CN108241621B - legal knowledge retrieval method and device - Google Patents
legal knowledge retrieval method and device Download PDFInfo
- Publication number
- CN108241621B CN108241621B CN201611204508.9A CN201611204508A CN108241621B CN 108241621 B CN108241621 B CN 108241621B CN 201611204508 A CN201611204508 A CN 201611204508A CN 108241621 B CN108241621 B CN 108241621B
- Authority
- CN
- China
- Prior art keywords
- dispute focus
- dispute
- text
- focus
- legal knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a legal knowledge retrieval method and device, relates to the technical field of data processing, and solves the problems of low retrieval efficiency and low applicability of the conventional legal knowledge. The main technical scheme of the invention is as follows: training a dispute focus data model according to text data corresponding to each dispute focus in the existing case document; the text data is used for explaining the corresponding dispute focus in the existing case document; when receiving an instruction of acquiring legal knowledge points of a target case document, identifying a dispute focus in the target case document through the dispute focus data model; and outputting the legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points. The method is mainly used for retrieving legal knowledge corresponding to the target case document.
Description
Technical Field
the invention relates to the technical field of data processing, in particular to a legal knowledge retrieval method and device.
background
the case document refers to a special document formed and used by law-enforcement agencies such as investigation, inspection, trial and judgment, notarization and the like in each link and step of processing various cases. Mainly includes documents with legal effectiveness, such as judgment books, adjudication books, etc.; documents which do not directly take place in legal effectiveness but have a practical guarantee of law enforcement, such as prosecution, response books, court trial notes and the like, are also included. The legal officer, the lawyer, the party and other personnel closely related to the case help the related personnel to better analyze the case condition by retrieving legal knowledge related to the judicial literature.
at present, the target case is analyzed by the personnel closely related to the case, such as a judge, a lawyer, a party and the like, the law and the fact focus in the target case are summarized by the French language, and then the legal knowledge related to the fact focus is searched by the keyword search technology, but the legal knowledge searched by adopting the method requires that the relevant personnel can accurately summarize the law and the fact focus in the target case, namely, the requirement on the user is too high, and in addition, the conclusion of the law and the fact focus in the target case requires extra manual time, so that the efficiency and the applicability of the conventional legal knowledge search are low.
disclosure of Invention
the present invention has been made in view of the above problems, and aims to provide a legal knowledge retrieval method and apparatus that overcomes or at least partially solves the above problems.
in order to achieve the purpose, the invention mainly provides the following technical scheme:
In one aspect, an embodiment of the present invention provides a legal knowledge retrieval method, including:
Training a dispute focus data model according to text data corresponding to each dispute focus in the existing case document; the text data is used for explaining the corresponding dispute focus in the existing case document;
when receiving an instruction of acquiring legal knowledge points of a target case document, identifying a dispute focus in the target case document through the dispute focus data model;
And outputting the legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points.
on the other hand, the embodiment of the invention also provides a legal knowledge retrieval device, which comprises:
The training unit is used for training a dispute focus data model according to the text data corresponding to each dispute focus in the existing case document; the text data is used for explaining the corresponding dispute focus in the existing case document;
The identification unit is used for identifying a dispute focus in the target case document through the dispute focus data model when receiving a legal knowledge point instruction for acquiring the target case document;
And the output unit is used for outputting the legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points.
by the technical scheme, the technical scheme provided by the embodiment of the invention at least has the following advantages:
the embodiment of the invention provides a legal knowledge retrieval method and a legal knowledge retrieval device, wherein a dispute focus data model is trained according to text data corresponding to each dispute focus in the existing case document; when an instruction for acquiring legal knowledge points of a target case document is received, identifying dispute focus in the target case document through the dispute focus data model, and outputting legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points. Compared with the prior art that the legal knowledge related to the target case is retrieved by manually summarizing the dispute focus in the target case, the embodiment of the invention can directly identify the dispute focus contained in the target case document according to the focus data model and output the legal knowledge point corresponding to the dispute focus according to the identified dispute focus, so that the legal knowledge point corresponding to the target case document can be rapidly retrieved by the embodiment of the invention without manually summarizing the dispute focus of the target case, and the retrieval efficiency and retrieval applicability of the legal knowledge can be improved by the embodiment of the invention.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flowchart of a legal knowledge retrieval method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another legal knowledge retrieval method provided by an embodiment of the present invention;
FIG. 3 is a block diagram of a legal knowledge retrieval apparatus according to an embodiment of the present invention;
fig. 4 is a block diagram of another legal knowledge retrieval apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In order to make the advantages of the technical solutions of the present invention clearer, the present invention is described in detail below with reference to the accompanying drawings and examples.
The embodiment of the invention provides a legal knowledge retrieval method, as shown in fig. 1, the method comprises the following steps:
101. And training a dispute focus data model according to the text data corresponding to each dispute focus in the existing case document.
Wherein the text data is used for explaining a corresponding dispute focus in the existing case document; the existing case documents can be litigation documents, answer documents, court trial notes, referee documents and the like, and the embodiment of the invention is not limited in detail. For the embodiment of the invention, the focus data model is obtained by training a large number of existing case documents, namely, the focus data model is obtained according to the dispute focus corresponding to the training of the existing case documents and the text statement and/or description statement corresponding to the dispute focus.
It should be noted that the focus of disputes is summarized by legal experts based on the analysis of existing case documents, i.e. the focus of disputes is summarized from different legal points of view. For example disputes over trademark infringement: it may be necessary to consider from the trademark law how to infringe trademark exclusive rights; it is also possible to consider from a contractual law perspective how contract agreements are violated in trademark authorization usage contracts; it may also be a dispute for reimbursement after a trademark infringement. If there are multiple angles of disputes in a case document, it is necessary to summarize these disputes.
In the embodiment of the invention, after combing the dispute focus of the existing case document, the legal expert needs to extract the text sentence corresponding to the dispute focus in the existing case document and write the text sentence describing the dispute focus according to the specification. And finally, forming a data set by the descriptive statement of the dispute focus and the excerpted text statement, wherein the data set is a dispute focus data set, and generating a focus data model by a machine learning method for the dispute focus data set. And identifying the dispute focus contained in the target case document through the generated dispute focus data model.
102. And when receiving an instruction of acquiring the legal knowledge point of the target case document, identifying the dispute focus in the target case document through the dispute focus data model.
the existing case document is a document to be retrieved corresponding to legal knowledge, namely a document needing to recommend the corresponding legal knowledge. For the embodiment of the invention, because the dispute focus data model is obtained by training the dispute focus data set, when the legal knowledge point instruction for obtaining the target case document is received, the target case document is put into the focus data model, and then the dispute focus contained in the target case document is identified by utilizing the natural semantic analysis technology.
103. and outputting the legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points.
in the embodiment of the invention, the legal knowledge structural system constructed from judicial practices firstly considers that the legal rules corresponding to a dispute focus are summarized into a legal knowledge point, and the legal knowledge point is the result of the convergence of a plurality of legal provisions of a plurality of legal rules, thereby reflecting the actual situation of applicable laws. And the legal knowledge points are connected into the whole legal and legal system through legal concepts and rules.
each of the dispute foci requires a point of knowledge in judicial practice to help judges, lawyers and others understand legal concepts, judicial interpretations, practice cases, academic opinions, etc. Therefore, the legal knowledge points corresponding to the dispute focus are the result of the convergence of a plurality of legal provisions of a plurality of legal rules, which reflects the actual situation of applicable laws, and are connected to the whole legal rule system through legal concepts and rules. The legal knowledge points may be legal concepts, judicial interpretations, practice cases, academic viewpoints, provisions of laws and regulations, judicial interpretation provisions, legal book articles, case documents and the like, and the embodiment of the present invention is not particularly limited.
It should be noted that the legal knowledge point is connected with a set of legal provisions, including judicial interpretation provisions, legal book articles, case documents, etc.; and (3) resolving the referee rule of dispute focus of a case at each legal knowledge point. All legal knowledge points are organized in order to form a judicial knowledge case document library, the judicial knowledge case document library is a knowledge system organized by the legal knowledge points required in judicial practice, and the knowledge system is formed by mixing specific contents of a plurality of related laws, so that the legality of the legal knowledge points is reflected.
The legal knowledge retrieval method provided by the embodiment of the invention trains a dispute focus data model according to the text data corresponding to each dispute focus in the existing case document; when an instruction for acquiring legal knowledge points of a target case document is received, identifying dispute focus in the target case document through the dispute focus data model, and outputting legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points. Compared with the prior art that the legal knowledge related to the target case is retrieved by manually summarizing the dispute focus in the target case, the embodiment of the invention can directly identify the dispute focus contained in the target case document according to the focus data model and output the legal knowledge point corresponding to the dispute focus according to the identified dispute focus, so that the legal knowledge point corresponding to the target case document can be rapidly retrieved by the embodiment of the invention without manually summarizing the dispute focus of the target case, and the retrieval efficiency and retrieval applicability of the legal knowledge can be improved by the embodiment of the invention.
the embodiment of the invention provides another legal knowledge retrieval method, as shown in fig. 2, the method comprises the following steps:
201. and intercepting text sentences respectively corresponding to the dispute focuses from the existing case documents.
in the embodiment of the invention, the dispute focus is summarized by legal experts according to the analysis of the existing case documents, namely, the dispute focus is summarized from different aspects of law. If there are multiple angles of disputes in a case document, it is necessary to summarize these disputes. Each of the dispute foci requires a point of knowledge in judicial practice to help judges, lawyers and others understand legal concepts, judicial interpretations, practice cases, academic opinions, etc.
And (3) abstracting the text sentence expressing a specific dispute focus in each existing case document by legal experts, namely abstracting the text sentence directly corresponding to the legal knowledge point, and recording the position of the abstracted text sentence in the existing case document. The extracted text sentence can be the paragraph contents of the original complaint requirement, the response content, the court trial debate content, the home opinion and the like in the existing case document, and the embodiment of the invention is not particularly limited.
202. And setting description sentences corresponding to the dispute focuses respectively according to the existing case documents.
the legal expert writes a text sentence describing the dispute focus according to the specification, and generates a new document knowledge point describing the dispute focus in the target case document, wherein the document knowledge point has a fixed format and is full and detailed in content. The processed dispute focus descriptive statement and the text statement extracted in step 201 together form a data set, which becomes a dispute focus data set. A dispute focus data model may be derived by training a focus data set.
203. And training a dispute focus data model according to the text statement and the description statement corresponding to the dispute focus.
For the embodiment of the present invention, the training of the dispute focus data model according to the text sentence and the description sentence corresponding to the dispute focus includes: acquiring text sentences and description sentences which comprise the same dispute focus and correspond to the existing case documents; performing semantic analysis on the acquired text sentences and description sentences to generate fact attribute vectors corresponding to the dispute focus; and generating the dispute focus data model according to the corresponding relation between the dispute focus and the fact attribute vector.
And the computer performs semantic analysis on the dispute focus data set to form a multi-dimensional data vector of legal knowledge and factual attributes. Then generating a dispute focus data model by a machine learning method for the dispute focus data set, analyzing all existing case documents by using the dispute focus model, and finding out the document matched with the dispute focus; and extracting a dispute focus text sentence from the partial matching document, processing a dispute focus description sentence by legal experts, and combining the dispute focus description sentence with the first dispute focus data set to form a dispute focus data model by machine learning. Repeating the above steps for a plurality of times, and the final version of the focus data model becomes the dispute focus data model of the legal knowledge point.
204. And when receiving an instruction of acquiring the legal knowledge point of the target case document, identifying the dispute focus in the target case document through the dispute focus data model.
for the embodiment of the present invention, identifying the dispute focus in the target case document through the dispute focus data model includes: generating a text vector corresponding to the target case document; acquiring a fact attribute vector with the highest similarity to the text vector; and determining the dispute focus corresponding to the acquired fact attribute vector as the dispute focus of the target case document.
In the embodiment of the invention, a multidimensional data vector of legal knowledge points and factual attributes is formed by performing semantic analysis on the dispute focus data set, and a dispute focus data model of the legal knowledge points is generated by a machine learning related algorithm. And then continuously acquiring a new dispute focus data set by using an iterative method, and learning a new dispute focus data model. The computer analyzes the target case document by using the focus data model, can acquire the dispute focus in the target case document, and recommends the corresponding legal knowledge point according to the acquired dispute focus. Therefore, the retrieval efficiency of legal knowledge is improved through the embodiment of the invention.
205. And outputting the legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points.
The dispute focus and the legal knowledge points are the result of the convergence of a plurality of legal provisions of a plurality of laws and regulations, the actual situation of applicable laws is reflected, and meanwhile, the legal knowledge points are connected to the whole law and regulation system through legal concepts and rules.
Further, the method further comprises: and marking a text sentence containing the dispute focus in the target case document. In the embodiment of the invention, the accurate legal knowledge points can be intelligently pushed to the obtained target case document through the focus data model, and the statement corresponding to the dispute focus in the target case document is marked. The computer analyzes the target case document by using the focus data model, and can identify the dispute focus contained in the target case document, thereby realizing the automatic retrieval and recommendation of legal and legal provisions, legal and academic books and periodicals, typical case documents, related case documents and the like corresponding to the legal knowledge points by the machine.
compared with the prior art that the legal knowledge related to the target case is retrieved by manually summarizing the dispute focus in the target case, the retrieval method of the legal knowledge provided by the embodiment of the invention can directly identify the dispute focus contained in the target case document according to the dispute focus data model, output the legal knowledge point corresponding to the dispute focus according to the identified dispute focus, and mark out the dispute focus sentences in the target case document without manually summarizing the dispute focus of the target case, so that the retrieval efficiency and retrieval applicability of the legal knowledge can be improved by the embodiment of the invention.
further, an embodiment of the present invention provides a legal knowledge retrieval apparatus, as shown in fig. 3, the apparatus includes: training section 31, recognition section 32, and output section 33.
The training unit 31 is used for training a dispute focus data model according to the text data corresponding to each dispute focus in the existing case document; the text data is used for explaining the corresponding dispute focus in the existing case document;
The identification unit 32 is used for identifying the dispute focus in the target case document through the dispute focus data model when receiving an instruction of acquiring the legal knowledge point of the target case document;
And the output unit 33 is configured to output the legal knowledge point corresponding to the dispute focus through the corresponding relationship between the dispute focus and the legal knowledge point.
it should be noted that, for other corresponding descriptions of the functional units related to the legal knowledge retrieval apparatus provided in the embodiment of the present invention, reference may be made to corresponding descriptions of the method shown in fig. 1, which are not described herein again, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the foregoing method embodiments.
the legal knowledge retrieval device provided by the embodiment of the invention trains a dispute focus data model according to the text data corresponding to each dispute focus in the existing case document; when an instruction for acquiring legal knowledge points of a target case document is received, identifying dispute focus in the target case document through the dispute focus data model, and outputting legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points. Compared with the prior art that the legal knowledge related to the target case is retrieved by manually summarizing the dispute focus in the target case, the embodiment of the invention can directly identify the dispute focus contained in the target case document according to the focus data model and output the legal knowledge point corresponding to the dispute focus according to the identified dispute focus, so that the legal knowledge point corresponding to the target case document can be rapidly retrieved by the embodiment of the invention without manually summarizing the dispute focus of the target case, and the retrieval efficiency and retrieval applicability of the legal knowledge can be improved by the embodiment of the invention.
further, another legal knowledge retrieval apparatus is provided in the embodiment of the present invention, as shown in fig. 4, the apparatus includes: training section 41, recognition section 42, and output section 43.
a training unit 41, configured to train a dispute focus data model according to text data corresponding to each dispute focus in an existing case document; the text data is used for explaining the corresponding dispute focus in the existing case document;
the identification unit 42 is used for identifying the dispute focus in the target case document through the dispute focus data model when receiving an instruction of acquiring the legal knowledge point of the target case document;
And the output unit 43 is configured to output the legal knowledge point corresponding to the dispute focus through the corresponding relationship between the dispute focus and the legal knowledge point. .
specifically, the training unit 41 includes:
an intercepting module 411, configured to intercept text statements corresponding to the dispute focuses from the existing case documents;
A setting module 412, configured to set description statements corresponding to the dispute focuses according to the existing case documents;
And the training module 413 is configured to train a dispute focus data model according to the text statement and the description statement corresponding to the dispute focus.
specifically, the training module 413 includes:
the obtaining submodule is used for obtaining text sentences and description sentences which contain the same dispute focus and correspond to the existing case documents;
The generation submodule is used for carrying out semantic analysis on the acquired text sentences and description sentences to generate fact attribute vectors corresponding to the dispute focus;
and the generation submodule is also used for generating the dispute focus data model according to the corresponding relation between the dispute focus and the fact attribute vector.
Specifically, the identification unit 42 includes:
a generating module 421, configured to generate a text vector corresponding to the target case document;
an obtaining module 422, configured to obtain a fact attribute vector with the highest similarity to the text vector;
The determining module 423 is configured to determine a dispute focus corresponding to the obtained fact attribute vector as a dispute focus of the target case document.
Further, the apparatus further comprises:
And the marking unit 44 is used for marking the text statement containing the dispute focus in the target case document.
It should be noted that, for other corresponding descriptions of the functional units related to the legal knowledge retrieval apparatus provided in the embodiment of the present invention, reference may be made to corresponding descriptions of the method shown in fig. 2, which are not described herein again, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the foregoing method embodiments.
compared with the prior art that the legal knowledge related to the target case is retrieved by manually summarizing the dispute focus in the target case, the retrieval device for the legal knowledge provided by the embodiment of the invention can directly identify the dispute focus contained in the target case document according to the dispute focus data model, output the legal knowledge point corresponding to the dispute focus according to the identified dispute focus, and mark out the dispute focus sentences in the target case document without manually summarizing the dispute focus of the target case, so that the retrieval efficiency and the retrieval applicability of the legal knowledge can be improved by the retrieval device for the legal knowledge.
The legal knowledge retrieval device comprises a processor and a memory, wherein the training unit, the identification unit, the output unit, the labeling unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
the processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the problem that the existing legal knowledge retrieval efficiency and applicability are low is solved by adjusting kernel parameters.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
The present application further provides a computer program product adapted to perform program code for initializing the following method steps when executed on a data processing device: training a dispute focus data model according to text data corresponding to each dispute focus in the existing case document; the text data is used for explaining the corresponding dispute focus in the existing case document; when receiving an instruction of acquiring legal knowledge points of a target case document, identifying a dispute focus in the target case document through the dispute focus data model; and outputting the legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points.
as will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
the present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (8)
1. a legal knowledge retrieval method, comprising:
training a dispute focus data model according to text data corresponding to each dispute focus in the existing case document; the text data is used for explaining a corresponding dispute focus in the existing case document, the dispute focus is obtained by a legal expert according to analysis of the existing case document summary, and the text data corresponding to the dispute focus is a text statement and/or a description statement corresponding to the dispute focus;
The training of the dispute focus data model according to the text sentences of the dispute focuses in the existing case documents comprises the following steps:
Intercepting text sentences corresponding to the dispute focuses from the existing case documents;
setting description sentences corresponding to the dispute focuses according to the existing case documents;
Training a dispute focus data model according to the text sentences and the description sentences corresponding to the dispute focuses;
The training of the dispute focus data model according to the text sentences and the description sentences corresponding to the dispute focuses comprises the following steps:
acquiring text sentences and description sentences which comprise the same dispute focus and correspond to the existing case documents;
Performing semantic analysis on the acquired text sentences and description sentences to generate fact attribute vectors corresponding to the dispute focus;
Generating a dispute focus data model according to the corresponding relation between the dispute focus and the fact attribute vector;
When receiving an instruction of acquiring legal knowledge points of a target case document, identifying a dispute focus in the target case document through the dispute focus data model;
And outputting the legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points.
2. The method of claim 1, wherein identifying the point of dispute focus in the target case document via the model of dispute focus data comprises:
Generating a text vector corresponding to the target case document;
Acquiring a fact attribute vector with the highest similarity to the text vector;
And determining the dispute focus corresponding to the acquired fact attribute vector as the dispute focus of the target case document.
3. the method according to claim 1 or 2, characterized in that the method further comprises:
and marking a text sentence containing the dispute focus in the target case document.
4. An apparatus for retrieving legal knowledge, comprising:
the training unit is used for training a dispute focus data model according to the text data corresponding to each dispute focus in the existing case document; the text data is used for explaining a corresponding dispute focus in the existing case document, the dispute focus is obtained by a legal expert according to analysis of the existing case document summary, and the text data corresponding to the dispute focus is a text statement and/or a description statement corresponding to the dispute focus;
The training unit includes:
The intercepting module is used for intercepting text sentences corresponding to the dispute focuses from the existing case documents;
The setting module is used for setting descriptive sentences corresponding to the dispute focuses respectively according to the existing case documents;
The training module is used for training a dispute focus data model according to the text sentences and the description sentences corresponding to the dispute focuses;
the training module comprises:
The obtaining submodule is used for obtaining text sentences and description sentences which contain the same dispute focus and correspond to the existing case documents;
the generation submodule is used for carrying out semantic analysis on the acquired text sentences and description sentences to generate fact attribute vectors corresponding to the dispute focus;
The generation submodule is further used for generating the dispute focus data model according to the corresponding relation between the dispute focus and the fact attribute vector;
The identification unit is used for identifying a dispute focus in the target case document through the dispute focus data model when receiving a legal knowledge point instruction for acquiring the target case document;
And the output unit is used for outputting the legal knowledge points corresponding to the dispute focus through the corresponding relation between the dispute focus and the legal knowledge points.
5. The apparatus of claim 4, wherein the identification unit comprises:
The generating module is used for generating a text vector corresponding to the target case document;
The obtaining module is used for obtaining a fact attribute vector with the highest similarity to the text vector;
And the determining module is used for determining the dispute focus corresponding to the acquired fact attribute vector as the dispute focus of the target case document.
6. The apparatus of claim 4 or 5, further comprising:
and the marking unit is used for marking the text statement containing the dispute focus in the target case document.
7. A storage medium, characterized in that the storage medium comprises a stored program, wherein, when the program runs, a device where the storage medium is located is controlled to execute the legal knowledge retrieval method of any one of claims 1 to 3.
8. A processor, characterized in that the processor is configured to execute a program, wherein the program executes the method for retrieving legal knowledge according to any one of claims 1 to 3.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611204508.9A CN108241621B (en) | 2016-12-23 | 2016-12-23 | legal knowledge retrieval method and device |
| PCT/CN2017/113804 WO2018113498A1 (en) | 2016-12-23 | 2017-11-30 | Method and apparatus for retrieving legal knowledge |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611204508.9A CN108241621B (en) | 2016-12-23 | 2016-12-23 | legal knowledge retrieval method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108241621A CN108241621A (en) | 2018-07-03 |
| CN108241621B true CN108241621B (en) | 2019-12-10 |
Family
ID=62624399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611204508.9A Active CN108241621B (en) | 2016-12-23 | 2016-12-23 | legal knowledge retrieval method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108241621B (en) |
| WO (1) | WO2018113498A1 (en) |
Families Citing this family (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717609A (en) * | 2018-07-12 | 2020-01-21 | 北京京东尚科信息技术有限公司 | Method and device for predicting claims |
| CN109241528B (en) * | 2018-08-24 | 2023-09-01 | 讯飞智元信息科技有限公司 | Criminal investigation result prediction method, device, equipment and storage medium |
| CN109359175B (en) * | 2018-09-07 | 2023-04-07 | 平安科技（深圳）有限公司 | Electronic device, litigation data processing method, and storage medium |
| CN110969017B (en) * | 2018-09-30 | 2024-02-20 | 北京国双科技有限公司 | Judicial data processing method and system |
| CN109460468A (en) * | 2018-10-23 | 2019-03-12 | 出门问问信息科技有限公司 | Classifying method, categorization arrangement and the corresponding electronic equipment of law related text |
| CN109597889B (en) * | 2018-11-19 | 2023-04-07 | 刘品新 | Crime determining method and system based on text classification and deep neural network |
| CN111367879A (en) * | 2018-12-26 | 2020-07-03 | 北京国双科技有限公司 | Legal document processing method and device |
| CN111401047A (en) * | 2018-12-29 | 2020-07-10 | 北京国双科技有限公司 | Method and device for generating dispute focus of legal document and computer equipment |
| CN110532359A (en) * | 2019-06-14 | 2019-12-03 | 平安科技（深圳）有限公司 | Legal provision query method, apparatus, computer equipment and storage medium |
| CN112329436B (en) * | 2019-07-30 | 2024-08-23 | 北京国双科技有限公司 | Legal document element analysis method and system |
| CN112395388B (en) * | 2019-08-16 | 2023-12-26 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN110825879B (en) * | 2019-09-18 | 2024-05-07 | 平安科技（深圳）有限公司 | Decide a case result determination method, device, equipment and computer readable storage medium |
| CN110795566A (en) * | 2019-09-18 | 2020-02-14 | 平安科技（深圳）有限公司 | Case recommendation method, device and equipment and computer-readable storage medium |
| CN110717041B (en) * | 2019-09-19 | 2023-10-03 | 太极计算机股份有限公司 | Case retrieval method and system |
| CN112561744A (en) * | 2019-09-25 | 2021-03-26 | 北京国双科技有限公司 | Method and device for generating similar case retrieval report |
| CN112580338A (en) * | 2019-09-27 | 2021-03-30 | 北京国双科技有限公司 | Method and device for determining dispute focus, storage medium and equipment |
| CN112579731A (en) * | 2019-09-30 | 2021-03-30 | 北京国双科技有限公司 | Data processing method and device |
| CN110928987B (en) * | 2019-10-18 | 2023-07-25 | 平安科技（深圳）有限公司 | Legal provision retrieval method and related equipment based on neural network hybrid model |
| CN110929039B (en) * | 2019-10-18 | 2023-09-29 | 平安科技（深圳）有限公司 | Data processing method, device, equipment and storage medium |
| CN112784034B (en) * | 2019-11-01 | 2024-05-31 | 阿里巴巴集团控股有限公司 | Digest generation method and device and computer equipment |
| CN111143550B (en) * | 2019-11-27 | 2022-05-03 | 浙江大学 | Method for automatically identifying dispute focus based on hierarchical attention neural network model |
| CN111695874B (en) * | 2020-06-09 | 2023-08-11 | 山东交通学院 | Judicial decision auxiliary system, judicial decision auxiliary method, judicial decision auxiliary equipment and storable medium |
| CN112395409A (en) * | 2020-11-30 | 2021-02-23 | 重庆工程职业技术学院 | Legal knowledge retrieval system and method |
| CN112487146B (en) * | 2020-12-02 | 2022-05-31 | 重庆邮电大学 | Legal case dispute focus acquisition method and device and computer equipment |
| CN112800746A (en) * | 2021-01-28 | 2021-05-14 | 北京华宇元典信息服务有限公司 | Text matching-based dispute focus recommendation method and device and electronic equipment |
| CN112950414B (en) * | 2021-02-25 | 2023-04-18 | 华东师范大学 | Legal text representation method based on decoupling legal elements |
| CN112989820B (en) * | 2021-03-22 | 2022-12-02 | 平安国际智慧城市科技股份有限公司 | Legal document positioning method, device, equipment and storage medium |
| CN115017917B (en) * | 2022-08-09 | 2022-10-28 | 北京肇祺信息科技有限公司 | Judgment document dispute focus identification method based on multi-head attention mechanism |
| CN118485054B (en) * | 2024-07-15 | 2024-09-20 | 人民法院信息技术服务中心 | Bulletin document generation method, device and equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408885A (en) * | 2007-10-05 | 2009-04-15 | 富士通株式会社 | Modeling topics using statistical distributions |
| CN102004774A (en) * | 2010-11-16 | 2011-04-06 | 清华大学 | Personalized user tag modeling and recommendation method based on unified probability model |
| CN102831558A (en) * | 2012-07-20 | 2012-12-19 | 桂林电子科技大学 | System and method for automatically scoring college English compositions independent of manual pre-scoring |
| CN104915396A (en) * | 2015-05-28 | 2015-09-16 | 杭州电子科技大学 | Knowledge retrieving method |
| CN105023214A (en) * | 2015-07-17 | 2015-11-04 | 蓝舰信息科技南京有限公司 | Title knowledge point intelligent recommending method |
| CN105095229A (en) * | 2014-04-29 | 2015-11-25 | 国际商业机器公司 | Method for training topic model, method for comparing document content and corresponding device |
| CN105893363A (en) * | 2014-09-26 | 2016-08-24 | 北大方正集团有限公司 | A method and a system for acquiring relevant knowledge points of a knowledge point |
| CN106095762A (en) * | 2016-02-05 | 2016-11-09 | 中科鼎富（北京）科技发展有限公司 | A kind of news based on ontology model storehouse recommends method and device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853449A (en) * | 2010-06-18 | 2010-10-06 | 上海百事通信息技术有限公司 | Legal question intelligent diagnosis method and system |
| CN104111933B (en) * | 2013-04-17 | 2017-08-04 | 阿里巴巴集团控股有限公司 | Obtain business object label, set up the method and device of training pattern |
| CN103995885B (en) * | 2014-05-29 | 2017-11-17 | 百度在线网络技术（北京）有限公司 | The recognition methods of physical name and device |
| CN104063427A (en) * | 2014-06-06 | 2014-09-24 | 北京搜狗科技发展有限公司 | Expression input method and device based on semantic understanding |
| CN104090863A (en) * | 2014-07-24 | 2014-10-08 | 高德良 | Intelligent legal instrument generating method and system |
| CN105930470B (en) * | 2016-04-25 | 2019-03-26 | 安徽富驰信息技术有限公司 | A kind of document retrieval method based on feature weight analytical technology |
-
2016
- 2016-12-23 CN CN201611204508.9A patent/CN108241621B/en active Active
-
2017
- 2017-11-30 WO PCT/CN2017/113804 patent/WO2018113498A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408885A (en) * | 2007-10-05 | 2009-04-15 | 富士通株式会社 | Modeling topics using statistical distributions |
| CN102004774A (en) * | 2010-11-16 | 2011-04-06 | 清华大学 | Personalized user tag modeling and recommendation method based on unified probability model |
| CN102831558A (en) * | 2012-07-20 | 2012-12-19 | 桂林电子科技大学 | System and method for automatically scoring college English compositions independent of manual pre-scoring |
| CN105095229A (en) * | 2014-04-29 | 2015-11-25 | 国际商业机器公司 | Method for training topic model, method for comparing document content and corresponding device |
| CN105893363A (en) * | 2014-09-26 | 2016-08-24 | 北大方正集团有限公司 | A method and a system for acquiring relevant knowledge points of a knowledge point |
| CN104915396A (en) * | 2015-05-28 | 2015-09-16 | 杭州电子科技大学 | Knowledge retrieving method |
| CN105023214A (en) * | 2015-07-17 | 2015-11-04 | 蓝舰信息科技南京有限公司 | Title knowledge point intelligent recommending method |
| CN106095762A (en) * | 2016-02-05 | 2016-11-09 | 中科鼎富（北京）科技发展有限公司 | A kind of news based on ontology model storehouse recommends method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108241621A (en) | 2018-07-03 |
| WO2018113498A1 (en) | 2018-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108241621B (en) | legal knowledge retrieval method and device | |
| CN111291570B (en) | Method and device for realizing element identification in judicial documents | |
| CN106649316B (en) | Video pushing method and device | |
| CN108280114B (en) | Deep learning-based user literature reading interest analysis method | |
| CN110968663B (en) | Answer display method and device of question-answering system | |
| US11170270B2 (en) | Automatic generation of content using multimedia | |
| CN108694178B (en) | Method and device for recommending judicial knowledge | |
| CN109145110B (en) | Label query method and device | |
| CN109471889B (en) | Report accelerating method, system, computer equipment and storage medium | |
| US11144579B2 (en) | Use of machine learning to characterize reference relationship applied over a citation graph | |
| CN109472017B (en) | Method and device for obtaining relevant information of text court deeds of referee to be generated | |
| CN109697231A (en) | A kind of display methods, system, storage medium and the processor of case document | |
| CN112329460A (en) | Text topic clustering method, device, equipment and storage medium | |
| WO2020063524A1 (en) | Method and system for determining legal instrument | |
| CN109472722B (en) | Method and device for obtaining relevant information of approved finding segment of official document to be generated | |
| Tardy et al. | Align then summarize: Automatic alignment methods for summarization corpus creation | |
| CN110019670A (en) | A kind of text searching method and device | |
| CN108255891B (en) | Method and device for judging webpage type | |
| CN117290481A (en) | Question and answer method and device based on deep learning, storage medium and electronic equipment | |
| AU2019290658B2 (en) | Systems and methods for identifying and linking events in structured proceedings | |
| CN116028626A (en) | Text matching method and device, storage medium and electronic equipment | |
| Yang et al. | Lecture video browsing using multimodal information resources | |
| CN111401047A (en) | Method and device for generating dispute focus of legal document and computer equipment | |
| CN110019665A (en) | Text searching method and device | |
| CN114817586A (en) | Target object classification method and device, electronic 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100083 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: Beijing Guoshuang Technology Co.,Ltd. Address before: 100086 Cuigong Hotel, 76 Zhichun Road, Shuangyushu District, Haidian District, Beijing Applicant before: Beijing Guoshuang Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |