CN108563773A - The accurate search ordering method of legal provision of knowledge based collection of illustrative plates - Google Patents
The accurate search ordering method of legal provision of knowledge based collection of illustrative plates Download PDFInfo
- Publication number
- CN108563773A CN108563773A CN201810361909.8A CN201810361909A CN108563773A CN 108563773 A CN108563773 A CN 108563773A CN 201810361909 A CN201810361909 A CN 201810361909A CN 108563773 A CN108563773 A CN 108563773A
- Authority
- CN
- China
- Prior art keywords
- theme
- descriptor
- legal
- weights
- search
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of accurate search ordering methods of legal provision of knowledge based collection of illustrative plates, include the following steps：S101, input keyword to be searched；S102, it is obtained from legal knowledge spectrum model and the descriptor of Keywords matching to be searched and the conjunctive word of the descriptor, formation theme dictionary；S103, according to and core subject in legal knowledge spectrum model incidence relation, dynamic generation with a case by theme dictionary in descriptor and its conjunctive word weights；S104, the sub-combinations for obtaining theme dictionary, it is m, the sub-combinations of m 1, m 2 ... 2 to sequentially form element number；S105, theme word combination of the descriptor formation eventually for search is respectively taken out from each sub-combinations；S106, in the theme word combination eventually for search number and the total weight of keyword be according to being ranked up to all sub-combinations；S107, it is scanned in legal provision database using the theme word combination selected after sequence, and display is ranked up to search result.
Description
Technical field
The present invention relates to legal provision search ordering methods, and in particular to a kind of legal provision of knowledge based collection of illustrative plates is accurate
Retrieval and search result priority ordering method.
Background technology
Strengthen the legal system China Reconstructs, promotes the basic principle of ruling the country by law particularly important, administration according to law is the weight run the country according to law
Want link.In each judicial case, all cases must all adjudge, judicial personnel, which removes, relies on own service knowledge and experience
Outside, it is often necessary to retrieve the legal provision arrived involved in pending case, precisely, efficiently carry out the retrieval of legal provision into department
The active demand of method staff other legal provisions reseaching staff.
With the universal and Efficient Operation of artificial intelligence, a kind of rudimentary knowledge expression side of the knowledge mapping as artificial intelligence
Method has been introduced into legal provision searching field.Knowledge mapping (Knowledge Graph) describes concept, the reality of objective world
Body, event and its between relationship, describe legal provision using knowledge mapping, so that the law article concept of each class is together in series, generally
The relationship of thought is more clear, and the retrieval for legal provision on this basis is more precisely, efficiently.
Since existing legal provision retrieval ordering method on the basis of keyword match degree based on realizing, such as
Fruit will not be that legal concept in legal provision is retrieved as keyword, it is possible to judicial personnel be caused at work can not
Ideal legal provision searching order is obtained as a result, needing to change keyword repeatedly and adjusting crucial combinatorics on words repeatedly
Mode can just search available legal provision result.
Invention content
The technical problem to be solved in the present invention is to be directed to the prior art in the retrieval of legal provision by not being law
Concept, which carries out retrieval, can not obtain the defect of ideal legal provision retrieval result, provide a kind of law item of knowledge based collection of illustrative plates
The accurate search ordering method of text.
The technical solution adopted by the present invention to solve the technical problems is：
A kind of accurate search ordering method of legal provision of knowledge based collection of illustrative plates is provided, is included the following steps：
S101, input keyword to be searched；
S102, it is obtained and the descriptor of Keywords matching to be searched and the pass of the descriptor from legal knowledge spectrum model
Join word, forms theme dictionary；Conjunctive word includes：Upper theme, the next theme and label synonym；Wherein, upper theme refers to
The big theme of representative range, the next theme refer to the small theme of representative range, and label synonym is fixed in the label
The similar theme of representative range of justice；Descriptor attribute includes：Descriptor title and descriptor weights, weights ranging from (0,1)；
S103, according to and core subject in legal knowledge spectrum model incidence relation, dynamic generation with a case by master
The weights of the descriptor and its conjunctive word in library are write inscription, the higher explanation of weights and the range that core subject represents are closer；
S104, the sub-combinations for obtaining theme dictionary, it is m, the sub-combinations of m-1, m-2 ... 2 to sequentially form number；
S105, theme word combination of the descriptor formation eventually for search is respectively taken out from each sub-combinations；
S106, in the theme word combination eventually for search number and the total weight of keyword be according to all sons
Collection combination is ranked up；
S107, it is scanned in legal provision database using the theme word combination selected after sequence, and search is tied
Fruit is ranked up display.
Above-mentioned technical proposal is connect, according to the search result in legal provision database, association is adjusted within the scope of weights
The weights of word.
It connects above-mentioned technical proposal, in step S107, when search, records each descriptor in theme word combination in law
Corresponding position and there is the number of descriptor in provision document, according to occurring the number of descriptor in legal provision document to method
Rule provision is ranked up, and the most legal provision of occurrence number comes search result and presents up front.
Above-mentioned technical proposal is connect, the legal knowledge spectrum model is according to the file progress to constructed legal knowledge collection of illustrative plates
It parses and converts and generate, the legal knowledge spectrum model is to same a case by the descriptor of Related Cases according to three main aspects
Tissue is carried out, is classified again to each aspect, the theme being related to it in each classification represent the analysis of range, fixed
Upper and lower between adopted theme or apposition；Three main aspects include main body, rights and obligations and object, juristic fact.
Above-mentioned technical proposal is connect, the descriptor weights being matched to are 1.0, upper theme, the next theme and upper bottom
The weights of the label synonym of theme are 0.5.
Connect above-mentioned technical proposal, the descriptor weights being matched to be 1.0, the upper theme of n-th layer, n-th layer bottom theme,
The weights of the label synonym of the next theme are 0.5 in n-th layern, wherein n is natural number.
The present invention also provides a kind of accurate searching order systems of the legal provision of knowledge based collection of illustrative plates, including：
Input module, for inputting keyword to be searched；
Theme dictionary generation module, for obtaining the theme with Keywords matching to be searched from legal knowledge spectrum model
The conjunctive word of word and the descriptor forms theme dictionary；Conjunctive word includes：Upper theme, the next theme and label synonym；Its
In, upper theme refers to the big theme of representative range, and the next theme refers to the small theme of representative range, and label is synonymous
Word is the similar theme of representative range defined in the label；Descriptor attribute includes：Descriptor title and descriptor weights, power
Value ranging from (0,1]；
Weights generation module, for according to the incidence relation with core subject in legal knowledge spectrum model, dynamic generation
With a case by theme dictionary in descriptor and its conjunctive word weights, weights it is higher explanation with core subject represent range
It is closer；
Sub-combinations generation module, the sub-combinations for obtaining theme dictionary, it is m, m-1, m-2 ... to sequentially form number
2 sub-combinations；Theme word combination of the descriptor formation eventually for search is respectively taken out from each sub-combinations；With most
The number in the theme word combination for searching for and the total weight of keyword are that foundation is ranked up all sub-combinations eventually；
Search result display module, for being carried out in legal provision database using the theme word combination selected after sequence
Search, and display is ranked up to search result.
The present invention also provides a kind of computer readable storage mediums, including the computer program that can be executed by processor,
The legal provision that the computer program specifically executes the knowledge based collection of illustrative plates as described in any one of claim 1-5 is precisely searched for
Sort method.
The beneficial effect comprise that：The present invention describes the logic between law descriptor using legal knowledge collection of illustrative plates
Logical relation between relationship, descriptor and other statement vocabulary, is obtained by parsing for legal knowledge collection of illustrative plates and analysis
The theme dictionary of keyword to be searched, in theme dictionary descriptor and conjunctive word carry out weights setting, pass through combined weights
The foundation that the height of value is searched for as priority is ranked up search result.
Description of the drawings
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing：
Fig. 1 is the flow chart of the accurate search ordering method of legal provision of the knowledge based collection of illustrative plates of the embodiment of the present invention one；
Fig. 2 is the flow chart of the accurate search ordering method of legal provision of the knowledge based collection of illustrative plates of the embodiment of the present invention two；
Fig. 3 is the legal knowledge collection of illustrative plates about proprietary.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, the accurate search ordering method of the legal provision of knowledge based collection of illustrative plates is main in the embodiment of the present invention one
Include the following steps：
S101, input keyword to be searched；
S102, it is obtained and the descriptor of Keywords matching to be searched and the pass of the descriptor from legal knowledge spectrum model
Join word, forms theme dictionary；Conjunctive word includes：Upper theme, the next theme and label synonym；Wherein, upper theme refers to
The big theme of representative range, the next theme refer to the small theme of representative range, and label synonym is fixed in the label
The similar theme of representative range of justice；Descriptor attribute includes：Descriptor title and descriptor weights, weights ranging from (0,1]；
S103, according to and core subject in legal knowledge spectrum model incidence relation, dynamic generation with a case by master
The weights of the descriptor and its conjunctive word in library are write inscription, the higher explanation of weights and the range that core subject represents are closer；
S104, the sub-combinations for obtaining theme dictionary, it is m, the sub-combinations of m-1, m-2 ... 2 to sequentially form number；
S105, theme word combination of the descriptor formation eventually for search is respectively taken out from each sub-combinations；
S106, in the theme word combination eventually for search number and the total weight of keyword be according to all sons
Collection combination is ranked up；
S107, it is scanned in legal provision database using the theme word combination selected after sequence, and search is tied
Fruit is ranked up display.
It further, can be according to practical situation within the scope of weights according to the search result in legal provision database
Adjust the weights of conjunctive word.
In step S107, when search, it is corresponding in legal provision document to record each descriptor in theme word combination
Position and there is the number of descriptor, legal provision is arranged according to the number for descriptor occur in legal provision document
Sequence, the most legal provision of occurrence number come search result and present up front.
The legal knowledge spectrum model is parsed and is converted and given birth to according to the file to constructed legal knowledge collection of illustrative plates
At the legal knowledge spectrum model carries out tissue by the descriptor of Related Cases to same a case according to three main aspects, to every
A aspect is classified again, and the theme being related to it in each classification represent the analysis of range, is defined between theme
Upper and lower or apposition；Three main aspects include main body, rights and obligations object, juristic fact.
The descriptor weights being matched to are 1.0, upper theme, the next theme and upper the next theme label synonym
Weights be 0.5-1, the number of plies is incremented by successively, and weights also change therewith.
To realize the above method, the present invention also provides the accurate searching order system of the legal provision of knowledge based collection of illustrative plates,
Including：
Input module, for inputting keyword to be searched；
Theme dictionary generation module, for obtaining the theme with Keywords matching to be searched from legal knowledge spectrum model
The conjunctive word of word and the descriptor forms theme dictionary；Conjunctive word includes：Upper theme, the next theme and label synonym；Its
In, upper theme refers to the big theme of representative range, and the next theme refers to the small theme of representative range, and label is synonymous
Word is the similar theme of representative range defined in the label；Descriptor attribute includes：Descriptor title and descriptor weights, power
Value is ranging from (0,1)；
Weights generation module, for according to the incidence relation with core subject in legal knowledge spectrum model, dynamic generation
With a case by theme dictionary in descriptor and its conjunctive word weights, weights it is higher explanation with core subject represent range
It is closer；
Sub-combinations generation module, the sub-combinations for obtaining theme dictionary, it is m, m-1, m-2 ... to sequentially form number
2 sub-combinations；Theme word combination of the descriptor formation eventually for search is respectively taken out from each sub-combinations；With most
The number in the theme word combination for searching for and the total weight of keyword are that foundation is ranked up all sub-combinations eventually；
Search result display module, for being carried out in legal provision database using the theme word combination selected after sequence
Search, and display is ranked up to search result.
The method of the present invention may be stored in computer readable storage medium comprising the calculating that can be executed by processor
Machine program, the computer program specifically execute the accurate searching order side of legal provision of the knowledge based collection of illustrative plates of above-described embodiment
Method.
As shown in Fig. 2, the legal provision search ordering method of the knowledge based collection of illustrative plates of the embodiment of the present invention two, including it is following
Step：
S01, domain expert build legal knowledge collection of illustrative plates in MindManager tools；
S02 generates law knowledge mapping model KGModel by the parsing and conversion for legal knowledge collection of illustrative plates file
(hereinafter, legal knowledge spectrum model abbreviation KGModel), wherein KGModel to same a case by Related Cases descriptor according to
Three main aspects (including main body, rights and obligations and object, juristic fact) carry out tissue, classify again in each aspect
(such as main body is further divided into natural person, self-employed entrepreneur and legal person), the theme being related to it in each classification carry out generation
The analysis of table range defines upper and lower or apposition between theme；
S03 imports legal provision database, has legal provision document in database；
S04, inputs keyword combination to be searched, and keyword is typically three aspects (main body, rights and obligations, juristic fact)
Respectively propose a crucial phrase at combination；
S05 is obtained and the descriptor of Keywords matching to be searched and conjunctive word (such as Fig. 3 of the descriptor from KGModel
Shown, KGModel includes：Upper theme SupTopic, bottom theme SubTopic and label synonym Label) (wherein,
Descriptor attribute includes：Descriptor title and descriptor weights), form theme dictionary；(weights explanation：Weights ranging from (0,
1].The descriptor weights being matched to are the label of 1.0,1 layer of upper theme (the next theme) and upper theme (the next theme)
The weights of synonym are 0.5, and the upper theme (the next theme) of the upper theme of n-layer (the next theme) and its corresponding label are same
The weights of adopted word are 0.5n；For convenience of description, the theme number of plies of embodiment is 3 layers, and the theme number of plies can be according to needing to set)
S06, for same a case by theme dictionary in descriptor and its conjunctive word weights with practical semantic association feelings
Subject to condition, its weights can suitably be adjusted within the scope of weights；
S07 obtains the sub-combinations of theme dictionary, such as：Descriptor number is m in theme dictionary, then sequentially forms member
Plain number is m, the sub-combinations of m-1, m-2 ... 2；
S08 respectively takes out theme phrase of element (descriptor) formation eventually for search from n sub-combinations
It closes；
S09, in the theme word combination eventually for search number (preferential) and theme word combination in keyword always weigh
Weight (secondly) is that foundation is ranked up all combinations；
S10, using combination sequence theme word combination scanned in legal provision database and to search result into
Row sequencing display.When search, by each descriptor in theme word combination in legal provision document corresponding position (law
When provision database imports, all legal subject matter words can search for one in legal provision database document in legal knowledge collection of illustrative plates
Time, the position that occurs in legal provision document of record descriptor is stored in XML document) intersection is done, according to occurring in document
The number of descriptor is ranked up legal provision, and the foremost that the most legal provision of occurrence number comes search result is in
It is existing.
For the above method is expanded on further, it is described below in conjunction with specific law application scenarios：
One, scene description
(1) case:
A property firms sign project construction contract with B building constructors, and agreement is that company A undertakes the construction of one by B companies
The commercial house.After contract signing, to raise engineering construction fund, company A signs loan contract with C banks, from company A to C banks
Provide a loan 30,000,000 yuan, at the same company A with the right to use of the housing sites of its exploitation as mortgage, carried on a shoulder pole for above-mentioned debt
It protects.Afterwards because company A cannot repay C bank loans, C banks are intended to exercise the housing sites of company A and the commercial house of exploitation
Hypothec.
(2) judicial personnel needs inquiry problem:
The commercial house security enforcement that can C banks develop company A
(3) it is used for the keyword (input keyword) of search：
" the commercial house ", " security enforcement "
Two, specific steps
Step 1：Importing in embodiment needs legal knowledge collection of illustrative plates to be used (by domain expert in MindManager tools
Middle structure) (as shown in Figure 3)；
Step 2：It is legal knowledge map construction model automatically by the parsing and conversion to legal knowledge collection of illustrative plates file,
Form theme dictionary；
Step 3：Legal provision database is imported, has legal provision document in database；
Step 4：Input the keyword for search in embodiment：" the commercial house, security enforcement "；
Step 5：The automatic similarity for calculating the descriptor in the theme dictionary that " the commercial house " word and KGModel are formed,
Obtain the conjunctive word with the matched descriptor of " the commercial house " word and the descriptor；" security enforcement " is similar, successively automatically into
Row matching.Matching result is shown in Table A- Keywords matching result tables；
Table A-Keywords matching result table
Step 6：According to case by practical semantic association situation the weights in Keywords matching result are adjusted, herein
It is not altered；Such as：The weights of property are 0.5, if reseaching staff thinks that the word is little with merit correlation in the present case, can be incited somebody to action
Its weights is changed to the arbitrary value of section (0,0.5), is then inquired；
Step 7：Use Keywords matching result and modified weights (when unmodified, using the original weights being matched to)
It is combined；Wherein, if keyword is not matched to identical descriptor therewith, such as above-mentioned " security enforcement " one
Word, when matching, fail to find the descriptor exactly matched, can be by the power of " security enforcement " word input by user in combination
Value is assigned to 0.9, is inserted into theme dictionary；
Step 8：Obtain the sub-combinations of theme dictionary：It is k (k when obtaining descriptor number>1) element is sequentially formed when is
K, k-1 ..., 2, total (2^k)-k kind collective combinations；1 kind of collective combinations, i.e. its theme set of words being matched to are obtained as k=1
Itself；When k is not 1, an element (descriptor) is respectively taken out from above-mentioned (2^k)-k kind collective combinations and forms a kind of final use
In the theme word combination of search.As in above-mentioned 2 yuan of collective combinations, it is assumed that a kind of binary collective combinations are (A, B), wherein set A
Middle element is that element is { b1, b2 } in { a1, a2 }, set B, then the descriptor that can be formed be combined as [a1b1], [a1b2],
[a2b1]、[a2b2]；
Step 9：Be k eventually for the number in the theme word combination of search, in theme word combination the total weight of keyword according to
It is varied from according to law databases, with the number (preferential) of theme word combination and total weight (secondly) is according to all when sequence
Phrase combination be ranked up；
Step 10：It is scanned in legal provision database using the theme word combination of combination sequence.When search, it will use
Each descriptor in the theme word combination that the word to be searched (" the commercial house " " security enforcement ") of family input is formed is in law
(when legal provision database imports, all legal subject matter words can be in legal knowledge collection of illustrative plates for corresponding position in provision document
It is searched for one time in legal provision database document, XML texts are stored in the position that record descriptor occurs in legal provision document
In shelves) intersection is done, legal provision is ranked up according to the number for occurring descriptor in document, the most law item of occurrence number
The foremost that text comes search result is presented.
To sum up, the present invention can be obtained using the legal knowledge spectrum model that the parsing and conversion of legal knowledge collection of illustrative plates generate
Keyword to be searched corresponding descriptor in knowledge mapping, and obtain the conjunctive word of these descriptor, i.e., upper theme, bottom
Theme, label synonym are retrieved, and the search word combination constituted according to descriptor and its conjunctive word can be such that legal provision searches
Hitch fruit from scratch, from having to excellent, i.e., search result coverage area more comprehensively, it is more accurate；The present invention can also be according to same
Class case by case actual conditions carry out descriptor weighed value adjusting, and search result is arranged according to descriptor weighed combination
Sequence pushes, and judicial personnel and other legal provisions reseaching staff can be helped quickly and correctly to obtain relevant all with case
Legal provision enhances the practicability of legal provision retrieval result.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (8)
1. a kind of accurate search ordering method of legal provision of knowledge based collection of illustrative plates, which is characterized in that include the following steps：
S101, input keyword to be searched；
S102, it obtains from legal knowledge spectrum model and to be associated with the descriptor of Keywords matching to be searched and the descriptor
Word forms theme dictionary；Conjunctive word includes：Upper theme, the next theme and label synonym；Wherein, upper theme refers to institute
The big theme of the range of representative, the next theme refer to the small theme of representative range, and label synonym is to define in the label
The similar theme of representative range；Descriptor attribute includes：Descriptor title and descriptor weights, weights are ranging from（0-1]；
S103, according to and core subject in legal knowledge spectrum model incidence relation, dynamic generation with a case by descriptor
The weights of descriptor and its conjunctive word in library, the higher explanation of weights and the range that core subject represents are closer；
S104, the sub-combinations for obtaining theme dictionary, it is m, the sub-combinations of m-1, m-2 ... 2 to sequentially form number；
S105, theme word combination of the descriptor formation eventually for search is respectively taken out from each sub-combinations；
S106, in the theme word combination eventually for search number and the total weight of keyword be according to all subset groups
Conjunction is ranked up；
S107, scanned in legal provision database using the theme word combination selected after sequence, and to search result into
Row sequencing display.
2. the accurate search ordering method of legal provision of knowledge based collection of illustrative plates according to claim 1, which is characterized in that root
According to the search result in legal provision database, the weights of conjunctive word are adjusted within the scope of weights according to practical situation.
3. the accurate search ordering method of legal provision of knowledge based collection of illustrative plates according to claim 1, which is characterized in that step
In rapid S107, when search, records each descriptor in theme word combination and corresponding position and go out in legal provision document
The number of existing descriptor, is ranked up legal provision according to the number for descriptor occur in legal provision document, occurrence number
Most legal provisions comes search result and presents up front.
4. the accurate search ordering method of legal provision of knowledge based collection of illustrative plates according to claim 1, which is characterized in that institute
It states legal knowledge spectrum model to be parsed and converted and generated according to the file to constructed legal knowledge collection of illustrative plates, which knows
Know spectrum model and tissue is carried out according to three main aspects by the descriptor of Related Cases to same a case, each aspect is carried out again
Classification, the theme being related to it in each classification represent the analysis of range, define the upper and lower between theme or same position
Relationship；Three main aspects include main body, rights and obligations, juristic fact.
5. the accurate search ordering method of legal provision of knowledge based collection of illustrative plates according to claim 1, which is characterized in that
The descriptor weights being fitted on are 1.0, and the weights of the label synonym of upper theme, the next theme and upper the next theme are
0.5。
6. the accurate search ordering method of legal provision of knowledge based collection of illustrative plates according to claim 1, which is characterized in that
The descriptor weights being fitted on are 1.0, and the upper theme of n-th layer, n-th layer bottom theme, the label of the next theme is synonymous in n-th layer
The weights of word are 0.5n, wherein n is natural number.
7. a kind of accurate searching order system of the legal provision of knowledge based collection of illustrative plates, which is characterized in that including：
Input module, for inputting keyword to be searched；
Theme dictionary generation module, for obtained from legal knowledge spectrum model with the descriptor of Keywords matching to be searched and
The conjunctive word of the descriptor forms theme dictionary；Conjunctive word includes：Upper theme, the next theme and label synonym；Wherein,
Upper theme refers to the big theme of representative range, and the next theme refers to the small theme of representative range, label synonym
For the similar theme of representative range defined in the label；Descriptor attribute includes：Descriptor title and descriptor weights, weights
Ranging from（0-1]；
Weights generation module, for according to the incidence relation with core subject in legal knowledge spectrum model, dynamic generation to be same
Case by theme dictionary in descriptor and its conjunctive word weights, weights are higher to illustrate that the range that is represented with core subject more connects
Closely；
Sub-combinations generation module, the sub-combinations for obtaining theme dictionary, it is m, m-1, m-2 ... to sequentially form element number
2 sub-combinations；Theme word combination of the descriptor formation eventually for search is respectively taken out from each sub-combinations；With most
The number in the theme word combination for searching for and the total weight of keyword are that foundation is ranked up all sub-combinations eventually；
Search result display module, for being searched in legal provision database using the theme word combination selected after sequence
Rope, and display is ranked up to search result.
8. a kind of computer readable storage medium, which is characterized in that including the computer program that can be executed by processor, the calculating
Machine program specifically executes the accurate searching order side of legal provision of the knowledge based collection of illustrative plates as described in any one of claim 1-6
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810361909.8A CN108563773B (en) | 2018-04-20 | 2018-04-20 | Knowledge graph-based legal provision accurate search ordering method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810361909.8A CN108563773B (en) | 2018-04-20 | 2018-04-20 | Knowledge graph-based legal provision accurate search ordering method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108563773A true CN108563773A (en) | 2018-09-21 |
| CN108563773B CN108563773B (en) | 2021-03-30 |
Family
ID=63536154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810361909.8A Active CN108563773B (en) | 2018-04-20 | 2018-04-20 | Knowledge graph-based legal provision accurate search ordering method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108563773B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947952A (en) * | 2019-03-20 | 2019-06-28 | 武汉市软迅科技有限公司 | Search method, device, equipment and storage medium based on english knowledge map |
| CN110321408A (en) * | 2019-05-30 | 2019-10-11 | 重庆金融资产交易所有限责任公司 | Searching method, device, computer equipment and the storage medium of knowledge based map |
| CN110674285A (en) * | 2019-09-18 | 2020-01-10 | 国网安徽省电力有限公司芜湖供电公司 | Intelligent retrieval system and method for power dispatching machine accounts |
| CN110674316A (en) * | 2019-09-27 | 2020-01-10 | 腾讯科技（深圳）有限公司 | Data conversion method and related device |
| CN110928992A (en) * | 2019-11-21 | 2020-03-27 | 邝俊伟 | Text search method, text search device, text search server and storage medium |
| CN111191042A (en) * | 2019-12-10 | 2020-05-22 | 同济大学 | Knowledge graph path semantic relation-based search accuracy evaluation method |
| CN111563168A (en) * | 2020-03-03 | 2020-08-21 | 天津蒙比利埃创新网络科技有限公司 | Method for intelligently classifying customs commodities based on AI knowledge graph algorithm |
| CN112182184A (en) * | 2020-09-29 | 2021-01-05 | 国网浙江省电力有限公司 | Audit database-based accurate matching search method |
| WO2021063077A1 (en) * | 2019-09-30 | 2021-04-08 | 北京国双科技有限公司 | Method and apparatus for constructing record-based map, and storage medium and device |
| CN113127761A (en) * | 2019-12-31 | 2021-07-16 | 中国科学技术信息研究所 | Intelligent sorting method for scientific and technological element retrieval, electronic equipment and storage medium |
| CN115905577A (en) * | 2023-02-08 | 2023-04-04 | 支付宝(杭州)信息技术有限公司 | Knowledge graph construction method and device, and regulation retrieval method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120239682A1 (en) * | 2011-03-15 | 2012-09-20 | International Business Machines Corporation | Object selection based on natural language queries |
| CN104090863A (en) * | 2014-07-24 | 2014-10-08 | 高德良 | Intelligent legal instrument generating method and system |
| US20150324399A1 (en) * | 2014-05-09 | 2015-11-12 | Edward-Robert Tyercha | Querying Spatial Data in Column Stores Using Tree-Order Scans |
| CN105069167A (en) * | 2015-08-28 | 2015-11-18 | 成都六四三六五科技有限公司 | Legal information search method and legal information search apparatus |
| CN105893551A (en) * | 2016-03-31 | 2016-08-24 | 上海智臻智能网络科技股份有限公司 | Method and device for processing data and knowledge graph |
| CN106874695A (en) * | 2017-03-22 | 2017-06-20 | 北京大数医达科技有限公司 | The construction method and device of medical knowledge collection of illustrative plates |
| CN107122444A (en) * | 2017-04-24 | 2017-09-01 | 北京科技大学 | A kind of legal knowledge collection of illustrative plates method for auto constructing |
-
2018
- 2018-04-20 CN CN201810361909.8A patent/CN108563773B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120239682A1 (en) * | 2011-03-15 | 2012-09-20 | International Business Machines Corporation | Object selection based on natural language queries |
| US20150324399A1 (en) * | 2014-05-09 | 2015-11-12 | Edward-Robert Tyercha | Querying Spatial Data in Column Stores Using Tree-Order Scans |
| CN104090863A (en) * | 2014-07-24 | 2014-10-08 | 高德良 | Intelligent legal instrument generating method and system |
| CN105069167A (en) * | 2015-08-28 | 2015-11-18 | 成都六四三六五科技有限公司 | Legal information search method and legal information search apparatus |
| CN105893551A (en) * | 2016-03-31 | 2016-08-24 | 上海智臻智能网络科技股份有限公司 | Method and device for processing data and knowledge graph |
| CN106874695A (en) * | 2017-03-22 | 2017-06-20 | 北京大数医达科技有限公司 | The construction method and device of medical knowledge collection of illustrative plates |
| CN107122444A (en) * | 2017-04-24 | 2017-09-01 | 北京科技大学 | A kind of legal knowledge collection of illustrative plates method for auto constructing |
Non-Patent Citations (1)
| Title |
|---|
| 汤志伟等: "基于CSSCI的国内公共安全研究知识图谱分析", 《现代情报》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947952A (en) * | 2019-03-20 | 2019-06-28 | 武汉市软迅科技有限公司 | Search method, device, equipment and storage medium based on english knowledge map |
| CN110321408A (en) * | 2019-05-30 | 2019-10-11 | 重庆金融资产交易所有限责任公司 | Searching method, device, computer equipment and the storage medium of knowledge based map |
| CN110674285A (en) * | 2019-09-18 | 2020-01-10 | 国网安徽省电力有限公司芜湖供电公司 | Intelligent retrieval system and method for power dispatching machine accounts |
| CN110674316A (en) * | 2019-09-27 | 2020-01-10 | 腾讯科技（深圳）有限公司 | Data conversion method and related device |
| CN110674316B (en) * | 2019-09-27 | 2022-05-31 | 腾讯科技（深圳）有限公司 | Data conversion method and related device |
| WO2021063077A1 (en) * | 2019-09-30 | 2021-04-08 | 北京国双科技有限公司 | Method and apparatus for constructing record-based map, and storage medium and device |
| CN110928992A (en) * | 2019-11-21 | 2020-03-27 | 邝俊伟 | Text search method, text search device, text search server and storage medium |
| CN111191042A (en) * | 2019-12-10 | 2020-05-22 | 同济大学 | Knowledge graph path semantic relation-based search accuracy evaluation method |
| CN113127761A (en) * | 2019-12-31 | 2021-07-16 | 中国科学技术信息研究所 | Intelligent sorting method for scientific and technological element retrieval, electronic equipment and storage medium |
| CN111563168A (en) * | 2020-03-03 | 2020-08-21 | 天津蒙比利埃创新网络科技有限公司 | Method for intelligently classifying customs commodities based on AI knowledge graph algorithm |
| CN111563168B (en) * | 2020-03-03 | 2022-12-13 | 天津蒙比利埃创新网络科技有限公司 | Method for intelligently classifying customs commodities based on AI knowledge graph algorithm |
| CN112182184A (en) * | 2020-09-29 | 2021-01-05 | 国网浙江省电力有限公司 | Audit database-based accurate matching search method |
| CN115905577A (en) * | 2023-02-08 | 2023-04-04 | 支付宝(杭州)信息技术有限公司 | Knowledge graph construction method and device, and regulation retrieval method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108563773B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108563773A (en) | The accurate search ordering method of legal provision of knowledge based collection of illustrative plates | |
| CN108959431B (en) | Automatic label generation method, system, computer readable storage medium and equipment | |
| Wu et al. | Harvesting social knowledge from folksonomies | |
| US12061615B2 (en) | Ranking and presenting search engine results based on category-specific ranking models | |
| CN109871446A (en) | Rejection method for identifying, electronic device and storage medium in intention assessment | |
| Palmero Aprosio et al. | Automatic expansion of DBpedia exploiting Wikipedia cross-language information | |
| US20110191335A1 (en) | Method and system for conducting legal research using clustering analytics | |
| US20160378847A1 (en) | Distributional alignment of sets | |
| Tao et al. | Doc2cube: Allocating documents to text cube without labeled data | |
| KR20180129001A (en) | Method and System for Entity summarization based on multilingual projected entity space | |
| KR20160149050A (en) | Apparatus and method for selecting a pure play company by using text mining | |
| Lerman et al. | Automatically labeling the inputs and outputs of web services | |
| CN114491079A (en) | Knowledge graph construction and query method, device, equipment and medium | |
| Zidi et al. | An ontology-based personalized retrieval model using case base reasoning | |
| Tao et al. | Doc2cube: Automated document allocation to text cube via dimension-aware joint embedding | |
| Kaothanthong et al. | Headline2Vec: A CNN-based feature for Thai clickbait headlines classification | |
| TW200807346A (en) | Knowledge framework system and method for integrating a knowledge management system with an e-learning system | |
| CN109344319B (en) | Online content popularity prediction method based on ensemble learning | |
| Guo et al. | Multi-level topical text categorization with wikipedia | |
| Christy et al. | A hybrid model for topic modeling using latent dirichlet allocation and feature selection method | |
| Scholtes et al. | Big data analytics for e-discovery | |
| Yang et al. | Transfer learning over big data | |
| Gharehchopogh et al. | Machine learning based question classification methods in the question answering systems | |
| Saraswathi et al. | Multi-document text summarization in e-learning system for operating system domain | |
| Cheng | Unsupervised topic discovery by anomaly detection |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |