CN108595547A - A kind of similar case search method based on semantics extraction - Google Patents
A kind of similar case search method based on semantics extraction Download PDFInfo
- Publication number
- CN108595547A CN108595547A CN201810311762.1A CN201810311762A CN108595547A CN 108595547 A CN108595547 A CN 108595547A CN 201810311762 A CN201810311762 A CN 201810311762A CN 108595547 A CN108595547 A CN 108595547A
- Authority
- CN
- China
- Prior art keywords
- case
- value
- variable
- document
- case element
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000000605 extraction Methods 0.000 title claims abstract description 20
- 239000000284 extract Substances 0.000 claims abstract description 9
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000035935 pregnancy Effects 0.000 description 2
- 241000272814 Anser sp. Species 0.000 description 1
- 208000001613 Gambling Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000035606 childbirth Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 206010036067 polydipsia Diseases 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The similar case search method based on semantics extraction that the present invention relates to a kind of, includes the following steps：1:Judgement document is obtained, case library is formed；2：Law expert defines the case element variable in case, and semantic-based method is described to establish case element base variable, and defines case element variate-value for each case element；3：Index is established according to the value of the case variable factors of retrieval to the judgement document of case library；4:The trial document for describing or importing for case input by user, extracts the value of the case element variable of file to be retrieved；5:The value of the case element variable of case to be retrieved is brought into index database and retrieves and exports retrieval result.The Similar case search method that this method provides disclosure satisfy that the case Search Requirement of nonlegal professional user and find the similar case of merit as possible, improve recall precision.
Description
Technical field
The present invention relates to law artificial intelligence fields, and in particular to a kind of similar case retrieval side based on semantics extraction
Method.
Background technology
The Case Retrieval of legal industry is not new things, it starts from word, symbol and pattern as other science
It generates, and is deepened continuously with the birth of specific scientific domain with developing.With the arrival in information huge explosion epoch and close
The deep reform of economic society, Case Retrieval have been raised to unprecedented height over year.Existing Case Retrieval system, packet
Include no lawsuit example, Beijing University's magic weapon, prestige section in advance etc. databases, the main method of use be to use the keyword and key of case
Simple operation symbol between word, is retrieved in Law Text.There are certain drawbacks for this method, such as user is usually not
It is legal profession, it is difficult to correct keyword be selected efficiently to be retrieved.For example, to inquire the sanction that bank card is stolen brush case
Sentence rule, if " central regulation judicial explanation " and " local regulation regulations " are retrieved under Beijing University's magic weapon, inputs keyword
After " bank card ", " stolen " or " bank card ", " steal brush ", do not obtain any retrieval result, but if input " puppet card ",
After " transaction ", 21 results are obtained.In addition, as the case that the ownership of society touches embodies the feature " more than four ",
I.e. more (case relates to each node for time more (time points more, span big), people more (cases relate to main body is more and relationship is mixed), Qian Duo, the origin of an incident
Event property span it is big, from infringement to promise breaking, it is numerous).The method of keyword is often difficult to embody the essence of case.
Therefore a kind of case retrieving method is needed, on the one hand disclosure satisfy that the case Search Requirement of nonlegal professional user；
On the other hand it can be conceived to case essence, find the similar case of merit as possible, improve recall precision.
Invention content
1, technical problem to be solved：
The present invention provides a kind of semantic-based similar case search method, and this method describes the case that user provides
Or the judgement document imported, it is retrieved in judgement document library, the similar case retrieved is carried out according to similarity degree
Sequence, and show user.
2, technical solution：
A kind of similar case search method based on semantics extraction, it is characterised in that：Include the following steps：
Step 1：Establish case library：Judgement document is obtained, is pre-processed and is stored, case library is formed.
Step 2：Establish case element base variable；Law expert defines all cases that may relate in judgement document and wants
Plain variable；And each case element variable is described by semantic method；Each case element variable defined in it is case
The pattern and possible value range of the key factor of part affirmation part or trial structure division；In a court verdict
In, each case element variable is presented as a numerical value, the i.e. value of case element variable.Each case element variable is case thing
The pattern and possible value range of the key factor of real statement or trial structure division.
Step 3：Index is established to the judgement document of case library：Extract the case in each judgement document in case library
The value of part element variable；The inverted index of judgement document is established according to the value of the case element variable retrieved.
Step 4：Extract the value of the case element variable of file to be retrieved：Case input by user is described or imported
Trial document, pre-processed and stored；Extract the value of the case element variable of case to be retrieved.
Step 5：It retrieves and exports retrieval result：The value of the case element variable of case to be retrieved is brought into case library
It is retrieved, the similar case retrieved is ranked up according to similarity degree, and show user.
Further, step 1 further includes：Judgement document is obtained by way of network crawl or by existing text
Present case obtains judgement document in library.
Further, the method for the semantic description of case element variable is to be realized based on TML language in step 2；Specifically
For：In TML, case element is defined as concept or conceptual relation, and concept to be extracted and conceptual relation are in the form of nonterminal symbol
It is embodied in method, character string, regular expression and calculating symbol are embodied in the form of terminal symbol；Also, the calculating symbol in TML
Including AND, OR, NOT, SENT, DIST_n, ORD；The TML language is used for indicating complicated semantic structure.
Further, step 3 further includes establishing falling for judgement document according to the value for extracting obtained case element variable
The case element vector of each judgement document is generated when row's index simultaneously.
Further, the case element vector is：In the N kind case elements defined for law expert extracted,
According to the variate-value of each case element for extracting and obtaining, the case element vector V for establishing judgement document is：V (d)=((t1,
w1),(t2,w2)…,(tn,wN)), wherein tiFor the value of i-th of case element variable in judgement document d, wiIt is wanted for i-th of case
The weight of plain variable, (1≤i≤N), value are 1 or are rule of thumb arranged.
Further, step 4 further includes the trial document input by user case description or imported, and extracts case and wants
The retrieval case element vector of file to be retrieved is generated when the value of plain variable.
Further, step 5 detailed process is the value first according to case element variable, is detected in case library related
Judgement document；Then the phase of the case element vector of file to be retrieved and the case element vector of the related judgement document is calculated
Like degree；Similar case is exported according to sequencing of similarity, and shows user.
3, advantageous effect：
The Similar case search method that this method provides, on the one hand meets the case Search Requirement of nonlegal professional user；
On the other hand it can be conceived to case essence, find the similar case of merit as possible, improve recall precision.
Description of the drawings
Fig. 1 is the flow chart of this method.
Specific implementation mode
The present invention is further detailed below in conjunction with the accompanying drawings.
A kind of similar case search method based on semantics extraction as described in Fig. 1, includes the following steps：Establish case
Library；Establish case element base variable；Index is established to the judgement document of case library；Extract the case element variable of file to be retrieved
Value；It retrieves and exports retrieval result.
This method is further detailed below for the embodiment of specific matrimonial dispute case.
Establish matrimonial dispute case library：Matrimonial dispute judgement document is obtained, is pre-processed and is stored, is formed
Case library.The method of acquisition can be from network crawl (such as Chinese judgement document's net：Wenshu.court.gov.cn) also may be used
To be existing text case library.
Law expert concludes case element and establishes case element base variable, and each case element variable is used
Semantic-based method description.Wherein case element includes the fact that element and result element.In the present embodiment, true element includes
But it is not limited to：Emotion situation, whether have children, the subordinate sentence time, whether extramarital affair, the marriage time limit, whether have domestic violence, which side
Prosecution divorce, whether have bigamy, whether be soldier spouse propose divorce, whether soldier spouse have great mistake, whether have it is bad
Hobby, the whether missing, wife's side whether in wife's side period of gestation, in childbirth latter year or after terminal pregnancy in six months, whether adjust
Section effectively, whether live together with other people, whether be for the first time prosecution divorce, apart from last time prosecution the time whether be more than 6 months, whether
Collateral relatives by blood up to the third degree of kinship, whether agree to divorce with the presence or absence of the disease that should not get married, defendant, often quarrel, whether having and
It is good, whether to have signed divorce agreement etc. 22 kinds；As a result element includes but not limited to：Whether permission is divorced, children's custody,
How property distributes, whom prosecution expense paid by, 5 kinds of cost of fostering payment etc..
The extraction mode of semantic-based case element can be based on TML systems and realize.In TML concept to be extracted and
Relationship name is embodied in a program in the form of nonterminal symbol, and character string, regular expression and calculating symbol are embodied in the form of terminal symbol.
It includes AND, OR, NOT, SENT, DIST_n, ORD and CONT etc. to calculate symbol, and contextual definition is as follows：
It is made of the relationship between regular expression, simple concept or concept based on the element of semantic description.
Wherein, regular expression is exemplified below：
Regular expression LAW-MARRIAGE-FACTOR-EMOTION is defined " defendant has gambling, excessive drinking or family sudden and violent "
Etc. bad habits the fact element.
Secondly, simple concept is exemplified below：
Simple concept ACCUSER-DEFENDANT defines the role in case, " quilt in OR (" defendant ", " plaintiff ")
Accuse ", " plaintiff " is character string constant, and OR is to calculate symbol.Simple concept AGREE-DIVOICE defines the approval feelings to divorce
Condition.Again, the relationship of concept is exemplified below：
Relationship LAW-MARRIAGE-FACTOR-EMOTION defines the side ACCUSER-DEFENDANT in marriage
No agreement divorce AGREE-DIVOICE.
When by TML code compilations at bytecode, for that not comprising the sentence for calculating symbol, they directly can be merged and turned
Finite state automata is turned to be matched；And for having used AND, the Relation extraction sentence of the calculating such as OR, SENT symbol needs
One group of operation virtual machine instructions add operation number is translated into execute.
Semantic-based abstracting method is referring specifically to paper：The quiet * of Li Jia, Li Xiaoming, Meng Tao, TML：A kind of Universal efficient
Text mining language, Journal of Computer Research and Development, 2015,52 (3)：553-560.
To be in the present embodiment below be, and each semantic feature defines corresponding variable, and the fact that obtained according to semantics extraction
Element state carries out assignment.It is the value paraphrase example of semantic feature below：
The state of the case element obtained according to semantics extraction is to case element variable assignments.For example, case text is " Tan
Wild goose is rather born on June 8th, 1969, is registered as agriculture family's registered permanent residence, and fertility has Tan jointly after being married at a registry before death with Li Weimei
Small graceful, two children of Tan.", by semantics extraction, the number of children is 2, then assigns the value of true element variable childnum
It is 2.
The N kind case elements defined for law expert extracted in case document are obtained according to each extraction
The variate-value of case element, the case element vector V for establishing document are：V (d)=((t1,w1),(t2,w2)…,(tn,wN)),
Middle tiFor the value of i-th of case element variable in document d, wiFor the weight (1≤i≤N) of i-th of case element variable, value is
1 or rule of thumb it is arranged.
Case element value based on extraction, establishes the inverted index of judgement document.The foundation of inverted index, can with but it is unlimited
It is realized in based on Elasticsearch systems.It specifically refers to《Elasticsearch Reference》:https://
www.elastic.co/guide/en/elasticsearch/reference/current/index.html。
The trial document for describing or importing for case input by user, extracts case element therein, is formed to be checked
The case element vector V (dx) of rope case.
According to the value that the case in document to be retrieved is wanted, the Rapid Detection judgement document in index database.Then it calculates each
The similarity of the case element vector V (dj) and V (dx) of judgement document, wherein 0≤i≤M, M are that the judgement document that retrieves is total
Number.Vector similarity method may be used but be not limited to cosine angle algorithm.Specifically refer to Lucene4.0http:// lucene.apache.org/core/4_0_0/core/overview-summary.html。
It is ranked up according to calculated vector similarity, exports similar case, and show user.
Although the present invention has been described by way of example and in terms of the preferred embodiments, they be not it is for the purpose of limiting the invention, it is any ripe
This those skilled in the art is practised, without departing from the spirit and scope of the invention, can make various changes or retouch from working as, therefore the guarantor of the present invention
Shield range should be subject to what claims hereof protection domain was defined.
Claims (7)
1. a kind of similar case search method based on semantics extraction, it is characterised in that：Include the following steps：
Step 1：Establish case library：Judgement document is obtained, is pre-processed and is stored, case library is formed；
Step 2：Establish case element base variable；Law expert defines all case elements that may relate in judgement document and becomes
Amount；And each case element variable is described by semantic method；Each case element variable defined in it is case thing
The pattern and possible value range of the key factor of real statement or trial structure division；In a court verdict, often
A case element variable is presented as a numerical value, the i.e. value of case element variable；
Step 3：Index is established to the judgement document of case library：The case extracted in each judgement document in case library is wanted
The value of plain variable；The inverted index that judgement document is established according to the value of the case element variable retrieved, establishes index database；
Step 4：Extract the value of the case element variable of file to be retrieved：It is examined what case input by user was described or imported
Sentence document, pre-processed and is stored；Extract the value of the case element variable of case to be retrieved；
Step 5：It retrieves and exports retrieval result：The value of the case element variable of case to be retrieved is brought into case library and is carried out
Retrieval, the similar case retrieved is ranked up according to similarity degree, and show user.
2. a kind of similar case search method based on semantics extraction according to claim 1, it is characterised in that：Step 1
Further include：Network crawl by way of obtain judgement document or by existing text case library in obtain judgement document.
3. a kind of similar case search method based on semantics extraction according to claim 1, it is characterised in that：Step 2
The method of the semantic description of middle case element variable is to be realized based on TML language；Specially：In TML, case element is defined as
Concept or conceptual relation, concept to be extracted and conceptual relation are embodied in the form of nonterminal symbol in method, character string, canonical table
It is embodied in the form of terminal symbol up to formula and calculating symbol；Also, the calculating symbol in TML includes AND, OR, NOT, SENT, DIST_
n,ORD；The TML language is used for indicating complicated semantic structure.
4. a kind of similar case search method based on semantics extraction according to claim 1, it is characterised in that：Step 3
Further include that each judge when establishing the inverted index of judgement document while being generated according to the value for extracting obtained case element variable
The case element vector of document.
5. a kind of similar case search method based on semantics extraction according to claim 1, it is characterised in that：The case
Part element vector is：The N kind case elements defined for law expert extracted in case document, are extracted according to each
The variate-value of the case element arrived, the case element vector V for establishing document are：V(d)=((t1,w1),(t2,w2)…,(tn,
wN)), wherein tiFor the value of i-th of case element variable in document d, wiFor the weight of i-th of case element variable, value 1
Or rule of thumb it is arranged.
6. a kind of similar case search method based on semantics extraction according to claim 1, it is characterised in that：Step 4
The trial document for further including case input by user description or importing, when value for extracting case element variable, generate text to be retrieved
The retrieval case element vector of part.
7. a kind of similar case search method based on semantics extraction according to claim 1, it is characterised in that：Step 5
Detailed process is the value first according to case element variable, and related judgement document is detected in case library；Then it calculates to be retrieved
The similarity of the case element vector of file and the case element vector of the related judgement document；It is exported according to sequencing of similarity
Similar case, and show user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810311762.1A CN108595547A (en) | 2018-04-09 | 2018-04-09 | A kind of similar case search method based on semantics extraction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810311762.1A CN108595547A (en) | 2018-04-09 | 2018-04-09 | A kind of similar case search method based on semantics extraction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108595547A true CN108595547A (en) | 2018-09-28 |
Family
ID=63621251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810311762.1A Pending CN108595547A (en) | 2018-04-09 | 2018-04-09 | A kind of similar case search method based on semantics extraction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108595547A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359173A (en) * | 2018-10-24 | 2019-02-19 | 南京大学 | A kind of search method of judgement document |
| CN109543044A (en) * | 2018-10-22 | 2019-03-29 | 杭州叙简科技股份有限公司 | A kind of event and legal provision automatic patching system and matching process |
| CN109739888A (en) * | 2018-12-25 | 2019-05-10 | 北京市律典通科技有限公司 | Accomplice is same to sentence method and system |
| CN110069609A (en) * | 2019-03-15 | 2019-07-30 | 平安科技（深圳）有限公司 | Judgement document's analysis method, device, computer equipment and storage medium |
| CN110347927A (en) * | 2019-07-16 | 2019-10-18 | 北京市律典通科技有限公司 | A kind of statement method for pushing and system |
| CN110580281A (en) * | 2019-09-11 | 2019-12-17 | 江苏鸿信系统集成有限公司 | similar case matching method based on semantic similarity |
| CN110674299A (en) * | 2019-09-30 | 2020-01-10 | 南京网感至察信息科技有限公司 | Detection method for plagiarism in article viewpoint |
| CN111198953A (en) * | 2018-11-16 | 2020-05-26 | 北京智慧正安科技有限公司 | Case text information based method and system for recommending cases and computer readable storage medium |
| CN112395406A (en) * | 2019-08-19 | 2021-02-23 | 阿里云计算有限公司 | Court trial record retrieval method and device |
| CN112561744A (en) * | 2019-09-25 | 2021-03-26 | 北京国双科技有限公司 | Method and device for generating similar case retrieval report |
| CN113177106A (en) * | 2021-05-19 | 2021-07-27 | 苏州黑云智能科技有限公司 | Similar decision book retrieval method based on element extraction |
| CN113535933A (en) * | 2021-06-01 | 2021-10-22 | 科大讯飞股份有限公司 | Case retrieval method and device, electronic equipment and storage device |
| CN113688635A (en) * | 2021-09-01 | 2021-11-23 | 中国矿业大学(北京) | Semantic similarity based class case recommendation method |
| CN114416965A (en) * | 2022-01-20 | 2022-04-29 | 北京北大英华科技有限公司 | Class case pushing method and device based on composite voting mechanism |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187927A (en) * | 2007-12-17 | 2008-05-28 | 电子科技大学 | Criminal case joint investigation intelligent analysis method |
| WO2009083833A1 (en) * | 2007-12-28 | 2009-07-09 | Koninklijke Philips Electronics N.V. | Retrieval of similar patient cases based on disease probability vectors |
| CN106502996A (en) * | 2016-12-13 | 2017-03-15 | 深圳爱拼信息科技有限公司 | A kind of judgement document's search method and server based on semantic matches |
| CN106934483A (en) * | 2016-11-18 | 2017-07-07 | 北京工业大学 | A kind of criminal justice reasoning by cases method based on body by linear programming |
| CN107153689A (en) * | 2017-04-29 | 2017-09-12 | 安徽富驰信息技术有限公司 | A kind of case search method based on Topic Similarity |
-
2018
- 2018-04-09 CN CN201810311762.1A patent/CN108595547A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187927A (en) * | 2007-12-17 | 2008-05-28 | 电子科技大学 | Criminal case joint investigation intelligent analysis method |
| WO2009083833A1 (en) * | 2007-12-28 | 2009-07-09 | Koninklijke Philips Electronics N.V. | Retrieval of similar patient cases based on disease probability vectors |
| CN106934483A (en) * | 2016-11-18 | 2017-07-07 | 北京工业大学 | A kind of criminal justice reasoning by cases method based on body by linear programming |
| CN106502996A (en) * | 2016-12-13 | 2017-03-15 | 深圳爱拼信息科技有限公司 | A kind of judgement document's search method and server based on semantic matches |
| CN107153689A (en) * | 2017-04-29 | 2017-09-12 | 安徽富驰信息技术有限公司 | A kind of case search method based on Topic Similarity |
Non-Patent Citations (2)
| Title |
|---|
| 吴笛: "《基于语义网的个性化网络学习服务》", 30 April 2017 * |
| 唐旭日，张际标: "《计算机辅助翻译基础》", 31 July 2017 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543044B (en) * | 2018-10-22 | 2021-06-18 | 杭州叙简科技股份有限公司 | Automatic matching system and matching method for event and legal provision |
| CN109543044A (en) * | 2018-10-22 | 2019-03-29 | 杭州叙简科技股份有限公司 | A kind of event and legal provision automatic patching system and matching process |
| CN109359173A (en) * | 2018-10-24 | 2019-02-19 | 南京大学 | A kind of search method of judgement document |
| CN111198953A (en) * | 2018-11-16 | 2020-05-26 | 北京智慧正安科技有限公司 | Case text information based method and system for recommending cases and computer readable storage medium |
| CN109739888A (en) * | 2018-12-25 | 2019-05-10 | 北京市律典通科技有限公司 | Accomplice is same to sentence method and system |
| CN110069609A (en) * | 2019-03-15 | 2019-07-30 | 平安科技（深圳）有限公司 | Judgement document's analysis method, device, computer equipment and storage medium |
| CN110069609B (en) * | 2019-03-15 | 2023-04-18 | 平安科技（深圳）有限公司 | Referee document analysis method, referee document analysis device, computer equipment and storage medium |
| CN110347927A (en) * | 2019-07-16 | 2019-10-18 | 北京市律典通科技有限公司 | A kind of statement method for pushing and system |
| CN110347927B (en) * | 2019-07-16 | 2022-03-25 | 北京市律典通科技有限公司 | Expression pushing method and system |
| CN112395406A (en) * | 2019-08-19 | 2021-02-23 | 阿里云计算有限公司 | Court trial record retrieval method and device |
| CN110580281A (en) * | 2019-09-11 | 2019-12-17 | 江苏鸿信系统集成有限公司 | similar case matching method based on semantic similarity |
| CN112561744A (en) * | 2019-09-25 | 2021-03-26 | 北京国双科技有限公司 | Method and device for generating similar case retrieval report |
| CN110674299A (en) * | 2019-09-30 | 2020-01-10 | 南京网感至察信息科技有限公司 | Detection method for plagiarism in article viewpoint |
| CN113177106A (en) * | 2021-05-19 | 2021-07-27 | 苏州黑云智能科技有限公司 | Similar decision book retrieval method based on element extraction |
| CN113177106B (en) * | 2021-05-19 | 2024-04-12 | 苏州黑云智能科技有限公司 | Similar decision book retrieval method based on element extraction |
| CN113535933A (en) * | 2021-06-01 | 2021-10-22 | 科大讯飞股份有限公司 | Case retrieval method and device, electronic equipment and storage device |
| CN113688635A (en) * | 2021-09-01 | 2021-11-23 | 中国矿业大学(北京) | Semantic similarity based class case recommendation method |
| CN113688635B (en) * | 2021-09-01 | 2023-05-30 | 中国矿业大学(北京) | Class case recommendation method based on semantic similarity |
| CN114416965A (en) * | 2022-01-20 | 2022-04-29 | 北京北大英华科技有限公司 | Class case pushing method and device based on composite voting mechanism |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108595547A (en) | A kind of similar case search method based on semantics extraction | |
| US10261973B2 (en) | System and method for causing downloads of applications based on user intents | |
| Trappey et al. | Intelligent trademark similarity analysis of image, spelling, and phonetic features using machine learning methodologies | |
| TW201931170A (en) | Content recommendation method and apparatus | |
| CN109933785A (en) | Method, apparatus, equipment and medium for entity associated | |
| CN107807962B (en) | A method of similarity mode being carried out to legal decision document using LDA topic model | |
| CN108595548A (en) | A kind of case judge's prediction of result method based on Markov Logic Network | |
| US9552422B2 (en) | System and method for detecting a search intent | |
| CN109388743B (en) | Language model determining method and device | |
| Atmaja | Implementation of k-Medoids Clustering Algorithm to Cluster Crime Patterns in Yogyakarta | |
| CN107066589A (en) | A kind of sort method and device of Entity Semantics and word frequency based on comprehensive knowledge | |
| Liu et al. | ML-LJP: multi-law aware legal judgment prediction | |
| CN110569350A (en) | Legal recommendation method, equipment and storage medium | |
| Plant et al. | CAPE: Context-aware private embeddings for private language learning | |
| CN109344246A (en) | A kind of electric questionnaire generation method, computer readable storage medium and terminal device | |
| Wang et al. | Comparison study on critical components in composition model for phrase representation | |
| Khan et al. | SwICS: Section-wise in-text citation score | |
| Haak et al. | Auditing search query suggestion bias through recursive algorithm interrogation | |
| Murai | Automatic extraction of reversal-type punch lines in shin'ichi hoshi's flash fictions | |
| Iosifyan et al. | And quiet flows the Don: the Sholokhov-Kryukov authorship debate | |
| Zhou et al. | Who likes me more? Analysing entity-centric language-specific bias in multilingual Wikipedia | |
| Ahmed et al. | Multimodal cyberbullying meme detection from social media using deep learning approach | |
| CN109471969A (en) | Application search method, device and equipment | |
| Yu et al. | Recommending features of mobile applications for developer | |
| Pormeister | The GDPR and big data: Leading the way for big genetic data? |
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 |