CN110490439A - Litigation risk appraisal procedure, device, electronic equipment and computer can storage mediums - Google Patents
Litigation risk appraisal procedure, device, electronic equipment and computer can storage mediums Download PDFInfo
- Publication number
- CN110490439A CN110490439A CN201910717917.6A CN201910717917A CN110490439A CN 110490439 A CN110490439 A CN 110490439A CN 201910717917 A CN201910717917 A CN 201910717917A CN 110490439 A CN110490439 A CN 110490439A
- Authority
- CN
- China
- Prior art keywords
- risk
- text
- case
- training
- assessed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 61
- 238000011156 evaluation Methods 0.000 claims abstract description 41
- 238000012502 risk assessment Methods 0.000 claims abstract description 41
- 238000004590 computer program Methods 0.000 claims description 12
- 230000001052 transient effect Effects 0.000 claims description 9
- 238000013473 artificial intelligence Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010353 genetic engineering Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
- G06Q50/182—Alternative dispute resolution
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Technology Law (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Can storage medium the embodiment of the invention discloses a kind of litigation risk appraisal procedure, device, electronic equipment and computer, comprising: obtain case to be assessed by program elements text and true element text；According to described program element text and the true element text, assessment input quantity is obtained；By the good litigation risk assessment models of the assessment input quantity input pre-training, the case to be assessed is exported by corresponding risk evaluation result；Wherein, the good litigation risk assessment models of the pre-training are obtained based on training sample set training, and it includes multiple assessment input quantities with risk evaluation result label that the training sample, which is concentrated,.By by case to be assessed by being used as input quantity after program elements text and true element text integrated treatment, it is input to litigation risk assessment models output risk evaluation result, and then complete to case to be assessed by risk assessment, due to introducing real-time element in input quantity, so that risk evaluation result is more acurrate, more comprehensively.
Description
Technical field
The present embodiments relate to field of computer technology, and in particular to a kind of litigation risk appraisal procedure, device, electronics
Equipment and computer can storage mediums.
Background technique
Artificial intelligence be by studying, developing, come find for simulate, extend and extend people intelligence theory, method,
One new comprehensive science and technology of technology and application system.It shows as, and computer system is allowed to pass through machine learning etc.
Mode can be fulfiled originally to obtain only by the ability of the competent complicated order task of wisdom ability of our mankind.People
Work is intelligently formally proposed that nineteen fifty, Marvin Lee Minsky has built First in the world in five sixties of last century
Neural computer, this is also seen as a starting point of artificial intelligence.The same year, the referred to as Alan of " father of computer "
Mathison Turin proposes an idea highly visible --- and turing test, this is generally considered natural language processing
The beginning of thought.Since nineteen seventies, the big sophisticated technology in the world three has been collectively referred to as with space technology, energy technology.Into
After 21st century, still persistently studied with genetic engineering, nano science as the big sophisticated technology of 21st century three.
Law artificial intelligence is the subdomains of artificial intelligence, the main application for studying artificial intelligence in legal information, and
Calculating the science of law is core therein.1949, American jurist Luo Wenjie lawyer delivered on " Minnesota law review "
" law tolerance: next advance step " text, proposition measure witness, judge and legislatorial row with statistical method
For.1956, college of law, Yale University professor Alan delivered a kind of " symbolic logic: the sharp keen of file of drafting and interpret laws
Tool ", proposition is drafted and is interpreted laws with symbolic logic mathematics mark.1958, Meier was in United Kingdom National Physical Experiment
" the automation in the law world: from legal information machine processing to method has been delivered in " the thought process mechanization forum " that room is held
Restrain machine " text.1970, Buchanan and Heidrick delivered on " Stamford law review " " about artificial intelligence with
The some pondering of analogy of law " article, it is formal for the first time that " artificial intelligence " is combined into thinking with " analogy of law ", this
Article delivers the prelude opened and carried out artificial intelligence study to analogy of law.
