CN109145106A - A kind of self-learning type legal advice robot - Google Patents
A kind of self-learning type legal advice robot Download PDFInfo
- Publication number
- CN109145106A CN109145106A CN201810805094.8A CN201810805094A CN109145106A CN 109145106 A CN109145106 A CN 109145106A CN 201810805094 A CN201810805094 A CN 201810805094A CN 109145106 A CN109145106 A CN 109145106A
- Authority
- CN
- China
- Prior art keywords
- module
- information
- answer
- answer information
- consultant
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services; Handling legal documents
Abstract
The present invention relates to legal advice fields, and in particular to a kind of self-learning type legal advice robot, including answer exam pool memory module, articles of law memory module, answer information generating module and adjustment module；Exam pool memory module is answered for storing answer information；Articles of law memory module generates basic material for storing legal opinion；Answer information generating module is asked a question for consultant to be found in articles of law memory module relevant asked a question relevant legal opinion when answering and not searching out corresponding answer information in exam pool memory module and generates basic material as answering information；Adjustment module is used to receive the answer information that answer information generating module is sent, and judge the answer information whether by correctly answer information of being asked a question, and judging result be answer information it is correct when the answer information played out.
Description
Technical field
The present invention relates to legal advice fields, and in particular to a kind of self-learning type legal advice robot.
Background technique
Legal advice refers to that the personnel for being engaged in legal services make explanations with regard to relevant laws affairs problem, illustrate, proposes to build
The activity of negotiation solution.Existing legal advice mode is worked as usually from telephone counseling, the network consulting or brief a barrister
Face consulting, but whether be telephone counseling, the network consulting or brief a barrister, be all answered by the personnel of profession, but
Since natural person's stock of knowledge is limited, legal case or legal opinion generation basic material are all relatively more, and natural person can not be complete
Portion is remembered by these legal knowledges completely.
To solve the above-mentioned problems, the Chinese patent document of Publication No. CN104240164A discloses a kind of based on big number
According to the law inquiry method and system of analysis, this method comprises: step S1, selection needs the legal field seeked advice from；Step S2, root
Corresponding problem describing framework is selected according to the legal field；Step S3, according to describing framework the problem of input from storage
Data cell analyzes consulting as a result, this method and system need manpower to retrieve during efficiently solving traditional legal advice
Legal provision and case come answer legal advice problem deficiency and manually during answering legal advice problem due to
Insufficient problem that legal information caused by the limitation of itself professional range utilizes.
But the consulting result needs in the above method are previously stored in data cell and could carry out law in consultant
Corresponding consulting result is found by carrying out analysis to the information in data cell when consulting.This leads to the data in data cell
It can not timely be updated, need being updated for artificial timing that the data storage information in data cell could be made to occur
Variation, so that the information in database has certain hysteresis quality, makes troubles, and be not easy to manage to consultant.
Summary of the invention
The technical issues of solution of the invention is to provide a kind of self-learning type legal advice robot, with solve it is existing into
The problem of system of row legal advice can not automatically automatically update law relevant information.
Base case provided by the invention are as follows: a kind of self-study formula legal advice robot, including answer exam pool memory module,
Articles of law memory module, answer information generating module and adjustment module；
Exam pool memory module is answered for storing answer information；Articles of law memory module is raw for storing legal opinion
At basic material；
Answer information generating module is asked a question for consultant and is not searched out accordingly in answer exam pool memory module
Answer information when find relevant asked a question relevant legal opinion in articles of law memory module and generate basic material
Then answer information is sent to adjustment module as answer information by material；
Adjustment module be used for receives answer information generating module transmission answer information, and judge the answer information whether be
It asks a question and correctly answers information, and be to play out the answer information when answer information is correct in judging result, if sentencing
Disconnected result is that the answer information is not when correctly answering information, after adding screening conditions on the basis of consultant is asked a question
It is sent to answer information generating module.
The working principle of the invention and advantage are: when consultant carries out legal advice by legal advice robot,
If problem carried out by consultant belongs in existing answer exam pool memory module the problem of being stored with, without passing through answer information
Generation module generates answer information, and the stored problem in answer exam pool memory module if consultant asks a question is led to
It crosses answer information generating module and is asked a question according to consultant and find corresponding legal opinion in articles of law memory module
Basic material is generated as answer information, the answer information is then sent to whether just adjustment module judges the answer information
Really, the answer information is stored into answer exam pool memory module when the answer information is correct, if the answer information is mistake
It mistakes, is sent to answer information generating module after increase screening conditions on the basis of consultant is asked a question and carries out answer letter
The searching again of breath.
Compared with prior art, this programme realizes oneself that information is answered in answer exam pool memory module by adjusting module
It is dynamic abundant, and before answer information is stored, adjustment module judges whether answer information is correct, avoids the answer letter of mistake
Breath is stored in answer exam pool memory module；Meanwhile will realize that answer information is found again when answering information errors, so that consulting
Each problem of inquiry person can be answered.
