neural network model of contract factor extraction, the contract factor to text information
For the key message that can express contract documents content of text purport, for example, the title of contract documents, contract documents party are double
Responsibility and obligation, the raising strong seedlings of promise breaking and the delay for inviting item, the execution date of contract, contracting parties of side, contract
Late Payment Fee fulfiled etc. information.But the keyword message of extraction is not limited to this, not according to the content of different contract documents
Together, the contract factor for needing to extract is also different, removes except some common contract factors, according to different types of contract
File extracts the different contract factors.
The array obtained after conversion is entered into preset text resolution model.Wherein, text resolution model is pre-
It first trains to convergence state and is used for the neural network model that emotion information characterized to data is analyzed.Text resolution model energy
Enough is the trained convolutional neural networks model (CNN) to convergence state, and still, not limited to this, text resolution model is also
Can be: the deformation of deep neural network model (DNN), Recognition with Recurrent Neural Network model (RNN) or above-mentioned three kinds of network models
Model.
Initial neural network model as text resolution model is converted in training by collecting a large amount of contract documents
Array afterwards is as training sample, by manually after the original text this document for having read training sample to each training sample
Demarcated that (calibration refers to the contract factor that the artificial contract factor in contract documents is extracted, and will manually be extracted
It is stored in xml format, and establishes the arborescence of the contract documents contract factor by the hierarchical relationship between content).Then
Training sample is input in initial neural network model, and obtain model output classification results (classification results are model
The contract factor of obtained training sample), and the classification results and calibration knot are calculated by the loss function of neural network model
The distance between fruit (such as: Euclidean distance, mahalanobis distance or COS distance etc.), by calculated result and the distance threshold of setting into
Row compares, and passes through verifying if calculated result is less than or equal to distance threshold, continues the training of next training sample, if meter
It calculates result and then calculates difference between the two by loss function greater than distance threshold, and nerve net is corrected by backpropagation
Weight in network model, can be improved neural network model can accurately express contract documents key content in training sample
The weight of the corresponding element of word increases the accuracy rate of extraction and comprehensive with this.By circulation execution above scheme and largely
Training sample training after, the accuracy rate that the obtained neural network model of training extracts the contract factor to array is greater than certain
Numerical value, for example, 97%, then to convergence state, then training to convergent neural network is for neural network model training
Text resolution model.
Text analyzing category of model layer is arranged to the title of each contract factor, such as: the title of contract documents, contract
Right and duty, claim for breaking an agreement, Late Payment Fee payment etc. in party, contract documents in file.Based on contract each in file
Confidence level between the content of a part and above-mentioned classification selects classification of the highest classification of confidence level as corresponding word segment
As a result, the contract factor corresponding with classification is extracted, and such as: the corresponding contract factor of the title of contract documents are as follows: labour contract,
Loan agreement or investment control etc..
The text resolution model of training to convergence state can accurately extract the contract factor of array characterization.
S1400, the contract factor for reading the text analyzing model output, and according to preset displaying rule to the conjunction
It is shown with the factor.
After the contract factor for having read the output of text analyzing model, the contract factor is shown, display can use
Attributed graph shown, such as: loan agreement --- credit amount --- guaranty information.In the same way, by contract
Different contents is sorted out in a manner of arborescence to " loan agreement " under one's name in file, completes to show.
But the displaying rule of the contract factor is not limited to this, according to the difference of concrete application scene, in some embodiment party
In formula, the contract factor can be shown by way of list or chart.
In some embodiments, it after obtaining the contract factor of contract documents, can based on contract the factor carry out together
Class retrieval, and search the identical origin of an incident but the different case that concludes of the dispute origin of an incident, reference is provided for user, is provided more for user
Specific case, auxiliary user to the helping system and the dispute origin of an incident of contract documents carry out deeper into understanding.
Above embodiment, by being the number that can be identified by neural network model by the document text conversion of contract documents
Group matrix, then by training to convergent neural network model to the number that can characterize contract documents key content in array
According to classification extraction is carried out, the contract factor of contract documents is formed, finally, the contract factor is carried out editor's displaying.Due to having mesh
The neural network model of property training can accurately extract the key contents of contract documents and therefore can be shown to user
Most important content in contract documents avoids user when reading contract documents due to experience deficiency, can not be from contract documents
Key content is drawn, leads to understand contract documents not thorough enough caused error understanding.Simultaneously as key point content
It extracts, is equivalent to the outline for foring contract documents before user reads contract documents, allows users to more accurately manage
The purport content for solving contract documents, achieving the effect that duplicate to teach in professional understands.
In some embodiments, after obtaining the contract factor of contract documents, by the part in the contract factor
Hold and search the example file same or similar with the contract documents origin of an incident, so that user learns to understand contract documents from other cases
Content.Referring to Fig. 2, Fig. 2 is the flow diagram that the present embodiment retrieves same type example file by the contract factor.
As shown in Fig. 2, after S1400, further includes:
S1411, according to preset search rule by the contract factor section Content Transformation be retrieval type；
In present embodiment, the contract factor to be used is needed when being retrieved are as follows: the contract of the characterization contract documents origin of an incident
The factor.For example, with without mortgage carry out debt-credit high interest loan contract, the contract factor scanned for are as follows: loan contract and without
Mortgage is greater than 20% without and Annual Percentage Rate.But the contract factor for participating in retrieval is not limited to this, not according to concrete application scene
Together, in some embodiments, the contract factor for participating in retrieval can also be: the method for performance arranged in contract documents and fulfil
Time limit.For example, with without mortgage carry out debt-credit high interest loan contract, the contract factor scanned for are as follows: loan contract and without
Mortgage is greater than 20%and installment reimbursement and equal principal without and Annual Percentage Rate.The contract factor in present embodiment, being capable of basis
The difference of treaty content and change, variation key concept are as follows: as far as possible extraction contract documents in can restore signing close
The contract factor indicated with file party's true intention.
S1412, it is retrieved, is searched and the conjunction in preset legal precedent database using the retrieval type as search condition
There is the identical example file for arranging the origin of an incident wherein with file, include the dispute origin of an incident in the example file.
The retrieval type that the said contract factor forms is retrieved in preset legal precedent database.Wherein, legal precedent data
The example file for occurring contract dispute dispute in history is included in library, includes entangling for example contract documents appearance in example file
The confused origin of an incident, for example, in the cargo transaction example file of signing, due to not arranging specifically date of delivery, Party B is receiving
Slowly it is reluctant to deliver the target of contract engagement after goods arrival payment；In the cargo transaction example file of signing, due to not arranging specific
Liquidated Damages, contract parties Party A break a contract after, be penalty the amount of money occur dispute；In agency agreement, due to not about
Determine the venue of solution to disputes, whether contracting parties have jurisdiction generation after generating dispute, to the mechanism for solving dispute
Dispute etc., in contract performance or termination, contracting parties in the agreement in the contract documents signed perhaps
Person since contract documents are not write exactly, caused by contract dispute, be the example file dispute origin of an incident to be recorded.
In legal precedent database, in every example file warehousing, the contract factor conduct in the example file is extracted
Label is stored.When being retrieved with the contract factor of current contract documents, identical contract documents can be obtained.From previous
Contract documents execute the problem of in user is educated, provide corresponding reference information for user.
In some embodiments, when example file be multiple and example file include dispute thing by when, by multiple
The result of example file is counted, and in conjunction with the dispute origin of an incident that current contract documents are stated, is entangled to current contract documents
The confused origin of an incident is predicted.Referring to Fig. 3, Fig. 3 is what the present embodiment was predicted by result of the example file to contract documents
Flow diagram.
After S1412 as shown in Figure 3 further include:
S1421, multiple example files are counted using the dispute origin of an incident as qualifications；
When example file is multiple, carried out with the contract factor qualifications that each example file characterizes its dispute origin of an incident
Statistics, because, the multiple example files the retrieved cooperation origin of an incident having the same, still, due between different parties
Dispute during contract execution is different, therefore, using the dispute origin of an incident as qualifications, can count for such conjunction
With the main trial thinking of file.
S1422, according to statistical result calculate each dispute classification shared by percentage；
According to statistics to each dispute classification middle example file quantity, then calculate each dispute classification total
The obtained example file quantity of retrieval in accounting.For example, to be carried out without mortgage in the loan contract of debt-credit high interest, search
Obtained same type example file is 10, wherein has the dispute origin of an incident of 3 example files are as follows: loan interest is higher than state's domestic discipline and family rules
Determine normal, caused refund people, which refunds, to break a contract；There is the dispute origin of an incident of 7 example files are as follows: due to, do not arrange refund penalty,
The promise breaking amount of money becomes the dispute origin of an incident after refund people promise breaking.Then the percentage of interest dispute is 30%, the dispute class of penalty dispute
It Wei 70%.But the division of dispute classification is not limited to this, according to the difference of concrete application scene, implements in some selectivity
Example in, dispute classification can be (being not limited to): loco dispute, the unqualified dispute of hand over of goods quality, operation installation dispute,
Freight dispute or amount for which loss settled dispute etc..
S1423, the percentage according to shared by each dispute classification predict the dissension risk of the contract documents.
It is predicted according to the dispute origin of an incident of the percentage shared by each dispute classification to contract documents.For example, for example, with
In the loan contract for carrying out debt-credit high interest without mortgage, the same type example file searched for is 10, wherein has 3 to show
The dispute origin of an incident of example text part are as follows: loan interest is higher than national regulation normal, and caused refund people, which refunds, to break a contract；There are 7 example texts
The dispute origin of an incident of part are as follows: due to not arranging refund penalty, the promise breaking amount of money becomes the dispute origin of an incident after refund people promise breaking.Then interest
The percentage of dispute is 30%, and the dispute classification of penalty dispute is 70%.It is determined by retrieval, it is just not upper in contract documents
Item setting attribution of liability clause and specific solution are stated, therefore, predicts that the possibility of interest dispute occur in the contract documents
Property be 30%, predict the contract documents occur a possibility that penalty dispute be 70%.
Current contract documents are predicted by example file, family is able to use and compares contract documents and history same type
It whether there is gap between dispute contract, and then go into seriously the reason of there are gaps, it is further to deepen user for contract text
The understanding of part.
In some embodiments, when in example file search cause corresponding dispute event the reason of the contract factor,
For the possibility for preventing such dispute from occurring in contract documents, retrieved in contract documents with the contract factor, with determination
Whether have in contract documents and restricts the restriction clause that such dispute occurs.Referring to Fig. 4, Fig. 4 is in the present embodiment by entangling
The contract factor of the confused origin of an incident searches the corresponding flow diagram for restricting clause in contract documents.
As shown in figure 4, after S1423, further includes:
S1431, the contract factor that the dispute origin of an incident is characterized in the example file is obtained；
The dispute item occurred in the corresponding contract of the example file is recorded in example file, for this before storage
Dispute item carries out the refinement of the contract factor, for example, not arranging specific carrier in cargo transaction contract, contract works as thing
People just carries undertaking for expense and dispute occurs, then when the example file enters database, extract the dispute be by contract because
Sub " carrier ", " freight charges " or " carrier ".Likewise, for other storage example file according to its dispute origin of an incident, mention
Take the corresponding contract factor.
S1432, it is retrieved in the contract documents using the contract factor as search condition, obtains the contract text
The restriction clause of the dispute origin of an incident is restricted in part；
Using the contract factor for characterizing the dispute origin of an incident in example file as search condition, examined in current contract documents
Rope, after retrieving the corresponding contract factor, according to sentence meaning understand the place clause with the identical contract factor is understood,
Confirm whether the clause is the clause for clearly arranging dispute item responsibility, if so, confirming the clause to restrict clause.Sentence meaning reason
The party of the dispute item whether characterized with the processing contract factor in solution i.e. confirmation clause.For example, being to close with " carrier "
When being retrieved with the factor, the clause sentence retrieved is " the riding artificial Party B of this cargo ", extracts contract in sentence
The factor and party's synonym just can determine that for whether the dispute origin of an incident has specific person liable.In another example the dispute origin of an incident
The contract factor is penalty, retrieves to obtain clause to be that " either party violations of both sides lead to this by the penalty
What contract engagement item can not continue to fulfil, delinquent party also needs payment contract total value 30% in addition to the loss for compensating observant party
Penalty ".By being retrieved to obtain the restriction clause of penalty payment with " penalty ".
S1433, restriction clause progress differentiation is shown.
After the restriction clause that retrieval obtains the promise breaking origin of an incident, shown to clause progress differentiation is restricted.When differentiation is shown,
The regular font parameter of contract documents where restricting clause is obtained first, then according to the regular font parameter, to restriction clause
Text carry out differentiation show, differentiation show including but not limited to modification font color, increase font, font is added
Underscore or mark of emphasis is then arranged in bulk processing below font, and the text for restricting clause is made to close on text in the environment with it
Word generates difference, restricts clause in order to which user quickly positions.
It is that the corresponding system of the example file dispute origin of an incident is not found in contract documents by retrieval in embodiment some
After about clause then shows that there are loopholes for the contract documents, and the loophole may result in contract documents signature, in implementation procedure
It is middle dispute item identical with example file occur.Therefore, it is necessary to prompt user, there are such risks.Referring to Fig. 5, Fig. 5 is
The present embodiment warns user's contract documents, and there are the flow diagrams of legal risk.
As shown in figure 5, before S1432 further include:
S1441, it is retrieved in the contract documents using the contract factor as search condition, to judge the contract
Whether there is the restriction clause for restricting the dispute origin of an incident in file；
Using the contract factor for characterizing the dispute origin of an incident in example file as search condition, examined in current contract documents
Rope, if retrieval is less than the corresponding contract factor or the similar contract factor, it is determined that lack of checks on power example in the contract documents
The restriction clause of file dispute item.After retrieving the corresponding contract factor, according to sentence meaning understand to identical contract because
The place clause of son is understood confirm whether the clause is the clause for clearly arranging dispute item responsibility, if so, confirmation should
Clause is to restrict clause, if not then confirming the restriction clause of lack of checks on power example file dispute item in the contract documents.
S1442, when not having the restriction clause for restricting the dispute origin of an incident in the contract documents, extract preset the
One information warning is simultaneously shown；Otherwise, then confirm and obtain the restriction clause；Wherein, first information warning is for mentioning
Show that there are legal risks in user's contract documents.
When determining the restriction clause for not having in contract documents and restricting the dispute origin of an incident, then preset first warning letter is called
Breath is shown, to warn to user.There are legal risks for prompting in user's contract documents for first information warning.?
User is prompted in some embodiments, in the first information warning, and there are which kind of legal risks.For example, not arranging to have in contract documents
When fulfiling the time of body, prompt is not " due to arranging specifically to fulfil due date, it is understood that there may be delay to hand in the first information warning
The risk paid ".
When not retrieving corresponding restriction clause, indicating risk is carried out to user, Contract Risk can be effectively reduced
A possibility that dispute occurs guarantees user benefit.
In some embodiments, it carries out to further aid user to contract documents perfect, is determining contract documents
In when not having the restriction clause for restricting the example file dispute origin of an incident, it is literary that corresponding restrictions clause is added by contract by retrieval
In part, to reduce the legal risk of contract documents, meanwhile, it is capable to provide professional contract completion function for user, make user
Without spending time and efforts evading in thing in Contract Risk, the completion efficiency of contract documents is improved.Referring to Fig. 6,
Fig. 6 is the flow diagram that the present embodiment completion restricts clause.
As shown in fig. 6, after S1442, further includes:
S1451, when not having the restriction clause for restricting the dispute origin of an incident in the contract documents, in preset strategy
The supplementary provision that there are mapping relations with the contract factor is retrieved in database, wherein include described in the supplementary provision
Writing position of the supplementary provision in the contract documents；
When determining the restriction clause for not having in contract documents and restricting the dispute origin of an incident, then characterization example file dispute is called
The contract factor of the origin of an incident retrieves the supplementary provision for having mapping relations with the contract factor in preset policy database.Wherein,
Supplementary provision is the restriction clause for restricting the sign example file dispute origin of an incident.
The corresponding restriction clause of the various dispute origins of an incident is recorded in present embodiment, in policy database, for example, record restricts
The clause of the penalty dispute origin of an incident is the supplementary provision for writing penalty calculation exactly；Record restricts the jurisdiction dispute origin of an incident
Clause is the supplementary provision for writing dispute prosecution ground exactly；The clause that record restricts goods return and replacement dispute is to write goods return and replacement prerequisite exactly
Supplementary provision etc..
Before supplementary provision is in Access strategy database, the dispute thing of the corresponding restriction of the supplementary provision is expressly recited
, and the label by the contract factor of the dispute item, as corresponding supplementary provision.
In policy database while recording supplementary provision, also record the supplementary provision with the write-in in contract documents
Position.For example, the clause that record restricts the penalty dispute origin of an incident is the supplementary provision for writing penalty calculation exactly, the supplement
The writing position of clause is the title lower section of " liability for breach of contract " in contract terms；Record restricts the clause of the jurisdiction dispute origin of an incident
To write the supplementary provision on dispute prosecution ground exactly, the writing position of the supplementary provision is the title of " solution to disputes " in contract terms
Lower section；The clause that record restricts goods return and replacement dispute is the supplementary provision for writing goods return and replacement prerequisite exactly, the write-in of the supplementary provision
Position is the title lower section of " after-sale service " in contract terms etc..
S1452, the supplementary provision is written into the contract documents according to said write position, and confirms the benefit
Fill the restriction clause that clause is the dispute origin of an incident.
After calling corresponding supplementary provision in policy database, by supplementary provision according to the writing position of setting, write-in
Into contract documents, and confirm that the supplementary provision is the restriction clause of the dispute origin of an incident.The supplementary provision is carried out simultaneously differential
It has been shown that, allows the user to the Fast Reading supplementary provision, is also able to use family quickly according to the demand of specific contract, to benefit
Clause is filled to be modified.
In some embodiments, it when contract documents are picture format, needs contract documents being converted to writing text.
Referring to Fig. 7, Fig. 7 is the flow diagram that the present embodiment converts contract documents format.
As shown in fig. 7, before S1100 further include:
S1011, the document picture for obtaining the contract documents；
The both sides of contract documents cooperation or number side reach to ensure respective legitimate rights and interests through both sides or number side's joint consultation
After consensus, the written material of signing.After contract documents generate paper piece, the contract documents scanning that user uploads is obtained
Or the document picture of shooting stroke.
S1012, the document picture is converted to by document text according to preset picture and text conversion regime.
When contract documents are with picture format, by preset picture and text conversion regime, such as OCR or it is trained for font
The neural network model of identification converts editable font format for picture format, is then replicated in the font after conversion
Document text is generated in ineffective law, rule, etc. sheet.
In order to solve the above technical problems, the embodiment of the present invention also provides a kind of contract documents analytical equipment.
It is the present embodiment contract documents analytical equipment basic structure schematic diagram referring specifically to Fig. 8, Fig. 8.
As shown in figure 8, a kind of contract documents analytical equipment, comprising: obtain module 2100, conversion module 2200, processing mould
Block 2300 and execution module 2400.Wherein, the document text that module 2100 is used to obtain contract documents to be identified is obtained；Conversion
Module 2200 is used to according to preset conversion regime be array by document text conversion；Processing module 2300 is used for array
Input matrix is into preset text analyzing model, wherein text analyzing model is that training in advance to convergence state is used for text
This information carries out the neural network model of contract factor extraction, and the contract factor is the crucial letter for expressing contract documents content purport
Breath；Execution module 2400 is used to read the contract factor of text analyzing model output, and according to preset displaying rule to contract
The factor is shown.
Contract documents analytical equipment is by being that can be identified by neural network model by the document text conversion of contract documents
Array, then by training to convergent neural network model to contract documents key content can be characterized in array
Data carry out classification extraction, the contract factor of contract documents is formed, finally, the contract factor is carried out editor's displaying.Due to tool
The neural network model of purposive training can accurately extract the key content of contract documents, therefore, can be to user
It shows most important content in contract documents, avoids user when reading contract documents due to experience deficiency, it can not be from contract text
Key content is drawn in part, leads to understand contract documents not thorough enough caused error understanding.Simultaneously as in key point
The extraction of appearance is equivalent to the outline that contract documents are formd before user reads contract documents, and it is more accurate to allow users to
The purport content for understanding contract documents, achieving the effect that duplicate to teach in professional understands.
In some embodiments, contract documents analytical equipment further include: the first transform subblock and the first processing submodule.
Wherein, the first transform subblock is used to according to preset search rule be retrieval type by contract factor section Content Transformation；First
Processing submodule is searched and is had with contract documents for being retrieved in preset legal precedent database using retrieval type as search condition
There is the identical example file for arranging the origin of an incident wherein, includes the dispute origin of an incident in example file.
In some embodiments, when example file is multiple, contract documents analytical equipment further include: the first statistics submodule
Block, the first computational submodule and the first implementation sub-module.Wherein, the first statistic submodule is used for using the dispute origin of an incident as qualifications
Multiple example files are counted；First computational submodule be used for according to statistical result calculate each dispute classification shared by hundred
Divide ratio；First implementation sub-module carries out pre- for dissension risk of the percentage according to shared by each dispute classification to contract documents
It surveys.
In some embodiments, contract documents analytical equipment further include: the first acquisition submodule, second processing submodule and
First display sub-module.Wherein, the first acquisition submodule is used to obtain the contract factor that the dispute origin of an incident is characterized in example file；The
Two processing submodules are obtained to restrict in contract documents and be entangled for being retrieved in contract documents using the contract factor as search condition
The restriction clause of the confused origin of an incident；First display sub-module is shown for that will restrict clause progress differentiation.
In some embodiments, contract documents analytical equipment further include: first searches submodule and the second implementation sub-module.
Wherein, the first lookup submodule using the contract factor as search condition in contract documents for being retrieved, to judge contract text
Whether there is the restriction clause for restricting the dispute origin of an incident in part；Second implementation sub-module, which is used to work as in contract documents not having to restrict, to be entangled
When the restriction clause of the confused origin of an incident, extracts preset first information warning and be shown；Otherwise, then confirm that acquisition restricts clause；
Wherein, there are legal risks for prompting in user's contract documents for the first information warning.
In some embodiments, contract documents analytical equipment further include: second searches submodule and third implementation sub-module.
Wherein, the second lookup submodule is used for when not having the restriction clause for restricting the dispute origin of an incident in contract documents, in preset plan
Retrieval has the supplementary provision of mapping relations with the contract factor slightly in database, wherein includes that supplementary provision exists in supplementary provision
Writing position in contract documents；Third implementation sub-module is for supplementary provision to be written to contract documents according to writing position
In, and confirm that supplementary provision is the restriction clause of the dispute origin of an incident.
In some embodiments, contract documents analytical equipment further include: the second acquisition submodule and third handle submodule.
Wherein, the second acquisition submodule is used to obtain the document picture of contract documents；Third handles submodule and is used for according to preset figure
Document picture is converted to document text by literary conversion regime.
In order to solve the above technical problems, the embodiment of the present invention also provides computer equipment.It is this referring specifically to Fig. 9, Fig. 9
Embodiment computer equipment basic structure block diagram.
As shown in figure 9, the schematic diagram of internal structure of computer equipment.The computer equipment includes being connected by system bus
Processor, non-volatile memory medium, memory and network interface.Wherein, the non-volatile memories of the computer equipment are situated between
Matter is stored with operating system, database and computer-readable instruction, can be stored with control information sequence in database, the computer
When readable instruction is executed by processor, processor may make to realize a kind of contract documents analysis method.The place of the computer equipment
Device is managed for providing calculating and control ability, supports the operation of entire computer equipment.It can in the memory of the computer equipment
It is stored with computer-readable instruction, when which is executed by processor, processor may make to execute a kind of contract
File analysis method.The network interface of the computer equipment is used for and terminal connection communication.It will be understood by those skilled in the art that
Structure shown in Fig. 9, only the block diagram of part-structure relevant to application scheme, is not constituted to application scheme institute
The restriction for the computer equipment being applied thereon, specific computer equipment may include than more or fewer portions as shown in the figure
Part perhaps combines certain components or with different component layouts.
Processor is for executing acquisition module 2100, conversion module 2200, processing module 2300 in Fig. 8 in present embodiment
With the concrete function of execution module 2400, program code and Various types of data needed for memory is stored with the above-mentioned module of execution.Net
Network interface is used for the data transmission between user terminal or server.Memory in present embodiment is stored with facial image
Program code needed for executing all submodules in critical point detection device and data, server are capable of the program of invoking server
Code and data execute the function of all submodules.
Computer equipment is by being the array that can be identified by neural network model by the document text conversion of contract documents
Matrix, then by training to convergent neural network model to the data that can characterize contract documents key content in array
Classification extraction is carried out, the contract factor of contract documents is formed, finally, the contract factor is carried out editor's displaying.Due to having purpose
Property training neural network model can accurately extract the key contents of contract documents, therefore, can show and close to user
With content most important in file, user is avoided, due to experience deficiency, can not to draw from contract documents when reading contract documents
Key content is taken, leads to understand contract documents not thorough enough caused error understanding.Simultaneously as key point content mentions
It takes, is equivalent to the outline for foring contract documents before user reads contract documents, allows users to more accurately understand
The purport content of contract documents, achieving the effect that duplicate to teach in professional understands.
The present invention also provides a kind of storage medium for being stored with computer-readable instruction, computer-readable instruction by one or
When multiple processors execute, so that one or more processors execute the step of any of the above-described embodiment contract documents analysis method
Suddenly.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, which can be stored in a computer-readable storage and be situated between
In matter, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium above-mentioned can be
The non-volatile memory mediums such as magnetic disk, CD, read-only memory (Read-Only Memory, ROM) or random storage note
Recall body (Random Access Memory, RAM) etc..
It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other
At least part of the sub-step or stage of step or other steps executes in turn or alternately.
Claims (10)
1. a kind of contract documents analysis method characterized by comprising
Obtain the document text of contract documents to be identified；
According to preset conversion regime by the document text conversion be array；
The array is input in preset text analyzing model, wherein the text analyzing model is training in advance
It is used to carry out text information the neural network model of contract factor extraction to convergence state, the contract factor is expression contract documents
The key message of content purport；
The contract factor of the text analyzing model output is read, and the contract factor is carried out according to preset displaying rule
Display.
2. contract documents analysis method according to claim 1, which is characterized in that described to read the text analyzing model
The contract factor of output, and after being shown according to preset displaying rule to the contract factor, further includes:
According to preset search rule by the contract factor section Content Transformation be retrieval type；
It is retrieved in preset legal precedent database using the retrieval type as search condition, lookup has with the contract documents
The example file of the identical agreement origin of an incident, wherein include the dispute origin of an incident in the example file.
3. contract documents analysis method according to claim 2, which is characterized in that when the example file is multiple,
Described to be retrieved in preset legal precedent database using the retrieval type as search condition, lookup has with the contract documents
After the example file of the identical agreement origin of an incident, further includes:
Multiple example files are counted using the dispute origin of an incident as qualifications；
According to statistical result calculate each dispute classification shared by percentage；
The dissension risk of the contract documents is predicted according to percentage shared by each dispute classification.
4. contract documents analysis method according to claim 3, which is characterized in that described according to shared by each dispute classification
Percentage the dissension risk of the contract documents is predicted after, further includes:
Obtain the contract factor that the dispute origin of an incident is characterized in the example file；
It is retrieved in the contract documents using the contract factor as search condition, obtains and restrict institute in the contract documents
State the restriction clause of the dispute origin of an incident；
Restriction clause progress differentiation is shown.
5. contract documents analysis method according to claim 4, which is characterized in that it is described with the contract factor be retrieval
Condition is retrieved in the contract documents, obtain restricted in the contract documents dispute origin of an incident restriction clause it
Before, further includes:
Retrieved in the contract documents using the contract factor as search condition, with judge in the contract documents whether
With the restriction clause for restricting the dispute origin of an incident；
When not having the restriction clause for restricting the dispute origin of an incident in the contract documents, preset first information warning is extracted
And it is shown；Otherwise, then confirm and obtain the restriction clause；Wherein, first information warning is for prompting user's contract
There are legal risks in file.
6. contract documents analysis method according to claim 5, which is characterized in that it is described with the contract factor be retrieval
Condition is retrieved in the contract documents, to judge whether there is the system for restricting the dispute origin of an incident in the contract documents
About after clause, further includes:
When not having the restriction clause for restricting the dispute origin of an incident in the contract documents, examined in preset policy database
Rope and the contract factor have the supplementary provision of mapping relations, wherein include that the supplementary provision exists in the supplementary provision
Writing position in the contract documents；
The supplementary provision is written into the contract documents according to said write position, and confirms that the supplementary provision is institute
State the restriction clause of the dispute origin of an incident.
7. contract documents analysis method according to claim 1, which is characterized in that described to obtain contract documents to be identified
Document text before, further includes:
Obtain the document picture of the contract documents；
The document picture is converted into document text according to preset picture and text conversion regime.
8. a kind of contract documents analytical equipment characterized by comprising
Module is obtained, for obtaining the document text of contract documents to be identified；
Conversion module is used to according to preset conversion regime be array by the document text conversion；
Processing module, for the array to be input in preset text analyzing model, wherein the text analyzing mould
Type is the neural network model that training in advance to convergence state is used to carry out text information the extraction of the contract factor, and the contract factor is
Express the key message of contract documents content purport；
Execution module, for reading the contract factor of the text analyzing model output, and according to preset displaying rule to institute
The contract factor of stating is shown.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor, so that the processor executes such as any one of claims 1 to 7 right
It is required that the step of contract documents analysis method.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors execute the contract documents point as described in any one of claims 1 to 7 claim
The step of analysis method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910199015.8A CN110084105A (en) | 2019-03-15 | 2019-03-15 | Contract documents analysis method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910199015.8A CN110084105A (en) | 2019-03-15 | 2019-03-15 | Contract documents analysis method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084105A true CN110084105A (en) | 2019-08-02 |
Family
ID=67412541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910199015.8A Pending CN110084105A (en) | 2019-03-15 | 2019-03-15 | Contract documents analysis method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084105A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110610348A (en) * | 2019-08-14 | 2019-12-24 | 深圳壹账通智能科技有限公司 | Contract expiration reminding method and device, computer equipment and storage medium |
| CN110706094A (en) * | 2019-09-26 | 2020-01-17 | 深圳前海微众银行股份有限公司 | Picture identification processing method, device and equipment and computer storage medium |
| 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 |
-
2019
- 2019-03-15 CN CN201910199015.8A patent/CN110084105A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110610348A (en) * | 2019-08-14 | 2019-12-24 | 深圳壹账通智能科技有限公司 | Contract expiration reminding method and device, computer equipment and storage medium |
| CN110706094A (en) * | 2019-09-26 | 2020-01-17 | 深圳前海微众银行股份有限公司 | Picture identification processing method, device and equipment and computer storage medium |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110069609B (en) | Referee document analysis method, referee document analysis device, computer equipment and storage medium | |
| Sun et al. | Embracing textual data analytics in auditing with deep learning. | |
| CN110084105A (en) | Contract documents analysis method, device, computer equipment and storage medium | |
| Schlogl et al. | Constructing the ‘Future of Work’: An analysis of the policy discourse | |
| CN111507097B (en) | Title text processing method and device, electronic equipment and storage medium | |
| Kuzminykh et al. | Information security risk assessment | |
| CN109902285A (en) | Corpus classification method, device, computer equipment and storage medium | |
| CN107657056A (en) | Method and apparatus based on artificial intelligence displaying comment information | |
| US20170293986A1 (en) | Lawsuit winning possibility evaluation device and method | |
| CN110968730B (en) | Audio mark processing method, device, computer equipment and storage medium | |
| CN111222308A (en) | Case decision book generation method and device and electronic equipment | |
| Li et al. | Development of an intelligent NLP-based audit plan knowledge discovery system | |
| CN113627194B (en) | Information extraction method and device, and communication message classification method and device | |
| CN113868391B (en) | Legal document generation method, device, equipment and medium based on knowledge graph | |
| Heavey et al. | Toward a common language for quality issues in forensic science | |
| Balona | ActuaryGPT: Applications of large language models to insurance and actuarial work | |
| CN110348006A (en) | Generation method, device, computer equipment and its storage medium of problem information | |
| TWI286718B (en) | Knowledge framework system and method for integrating a knowledge management system with an e-learning system | |
| CN115422920A (en) | Referee document dispute focus identification method based on BERT and GAT | |
| CN116980665A (en) | Video processing method, device, computer equipment, medium and product | |
| CN116089644A (en) | Event detection method integrating multi-mode features | |
| Okoye | Mediated representation of Middle Eastern and African migrants in UK and US press in the Wake of Brexit and Trumpism | |
| Chen | Public narratives of the relationship between post-pandemic economic recovery and decarbonization: A case study of Toronto’s media sphere | |
| Sun | Accounting Information Systems outputs: XBRL, AI and in-memory technologies | |
| CN111143688A (en) | Evaluation method and system based on mobile news client |
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 |