CN107292776A - The law of identity-based identification recommends method and system - Google Patents
The law of identity-based identification recommends method and system Download PDFInfo
- Publication number
- CN107292776A CN107292776A CN201710436215.1A CN201710436215A CN107292776A CN 107292776 A CN107292776 A CN 107292776A CN 201710436215 A CN201710436215 A CN 201710436215A CN 107292776 A CN107292776 A CN 107292776A
- Authority
- CN
- China
- Prior art keywords
- law
- case
- information
- identity
- parameter
- 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
-
- 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
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
Abstract
A kind of law of identity-based identification recommends method, and it comprises the following steps:S1, the identity to user are identified;S2, according to recognition result adjust law Generalization bounds;Law recommendation is carried out according to the law Generalization bounds of selection;S3, law recommendation results are shown to user.The present invention also provides a kind of law commending system of identity-based identification.
Description
Technical field
The present invention relates to big data technical field, more particularly to a kind of law of identity-based identification recommends method and is
System.
Background technology
With the constantly improve of laws of China, and iterative method disclosed in legal precedent so that the application of lawsuit legal precedent
Become possibility.
But the retrieval on legal information information also rests on the comparison primary stage in the prior art:User's selection is told
Lawsuit example classification information, inputs some keywords, system will contain the case of above-mentioned keyword automatically in the type lawsuit case
Example shows user.
Firstth, the case that may be returned so is retrieved more, it is impossible to easy-to-read;Secondth, there is lawsuit merit similar
Situation, there are many conflicting legal precedents;3rd, ordinary people, lawyer, method official rank can not be taken into account because identity, specialty
Degree is different, and the result unification of return, personalization level is not high, it is impossible to meet the individual demand of different crowd.
The content of the invention
In view of this, the present invention provides a kind of law recommendation method and system of identity-based identification.
A kind of law of identity-based identification recommends method, and it comprises the following steps:
S1, the identity to user are identified;
S2, according to recognition result adjust law Generalization bounds;Law recommendation is carried out according to the law Generalization bounds of selection;
S3, law recommendation results are shown to user.
The present invention also provides a kind of law commending system of identity-based identification, and it includes such as lower unit:
User identity identification unit, is identified for the identity to user;
Information recommendation unit, for adjusting law Generalization bounds according to recognition result;According to the law Generalization bounds of selection
Carry out law recommendation;
Information display unit, for law recommendation results to be shown to user.
Advantageous effects:The present invention relative to prior art, can realize:Known by the identity to user
Not;Law Generalization bounds are adjusted according to recognition result;Law recommendation is carried out according to the law Generalization bounds of selection;Law is recommended
As a result shown to user so that different crowds can be concerned about oneself point interested, reduce the amount of reading of user.
Brief description of the drawings
Fig. 1 is that the law of identity-based identification provided in an embodiment of the present invention recommends method flow diagram.
Embodiment
As shown in figure 1, in embodiments of the present invention, a kind of law of identity-based identification recommends method, and it includes as follows
Step:
S1, the identity to user are identified;
S2, according to recognition result adjust law Generalization bounds;Law recommendation is carried out according to the law Generalization bounds of selection;
S3, law recommendation results are shown to user.
Advantageous effects:The present invention relative to prior art, can realize:Known by the identity to user
Not;Law Generalization bounds are adjusted according to recognition result;Law recommendation is carried out according to the law Generalization bounds of selection;Law is recommended
As a result shown to user so that different crowds can be concerned about oneself point interested, reduce the amount of reading of user.
In the law recommendation method that identity-based of the present invention is recognized,
The step S1 includes:
The identity of user is identified and is identified result, the recognition result includes:
Suitor, defendant, in cube.
Alternatively, the suitor, defendant include party oneself, or its attorney.The neutrality side is permissible
Including judge, or the lawyer or scholar studied just to merit.Specific implementation can be as follows:Shown to user
The side of telling, defendant, in cube button, and the click information of user is obtained, according to identity of the click information of user to user
It is identified and is identified result.
In the law recommendation method that identity-based of the present invention is recognized,
The step S2 includes following sub-step:
S21, access legal precedent database;Obtain legal precedent and add local.
Legal precedent database can be " Chinese judgement document's net ", " Intellectual Property in China judgement document net " etc., the present invention
It is without limitation.Obtain after judging and add in local server, it is to avoid think the effect that network speed influence is recommended.It is excellent
Choosing is stored legal precedent with word or txt forms, is convenient for information extraction.
S22, by legal precedent in local case database according to trial rank, obtain the first effect case, the second effect case,
3rd effect case, the 3rd effect case, the 4th effect case;
Although our countries are not case law countries, higher court can receive to refuse to obey the appeal of inferior court's judgement
Case, therefore according to the setting of current level Four people's court of China, by legal precedent in local case database according to trial rank,
The first effect case, the second effect case, the 3rd effect case, the 3rd effect case, the 4th effect case is obtained to be divided,
It can realize when legal precedent is clashed, selection suitably refers to legal precedent.
Preferably for the first effect case, the second effect case, the 3rd effect case, the 3rd effect case, quadruple effect
Power case sets following rule, if the rank shown by user profile information judges that parameter is pointed in the 4th effect legal precedent correspondence
During rank law court, the effect cases of the 3rd effect case > the second effect cases > of the first effect case > the 4th;If user believes
Rank shown by breath information judges that parameter is pointed in the 3rd effect legal precedent corresponding level law court, the first effect case > second
The effect cases of the 3rd effect case > of effect case > the 4th;If the rank shown by user profile information judges that parameter is pointed to
In the second effect legal precedent corresponding level law court, the effect case > quadruple effects of first effect case > the second effect cases > the 3rd
Power case;If the rank shown by user profile information judges that parameter is pointed in the first effect legal precedent corresponding level law court,
The effect cases of first the 3rd effect case > of effect case > the second effect case > the 4th.Corresponding first effect case correspondence
Most Supreme Court, Supreme Court of the second effect case correspondence province, the 3rd effect case correspondence intermediate court, the 4th effect case correspondence grass-roots court.
Rank shown by user profile information judges that parameter is pointed to can be by extracting key value in the upload information that is provided from user
Obtain administration class information in information to obtain, rank judges that parameter is jurisdiction rank.
S23, by the first effect case, the second effect case, the 3rd effect case, the 3rd effect case, the 4th effect case
Example is direct case database, reference case database according to region division.
In above-mentioned steps, direct case database be the whole nation, province, city of subordinate of province, district one-level law court of subordinate of city, directly
Case database is stronger in actual pendente lite referential, is used as direct case database;If can not in direct case database
The case of correlation is matched, or the case matched is less desirable for suitor or defendant, can be by reference
Case database is matched, and is used as the support of pendente lite case.In the prior art, user often can only be by artificial to magnanimity
Case scan for and match, can not often correctly find and can be used in reference, it is and favourable to one's own side, and to other side
The case that can favorably point out, by the present embodiment step, can be divided according to effect availability on to greatest extent, and
And find accurately, look for full reference case.Such as, together in case, CROSS REFERENCE can not be found in prosecution law court and with the court, or
Person can not find the case favourable to one's own side, then be expanded to reference case database and scan for, and can expand database, and
And while looking into complete, the case that be able to may be used to other side is prepared in advance.
S24, bibliographic information extraction is carried out to case in direct case database, reference case database, and set up
Bibliographic information and the mapping relations using rule.
Alternatively, in the law recommendation method of the identity-based identification described in the embodiment of the present invention,
The step S24 includes:
Case carries out bibliographic information extraction in direct case database, reference case database, and generation includes 7 degree of freedom
Model is put to the proof in the contrast of parameter, and seven characteristic parameters include case by parameter, the first evidence parameter, the second evidence parameter, card successively
According to intensive parameter, infer that model parameter, rank judge parameter, result parameter;Set up the mapping pass that model and case are put to the proof in contrast
System.
Preferably, case by parameter according to the case of most Supreme Court by mode classification by the different case of the formal definition of character string by
Parameter;Because case uses unified formatted data by statement in each court verdict, it can be obtained by the form of keyword extraction
Case is by parameter.
First evidence parameter, the second evidence parameter are identical in form, for suitor, the evidence that suitor provides
Type is the first evidence parameter, and the evidence that other side provides is the second evidence parameter;In turn, then conversely.First evidence parameter bag
Include the first proof backlog information;Second evidence parameter, which includes second, proves backlog information;In court verdict, it will usually by both sides'
Evidence is listed, and First Certificate parameter information, the second evidence parameter information are obtained by way of keyword extraction, such as with
Exemplified by deal contract dispute, contract evidence is the item that proof contract is set up, and payment voucher is to prove the item of contract performance.
Strength of confirmation parameter is set according to general strength of confirmation standard, it is alternatively possible to which it is public more than public affairs to be set to government's text
Demonstrate,prove document and be more than common document=material evidence more than words evidence, the public strength of confirmation of government's text is set to 3, notarial is set
For 3, common document is set to 2, material evidence is set to 3, words evidence strength of confirmation 1 is set to, and set words evidence
Cumulative rule, is added up according to witness's quantity.Or so that by taking deal contract dispute as an example, contract evidence is set up for proof contract
Item, strength of confirmation parameter is set to 2;Payment voucher is proves the item of contract performance, and corresponding strength of confirmation is joined
Number is set to 2.
It is that process letter is assert for the deduction of the first evidence parameter, the second evidence parameter by the rank law court to infer model parameter
Breath and major premise, minor premise assert procedural information;Law court was assert for the deduction of the first evidence parameter, the second evidence parameter
Journey information is to prove each in the first evidence parameter, the second evidence parameter receiving or the refusal information of backlog information, it is big before
Carry, minor premise assert that procedural information is carried out being simplified in the process of case reasoning, the embodiment of the present invention for some keywords,
And deduction relation is represented by " → ".
Rank judges parameter for the corresponding rank of the case, and specific manifestation form passes through 1/2/3/4 the first effect case of correspondence
Example, the second effect case, the 3rd effect case, the 3rd effect case, the 4th effect case.
Result parameter is wins a lawsuit, information of losing a lawsuit, and is represented by 1/0.
Above-mentioned seven characteristic parameters are included to case successively by parameter, the first evidence parameter, the second evidence parameter, strength of confirmation
Parameter, deduction model parameter, rank judge that parameter, result parameter are respectively converted into character string information, and will be each by separator
Individual characteristic parameter is separated.
S25, the identification result for obtaining user, determine to use Rule Information according to the identification result of user;
S26, the upload information that user's offer is provided;Crucial value information is provided in the upload information provided from user;
In the law recommendation method that identity-based of the present invention is recognized,
The step S26 includes:
Obtain the upload information that user provides;
Crucial value information is provided in the upload information provided from user;Key value is extracted in the upload information provided from user
Information is similar to the determination process of seven characteristic parameters, in determination process, can pass through Text region, speech recognition, prompting
The mode of user carries out information extraction and supplement.
Weights demarcation is carried out to the crucial value information of extraction according to the use Rule Information determined in step S25;
Weights demarcation is carried out by the crucial value information to extraction, mainly according to user identity identification result:Prosecution
Side, defendant, in cube.Emphasis per side's concern is different, then carries out weights demarcation by the crucial value information to extraction, will
The higher information of weight setting carries out priority match and display.Herein can be with flexible configuration.
The calibrated examples comparative model of weights has been carried out to generation according to the identification result of user.
S27, retrieved in directly management database according to the use Rule Information of determination, and judge whether with
The bibliographic information matched somebody with somebody, when matching bibliographic information, jumps to step S29;Otherwise step S28 is jumped to;
In the law recommendation method that identity-based of the present invention is recognized,
Retrieved, and judged in directly management database according to the use Rule Information of determination in the step S27
Whether the bibliographic information with matching includes:
S271, according to generation the calibrated examples comparative model of weights is carried out and judges whether to need pair to 7 degree of freedom parameter
Default process is carried out than putting to the proof characteristic parameter in model, when needing to carry out default process, step S272 is jumped to, otherwise redirects
To step S273;
S272, according to carried out weights calibrated examples comparative model the contrast of 7 degree of freedom parameter is put to the proof it is corresponding in model
Characteristic parameter carries out default process, and jumps to step S273;
By carrying out default process, data retrieval amount can be substantially reduced, recall precision is improved.
S273, model is put to the proof according to the contrast after default process retrieved in directly management database, and according to spy
Levy whether the matching judgment of parameter has the bibliographic information of matching.
S28, retrieved in reference to management database according to the use Rule Information of determination, and judge whether with
The bibliographic information matched somebody with somebody, when matching bibliographic information, jumps to step S29;
S29, counted by computation model according to crucial value information in step S26 and the bibliographic information matched
Calculate, obtain result of calculation.
In the law recommendation method that identity-based of the present invention is recognized,
The step S29 includes:
Obtain the calibrated examples comparative model of weights and the bibliographic information matched;
Obtain the corresponding contrast comprising 7 degree of freedom parameter of the bibliographic information matched and put to the proof model;
According to the law Generalization bounds of selection to the calibrated examples comparative model of weights and the 7 degree of freedom parameter matched
Contrast put to the proof model calculated, obtain law recommended entry.
According to the law Generalization bounds of selection to the calibrated examples comparative model of weights and the 7 degree of freedom parameter matched
Contrast put to the proof model calculated.
By recognizing that the contrast of the calibrated examples comparative model of weights and the 7 degree of freedom parameter matched is put to the proof in model
Each separator, obtains each single information.
Infer that contrast of the model parameter to 7 degree of freedom parameter is put to the proof the first evidence parameter of model, the second evidence and joined by combining
Number is evaluated, and evaluation result is receiving or does not receive;And calculate the first evidence ginseng in the calibrated examples comparative model of weights
The first evidence parameter of model, the similarity distance of the second evidence parameter are put to the proof in the contrast of number, the second evidence parameter and 7 degree of freedom parameter
Value.
Relevancy ranking is carried out to the case that the match is successful by similar distance and evaluation result, and passes through rank
Parameter is modified to ranking results obtains point of reference ranking sequence;According to result parameter to having carried out point of reference ranking sequence
Case carries out risk markers.
In the law recommendation method that identity-based of the present invention is recognized,
The step S3 includes:
Display recommendation is carried out after law recommended entry is adjusted according to the corresponding way of recommendation of user identity.
Alternatively, arrange to carry out display recommendation to oneself favourable result respectively for suitor, defendant, for neutrality
Ranking results are modified and obtain point of reference ranking sequence by side by level parameters;And retain risk markers.
The embodiment of the present invention also provides a kind of law commending system of identity-based identification, and it includes such as lower unit:
User identity identification unit, is identified for the identity to user;
Information recommendation unit, for adjusting law Generalization bounds according to recognition result;According to the law Generalization bounds of selection
Carry out law recommendation;
Information display unit, for law recommendation results to be shown to user.
Present invention method embodiment is one-to-one with system embodiment, and embodiment of the method can also be used for extension
System embodiment.The embodiment of each in this specification is described by the way of progressive, what each embodiment was stressed be with
Between the difference of other embodiment, each embodiment identical similar portion mutually referring to.
It is understood that for the person of ordinary skill of the art, can be done with technique according to the invention design
Go out other various corresponding changes and deformation, and all these changes and deformation should all belong to the protection model of the claims in the present invention
Enclose.
Claims (9)
1. a kind of law of identity-based identification recommends method, it is characterised in that it comprises the following steps:
S1, the identity to user are identified;
S2, according to recognition result adjust law Generalization bounds;Law recommendation is carried out according to the law Generalization bounds of selection;
S3, law recommendation results are shown to user.
2. the law of identity-based identification as claimed in claim 1 recommends method, it is characterised in that
The step S1 includes:
The identity of user is identified and is identified result, the recognition result includes:
Suitor, defendant, in cube.
3. the law of identity-based identification as claimed in claim 2 recommends method, it is characterised in that
The step S2 includes following sub-step:
S21, access legal precedent database;Obtain legal precedent and add local;
S22, by legal precedent in local case database according to trial rank, obtain the first effect case, the second effect case, the 3rd
Effect case, the 3rd effect case, the 4th effect case;
S23, the first effect case, the second effect case, the 3rd effect case, the 3rd effect case, the 4th effect case pressed
It is direct case database, reference case database according to region division;
S24, in direct case database, reference case database case carry out bibliographic information extraction, and set up record
Project information and the mapping relations using rule;
S25, the identification result for obtaining user, determine to use Rule Information according to the identification result of user;
S26, the upload information that user's offer is provided;Crucial value information is provided in the upload information provided from user;
S27, retrieved according to the use Rule Information of determination, and judged whether with matching in directly management database
Bibliographic information, when matching bibliographic information, jumps to step S29;Otherwise step S28 is jumped to;
S28, retrieved according to the use Rule Information of determination, and judged whether with matching in reference to management database
Bibliographic information, when matching bibliographic information, jumps to step S29;
S29, calculated by computation model according to crucial value information in step S26 and the bibliographic information matched,
Obtain result of calculation.
4. the law of identity-based identification as claimed in claim 3 recommends method, it is characterised in that
The step S24 includes:
Case carries out bibliographic information extraction in direct case database, reference case database, and generation includes 7 degree of freedom parameter
Contrast put to the proof model, seven characteristic parameters successively include case it is strong by parameter, the first evidence parameter, the second evidence parameter, evidence
Degree parameter, deduction model parameter, rank judge parameter, result parameter;Set up the mapping relations that model and case are put to the proof in contrast.
5. the law of identity-based identification as claimed in claim 4 recommends method, it is characterised in that
The step S26 includes:
Obtain the upload information that user provides;
Crucial value information is provided in the upload information provided from user;
Weights demarcation is carried out to the crucial value information of extraction according to the use Rule Information determined in step S25;
The calibrated examples comparative model of weights has been carried out to generation according to the identification result of user.
6. the law of identity-based identification as claimed in claim 5 recommends method, it is characterised in that
Retrieved, and judged whether in directly management database according to the use Rule Information of determination in the step S27
Bibliographic information with matching includes:
S271, the calibrated examples comparative model of weights has been carried out according to generation judge whether to need the contrast to 7 degree of freedom parameter to lift
Characteristic parameter carries out default process in model of a syndrome, when needing to carry out default process, jumps to step S272, otherwise jumps to step
Rapid S273;
S272, individual features in model are put to the proof to the contrast of 7 degree of freedom parameter according to having carried out weights calibrated examples comparative model
Parameter carries out default process, and jumps to step S273;
S273, model is put to the proof according to the contrast after default process retrieved in directly management database, and joined according to feature
Whether several matching judgments has the bibliographic information of matching.
7. the law of identity-based identification as claimed in claim 6 recommends method, it is characterised in that
The step S29 includes:
Obtain the calibrated examples comparative model of weights and the bibliographic information matched;
Obtain the corresponding contrast comprising 7 degree of freedom parameter of the bibliographic information matched and put to the proof model;
According to the law Generalization bounds of selection to the calibrated examples comparative model of weights and pair of the 7 degree of freedom parameter matched
Calculated than putting to the proof model, obtain law recommended entry.
8. the law of identity-based identification as claimed in claim 7 recommends method, it is characterised in that
The step S3 includes:
Display recommendation is carried out after law recommended entry is adjusted according to the corresponding way of recommendation of user identity.
9. a kind of law commending system of identity-based identification, it is characterised in that it includes such as lower unit:
User identity identification unit, is identified for the identity to user;
Information recommendation unit, for adjusting law Generalization bounds according to recognition result;Carried out according to the law Generalization bounds of selection
Law is recommended;
Information display unit, for law recommendation results to be shown to user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710436215.1A CN107292776B (en) | 2017-06-12 | 2017-06-12 | Legal recommendation method and system based on identity recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710436215.1A CN107292776B (en) | 2017-06-12 | 2017-06-12 | Legal recommendation method and system based on identity recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107292776A true CN107292776A (en) | 2017-10-24 |
CN107292776B CN107292776B (en) | 2020-06-12 |
Family
ID=60096448
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710436215.1A Active CN107292776B (en) | 2017-06-12 | 2017-06-12 | Legal recommendation method and system based on identity recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107292776B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN113626700A (en) * | 2021-08-09 | 2021-11-09 | 深圳市鼎法科技有限公司 | Lawyer recommendation method, system and equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20110068277A (en) * | 2009-12-15 | 2011-06-22 | 한국발명진흥회 | Patent rating system and rating factor information processing method of the same system |
CN102970606A (en) * | 2012-12-04 | 2013-03-13 | 深圳Tcl新技术有限公司 | Television program recommending method and device based on identity identification |
CN103995867A (en) * | 2014-05-20 | 2014-08-20 | 中国科学院重庆绿色智能技术研究院 | Character identification matching and process collaboration method and system in medical technology transformation |
CN105225177A (en) * | 2015-09-14 | 2016-01-06 | 福建风林火山信息技术有限公司 | A kind of law court's self-help serving system and method for servicing thereof |
CN105930336A (en) * | 2016-03-28 | 2016-09-07 | 安阳师范学院 | Environmental law case storage and query system |
-
2017
- 2017-06-12 CN CN201710436215.1A patent/CN107292776B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20110068277A (en) * | 2009-12-15 | 2011-06-22 | 한국발명진흥회 | Patent rating system and rating factor information processing method of the same system |
CN102970606A (en) * | 2012-12-04 | 2013-03-13 | 深圳Tcl新技术有限公司 | Television program recommending method and device based on identity identification |
CN103995867A (en) * | 2014-05-20 | 2014-08-20 | 中国科学院重庆绿色智能技术研究院 | Character identification matching and process collaboration method and system in medical technology transformation |
CN105225177A (en) * | 2015-09-14 | 2016-01-06 | 福建风林火山信息技术有限公司 | A kind of law court's self-help serving system and method for servicing thereof |
CN105930336A (en) * | 2016-03-28 | 2016-09-07 | 安阳师范学院 | Environmental law case storage and query system |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN113626700A (en) * | 2021-08-09 | 2021-11-09 | 深圳市鼎法科技有限公司 | Lawyer recommendation method, system and equipment |
CN113626700B (en) * | 2021-08-09 | 2023-08-22 | 深圳市鼎法科技有限公司 | Lawyer recommendation method, system and equipment |
Also Published As
Publication number | Publication date |
---|---|
CN107292776B (en) | 2020-06-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104199822B (en) | It is a kind of to identify the method and system for searching for corresponding demand classification | |
Shahin et al. | Big data and the illusion of choice: Comparing the evolution of India’s aadhaar and China’s social credit system as technosocial discourses | |
CN103593474B (en) | Image retrieval sort method based on deep learning | |
CN105787025B (en) | Network platform public account classification method and device | |
CN105488233A (en) | Reading information recommendation method and system | |
US20100153094A1 (en) | Topic map based indexing and searching apparatus | |
US20150205580A1 (en) | Method and System for Sorting Online Videos of a Search | |
CN107423374A (en) | Law based on classification annotation recommends method and system | |
US10997368B2 (en) | Resolving ambiguity in a statement | |
CN110134792B (en) | Text recognition method and device, electronic equipment and storage medium | |
WO2009014361A2 (en) | Method, system, and computer readable recording medium for filtering obscene contents | |
CN109325115B (en) | Role analysis method and analysis system | |
CN108228867A (en) | A kind of theme collaborative filtering recommending method based on viewpoint enhancing | |
CN115380284A (en) | Unstructured text classification | |
CN114332680A (en) | Image processing method, video searching method, image processing device, video searching device, computer equipment and storage medium | |
CN107943514A (en) | The method for digging and system of core code element in a kind of software document | |
EP3616185A1 (en) | Cue data model implementation for adaptive presentation of collaborative recollections of memories | |
CN108241619A (en) | A kind of recommendation method based on the more interest of user | |
CN109902229A (en) | A kind of interpretable recommended method based on comment | |
CN107292776A (en) | The law of identity-based identification recommends method and system | |
CN111125457A (en) | Deep cross-modal Hash retrieval method and device | |
Omara et al. | Deep features for efficient multi-biometric recognition with face and ear images | |
Chu et al. | Blog article summarization with image-text alignment techniques | |
Iliev et al. | Information retrieval and recommendation using emotion from speech signals | |
CN114781348B (en) | Text similarity calculation method and system based on word bag model |
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: 20200519 Address after: 210000 709, 7th floor, building D, yunmi City, No. 19, ningshuang Road, Yuhuatai District, Nanjing City, Jiangsu Province Applicant after: Nanjing Hangxing video information technology Co., Ltd Address before: 430000 East Lake New Technology Development Zone, Wuhan City, Hubei Province Applicant before: WUHAN KANGHUIRAN INFORMATION TECHNOLOGY CONSULTING Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |