CN107133283A - A kind of Legal ontology knowledge base method for auto constructing - Google Patents
A kind of Legal ontology knowledge base method for auto constructing Download PDFInfo
- Publication number
- CN107133283A CN107133283A CN201710248747.2A CN201710248747A CN107133283A CN 107133283 A CN107133283 A CN 107133283A CN 201710248747 A CN201710248747 A CN 201710248747A CN 107133283 A CN107133283 A CN 107133283A
- Authority
- CN
- China
- Prior art keywords
- law
- word
- classification
- legal
- knowledge base
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Abstract
The present invention provides a kind of Legal ontology knowledge base method for auto constructing, can try document according to law and build Legal ontology knowledge base.Methods described includes：The specialist high frequency word in law trial document is counted using network law text data, and the specialist high frequency word obtained according to statistics builds legal field vocabulary；Law trial document is gone after stop words according to the legal field vocabulary of structure and participle is carried out；Document data are tried according to the law of participle classification is iterated to law trial document data, extract the Topic word of each classification in each subseries, and divided the Topic word of each classification according to taxonomical hierarchy order, obtain the hierarchical relationship between Topic word；According to the hierarchical relationship between the Topic word of extraction and obtained Topic word, Legal ontology knowledge base is built.The present invention is applied to knowledge engineering technology field.
Description
Technical field
The present invention relates to knowledge engineering technology field, a kind of Legal ontology knowledge base method for auto constructing is particularly related to.
Background technology
Ontologies be it is clear and definite to concept system, formalization, sharable specification explanation.Ontology definition composition master
The basic terms and its relation of the vocabulary in topic field, and combine these terms and relation to define the rule that vocabulary off-balancesheet is prolonged
Then.Knowledge base is structuring in knowledge engineering, easy to operate, is easily utilized, comprehensive organized knowledge cluster, is to be directed to a certain field
The need for problem solving, using certain knowledge representation mode store, organize, manage and use in computer storage it is mutual
The knowledge piece set of contact.Ontology knowledge base by information representation into the form closer to the human cognitive world there is provided it is a kind of more
The ability of internet mass information is organized, manages and understood well.Ontology knowledge base brings vigor to internet semantic search,
Simultaneously also in intelligent answer, big data analysis with showing powerful power in decision-making, internet Knowledge based engineering intelligence is had become
The infrastructure that can be serviced.With the arrival in big data epoch, big data is converted into knowledge, strengthened in Internet resources
Hold and understand, Contemporary Information treatment technology will be promoted to change from information service to knowledge services.
Law Domain-specific ontology knowledge base is built to integrating legal knowledge, excavating law focus, prediction legal matter, structure
Building legal field expert system etc. will play an important role, still, in the prior art, the Legal ontology knowledge being also constructed without
Storehouse.
The content of the invention
It is existing to solve the technical problem to be solved in the present invention is to provide a kind of Legal ontology knowledge base method for auto constructing
Present in technology the problem of lacking Legal ontology knowledge base.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of Legal ontology knowledge base method for auto constructing, bag
Include：
Using network law text data count law trial document in specialist high frequency word, and according to statistics obtain it is special
Industry high frequency words build legal field vocabulary；
Law trial document is gone after stop words according to the legal field vocabulary of structure and participle is carried out；
Document data are tried according to the law of participle classification is iterated to law trial document data, extracted each time
The Topic word of each classification in classification, and the Topic word of each classification is divided according to taxonomical hierarchy order, obtain
Hierarchical relationship between Topic word；
According to the hierarchical relationship between the Topic word of extraction and obtained Topic word, Legal ontology knowledge base is built.
Further, the specialist high frequency word in the utilization network law text data statistics law trial document, and root
The specialist high frequency word obtained according to statistics, which builds legal field vocabulary, to be included：
Civil, criminal, administrative trial document specialist high frequency word is counted using network law text data；
According to civil, criminal, the administrative trial document specialist high frequency word of statistics, method is built with reference to default input method dictionary
Rule field vocabulary.
Further, the civil justice document specialist high frequency word includes：Civil justice, civil case, civil disputation, the people
Duties and responsibilities benefit, property, the person, citizen, minor, capacity for civil rights, capacity for civil acts, monitoring, adjudication of disappearance, declaration are dead
Die, voting qualification, assert property dereliction, the restitution of property, self-employed entrepreneur, leaseholding farm households, credits, debt, personal close
Partner, legal person, business entity, corporate body, joint operation, act in-the-law, civil right, civil liability, agency, commission generation
Reason, legal agency, authorized agency, property right, lien, be sold, leased, mortgaged or transferred, debtor-creditor relationship, unjustified enrichment,
Intellectual property, copyright, patent right, exclusive right to use trademark, personal rights, the right of health, the right of name, portraiture right, the right of fame, the right of discovery,
Inventor's patent right, reputation right, marriage, divorce, bring up, adopting, fostering, legacy, succession, testament, bequeath, agreement for legacy in return for support, premises
Production, house charter in one or more.
Further, the criminal justice document specialist high frequency word includes：Criminal, criminal justice, criminal case, crime,
Important cases, economic crime, juvenile delinquency, analogy in criminal law, criminal responsibility, object of crime, subject of crime, criminal capacity,
Age for criminal responsibility, body corporate of crime, self-defence, urgent danger prevention, completed offence, crime in preparation, attempted crime, discontinuation of a crime,
Joint crime, criminal group, punishment, control, detention, fixed-term imprisonment, life imprisonment, death penalty, fine, deprive of political rights, do not have
Receive property, deport, the measurement of penalty, recidivist, confess one's crime, concurrence of offences, sentence calculation, the prison term folding support, reprieve, reducing a penalty, paroling, prosecuting
Timeliness, absolution, anti-revolutionary, tissue are escaped from prison, spy, spy, set fire, explode, poisoning, endangering public security, destroy the vehicles,
Destruction transit equipment, destruction communication apparatus, sabotage of electrical power equipment, traffic accident, serious accident involving serious consequences, smuggle, engage in speculation and profiteering, escaping
Foreign exchange is covered, counterfeits currency, counterfeit valuable securities, forging value warrant, tax dodging, tax refusal, counterfeit trademark, Holiday culture, woods of felling trees unlawfully
Wood, excessive cutting and felling of trees, intentional murder, involuntary homicide, intentional injury, fault severe injury, prostitution and whoring, extort a confession by torture, falsely charge, by force
Paramour female, fornication with an underage girl, prostitution, kidnap and sell people, kidnap women and children, trafficking in women and children, illegal detention, bag job, insult
Disgrace, calumny, revenge frame, false wittness, invade freedom of correspondence, destruction election, property tort, robbery, grab, blackmail, stealing,
Hardened thief, swindle, hardened swindler, corrupt, appropriate public funds for personal use, kidnapping, interference with state functions, refuse to implement judgement decide, upset the public,
Rogue, run away, shelter, shielding, manufacturing and peddle counterfeit drug, swindle by false pretences, gamble, obscene goods, drugs, receive stolen goods, dispose of stolen goods, destroying treasure
Your historical relic, cross illegally state border, crime of insulting the national flag or the national emblem national emblem, impart criminal method, harm marriage and family, it is bigamy, destruction soldier marriage, cruel
Treat, abandon, swindle children, malfeasance, accept bribes, bribe, bribery-pander, leakage state secret, neglect one's duties, bend the law for the benefit of relatives or friends, private is put
One or more in criminal, destruction post and telecommunications, soldier's breach of duty, drug smuggling, drug trafficking, transport drugs.