2017, it is named as the law artificial intelligence " machine lawyer " of Case Cruncher Alpha and 100 rules in London
Legal issue of the teacher just " based on hundreds of PPI (payment protection insurance) mis-selling case fact come whether judging claim " is unfolded
Match, as a result " machine lawyer " law AI leads over the 66.3% of lawyer with 86.6% accuracy rate.The Erie of Chicago,U.S
Promise Polytechnics and southern Texas college of law utilize 1791 to 2015 years the US Supreme Court's databases, have developed one cooperatively
Kind algorithm, the algorithm have reproduced 28000 decisions and 240000 throwings of year U.S. Supreme from 1816 to 2015
Ticket, accuracy respectively reach 70.2% and 71.9%.And the criminal that California Santa Cruz big data innovative enterprises Predpol is researched and developed
Guilty forecasting software, can be by the analysis to criminal history data, and where hour one by one is most likely to occur criminal activity if calculating.
In theory, the police only need often go on patrol in these areas that crime, Santa Cruz, Los Angeles can be prevented in advance
Crime rate is all reduced using the city of the software with Atlanta etc..It is bailing out and is paroling in decision, some state courts, the U.S.
" degree of risk " of defendant is determined using algorithm: from this people can again crime a possibility that, can appear in court as scheduled to defendant
Each factor such as possibility, and then decide whether to bail it out or parole.Artificial intelligence starts gradually to be applied to law judge's neck
Domain.
But in the current litigation risk appraisal procedure based on artificial intelligence energy, when obtaining the input of assessment models,
The risk assessment knot that often only considered program elements, therefore accurate litigation risk assessment result can not be obtained, and got
Fruit is not often comprehensive.
Summary of the invention
For this purpose, the embodiment of the present invention, which provides a kind of litigation risk appraisal procedure, device, electronic equipment and computer, to be stored
Medium, to solve the above problem in the prior art.
To achieve the goals above, the embodiment of the present invention provides the following technical solutions:
In a first aspect, the embodiment of the invention provides a kind of litigation risk appraisal procedures, comprising:
Obtain case to be assessed by program elements text and true element text；
According to described program element text and the true element text, assessment input quantity is obtained；
By the good litigation risk assessment models of the assessment input quantity input pre-training, the case to be assessed is exported by corresponding to
Risk evaluation result；Wherein, the good litigation risk assessment models of the pre-training are obtained based on training sample set training,
It includes multiple assessment input quantities with risk evaluation result label that the training sample, which is concentrated,.
Optionally, it is described obtain case to be assessed by program elements text and true element text, specifically include:
The case to be assessed is obtained by corresponding related question collection；The related question collection includes that procedural problem and the fact are asked
Topic；
According to the case to be assessed by party complete the related question collection as a result, obtaining the case to be assessed
By the program elements text and true element text of lower current case.
Optionally, the method also includes:
Building includes the related question database of a variety of related question collection；Wherein, every kind of related question collection corresponds to one kind
Case to be assessed by；Correspondingly,
The case to be assessed is obtained by corresponding related question collection, is specifically included:
Corresponding related question collection is obtained from the related question database.
Optionally, described according to described program element text and the true element text, assessment input quantity is obtained, specifically
Include:
By described program element text and the true element text vector, corresponding first row vector sum is respectively obtained
Second column vector；
The element combinations in element and the second column vector in first column vector are extracted into third column vector to get arriving
The assessment input quantity.
Optionally, training obtains the good litigation risk assessment models of the pre-training in the following manner:
Obtain the training sample set；
The litigation risk assessment models are trained based on the training sample set, until the litigation risk is assessed
The corresponding loss function convergence of model is to get the litigation risk assessment models good to the pre-training.
Optionally, the risk evaluation result includes event risk weight, economic risk weight and evidence Risk rated ratio.
Optionally, further includes:
The risk evaluation result is converted into corresponding risk evaluation result text.
The embodiment of the invention provides a kind of litigation risks to assess device for second aspect, comprising:
First obtains module, for obtain case to be assessed by program elements text and true element text；
Second obtains module, for obtaining assessment input according to described program element text and the true element text
Amount；
Evaluation module, for by the good litigation risk assessment models of the assessment input quantity input pre-training, described in output
Case to be assessed is by corresponding risk evaluation result；Wherein, the good litigation risk assessment models of the pre-training are based on training sample
What this training was got, it includes multiple assessment input quantities with risk evaluation result label that the training sample, which is concentrated,.
The third aspect, the embodiment of the invention provides a kind of computer program product, the computer program product includes
The computer program being stored in non-transient computer readable storage medium, the computer program include program instruction, work as institute
When stating program instruction and being computer-executed, the computer is made to execute litigation risk appraisal procedure described in first aspect.
Fourth aspect, the embodiment of the invention provides a kind of non-transient computer readable storage medium, the non-transient meter
Calculation machine readable storage medium storing program for executing stores computer instruction, and the litigation risk that the computer instruction keeps the computer execution described is commented
Estimate method.
The embodiment of the present invention has the advantages that
By the way that case to be assessed by being used as input quantity after program elements text and true element text integrated treatment, is input to
Litigation risk assessment models export risk evaluation result, and then complete to case to be assessed by litigation risk assess, due to defeated
Enter and introduce real-time element in amount, so that risk evaluation result is more acurrate, more comprehensively.
Detailed description of the invention
It, below will be to embodiment party in order to illustrate more clearly of embodiments of the present invention or technical solution in the prior art
Formula or attached drawing needed to be used in the description of the prior art are briefly described.It should be evident that the accompanying drawings in the following description is only
It is merely exemplary, it for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing amplification of offer obtains other implementation attached drawings.
Structure depicted in this specification, ratio, size etc., only to cooperate the revealed content of specification, for
Those skilled in the art understands and reads, and is not intended to limit the invention enforceable qualifications, therefore does not have technical
Essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the function of the invention that can be generated
Under effect and the purpose that can reach, should all still it fall in the range of disclosed technology contents can cover.
Fig. 1 is a kind of flow diagram of litigation risk appraisal procedure provided in an embodiment of the present invention；
Fig. 2 is the structural block diagram that a kind of litigation risk provided in an embodiment of the present invention assesses device.
Specific embodiment
Embodiments of the present invention are illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book is understood other advantages and efficacy of the present invention easily, it is clear that described embodiment is the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Fig. 1 is a kind of flow diagram of litigation risk appraisal procedure provided in an embodiment of the present invention, as shown in Figure 1, packet
It includes:
S101, obtain case to be assessed by program elements text and true element text；
S102 obtains assessment input quantity according to described program element text and the true element text；
The good litigation risk assessment models of the assessment input quantity input pre-training are exported the case to be assessed by S103
By corresponding risk evaluation result；Wherein, the good litigation risk assessment models of the pre-training are based on training sample set training
It obtains, it includes multiple assessment input quantities with risk evaluation result label that the training sample, which is concentrated,.
Wherein, in step s101, case to be assessed is extracted therein by presenting in the form of text according to relevant laws and regulations
Program elements text and true element text.
In step s 102, since program elements text and true element text cannot assess mould directly as litigation risk
The input of type needs the two is comprehensive for assessment input quantity.
In step s 103, the good litigation risk assessment models of input quantity input pre-training will be assessed, case to be assessed is exported
By corresponding risk evaluation result, litigation risk can intuitively be learnt according to risk evaluation result.
A kind of litigation risk appraisal procedure provided in an embodiment of the present invention, by by case to be assessed by program elements text and
As input quantity is used as after true element text integrated treatment, it is input to litigation risk assessment models output risk evaluation result,
And then complete treat case to be assessed by risk assessment, due to introducing real-time element in input quantity, so that risk assessment knot
Fruit is more acurrate, more comprehensively.
In the above-described embodiments, it is described obtain case to be assessed by program elements text and true element text, it is specific to wrap
It includes:
The case to be assessed is obtained by corresponding related question collection；The related question collection includes that procedural problem and the fact are asked
Topic；
According to the case to be assessed by party complete the related question collection as a result, obtaining the case to be assessed
By the program elements text and true element text of lower current case.
In the above-described embodiments, the method also includes:
Building includes the related question database of a variety of related question collection；Wherein, every kind of related question collection corresponds to one kind
Case to be assessed by；Correspondingly,
The case to be assessed is obtained by corresponding related question collection, is specifically included:
Corresponding related question collection is obtained from the related question database.
Specifically, program elements text and true element text are obtained, can be obtained by way of rhetoric question, that is, pass through pass
Join the problems in problem set, party is to obtain associated answer for inquiry, and then obtains corresponding program elements text and the fact
Element text.
