CN106503239A - A kind of method and apparatus of legal information inquiry - Google Patents
A kind of method and apparatus of legal information inquiry Download PDFInfo
- Publication number
- CN106503239A CN106503239A CN201610976905.1A CN201610976905A CN106503239A CN 106503239 A CN106503239 A CN 106503239A CN 201610976905 A CN201610976905 A CN 201610976905A CN 106503239 A CN106503239 A CN 106503239A
- Authority
- CN
- China
- Prior art keywords
- legal
- semantic feature
- provision
- laws
- key element
- 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 58
- 230000008878 coupling Effects 0.000 claims abstract description 83
- 238000010168 coupling process Methods 0.000 claims abstract description 83
- 238000005859 coupling reaction Methods 0.000 claims abstract description 83
- 238000000605 extraction Methods 0.000 claims abstract description 36
- 238000009223 counseling Methods 0.000 claims description 53
- 230000013011 mating Effects 0.000 claims description 35
- 238000001914 filtration Methods 0.000 claims description 20
- 230000004044 response Effects 0.000 claims description 17
- 239000013589 supplement Substances 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 3
- 206010068052 Mosaicism Diseases 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 claims 1
- 210000003765 sex chromosome Anatomy 0.000 claims 1
- 230000007246 mechanism Effects 0.000 description 8
- 239000000284 extract Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/243—Natural language query formulation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Physics (AREA)
- Technology Law (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Machine Translation (AREA)
Abstract
The present invention provides a kind of method and apparatus of legal information inquiry, and methods described includes:Legal Knowledge Base is provided, the Legal Knowledge Base includes legal provision, and every legal provision is associated with corresponding laws and regulations key element;Nature semantic feature extraction is carried out to legal advice problem, to obtain the corresponding natural semantic feature of the legal advice problem;Judge the legal provision with the presence or absence of coupling in the Legal Knowledge Base so that the corresponding natural semantic feature of legal advice problem laws and regulations key element corresponding with the legal provision of the coupling matches;If existing, the legal provision of the coupling is exported.Described device is corresponding with methods described.
Description
Technical field
The present invention relates to a kind of method and apparatus of legal information inquiry, more particularly to one kind is according to legal advice problem,
The method and apparatus for providing corresponding law.
Background technology
Taking database retrieval mode to realize existing laws and regulations consultancy service, there is provided two dimensions of keyword and descriptor more
The fuzzy query of degree, directory, field inquiry, classified inquiry and mechanism's inquiry.Functionally with simple question and answer, keyword match
Based on, lack semantic fault-tolerant understanding mechanism;In service based on the access of webpage word, it is impossible to support complicated legal advice, case
Mutual affection analysis, legal retrieval service scenarios.When user's counseling problem is not detailed enough, it is impossible to provide legal provision exactly, or even
Corresponding legal provision cannot be given because of the legal issue of None- identified user.
Content of the invention
It is an object of the invention to provide a kind of method and apparatus of legal information inquiry, overcomes of the prior art asking
Topic, can accurate assurance customer problem, and then provide correct legal provision, improve accuracy rate when legal information is inquired about.
According to above-mentioned purpose, the present invention provides a kind of method of legal information inquiry, including:
Legal Knowledge Base is provided, the Legal Knowledge Base includes legal provision, and every legal provision is associated with corresponding
Laws and regulations key element;Nature semantic feature extraction is carried out to legal advice problem, corresponding to obtain the legal advice problem
Natural semantic feature;Judge the legal provision with the presence or absence of coupling in the Legal Knowledge Base so that the legal advice problem
Corresponding natural semantic feature laws and regulations key element corresponding with the legal provision of the coupling matches;If existing, export
The legal provision of the coupling.
In one embodiment, include the step of the judgement:By corresponding for the legal advice problem natural semantic feature
Laws and regulations key element is mapped to, as the corresponding laws and regulations key element of legal advice problem;Judge in the Legal Knowledge Base be
The no legal provision that there is coupling so that the corresponding laws and regulations key element of the legal advice problem and the law bar for mating
The corresponding laws and regulations key element of text matches.
In one embodiment, include the step of the judgement:Judge to whether there is in the Legal Knowledge Base and mate completely
Legal provision so that the corresponding natural semantic feature of the legal advice problem is corresponding with the legal provision for mating completely
Laws and regulations key element mate completely;If exist, the step of the output in export the legal provision for mating completely.
In one embodiment, also include the step of the judgement:If the legal provision not mated completely, judges whether
There is the legal provision of part coupling so that the corresponding natural semantic feature of the legal advice problem is mated with the part
A part for the corresponding laws and regulations key element of legal provision matches;If existing, the step of the output in output described
The legal provision of part coupling.
In one embodiment, also include the step of the judgement:If the legal provision not mated completely, judges whether
There is the legal provision of part coupling so that the corresponding natural semantic feature of the legal advice problem is mated with the part
A part for the corresponding laws and regulations key element of legal provision matches;If existing, methods described also includes:According to the part
The laws and regulations key element being not matched in the legal provision of coupling, generates rhetorical question problem and is asked in reply;And rhetorical question is obtained
Answer carry out nature semantic feature extraction, with obtain supplement natural semantic feature;Wherein, also wrap the step of the judgement
Include:The laws and regulations not being matched in the legal provision that the natural semantic feature of the supplement is mated are judged with the part
Whether key element mates completely;If mating completely, the step of the output in export the legal provision for mating completely.
In one embodiment, the laws and regulations being not matched in the legal provision according to part coupling will
Element, generation rhetorical question problem carries out rhetorical question to be included:The laws and regulations being not matched in the legal provision that the part is mated will
Element is combined into selective problems and is asked in reply.
In one embodiment, methods described also includes:Before natural semantic feature extraction step, to the legal advice
Problem carries out pretreatment, and the pretreatment includes that illegal word is filtered, sews filtration in front and back, stops word filtration and/or phonetic filtration;Described
Natural semantic feature extraction step is to carry out nature semantic feature extraction to pretreated legal advice problem.
In one embodiment, methods described also includes:The Legal Knowledge Base is expansible data base, is led with receive user
Other law databases for entering.
In one embodiment, the Legal Knowledge Base includes multiple sons that is classified according to region and/or law classification
Storehouse, the judgement step include:According to region and/or the law classification of the legal advice problem, in corresponding region and/or
The judgement that there is the legal provision for mating is made whether in law classification character library.
In one embodiment, methods described also includes:If the legal advice problem is voice messaging, by the voice
Information is converted into Word message, so that natural semantic feature is extracted.
In one embodiment, methods described also includes:History counseling problem storehouse is provided, in the history counseling problem storehouse
Every history counseling problem is associated with corresponding natural semantic feature;Judge in the history counseling problem storehouse, to whether there is phase
The history counseling problem of coupling so that the corresponding natural semantic feature of user input problem is asked with the history consulting for matching
Inscribe corresponding natural semantic feature coupling;If existing, the history counseling problem for matching is exported, selected for user.
In one embodiment, the legal advice problem is obtained by following at least one mode:Wechat, webpage, application
Software, phone, note, tangible machine people and independently seek advice from terminal.
Corresponding said method, the present invention also provide a kind of device of legal information inquiry, and described device includes:Legal knowledge
Storehouse, the Legal Knowledge Base include legal provision, and every legal provision is associated with corresponding laws and regulations key element;Naturally semantic
Elements recognition module, for carrying out nature semantic feature extraction to legal advice problem, to obtain the legal advice problem pair
The natural semantic feature that answers;Matching module, for judging the legal provision in the Legal Knowledge Base with the presence or absence of coupling so that
The corresponding natural semantic feature of legal advice problem laws and regulations key element phase corresponding with the legal provision of the coupling
Match somebody with somebody;Output module, for the legal provision in response to there is coupling in the Legal Knowledge Base, then exports the law of the coupling
Provision.
In one embodiment, the matching module includes:Mapping submodule, for will be corresponding for the legal advice problem
Natural semantic feature is mapped to laws and regulations key element, used as the corresponding laws and regulations key element of legal advice problem;Judging submodule,
For judging the legal provision in the Legal Knowledge Base with the presence or absence of coupling so that the corresponding law of the legal advice problem
Regulation key element laws and regulations key element corresponding with the legal provision of the coupling matches.
In one embodiment, the matching module is further used for judging to whether there is complete in the Legal Knowledge Base
The legal provision that matches somebody with somebody so that the corresponding natural semantic feature of the legal advice problem and the legal provision pair for mating completely
The laws and regulations key element that answers is mated completely;The output module is further used in response to existing completely in the Legal Knowledge Base
The legal provision of coupling, then export the legal provision for mating completely.
In one embodiment, the matching module is further used in response to the legal provision not mated completely, then sentencing
The disconnected legal provision with the presence or absence of part coupling so that the corresponding natural semantic feature of the legal advice problem and the part
A part for the corresponding laws and regulations key element of the legal provision of coupling matches;The output module is further used in response to institute
The legal provision that there is part coupling in Legal Knowledge Base is stated, then exports the legal provision of the part coupling.
In one embodiment, the matching module is further used in response to the legal provision not mated completely, then sentencing
The disconnected legal provision with the presence or absence of part coupling so that the corresponding natural semantic feature of the legal advice problem and the part
A part for the corresponding laws and regulations key element of the legal provision of coupling matches;Described device also includes:Rhetorical question module, for root
According to the laws and regulations key element being not matched in the legal provision that the part is mated, generate rhetorical question problem and asked in reply;Described
Natural semantic feature extraction module is additionally operable to carry out nature semantic feature extraction to the answer that obtains of rhetorical question, with obtain supplement from
Right semantic feature;The matching module is further used for judging the method that the natural semantic feature of the supplement is mated with the part
Whether the laws and regulations key element not being matched in rule provision mates completely;The output module is further used in response to institute
It is complete that the laws and regulations key element not being matched in the legal provision that supplementary natural semantic feature is mated is stated with the part
Coupling, then export the legal provision for mating completely.
In one embodiment, the rhetorical question module includes:Composite module, in the legal provision that mates the part
The laws and regulations factor combination being not matched to is asked in reply into selective problems.
In one embodiment, described device also includes:Pretreatment module is for before natural semantic feature is extracted, right
The legal advice problem carries out pretreatment, the pretreatment include illegal word filter, sew filtrations in front and back, stop word filtration and/or
Phonetic is filtered;The natural semantic feature extraction module carries out nature semantic feature to pretreated legal advice problem and carries
Take.
In one embodiment, described device also includes:Expansion interface, for other law data that receive user is imported
Storehouse.
In one embodiment, the Legal Knowledge Base includes multiple sons that is classified according to region and/or law classification
Storehouse, described device also include:Sort module, for recognizing region and/or the law classification of the legal advice problem;Described
With region and/or law classification that module is further used for responding the legal advice problem, in corresponding region and/or law
The judgement that there is the legal provision for mating is made whether in classification character library.
In one embodiment, described device also includes:Voice conversion module, in response to the legal advice problem being
Voice messaging, then by the converting voice message into text message, so that natural semantic feature is extracted.
In one embodiment, described device also includes:History counseling problem storehouse, in the history counseling problem storehouse per bar
History counseling problem is associated with corresponding natural semantic feature;Trouble-shoots module, for judging the history counseling problem
With the presence or absence of the history counseling problem for matching in storehouse so that the corresponding natural semantic feature of user input problem and the phase
The corresponding natural semantic feature coupling of the history counseling problem matched somebody with somebody;Problem output module, for responding the history counseling problem
There is the history counseling problem for matching in storehouse, then export the history counseling problem for matching, select for user.
In one embodiment, described device also includes:Counseling problem acquisition module, for passing through following at least one side
Formula:Wechat, webpage, application software, phone, note, tangible machine people and autonomous consulting terminal obtain the legal advice problem.
As described above, the method and apparatus that the legal information that the present invention is provided is inquired about, with rhetorical question mechanism, being capable of same user
Interaction, and complete legal advice problem is obtained, and then provide accurate legal provision.
Description of the drawings
The flow chart that Fig. 1 shows the method for the legal information inquiry of one aspect of the invention;
Fig. 2 shows the method flow diagram under coupling and part match condition completely;
Fig. 3 shows the method flow diagram of rhetorical question mechanism;
Fig. 4 shows the structure chart of the device of the legal information inquiry of one aspect of the invention.
Specific embodiment
The present invention is based on the natural semantic feature in natural semantic feature extractive technique extraction problem, and then decision problem
Natural semantic feature and the laws and regulations key element matching degree of law, while provide so semanteme fault tolerant mechanism, prolongable external number
According to interface.For counseling problem there may be incomplete situation, the core of the present invention is to provide rhetorical question mechanism, to have obtained
Kind counseling problem, and then provide accurate legal provision.Additionally, the present invention is also supported:Wechat, webpage, application software, electricity
The acquisition channel of words, note, tangible machine people and autonomous consulting terminal as counseling problem.
The method of legal information inquiry of the present invention is provided with Legal Knowledge Base, Legal Knowledge Base and includes numerous law bars
Text, Legal Knowledge Base can be existing code, local regulation etc., according to different clients seek be customized.
Laws and regulations elements recognition is carried out to the legal provision in Legal Knowledge Base in advance, each legal provision is obtained corresponding
Laws and regulations key element, can will extract the laws and regulations key element that obtains and also be stored in Legal Knowledge Base.Here method law
The dialect that rule key element refers mainly in legal field, for example naturally semantic in " house ", corresponding in legal field is " no
Movable property ", and real estate is exactly laws and regulations key element.It is legal language due to necessarily included in law, in consideration of it, law
Keyword is exactly the laws and regulations key element of law.As long as can so extract the keyword of law, then can obtain law corresponding
Laws and regulations key element.Visible in prior art, method law is directly carried out to the law in code or regulation by manual type
The extraction of rule key element.Have in prior art simultaneously much carries out the technology of keyword extraction to text, mainly includes TF-IDF (words
Frequently-inverse document frequency), Topic-Model (theme-model) scheduling algorithm, key word is carried out to law with these algorithms and is carried
Take and can be obtained by the corresponding laws and regulations key element of law.
The basic thought of TF-IDF is:Judge whether a word is important in an article, a measurement being readily apparent that
Index is exactly word frequency, and important word often repeatedly occurs in article.But then, it is not word more than occurrence number with regard to one
Fixed important, because some words are all frequently occurred in various articles, its importance is certainly not as those are only in certain article
In the word importance that frequently occurs strong.From statistical angle, those uncommon words are exactly given with larger weight, and subtracted
The weight of few common word.IDF (inverse document frequency) is exactly this weight, and TF then refers to word frequency.
And Topic-Model then thinks that article is made up of theme, word in article is selected from theme with certain probability
Take.Under different themes, the probability distribution that word occurs is different.Such as " torpedo " word, goes out under " military affairs " theme
Existing probability is much larger than the probability occurred under " food " theme.That is Topic-Model thinks also have one between document and word
Layer relation.
Refer to Fig. 1, the flow chart that Fig. 1 shows the method for the legal information inquiry of one aspect of the invention.The side
Method includes:
101:Nature semantic feature extraction is carried out to legal advice problem, corresponding certainly to obtain the legal advice problem
Right semantic feature;
102:Judge the legal provision with the presence or absence of coupling in the Legal Knowledge Base so that the legal advice problem pair
The natural semantic feature that answers laws and regulations key element corresponding with the legal provision of the coupling matches;
103:If existing, the legal provision of the coupling is exported.
Step 101 carries out nature semantic feature extraction to legal advice problem, actually or directly uses aforesaid key
Keyword extraction in legal advice problem out, that is, is obtained word extractive technique nature semantic feature.Just it has been observed that a lot of feelings
Under condition, user directly can be putd question to " house " this kind of popular language, and non-immediate is retouched with as real estate
State.
Step 102 is that the corresponding natural semantic feature description of decision problem and the corresponding laws and regulations of legal provision want sketch
The matching degree that states, after both mate, represents the asked a question legal provision for having corresponded to correlation of user, then in step 103
Provide corresponding legal provision.
In one embodiment, the judge process of step 102 also includes step:
A) corresponding for the legal advice problem natural semantic feature is mapped to laws and regulations key element, as legal advice
The corresponding laws and regulations key element of problem;
B) judge the legal provision with the presence or absence of coupling in the Legal Knowledge Base so that the legal advice problem is corresponding
Corresponding with the legal provision of the coupling laws and regulations key element of laws and regulations key element match.
Step a) is that the natural semantic feature " house " of the problem in previous example is mapped to laws and regulations key element is " motionless
Produce " the corresponding laws and regulations key element real estate of problem is obtained, the corresponding laws and regulations key element of step b) decision problems is " motionless
Produce " whether can match the corresponding laws and regulations key element real estate of law in Legal Knowledge Base.Mapping in step 1021
Step can be realized by mapping database of the prior art, also can be realized by human translation.The coupling of indication in Fig. 1
Include two kinds of situations:Coupling and part are mated completely.
In one embodiment, Fig. 2 specifically refer to, and methods described comprises the steps:
200:Input matching degree;
201:The legal provision for mating completely is judged whether, step 202 is entered if existing, otherwise enter step
203;
202:The legal provision for mating completely is given, step 205 is entered;
203:The legal provision of part coupling is judged whether, step 204 is entered if existing, otherwise enter step
205;
204:The legal provision of part coupling is given, step 205 is entered;
205:Terminate.
In one embodiment, corresponding for legal advice problem laws and regulations key element is found by mapping relations first.This
In the case of kind, coupling includes two kinds of situations completely:First, all laws and regulations key elements of counseling problem have all uniquely corresponded to law
Laws and regulations key element, all laws and regulations key elements of law have also all uniquely corresponded to the laws and regulations key element of counseling problem, exist
One-to-one relation;2nd, all of laws and regulations key element of law is included in problem laws and regulations key element, but problem also has
Other laws and regulations key elements are not comprised in law laws and regulations key element.Same part coupling also includes two kinds of situations:First, consult
Inquiry is inscribed all laws and regulations key elements and is included in law laws and regulations key element, but has or not in law laws and regulations key element
The part covered by problem laws and regulations key element;2nd, laws and regulations key element in counseling problem part includes law part laws and regulations
Have the part covered by problem laws and regulations key element in key element, but law laws and regulations key element or not.
The corresponding laws and regulations key element of such as one counseling problem is (A, B, C, D, E, F, G), if depositing in Legal Knowledge Base
Also it is just (A, B, C, D, E, F, G) in the corresponding laws and regulations key element of law, then this coupling is just for mating completely.Or
Person, there is the corresponding laws and regulations key element of law is (B, C, D, E, F), then this coupling is also to mate completely.If law
There is one (A, B, C, D, E, F, G, H, I) in knowledge base, then have (H, the I) being matched in law or not, and this is exactly portion
Divide the situation of coupling.If there is the legal provision of (C, D, E, F, G, H, I, J, K), wherein there is (C, D, E, F, G)
Match somebody with somebody, and (H, I, J, the K) in legal provision is not matched to, such case is also part coupling.In a word, when in legal provision
It is then to mate when laws and regulations key element is matched entirely completely, will if there are the laws and regulations being not matched in legal provision
Element, then be the situation of part coupling.
In another preferred embodiment, also include rhetorical question mechanism when the situation that there is preceding sections coupling.Refer to figure
3, step is as follows:
301:The laws and regulations key element being not matched in legal provision according to part coupling, generates rhetorical question problem
Asked in reply;
302:Nature semantic feature extraction is carried out to the answer that rhetorical question is obtained, to obtain the natural semantic feature of supplement;
303:Judge not to be matched in the legal provision that the natural semantic feature of the supplement is mated with the part
Laws and regulations key element whether mate completely, if mating completely enter step 304, otherwise enter step 305;
304:The legal provision that output is mated completely;
305:Terminate.
The purpose of rhetorical question is the content for being more fully to obtain counseling problem such that it is able to more targetedly give
Go out corresponding law, the process of rhetorical question is exactly constantly to improve the process of problem content.When supplementary problem content, (problem is corresponding
Natural semantic feature) when more to can correspond in corresponding law enough, provide corresponding law.
In a preferred embodiment, will in the legal provision of part coupling the laws and regulations factor combination that is not matched to into
Selective problems are asked in reply.And then previous example, if the corresponding laws and regulations key element of legal advice problem for (A, B, C, D,
E, F, G), the legal provision of part coupling has two, the corresponding laws and regulations key element of provision for (A, B, C, D, E, F, G,
H), the corresponding laws and regulations key element of another provision is (A, B, C, D, E, F, G, I), then will by the laws and regulations not being matched
Plain (H), (I) generate selective problems, that is, generate similar " may I ask you and refer to H or I ", if the rhetorical question for obtaining is answered as " H "
The legal provision output of (A, B, C, D, E, F, G, H) will be corresponded to.
In another preferred embodiment, before natural semantic feature extraction step, pre- place is carried out to legal advice problem
Reason, here pretreatment include that illegal word is filtered, sews filtration in front and back, stops word filtration and/or phonetic filtration.Then, then law is carried out
Regulation elements recognition, coupling etc. are operated.The purpose of the pretreatment is counseling problem content itself not to be anticipated in order to filter out
The part of justice, and then the laws and regulations key element for enabling to extract contains the content that user really wants to ask.
Illegal word refers to some sensitive vocabulary, against law or the content of morals, has had now a lot of illegal words to stop
Dictionary is available, and from dictionary is arbitrarily stopped, control can carry out the word that stops of illegal word and filter.
It is all to filter out the word in text without practical significance to sew filtration in front and back and stop word to filter, and sews filtration master in front and back
If filtering out some adverbial words, adjective etc..Stop word to filter is to stop dictionary by existing, compares the mistake for completing meaningless word
Filter.
Phonetic filtration is referred to and filters out the pinyin character of user's erroneous input, or is translated directly into by dictionary corresponding
Word.
In a preferred embodiment, the Legal Knowledge Base that the present invention is provided is expansible data base, is imported with receive user
Other law databases.This makes it possible to adapt to law, regulation change, or the situation of newly-increased laws and regulations.
As each local law, regulation are it is possible that difference, the also phase not to the utmost of the law classification needed for each user
With in a preferred embodiment, Legal Knowledge Base that the present invention is provided includes multiple carrying out point according to region and/or law classification
The word bank of class, according to different user problem category, is made whether there is coupling in corresponding region and/or law classification character library
Legal provision judgement.Data base's cost is this reduces, while greatly reducing operand when carrying out matching operation.
In a preferred embodiment, if the legal advice problem of user input is voice messaging, voice messaging is changed
For Word message.At present to turn text technology quite ripe for voice, in actual applications can directly will be embedded for algorithm of the invention
In method.
User be input into problem when possibly cannot know for sure the problem of oneself should include which natural semantic feature and
Content, in another preferred embodiment, the problem that user was once asked by the present invention is stored in history as historic user question sentence
In counseling problem storehouse, during user input problem, the problem nature semantic feature that user has been input into is used with history
The corresponding natural semantic feature of historic user question sentence in the question sentence storehouse of family carries out real-time matching, can use aforesaid key word in advance
Extractive technique, corresponding for historic user question sentence in historic user question sentence storehouse natural semantic feature is all extracted, and is preserved
In historic user question sentence storehouse..When finding to exist the historic user question sentence that matches in historic user question sentence storehouse, then export phase
The history counseling problem that matches somebody with somebody, selects for user, and user need to only select to confirm which wants the problem that asks, both improve user's body
Test, turn avoid when customer problem content not enough comprehensively when that may be present law cannot be provided, or need constantly rhetorical question user
The situation of law can be just given.For example, exist in history question sentence storehouse natural semantic feature that history question sentence includes for (A, B,
C, D, E, F), the natural semantic feature that another history question sentence includes is (M, B, Q, D, F), then as user input (B, D), by
(B, D) is all contained in (A, B, C, D, E, F) and (M, B, Q, D, F), then by above-mentioned come two history question sentences recommend out for
Family selects.In another case, user has directly inputted the question sentence comprising nature semantic feature (A, B, C, D, E, F), goes through together
The natural semantic feature of a historic user question sentence in history user's question sentence storehouse is mated completely, now pushes away this historic user question sentence
Recommend out and confirm for user.
Corresponding a kind of aforementioned method of legal information inquiry, the present invention also provide a kind of device of legal information inquiry, please
Referring to Fig. 4, Fig. 4 shows the structure chart of one embodiment of device of legal information inquiry of the present invention.Device 400 includes:Natural language
Adopted elements recognition module 401, matching module 402 and output module 403.Legal advice problem input nature semantic feature is extracted
Module 401, and the corresponding natural semantic feature of law counseling problem is extracted, by the legal advice problem nature semantic feature that extracts
Input matching module 402, matching module 402 based on the corresponding laws and regulations key element of the legal provision in Legal Knowledge Base,
Carry out matching degree computing.If there is legal provision and the legal advice for matching, the output of output module 403 is allowed to match
Legal provision, in this embodiment, described match including aforesaid complete match condition or part match condition.
The matching module 402 can include:
Mapping submodule, will for corresponding for the legal advice problem natural semantic feature is mapped to laws and regulations
Element, used as the corresponding laws and regulations key element of legal advice problem;
Judging submodule, for judging the legal provision in the Legal Knowledge Base with the presence or absence of coupling so that the method
The corresponding laws and regulations key element of rule counseling problem laws and regulations key element corresponding with the legal provision of the coupling matches.
In one example, the matching module is further used for judging to whether there is complete in the Legal Knowledge Base
The legal provision that matches somebody with somebody so that the corresponding natural semantic feature of the legal advice problem and the legal provision pair for mating completely
The laws and regulations key element that answers is mated completely;
The output module is further used in response to there is the legal provision for mating completely in the Legal Knowledge Base, then
The output legal provision for mating completely.
In another example, the matching module is further used for the legal provision in response to not mating completely, then
Judge whether the legal provision of part coupling so that the corresponding natural semantic feature of the legal advice problem and the portion
A part for the corresponding laws and regulations key element of the legal provision for mating is divided to match;
The output module is further used for the legal provision in response to there is part coupling in the Legal Knowledge Base, then
Export the legal provision of the part coupling.
In a preferred embodiment, device 400 also includes asking in reply module 404, when matching module 402 carries out matching operation
When as a result mating for part, asking in reply the laws and regulations being not matched in legal provision of the module 404 then according to part coupling will
Element, generates rhetorical question problem and is asked in reply.In this embodiment, natural semantic feature extraction module 401 is additionally operable to obtain rhetorical question
Answer carries out nature semantic feature extraction, and to obtain the natural semantic feature of supplement, matching module 402 is further used for judging to mend
Whether the laws and regulations key element not being matched in the legal provision that the natural semantic feature that fills is mated with part mates completely,
If the laws and regulations key element not being matched in the legal provision that the natural semantic feature that supplements is mated with part is mated completely,
Output module 403 exports the legal provision for mating completely.
In another embodiment, device 400 also includes composite module 4041, for the legal provision for mating the part
In the laws and regulations factor combination that is not matched to asked in reply into selective problems, the combined method of selective problems herein
Same preceding method.
In another embodiment, device 400 also includes pretreatment module 405, natural semantic feature extraction module 401 it
Before, illegal word filtration is carried out to legal advice problem, is sewed filtration in front and back, is stopped the pretreatment operations such as word is filtered, phonetic is filtered, then
401 pairs of legal advice problems through pretreatment of natural semantic feature extraction module carry out nature semantic feature extraction.
More preferably, described device also includes expansion interface, for other law databases that receive user is imported.
Additionally, the Legal Knowledge Base can include multiple word banks that is classified according to region and/or law classification, institute
Stating device also includes sort module, for recognizing region and/or the law classification of the legal advice problem, and then can basis
The region of legal advice problem and/or law classification, respectively enteing different Legal Knowledge Base character libraries carries out the inquiry of law.