Further, the administrative trial document specialist high frequency word includes：Administrative trial, administrative case, state administration machine
Pass, national public servants, administrative behavior, administrative responsibility, disciplinary sanction, administrative penalty, disciplinary management, administrative compensation, administrative reexamination,
Public security, customs, commodity inspection, land management, geological and mineral, the energy, administrative execution, traffic are raided, wild fauna and flora protection, plan life
Educate, fishery, salt industry, water resource, salt political affairs, compulsory administrative measure, Lu Zheng, technical supervision, patent, herding, housing demolition, river
Road, post and telecommunications, science and technology, traffic, health, medicine, environmental protection, industry, economy and trade, agricultural, forestry, culture, education, statistics, physical culture,
Civil administration, urban planning, town and country construction, metering, price, industry and commerce, work, historical relic, finance, audit, the tax, water conservancy, business administration,
One or more in railway, civil aviaton, occurrences in human life, journalism, radio, film and television, tourism, meteorology.
Further, the legal field vocabulary according to structure goes after stop words to law trial document and carries out participle
Including：
Stop words dictionary and dictionary for word segmentation are removed using the legal field vocabulary of structure is self-defined；
Stop words dictionary and dictionary for word segmentation are removed according to customized, text is tried to law using Java Chinese word segmentation machines Ansj
Book goes after stop words and carries out participle.
Further, the law trial document data of basis participle are iterated point to law trial document data
Class, extracts the Topic word of each classification in each subseries, and by the Topic word of each classification according to taxonomical hierarchy order
Divided, the hierarchical relationship obtained between Topic word includes：
Document data are tried using the law of participle, theme point is carried out to law trial document using LDA topic models
Class, extracts each classification Topic word；
Subject classification is proceeded to the law trial document application LDA topic models under each classification, each class is extracted
Other Topic word, and the Topic word of each classification is divided according to taxonomical hierarchy order, until meeting default end
Only iterated conditional, then stop iteration.
Further, the application LDA topic models carry out subject classification to law trial document, extract each classification master
Epigraph language includes：
Document is tried to law according to maximum theme probability selection theme；
Subject classification is carried out to law trial document according to the theme of selection, and each class is obtained by LDA topic models
Other Topic word.
Further, described up to meeting default termination iterated conditional, then stopping iteration including：
During the application continuous iteration of LDA topic models is by subject classification and extraction Topic word, subject classification is judged
As a result the maximum theme probability for whether having the data of preset ratio in is less than default threshold value；
If so, then judging to continue to classify according to theme, stop iteration.
Further, the hierarchical relationship between the Topic word according to extraction and obtained Topic word, builds law
Ontology knowledge base includes：
Make the Topic word of extraction as the hierarchical relationship between the body, obtained Topic word of Legal ontology knowledge base
For the sub- parent relation of Legal ontology knowledge base, the triple structure of body-sub- parent relation-body is formed, law sheet is completed
The structure of body knowledge base.
The above-mentioned technical proposal of the present invention has the beneficial effect that：
In such scheme, the specialist high frequency word in law trial document is counted by using network law text data, and
Legal field vocabulary is built according to the specialist high frequency word that statistics is obtained；Document is tried to law according to the legal field vocabulary of structure
Go after stop words and carry out participle；Document data are tried according to the law of participle to be iterated point law trial document data
Class, extracts the Topic word of each classification in each subseries, and by the Topic word of each classification according to taxonomical hierarchy order
Divided, obtain the hierarchical relationship between Topic word；According to the level between the Topic word of extraction and obtained Topic word
Relation, builds Legal ontology knowledge base.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of Legal ontology knowledge base method for auto constructing provided in an embodiment of the present invention；
Fig. 2 is entity word and its pass in the Legal ontology knowledge base that the first subseries provided in an embodiment of the present invention is obtained
It is level schematic diagram；
Fig. 3 carries out subject classification, obtained entity for the classification 0 provided in an embodiment of the present invention obtained to the first subseries
Word and its relational hierarchy schematic diagram；
Fig. 4 carries out subject classification, obtained entity for the classification 1 provided in an embodiment of the present invention obtained to the first subseries
Word and its relational hierarchy schematic diagram；
Fig. 5 carries out subject classification, obtained entity for the classification 2 provided in an embodiment of the present invention obtained to the first subseries
Word and its relational hierarchy schematic diagram；
Fig. 6 carries out subject classification, obtained entity for the classification 0 provided in an embodiment of the present invention obtained to the second subseries
Word and its relational hierarchy schematic diagram.
Embodiment
To make the technical problem to be solved in the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing and tool
Body embodiment is described in detail.
The present invention for it is existing lack Legal ontology knowledge base the problem of there is provided a kind of automatic structure of Legal ontology knowledge base
Construction method.
As shown in figure 1, Legal ontology knowledge base method for auto constructing provided in an embodiment of the present invention, including：
Step 101, the specialist high frequency word in law trial document is counted using network law text data, and according to statistics
Obtained specialist high frequency word builds legal field vocabulary；
Step 102, law trial document is gone after stop words according to the legal field vocabulary of structure and carries out participle；
Step 103, document data are tried according to the law of participle and classification is iterated to law trial document data, carried
The Topic word of each classification in each subseries is taken, and the Topic word of each classification is drawn according to taxonomical hierarchy order
Point, obtain the hierarchical relationship between Topic word；
Step 104, according to the hierarchical relationship between the Topic word of extraction and obtained Topic word, build Legal ontology and know
Know storehouse.
Legal ontology knowledge base method for auto constructing described in the embodiment of the present invention, by using network law text data
The specialist high frequency word in law trial document is counted, and the specialist high frequency word obtained according to statistics builds legal field vocabulary；Root
Law trial document is gone after stop words according to the legal field vocabulary of structure and participle is carried out；Text is tried according to the law of participle
Book data are iterated classification to law trial document data, extract the Topic word of each classification in each subseries, and will
The Topic word of each classification is divided according to taxonomical hierarchy order, obtains the hierarchical relationship between Topic word；According to extraction
Topic word and obtained Topic word between hierarchical relationship, build Legal ontology knowledge base.
In the embodiment of foregoing Legal ontology knowledge base method for auto constructing, further, the utilization net
Specialist high frequency word in network Law Text data statistics law trial document, and the specialist high frequency word obtained according to statistics builds method
Rule field vocabulary includes：
Civil, criminal, administrative trial document specialist high frequency word is counted using network law text data；
According to civil, criminal, the administrative trial document specialist high frequency word of statistics, method is built with reference to default input method dictionary
Rule field vocabulary.
In the present embodiment, first obtain network law text data, using acquisition network law text data statistics it is civil,
Criminal, administrative specialist high frequency word, the high frequency words refer to occurrence number and exceed predetermined threshold more than predetermined threshold or access times
Word, and combine default input method dictionary structure legal field vocabulary, it is preferable that the default input method dictionary is search dog
Input method dictionary.
In the present embodiment, counting obtained civil, criminal, administrative trial document specialist high frequency word has 268, actually should
In, obtained civil, criminal, administrative trial document specialist high frequency word is counted relevant with the network law text data of acquisition.
It is further, described civil careful in the embodiment of foregoing Legal ontology knowledge base method for auto constructing
Sentencing document specialist high frequency word includes：Civil justice, civil case, civil disputation, civil rights and interests, property, the person, citizen, not into
Year people, capacity for civil rights, capacity for civil acts, monitoring, adjudication of disappearance, the declaration of death, voting qualification, assert property dereliction,
The restitution of property, self-employed entrepreneur, leaseholding farm households, credits, debt, individual partnership, legal person, business entity, public organization
Legal person, joint operation, act in-the-law, civil right, civil liability, agency, agency by agreement, legal agency, authorized agency, property
Ownership, lien, be sold, leased, mortgaged or transferred, debtor-creditor relationship, unjustified enrichment, intellectual property, copyright, patent right, business
Mark private right, personal rights, the right of health, the right of name, portraiture right, the right of fame, the right of discovery, inventor's patent right, reputation right, marriage, divorce, comfort
Support, adopt, fostering, legacy, succession, testament, bequeath, agreement for legacy in return for support, real estate, house charter in one or more.
It is further, described criminal careful in the embodiment of foregoing Legal ontology knowledge base method for auto constructing
Sentencing document specialist high frequency word includes：Criminal, criminal justice, criminal case, crime, important cases, economic crime, juvenile delinquency,
It is analogy in criminal law, criminal responsibility, object of crime, subject of crime, criminal capacity, age for criminal responsibility, body corporate of crime, proper anti-
Defend, urgent danger prevention, completed offence, crime in preparation, attempted crime, discontinuation of a crime, joint crime, criminal group, punishment, control,
Detention, fixed-term imprisonment, life imprisonment, death penalty, fine, deprivation of political rights, confiscate property, deport, the measurement of penalty, recidivist, from
Head, concurrence of offences, sentence calculation, prison term folding are supported, reprieved, reducing a penalty, paroling, the limitation of prosecution, absolution, anti-revolutionary, tissue are escaped from prison,
Spy, spy, set fire, explode, poisoning, endangering public security, destroying the vehicles, it is destruction transit equipment, destruction communication apparatus, broken
Bad power equipment, traffic accident, serious accident involving serious consequences, smuggle, engage in speculation and profiteering, escape set foreign exchange, counterfeit currency, forge valuable card
Certificate, forgery value warrant, tax dodging, tax refusal, counterfeit trademark, Holiday culture, unlawful cutting trees, excessive cutting and felling of trees, intentional murder, fault are killed
People, intentional injury, fault severe injury, prostitution and whoring, extort a confession by torture, falsely charge, making an indecent assault on women, fornicating with an underage girl, prostitution, abducting people
Mouthful, kidnapping women and children, trafficking in women and children, illegal detention, bag job, insult, calumny, revenge frame, false wittness, invade logical
Letter freely, destruction election, property tort, robbery, grab, blackmail, stealing, hardened thief, swindle, hardened swindler, corruption, divert public affairs
Money, kidnapping, interference with state functions, refuse to implement judgement and decide, upset the public, rogue, run away, shelter, shielding, manufacturing dealer
Sell quack medicine, swindle by false pretences, gambling, obscene goods, drugs, receive stolen goods, dispose of stolen goods, destroy rare cultural relics, cross state border, crime of insulting the national flag or the national emblem illegally
National emblem, impart criminal method, harm marriage and family, bigamy, destruction soldier marriage, maltreat, abandon, swindle children, malfeasance, by
Bribe, bribe, bribery-pander, leakage state secret, neglect one's duties, bend the law for the benefit of relatives or friends, criminal is put in private, destruction post and telecommunications, soldier disobey
One or more in anti-responsibility, drug smuggling, drug trafficking, transport drugs.
It is further, described administrative careful in the embodiment of foregoing Legal ontology knowledge base method for auto constructing
Sentencing document specialist high frequency word includes：Administrative trial, administrative case, state administrative organs, national public servants, administrative behavior, administration
Responsibility, disciplinary sanction, administrative penalty, disciplinary management, administrative compensation, administrative reexamination, public security, customs, commodity inspection, land management,
Matter mineral products, the energy, administrative execution, traffic are raided, wild fauna and flora protection, family planning, fishery, salt industry, water resource, salt
Political affairs, compulsory administrative measure, Lu Zheng, technical supervision, patent, herding, housing demolition, river course, post and telecommunications, science and technology, traffic, health, doctor
Medicine, environmental protection, industry, economy and trade, agricultural, forestry, culture, education, statistics, physical culture, civil administration, urban planning, town and country construction, meter
Amount, price, industry and commerce, work, historical relic, finance, audit, the tax, water conservancy, business administration, railway, civil aviaton, occurrences in human life, journalism,
One or more in radio, film and television, tourism, meteorology.
It is further, described according to structure in the embodiment of foregoing Legal ontology knowledge base method for auto constructing
The legal field vocabulary built goes after stop words to law trial document and carries out participle to include：
Stop words dictionary and dictionary for word segmentation are removed using the legal field vocabulary of structure is self-defined；
Stop words dictionary and dictionary for word segmentation are removed according to customized, text is tried to law using Java Chinese word segmentation machines Ansj
Book goes after stop words and carries out participle.
In the present embodiment, it is possible to use the legal field vocabulary of structure is self-defined to remove stop words dictionary
NewWordFilter.dic and dictionary for word segmentation LegalWord.dic, and remove stop words dictionary according to customized
NewWordFilter.dic and dictionary for word segmentation LegalWord.dic, document is tried using Java Chinese word segmentation machines Ansj to law
Go after stop words and carry out participle, be that the automatic Legal ontology knowledge base that builds is prepared.