In concrete practice, the construction of problem is by case as unit of, therefore include is this case by lower whole
Case facts, but only comprising the case by a part in lower whole case facts in the case of the party fact, it is therefore desirable to
According to the answer situation of foregoing problems, only with the associated relevant issues of this case, other unrelated problems are rejected for intelligently pushing.
For example, comprising the question and answer about " disability grade " in the complete problem of vehicle traffic accident responsibility dispute, but the problem should
It should be putd question to below the case where there are personnel's disabilities for this case, therefore, which is not required the problem, it should according to this
The case where case intelligence choose whether push.
To solve the problems, such as the intelligently pushing, Question Classification is " default pushes " and " pushing according to condition " two by the present invention
Class defaults basic problem of the problem of pushing for case under and requires to answer regardless of this case fact；And it " is pushed away according to condition
Send " it is front and back problem there are associated Questions types, with the condition for being selected as the push of postposition problem of preposition problem answers, according to
Judgement to the selection answer of preposition problem, system by service condition rule, selection continue which postposition problem pushed.
In the above-described embodiments, described according to described program element text and the true element text, it is defeated to obtain assessment
Enter amount, specifically include:
By described program element text and the true element text vector, corresponding first row vector sum is respectively obtained
Second column vector；
The element combinations in element and the second column vector in first column vector are extracted into third column vector to get arriving
The assessment input quantity.
Specifically, the input of litigation risk assessment models is column vector, is needed program elements text and true element text
This vectorization, it is then comprehensive to obtain input column vector.
In the above-described embodiments, training obtains the good litigation risk assessment models of the pre-training in the following manner:
Obtain the training sample set；
The litigation risk assessment models are trained based on the training sample set, until the litigation risk is assessed
The corresponding loss function convergence of model is to get the litigation risk assessment models good to the pre-training.
In the above-described embodiments, the risk evaluation result includes event risk weight, economic risk weight and evidence wind
Dangerous weight.
Specifically, risk evaluation result be obtain user's question and answer whole case information on the basis of, by the time,
The analysis of the rule of economy, evidence etc., it is comprehensive to release assessment result.Event risk, economic risk and evidence risk are said respectively
It is bright as follows:
1, event risk
Event risk includes two parts, statute of limitation risk and lawsuit period risk.Wherein statute of limitation risk is interior
Holding presentation need to be by carrying out rule process to the related temporal information in user's question and answer, and the statute of limitation by obtaining this case originates
Time obtains the deadline of statute of limitation by calculating in conjunction with the case by the configuration in lower statute of limitation time limit, prompts party
It is prosecuted in deadline Qian Qu law court.
The embodiment of the present invention obtains relevant issues and each case that each case is calculated by middle statute of limitation by the way of configuration
By statute of limitation deadline information, the dispute of vehicle traffic accident responsibility, service for infrastructure contract dispute, finance can be completed at present
Loan contract dispute, credit card dispute, personalized lending dispute, divorce dispute, labour remuneration is entangled, house-leasing contract entangles for recourse
Confusingly, property dispute, the commercial house presell contract dispute, merchandise building contract after abatement of nuisance dispute, Return of Original dispute, divorce
The multiple types cases such as dispute, decorations contract dispute by configuration.
2, economic risk
Economic risk includes legitimation fee and attorney fee two parts.The calculating of expense is by sentencing question and answer data
It is disconnected, the complete target volume of case is obtained to carry out, and wherein the calculating of attorney fee then passes through setting lawyer due to being related to regional difference
Take the mode of related question, obtains regional information.By to each department difference attorney fee charge situation collection, summarize, arrange,
Attorney fee calculating information is established into bottom computation rule by way of configuring, in target total value, the regional information for obtaining case
Afterwards by operation rule, the last attorney fee amount of money is calculated.
3, evidence risk
The core of civil case is that the identification of evidentiary fact, lack of evidence are to lead to the maximum risk of lawsuit failure.The people
The evidence composition of thing case be by case by and the fact based on, evidence that every case is related in is different, and same a case
Under, the different facts can also correspond to different evidences.The present invention is by analysis case by lower factual evidence, the construction fact and evidence
That is problem and evidence is associated with, and by obtaining the true element information in answering a question, offering question obtains the evidence of party
Grasp situation.The evidence of this case fact correlation is supplied to user's selection in a manner of option, the evidence in option is all to prove
True indispensable evidence.By analyzing the selection situation of user, user is obtained currently without the evidence of grasp, and just such
Risk existing for missing evidence and related collect suggest pushing to user.
In the above-described embodiments, the method also includes:
The risk evaluation result is converted into corresponding risk evaluation result text.
Specifically, it since the object that result of the present invention is applicable in is the public, must also be able to jerky risk
Assessment result is converted to the understandable popular language of the public, i.e., the risk evaluation result is converted to corresponding risk assessment
Resulting text.
Fig. 2 is the structural block diagram that a kind of litigation risk provided in an embodiment of the present invention assesses device, as shown in Figure 2, comprising:
First, which obtains module 201, second, obtains module 202 and evaluation module 203.Wherein:
First acquisition module 201 be used to obtain case to be assessed by program elements text and true element text；
Second, which obtains module 202, is used to that it is defeated to obtain assessment according to described program element text and the true element text
Enter amount；
Evaluation module 203 is used for the litigation risk assessment models that the assessment input quantity input pre-training is good, exports institute
Case to be assessed is stated by corresponding risk evaluation result；Wherein, the good litigation risk assessment models of the pre-training are based on training
Sample set training obtains, and it includes multiple assessment input quantities with risk evaluation result label that the training sample, which is concentrated,.
The embodiment of the invention provides a kind of litigation risks to assess device, by by case to be assessed by program elements text and
It is used as input quantity after true element text integrated treatment, is input to litigation risk assessment models output risk evaluation result, in turn
Complete treat case to be assessed by risk assessment, due to introducing real-time element in input quantity, so that risk evaluation result is more
Accurately, more comprehensively.
The embodiment of the present invention discloses a kind of computer program product, and the computer program product is non-transient including being stored in
Computer program on computer readable storage medium, the computer program include program instruction, when described program instructs quilt
When computer executes, computer is able to carry out method provided by above-mentioned each method embodiment, for example, obtains case to be assessed
By program elements text and true element text；According to described program element text and the true element text, acquisition is commented
Estimate input quantity；By the good litigation risk assessment models of the assessment input quantity input pre-training, the case to be assessed is exported by right
The risk evaluation result answered；Wherein, the good litigation risk assessment models of the pre-training are obtained based on training sample set training
, it includes multiple assessment input quantities with risk evaluation result label that the training sample, which is concentrated,.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage
Medium storing computer instruction, the computer instruction make the computer execute side provided by above-mentioned each method embodiment
Method, for example, obtain case to be assessed by program elements text and true element text；According to described program element text and
The fact element text, obtains assessment input quantity；The good litigation risk of the assessment input quantity input pre-training is assessed into mould
Type exports the case to be assessed by corresponding risk evaluation result；Wherein, the good litigation risk assessment models of the pre-training are
It is obtained based on training sample set training, it includes that multiple assessments with risk evaluation result label are defeated that the training sample, which is concentrated,
Enter amount.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes: ROM, RAM, magnetic disk or light
The various media that can store program code such as disk.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of litigation risk appraisal procedure characterized by comprising
Obtain case to be assessed by program elements text and true element text；
According to described program element text and the true element text, assessment input quantity is obtained；
By the good litigation risk assessment models of the assessment input quantity input pre-training, the case to be assessed is exported by corresponding wind
Dangerous assessment result；Wherein, the good litigation risk assessment models of the pre-training are obtained based on training sample set training, described
It includes multiple assessment input quantities with risk evaluation result label that training sample, which is concentrated,.
2. the method according to claim 1, wherein it is described obtain case to be assessed by program elements text and thing
Real element text, specifically includes:
The case to be assessed is obtained by corresponding related question collection；The related question collection includes procedural problem and the question of fact；
According to the case to be assessed by party complete the related question collection as a result, obtaining the case to be assessed under
The program elements text of current case and true element text.
3. according to the method described in claim 2, it is characterized in that, the method also includes:
Building includes the related question database of a variety of related question collection；Wherein, every kind of related question collection corresponds to a kind of to be evaluated
Estimate case by；Correspondingly,
The case to be assessed is obtained by corresponding related question collection, is specifically included:
Corresponding related question collection is obtained from the related question database.
4. the method according to claim 1, wherein described want according to described program element text and the fact
Plain text obtains assessment input quantity, specifically includes:
By described program element text and the true element text vector, corresponding first row vector sum second is respectively obtained
Column vector；
The element combinations in the element and the second column vector in first column vector are extracted into third column vector to get described in
Assess input quantity.
5. the method according to claim 1, wherein the good litigation risk assessment models of the pre-training by with
Under type training obtains:
Obtain the training sample set；
The litigation risk assessment models are trained based on the training sample set, until the litigation risk assessment models
Corresponding loss function convergence is to get the litigation risk assessment models good to the pre-training.
6. the method according to claim 1, wherein the risk evaluation result includes event risk weight, warp
Risk rated ratio of helping and evidence Risk rated ratio.
7. method according to claim 1 to 6, which is characterized in that further include:
The risk evaluation result is converted into corresponding risk evaluation result text.
8. a kind of litigation risk assesses device characterized by comprising
First obtains module, for obtain case to be assessed by program elements text and true element text；
Second obtains module, for obtaining assessment input quantity according to described program element text and the true element text；
Evaluation module exports described to be evaluated for the litigation risk assessment models that the assessment input quantity input pre-training is good
Case is estimated by corresponding risk evaluation result；Wherein, the good litigation risk assessment models of the pre-training are based on training sample set
What training obtained, it includes multiple assessment input quantities with risk evaluation result label that the training sample, which is concentrated,.
9. a kind of computer program product, which is characterized in that the computer program product includes being stored in non-transient computer
Computer program on readable storage medium storing program for executing, the computer program include program instruction, when described program is instructed by computer
When execution, the computer is made to execute the litigation risk appraisal procedure as described in any one of claims 1 to 7.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute the lawsuit wind as described in any one of claims 1 to 7
Dangerous appraisal procedure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910717917.6A CN110490439A (en) | 2019-08-05 | 2019-08-05 | Litigation risk appraisal procedure, device, electronic equipment and computer can storage mediums |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910717917.6A CN110490439A (en) | 2019-08-05 | 2019-08-05 | Litigation risk appraisal procedure, device, electronic equipment and computer can storage mediums |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110490439A true CN110490439A (en) | 2019-11-22 |
Family
ID=68549455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910717917.6A Pending CN110490439A (en) | 2019-08-05 | 2019-08-05 | Litigation risk appraisal procedure, device, electronic equipment and computer can storage mediums |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110490439A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111047092A (en) * | 2019-12-11 | 2020-04-21 | 深圳前海环融联易信息科技服务有限公司 | Dispute case victory rate prediction method and device, computer equipment and storage medium |
| CN111160801A (en) * | 2019-12-31 | 2020-05-15 | 重庆百事得大牛机器人有限公司 | Electronic evidence risk judgment method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110119198A1 (en) * | 2003-09-26 | 2011-05-19 | Courson Gardner G | Method of early case assessment in law suits |
| CN104850905A (en) * | 2015-05-15 | 2015-08-19 | 上海集本信息技术服务有限公司 | Machine-learning-based legal risk quantitative evaluation system and method |
| EP3206181A1 (en) * | 2014-10-06 | 2017-08-16 | Kim, Jeongchul | Lawsuit winning possibility evaluation device and method |
| CN108876186A (en) * | 2018-07-04 | 2018-11-23 | 武汉百智诚远科技有限公司 | A kind of lawsuit consulting comprehensive estimation method |
| CN109377000A (en) * | 2018-09-21 | 2019-02-22 | 安徽和信科技发展有限责任公司 | A kind of litigation risk assessment device of artificial intelligence technology |
| US20190220937A1 (en) * | 2016-07-01 | 2019-07-18 | Nelson E. Brestoff | Using classified text and deep learning algorithms to assess risk and provide early warning |
-
2019
- 2019-08-05 CN CN201910717917.6A patent/CN110490439A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110119198A1 (en) * | 2003-09-26 | 2011-05-19 | Courson Gardner G | Method of early case assessment in law suits |
| EP3206181A1 (en) * | 2014-10-06 | 2017-08-16 | Kim, Jeongchul | Lawsuit winning possibility evaluation device and method |
| CN104850905A (en) * | 2015-05-15 | 2015-08-19 | 上海集本信息技术服务有限公司 | Machine-learning-based legal risk quantitative evaluation system and method |
| US20190220937A1 (en) * | 2016-07-01 | 2019-07-18 | Nelson E. Brestoff | Using classified text and deep learning algorithms to assess risk and provide early warning |
| CN108876186A (en) * | 2018-07-04 | 2018-11-23 | 武汉百智诚远科技有限公司 | A kind of lawsuit consulting comprehensive estimation method |
| CN109377000A (en) * | 2018-09-21 | 2019-02-22 | 安徽和信科技发展有限责任公司 | A kind of litigation risk assessment device of artificial intelligence technology |
Non-Patent Citations (3)
| Title |
|---|
| 岳涛等: "民事诉讼中事实推定的评判", 《科技信息(科学教研)》 * |
| 朱伟: "《法律应用规则 律师 法官 警官 检察官办案的原理与实践》", 31 October 2018 * |
| 范振华: "从诉讼情况证明文件评估投标人履约风险", 《招标采购管理》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111047092A (en) * | 2019-12-11 | 2020-04-21 | 深圳前海环融联易信息科技服务有限公司 | Dispute case victory rate prediction method and device, computer equipment and storage medium |
| CN111160801A (en) * | 2019-12-31 | 2020-05-15 | 重庆百事得大牛机器人有限公司 | Electronic evidence risk judgment method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kshatri et al. | An empirical analysis of machine learning algorithms for crime prediction using stacked generalization: an ensemble approach | |
| Samset | Early project appraisal: making the initial choices | |
| Cao et al. | A study of risk relevance reasoning based on a context ontology of railway accidents | |
| Khisty et al. | Systems engineering with economics, probability, and statistics | |
| CN110490439A (en) | Litigation risk appraisal procedure, device, electronic equipment and computer can storage mediums | |
| Varade et al. | Academic performance prediction of undergraduate students using decision tree algorithm | |
| Mostafavi et al. | Innovation policy assessment for civil infrastructure system-of-systems | |
| CN109840705A (en) | A kind of electric power field work personnel smart allocation application method | |
| Corbett | Leaders and lemmings: Organizational responses to smart grid transformation | |
| Gladshiya et al. | A Review Study on Predictive Analytical Tools and Techniques in Education | |
| Xu et al. | [Retracted] Early Warning Method of Postgraduate Education Quality in Colleges and Universities Based on Multisource Information Fusion | |
| Cozac | The Process of Designing Artificial Intelligence: Development Trends and Prospects | |
| Li et al. | Economic system simulation with big data analytics approach | |
| Scheer | In silico science for climate policy: How policy-makers process and use carbon storage simulation data | |
| CN110443717A (en) | A kind of settlement of insurance claim method and system based on credit evaluation | |
| Fu et al. | A visual analysis of frontiers and dynamic tendencies for humanitarian logistics | |
| Beroggi | Designing and evaluating e-management decision tools: The integration of decision and negotiation models into Internet-multimedia technologies | |
| Nguyen et al. | Navigating critical barriers for green bond markets using A fuzzy multi-criteria decision-making model: Case study in Vietnam | |
| Page et al. | SIC semper simulation—balancing simplicity and complexity in modeling and analysis | |
| Schoonenberg | Engineering systems: Structure, behavior, and optimization with hetero-functional graph theory | |
| Rodonaia et al. | Modeling and Analysis of Power Engineering by Using Cognitive Approach | |
| Khalimon et al. | The System Dynamics Model for the Impact Assessment of Project Management on Circular Economic Processes | |
| Minato | A methodology for project risk control: A work package-based approach using historical cost control data | |
| Koen | Aspects of MCDA classification and sorting methods | |
| Rabiha et al. | A Neural Network based Approach for Predicting Indonesian Teacher Engagement Index (ITEI) |
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 |