CN110781254A - Automatic case knowledge graph construction method, system, equipment and medium - Google Patents
Automatic case knowledge graph construction method, system, equipment and medium Download PDFInfo
- Publication number
- CN110781254A CN110781254A CN202010001253.6A CN202010001253A CN110781254A CN 110781254 A CN110781254 A CN 110781254A CN 202010001253 A CN202010001253 A CN 202010001253A CN 110781254 A CN110781254 A CN 110781254A
- Authority
- CN
- China
- Prior art keywords
- entity
- model
- case
- knowledge graph
- bert
- 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 20
- 238000000605 extraction Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000013145 classification model Methods 0.000 claims abstract description 21
- 238000004590 computer program Methods 0.000 claims description 20
- 230000004927 fusion Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 7
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 206010039203 Road traffic accident Diseases 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000002585 base Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012458 free base Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000007 visual effect 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method, a system, equipment and a medium for automatically constructing a case knowledge graph, which comprise the following steps: predefining entity relationships based on an expert library; training a structured classification model of the referee document by adopting a Bert classification model; training an entity recognition model by adopting a model prototype Bert + CRF; training a relation extraction model by adopting a model prototype based on a Bert relation extraction model; constructing a case knowledge graph; improving the coding layer of the entity recognition reference model by using the CRF to obtain a Bert-CRF model, and further improving the entity recognition effect F1 value; and fusing the translation embedded multi-task combined semantic relation extraction model Bert, and improving the relation extraction result F1 value. The invention designs a case situation knowledge graph automatic construction method fusing a structured text and an unstructured text, constructs a case situation knowledge graph of a large-scale judicial case, and provides semantic support for accurate pushing of class cases and the like.
Description
Technical Field
The invention relates to the field of artificial intelligence and data processing, in particular to a method, a system, equipment and a medium for automatically constructing a case knowledge graph.
Background
Google corporation formally proposed the concept of knowledge-graph in 2012. The existing representative knowledge base includes: freebase, Wikidata, DBpedia, YAGO and the like. The knowledge base belongs to a general knowledge map, data basically come from data of an open community or an open domain, and the significance of the application to the actual vertical field is not large. In the conventional knowledge graph facing to the vertical field, a data source is mainly structured or quasi-structured text data.
Text data in the legal field is mainly unstructured text information, and the construction of a knowledge graph in the legal field is still in an exploration stage at present.
Disclosure of Invention
The invention aims to realize that a machine can recognize a mass referee document resource library through a technology in a judicial reform process promoted by artificial intelligence; the automatic learning and case recognition by the machine are realized, and a foundation is laid for a series of judicial applications such as similar case retrieval, accurate pushing of class cases, automatic generation of referee documents and the like.
In order to achieve the aim, the invention provides an automatic construction method of a case knowledge graph, which comprises the following steps:
step A: establishing an expert database, and predefining entity relationships based on the expert database, wherein the entities are topics related by law, the relationships are associations among the entities, and the predefined entity relationships are used for subsequent entity identification, relationship extraction and triple construction;
and B: training a structured classification model of the referee document by adopting a Bert classification model; training an entity recognition model by adopting a model prototype Bert + CRF; training a relation extraction model by adopting a model prototype based on a Bert relation extraction model;
and C: constructing a case knowledge graph, comprising the following steps:
step C1: classifying the content of the referee document based on the trained structured classification model of the referee document, and extracting the basic fact and the basic fact of the case;
step C2: carrying out entity recognition on the case basic facts based on the trained entity recognition model, and extracting various entities in the case basic facts;
step C3: based on the entities extracted in the step C2 and the case basic facts obtained in the step C1, extracting the relationships between the entities using the trained relationship extraction model to obtain entity relationship triples, the basic form of the triples being (entity 1, relationship between entity 1 and entity 2, entity 2);
step C4: and C, extracting the entities and attributes in the basic facts obtained in the step C1, and carrying out knowledge fusion on the obtained entities and attributes and the triples obtained in the step C3 to obtain a complete case situation knowledge graph.
Preferably, the expert database comprises a plurality of legal professional experts, and the experts specifically analyze and summarize judicial practices according to cases and then define entity relationships in advance.
Preferably, the ground truth is the court certified fact portion of the official document; the basic fact is the case basic information part of the official document, including: basic information of the defendant and the original defendant.
Preferably, step C3 further includes: and fusing the obtained triples by adopting an entity alignment and entity link method.
Preferably, the step C further includes:
step C5: storing the acquired case knowledge map by using a map database;
step C6: and visually displaying the case knowledge map.
Preferably, the method adopts a CRF to improve an encoding layer of an entity recognition reference model (bi-LSTM + CRF) to obtain a Bert + CRF model, namely an entity recognition model, so that the entity recognition effect F1 value is further improved.
Preferably, the relationship extraction model in the method is a translation-embedded multi-task combined semantic relationship extraction model Bert, so that the value of the relationship extraction result F1 is improved.
The invention also provides an automatic case knowledge graph construction system, which comprises:
the pre-defining unit is used for establishing an expert database and predefining entity relationships based on the expert database;
the model training unit is used for carrying out structured classification models on the referee documents by adopting a Bert classification model; training an entity recognition model by adopting a model prototype Bert + CRF; training a relation extraction model by adopting a model prototype based on a Bert relation extraction model;
the case knowledge graph building unit is used for building a case knowledge graph and comprises the following steps:
classifying the content of the referee document based on the trained structured classification model of the referee document, and extracting the basic fact and the basic fact of the case; carrying out entity recognition on the case basic facts based on the trained entity recognition model, and extracting various entities in the case basic facts; extracting the relationship between the entities by using a trained relationship extraction model based on the extracted entities and the obtained case basic facts to obtain entity relationship triples; and extracting the entity and the attribute of the case basic fact, and carrying out knowledge fusion on the obtained entity and attribute and the triples to obtain a complete case knowledge map.
The invention also provides automatic case knowledge graph construction equipment which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the steps of the method for automatically constructing the case knowledge graph when executing the computer program.
A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method of automatically constructing a case knowledge graph.
One or more technical schemes provided by the invention at least have the following technical effects or advantages:
according to the method, the CRF is adopted to improve the coding layer of the entity recognition reference model to obtain the Bert-CRF model, so that the entity recognition effect F1 value is further improved; the invention provides a translation-embedded multi-task combined semantic relation extraction model Bert, and a relation extraction result F1 is improved; the invention designs a case situation knowledge graph automatic construction process integrating the structured text and the unstructured text, constructs the case situation knowledge graph of a large-scale judicial case, and provides semantic support for downstream tasks such as accurate class case pushing.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention;
FIG. 1 is a schematic flow chart of a method for automatically constructing a case knowledge graph according to the present invention;
FIG. 2 is a schematic diagram of an automatic construction system of a case knowledge graph according to the present invention;
FIG. 3 is a schematic structural diagram of an automatic construction device of a case knowledge graph in the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflicting with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described and thus the scope of the present invention is not limited by the specific embodiments disclosed below.
The invention aims to construct a visual case knowledge map through a legal referee document. Referring to fig. 1, the method mainly includes three major steps: step A, entity relation predefining; b, training a model; and step C, constructing batch case knowledge maps.
Step A: entity relationships are predefined. Expert scholars in the legal profession summarize the judicial practice according to case specific analysis, and then define the entity relationship in advance. Entity: refers to something that is distinguishable and exists independently, the relationship: used to connect two entities, depicting the association between them.
And B: and (5) training the model. Training a structured classification model of the referee document by adopting a Bert classification model; training an entity recognition model by adopting a model prototype Bert + CRF; and training the relation extraction model by adopting a model prototype based on the Bert relation extraction model.
And C: and constructing batch case knowledge maps. And (C) after the model training of the step B is finished, constructing case situation knowledge maps for all referee documents of the case. The construction is completed by the following 7 steps, and the specific flow chart is shown in figure 1:
step C1: the structured classification model of the referee document is utilized to classify the content of the referee document, and basic facts of the case (the basic facts are the court affirmation facts, the basic facts are the basic information of the case and contain the basic information of the announcements, the original announcements and the like) are extracted.
Step C2: and D, utilizing the entity recognition model trained in the step B to perform entity recognition on the case basic facts, and extracting various entities in the case basic facts.
Step C3: and B, extracting the relationship between the entities by using the relationship extraction model trained in the step B based on the extracted entities and the case basic facts to obtain entity relationship triples.
Step C4: and fusing the obtained triples by adopting the methods of entity alignment and entity link.
Step C5: and (4) extracting the entity and the attribute of the case basic fact in a regular form, and then fusing the entity and the attribute with the triple knowledge obtained in the step C4 to obtain a complete case knowledge map.
Step C6: and storing the obtained case knowledge map by using a map database.
Step C7: and visually displaying the case knowledge map.
The method is mainly divided into three steps for execution, predefining of entity relation, model training and predefining of batch case knowledge maps.
In the first step, the law enforcement of the road traffic plan is summarized by 4 law experts having years of experience on the road traffic law enforcement, and then the 4 experts and two knowledge map technical experts together define the entities and the relations involved in the road traffic. Under the road traffic case by type, 22 types of entities and 9 types of relations are defined.
And secondly, model training, wherein 2000 pieces of judge document are randomly sampled from 300 ten thousand plus 'motor vehicle traffic accident liability dispute' trial and judge document to carry out structuralization of the judge document, data marking of entity identification and relation extraction is carried out, after the data marking is finished, a classification model based on Bert, an entity identification model and a relation extraction model are trained, after the model training is finished, 300 ten thousand plus 'motor vehicle traffic accident liability dispute' trial and judge document is screened through the model, and the entity identification model and the relation extraction model are optimized by utilizing the screened 2000 pieces of judge document.
And thirdly, constructing case knowledge maps in batches. And (3) constructing a case situation knowledge graph of 300 ten thousand plus 'motor vehicle traffic accident responsibility dispute' one-pass judge document. As shown in the flow chart of FIG. 1, each referee document goes through the entire flow chart. Firstly, acquiring a referee document, classifying by using a structured model of the referee document, extracting basic facts and basic fact parts, then obtaining triplets related to case situations by the basic facts through an entity identification model and a relation extraction model, removing duplication of the triplets, aligning entities, linking the entities, simultaneously carrying out rule extraction on the basic fact parts, extracting original and advertised basic information, and then carrying out knowledge fusion on the two parts. And finally, storing the knowledge obtained after fusion in a neo4j database, and then visually displaying the constructed case knowledge map. The construction of the 300 ten thousand plus 'motor vehicle traffic accident responsibility dispute' one-pass official document case knowledge graph is completed through the process.
Referring to fig. 2, the present invention provides an automatic construction system of case knowledge graph, which comprises:
the pre-defining unit is used for establishing an expert database and predefining entity relationships based on the expert database;
the model training unit is used for training the structured classification model of the referee document by adopting a Bert classification model; training an entity recognition model by adopting a model prototype of Bert + CRF; training a relation extraction model by adopting a model prototype as a relation extraction model based on Bert;
the case knowledge graph building unit is used for building a case knowledge graph and comprises the following steps:
classifying the content of the referee document based on the trained structured classification model of the referee document, and extracting the basic fact and the basic fact of the case; carrying out entity recognition on the case basic facts based on the trained entity recognition model, and extracting various entities in the case basic facts; extracting the relationship between the entities by using a trained relationship extraction model based on the extracted entities and the obtained case basic facts to obtain a triple composed of entity relationships; and extracting the entities and attributes in the basic facts of the case, and carrying out knowledge fusion on the obtained entities and attributes and the triples to obtain a complete case knowledge map.
The invention provides a case knowledge graph automatic construction device by an embodiment, which comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as: and (5) automatically constructing a case knowledge graph. The processor, when executing the computer program, implements the steps in each of the above embodiments of the method for automatically constructing a case knowledge graph, for example, the steps of the method for automatically constructing a case knowledge graph shown in fig. 1. Or the processor implements the functions of the units of the system when executing the computer program, for example: the function of each unit in the system for automatically constructing the case knowledge graph.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory and executed by the processor to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the device for automatically constructing the case knowledge graph. For example, the computer program may be segmented into a predefined unit, a model training unit, a case knowledge graph construction unit.
The device for automatically constructing the case knowledge graph can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The device for automatically constructing the case knowledge map can comprise, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram 3 is merely an example of an apparatus for automatically constructing a case knowledge graph, and does not constitute a limitation on the apparatus for automatically constructing a case knowledge graph, and may include more or less components than those shown, or combine some components, or different components, for example, the apparatus for automatically constructing a case knowledge graph may further include an input/output device, a network access device, a bus, etc.
The processor may be a Central Processing Unit (CPU), other general purpose processor, a digital signal processor (digital signal processor), an application specific Integrated Circuit (application specific Integrated Circuit), a field programmable gate array (field programmable gate array) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc. The general processor can be a microprocessor or the processor can be any conventional processor and the like, the processor is a control center of the device for automatically constructing the case knowledge graph, and various interfaces and lines are utilized to connect various parts of the device for automatically constructing the case knowledge graph.
The memory may be used for storing the computer program and/or the module, and the processor may implement various functions of the apparatus for automatically constructing a case knowledge graph by operating or executing data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function (such as a sound playing function, an image playing function, etc.), and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, at least one magnetic disk storage device, a flash memory device, or other volatile solid state storage device.
The apparatus for automatically constructing a case knowledge map may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, all or part of the flow in the method of implementing the embodiments of the present invention may also be stored in a computer readable storage medium through a computer program, and when the computer program is executed by a processor, the computer program may implement the steps of the above-described method embodiments. Wherein the computer program comprises computer program code, an object code form, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying said computer program code, a recording medium, a usb-disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, a point carrier signal, a telecommunications signal, a software distribution medium, etc. It should be noted that the computer readable medium may contain content that is appropriately increased or decreased as required by legislation and patent practice in the jurisdiction. For example, in certain jurisdictions, in accordance with legislation and patent practice, the computer-readable medium does not include point carrier signals and telecommunications signals.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for automatically constructing a case knowledge graph is characterized by comprising the following steps:
step A: establishing an expert database, and predefining entity relationships based on the expert database, wherein the entities are topics related by law, the relationships are associations among the entities, and the predefined entity relationships are used for entity identification, relationship extraction and triple construction;
and B: training a structured classification model of the referee document by adopting a Bert classification model; training an entity recognition model by adopting a model prototype Bert + CRF; training a relation extraction model by adopting a model prototype based on a Bert relation extraction model;
and C: constructing a case knowledge graph, comprising the following steps:
step C1: classifying the content of the referee document based on the trained structured classification model of the referee document, and extracting the basic fact and the basic fact of the case;
step C2: carrying out entity recognition on the case basic facts based on the trained entity recognition model, and extracting various entities in the case basic facts;
step C3: based on the entities extracted in step C2 and the case basic facts obtained in step C1, the trained relationship extraction model is used to extract the relationships between the entities to obtain entity relationship triples, where the basic form of the triples is: entity 1, the relationship between entity 1 and entity 2, entity 2;
step C4: and C, extracting the entities and attributes of the basic facts obtained in the step C1, and carrying out knowledge fusion on the obtained entities and attributes and the triples obtained in the step C3 to obtain a complete case situation knowledge graph.
2. The method for automatically constructing case knowledge graph according to claim 1, wherein the expert database comprises a plurality of legal professional experts, and the experts specifically analyze and summarize judicial practices according to the case and then define entity relationships in advance.
3. The method for automatically constructing a case knowledge graph according to claim 1, wherein basic facts are court affirmation fact parts of official documents; the basic fact is the case basic information part of the official document, including: basic information of the defendant and the original defendant.
4. The method for automatically constructing a case knowledge graph according to claim 1, wherein the step C3 further comprises: and fusing the obtained triples by adopting an entity alignment and entity link method.
5. The method for automatically constructing a case knowledge graph according to claim 1, wherein the step C further comprises:
step C5: storing the acquired case knowledge map by using a map database;
step C6: and visually displaying the case knowledge map.
6. The method according to claim 1, wherein the method uses CRF to improve the coding layer of the entity recognition reference model to obtain a Bert + CRF model, i.e. an entity recognition model.
7. The method for automatically constructing a case knowledge graph according to claim 1, wherein the relationship extraction model in the method is a translation-embedded multitask combined semantic relationship extraction model Bert.
8. An automatic case knowledge graph construction system, characterized in that the system comprises:
the system comprises a predefining unit, a relation extracting unit and a matching unit, wherein the predefining unit is used for establishing an expert database and predefining entity relations based on the expert database, the entities are subjects related by law, the relations are relations among the entities, and the predefined entity relations are used for entity identification, relation extraction and triple construction;
the model training unit is used for training the structured classification model of the referee document by adopting the Bert classification model; training an entity recognition model by adopting a model prototype Bert + CRF; training a relation extraction model by adopting a model prototype based on a Bert relation extraction model;
the case knowledge graph building unit is used for building a case knowledge graph and comprises the following steps:
classifying the content of the referee document based on the trained structured classification model of the referee document, and extracting the basic fact and the basic fact of the case; carrying out entity recognition on the case basic facts based on the trained entity recognition model, and extracting various entities in the case basic facts; based on the extracted entities and the obtained case basic facts, the trained relation extraction model is used for extracting the relation between the entities to obtain entity relation triples, and the basic form of the triples is as follows: entity 1, the relationship between entity 1 and entity 2, entity 2; and extracting the entity and the attribute of the case basic fact, and carrying out knowledge fusion on the obtained entity and attribute and the triples to obtain a complete case knowledge map.
9. An automatic case knowledge graph construction device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001253.6A CN110781254A (en) | 2020-01-02 | 2020-01-02 | Automatic case knowledge graph construction method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001253.6A CN110781254A (en) | 2020-01-02 | 2020-01-02 | Automatic case knowledge graph construction method, system, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110781254A true CN110781254A (en) | 2020-02-11 |
Family
ID=69394824
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010001253.6A Pending CN110781254A (en) | 2020-01-02 | 2020-01-02 | Automatic case knowledge graph construction method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110781254A (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111444353A (en) * | 2020-04-03 | 2020-07-24 | 杭州叙简科技股份有限公司 | Construction and use method of warning situation knowledge graph |
| CN111476034A (en) * | 2020-04-07 | 2020-07-31 | 同方赛威讯信息技术有限公司 | Legal document information extraction method and system based on combination of rules and models |
| CN111496784A (en) * | 2020-03-27 | 2020-08-07 | 山东大学 | Space environment identification method and system for robot intelligent service |
| CN111581376A (en) * | 2020-04-17 | 2020-08-25 | 中国船舶重工集团公司第七一四研究所 | Automatic knowledge graph construction system and method |
| CN111599479A (en) * | 2020-04-02 | 2020-08-28 | 云知声智能科技股份有限公司 | ICD 9-CM-3-based surgical knowledge map construction method and device |
| CN111613341A (en) * | 2020-05-22 | 2020-09-01 | 云知声智能科技股份有限公司 | Entity linking method and device based on semantic components |
| CN111737471A (en) * | 2020-06-28 | 2020-10-02 | 中国农业科学院农业信息研究所 | Archive management model construction method and system based on knowledge graph |
| CN111753099A (en) * | 2020-06-28 | 2020-10-09 | 中国农业科学院农业信息研究所 | Method and system for enhancing file entity association degree based on knowledge graph |
| CN111813906A (en) * | 2020-06-18 | 2020-10-23 | 贵州大学 | Similar case calculation method based on criminal behavior chain |
| CN111832295A (en) * | 2020-07-08 | 2020-10-27 | 昆明理工大学 | Criminal case element identification method based on BERT pre-training model |
| CN111859922A (en) * | 2020-07-31 | 2020-10-30 | 上海银行股份有限公司 | Application method of entity relation extraction technology in bank wind control |
| CN112559766A (en) * | 2020-12-08 | 2021-03-26 | 杭州互仲网络科技有限公司 | Legal knowledge map construction system |
| CN112632223A (en) * | 2020-12-29 | 2021-04-09 | 天津汇智星源信息技术有限公司 | Case and event knowledge graph construction method and related equipment |
| CN112699248A (en) * | 2020-12-24 | 2021-04-23 | 厦门市美亚柏科信息股份有限公司 | Knowledge ontology construction method, terminal equipment and storage medium |
| CN112733874A (en) * | 2020-10-23 | 2021-04-30 | 招商局重庆交通科研设计院有限公司 | Suspicious vehicle discrimination method based on knowledge graph reasoning |
| CN112836501A (en) * | 2021-01-18 | 2021-05-25 | 同方知网(北京)技术有限公司 | Automatic knowledge element extraction method based on Bert + BiLSTM + CRF |
| CN113011185A (en) * | 2020-07-17 | 2021-06-22 | 上海浦东华宇信息技术有限公司 | Legal field text analysis and identification method, system, storage medium and terminal |
| CN113010684A (en) * | 2020-12-31 | 2021-06-22 | 北京法意科技有限公司 | Construction method and system of civil complaint and judgment map |
| CN113918682A (en) * | 2021-10-19 | 2022-01-11 | 四川大学 | Knowledge extraction method of case-related property knowledge base |
| CN114169429A (en) * | 2021-12-03 | 2022-03-11 | 湘潭大学 | Case similarity calculation method and system based on graph convolution |
| CN114647734A (en) * | 2020-12-18 | 2022-06-21 | 同方威视科技江苏有限公司 | Method and device for generating event map of public opinion text, electronic equipment and medium |
| CN115269931A (en) * | 2022-09-28 | 2022-11-01 | 深圳技术大学 | Rail transit station data map system based on service drive and construction method thereof |
| WO2022237013A1 (en) * | 2021-05-11 | 2022-11-17 | 西安交通大学 | Entity relationship joint extraction-based legal knowledge graph construction method and device |
| CN115730078A (en) * | 2022-11-04 | 2023-03-03 | 南京擎盾信息科技有限公司 | Event knowledge graph construction method and device for class case retrieval and electronic equipment |
| CN116662559A (en) * | 2023-02-15 | 2023-08-29 | 北京北明数科信息技术有限公司 | Case knowledge graph construction platform and method based on big data technology |
| CN117609440A (en) * | 2023-10-27 | 2024-02-27 | 中国司法大数据研究院有限公司 | Document-level intelligent question-answering implementation method for referee document |
| CN118012983A (en) * | 2024-02-05 | 2024-05-10 | 北京智谱华章科技有限公司 | Automatic knowledge extraction method, equipment and storage medium based on large model |
| CN118172206A (en) * | 2024-01-24 | 2024-06-11 | 杭州太振科技有限公司 | Method and system for simulating and predicting judgment result of case of personnel dispute |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522416A (en) * | 2018-10-19 | 2019-03-26 | 广东工业大学 | A kind of construction method of Financial Risk Control knowledge mapping |
| CN110083831A (en) * | 2019-04-16 | 2019-08-02 | 武汉大学 | A kind of Chinese name entity recognition method based on BERT-BiGRU-CRF |
| CN110188346A (en) * | 2019-04-29 | 2019-08-30 | 浙江工业大学 | A kind of network security bill part intelligence analysis method based on information extraction |
| CN110287334A (en) * | 2019-06-13 | 2019-09-27 | 淮阴工学院 | A kind of school's domain knowledge map construction method based on Entity recognition and attribute extraction model |
| CN110309393A (en) * | 2019-03-28 | 2019-10-08 | 平安科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium storing program for executing |
| CN110442676A (en) * | 2019-07-02 | 2019-11-12 | 北京邮电大学 | Patent retrieval method and device based on more wheel dialogues |
| CN110489750A (en) * | 2019-08-12 | 2019-11-22 | 昆明理工大学 | Burmese participle and part-of-speech tagging method and device based on two-way LSTM-CRF |
| CN110516256A (en) * | 2019-08-30 | 2019-11-29 | 的卢技术有限公司 | A kind of Chinese name entity extraction method and its system |
| CN110597999A (en) * | 2019-08-01 | 2019-12-20 | 湖北工业大学 | Judicial case knowledge graph construction method of dependency syntactic analysis relation extraction model |
| CN110633458A (en) * | 2018-06-25 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Method and device for generating referee document |
-
2020
- 2020-01-02 CN CN202010001253.6A patent/CN110781254A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633458A (en) * | 2018-06-25 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Method and device for generating referee document |
| CN109522416A (en) * | 2018-10-19 | 2019-03-26 | 广东工业大学 | A kind of construction method of Financial Risk Control knowledge mapping |
| CN110309393A (en) * | 2019-03-28 | 2019-10-08 | 平安科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium storing program for executing |
| CN110083831A (en) * | 2019-04-16 | 2019-08-02 | 武汉大学 | A kind of Chinese name entity recognition method based on BERT-BiGRU-CRF |
| CN110188346A (en) * | 2019-04-29 | 2019-08-30 | 浙江工业大学 | A kind of network security bill part intelligence analysis method based on information extraction |
| CN110287334A (en) * | 2019-06-13 | 2019-09-27 | 淮阴工学院 | A kind of school's domain knowledge map construction method based on Entity recognition and attribute extraction model |
| CN110442676A (en) * | 2019-07-02 | 2019-11-12 | 北京邮电大学 | Patent retrieval method and device based on more wheel dialogues |
| CN110597999A (en) * | 2019-08-01 | 2019-12-20 | 湖北工业大学 | Judicial case knowledge graph construction method of dependency syntactic analysis relation extraction model |
| CN110489750A (en) * | 2019-08-12 | 2019-11-22 | 昆明理工大学 | Burmese participle and part-of-speech tagging method and device based on two-way LSTM-CRF |
| CN110516256A (en) * | 2019-08-30 | 2019-11-29 | 的卢技术有限公司 | A kind of Chinese name entity extraction method and its system |
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111496784A (en) * | 2020-03-27 | 2020-08-07 | 山东大学 | Space environment identification method and system for robot intelligent service |
| CN111599479B (en) * | 2020-04-02 | 2023-08-11 | 云知声智能科技股份有限公司 | ICD 9-CM-3-based surgical knowledge graph construction method and device |
| CN111599479A (en) * | 2020-04-02 | 2020-08-28 | 云知声智能科技股份有限公司 | ICD 9-CM-3-based surgical knowledge map construction method and device |
| CN111444353B (en) * | 2020-04-03 | 2023-02-28 | 杭州叙简科技股份有限公司 | Construction and use method of warning situation knowledge graph |
| CN111444353A (en) * | 2020-04-03 | 2020-07-24 | 杭州叙简科技股份有限公司 | Construction and use method of warning situation knowledge graph |
| CN111476034A (en) * | 2020-04-07 | 2020-07-31 | 同方赛威讯信息技术有限公司 | Legal document information extraction method and system based on combination of rules and models |
| CN111476034B (en) * | 2020-04-07 | 2023-05-12 | 同方赛威讯信息技术有限公司 | Legal document information extraction method and system based on combination of rules and models |
| CN111581376B (en) * | 2020-04-17 | 2024-04-19 | 中国船舶重工集团公司第七一四研究所 | Automatic knowledge graph construction system and method |
| CN111581376A (en) * | 2020-04-17 | 2020-08-25 | 中国船舶重工集团公司第七一四研究所 | Automatic knowledge graph construction system and method |
| CN111613341B (en) * | 2020-05-22 | 2024-02-02 | 云知声智能科技股份有限公司 | Entity linking method and device based on semantic components |
| CN111613341A (en) * | 2020-05-22 | 2020-09-01 | 云知声智能科技股份有限公司 | Entity linking method and device based on semantic components |
| CN111813906A (en) * | 2020-06-18 | 2020-10-23 | 贵州大学 | Similar case calculation method based on criminal behavior chain |
| CN111753099A (en) * | 2020-06-28 | 2020-10-09 | 中国农业科学院农业信息研究所 | Method and system for enhancing file entity association degree based on knowledge graph |
| CN111737471A (en) * | 2020-06-28 | 2020-10-02 | 中国农业科学院农业信息研究所 | Archive management model construction method and system based on knowledge graph |
| CN111737471B (en) * | 2020-06-28 | 2023-10-13 | 中国农业科学院农业信息研究所 | File management model construction method and system based on knowledge graph |
| CN111753099B (en) * | 2020-06-28 | 2023-11-21 | 中国农业科学院农业信息研究所 | Method and system for enhancing relevance of archive entity based on knowledge graph |
| CN111832295A (en) * | 2020-07-08 | 2020-10-27 | 昆明理工大学 | Criminal case element identification method based on BERT pre-training model |
| CN113011185A (en) * | 2020-07-17 | 2021-06-22 | 上海浦东华宇信息技术有限公司 | Legal field text analysis and identification method, system, storage medium and terminal |
| CN111859922A (en) * | 2020-07-31 | 2020-10-30 | 上海银行股份有限公司 | Application method of entity relation extraction technology in bank wind control |
| CN111859922B (en) * | 2020-07-31 | 2023-12-01 | 上海银行股份有限公司 | Application method of entity relation extraction technology in bank wind control |
| CN112733874A (en) * | 2020-10-23 | 2021-04-30 | 招商局重庆交通科研设计院有限公司 | Suspicious vehicle discrimination method based on knowledge graph reasoning |
| CN112559766A (en) * | 2020-12-08 | 2021-03-26 | 杭州互仲网络科技有限公司 | Legal knowledge map construction system |
| CN112559766B (en) * | 2020-12-08 | 2022-08-26 | 杭州互仲网络科技有限公司 | Legal knowledge map construction system |
| CN114647734A (en) * | 2020-12-18 | 2022-06-21 | 同方威视科技江苏有限公司 | Method and device for generating event map of public opinion text, electronic equipment and medium |
| CN112699248B (en) * | 2020-12-24 | 2022-09-16 | 厦门市美亚柏科信息股份有限公司 | Knowledge ontology construction method, terminal equipment and storage medium |
| CN112699248A (en) * | 2020-12-24 | 2021-04-23 | 厦门市美亚柏科信息股份有限公司 | Knowledge ontology construction method, terminal equipment and storage medium |
| CN112632223A (en) * | 2020-12-29 | 2021-04-09 | 天津汇智星源信息技术有限公司 | Case and event knowledge graph construction method and related equipment |
| CN112632223B (en) * | 2020-12-29 | 2023-01-20 | 天津汇智星源信息技术有限公司 | Case and event knowledge graph construction method and related equipment |
| CN113010684B (en) * | 2020-12-31 | 2024-02-09 | 北京法意科技有限公司 | Construction method and system of civil complaint judging map |
| CN113010684A (en) * | 2020-12-31 | 2021-06-22 | 北京法意科技有限公司 | Construction method and system of civil complaint and judgment map |
| CN112836501A (en) * | 2021-01-18 | 2021-05-25 | 同方知网(北京)技术有限公司 | Automatic knowledge element extraction method based on Bert + BiLSTM + CRF |
| WO2022237013A1 (en) * | 2021-05-11 | 2022-11-17 | 西安交通大学 | Entity relationship joint extraction-based legal knowledge graph construction method and device |
| CN113918682A (en) * | 2021-10-19 | 2022-01-11 | 四川大学 | Knowledge extraction method of case-related property knowledge base |
| CN114169429A (en) * | 2021-12-03 | 2022-03-11 | 湘潭大学 | Case similarity calculation method and system based on graph convolution |
| CN114169429B (en) * | 2021-12-03 | 2024-10-15 | 湘潭大学 | Case similarity calculation method and system based on graph convolution |
| CN115269931B (en) * | 2022-09-28 | 2022-11-29 | 深圳技术大学 | Rail transit station data map system based on service drive and construction method thereof |
| CN115269931A (en) * | 2022-09-28 | 2022-11-01 | 深圳技术大学 | Rail transit station data map system based on service drive and construction method thereof |
| CN115730078A (en) * | 2022-11-04 | 2023-03-03 | 南京擎盾信息科技有限公司 | Event knowledge graph construction method and device for class case retrieval and electronic equipment |
| CN116662559A (en) * | 2023-02-15 | 2023-08-29 | 北京北明数科信息技术有限公司 | Case knowledge graph construction platform and method based on big data technology |
| CN117609440A (en) * | 2023-10-27 | 2024-02-27 | 中国司法大数据研究院有限公司 | Document-level intelligent question-answering implementation method for referee document |
| CN118172206A (en) * | 2024-01-24 | 2024-06-11 | 杭州太振科技有限公司 | Method and system for simulating and predicting judgment result of case of personnel dispute |
| CN118172206B (en) * | 2024-01-24 | 2024-09-13 | 杭州太振科技有限公司 | Method and system for simulating and predicting judgment result of case of personnel dispute |
| CN118012983A (en) * | 2024-02-05 | 2024-05-10 | 北京智谱华章科技有限公司 | Automatic knowledge extraction method, equipment and storage medium based on large model |
| CN118012983B (en) * | 2024-02-05 | 2024-08-23 | 北京智谱华章科技有限公司 | Automatic knowledge extraction method, equipment and storage medium based on large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110781254A (en) | Automatic case knowledge graph construction method, system, equipment and medium | |
| CN108595583B (en) | Dynamic graph page data crawling method, device, terminal and storage medium | |
| CN106874279B (en) | Method and device for generating application category label | |
| CN109189959B (en) | Method and device for constructing image database | |
| CN111275107A (en) | Multi-label scene image classification method and device based on transfer learning | |
| CN109684476B (en) | Text classification method, text classification device and terminal equipment | |
| CN101877064B (en) | Image classification method and image classification device | |
| US10108661B2 (en) | Using synthetic events to identify complex relation lookups | |
| CN111309910A (en) | Text information mining method and device | |
| CN111563192A (en) | Entity alignment method and device, electronic equipment and storage medium | |
| CN112348417A (en) | Marketing value evaluation method and device based on principal component analysis algorithm | |
| CN114372532A (en) | Method, device, equipment, medium and product for determining label marking quality | |
| US20170193333A1 (en) | Analyzing and exploring images posted on social media | |
| CN110263345B (en) | Keyword extraction method, keyword extraction device and storage medium | |
| US10229156B2 (en) | Using priority scores for iterative precision reduction in structured lookups for questions | |
| CN111611781B (en) | Data labeling method, question answering device and electronic equipment | |
| CN114186072B (en) | Traffic accident report extraction and scene type reasoning method, system and storage medium | |
| CN116010545A (en) | Data processing method, device and equipment | |
| CN113610080B (en) | Cross-modal perception-based sensitive image identification method, device, equipment and medium | |
| Xu et al. | The semantic analysis of knowledge map for the traffic violations from the surveillance video big data. | |
| CN113724817A (en) | Knowledge recommendation method and device based on artificial intelligence, computer equipment and medium | |
| CN114170476A (en) | Image retrieval model training method and device, electronic equipment and storage medium | |
| CN114490929A (en) | Bidding information acquisition method and device, storage medium and terminal equipment | |
| Chang et al. | Code Transform Model Producing High-Performance Program. | |
| CN112579841B (en) | Multi-mode database establishment method, retrieval method and system |
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 |
Application publication date: 20200211 |
|
| RJ01 | Rejection of invention patent application after publication |