In the present embodiment, the Chinese word segmentation machine Ansj is realized based on Java, and stop words word is removed using customized
Allusion quotation, which is realized, goes stop words code as follows：
In the present embodiment, call the code of self-defined dictionary for word segmentation as follows：
In the present embodiment, document data are tried using the law of participle, can be using implicit Di Li Crays distribution
(Latent Dirichlet Allocation, LDA) topic model carries out subject classification to law trial document, and extracts every
One classification Topic word；Then application LDA topic models are continued to the law trial document under each classification and carries out subject classification
And the Topic word of each classification is extracted, while the Topic word of each classification is divided according to taxonomical hierarchy order, directly
To default termination iterated conditional is met, then stop iteration.
In the present embodiment, the LDA is a kind of document subject matter generation model, also referred to as one three layers of Bayesian probability mould
Type, includes word, theme and document three-decker.Each word of every article is by the way that " some is led with certain probability selection
Topic, and with certain probability selection some word, " such a process is obtained from this theme.Document obeys multinomial to theme
Distribution, theme to word obeys multinomial distribution.The Topic word of article can be thus obtained by theme.So using LDA
Topic model, tries document to law and selects certain theme according to maximum probability, and then law trial document is carried out according to theme
Subject classification, and each classification Topic word is obtained by LDA topic models；Then the trial document under each classification is distinguished
Continue application LDA topic models to carry out subject classification and obtain the Topic word of each classification (subclass).Similarly, after classification
Continue using LDA topic models to classify and obtain the Topic word of each classification in each classification (subclass), and by each class
Other Topic word is divided according to taxonomical hierarchy order.
In the present embodiment, using the LDA topic models, civil to 2000 parts, criminal, administrative trial document carries out first
Subseries and the Topic word for obtaining each classification.Number of topics is set to 3 (the classification number per subseries is 3), and takes first 20
Probability highest word is used as each classification Topic word；After classification, Topic word and its probability under three obtained themes
It is as follows：
topic 0：
Appeal 0.020716457203748394
Defendant 0.015358624096518602
Soil 0.013313991406572972
Compensation 0.011940953395806564
Management 0.011463374957279117
Removal 0.009224726026681711
People's court 0.009090407090845867
In accordance with the law 0.008612828652318421
Judgement 0.008582979999910454
Trial 0.008299417802034784
Government 0.008045704256567077
Plaintiff 0.00783676368971132
Ruling 0.007791990711099372
Assert 0.007642747449059544
Confirm 0.007045774400900236
The people 0.006702514898208634
Interim 0.00662789326718872
Certain person 0.006553271636168806
RMB 0.006329406743109066
Standard 0.006210012133477204
topic 1:
Company 0.06931993926904303
Lawsuit 0.020827735689207656
This case 0.017832326507314325
Second trial 0.014348395656271011
Review 0.01391129732071576
Contract 0.01370560398633682
Regulation 0.013242793983984202
Civil 0.012240038978886866
Judgement 0.01215004814509608
The first sentence 0.011597247308952674
Law court 0.011584391475553991
Application 0.010825897305031645
Applicant 0.010530213136861918
People's court 0.010183105635097455
Law 0.009643160632352734
Evidence 0.008936089795425125
Agency 0.008370433125883035
Assert 0.007984758123922521
Agreement 0.007907623123530418
Co., Ltd 0.007869055623334367
topic 2:
Trade mark 0.04003179012285558
Company 0.028305286471471677
Appeal 0.027311845132234835
The first sentence 0.021623906484055266
Application 0.01940327290223174
Prosecution 0.016052843287550623
Birth 0.013559500318485606
Evidence 0.01324783244735248
Tourism 0.01194272323698251
It is required that 0.01188428551114505
Regulation 0.011221991284987154
Patent 0.011144074317203873
Administration 0.010910323413854027
Right 0.010715530994395824
Judgement 0.010248029187696133
Technology 0.01018959146185867
Dispute 0.01017011221991285
The committee 0.009975319800454647
Product 0.009605214203484059
Assert 0.009468859509863314
In the present embodiment, entity word and its relational hierarchy, such as Fig. 2 in the Legal ontology knowledge base that the first subseries is obtained
It is shown.
In the present embodiment, the document of theme 0 (topic 0), theme 1 (topic 1), theme 2 (topic 2) is divided into three
Class, is designated as classification 0 respectively, and then classification 1, classification 2 carries out the second wheel classification：
In the present embodiment, the second subseries, the classification 0 obtained to the first subseries carries out subject classification, three obtained
Topic word and its probability under theme is as follows：
topic 0:
Compensation 0.025827294598994424
Management 0.02316208779335283
Appeal 0.022909973636062408
Soil 0.021361272384135536
Removal 0.020857044069554694
Plaintiff 0.017471511100226184
Company 0.016643136011986227
Interim 0.01581476092374627
Pay 0.01549061415008716
The first sentence 0.014518173829109821
Contract 0.012933456268998602
Defendant 0.012825407344445566
Government 0.012465244262602107
Standard 0.012465244262602107
Administration 0.011744918098915189
Administration commission 0.01156483655799346
Agreement 0.010808494086122196
This case 0.010628412545200467
Agreement 0.010052151614250934
Regulation 0.00972800484059182
topic 1:
Defendant 0.039311415137042616
People's court 0.020743457335267113
Ruling 0.020466323636733147
Trial 0.019773489390398243
Criminal 0.01857257669675107
Criminal 0.015662672862144462
Judgement 0.015246972314343517
In accordance with the law 0.014923649666053893
Sentence 0.014646515967519931
Perform 0.014046059620696345
The People's Republic of China (PRC) 0.011828990032424644
Assert 0.01155185633389068
The injured party 0.010443321539754828
Office 0.009750487293419922
Law 0.0096581093939086
Intentional 0.0096581093939086
Appeal 0.00961192044415294
Fixed-term imprisonment 0.009427164645130298
Occur 0.009057653047085015
Judge 0.009011464097329355
topic 2:
Company 0.025217530195625056
Appeal 0.01833414463476224
Bank 0.012971949253095623
Without 0.01137469956493961
Prove 0.010804253247741032
RMB 0.010576074720861603
Testimony 0.010461985457421887
Situation 0.010119717667102741
Project 0.009929568894703216
Engineering 0.009207003559585019
Confirm 0.008902765523745778
Account 0.008560497733426632
Witness 0.008294289452067297
Evidence 0.008028081170707961
Cash 0.007571724116949101
Wuqi County 0.007533694362469196
Work 0.0071533968176701445
Defender 0.0065829505004715684
Post 0.006468861237031854
Assert 0.006392801728072043
In the present embodiment, the classification 0 obtained to the first subseries carries out subject classification, obtained entity word and its relation
Level, as shown in Figure 3.
In the present embodiment, the second subseries, the classification 1 obtained to the first subseries carries out subject classification, three obtained
Topic word and its probability under theme is as follows：
topic 0:
Lawsuit 0.03758776353541387
Second trial 0.03037409869990828
Review 0.03030881666519782
Applicant 0.023927497772250565
This case 0.02302986979498177
Application 0.02226280588713389
Regulation 0.019863691111524563
The first sentence 0.019618883481360348
Civil 0.019178229747064755
Judgement 0.0167464739541002
Law court 0.015783563942120948
The People's Republic of China (PRC) 0.015147064103693984
Company 0.014788012912786466
Timeliness 0.013939346461550515
Appeal 0.013727179848741526
Evidence 0.013319167131801165
Law 0.013221244079735479
Agency 0.012796910854117502
Period 0.01253578271527567
People's court 0.01206248796362485
topic 1:
Company 0.09230282265274267
Engineering 0.016336205438475256
People's court 0.014668999144650686
Contract 0.014209913353597543
There is provided 0.01203529644860897
Prove 0.010295602924618114
Perform 0.010223115694451829
Co., Ltd 0.009739867493343256
Product 0.008894183141403257
Senior 0.0085075845805164
Arbitration 0.007541088178299257
Judgement 0.007444438538077543
Agreement 0.007444438538077543
Assert 0.0073236264878004
Ruling 0.007251139257634114
This case 0.007251139257634114
Sign 0.007178652027467828
House 0.007106164797301543
Evidence 0.007106164797301543
Appeal 0.007082002387246114
topic 2:
Company 0.07835860181090756
Contract 0.019682281289988175
Transfer the possession of 0.01802201273142524
Agreement 0.013324667541344738
Property 0.013243678831170936
Both sides 0.012231319953998414
Pay 0.011785882048042503
Soil 0.011502421562434197
Judgement 0.010530557040348576
Regulation 0.010145860667023018
This case 0.010064871956849216
Technology 0.009740917116154008
Evidence 0.008546333641090432
Common 0.008303367510569027
Law 0.008262873155482126
Agreement 0.00797941266987382
Man and wife 0.007817435249526217
Fund 0.007371997343570307
Prove 0.007108784035505451
Application 0.006724087662179893
In the present embodiment, the classification 1 obtained to the first subseries carries out subject classification, obtained entity word and its relation
Level, as shown in Figure 4.
In the present embodiment, the second subseries, the classification 2 obtained to the first subseries carries out subject classification, obtains three masters
Topic word and its probability under topic is as follows：
topic 0:
Patent 0.046073634052009656
It is required that 0.03962050471163914
Right 0.037270027137332
Technology 0.03427851022457745
Company 0.023081689779696147
Product 0.01735507168956602
Evidence 0.015132801982948354
Application 0.01457723455629394
Disclose 0.014363554776811472
Feature 0.012825060364537705
Specification 0.012269492937883288
Judgement 0.011030150216884978
Second trial 0.010944678305091991
Determine 0.009833543451783158
Review 0.009705335584093677
Assert 0.009662599628197183
Examine 0.009577127716404196
Design 0.009064296245646274
Effect 0.008807880510267313
Patent right 0.00863693668668134
topic 1:
Trade mark 0.1053547720902788
Company 0.04951387305716853
Application 0.02668937494132951
Dispute 0.020493770869932548
The committee 0.01821400313803323
This case 0.013976317236385094
Evidence 0.013466722096313482
Second trial 0.013252155721546487
Assert 0.012796202175166626
Judgement 0.01239389022247851
Review 0.012045219863482145
Regulation 0.011991578269790396
Ruling 0.01183065348871515
Objection 0.010865104802263676
Constitute 0.010194584881116818
Applicant 0.00957770655366171
The People's Republic of China (PRC) 0.009524064959969962
Correlation 0.009443602569432339
Administration 0.00882672424197723
Submit 0.00845123308613499
topic 2:
Appeal 0.07846932751310445
The first sentence 0.049236989462761865
Prosecution 0.04644614201119917
Birth 0.04186628978299372
Tourism 0.03871764137610247
Administration 0.01696334329212659
Plaintiff 0.016784442814462317
Company 0.015603699661878098
Punishment 0.012741292019249692
Regulation 0.011560548866665474
First trial 0.011417428484534054
Science and technology 0.010916507147074083
Behavior 0.010129345045351273
Defendant 0.009449523230227026
Make 0.009127502370431329
Travel agency 0.007803638835715691
Prove 0.006730235969730039
Legal 0.006336654918868633
Carry out 0.006336654918868633
Determine 0.006300874823335778
In the present embodiment, the classification 2 obtained to the first subseries carries out subject classification, obtained entity word and its relation
Level, as shown in Figure 5.
In the present embodiment, third time is classified, so that the second subseries obtains topic0 subject categories (classification 0) as an example, to the
The classification 0 that secondary classification is obtained carries out subject classification, and obtained classification results are as follows：
topic 0:
Removal 0.02838756716488881
Management 0.02680255503954605
Compensation 0.026327051401943222
Appeal 0.02490054048913474
Interim 0.019987002900572187
Plaintiff 0.019352998050435083
Pay 0.017767985925092326
The first sentence 0.01681697864988667
Company 0.015390467737078186
Contract 0.015390467737078186
Administration commission 0.015231966524543911
Defendant 0.014597961674406808
Standard 0.014439460461872531
Agreement 0.013171450761598324
House 0.013171450761598324
Agreement 0.012378944698926945
Area 0.01142793742372129
Government 0.010952433786118463
Fulfil 0.010635431361049911
This case 0.010635431361049911
topic 1:
Defendant 0.03511978747776071
People's court 0.019034388632984813
In accordance with the law 0.018790670468670025
Trial 0.018303234140040453
Judgement 0.015622334332577804
Ruling 0.015622334332577804
Criminal 0.015134898003948233
Sentence 0.013428870853744728
Assert 0.01269771636080037
The People's Republic of China (PRC) 0.01196656186785601
The injured party 0.01196656186785601
Perform 0.010747971046282079
Criminal 0.010504252881967293
Appeal 0.010260534717652507
RMB 0.010016816553337719
Fixed-term imprisonment 0.009773098389022933
Crime 0.009529380224708147
Opinion 0.009529380224708147
Judge 0.00928566206039336
Confirm 0.009041943896078574
topic 2:
Wuqi County 0.040996668115312176
Engineering 0.03354649117360981
Project 0.030028352062250362
Company 0.027544959748349574
Build 0.015955795616812565
Science and technology 0.01574884625732083
Situation 0.011816808426977918
Post 0.011816808426977918
Without 0.011609859067486185
Agree to 0.011609859067486185
Account 0.010989010989010988
Testimony 0.010989010989010988
Appeal 0.010989010989010988
Contract 0.010989010989010988
Bribe 0.010782061629519257
Hunan 0.009747314832060594
Manager 0.008091719956126736
Investment 0.007884770596635003
Investment 0.007470871877651539
Dividend 0.007263922518159806
In the present embodiment, the classification 0 obtained to the second subseries carries out subject classification, hierarchical relationship such as Fig. 6 institutes of formation
Show.
It is further, described until symbol in the embodiment of foregoing Legal ontology knowledge base method for auto constructing
Default termination iterated conditional is closed, then stopping iteration including：
During the application continuous iteration of LDA topic models is by subject classification and extraction Topic word, subject classification is judged
As a result the maximum theme probability for whether having the data of preset ratio in is less than default threshold value；
If so, then judging to continue to classify according to theme, stop iteration.
In the present embodiment, the probability distribution that some themes of each documents representative are constituted in LDA topic models,
And each theme represents the probability distribution that many words are constituted.It therefore, it can regard as a document according to one
Determine document MAXIMUM SELECTION probability in a certain theme of probability selection, the theme some words of correspondence distribution again, the present embodiment
Theme as document theme.So, in the application continuous iteration of LDA topic models by subject classification and extraction Topic word process
In, rational critical value need to be set, it can be assumed for instance that the preset ratio is 30%, default threshold value is 0.5, i.e.,：Answering
With the continuous iteration of LDA topic models by subject classification and extracting Topic word during, need to judge in subject classification result whether
The maximum theme probability for having 30% data is less than<0.5, if so, then judging to continue to classify according to theme, stop iteration.
In the embodiment of foregoing Legal ontology knowledge base method for auto constructing, further, the basis is carried
Hierarchical relationship between the Topic word taken and obtained Topic word, building Legal ontology knowledge base includes：
Make the Topic word of extraction as the hierarchical relationship between the body, obtained Topic word of Legal ontology knowledge base
For the sub- parent relation of Legal ontology knowledge base, the triple structure of body-sub- parent relation-body is formed, law neck is completed
The structure of domain ontology knowledge base.
, will using the Topic word extracted during Iterative classification as the body of Legal ontology knowledge base in the present embodiment
Hierarchical relationship between the Topic word that each subseries is obtained forms body as the sub- parent relation of Legal ontology knowledge base
The triple structure of (entity word)-sub- parent relation-body (entity word), so as to build Legal ontology knowledge base automatically.
The method of automatic structure Legal ontology knowledge base described in the present embodiment can be applied not only to legal field body
The structure of knowledge base, is also applied for the structure of other Domain-specific ontology knowledge bases, specifically, counting the special of other specific areas
Industry high frequency words, build other specific area vocabularys, other specific area vocabularys based on structure, and other specific areas are built automatically
Ontology knowledge base.
Described above is the preferred embodiment of the present invention, it is noted that for those skilled in the art
For, on the premise of principle of the present invention is not departed from, some improvements and modifications can also be made, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of Legal ontology knowledge base method for auto constructing, it is characterised in that including：
The specialist high frequency word in law trial document is counted using network law text data, and the specialty obtained according to statistics is high
Frequency word builds legal field vocabulary；
Law trial document is gone after stop words according to the legal field vocabulary of structure and participle is carried out；
Document data are tried according to the law of participle classification is iterated to law trial document data, extract each subseries
In each classification Topic word, and the Topic word of each classification is divided according to taxonomical hierarchy order, obtains theme
Hierarchical relationship between word；
According to the hierarchical relationship between the Topic word of extraction and obtained Topic word, Legal ontology knowledge base is built.
2. Legal ontology knowledge base method for auto constructing according to claim 1, it is characterised in that the utilization network technique
The specialist high frequency word in text data statistics law trial document is restrained, and the specialist high frequency word obtained according to statistics builds law neck
Domain vocabulary includes：
Civil, criminal, administrative trial document specialist high frequency word is counted using network law text data；
According to civil, criminal, the administrative trial document specialist high frequency word of statistics, law neck is built with reference to default input method dictionary
Domain vocabulary.
3. Legal ontology knowledge base method for auto constructing according to claim 2, it is characterised in that the civil justice text
Book specialist high frequency word includes：Civil justice, civil case, civil disputation, civil rights and interests, property, the person, citizen, minor,
Capacity for civil rights, capacity for civil acts, monitoring, adjudication of disappearance, the declaration of death, voting qualification, identification property dereliction, return wealth
Production, self-employed entrepreneur, leaseholding farm households, credits, debt, individual partnership, legal person, business entity, corporate body, connection
Battalion, act in-the-law, civil right, civil liability, agency, agency by agreement, legal agency, authorized agency, property right,
Lien, be sold, leased, mortgaged or transferred, debtor-creditor relationship, unjustified enrichment, intellectual property, copyright, patent right, trade mark it is special
Power, personal rights, the right of health, the right of name, portraiture right, the right of fame, the right of discovery, inventor's patent right, reputation right, marriage, divorce, bring up, receiving
Support, foster, legacy, succession, testament, bequeath, agreement for legacy in return for support, real estate, house charter in one or more.
4. Legal ontology knowledge base method for auto constructing according to claim 2, it is characterised in that the criminal justice text
Book specialist high frequency word includes：It is criminal, criminal justice, criminal case, crime, important cases, economic crime, juvenile delinquency, criminal
Analogize, criminal responsibility, object of crime, subject of crime, criminal capacity, age for criminal responsibility, body corporate of crime, self-defence,
Urgent danger prevention, completed offence, crime in preparation, attempted crime, discontinuation of a crime, joint crime, criminal group, punishment, control, arrest
Labour, fixed-term imprisonment, life imprisonment, death penalty, fine, deprivation of political rights, confiscate property, deport, the measurement of penalty, recidivist, confess one's crime,
Concurrence of offences, sentence calculation, prison term folding are supported, reprieved, reducing a penalty, paroling, the limitation of prosecution, absolution, anti-revolutionary, tissue are escaped from prison, spy,
Spy, set fire, explode, poisoning, endangering public security, destroy the vehicles, destruction transit equipment, destruction communication apparatus, destruction
Power equipment, traffic accident, serious accident involving serious consequences, smuggle, engage in speculation and profiteering, escape set foreign exchange, counterfeit currency, counterfeit valuable securities,
Forge value warrant, tax dodging, tax refusal, counterfeit trademark, Holiday culture, unlawful cutting trees, excessive cutting and felling of trees, intentional murder, involuntary homicide,
Intentional injury, fault severe injury, prostitution and whoring, extort a confession by torture, falsely charge, making an indecent assault on women, fornicating with an underage girl, prostitution, kidnap and sell people,
Kidnapping women and children, trafficking in women and children, illegal detention, bag job, insult, calumny, revenge frame, false wittness, invade communication
Freely, destruction election, property tort, robbery, grab, blackmail, stealing, hardened thief, swindle, hardened swindler, corrupt, appropriate public funds for personal use,
Kidnapping, interference with state functions, refuse to implement judgement and decide, upset the public, rogue, run away, shelter, shielding, manufacturing and peddle
Counterfeit drug, swindle by false pretences, gamble, obscene goods, drugs, receive stolen goods, dispose of stolen goods, destroy rare cultural relics, cross state border, crime of insulting the national flag or the national emblem state illegally
Emblem, impart criminal method, harm marriage and family, bigamy, destruction soldier marriage, maltreat, abandon, swindle children, malfeasance, accept bribes,
Bribe, bribery-pander, leakage state secret, neglect one's duties, bend the law for the benefit of relatives or friends, criminal is put in private, destruction post and telecommunications, soldier violate duty
One or more in duty, drug smuggling, drug trafficking, transport drugs.
5. Legal ontology knowledge base method for auto constructing according to claim 2, it is characterised in that the administrative trial text
Book specialist high frequency word includes：Administrative trial, administrative case, state administrative organs, national public servants, administrative behavior, administrative responsibility,
Disciplinary sanction, administrative penalty, disciplinary management, administrative compensation, administrative reexamination, public security, customs, commodity inspection, land management, geology ore deposit
Production, the energy, administrative execution, traffic are raided, wild fauna and flora protection, family planning, fishery, salt industry, water resource, salt political affairs, OK
Political affairs compulsory measure, Lu Zheng, technical supervision, patent, herding, housing demolition, river course, post and telecommunications, science and technology, traffic, health, medicine, ring
Border protection, industry, economy and trade, agricultural, forestry, culture, education, statistics, physical culture, civil administration, urban planning, town and country construction, metering, thing
Valency, industry and commerce, work, historical relic, finance, audit, the tax, water conservancy, business administration, railway, civil aviaton, occurrences in human life, journalism, broadcast shadow
Depending on, travel, it is meteorological in one or more.
6. Legal ontology knowledge base method for auto constructing according to claim 1, it is characterised in that described according to structure
Legal field vocabulary goes after stop words to law trial document and carries out participle to include：
Stop words dictionary and dictionary for word segmentation are removed using the legal field vocabulary of structure is self-defined；
Stop words dictionary and dictionary for word segmentation are removed according to customized, law trial document is gone using Java Chinese word segmentation machines Ansj
After stop words and carry out participle.
7. Legal ontology knowledge base method for auto constructing according to claim 1, it is characterised in that basis participle
Law trial document data classification is iterated to law trial document data, the master of each classification in each subseries of extraction
Language is write inscription, and the Topic word of each classification is divided according to taxonomical hierarchy order, the level obtained between Topic word is closed
System includes：
Document data are tried using the law of participle, subject classification is carried out to law trial document using LDA topic models, carried
Take each classification Topic word；
Subject classification is proceeded to the law trial document application LDA topic models under each classification, each classification is extracted
Topic word, and the Topic word of each classification is divided according to taxonomical hierarchy order, changed until meeting default termination
For condition, then stop iteration.
8. Legal ontology knowledge base method for auto constructing according to claim 7, it is characterised in that the application LDA master
Inscribe model and subject classification is carried out to law trial document, extracting each classification Topic word includes：
Document is tried to law according to maximum theme probability selection theme；
Subject classification is carried out to law trial document according to the theme of selection, and each classification master is obtained by LDA topic models
Write inscription language.
9. Legal ontology knowledge base method for auto constructing according to claim 7, it is characterised in that described until meeting pre-
If termination iterated conditional, then stop iteration including：
During the application continuous iteration of LDA topic models is by subject classification and extraction Topic word, subject classification result is judged
In whether have preset ratio data maximum theme probability be less than default threshold value；
If so, then judging to continue to classify according to theme, stop iteration.
10. Legal ontology knowledge base method for auto constructing according to claim 1, it is characterised in that described according to extraction
Topic word and obtained Topic word between hierarchical relationship, building Legal ontology knowledge base includes：
The Topic word of extraction is regard as method as the hierarchical relationship between the body, obtained Topic word of Legal ontology knowledge base
The sub- parent relation of ontology knowledge base is restrained, the triple structure of body-sub- parent relation-body is formed, Legal ontology is completed and knows
Know the structure in storehouse.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710248747.2A CN107133283A (en) | 2017-04-17 | 2017-04-17 | A kind of Legal ontology knowledge base method for auto constructing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710248747.2A CN107133283A (en) | 2017-04-17 | 2017-04-17 | A kind of Legal ontology knowledge base method for auto constructing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107133283A true CN107133283A (en) | 2017-09-05 |
Family
ID=59715813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710248747.2A Pending CN107133283A (en) | 2017-04-17 | 2017-04-17 | A kind of Legal ontology knowledge base method for auto constructing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107133283A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679226A (en) * | 2017-10-23 | 2018-02-09 | 中国科学院重庆绿色智能技术研究院 | Tourism body constructing method based on theme |
| CN107918824A (en) * | 2017-11-02 | 2018-04-17 | 中交第二公路工程局有限公司 | A kind of highway engineering construction Norm Measure method |
| CN108280149A (en) * | 2018-01-04 | 2018-07-13 | 东南大学 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
| CN108304488A (en) * | 2018-01-04 | 2018-07-20 | 上海电机学院 | A method of utilizing the automatic study ontology of Topic Model |
| CN108563630A (en) * | 2018-03-21 | 2018-09-21 | 上海蔚界信息科技有限公司 | A kind of construction method of text analyzing knowledge base |
| CN109614606A (en) * | 2018-10-23 | 2019-04-12 | 中山大学 | Long article this case fine range classification prediction technique and device based on document insertion |
| CN110046262A (en) * | 2019-06-10 | 2019-07-23 | 南京擎盾信息科技有限公司 | A kind of Context Reasoning method based on law expert's knowledge base |
| CN110119473A (en) * | 2019-05-23 | 2019-08-13 | 北京金山数字娱乐科技有限公司 | A kind of construction method and device of file destination knowledge mapping |
| CN110334337A (en) * | 2019-04-24 | 2019-10-15 | 北京科技大学 | A kind of short phrase picking method and system based on Chinese medical book document |
| CN110795932A (en) * | 2019-09-30 | 2020-02-14 | 中国地质大学（武汉） | Geological report text information extraction method based on geological ontology |
| CN110895703A (en) * | 2018-09-12 | 2020-03-20 | 北京国双科技有限公司 | Legal document routing identification method and device |
| WO2021002800A1 (en) * | 2019-07-01 | 2021-01-07 | Intelllex Holdings Private Limited | Apparatus and method for tagging electronic legal documents for classification and retrieval |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6502081B1 (en) * | 1999-08-06 | 2002-12-31 | Lexis Nexis | System and method for classifying legal concepts using legal topic scheme |
| CN102402599A (en) * | 2011-11-17 | 2012-04-04 | 天津大学 | Dynamic maintenance system for large-scale semantic knowledge base |
| CN103049532A (en) * | 2012-12-21 | 2013-04-17 | 东莞中国科学院云计算产业技术创新与育成中心 | Method for creating knowledge base engine on basis of sudden event emergency management and method for inquiring knowledge base engine |
| CN103324700A (en) * | 2013-06-08 | 2013-09-25 | 同济大学 | Noumenon concept attribute learning method based on Web information |
| CN103412917A (en) * | 2013-08-08 | 2013-11-27 | 广西大学 | Extensible database system and management method for coordinated management of data in multi-type field |
| CN105893551A (en) * | 2016-03-31 | 2016-08-24 | 上海智臻智能网络科技股份有限公司 | Method and device for processing data and knowledge graph |
| CN106407208A (en) * | 2015-07-29 | 2017-02-15 | 清华大学 | Establishment method and system for city management ontology knowledge base |
-
2017
- 2017-04-17 CN CN201710248747.2A patent/CN107133283A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6502081B1 (en) * | 1999-08-06 | 2002-12-31 | Lexis Nexis | System and method for classifying legal concepts using legal topic scheme |
| CN102402599A (en) * | 2011-11-17 | 2012-04-04 | 天津大学 | Dynamic maintenance system for large-scale semantic knowledge base |
| CN103049532A (en) * | 2012-12-21 | 2013-04-17 | 东莞中国科学院云计算产业技术创新与育成中心 | Method for creating knowledge base engine on basis of sudden event emergency management and method for inquiring knowledge base engine |
| CN103324700A (en) * | 2013-06-08 | 2013-09-25 | 同济大学 | Noumenon concept attribute learning method based on Web information |
| CN103412917A (en) * | 2013-08-08 | 2013-11-27 | 广西大学 | Extensible database system and management method for coordinated management of data in multi-type field |
| CN106407208A (en) * | 2015-07-29 | 2017-02-15 | 清华大学 | Establishment method and system for city management ontology knowledge base |
| CN105893551A (en) * | 2016-03-31 | 2016-08-24 | 上海智臻智能网络科技股份有限公司 | Method and device for processing data and knowledge graph |
Non-Patent Citations (1)
| Title |
|---|
| 甘绍宁: "《专利文献研究2016》", 30 September 2016, 知识产权出版社 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679226B (en) * | 2017-10-23 | 2019-03-05 | 中国科学院重庆绿色智能技术研究院 | Tourism body constructing method based on theme |
| CN107679226A (en) * | 2017-10-23 | 2018-02-09 | 中国科学院重庆绿色智能技术研究院 | Tourism body constructing method based on theme |
| CN107918824B (en) * | 2017-11-02 | 2022-03-08 | 中交第二公路工程局有限公司 | Method for determining construction quota of highway engineering |
| CN107918824A (en) * | 2017-11-02 | 2018-04-17 | 中交第二公路工程局有限公司 | A kind of highway engineering construction Norm Measure method |
| CN108280149A (en) * | 2018-01-04 | 2018-07-13 | 东南大学 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
| CN108304488A (en) * | 2018-01-04 | 2018-07-20 | 上海电机学院 | A method of utilizing the automatic study ontology of Topic Model |
| CN108563630A (en) * | 2018-03-21 | 2018-09-21 | 上海蔚界信息科技有限公司 | A kind of construction method of text analyzing knowledge base |
| CN110895703B (en) * | 2018-09-12 | 2023-05-23 | 北京国双科技有限公司 | Legal document case recognition method and device |
| CN110895703A (en) * | 2018-09-12 | 2020-03-20 | 北京国双科技有限公司 | Legal document routing identification method and device |
| CN109614606A (en) * | 2018-10-23 | 2019-04-12 | 中山大学 | Long article this case fine range classification prediction technique and device based on document insertion |
| CN109614606B (en) * | 2018-10-23 | 2023-02-03 | 中山大学 | Document embedding-based long text case penalty range classification prediction method and device |
| CN110334337A (en) * | 2019-04-24 | 2019-10-15 | 北京科技大学 | A kind of short phrase picking method and system based on Chinese medical book document |
| CN110119473A (en) * | 2019-05-23 | 2019-08-13 | 北京金山数字娱乐科技有限公司 | A kind of construction method and device of file destination knowledge mapping |
| CN110046262A (en) * | 2019-06-10 | 2019-07-23 | 南京擎盾信息科技有限公司 | A kind of Context Reasoning method based on law expert's knowledge base |
| WO2021002800A1 (en) * | 2019-07-01 | 2021-01-07 | Intelllex Holdings Private Limited | Apparatus and method for tagging electronic legal documents for classification and retrieval |
| CN110795932A (en) * | 2019-09-30 | 2020-02-14 | 中国地质大学（武汉） | Geological report text information extraction method based on geological ontology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107133283A (en) | A kind of Legal ontology knowledge base method for auto constructing | |
| Coleman et al. | Surveillance and crime | |
| CN107103087A (en) | Block chain big data analysis of market conditions system | |
| CN113011185A (en) | Legal field text analysis and identification method, system, storage medium and terminal | |
| Khalyubi et al. | Electoral manipulation informationally on hoax production in 2019 presidential and vice presidential election in Indonesia | |
| Trikoz et al. | Russian experience of using digital technologies and legal risks of AI | |
| Sahramäki et al. | Wasting opportunities: prevention of illicit cross-border waste trafficking | |
| Joutsen | The European Union and cooperation in criminal matters: the search for balance | |
| Wood et al. | Analysing the multiple dimensions of predictive policing’s techno-social harms | |
| Ugwu | Forensic accounting and fraud control in Nigeria: A critical review | |
| Pohoretskyi et al. | Detection and proof of cybercrime | |
| Roddy | The federal computer systems Protection Act | |
| Zhu et al. | Construction and application of knowledge-base in telecom fraud domain | |
| Steel | The harms and wrongs of stealing: the harm principle and dishonesty in theft. | |
| Child et al. | Criminal Law Reform Now: Proposals & Critique | |
| Leighton-Daly | Identity Theft and Tax Crime: Has Technology Made It Easier to Defraud the Revenue | |
| Dewey | The Characteristics of Illegal Markets | |
| Demydova et al. | Intellectual property: search of the optimum model of legal protection | |
| Bak et al. | Application of an ontology-based and rule-based model to selected economic crimes: fraudulent disbursement and money laundering | |
| Genosko et al. | Administrative surveillance of alcohol consumption in Ontario, Canada: pre electronic technologies of control | |
| Isibor | Using Blockchain Technology to Curb Voter Fraud in Nigeria: Prospects and Challenges | |
| Glynn | Computer Abuse: The Emerging Crime and the Need for Legislation | |
| Bak et al. | Application of an ontology-based model to a selected fraudulent disbursement economic crime | |
| Liao | Review of Big Data Evidence in Criminal Proceedings: Basis of Academic Theory, Practical Pattern and Mode Selection | |
| Li | Roles of information systems in socio-legal context. |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170905 |