In one embodiment, described device also includes voice conversion module, when user input is voice messaging, is converted into
Word message, provides basis for operations such as follow-up natural extraction of semantics extraction, couplings.
More preferably, in order to preferably obtain customer problem, and Consumer's Experience is improved.Described device also includes:History is seeked advice from
Problem base, trouble-shoots module and problem output module.History counseling problem storehouse contains the historical problem that user once asked;
Whether Already in trouble-shoots module, for the problem in historical problem storehouse of real-time searching user input;If existing, make
The historical problem is exported with problem output module.
The acquisition modes of legal advice problem cover multiple channel of the prior art, and such as wechat, webpage, application are soft
Part, phone, note, tangible machine people and autonomous consulting terminal etc., the equipment also includes counseling problem acquisition module, for
Law counseling problem is obtained in above-mentioned channel.
The present invention extracts the natural semantic feature in law counseling problem, and the laws and regulations key element with law is mated
Computing, provides corresponding law if coupling.The invention allows for problem rhetorical question mechanism, can more intelligently obtain user's
Counseling problem information, and then can more accurately provide corresponding legal provision.Meanwhile, the function of question sentence intelligent recommendation, greatly
Consumer's Experience is improve greatly.
It is for so that any person skilled in the art can all make or using this public affairs to provide of this disclosure being previously described
Open.Various modifications of this disclosure all will be apparent for a person skilled in the art, and as defined herein general
Suitable principle can be applied to spirit or scope of other variants without departing from the disclosure.Thus, the disclosure is not intended to be limited
Due to example described herein and design, but should be awarded and principle disclosed herein and novel features phase one
The widest scope of cause.
Claims (24)
1. a kind of method that legal information is inquired about, including:
Legal Knowledge Base is provided, the Legal Knowledge Base includes legal provision, and every legal provision is associated with corresponding law
Regulation key element;
Nature semantic feature extraction is carried out to legal advice problem, will to obtain the corresponding semanteme naturally of the legal advice problem
Element;
Judge the legal provision with the presence or absence of coupling in the Legal Knowledge Base so that the corresponding nature of the legal advice problem
Semantic feature laws and regulations key element corresponding with the legal provision of the coupling matches;
If existing, the legal provision of the coupling is exported.
2. the method for claim 1, it is characterised in that include the step of the judgement:
Corresponding for the legal advice problem natural semantic feature is mapped to laws and regulations key element, as legal advice problem pair
The laws and regulations key element that answers;
Judge the legal provision with the presence or absence of coupling in the Legal Knowledge Base so that the corresponding law of the legal advice problem
Regulation key element laws and regulations key element corresponding with the legal provision of the coupling matches.
3. the method for claim 1, it is characterised in that include the step of the judgement:
Judge in the Legal Knowledge Base with the presence or absence of the legal provision for mating completely so that the legal advice problem is corresponding
Natural semantic feature laws and regulations key element corresponding with the legal provision for mating completely is mated completely;
If exist, the step of the output in export the legal provision for mating completely.
4. method as claimed in claim 3, it is characterised in that also include the step of the judgement:
If the legal provision not mated completely, the legal provision of part coupling is judged whether so that the law is consulted
A part of phase of corresponding natural semantic feature laws and regulations key element corresponding with the legal provision that the part is mated is inscribed in inquiry
Coupling;
If existing, the step of the output in export the legal provision of part coupling.
5. method as claimed in claim 3, it is characterised in that also include the step of the judgement:
If the legal provision not mated completely, the legal provision of part coupling is judged whether so that the law is consulted
A part of phase of corresponding natural semantic feature laws and regulations key element corresponding with the legal provision that the part is mated is inscribed in inquiry
Coupling;
If existing, methods described also includes:
The laws and regulations key element being not matched in legal provision according to part coupling, generating rhetorical question problem is carried out instead
Ask;And
Nature semantic feature extraction is carried out to the answer that rhetorical question is obtained, to obtain the natural semantic feature of supplement;
Wherein, also include the step of the judgement:
The method law not being matched in the legal provision that the natural semantic feature of the supplement is mated is judged with the part
Whether rule key element mates completely;
If mating completely, the step of the output in export the legal provision for mating completely.
6. method as claimed in claim 5, it is characterised in that do not have in the legal provision according to part coupling
The laws and regulations key element being fitted on, generation rhetorical question problem carries out rhetorical question to be included:
The laws and regulations factor combination being not matched in the legal provision that the part is mated is carried out instead into selective problems
Ask.
7. the method for claim 1, it is characterised in that methods described also includes:
Before natural semantic feature extraction step, pretreatment is carried out to the legal advice problem, the pretreatment includes non-
Method word is filtered, sews filtration in front and back, stops word filtration and/or phonetic filtration;
The natural semantic feature extraction step is to carry out nature semantic feature extraction to pretreated legal advice problem.
8. the method for claim 1, it is characterised in that methods described also includes:
The Legal Knowledge Base is expansible data base, with other law databases that receive user is imported.
9. the method for claim 1, the Legal Knowledge Base include multiple carrying out point according to region and/or law classification
The word bank of class, it is characterised in that the judgement step includes:
According to region and/or the law classification of the legal advice problem, enter in corresponding region and/or law classification character library
Judgement of the row with the presence or absence of the legal provision of coupling.
10. the method for claim 1, it is characterised in that methods described also includes:
If the legal advice problem is voice messaging, by the converting voice message into text message, for natural semanteme
Elements recognition.
11. the method for claim 1, it is characterised in that methods described also includes:
History counseling problem storehouse is provided, every history counseling problem in the history counseling problem storehouse is associated with oneself corresponding
Right semantic feature;
Judge in the history counseling problem storehouse with the presence or absence of the history counseling problem for matching so that user input problem is corresponding
Corresponding with the history counseling problem for the matching natural semantic feature coupling of natural semantic feature;
If existing, the history counseling problem for matching is exported, selected for user.
12. the method for claim 1, it is characterised in that
The legal advice problem is obtained by following at least one mode:Wechat, webpage, application software, phone, note, reality
Body robot and autonomous consulting terminal.
13. a kind of devices of legal information inquiry, it is characterised in that described device includes:
Legal Knowledge Base, the Legal Knowledge Base include legal provision, and every legal provision is associated with corresponding laws and regulations
Key element;
Natural semantic feature extraction module, for carrying out nature semantic feature extraction to legal advice problem, to obtain the method
The corresponding natural semantic feature of rule counseling problem;
Matching module, for judging the legal provision in the Legal Knowledge Base with the presence or absence of coupling so that the legal advice
The corresponding natural semantic feature of problem laws and regulations key element corresponding with the legal provision of the coupling matches;
Output module, for the legal provision in response to there is coupling in the Legal Knowledge Base, then exports the method for the coupling
Rule provision.
14. devices as claimed in claim 13, it is characterised in that the matching module includes:
Mapping submodule, for corresponding for the legal advice problem natural semantic feature is mapped to laws and regulations key element, makees
For the corresponding laws and regulations key element of legal advice problem;
Judging submodule, for judging the legal provision in the Legal Knowledge Base with the presence or absence of coupling so that the law is consulted
Inquiry is inscribed corresponding laws and regulations key element laws and regulations key element corresponding with the legal provision of the coupling and is matched.
15. devices as claimed in claim 13, it is characterised in that
The matching module is further used for judging in the Legal Knowledge Base with the presence or absence of the legal provision for mating completely so that
The corresponding natural semantic feature of legal advice problem laws and regulations key element corresponding with the legal provision for mating completely
Mate completely;
The output module is further used in response to there is the legal provision for mating completely in the Legal Knowledge Base, then exporting
The legal provision for mating completely.
16. devices as claimed in claim 15, it is characterised in that
The matching module is further used for the legal provision in response to not mating completely, then judge whether that part is mated
Legal provision so that the corresponding natural semantic feature of the legal advice problem is corresponding with the legal provision that the part is mated
The part of laws and regulations key element match;
The output module is further used in response to the legal provision that there is part coupling in the Legal Knowledge Base, then exporting
The legal provision of the part coupling.
17. devices as claimed in claim 15, it is characterised in that
The matching module is further used for the legal provision in response to not mating completely, then judge whether that part is mated
Legal provision so that the corresponding natural semantic feature of the legal advice problem is corresponding with the legal provision that the part is mated
The part of laws and regulations key element match;
Described device also includes:
Rhetorical question module, for the laws and regulations key element being not matched in the legal provision that mate according to the part, generates instead
Ask questions and asked in reply;
The natural semantic feature extraction module is additionally operable to carry out nature semantic feature extraction to the answer that rhetorical question is obtained, to obtain
Supplementary natural semantic feature;
The matching module is further used for judging the legal provision that the natural semantic feature of the supplement is mated with the part
In the laws and regulations key element that is not matched whether mate completely;
The output module is further used for the law bar mated in response to the natural semantic feature of the supplement with the part
The laws and regulations key element not being matched in text is mated completely, then export the legal provision for mating completely.
18. devices as claimed in claim 17, it is characterised in that the rhetorical question module includes:
Composite module, for the laws and regulations factor combination that is not matched in the legal provision that mates the part into selection
Sex chromosome mosaicism is asked in reply.
19. devices as claimed in claim 13, it is characterised in that described device also includes:
Pretreatment module, for, before natural semantic feature is extracted, carrying out pretreatment to the legal advice problem, described pre-
Processing includes that illegal word is filtered, sews filtration in front and back, stops word filtration and/or phonetic filtration;
The natural semantic feature extraction module carries out nature semantic feature extraction to pretreated legal advice problem.
20. devices as claimed in claim 13, it is characterised in that described device also includes:
Expansion interface, for other law databases that receive user is imported.
21. devices as claimed in claim 13, it is characterised in that the Legal Knowledge Base include multiple according to region and/or
The word bank classified by law classification, described device also include:
Sort module, for recognizing region and/or the law classification of the legal advice problem;
The matching module is further used for region and/or the law classification for responding the legal advice problem, accordingly
The judgement that there is the legal provision for mating is made whether in domain and/or law classification character library.
22. devices as claimed in claim 13, it is characterised in that described device also includes:
The voice messaging for being voice messaging in response to the legal advice problem, is then converted into by voice conversion module
Word message, so that natural semantic feature is extracted.
23. devices as claimed in claim 13, it is characterised in that described device also includes:
History counseling problem storehouse, every history counseling problem in the history counseling problem storehouse are associated with corresponding natural language
Adopted key element;
Trouble-shoots module, for judging in the history counseling problem storehouse with the presence or absence of the history counseling problem for matching, makes
Obtain the corresponding natural semantic feature of user input problem natural semantic feature corresponding with the history counseling problem for matching
Coupling;
, there is the history counseling problem for matching in the history counseling problem storehouse for responding, then export in problem output module
The history counseling problem for matching, selects for user.
24. devices as claimed in claim 12, it is characterised in that described device also includes:
Counseling problem acquisition module, for by following at least one mode:Wechat, webpage, application software, phone, note, reality
Body robot and autonomous consulting terminal obtain the legal advice problem.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610976905.1A CN106503239A (en) | 2016-11-07 | 2016-11-07 | A kind of method and apparatus of legal information inquiry |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610976905.1A CN106503239A (en) | 2016-11-07 | 2016-11-07 | A kind of method and apparatus of legal information inquiry |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106503239A true CN106503239A (en) | 2017-03-15 |
Family
ID=58323225
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610976905.1A Pending CN106503239A (en) | 2016-11-07 | 2016-11-07 | A kind of method and apparatus of legal information inquiry |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106503239A (en) |
Cited By (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107169896A (en) * | 2017-04-13 | 2017-09-15 | 甘肃建筑职业技术学院 | A kind of legal services system based on Internet technology |
CN107220912A (en) * | 2017-06-12 | 2017-09-29 | 上海市高级人民法院 | Litigation services intelligence system and robot |
CN107330071A (en) * | 2017-06-30 | 2017-11-07 | 北京神州泰岳软件股份有限公司 | A kind of legal advice information intelligent replies method and platform |
CN107423374A (en) * | 2017-07-06 | 2017-12-01 | 武汉康慧然信息技术咨询有限公司 | Law based on classification annotation recommends method and system |
CN107894981A (en) * | 2017-12-13 | 2018-04-10 | 武汉烽火普天信息技术有限公司 | A kind of automatic abstracting method of case semantic feature |
CN108073569A (en) * | 2017-06-21 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of law cognitive approach, device and medium based on multi-layer various dimensions semantic understanding |
CN108595415A (en) * | 2018-03-26 | 2018-09-28 | 北京北大英华科技有限公司 | A kind of law differentiation determination method, device and computer equipment, storage medium |
CN108681552A (en) * | 2018-04-02 | 2018-10-19 | 厦门智融合科技有限公司 | Patent Information Services cyberspeak system and patent information Virtual Service method |
CN108694178A (en) * | 2017-04-06 | 2018-10-23 | 北京国双科技有限公司 | A kind of method and device for recommending judicial cognizance |
CN108920706A (en) * | 2018-07-20 | 2018-11-30 | 吴怡 | A kind of legal advice consulting Database and its construction method |
CN109002538A (en) * | 2018-07-20 | 2018-12-14 | 吴怡 | Legal advice cloud platform and method based on database |
CN109002431A (en) * | 2018-07-20 | 2018-12-14 | 吴怡 | Legal opinion generates system and production method |
CN109033083A (en) * | 2018-07-20 | 2018-12-18 | 吴怡 | A kind of legal advice system based on semantic net |
CN109063060A (en) * | 2018-07-20 | 2018-12-21 | 吴怡 | A kind of semantic net legal advice service robot |
CN109086371A (en) * | 2018-07-20 | 2018-12-25 | 吴怡 | A kind of semantic net interactive system and exchange method for legal advice |
CN109108989A (en) * | 2018-07-20 | 2019-01-01 | 吴怡 | A kind of legal services special purpose robot of semantics recognition |
CN109145106A (en) * | 2018-07-20 | 2019-01-04 | 吴怡 | A kind of self-learning type legal advice robot |
CN109165281A (en) * | 2018-07-20 | 2019-01-08 | 吴怡 | A kind of shared legal advice system of multirobot terminal based on semantic net |
WO2019028615A1 (en) * | 2017-08-07 | 2019-02-14 | 深圳益强信息科技有限公司 | Relative novelty determining method |
CN109460468A (en) * | 2018-10-23 | 2019-03-12 | 出门问问信息科技有限公司 | Classifying method, categorization arrangement and the corresponding electronic equipment of law related text |
CN109508458A (en) * | 2018-10-31 | 2019-03-22 | 北京国双科技有限公司 | The recognition methods of legal entity and device |
CN109670120A (en) * | 2018-12-29 | 2019-04-23 | 重庆木舌科技有限公司 | A kind of online real-time law inquiry method for college student |
CN109726275A (en) * | 2018-12-29 | 2019-05-07 | 重庆工商大学融智学院 | Legal knowledge intelligent inquiry method applied to legal advice service |
CN109766425A (en) * | 2018-12-29 | 2019-05-17 | 重庆木舌科技有限公司 | The online system of campus legal advice in real time |
CN109766415A (en) * | 2019-01-18 | 2019-05-17 | 广东小天才科技有限公司 | A kind of localization method and system of paper catalogue |
CN109903754A (en) * | 2017-12-08 | 2019-06-18 | 北京京东尚科信息技术有限公司 | Method for voice recognition, equipment and memory devices |
CN109947909A (en) * | 2018-06-19 | 2019-06-28 | 平安科技(深圳)有限公司 | Intelligent customer service answer method, equipment, storage medium and device |
CN109949184A (en) * | 2017-12-21 | 2019-06-28 | 北京市伊德众鑫科技发展有限公司 | A kind of method, electronic equipment and readable storage medium storing program for executing generating law solution |
CN110309168A (en) * | 2018-03-09 | 2019-10-08 | 北京国双科技有限公司 | A kind of judgement document's searching method and device |
CN110472070A (en) * | 2018-05-10 | 2019-11-19 | 上海利业律兴企业管理有限公司 | The searching method and device of law article |
CN110561452A (en) * | 2019-09-12 | 2019-12-13 | 广州法通信息咨询服务有限公司 | robot for improving efficiency of law-related workers and working method thereof |
CN110569350A (en) * | 2019-08-08 | 2019-12-13 | 河北省讯飞人工智能研究院 | Legal recommendation method, equipment and storage medium |
CN110634088A (en) * | 2018-06-25 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Case refereeing method, device and system |
CN110750625A (en) * | 2018-07-04 | 2020-02-04 | 北京国双科技有限公司 | Judicial question-answering method and related equipment |
CN110807094A (en) * | 2018-07-20 | 2020-02-18 | 林威伶 | Big data analysis, prediction and data visualization system and device for legal document |
CN110941702A (en) * | 2019-11-26 | 2020-03-31 | 北京明略软件系统有限公司 | Retrieval method and device for laws and regulations and laws and readable storage medium |
CN111581327A (en) * | 2020-04-08 | 2020-08-25 | 华迪计算机集团有限公司 | Administrative law enforcement assisting method and device |
CN111753071A (en) * | 2020-06-28 | 2020-10-09 | 中山市臻龙信息科技发展有限公司 | Artificial intelligence-based legal consultation interaction method and device |
CN112395388A (en) * | 2019-08-16 | 2021-02-23 | 阿里巴巴集团控股有限公司 | Information processing method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101398835A (en) * | 2007-09-30 | 2009-04-01 | 日电(中国)有限公司 | Service selecting system and method, and service enquiring system and method based on natural language |
CN102737049A (en) * | 2011-04-11 | 2012-10-17 | 腾讯科技(深圳)有限公司 | Method and system for database query |
CN103218359A (en) * | 2012-01-18 | 2013-07-24 | 朱颖 | Intelligent law knowledge base for legal consultancy service and inquiring system thereof |
CN104240164A (en) * | 2014-09-29 | 2014-12-24 | 南京提坦信息科技有限公司 | Legal consulting method and legal consulting system based on big data analysis |
-
2016
- 2016-11-07 CN CN201610976905.1A patent/CN106503239A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101398835A (en) * | 2007-09-30 | 2009-04-01 | 日电(中国)有限公司 | Service selecting system and method, and service enquiring system and method based on natural language |
CN102737049A (en) * | 2011-04-11 | 2012-10-17 | 腾讯科技(深圳)有限公司 | Method and system for database query |
CN103218359A (en) * | 2012-01-18 | 2013-07-24 | 朱颖 | Intelligent law knowledge base for legal consultancy service and inquiring system thereof |
CN104240164A (en) * | 2014-09-29 | 2014-12-24 | 南京提坦信息科技有限公司 | Legal consulting method and legal consulting system based on big data analysis |
Cited By (48)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108694178A (en) * | 2017-04-06 | 2018-10-23 | 北京国双科技有限公司 | A kind of method and device for recommending judicial cognizance |
CN107169896A (en) * | 2017-04-13 | 2017-09-15 | 甘肃建筑职业技术学院 | A kind of legal services system based on Internet technology |
CN107220912A (en) * | 2017-06-12 | 2017-09-29 | 上海市高级人民法院 | Litigation services intelligence system and robot |
CN108073569A (en) * | 2017-06-21 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of law cognitive approach, device and medium based on multi-layer various dimensions semantic understanding |
CN107330071A (en) * | 2017-06-30 | 2017-11-07 | 北京神州泰岳软件股份有限公司 | A kind of legal advice information intelligent replies method and platform |
CN107423374A (en) * | 2017-07-06 | 2017-12-01 | 武汉康慧然信息技术咨询有限公司 | Law based on classification annotation recommends method and system |
CN107423374B (en) * | 2017-07-06 | 2021-11-30 | 广州越富嘉驰网络科技有限公司 | Legal recommendation method and system based on classification labeling |
WO2019028615A1 (en) * | 2017-08-07 | 2019-02-14 | 深圳益强信息科技有限公司 | Relative novelty determining method |
CN109903754B (en) * | 2017-12-08 | 2022-04-26 | 北京京东尚科信息技术有限公司 | Method, device and memory device for speech recognition |
CN109903754A (en) * | 2017-12-08 | 2019-06-18 | 北京京东尚科信息技术有限公司 | Method for voice recognition, equipment and memory devices |
CN107894981A (en) * | 2017-12-13 | 2018-04-10 | 武汉烽火普天信息技术有限公司 | A kind of automatic abstracting method of case semantic feature |
CN109949184A (en) * | 2017-12-21 | 2019-06-28 | 北京市伊德众鑫科技发展有限公司 | A kind of method, electronic equipment and readable storage medium storing program for executing generating law solution |
CN110309168A (en) * | 2018-03-09 | 2019-10-08 | 北京国双科技有限公司 | A kind of judgement document's searching method and device |
CN108595415A (en) * | 2018-03-26 | 2018-09-28 | 北京北大英华科技有限公司 | A kind of law differentiation determination method, device and computer equipment, storage medium |
CN108595415B (en) * | 2018-03-26 | 2022-06-14 | 北京北大英华科技有限公司 | Law differentiation judgment method and device, computer equipment and storage medium |
CN108681552A (en) * | 2018-04-02 | 2018-10-19 | 厦门智融合科技有限公司 | Patent Information Services cyberspeak system and patent information Virtual Service method |
CN110472070A (en) * | 2018-05-10 | 2019-11-19 | 上海利业律兴企业管理有限公司 | The searching method and device of law article |
CN109947909A (en) * | 2018-06-19 | 2019-06-28 | 平安科技(深圳)有限公司 | Intelligent customer service answer method, equipment, storage medium and device |
CN109947909B (en) * | 2018-06-19 | 2024-03-12 | 平安科技(深圳)有限公司 | Intelligent customer service response method, equipment, storage medium and device |
CN110634088A (en) * | 2018-06-25 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Case refereeing method, device and system |
CN110750625A (en) * | 2018-07-04 | 2020-02-04 | 北京国双科技有限公司 | Judicial question-answering method and related equipment |
CN109002431A (en) * | 2018-07-20 | 2018-12-14 | 吴怡 | Legal opinion generates system and production method |
CN109145106B (en) * | 2018-07-20 | 2022-06-28 | 重庆百事得大牛机器人有限公司 | Self-learning type law consultation robot |
CN109063060A (en) * | 2018-07-20 | 2018-12-21 | 吴怡 | A kind of semantic net legal advice service robot |
CN109002538A (en) * | 2018-07-20 | 2018-12-14 | 吴怡 | Legal advice cloud platform and method based on database |
CN108920706A (en) * | 2018-07-20 | 2018-11-30 | 吴怡 | A kind of legal advice consulting Database and its construction method |
CN109086371A (en) * | 2018-07-20 | 2018-12-25 | 吴怡 | A kind of semantic net interactive system and exchange method for legal advice |
CN110807094A (en) * | 2018-07-20 | 2020-02-18 | 林威伶 | Big data analysis, prediction and data visualization system and device for legal document |
CN109108989A (en) * | 2018-07-20 | 2019-01-01 | 吴怡 | A kind of legal services special purpose robot of semantics recognition |
CN109033083A (en) * | 2018-07-20 | 2018-12-18 | 吴怡 | A kind of legal advice system based on semantic net |
CN109165281A (en) * | 2018-07-20 | 2019-01-08 | 吴怡 | A kind of shared legal advice system of multirobot terminal based on semantic net |
CN109145106A (en) * | 2018-07-20 | 2019-01-04 | 吴怡 | A kind of self-learning type legal advice robot |
CN109460468A (en) * | 2018-10-23 | 2019-03-12 | 出门问问信息科技有限公司 | Classifying method, categorization arrangement and the corresponding electronic equipment of law related text |
CN109508458A (en) * | 2018-10-31 | 2019-03-22 | 北京国双科技有限公司 | The recognition methods of legal entity and device |
CN109726275A (en) * | 2018-12-29 | 2019-05-07 | 重庆工商大学融智学院 | Legal knowledge intelligent inquiry method applied to legal advice service |
CN109670120A (en) * | 2018-12-29 | 2019-04-23 | 重庆木舌科技有限公司 | A kind of online real-time law inquiry method for college student |
CN109766425A (en) * | 2018-12-29 | 2019-05-17 | 重庆木舌科技有限公司 | The online system of campus legal advice in real time |
CN109766415A (en) * | 2019-01-18 | 2019-05-17 | 广东小天才科技有限公司 | A kind of localization method and system of paper catalogue |
CN109766415B (en) * | 2019-01-18 | 2022-05-06 | 广东小天才科技有限公司 | Book directory positioning method and system |
CN110569350A (en) * | 2019-08-08 | 2019-12-13 | 河北省讯飞人工智能研究院 | Legal recommendation method, equipment and storage medium |
CN110569350B (en) * | 2019-08-08 | 2022-08-09 | 河北省讯飞人工智能研究院 | Legal recommendation method, equipment and storage medium |
CN112395388A (en) * | 2019-08-16 | 2021-02-23 | 阿里巴巴集团控股有限公司 | Information processing method and device |
CN112395388B (en) * | 2019-08-16 | 2023-12-26 | 阿里巴巴集团控股有限公司 | Information processing method and device |
CN110561452A (en) * | 2019-09-12 | 2019-12-13 | 广州法通信息咨询服务有限公司 | robot for improving efficiency of law-related workers and working method thereof |
CN110941702A (en) * | 2019-11-26 | 2020-03-31 | 北京明略软件系统有限公司 | Retrieval method and device for laws and regulations and laws and readable storage medium |
CN111581327A (en) * | 2020-04-08 | 2020-08-25 | 华迪计算机集团有限公司 | Administrative law enforcement assisting method and device |
CN111753071A (en) * | 2020-06-28 | 2020-10-09 | 中山市臻龙信息科技发展有限公司 | Artificial intelligence-based legal consultation interaction method and device |
CN111753071B (en) * | 2020-06-28 | 2023-09-05 | 中山市臻龙信息科技发展有限公司 | Legal consultation interaction method and device based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106503239A (en) | A kind of method and apparatus of legal information inquiry | |
CN106469212B (en) | Man-machine interaction method and device based on artificial intelligence | |
JP6684391B2 (en) | Multi-domain real-time question and answer system | |
CN107291783B (en) | Semantic matching method and intelligent equipment | |
US20190163691A1 (en) | Intent Based Dynamic Generation of Personalized Content from Dynamic Sources | |
US9564122B2 (en) | Language model adaptation based on filtered data | |
Lowe et al. | Incorporating unstructured textual knowledge sources into neural dialogue systems | |
US20210064821A1 (en) | System and method to extract customized information in natural language text | |
KR20160147303A (en) | Method for dialog management based on multi-user using memory capacity and apparatus for performing the method | |
CN113239169A (en) | Artificial intelligence-based answer generation method, device, equipment and storage medium | |
KR101677859B1 (en) | Method for generating system response using knowledgy base and apparatus for performing the method | |
CN111353026A (en) | Intelligent law attorney assistant customer service system | |
CN116541493A (en) | Interactive response method, device, equipment and storage medium based on intention recognition | |
KR101333485B1 (en) | Method for constructing named entities using online encyclopedia and apparatus for performing the same | |
Kuhn et al. | Coral: Corpus access in controlled language | |
CN116662522A (en) | Question answer recommendation method, storage medium and electronic equipment | |
CN107153685B (en) | Cognitive method and device based on timeline memory in man-machine conversation system | |
Assem et al. | QASAR: self-supervised learning framework for extractive question answering | |
CN111858860A (en) | Search information processing method and system, server, and computer readable medium | |
US11257479B2 (en) | Chat and knowledge domain driven task-specific query and response system | |
Singh et al. | Deep neural based name entity recognizer and classifier for English language | |
Yang et al. | Common sense-based reasoning using external knowledge for question answering | |
Yeh et al. | Ontology‐based speech act identification in a bilingual dialog system using partial pattern trees | |
CN108829663B (en) | Article evaluation method and system | |
CN115408500A (en) | Question-answer consistency evaluation method and device, electronic equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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: 20170315 |