CN113239130A - Criminal judicial literature-based knowledge graph construction method and device, electronic equipment and storage medium - Google Patents
Criminal judicial literature-based knowledge graph construction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113239130A CN113239130A CN202110677480.5A CN202110677480A CN113239130A CN 113239130 A CN113239130 A CN 113239130A CN 202110677480 A CN202110677480 A CN 202110677480A CN 113239130 A CN113239130 A CN 113239130A
- Authority
- CN
- China
- Prior art keywords
- criminal
- knowledge
- graph
- judicial
- entity
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 35
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 16
- 230000004927 fusion Effects 0.000 claims abstract description 14
- 230000033228 biological regulation Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 10
- 238000005516 engineering process Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 14
- 230000014509 gene expression Effects 0.000 claims description 8
- 230000006698 induction Effects 0.000 claims description 8
- 238000003058 natural language processing Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000009897 systematic effect Effects 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 9
- 239000000463 material Substances 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011840 criminal investigation Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services; Handling legal documents
Abstract
The invention discloses a construction method of a knowledge graph based on criminal judicial documents, which comprises the following steps: the method comprises the steps of classifying, processing, summarizing and summarizing various criminal plots specified by law regulations based on a server terminal, establishing a structured semantic knowledge base, forming and establishing a data set by automatically synchronizing data from a criminal referee document network or manually adding document data based on criminal factor map rules, obtaining entity information through entity identification, information extraction, knowledge fusion and knowledge storage, constructing a knowledge map, collecting and studying and analyzing the criminal referee document by adopting an artificial intelligence technical means, continuously iterating and updating, and perfecting the knowledge map. The invention has sufficient legal basis as legal support, and has high numerical accuracy; the method fully considers the difference factor of the criminal penalty amount, can be suitable for different criminal environments, and can be continuously updated and perfected.
Description
Technical Field
The invention relates to the technical field of judicial file character recognition, in particular to a construction method and a device of a knowledge map based on criminal judicial documents, an electronic device and a storage medium.
Background
The fact is the iron law which is based on the crime of the Chinese and foreign criminal law to convince and measure the criminal, and the fact corresponding to the criminal treatment mode and degree is the fact reflecting the specific form of the criminal and the agent factors attached to the criminal. Basic crime facts and related criminal cases are factors which have important influence on the degree of criminal fatality, the criminal fatality and the degree of criminal fatality of the same kind of crimes can be reflected, the omission of any factor can cause deviation of final criminal results, and relatively fair criminal results can be obtained only by designing legal compliance, scientific and reasonable case extraction factors.
Any crime has a plurality of basic plots, the plots for crime determination and criminal investigation are the most basic crime forms, the basic conditions of crime behaviors are reflected, the content forms of the crime determination plot and the criminal investigation plot are changeable, the constructed words are standard and complex, a specific character mode is not followed, and the extraction difficulty is high.
Disclosure of Invention
Aiming at the technical defects in the background art, the invention provides a construction method and a device of a knowledge graph based on criminal judicial documents, electronic equipment and a storage medium, which solve the technical problems and meet the actual requirements, and the specific technical scheme is as follows:
a construction method of a knowledge graph based on criminal judicial papers, the construction method comprising:
classifying, processing and summarizing various criminal episodes specified by law specifications of criminal law, criminal instruction and criminal law on the basis of a server terminal;
according to the classification processing and induction summary of various criminal plots, the plots are used as basic variables, legal logic is expanded, a structured semantic knowledge base is established, and a systematic complete criminal factor map rule is formed;
based on the criminal factor map rule, extracting criminal referee document automatic synchronization data from a large amount of document data of a criminal referee document network, or manually adding document data directly on a data set detail page to create a data set;
according to the content of the data set, entity information is obtained and labeled through entity identification, information extraction, knowledge fusion and knowledge storage;
constructing a knowledge graph based on a criminal referee document based on an criminal factor graph rule according to the marked entity information;
the established knowledge graph continuously adopts an artificial intelligence technical means, public legal documents are collected, legal and appropriate plot entity information is extracted from the large amount of criminal referee documents through learning and analyzing, and part of the legal and appropriate plot entity information is added into a knowledge base after manual examination and continuously iterated and updated, so that the knowledge graph is perfected.
As a further scheme of the present invention, the classification processing and induction summarization includes concept functions and features of sentencing, sentencing principles, sentencing related systems, various sentencing elements which need to be considered in the sentencing process according to the sentencing law, sentencing directive opinions, sentencing rules of different sentencing according to the sentencing law enforcement rules, and the present law and law, judicial interpretation and other notice regulations.
As a further scheme of the present invention, the criminal factor map rule is based on legislation or judicial evidence presented in the form of normative legal documents, including "the people's republic of china" law of highest people < criminal guidance opinions on common crimes > "the law of advanced people of Guangdong province < criminal guidance opinions on common crimes >" implementation rules "the law of highest people, the explanation of the highest people's inspection institute on handling several problems of law applicable to stolen criminal cases" (the law of advanced people of Guangdong province, the notice of the inspection institute of Guangdong province on determining the standard of the amount of stolen criminal cases ".
As a further scheme of the invention, the creation of the data set is based on the massive judicial data formed by criminal officials documents published by the Internet, and the data analysis and the data preprocessing are carried out on the judicial data in the criminal officials documents based on the criminal factor map rules, so as to label the given criminal officials documents in sections.
As a further scheme of the invention, the entity identification, the information extraction, the knowledge fusion and the knowledge storage are that according to the mutual relation of different case entities in the criminal factor map rule, the mass judicial text information is automatically, real-timely and definitely analyzed, deduced, extracted and fused through an NLP natural language processing technology, the specific expression and the elements in the criminal referee document are extracted by using a regular expression in combination with a mode matching method, and the type marking is carried out on the extracted entities by using a named entity identification technology.
As a further aspect of the present invention, the type label of the named entity includes a label entity label, a label relationship label and a specific rule, the entity label is obtained based on entity information of the entity identification, information extraction, knowledge fusion and knowledge storage, the relationship label is obtained based on a combination of interrelations of different case entities in the criminal factor map rule, and the specific rule means that the entity and the label are in a matching correspondence and is determined by the criminal factor map rule.
As a further scheme of the present invention, the construction of the knowledge graph specifically includes performing relationship construction on the entity information according to the entity labels and the relationship labels labeled by the entity information through the sentencing factor graph rule, so as to determine the relationship between the entity information and construct the knowledge graph.
A server based on a construction method of a knowledge-graph based on criminal judicial papers, comprising: one or more processors, memory, one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: the construction method of the criminal judicial paperwork-based knowledge graph in the above embodiment is performed.
The invention has the beneficial effects that: the criminal referee document-based knowledge graph is constructed in a top-down mode and a bottom-up mode, high-quality data, a body and mode information are extracted from legal and legal contents, the criminal factor graph rule is constructed, the law and the legal are fully followed, and sufficient legal basis is provided as legal support. Then, by means of an artificial intelligence technology, public legal documents are collected, mass criminal referee documents are learned and analyzed, legal and appropriate plot entity information is extracted from the documents, part of the documents are added into a knowledge base after being manually checked, the documents are enough in number, the documents can comprehensively reflect all required materials depending on the structural content of the documents, and the numerical accuracy obtained by intelligent calculation through a big data algorithm is also high enough.
Besides, the knowledge map takes the actual criminal referee document stolen as a material, so that the free referee right of the officers involved in the criminal penalty referee, the regional difference, the economic culture difference and other factors of the officers are taken into consideration, the knowledge map can be suitable for different quantitative environments, and accurate data information is provided to greatly assist the realization of criminal monitoring. Meanwhile, the construction of the knowledge graph can be realized through deep learning, intelligent capture and locking and automatic absorption of the criminal rules established in the latest legislation, judicial interpretation and instructional cases.
Drawings
FIG. 1 is a logic flow diagram of the present invention.
Detailed Description
Embodiments of the present invention will be described below with reference to the accompanying drawings and related embodiments, wherein the following related embodiments are merely preferred embodiments for better illustrating the present invention itself, and the embodiments of the present invention are not limited to the following embodiments, and the present invention relates to the related essential parts in the technical field, which should be regarded as the known technology in the technical field and can be known and grasped by those skilled in the art.
A construction method of a knowledge graph based on criminal judicial papers, the construction method comprising:
classifying, processing and summarizing various criminal episodes specified by law specifications of criminal law, criminal instruction and criminal law on the basis of a server terminal;
according to the classification processing and induction summary of various criminal plots, the plots are used as basic variables, legal logic is expanded, a structured semantic knowledge base is established, and a systematic complete criminal factor map rule is formed;
based on the criminal factor map rule, extracting criminal referee document automatic synchronization data from a large amount of document data of a criminal referee document network, or manually adding document data directly on a data set detail page to create a data set;
according to the content of the data set, entity information is obtained and labeled through entity identification, information extraction, knowledge fusion and knowledge storage;
constructing a knowledge graph based on a criminal referee document based on an criminal factor graph rule according to the marked entity information;
the established knowledge graph continuously adopts an artificial intelligence technical means, public legal documents are collected, legal and appropriate plot entity information is extracted from the large amount of criminal referee documents through learning and analyzing, and part of the legal and appropriate plot entity information is added into a knowledge base after manual examination and continuously iterated and updated, so that the knowledge graph is perfected.
The judicial knowledge map is the basis of judicial intelligent application, and the construction of the stealing knowledge map by using an artificial intelligent technology is the first step for realizing the criminal monitoring model. The method is also a technical guarantee for promoting judicial intelligence, and comprises information such as entities, concepts, attributes, relationships and the like. The construction of a knowledge graph requires that various kinds of knowledge constructed by the knowledge graph are obtained from different forms of data sources through a knowledge extraction technology, and various kinds of unsuitable knowledge are removed through knowledge fusion, so that the quality and the performance of the knowledge graph are improved. For example, from the perspective of blending the knowledge map into a legal situation model, the criminal knowledge map for stealing is to organize a structured semantic knowledge base describing the relationship between case facts and referee results by combing and refining criminal facts for stealing crimes into case elements such as crime-making situation elements and criminal situation elements, and thus objectively reflect the relationship between crimes and criminal penalties. The invention carries out classification processing and induction summarization on various criminal plots specified by law specifications such as criminal law, criminal instruction, criminal law, and the like through the server terminal, takes the plots as basic variables, expands legal logic, establishes a structured semantic knowledge base, and forms a systematic complete criminal factor map rule. For example, in the aspect of a crime scene, the theft amount can be subdivided into a large amount, a huge amount and a special huge amount, and is linked with a specific amount. As another example, the criminal scenario of self-beginning can be subdivided into "self-beginning of active case," self-beginning (light crime) "," self-beginning (actively taking a position after questioning due to suspicious patterns or during forced drug abstinence) "," self-beginning (discovered by the handling organization but not investigating conversation, actively taking a position) "," self-beginning (actively taking a position to a criminal or dissuading by relatives and accompanying with self) "," other types of self-beginning ", and is connected with the penalty relief.
After the criminal factor map rule is established, the artificial intelligence and the big data technology are comprehensively applied, structured and semi-structured text data are extracted from legal regulations and judicial criminal referee documents, the knowledge map of stealing criminal cases is drawn by setting the knowledge elements such as crime-setting case elements and criminal case elements, and the knowledge map of stealing criminal cases is established through continuous iterative updating of links such as 'entity identification, information extraction, knowledge fusion and knowledge storage' so as to ensure standardization and precision of criminals. The construction technology of the knowledge graph is mainly divided into a top-down mode and a bottom-up mode in practice. The realization path of constructing the map from top to bottom mainly refers to the legal and legal contents, extracts high-quality data and body and mode information in the data, such as entity information of a legal conviction and an appraisal, and adds the entity information into a knowledge base. The bottom-up atlas structure is obtained by means of artificial intelligence technology, public legal documents are collected, mass criminal referee documents are studied and analyzed, legal and appropriate plot entity information is extracted from the documents, and part of the documents are added into a knowledge base after manual examination. The knowledge graph can be completely constructed according to laws and regulations, and meanwhile, information receipts are continuously extracted from mass criminal referee document data for learning and perfecting, so that the accurate criminal knowledge graph suitable for the judicial field is constructed, the optimization of a machine model is facilitated, and the recognition accuracy is improved.
As a further scheme of the present invention, the classification processing and induction summarization includes concept functions and features of sentencing, sentencing principles, sentencing related systems, various sentencing elements which need to be considered in the sentencing process according to the sentencing law, sentencing directive opinions, sentencing rules of different sentencing according to the sentencing law enforcement rules, and the present law and law, judicial interpretation and other notice regulations.
As a further scheme of the present invention, the criminal factor map rule is based on legislation or judicial evidence presented in the form of normative legal documents, including "the people's republic of china" law of highest people < criminal guidance opinions on common crimes > "the law of advanced people of Guangdong province < criminal guidance opinions on common crimes >" implementation rules "the law of highest people, the explanation of the highest people's inspection institute on handling several problems of law applicable to stolen criminal cases" (the law of advanced people of Guangdong province, the notice of the inspection institute of Guangdong province on determining the standard of the amount of stolen criminal cases ".
The classification processing and the induction summarization are based on the rules of the criminal law general rule on the basic principle of the sentencing, and specifically include but not limited to the concept function and the characteristics of the sentencing, the sentencing principle, the basic theoretical knowledge of the sentencing relevant system and the like, and are also based on various sentencing plot elements which need to be considered in the sentencing process of the sentencing law, sentencing instruction opinions and sentencing rules of different sentencing rules of each criminal specified by the sentencing implementation rules of the corresponding sentencing of each province.
The sentention factor map rules are based on, but not limited to, the current laws and regulations, judicial explanations and other notice regulations, and specifically include, but not limited to, legislation or judicial bases presented in the form of normative legal documents, such as "national common people's republic of china" highest people's court < sentention instruction comments on common crimes > "," high-level people's court of Guangdong province < sentention instruction comments on common crimes > implementation rules ".
According to certain laws and regulations, the criminal factor map rule takes documents such as highest people's law of the people's republic of China < criminal instruction opinions about common crimes >, (high-grade people's law of Guangdong province < criminal instruction opinions about common crimes >) and the like as a legal basis for constructing the criminal factor map rule, and the factors influencing the criminal are quantitatively analyzed. In conclusion, the knowledge graph construction has enough legal basis for law support for monitoring, massive case big data obtained by big data artificial intelligence application technical means are enough in quantity, documents can comprehensively reflect all materials required by monitoring depending on the structural content of the documents, numerical value accuracy obtained by intelligent calculation of a big data algorithm is also high enough, meanwhile, the criminal monitoring theoretical model takes criminal referees documents as materials and monitoring objects, the criminal free cutting right involved in the criminal referees and the factors such as regional difference and economic and cultural difference of the criminal referees are necessarily considered, and the criminal monitoring theoretical model integrates all positive factors to greatly assist in realizing the criminal monitoring.
As a further scheme of the invention, the creation of the data set is based on the massive judicial data formed by criminal officials documents published by the Internet, and the data analysis and the data preprocessing are carried out on the judicial data in the criminal officials documents based on the criminal factor map rules, so as to label the given criminal officials documents in sections.
The legal documents are the main expression form of case data, and the mass judicial big data formed by criminal referee documents published by people's court on the internet becomes important materials for analyzing criminal law theft and criminal law construction and criminal monitoring models, and mainly comprises the occurrence process of cases, case related personnel information, referee results and the like. The invention carries out data analysis and data preprocessing on judicial data in the criminal official document, labels the given criminal official document in a segmented mode, and carries out information arrangement on the criminal official document from the content structure, such as classified segmentation of a title, a text and a tail. Numbering the name of the judging mechanism and the type of the document in the title part, and the information of the personnel involved in the case, the case generation process and the judgment and identification result in the text part; and (3) labeling the names, the trial time and other contents of the participants at the end, and degrading the information of the criminal referee document from the document level to the label level, so that the next step of entity information processing is facilitated. A criminal referee document is accurately identified, collected, labeled and associated with information in the case, including but not limited to, the name of a crime, the year of the referee, the level of a court, an accreditation program, the nature of the document, the crime episode, the sentencing episode, the president, the postponement of criminals, and the like.
As a further scheme of the invention, the entity identification, the information extraction, the knowledge fusion and the knowledge storage are that according to the mutual relation of different case entities in the criminal factor map rule, the mass judicial text information is automatically, real-timely and definitely analyzed, deduced, extracted and fused through an NLP natural language processing technology, the specific expression and the elements in the criminal referee document are extracted by using a regular expression in combination with a mode matching method, and the type marking is carried out on the extracted entities by using a named entity identification technology.
Extracted in the data set: the contents of the name of the advertiser, the year of the judge, the judging structure, the court level, the treating program, the nature of the document, the chief criminal, the delay criminal and the like are obvious in text form characteristics and follow a certain character pattern, so that the method can adopt a pattern matching mode and carry out directional extraction on the contents by constructing a regular expression model.
Any crime has a plurality of basic plots, the plots for crime and sentencing are the most basic crime forms, the basic conditions of crime behaviors are reflected, the content forms of the crime and sentencing plots are changeable, the constructed words are standard and complex, a specific character mode is not followed, and the extraction difficulty is large. The entity identification, information extraction, knowledge fusion and knowledge storage are used for preprocessing semi-structured and unstructured text data in the field of data mining, extracting information such as specified events and facts from massive criminal referee documents, and forming structured storage in the server terminal. Under the legal situation, the NLP natural language processing technology automatically, real-timely and definitely analyzes, deduces, extracts and fuses massive judicial text information, and can accurately extract corresponding plots from the legal language (one state of natural language) of the legal document. The method has the advantages that based on a designed criminal case body framework, semi-structured and unstructured data in batch criminal referee documents are subjected to semantic annotation and characteristic extraction, tags with good structuring degree and rich semantic information are formed and stored in a case library, and valuable information conversion from 'sleeping' mass data to the operation of a support model is realized.
As a further aspect of the present invention, the type label of the named entity includes a label entity label, a label relationship label and a specific rule, the entity label is obtained based on entity information of the entity identification, information extraction, knowledge fusion and knowledge storage, the relationship label is obtained based on a combination of interrelations of different case entities in the criminal factor map rule, and the specific rule means that the entity and the label are in a matching correspondence and is determined by the criminal factor map rule.
As a further scheme of the present invention, the construction of the knowledge graph specifically includes performing relationship construction on the entity information according to the entity labels and the relationship labels labeled by the entity information through the sentencing factor graph rule, so as to determine the relationship between the entity information and construct the knowledge graph.
And the entity information constructs entity triples through the entity labels and the relationship labels obtained by naming the entities, and the triples are screened and sorted for effectiveness to form entity relationship triples which are most suitable for the rules of the sentencing factor maps, and the obtained entity relationship triples form a complete knowledge language logic system to become the theoretical basis of the knowledge maps. The entity labels and the relation labels define a plurality of relations such as case involvement, type, acceptance and the like in the criminal referee document, the relations among a plurality of entity information can form a complete knowledge base, and a knowledge map based on the criminal referee document is formed through data construction. Then, through the technical means of continuously adopting artificial intelligence, the public legal documents are collected, the legal and appropriate plot entity information is extracted from the large amount of criminal referee documents through learning and analyzing, part of the legal and appropriate plot entity information is added into a knowledge base after manual examination and continuously iterated and updated, and the knowledge map is continuously perfected.
A server based on a construction method of a knowledge-graph based on criminal judicial papers, comprising: one or more processors, memory, one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: the construction method of the criminal judicial paperwork-based knowledge graph in the above embodiment is performed.
An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for predicting the actual criminal period of a crime according to any one of the technical solutions. The computer-readable storage medium includes, but is not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magnetic-optical disks, ROMs (read-only memories), RAMs (random access memories), EPROMs (erasable programmable read-only memories), EEPROMs (electrically erasable programmable read-only memories), flash memory, magnetic cards, or optical cards. That is, a storage device includes any medium that stores or transmits a message in a form readable by a device (e.g., a computer, a cell phone), and may be a read-only memory, a magnetic or optical disk, or the like.
As one embodiment, the server includes: one or more processors, a memory, one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of criminal law document based knowledge-graph construction in the above embodiments.
The server provided by the embodiment of the invention can realize the embodiment of the construction method of the knowledge graph based on the criminal judicial essay, and for the specific function realization, please refer to the description in the detailed method embodiment, which is not repeated herein.
In the embodiment of the invention, artificial intelligence and big data technology are comprehensively applied, structured and semi-structured text data are extracted from law, regulation and judicial criminal officials documents, the knowledge map based on the criminal officials documents is drawn by setting the knowledge elements such as criminal case elements, criminal case elements and the like, and the knowledge map for stealing criminal cases is constructed through continuous iterative updating of links such as 'entity identification, information extraction, knowledge fusion, knowledge storage' and the like, so as to ensure standardization and precision of criminal officials.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (8)
1. A construction method of a knowledge graph based on criminal judicial documents is characterized by comprising the following steps:
classifying, processing and summarizing various criminal episodes specified by law specifications of criminal law, criminal instruction and criminal law on the basis of a server terminal;
according to the classification processing and induction summary of various criminal plots, the plots are used as basic variables, legal logic is expanded, a structured semantic knowledge base is established, and a systematic complete criminal factor map rule is formed;
based on the criminal factor map rule, extracting criminal referee document automatic synchronization data from a large amount of document data of a criminal referee document network, or manually adding document data directly on a data set detail page to create a data set;
according to the content of the data set, entity information is obtained through entity identification, information extraction, knowledge fusion and knowledge storage, and type marking is carried out;
constructing a knowledge graph based on criminal referee documents based on the criminal factor graph rule according to the marked entity information;
the established knowledge graph continuously adopts an artificial intelligence technical means, public legal documents are collected, legal and appropriate plot entity information is extracted from the large amount of criminal referee documents through learning and analyzing, and part of the legal and appropriate plot entity information is added into a knowledge base after manual examination and continuously iterated and updated, so that the knowledge graph is perfected.
2. The criminal judicial paperwork-based knowledge-graph construction method according to claim 1, wherein said classification and induction summarize comprises concept functions and features of criminal, principles of criminal, related laws of criminal, various elements of criminal plots to be considered in the course of criminal regulation, and different rules of criminal regulation, which are regulated by the corresponding law enforcement rules of each province, as well as current laws and regulations, judicial interpretations and other notice regulations.
3. The construction method of knowledge-graph based on criminal judicial papers according to claim 1, characterized in that the criminal factor-graph rules are based on legislation or judicial evidence presented in the form of normative legal documents, including "people's republic of china" criminal law of the highest people's court < criminal instruction opinions on common crimes > "law of senior people of Guangdong province < criminal instruction opinions on common crimes >" enforcement rules of the highest people's court, the highest people's inspection institute about handling a plurality of problems of applicable law for stealing criminal cases "(notice of senior people's court of Guangdong province, Guangdong province's inspection institute about determining the amount standard of stealing criminal cases).
4. The criminal judicial paperwork-based knowledge-graph construction method according to claim 1, wherein the data set is created according to massive large judicial data formed by criminal officials paperwork published on the internet, and the judicial data in the criminal officials paperwork is subjected to data analysis and data preprocessing based on the criminal factor graph rule, so as to label the given criminal officials paperwork in sections.
5. The criminal judicial paperwork-based knowledge-graph construction method according to claim 1, wherein the entity recognition, information extraction, knowledge fusion and knowledge storage are implemented by analyzing, deducing, extracting and fusing mass judicial text information automatically, in real time and definitely through an NLP (non line language processing) natural language processing technology according to the interrelation of different case entities in the criminal factor graph rule, combining a mode matching method, extracting specific expressions and elements in the criminal judicial paperwork through a regular expression, and performing the type marking on the extracted entities through a named entity recognition technology.
6. The criminal judicial paperwork-based knowledge-graph construction method according to claim 5, wherein the type labels of the named entities comprise labeled entity labels, labeled relationship labels and specific rules, the entity labels are obtained based on entity information of the entity identification, information extraction, knowledge fusion and knowledge storage, the relationship labels are obtained based on the mutual relationship combination of different case entities in the criminal factor graph rules, and the specific rules refer to the fact that the entities and the labels are in matching correspondence and are determined by the criminal factor graph rules.
7. The criminal judicial paperwork-based knowledge-graph construction method according to claim 6, wherein the knowledge-graph is specifically constructed by performing relationship construction on the entity information according to the entity labels marked on the entity information and the relationship labels through the criminal factor graph rule, so as to determine the relationship between the entity information and construct the knowledge-graph.
8. A server, characterized in that it comprises: one or more processors, memory, one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: a construction method of a criminal law document based knowledge-graph according to any one of claims 1 to 7 is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110677480.5A CN113239130A (en) | 2021-06-18 | 2021-06-18 | Criminal judicial literature-based knowledge graph construction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110677480.5A CN113239130A (en) | 2021-06-18 | 2021-06-18 | Criminal judicial literature-based knowledge graph construction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113239130A true CN113239130A (en) | 2021-08-10 |
Family
ID=77140351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110677480.5A Pending CN113239130A (en) | 2021-06-18 | 2021-06-18 | Criminal judicial literature-based knowledge graph construction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113239130A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114610954A (en) * | 2022-03-09 | 2022-06-10 | 上海弘玑信息技术有限公司 | Information processing method and device, storage medium and electronic equipment |
| CN114911879A (en) * | 2022-07-19 | 2022-08-16 | 南京航天数智科技有限公司 | Criminal case knowledge map relation reasoning method based on graph attention network |
| CN115203439B (en) * | 2022-09-15 | 2022-11-29 | 天津市道本科技有限公司 | Construction method of knowledge graph for compliance supervision, related method and system |
| CN115687632A (en) * | 2022-08-25 | 2023-02-03 | 中国司法大数据研究院有限公司 | Criminal measuring plot decomposition analysis method and system |
| CN115858507A (en) * | 2022-08-25 | 2023-03-28 | 中国司法大数据研究院有限公司 | Method and system for automatic assessment, error correction and completion of criminal investigation rule |
| CN115982388A (en) * | 2023-03-06 | 2023-04-18 | 共道网络科技有限公司 | Case quality control map establishing method, case document quality testing method, case quality control map establishing equipment and storage medium |
| CN116127977A (en) * | 2023-02-08 | 2023-05-16 | 中国司法大数据研究院有限公司 | Casualties extraction method for referee document |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN110837564A (en) * | 2019-09-25 | 2020-02-25 | 中央民族大学 | Construction method of knowledge graph of multilingual criminal judgment books |
| US20200073932A1 (en) * | 2018-08-30 | 2020-03-05 | Intelligent Fusion Technology, Inc | Method and system for pattern discovery and real-time anomaly detection based on knowledge graph |
| CN111291161A (en) * | 2020-02-20 | 2020-06-16 | 平安科技（深圳）有限公司 | Legal case knowledge graph query method, device, equipment and storage medium |
| CN111930856A (en) * | 2020-07-06 | 2020-11-13 | 北京邮电大学 | Method, device and system for constructing domain knowledge graph ontology and data |
| CN112347270A (en) * | 2020-11-30 | 2021-02-09 | 重庆工程职业技术学院 | Legal knowledge graph construction system and method |
-
2021
- 2021-06-18 CN CN202110677480.5A patent/CN113239130A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| US20200073932A1 (en) * | 2018-08-30 | 2020-03-05 | Intelligent Fusion Technology, Inc | Method and system for pattern discovery and real-time anomaly detection based on knowledge graph |
| CN110837564A (en) * | 2019-09-25 | 2020-02-25 | 中央民族大学 | Construction method of knowledge graph of multilingual criminal judgment books |
| CN111291161A (en) * | 2020-02-20 | 2020-06-16 | 平安科技（深圳）有限公司 | Legal case knowledge graph query method, device, equipment and storage medium |
| CN111930856A (en) * | 2020-07-06 | 2020-11-13 | 北京邮电大学 | Method, device and system for constructing domain knowledge graph ontology and data |
| CN112347270A (en) * | 2020-11-30 | 2021-02-09 | 重庆工程职业技术学院 | Legal knowledge graph construction system and method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114610954A (en) * | 2022-03-09 | 2022-06-10 | 上海弘玑信息技术有限公司 | Information processing method and device, storage medium and electronic equipment |
| CN114911879A (en) * | 2022-07-19 | 2022-08-16 | 南京航天数智科技有限公司 | Criminal case knowledge map relation reasoning method based on graph attention network |
| CN115687632A (en) * | 2022-08-25 | 2023-02-03 | 中国司法大数据研究院有限公司 | Criminal measuring plot decomposition analysis method and system |
| CN115858507A (en) * | 2022-08-25 | 2023-03-28 | 中国司法大数据研究院有限公司 | Method and system for automatic assessment, error correction and completion of criminal investigation rule |
| CN115687632B (en) * | 2022-08-25 | 2024-04-09 | 中国司法大数据研究院有限公司 | Criminal investigation plot decomposition analysis method and system |
| CN115203439B (en) * | 2022-09-15 | 2022-11-29 | 天津市道本科技有限公司 | Construction method of knowledge graph for compliance supervision, related method and system |
| CN116127977A (en) * | 2023-02-08 | 2023-05-16 | 中国司法大数据研究院有限公司 | Casualties extraction method for referee document |
| CN116127977B (en) * | 2023-02-08 | 2023-10-03 | 中国司法大数据研究院有限公司 | Casualties extraction method for referee document |
| CN115982388A (en) * | 2023-03-06 | 2023-04-18 | 共道网络科技有限公司 | Case quality control map establishing method, case document quality testing method, case quality control map establishing equipment and storage medium |
| CN115982388B (en) * | 2023-03-06 | 2024-04-19 | 共道网络科技有限公司 | Case quality control map establishment method, case document quality inspection method, case quality control map establishment equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113239130A (en) | Criminal judicial literature-based knowledge graph construction method and device, electronic equipment and storage medium | |
| Sleimi et al. | Automated extraction of semantic legal metadata using natural language processing | |
| CN108572967B (en) | Method and device for creating enterprise portrait | |
| CN112182246B (en) | Method, system, medium, and application for creating an enterprise representation through big data analysis | |
| CN107403375A (en) | A kind of listed company's bulletin classification and abstraction generating method based on deep learning | |
| CN113239208A (en) | Mark training model based on knowledge graph | |
| CN108108744B (en) | Method and system for radiation image auxiliary analysis | |
| CN108563783B (en) | Financial analysis management system and method based on big data | |
| CN109800354B (en) | Resume modification intention identification method and system based on block chain storage | |
| CN110147540B (en) | Method and system for generating business security requirement document | |
| CN109492097B (en) | Enterprise news data risk classification method | |
| CN103176984A (en) | Detection method of deceptive rubbish suggestions in user generated contents | |
| CN110770781A (en) | Legal information processing system, method and program | |
| CN114860882A (en) | Fair competition review auxiliary method based on text classification model | |
| CN112347254A (en) | News text classification method and device, computer equipment and storage medium | |
| Bacalu | Digital policing tools as social control technologies: data-driven predictive algorithms, automated facial recognition surveillance, and law enforcement biometrics | |
| CN115794798B (en) | Market supervision informatization standard management and dynamic maintenance system and method | |
| CN115936932A (en) | Method and device for processing judicial documents, electronic equipment and storage medium | |
| CN115618085A (en) | Interface data exposure detection method based on dynamic label | |
| Kruse et al. | Developing a legal form classification and extraction approach for company entity matching: Benchmark of rule-based and machine learning approaches | |
| CN112988972A (en) | Administrative penalty file evaluation and checking method and system based on data model | |
| Watanabe et al. | A study on support method of consulting service using text mining | |
| Burley et al. | Nlp workflows for computational social science: Understanding triggers of state-led mass killings | |
| KR20220068937A (en) | Standard Industrial Classification Based on Machine Learning Approach | |
| CN113157949A (en) | Method and device for extracting event information, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210810 |