CN110837564B - Method for constructing multi-language criminal judgment book knowledge graph - Google Patents
Method for constructing multi-language criminal judgment book knowledge graph Download PDFInfo
- Publication number
- CN110837564B CN110837564B CN201910909778.7A CN201910909778A CN110837564B CN 110837564 B CN110837564 B CN 110837564B CN 201910909778 A CN201910909778 A CN 201910909778A CN 110837564 B CN110837564 B CN 110837564B
- Authority
- CN
- China
- Prior art keywords
- criminal
- criminal judgment
- book
- judgment
- chinese
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000004927 fusion Effects 0.000 claims abstract description 13
- 230000001915 proofreading effect Effects 0.000 claims abstract description 10
- 238000002372 labelling Methods 0.000 claims description 44
- 238000000605 extraction Methods 0.000 claims description 31
- 230000008569 process Effects 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 238000012549 training Methods 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000009937 brining Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application provides a method for constructing a multi-language criminal judgment knowledge graph, and relates to the field of computational linguistics. The application can make the manufacture and proofreading of the existing criminal judgment to obtain a more objective and reasonable expression mode by constructing the knowledge graph of the Chinese and national fusion criminal judgment, and helps to improve and perfect the education and training mode and content of judicial practitioners. Meanwhile, the method can provide a standardized writing mode more carefully, realizes cross-language comparison query of professional knowledge, and can be widely applied to the fields of Chinese and national language judge documents and advanced intelligence.
Description
Technical Field
The application relates to the technical field of computational linguistics, in particular to a method for constructing a multi-language criminal decision knowledge graph.
Background
With the continuous promotion of the high-speed development of computer technology and intelligent judicial construction, the traditional manual examination paper and verification cannot meet the higher and higher requirements of people. Judicial practitioners want to be able to bring more convenient work services and efficiency improvements to the machine. The network disclosure of referee documents makes referee documents of increasing interest to legal researchers and masses as a research material or as a material for law.
Through research, the lack of bilingual officers in the national region and average business literacy are still different. When the national region refers to the criminal judgment books of the national language, the court needs to present the criminal judgment books of the national language version to meet the demands of users of the national language and is public, however, the criminal judgment books of the national language version are not expressed normally because the manufacturing standardization of the criminal judgment books of the national language version is not checked, the writing content is not checked, and the expression of the criminal judgment books of the national language version is not normal. Thus, the method is not beneficial to maintaining judicial images and is not convenient for masses to know related information.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the application provides a method for constructing a multi-language criminal judgment knowledge graph, which is used for manufacturing a national version criminal judgment graph through the multi-language criminal judgment graph text knowledge graph and solving the technical problem that the national version criminal judgment graph is not expressed normally.
(II) technical scheme
In order to achieve the above purpose, the application is realized by the following technical scheme:
the application provides a method for constructing a multilingual criminal judgment knowledge graph, which is executed by a computer and comprises the following steps of:
s1, acquiring a Chinese criminal judgment book corpus, and preprocessing the Chinese criminal judgment book corpus;
constructing a criminal judgment book term and legal provision ontology knowledge base consisting of a legal term knowledge base and a criminal judgment book term knowledge base;
s2, extracting criminal judgment book attribute tags based on the preprocessed Chinese criminal judgment book corpus and the criminal judgment book terms and French ontology knowledge base;
s3, processing the criminal judgment book attribute labels to form a criminal judgment book attribute label system and an extraction rule template;
s4, optimizing the criminal judgment term and legal ontology knowledge base based on the criminal judgment attribute tag system and the extraction rule template;
s5, acquiring an automatic labeling model of the criminal judgment book based on the optimized criminal judgment book terms and the legal ontology knowledge base;
s6, automatically labeling the criminal judgment book based on a computer pattern matching algorithm and the automatic criminal judgment book labeling model;
s7, extracting information of the automatically marked criminal judgment books, and constructing a Chinese criminal judgment book knowledge graph;
s8, constructing a national language criminal judgment book knowledge graph corresponding to the Chinese criminal judgment book knowledge graph based on the mapping relation between Chinese and national language; combining the Chinese criminal judgment knowledge graph to form a Chinese and national fusion criminal judgment knowledge graph.
Preferably, in step S1, the specific process of preprocessing the corpus of chinese criminal judgement books is as follows:
labeling the first-level case in the corpus of Chinese criminal judgment books; and the internal structure of the criminal judgment text in the Chinese criminal judgment corpus is divided.
Preferably, the step S3 specifically includes:
labeling the attribute labels of the criminal judgment books, extracting rules, performing proofreading, judging whether the labeled text content is matched with the labeling rules, if so, forming a criminal judgment book attribute label system and extracting rule templates, and if not, returning to the process, and re-labeling.
Preferably, in step S4, the method further includes: labeling the criminal judgment book terms and the legal ontology knowledge base, extracting rules, performing proofreading, judging whether the labeled text content is matched with the labeling rules, if so, forming a criminal judgment book attribute label system and extracting rule templates, and if not, returning to the process, and re-labeling.
Preferably, the step S6 specifically includes:
s601, converting a criminal judgment book from an unstructured criminal judgment book text to a structured criminal judgment book text by using a computer pattern matching algorithm and the automatic criminal judgment book labeling model;
s602, extracting an attribution representation method of the criminal judgment text based on the structured criminal judgment text.
Preferably, in step S7, the information extraction specifically includes: chapter structure analysis, sentence level extraction and word level extraction.
(III) beneficial effects
The application provides a method for constructing a multi-language criminal judgment text knowledge graph. Compared with the prior art, the method has the following beneficial effects:
the method comprises the steps of extracting criminal judgment attribute labels through a preprocessed Chinese criminal judgment corpus, criminal judgment terms and a legal ontology knowledge base, processing the criminal judgment attribute labels to form a criminal judgment attribute label system and an extraction rule template, optimizing and perfecting the criminal judgment terms and the legal ontology knowledge base based on the criminal judgment attribute label system and the extraction rule template, acquiring an automatic criminal judgment labeling model according to the criminal judgment terms and the legal ontology knowledge base, automatically labeling the criminal judgment by the automatic criminal judgment labeling model in combination with a computer pattern matching algorithm, extracting information of the labeled criminal judgment, and constructing a Chinese criminal judgment knowledge map; and finally, constructing an national language criminal judgment knowledge graph corresponding to the Chinese criminal judgment knowledge graph through the mapping relation between the Chinese and the national language, and combining the Chinese criminal judgment knowledge graph to form a Chinese and national language fusion criminal judgment knowledge graph. The application can make the manufacture and proofreading of the existing criminal judgment to obtain a more objective and reasonable expression mode by constructing the knowledge graph of the Chinese and national fusion criminal judgment, and helps to improve and perfect the education and training mode and content of judicial practitioners. Meanwhile, the method can provide a standardized writing mode more carefully, realizes cross-language comparison query of professional knowledge, and can be widely applied to the fields of Chinese and national language judge documents and advanced intelligence.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a method for constructing a knowledge graph of a multilingual criminal decision in an embodiment of the present application;
FIG. 2 is a framework for automatically labeling models of criminal judgment books;
fig. 3 is a schematic diagram of an information extraction flow.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application are clearly and completely described, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application provides a method for constructing the multilingual criminal judgment knowledge graph, which provides a regular writing template for the national criminal judgment graph, solves the problem that the national criminal judgment graph is not expressed normally, and realizes an objective and reasonable expression mode of the national criminal judgment graph.
The technical scheme in the embodiment of the application aims to solve the technical problems, and the overall thought is as follows:
according to the embodiment of the application, the criminal judgment attribute labels are extracted through a preprocessed Chinese criminal judgment corpus, criminal judgment terms and a legal ontology knowledge base, then the criminal judgment attribute labels are processed to form a criminal judgment attribute label system and an extraction rule template, then the criminal judgment terms and the legal ontology knowledge base are optimized and perfected based on the criminal judgment attribute label system and the extraction rule template, then an automatic criminal judgment labeling model is obtained according to the criminal judgment terms and the legal ontology knowledge base, the automatic criminal judgment labeling model is combined with a computer pattern matching algorithm to automatically label the criminal judgment, and the labeled criminal judgment is subjected to information extraction to construct a Chinese criminal judgment knowledge map; and finally, constructing an national language criminal judgment knowledge graph corresponding to the Chinese criminal judgment knowledge graph through the mapping relation between the Chinese and the national language, and combining the Chinese criminal judgment knowledge graph to form a Chinese and national language fusion criminal judgment knowledge graph. The Chinese and national fusion criminal judgment knowledge graph constructed by the embodiment of the application can enable the manufacture and the proofreading of the existing criminal judgment to obtain a more objective and reasonable expression mode, and helps to improve and perfect education and training modes and contents of judicial practitioners.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
The embodiment of the application provides a method for constructing a multilingual criminal judgment knowledge graph, which is shown in fig. 1 and comprises the following steps:
s1, acquiring a Chinese criminal judgment book corpus, and preprocessing the Chinese criminal judgment book corpus;
constructing a criminal judgment book term and legal provision ontology knowledge base consisting of a legal term knowledge base and a criminal judgment book term knowledge base;
s2, extracting criminal judgment book attribute tags based on the preprocessed Chinese criminal judgment book corpus and the criminal judgment book terms and French ontology knowledge base;
s3, processing the criminal judgment book attribute labels to form a criminal judgment book attribute label system and an extraction rule template;
s4, optimizing the criminal judgment term and legal ontology knowledge base based on the criminal judgment attribute tag system and the extraction rule template;
s5, acquiring an automatic labeling model of the criminal judgment book based on the optimized criminal judgment book terms and the legal ontology knowledge base;
s6, automatically labeling the criminal judgment book based on a computer pattern matching algorithm and the automatic criminal judgment book labeling model;
s7, extracting information of the automatically marked criminal judgment books, and constructing a Chinese criminal judgment book knowledge graph;
s8, constructing a national language criminal judgment book knowledge graph corresponding to the Chinese criminal judgment book knowledge graph based on the mapping relation between Chinese and national language; combining the Chinese criminal judgment knowledge graph to form a Chinese and national fusion criminal judgment knowledge graph.
The Chinese and national fusion criminal judgment knowledge graph constructed by the embodiment of the application can enable the manufacture and the proofreading of the existing criminal judgment to obtain a more objective and reasonable expression mode, and helps to improve and perfect education and training modes and contents of judicial practitioners.
The steps are described in detail below, as shown in fig. 1-3.
Here, the ethnic language is exemplified by mongolian.
S1, acquiring a Chinese criminal judgment book corpus, and preprocessing the Chinese criminal judgment book corpus. And constructing a criminal judgment term and legal provision ontology knowledge base consisting of a legal term knowledge base, a criminal judgment term knowledge base and a legal provision knowledge base. The method specifically comprises the following steps:
s101, acquiring criminal judgment corpus by means of network crawling or manual downloading, and constructing a Chinese criminal judgment corpus.
S102, marking 11 first-class case pairs in the Chinese criminal judgment corpus, and dividing the internal structure of the criminal judgment text in the Chinese criminal judgment corpus.
Wherein, 11 first-order cases are as follows: the criminal case is formed by the steps of compromising national safety, compromising public safety, destroying social market economic order, infringing personal rights and civil rights, infringing property, jeopardizing social management order, jeopardizing national defense benefit, brining brix, malpractice, soldier infringement of responsibility and ninety-seven years ago.
The internal structure of the criminal decision text is divided into the following structures: the title comprises a head part, a tail part and a text, wherein the head part and the tail part comprise information such as a complaint authority, a person to be told, sex, birth date, ethnicity, cultural degree, criminal reason, indicting criminal name and the like, and the text comprises information such as facts, reasons and judgment results.
S103, constructing a criminal judgment book term and legal provision ontology knowledge base composed of a legal term knowledge base and a criminal judgment book term knowledge base.
And S2, extracting criminal judgment attribute labels based on the preprocessed Chinese criminal judgment corpus and the criminal judgment terminology and French ontology knowledge base. In the specific implementation process, the number of attribute tags is 149, wherein 6 attribute tags are arranged on the first level, 24 attribute tags are arranged on the second level, 112 attribute tags are arranged on the third level, and 7 attribute tags are arranged on the fourth level.
S3, processing the criminal judgment book attribute labels to form a criminal judgment book attribute label system and an extraction rule template. The method specifically comprises the following steps:
labeling the attribute labels of the criminal judgment books, extracting rules, performing proofreading, judging whether the labeled text content is matched with the labeling rules, if so, forming a criminal judgment book attribute label system and extracting rule templates, and if not, returning to the process, and re-labeling.
And S4, optimizing and perfecting the criminal judgment term and the legal ontology knowledge base based on the criminal judgment attribute label system and the extraction rule template. In the specific implementation process, the criminal judgment book terms and the legal ontology knowledge base are required to be marked, rules are extracted, verification is conducted, whether the marked text content is matched with the marking rules or not is judged, if so, a criminal judgment book attribute tag system and an extraction rule template are formed, if not, returning is conducted, and the marking is conducted again, and in step S3, a circulation process is formed.
S5, acquiring an automatic labeling model of the criminal judgment book based on the optimized and perfected criminal judgment book terms and the legal ontology knowledge base. In the specific implementation process, the automatic labeling model of the criminal judgment book comprises the following structures as shown in fig. 2, and comprises the following structures: an input layer, a labeling layer and an output layer. The method comprises the steps of inputting a plurality of criminal judgment books and a legal term knowledge base at an input layer, extracting the criminal judgment books by a labeling layer, labeling the criminal judgment books by a criminal judgment book attribute label system after extracting the rules, outputting the labeled criminal judgment books at an output layer, and forming the labeled criminal judgment book knowledge base by the labeled criminal judgment books.
And S6, automatically labeling the criminal judgment book based on a computer pattern matching algorithm and the automatic criminal judgment book labeling model. The method specifically comprises the following steps:
s601, converting a criminal judgment book from an unstructured criminal judgment book text to a structured criminal judgment book text by using a computer pattern matching algorithm and the automatic criminal judgment book labeling model;
s602, extracting an attribution representation method of the criminal judgment text based on the structured criminal judgment text.
And S7, extracting information of the automatically marked criminal judgment books, and constructing a Chinese criminal judgment book knowledge graph.
In the specific implementation process, as shown in fig. 3, information extraction is performed on a plurality of automatically labeled criminal judgment books, and the information extraction process comprises chapter structure analysis, sentence level extraction and word level extraction. Firstly, in the chapter structure analysis process, a criminal decision book is divided from unstructured criminal decision book text and structured criminal decision book text by a computer pattern matching algorithm. Wherein the unstructured criminal decision text comprises: text information, text-fact information, and text-reason information. The structured criminal decision text includes: head, tail, and body-judgment results.
In the sentence-level extraction process, sentence segmentation is carried out on the text information of the criminal judgment book text, and the fact information and the reason information in the text are matched through a computer pattern matching algorithm. Wherein the text-fact information includes control information, evidence information, court approval information, dialect opinion, interviewee regret information, reimbursement information, and crime preparation information. The text-reason information includes: crime information and court approval information.
In the word level extraction process, the information obtained by the analysis of the chapter structure and the sentence level extraction is combined, the information is subjected to rule extraction, and then attribute labeling is carried out. And finally, converting the criminal judgment books subjected to space and chapter structure analysis, sentence level extraction and word level extraction into XML documents and storing the XML documents to construct a Chinese criminal judgment book knowledge graph.
S8, constructing a national language criminal judgment knowledge graph corresponding to the Chinese criminal judgment knowledge graph based on the mapping relation of the Chinese and the national language, and forming a Chinese and national language fusion criminal judgment knowledge graph. In the specific implementation process, based on the mapping relation between Chinese and Mongolian, the Chinese criminal judgment book knowledge graph is converted into the Mongolian criminal judgment book knowledge graph, and the Chinese criminal judgment book knowledge graph and the Mongolian criminal judgment book knowledge graph are synthesized to form a Chinese and Mongolian fusion criminal judgment book knowledge graph. And providing a standardized writing mode for Mongolian according to the criminal judgment knowledge graph of Chinese and Mongolian fusion.
In summary, compared with the prior art, the method has the following beneficial effects:
1. the Chinese and national fusion criminal judgment knowledge graph constructed by the embodiment of the application can enable the manufacture and the proofreading of the existing criminal judgment to obtain a more objective and reasonable expression mode, and helps to improve and perfect education and training modes and contents of judicial practitioners.
2. The embodiment of the application realizes the automatic labeling of the text of the Chinese and national bilingual criminal judgment book by using a computer pattern matching method, improves the cross-language retrieval and bilingual judgment auxiliary level in the professional field, and can be widely applied to the Chinese and national judgment books and the advanced intelligent field.
It should be noted that, from the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by means of software plus necessary general hardware platform. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (5)
1. A method for constructing a multi-language criminal decision knowledge graph, the method being executed by a computer and comprising the steps of:
s1, acquiring a Chinese criminal judgment book corpus, and preprocessing the Chinese criminal judgment book corpus; constructing a criminal judgment book term and legal provision ontology knowledge base consisting of a legal term knowledge base and a criminal judgment book term knowledge base;
s2, extracting criminal judgment book attribute tags based on the preprocessed Chinese criminal judgment book corpus and the criminal judgment book terms and French ontology knowledge base;
s3, processing the criminal judgment book attribute labels to form a criminal judgment book attribute label system and an extraction rule template;
s4, optimizing the criminal judgment term and legal ontology knowledge base based on the criminal judgment attribute tag system and the extraction rule template;
s5, acquiring an automatic labeling model of the criminal judgment book based on the optimized criminal judgment book terms and the legal ontology knowledge base;
s6, automatically labeling the criminal judgment book based on a computer pattern matching algorithm and the automatic criminal judgment book labeling model;
s7, extracting information of the automatically marked criminal judgment books, and constructing a Chinese criminal judgment book knowledge graph;
s8, converting the Chinese criminal judgment book knowledge graph into a national criminal judgment book knowledge graph based on the mapping relation of Chinese and national language; combining the Chinese criminal judgment knowledge graph to form a Chinese and national fusion criminal judgment knowledge graph;
wherein the preprocessing of the corpus of chinese criminal judgment books comprises:
labeling the first-level case list in the Chinese criminal judgment book corpus, and dividing the internal structure of the criminal judgment book text in the Chinese criminal judgment book corpus;
wherein, the internal structure of criminal judgement book text is divided into following structures: the title comprises a head part, a tail part and a text, wherein the head part and the tail part comprise information of a complaint authority, a person to be told, sex, birth date, ethnicity, cultural degree, criminal restraint reason and prosecution name, and the text comprises information of facts, reasons and judgment results.
2. The method for constructing the knowledge graph of the multilingual criminal judgment book as claimed in claim 1, wherein the step S3 is specifically as follows:
labeling the attribute labels of the criminal judgment books, extracting rules, performing proofreading, judging whether the labeled text content is matched with the labeling rules, if so, forming a criminal judgment book attribute label system and extracting rule templates, and if not, returning to the process, and re-labeling.
3. The method for constructing a knowledge graph of a multilingual criminal decision as claimed in claim 2, further comprising, in step S4: labeling the criminal judgment book terms and the legal ontology knowledge base, extracting rules, performing proofreading, judging whether the labeled text content is matched with the labeling rules, if so, forming a criminal judgment book attribute label system and extracting rule templates, and if not, returning to the process, and re-labeling.
4. The method for constructing the knowledge graph of the multilingual criminal judgment book as claimed in claim 1, wherein the step S6 is specifically as follows:
s601, converting a criminal judgment book from an unstructured criminal judgment book text to a structured criminal judgment book text by using a computer pattern matching algorithm and the automatic criminal judgment book labeling model;
s602, extracting an attribution representation method of the criminal judgment text based on the structured criminal judgment text.
5. The method for constructing a knowledge graph of a multilingual criminal decision as claimed in claim 4, wherein in step S7, the information extraction specifically includes: chapter structure analysis, sentence level extraction and word level extraction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910909778.7A CN110837564B (en) | 2019-09-25 | 2019-09-25 | Method for constructing multi-language criminal judgment book knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910909778.7A CN110837564B (en) | 2019-09-25 | 2019-09-25 | Method for constructing multi-language criminal judgment book knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110837564A CN110837564A (en) | 2020-02-25 |
| CN110837564B true CN110837564B (en) | 2023-10-27 |
Family
ID=69575137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910909778.7A Active CN110837564B (en) | 2019-09-25 | 2019-09-25 | Method for constructing multi-language criminal judgment book knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110837564B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737412A (en) * | 2020-05-21 | 2020-10-02 | 电子科技大学 | Citizen visiting guiding method based on natural language processing and knowledge graph |
| CN112001159A (en) * | 2020-08-24 | 2020-11-27 | 平安国际智慧城市科技股份有限公司 | Document generation method and device, electronic equipment and storage medium |
| CN112199511B (en) * | 2020-09-28 | 2022-07-08 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Cross-language multi-source vertical domain knowledge graph construction method |
| CN112445915A (en) * | 2021-01-28 | 2021-03-05 | 京华信息科技股份有限公司 | Document map extraction method and device based on machine learning and storage medium |
| CN113435164B (en) * | 2021-05-17 | 2024-02-13 | 中央民族大学 | Automatic labeling and extracting method and device for Mongolian arbitration document information |
| CN113239130A (en) * | 2021-06-18 | 2021-08-10 | 广东博维创远科技有限公司 | Criminal judicial literature-based knowledge graph construction method and device, electronic equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101576909A (en) * | 2009-05-11 | 2009-11-11 | 内蒙古蒙科立软件有限责任公司 | Mongolian digital knowledge base system construction method |
| CN104133848A (en) * | 2014-07-01 | 2014-11-05 | 中央民族大学 | Tibetan language entity knowledge information extraction method |
| CN104809176A (en) * | 2015-04-13 | 2015-07-29 | 中央民族大学 | Entity relationship extracting method of Zang language |
| 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 |
| CN107273106A (en) * | 2016-04-08 | 2017-10-20 | 北京三星通信技术研究有限公司 | Object information is translated and derivation information acquisition methods and device |
| CN107589826A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | The man-machine interaction method and system of knowledge based collection of illustrative plates |
| CN108009299A (en) * | 2017-12-28 | 2018-05-08 | 北京市律典通科技有限公司 | Law tries method and device for business processing |
| CN108197163A (en) * | 2017-12-14 | 2018-06-22 | 上海银江智慧智能化技术有限公司 | A kind of structuring processing method based on judgement document |
| CN108334500A (en) * | 2018-03-05 | 2018-07-27 | 上海思贤信息技术股份有限公司 | A kind of judgement document's mask method and device based on machine learning algorithm |
| CN108681977A (en) * | 2018-03-27 | 2018-10-19 | 成都律云科技有限公司 | A kind of lawyer's information processing method and system |
| CN109271529A (en) * | 2018-10-10 | 2019-01-25 | 内蒙古大学 | Cyrillic Mongolian and the double language knowledge mapping construction methods of traditional Mongolian |
-
2019
- 2019-09-25 CN CN201910909778.7A patent/CN110837564B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101576909A (en) * | 2009-05-11 | 2009-11-11 | 内蒙古蒙科立软件有限责任公司 | Mongolian digital knowledge base system construction method |
| CN104133848A (en) * | 2014-07-01 | 2014-11-05 | 中央民族大学 | Tibetan language entity knowledge information extraction method |
| CN104809176A (en) * | 2015-04-13 | 2015-07-29 | 中央民族大学 | Entity relationship extracting method of Zang language |
| CN107273106A (en) * | 2016-04-08 | 2017-10-20 | 北京三星通信技术研究有限公司 | Object information is translated and derivation information acquisition methods and device |
| CN107589826A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | The man-machine interaction method and system of knowledge based 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 |
| CN108197163A (en) * | 2017-12-14 | 2018-06-22 | 上海银江智慧智能化技术有限公司 | A kind of structuring processing method based on judgement document |
| CN108009299A (en) * | 2017-12-28 | 2018-05-08 | 北京市律典通科技有限公司 | Law tries method and device for business processing |
| CN108334500A (en) * | 2018-03-05 | 2018-07-27 | 上海思贤信息技术股份有限公司 | A kind of judgement document's mask method and device based on machine learning algorithm |
| CN108681977A (en) * | 2018-03-27 | 2018-10-19 | 成都律云科技有限公司 | A kind of lawyer's information processing method and system |
| CN109271529A (en) * | 2018-10-10 | 2019-01-25 | 内蒙古大学 | Cyrillic Mongolian and the double language knowledge mapping construction methods of traditional Mongolian |
Non-Patent Citations (2)
| Title |
|---|
| 多民族语言本体知识库构建技术;赵小兵 等;《中文信息报》;20110731;第25卷(第04期);71-74 * |
| 面向旅游的蒙汉双语知识图谱的研究与构建;耿雪来;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20190915(第09期);I138-1308 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110837564A (en) | 2020-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110837564B (en) | Method for constructing multi-language criminal judgment book knowledge graph | |
| CN109493265A (en) | A kind of Policy Interpretation method and Policy Interpretation system based on deep learning | |
| Adrian et al. | Contag: A semantic tag recommendation system | |
| US20120158400A1 (en) | Methods and systems for knowledge discovery | |
| CN112836046A (en) | Four-risk one-gold-field policy and regulation text entity identification method | |
| Lu et al. | USPTO patent prosecution research data: Unlocking office action traits | |
| CN110889786A (en) | Legal action insured advocate security use judging service method based on LSTM technology | |
| Curtotti et al. | Corpus based classification of text in Australian contracts | |
| Lee et al. | Sentiment classification for unlabeled dataset using doc2vec with jst | |
| CA2807494A1 (en) | Method and system for integrating web-based systems with local document processing applications | |
| US20140149106A1 (en) | Categorization Based on Word Distance | |
| Sinha et al. | Resume screening using natural language processing and machine learning: A systematic review | |
| CN113010684A (en) | Construction method and system of civil complaint and judgment map | |
| CN115329765A (en) | Method and device for identifying risks of listed enterprises, electronic equipment and storage medium | |
| Sirisha et al. | Semantic interdisciplinary evaluation of image captioning models | |
| Yeshpanov et al. | KazNERD: Kazakh named entity recognition dataset | |
| CN111563374B (en) | Personnel social relationship extraction method based on judicial official documents | |
| CN116308758B (en) | Financial risk analysis method and system based on big data | |
| CN110888940B (en) | Text information extraction method and device, computer equipment and storage medium | |
| CN112257442A (en) | Policy document information extraction method based on corpus expansion neural network | |
| Szabó et al. | Exploring the dynamic changes of key concepts of the Hungarian socialist era with natural language processing methods | |
| CN115422920B (en) | Method for identifying dispute focus of referee document based on BERT and GAT | |
| CN115600561A (en) | Webpage structuring method, equipment and storage medium fusing rules and small samples | |
| Ren et al. | Emotion detection in cross-lingual text based on bidirectional LSTM | |
| CN110516069B (en) | Fasttext-CRF-based quotation metadata extraction method |
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 |