Further, answer library memory module and the setting of articles of law memory module adjust mould in consulting robot terminal
Block setting is adjusting in terminal, and adjustment module is connected with consulting robot terminal signaling, and adjustment module is used for according to acquisition law
Professional is to the answer whether correct judging result of information.
Whether answer information is correctly judged by legal professionals, so that judging result is more accurate.
Further, answer library memory module, articles of law memory module, answer information generating module and adjustment module setting
In consulting robot terminal, adjustment module is for obtaining consultant to the answer whether correct judging result of information.
Adjustment module is arranged in robot terminal, whether answer information is correctly judged by consultant, i.e.,
Judge whether the answer information is answer information needed for consultant, so that answer information is more in line with the demand of consultant.
Further, consulting robot terminal further includes related information extraction module, and related information extraction module is used for official communication
Inquiry person asks a question and asks a question relevant answer information as related information.
It is asked questions when consultant asks questions in order to become more apparent upon, it will carried out to relevant information is asked questions
Solution extracts convenient for these related informations are recommended consultant related information,
Further, consulting robot terminal further includes voice collecting judgment module and related question extraction module, and voice is adopted
Collection judgment module is used for when consultant asks questions to asking questions carry out keyword extraction, the keyword that then will be extracted
It is successively arranged according to extraction time and generates time shaft, and the time shaft of generation is sent to related information output module；Association is asked
Topic extraction module is used to judge according to keyword in time shaft which related information to be that the consultant not seeked advice from seeks advice from
It crosses, and to not extracted by the related information that the consultant seeked advice from.
By the generation of time shaft, related information output module is avoided to seek advice from consultant oneself in related information output
The problem of crossing recommends consultant.
It further, further include related information output module, related information output module is used for related question extraction module
The related information extracted carries out voice output.
Voice output is carried out to related information by related information output module, is asked questions convenient for consultant's understanding
Related information.
Detailed description of the invention
Fig. 1 is a kind of logic diagram of self-learning type legal advice robot in the embodiment of the present invention one；
Fig. 2 is the logic diagram of consulting robot terminal and adjustment terminal in the embodiment of the present invention one；
Fig. 3 is a kind of logic diagram of self-learning type legal advice robot in the embodiment of the present invention two；
Fig. 4 is a kind of implementation flow chart of self-learning type legal advice robot in the embodiment of the present invention two；
Specific embodiment
Below by the further details of explanation of specific embodiment:
Embodiment
It is as depicted in figs. 1 and 2: a kind of self-learning type legal advice robot, including adjustment terminal and consulting robot end
End, module is communicated consulting robot terminal with adjustment terminal by wireless communication, and wireless communication module selects existing Risym
The WIFI communication module of brand.Adjustment terminal can select existing mobile phone or computer.
One, adjustment terminal includes:
Module is adjusted, judges whether match just between problem topic and legal opinion in answer information for staff
Really；After answer information generating module, which will answer information, is sent to adjustment module, adjustment module carries out display confession for information is answered
Staff checks that staff judges to answer whether match between problem topic and legal opinion in information correctly, then
Carry out judging result input.When judging result information is inputted, if being matched between problem topic and legal opinion, input
Judging result information be pair, if mismatching between problem topic and legal opinion, the judging result information inputted is work
Personnel show that one generates keyword relevant in basic material to required searching legal opinion according to problem topic.Work as work
When personnel judge to match correct between the problem topic and legal opinion, then judging result information is carried out from adjustment module
Input, if matching between problem topic and legal opinion, adjusts module for the corresponding answer information of the judging result information
It stores in answer exam pool memory module, meanwhile, adjustment module is sent to voice output module for information is answered.Work as staff
Between decision problem topic and legal opinion when matching error, then module is adjusted by the judging result information and the judging result
The problems in the corresponding answer information of information topic information is sent to answer information generating module.
Two, consulting robot terminal includes:
Articles of law memory module is stored with the law for being refined and being put in order by professional lawyer in articles of law memory module
The legal opinion such as regulation, judicial explanation, local laws and regulations, the department regulation of each ministries and commissions and case generate basic material.
Exam pool memory module is answered, for storing answer information, answer information includes problem topic and method corresponding with problem topic
Restrain position paper.
Consultation module carries out the voice messaging input of legal advice problem for consultant, then sends out the problem of consulting
Give parsing module.
Parsing module, the voice messaging sent for receiving consultation module, then converts speech information into text information,
Exist further according to legal field involved by text information institute suitable environment, the relevant existence general knowledge of text information and text information etc.
The answer information that matching text information is suitable in exam pool memory module is answered, according in answer information when answering information matches
The problem of topic and the matching degree of text information judge whether text information corresponding with answer information, when answer information the problem of
When the matching degree of topic and text information is up to 90%, answer information is sent to adjustment module and voice output module.
Then voice output module will answer information for receiving parsing module and adjusting the answer information of module transmission
In legal opinion carry out voice output, i.e., to consultant propose the problem of answer, then send related question output
It requests to give related question extraction module.
Information generating module is answered, for receiving the text information of parsing module transmission, then by text information and law
The legal opinion stored in clause memory module generates basic material and is matched, when text information and legal opinion generate
Basic material matching degree reaches 90%, then the legal opinion is generated basic material information as legal opinion, by text
Then problem topic and legal opinion are combined into answer information and are sent to adjustment module by information as problem topic.Answer
Information generating module is also used to receive the answer information judging result information corresponding with answer information that adjustment module is sent, and is solving
Answering will answer information and judgement knot after information generating module receives the answer information and judging result information that adjustment module is sent
Text information in fruit information generates basic material with legal opinion and is matched, when text information and legal opinion generate
Basic material matching degree reaches 90%, then the legal opinion is generated basic material information as legal opinion, by text
Then problem topic and legal opinion are combined into answer information and are sent to adjustment module by information as problem topic.
When it is implemented, implementing procedure includes the following steps:
S1, voice input: the consultant for needing to carry out legal advice is carried out by the consultation module of consulting robot terminal
The voice messaging of legal issue inputs, and then the voice messaging of input is sent to server by consultation module.
S2, speech analysis: after speech analysis module receives the voice messaging of consultation module transmission, the voice that will receive
Information is parsed into text information by the speech analysis technology of Iflytek limited liability company, and text information is conciliate answer
Topic is matched the problem of storage in the memory module of library, when text information and problem topic matching degree are up to 90%, by this
The corresponding legal opinion of problem topic is sent to voice output module；If text information and problem topic matching degree are lower than
90%, then text information is sent to answer information generating module.
S3, voice output: the voice output module in consulting robot terminal receives parsing module and adjustment module hair
After the answer information sent, the problem of legal opinion in information carries out voice output, i.e., proposes to consultant will be answered and carried out
Answer.
S4, answer information generate:, will after answer information generating module receives the text information of speech analysis module transmission
The legal opinion that stores in text information and articles of law memory module generates basic material and is matched, when text information and
Legal opinion generates basic material matching degree and reaches 90%, then the legal opinion is generated basic material information as law
Then problem topic and legal opinion are combined into answer information and are sent to by position paper using text information as problem topic
Adjust module.
S5, judge whether answer information is correct: the adjustment module in adjustment terminal receives answer information generating module hair
After the answer information sent, answer information is shown and is checked for staff, staff judges problem topic in answer information
Whether matched between mesh and legal opinion correctly, then carries out the text input of judging result；Judging result information carries out defeated
Fashionable, if matching between problem topic and legal opinion, the judging result information of input is pair, if problem topic and law meaning
See between book and mismatch, then the judging result information inputted is that staff according to problem topic obtains one and required searching method
It restrains position paper and generates the relevant voice messaging of basic material.When staff judges between the problem topic and legal opinion
With it is correct when, then by judging result information from adjustment module on input, if being matched between problem topic and legal opinion,
Module is then adjusted by the corresponding answer information storage of the judging result information into answer exam pool memory module, meanwhile, adjust mould
Block is sent to voice output module for information is answered, when matching error between staff's decision problem topic and legal opinion
When, then it adjusts module and sends the problems in judging result information answer information corresponding with judging result information topic information
Give answer information generating module.
S6, answer information adjustment: answer information generating module receives the answer information that adjustment module is sent and answer letter
After ceasing corresponding judging result information, the text information in information and judging result information will be answered and legal opinion generates base
Plinth material is matched, and is reached 90% when text information and legal opinion generate basic material matching degree, then the law is anticipated
See inteilectual at basic material information as legal opinion, using text information as problem topic, then by problem topic and method
Rule position paper is combined into answer information and is sent to adjustment module.
Embodiment two
As shown in figure 3, embodiment two and the difference of embodiment one are, robot is seeked advice from embodiment two further include:
Related information memory module, for storing answer information related information relevant with the answer information.
Intelligence questions memory module is not usually consulted what person was inquired as related information for storing in answer information
Related information.
Related question seeks module, for receiving the judgement request of related question extraction module transmission, and sentences receiving
After disconnected request voice output " needing to be associated problem understanding? " determination information, consultant pass through consultation module return
When answering " needs ", related question seeks module and consultant's answer information is fed back to related question extraction module.
Related information output module is believed for receiving the related information of related question extraction module transmission, and by association
Problem topic carries out voice broadcasting in breath, allows consultant's selection to need the problem of playing legal opinion topic, then consultant
It is exported in a manner of voice input and needs the problem of playing legal opinion topic, when consultant is output by voice module input
After needing the problem of playing topic, voice broadcasting is carried out to the corresponding legal opinion of input problem topic.
Intelligent sound playing module, for receive screening module transmission related information, then automatically to related information into
Row plays.
Then problem relevance composite module is successively being solved for extracting answer information in answer exam pool memory module
Keyword is extracted in the problem of answering information topic, and the legal opinion in keyword and other answer information is matched,
In the presence of this keyword is in the legal opinion of other answer information, then successful two answers of Keywords matching are believed
Breath is combined into related information, and related information is then sent to related information memory module and is stored.Such as: now in difference
Legal opinion in the keyword that extracts respectively include: the keywords such as divorce, injury, traffic accident, property, children, debt-credit,
So by the keyword and other answer information legal opinion in Keywords matching when, then divorce, property and children it is several
A keyword by successful match, traffic accident, injury and borrow or lend money these keywords also can successful match, successful match it is several
The answer information of keyword can then be combined into related information.
Related question extraction module for receiving the output request of voice output module transmission, and is asked receiving output
It extracts in related information memory module after asking and asks a question relevant related information to consultant, then according to the elder generation of time shaft
Sequence is found in related information and asks a question related information that is related but not seeking advice to the consultant afterwards, backward association
Problem seeks module and sends the judgement request whether related information exports.It is sought when related question extraction module receives related question
After asking the consultant of module feedback to answer information, corresponding related information is sent to related information output module.
Related question adjusts module, needs to carry out law for what is inputted on related information output module according to consultant
Position paper play the problem of topic recorded and counted, be also used to count two problem topics interval 20 minutes in it is successive
Then the probability of proposition will be spaced in 20 minutes and successively be proposed that probability answer corresponding higher than 80% two problem topics is believed
Breath is used as related information, and into related information memory module, the original phase of both of these problems topic is closed in covering by related information storage
The related information of pass.When the probability that successively proposes is higher than 98% to two problems in interval 20 minutes, then both of these problems conduct
Related information will be stored in intelligence questions memory module.
Screening module, for receiving the time shaft of voice collecting judgment module transmission, and one according to time shaft recently
Keyword found in intelligence questions memory module with the related information of the Keywords matching, then by keyword on time shaft with
Answer information in related information is matched, and the answer information by matching rate higher than 90% corresponds on time shaft, and will not have
There is related information corresponding with time shaft to be sent to intelligent sound playing module.
Voice collecting judgment module carries out mentioning for keyword when carrying out voice input by consultation module for consultant
It takes, the keyword extraction time order and function extracted is then arranged in time shaft and is sent to screening module.Voice collecting judges mould
Block restarts the keyword in acquisition input voice, then after the interrupt instruction for receiving the transmission of time shaft update module
The keyword extracted is successively rearranged into time shaft according to extraction time and is sent to screening module.
Time shaft update module is extracted in adjacent input in voice twice for consultant when carrying out voice input respectively
Keyword, and the relevance between two keywords is being judged after keyword extraction, when the relevance between two keywords is low
When 60%, time shaft update module will send interrupt instruction and give voice collecting judgment module.
As shown in figure 4, when it is implemented, specific implementation process is as follows:
S1, voice input: the consultant for needing to carry out legal advice is carried out by the consultation module of consulting robot terminal
The voice messaging of legal issue inputs, and then the voice messaging of input is sent to server by consultation module, enters step later
Rapid S2, S7 and S10.
S2, speech analysis: after speech analysis module receives the voice messaging of consultation module transmission, the voice that will receive
Information is parsed into text information by the speech analysis technology of Iflytek limited liability company, and text information is conciliate answer
Topic is matched the problem of storage in the memory module of library, when text information and problem topic matching degree are up to 90%, by this
The corresponding legal opinion of problem topic is sent to voice output module, enters step S3；If text information and problem topic
It is lower than 90% with degree, then text information is sent to answer information generating module, enters step S11 later.
S3, voice output: the voice output module in consulting robot terminal receives parsing module and adjustment module hair
After the answer information sent, the problem of legal opinion in information carries out voice output, i.e., proposes to consultant will be answered and carried out
Then answer sends related question output request and gives related question extraction module, enters step S4 later.
S4, related question extract: after related question extraction module receives the output request of voice output module transmission,
It extracts in related information memory module and asks a question relevant related information to consultant, the time that then consultant is asked a question
Sequencing is found in related information asks a question related information that is related but not being consulted to the consultant, backward
Related question seeks module and sends the judgement request whether related information exports, and enters step S5.
Whether S5, inquiry related information need: the related question for seeking advice from robot terminal seeks module and receives association to ask
After inscribing the judgement request that extraction module is sent, the confirmation message of voice output " whether needing to be associated problem understanding " is being consulted
When inquiry person answers " needs " by consultation module, related question seeks module and consultant's answer information is sent to related question and is mentioned
Modulus block, enters step S6 later.
S6, related information output: when related question extraction module receives the consultant that related question seeks module feedback
After answering information, corresponding related information is sent to the related information output module in consulting robot terminal, related information
After output module receives the related information of related question extraction module transmission, problem topic in related information is subjected to voice and is broadcast
It puts, consultant's selection is allowed to need the problem of playing legal opinion topic, then consultant is exported in a manner of voice input and needed
The problem of playing legal opinion topic, after consultant, which is output by voice module input, needs the problem of playing topic,
Voice broadcasting is carried out to the corresponding legal opinion of input problem topic, enters step S7.
S7, keyword extraction time shaft generate: the voice collecting judgment module in consulting robot terminal is logical in consultant
It crosses consultation module and carries out the extraction for carrying out keyword when voice input, then arrange the keyword extraction time order and function extracted
It is sent to screening module at time shaft, enters step S8.
S8, related information screening: after screening module receives the time shaft of voice collecting judgment module transmission, according to the time
A nearest keyword of axis is found in intelligence questions memory module and the related information of the Keywords matching, then by the time
Keyword is matched with the answer information in related information on axis, and the answer information by matching rate higher than 90% corresponds to the time
On axis, and the no and corresponding related information of time shaft is sent to intelligent sound playing module, enters step S9.
S9, intelligent sound play: the intelligent sound playing module in consulting robot terminal receives screening module transmission
Related information, automatically to related information carry out voice broadcasting enter step S10 later.
S10, time shaft update: the time shaft update module in consulting robot terminal is passing through consultation module in consultant
Keyword is extracted in adjacent input in voice twice respectively when carrying out voice input, and judges two keys after keyword extraction
Relevance between word, when the relevance between two keywords be lower than 60% when, time shaft update module will send in severed finger
It enables and gives voice collecting judgment module；Voice collecting judgment module receive time shaft update module transmission interrupt instruction after,
Restart the keyword in acquisition input voice, is then successively rearranged into the keyword extracted according to extraction time
Time shaft is sent to screening module, enters step S11.
S11, answer information generate:, will be literary after answer information generating module receives the text information of parsing module transmission
The legal opinion stored in this information and articles of law memory module generates basic material and is matched, when text information and method
Rule position paper generates basic material matching degree and reaches 90%, then the legal opinion is generated basic material information as law and anticipated
See book, using text information as problem topic, problem topic and legal opinion is then combined into answer information and are sent to tune
Mould preparation block, enters step S12 and S2.
S12, judge whether answer information is correct: the adjustment module in adjustment terminal receives answer information generating module hair
After the answer information sent, answer information is shown and is checked for staff, staff judges problem topic in answer information
Whether matched between mesh and legal opinion correctly, then carries out the text input of judging result；Judging result information carries out defeated
Fashionable, if matching between problem topic and legal opinion, the judging result information of input is pair, if problem topic and law meaning
See between book and mismatch, then the judging result information inputted is that staff according to problem topic obtains one and required searching method
It restrains position paper and generates the relevant keyword of basic material.When staff judges to match between the problem topic and legal opinion
When correct, then judging result information is inputted from adjustment module, if being matched between problem topic and legal opinion,
Module is adjusted by the corresponding answer information storage of the judging result information into answer exam pool memory module, meanwhile, adjust module
Answer information is sent to voice output module, enters step S3.When staff's decision problem topic and legal opinion it
Between matching error when, then adjust module by the problems in judging result information answer information corresponding with the judging result information inscribe
Mesh information is sent to answer information generating module, enters step S13.
S13, answer information adjustment: answer information generating module receives the answer information that adjustment module is sent and answer letter
After ceasing corresponding judging result information, the keyword in information and judging result information will be answered and legal opinion generates basis
Material is matched, when keyword and legal opinion generate basic material matching degree and reach 90%, then by the legal opinion
Basic material information is generated as legal opinion, using text information as problem topic, then problem topic and law are anticipated
See that book is combined into answer information and is sent to adjustment module, enters step S12.
Embodiment three
Embodiment three and the difference of embodiment two are that adjustment module is located in consulting robot terminal rather than is adjusting
In terminal；
Adjustment terminal judges to answer between information and oneself institute's problem mesh whether match correctly for consultant；When answer is believed
Breath generation module will answer after information is sent to adjustment module, and adjustment module will answer information and carry out voice broadcasting, and consultant sentences
Whether correct, then progress judging result input is matched in disconnected answer information between problem topic and legal opinion.Judgement knot
When fruit information is inputted, if matching between problem topic and legal opinion, the judging result information of input is " to ", if asking
It is mismatched between topic topic and legal opinion, then the judging result information inputted is " not to ", while consultant is according to problem
Topic says a keyword relevant to required searching legal opinion generation basic material.When consultant judges that the problem is inscribed
When matching correct between mesh and legal opinion, then judging result information is inputted from adjustment module, if problem topic
It is matched between legal opinion, then adjusts module and deposit the corresponding answer information storage of the judging result information to answer exam pool
It stores up in module, meanwhile, adjustment module is sent to voice output module for information is answered.When consultant's decision problem topic and law
Between position paper when matching error, then adjusting module will be in judging result information answer information corresponding with the judging result information
The problem of topic information be sent to answer information generating module.
Example IV
The difference of example IV and embodiment three is, without adjustment terminal in example IV, but sets in server
It is equipped with to ask questions and does not answer logging modle, ask questions and do not answer logging modle and do not generate for answering information generating module
When suitable answer information, asks questions and do not answer the problem of logging modle will be without answering consultant topic and record, specially
Industry lawyer is made in corresponding legal opinion storage to answer exam pool memory module after focusing on to these problems.This
Sample, professional lawyer are just not necessarily to carry out the answer of legal advice problem all the time, only need to carry out in a regular time daily
Answer, and consultant only need to guarantee understanding in professional lawyer to inquire after asking questions answer and can know answer information
Answer the accuracy of information.
Embodiment five
Embodiment five and the difference of example IV are that server further includes dereferenced problem inquiry mould in example IV
Block, dereferenced problem inquiry module are used to ask questions not with consultant when consultant has just started and asked questions needed for consulting
(no relevance refers to that selection consultant asks a question and answers and is not belonging to be associated between information the answer information of relevant property
Information) it is sent to voice output module progress voice output, then consultant carries out response voice messaging by consultation module
Input just starts the answer information matches and output asked questions needed for carrying out consultant later.When answer information is exported
The problem of information is answered in main output topic, when generating time shaft, dereferenced problem consultation module is sent to voice output mould
The ingredient and time that the keyword that the response voice messaging of the answer information of block and consultant extract is generated not as time shaft
The foundation that axis updates.
Emotion judgment module, emotion judgment module are used to judge consultant in response according to the response voice messaging of consultant
The mood contained by voice messaging when carrying out other problems input after information input, then believes mood contained by the voice messaging
Breath is sent to information authenticity judgment module.When emotion judgment module judges the voice messaging mood that consultant inputs,
The reason of being judged according to response voice messaging is, when consultant inputs response voice messaging, since dereferenced problem is ask
The problem of consulting needed for asking the answer information and consultant that module exports, is simultaneously uncorrelated, so consultant is hearing this answer letter
When the problems in breath topic, it will feel extremely to confuse, but under normal circumstances although consultant is puzzled but can feel this solution
It answers the consulting of information necessarily and needed for oneself to ask questions associated or certainly exist certain purpose, so consultant can confuse
In the state of tranquiler input response voice messaging.It is asked questions after judging consultant according to response voice messaging defeated
When the voice messaging mood entered, the word speed and volume of consultant in response voice messaging are judged, it then will consulting
The voice messaging inputted when seeking advice from after person compares with the word speed and volume of response voice messaging and judges its word speed
Increase how many with volume, the number of the word speed of input voice information and volume incrementss when asking questions later according to consultant
Judge contained mood in the voice messaging inputted when the consultant asks questions, Main Analysis consultant's excitement journey when mood is analyzed
Degree.
Then information authenticity judgment module is believed for receiving the emotional information of emotion judgment module transmission according to mood
Breath judges contained content authenticity in corresponding voice messaging.Information authenticity judgment module is true to content contained in voice messaging
When property is judged, judge institute's presentation content in the voice messaging according to the exciting degree of consultant's input voice information
Authenticity.Since people is when being related to oneself interests or exciting grievance, the fact can usually be exaggerated when statement and towards
Oneself is spoken, that is, the content spoken is more advantageous to oneself, if at this moment according to the voice messaging of consultant's input according to embodiment one
Mode match answer information will likely matched answer information practicability or grade of fit reduction, so judging authenticity
It is that more particularly suitable answer information is matched for the authenticity of the content according to expressed by voice messaging.
Information generating module is answered in the authenticity matching answer information of the content according to expressed by voice messaging, according to language
Message ceases the reduction of expressed content authenticity, and the answer information of output is related to that possibility is more, i.e., consultant is more exciting, defeated
A possibility that content authenticity expressed by the voice messaging entered is just lower, corresponds to involved in the answer information of output is just more,
The information content contained in answer information is bigger, can not only understand oneself institute's input voice information expression content most convenient for consultant
Close to answer information, moreover it is possible to obtain the answer information under consultant's voice messaging expression content contrary circumstance.
What has been described above is only an embodiment of the present invention, and the common sense such as well known specific structure and characteristic are not made herein in scheme
Excessive description, technical field that the present invention belongs to is all before one skilled in the art know the applying date or priority date
Ordinary technical knowledge can know the prior art all in the field, and have using routine experiment hand before the date
The ability of section, one skilled in the art can improve and be implemented in conjunction with self-ability under the enlightenment that the application provides
This programme, some typical known features or known method should not become one skilled in the art and implement the application
Obstacle.It should be pointed out that for those skilled in the art, without departing from the structure of the invention, can also make
Several modifications and improvements out, these also should be considered as protection scope of the present invention, these all will not influence the effect that the present invention is implemented
Fruit and patent practicability.The scope of protection required by this application should be based on the content of the claims, the tool in specification
The records such as body embodiment can be used for explaining the content of claim.
Claims (6)
1. a kind of self-learning type legal advice robot, which is characterized in that including answer exam pool memory module, articles of law storage
Module, answer information generating module and adjustment module；Exam pool memory module is answered for storing answer information；Articles of law storage
Module generates basic material for storing legal opinion；
Answer information generating module asks a question for consultant and does not search out corresponding solution in answer exam pool memory module
Relevant asked a question relevant legal opinion is found when answering information in articles of law memory module and generates basic material work
To answer information, answer information is then sent to adjustment module；
Whether adjustment module is used to receive the answer information of answer information generating module transmission, and judge the answer information to be mentioned
Problem correctly answers information, and is to play out the answer information when answer information is correct in judging result, if judgement knot
Fruit is that the answer information is not when correctly answering information, to send after adding screening conditions on the basis of consultant is asked a question
Give answer information generating module.
2. a kind of self-learning type legal advice robot according to claim 1, it is characterised in that: answer library memory module
With articles of law memory module setting consulting robot terminal in, adjustment module setting adjustment terminal in, adjustment module and
The connection of robot terminal signaling is seeked advice from, and adjustment module is used to answer information whether is correctly sentenced according to acquisition legal professionals
Disconnected result.
3. a kind of self-learning type legal advice robot according to claim 1, it is characterised in that: answer library stores mould
Block, articles of law memory module, answer information generating module and the setting of adjustment module adjust module in consulting robot terminal
For obtaining consultant to the answer whether correct judging result of information.
4. a kind of self-learning type legal advice robot according to claim 2 or 3, it is characterised in that: consulting robot
Terminal further includes related information extraction module, and related information extraction module is used to ask a question to consultant and asked a question phase
The answer information of pass is as related information.
5. a kind of self-learning type legal advice robot according to claim 4, it is characterised in that: consulting robot terminal
It further include voice collecting judgment module and related question extraction module, voice collecting judgment module in consultant for asking questions
When to carry out keyword extraction is asked questions, then by the keyword extracted according to extraction time successively arrange generate the time
Axis, and the time shaft of generation is sent to related information output module；Related question extraction module according in time shaft for closing
Keyword judges which related information is that the consultant not seeked advice from seeked advice from, and to not seeked advice from by the consultant
Related information extracts.
6. a kind of self-learning type legal advice robot according to claim 5, it is characterised in that: further include related information
Output module, it is defeated that the related information that related information output module is used to extract related question extraction module carries out voice
Out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810805094.8A CN109145106B (en) | 2018-07-20 | 2018-07-20 | Self-learning type law consultation robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810805094.8A CN109145106B (en) | 2018-07-20 | 2018-07-20 | Self-learning type law consultation robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109145106A true CN109145106A (en) | 2019-01-04 |
| CN109145106B CN109145106B (en) | 2022-06-28 |
Family
ID=64801421
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810805094.8A Active CN109145106B (en) | 2018-07-20 | 2018-07-20 | Self-learning type law consultation robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109145106B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368053A (en) * | 2020-02-29 | 2020-07-03 | 重庆百事得大牛机器人有限公司 | Mood pacifying system based on legal consultation robot |
| CN111368031A (en) * | 2020-02-29 | 2020-07-03 | 重庆百事得大牛机器人有限公司 | Deep self-learning system and method in legal consultation field |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106503239A (en) * | 2016-11-07 | 2017-03-15 | 上海智臻智能网络科技股份有限公司 | A kind of method and apparatus of legal information inquiry |
| US20170243278A1 (en) * | 2012-07-25 | 2017-08-24 | CapitalRock LLC | Generation of suggestions and reasoning for product selection |
| 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 |
| 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 |
| CN107330820A (en) * | 2017-08-28 | 2017-11-07 | 北京智诚律法科技有限公司 | A kind of forecasting system and method for lawsuit result |
| CN107515932A (en) * | 2017-08-28 | 2017-12-26 | 北京智诚律法科技有限公司 | Artificial intelligence law consulting system based on typical problem storehouse |
| CN107562863A (en) * | 2017-08-30 | 2018-01-09 | 深圳狗尾草智能科技有限公司 | Chat robots reply automatic generation method and system |
| CN107833164A (en) * | 2017-11-11 | 2018-03-23 | 深圳知赢科技有限公司 | Law business online service system |
-
2018
- 2018-07-20 CN CN201810805094.8A patent/CN109145106B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218359A (en) * | 2012-01-18 | 2013-07-24 | 朱颖 | Intelligent law knowledge base for legal consultancy service and inquiring system thereof |
| US20170243278A1 (en) * | 2012-07-25 | 2017-08-24 | CapitalRock LLC | Generation of suggestions and reasoning for product selection |
| 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 |
| CN106503239A (en) * | 2016-11-07 | 2017-03-15 | 上海智臻智能网络科技股份有限公司 | A kind of method and apparatus of legal information inquiry |
| 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 |
| 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 |
| CN107330820A (en) * | 2017-08-28 | 2017-11-07 | 北京智诚律法科技有限公司 | A kind of forecasting system and method for lawsuit result |
| CN107515932A (en) * | 2017-08-28 | 2017-12-26 | 北京智诚律法科技有限公司 | Artificial intelligence law consulting system based on typical problem storehouse |
| CN107562863A (en) * | 2017-08-30 | 2018-01-09 | 深圳狗尾草智能科技有限公司 | Chat robots reply automatic generation method and system |
| CN107833164A (en) * | 2017-11-11 | 2018-03-23 | 深圳知赢科技有限公司 | Law business online service system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368053A (en) * | 2020-02-29 | 2020-07-03 | 重庆百事得大牛机器人有限公司 | Mood pacifying system based on legal consultation robot |
| CN111368031A (en) * | 2020-02-29 | 2020-07-03 | 重庆百事得大牛机器人有限公司 | Deep self-learning system and method in legal consultation field |
| CN111368053B (en) * | 2020-02-29 | 2020-12-11 | 重庆百事得大牛机器人有限公司 | Mood pacifying system based on legal consultation robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109145106B (en) | 2022-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11645547B2 (en) | Human-machine interactive method and device based on artificial intelligence | |
| CN109033336A (en) | Legal advice robot and business model based on artificial intelligence | |
| CN109146726A (en) | A kind of artificial intelligence law consultation platform and business model | |
| CN107329967B (en) | Question answering system and method based on deep learning | |
| CN111653262B (en) | Intelligent voice interaction system and method | |
| US5870755A (en) | Method and apparatus for capturing and presenting digital data in a synthetic interview | |
| CN109002538A (en) | Legal advice cloud platform and method based on database | |
| WO2022095380A1 (en) | Ai-based virtual interaction model generation method and apparatus, computer device and storage medium | |
| US20100114684A1 (en) | Chat rooms search engine queryer | |
| CN109086371A (en) | A kind of semantic net interactive system and exchange method for legal advice | |
| CN110825858A (en) | Intelligent interaction robot system applied to customer service center | |
| CN108920706A (en) | A kind of legal advice consulting Database and its construction method | |
| CN107609736A (en) | A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology | |
| CN109033083A (en) | A kind of legal advice system based on semantic net | |
| CN112364234A (en) | Automatic grouping system for online discussion | |
| CN109145106A (en) | A kind of self-learning type legal advice robot | |
| CN109108989A (en) | A kind of legal services special purpose robot of semantics recognition | |
| TW202036323A (en) | Intelligent online customer service convergence core system which can provide a reply or query to an intention generated through voice recognition and natural language processing procedures | |
| CN110321414B (en) | Artificial intelligence consultation service method and system based on deep learning | |
| CN109086368A (en) | A kind of legal advice robot based on artificial intelligence cloud platform | |
| CN109086372A (en) | It is a kind of based on artificial intelligence application in the more wheel session methods and system of legal advice | |
| CN110414465B (en) | Emotion analysis method for video communication | |
| CN111858884A (en) | Method and system for robot to learn real person deep dialogue content | |
| CN109146725A (en) | It is a kind of for support robot provide legal advice service cloud platform | |
| CN109165281A (en) | A kind of shared legal advice system of multirobot terminal based on semantic net |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200107 Address after: 401147 Office 1, building 18, xiangnai mansion, Zhongyu, No. 101, Xinji Avenue, Longxi street, Yubei District, Chongqing Applicant after: Chongqing best Daniel robot Co.,Ltd. Address before: 401147 Nineteen Floors, 7 Chennai Mansion, No. 99 Xinji Avenue, Yubei District, Chongqing Applicant before: Wu Yi |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Office 1, 18, building 7, Zhongyu xiangnai mansion, No. 101, Xinji Avenue, Longxi street, Yubei District, Chongqing Patentee after: Chongqing Daniu Cognitive Technology Co.,Ltd. Address before: Office 1, 18, building 7, Zhongyu xiangnai mansion, No. 101, Xinji Avenue, Longxi street, Yubei District, Chongqing Patentee before: Chongqing best Daniel robot Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |