CN115759038B

CN115759038B - Legal litigation case recognition method and device

Info

Publication number: CN115759038B
Application number: CN202211480950.XA
Authority: CN
Inventors: 刘阳; 李凯
Original assignee: Yancheng Tianyanchawei Technology Co ltd
Current assignee: Yancheng Tianyanchawei Technology Co ltd
Filing date: 2022-11-24
Publication date: 2024-07-09
Anticipated expiration: 2042-11-24

Abstract

The embodiment of the invention discloses a method and a device for identifying legal litigation cases, wherein the method comprises the following steps: acquiring legal document data, and dividing the legal document data to obtain specified domain block data; wherein the specified domain block comprises: a case number field block; the method comprises the steps of extracting case-by-case information from case-by-case number field block data; and carrying out multistage matching on the case-by-information and a plurality of preset case-by-information contained in the preset case-by-tree, and displaying the case-by-information contained in the matching result as a case-by-information. According to the case-by-information in the extracted legal document data, the multi-level matching is carried out on the case-by-information by utilizing a plurality of preset case-by-information of the preset case-by-tree, and the preset case-by-information is accurately determined through the multi-level matching, so that the case-by-determination accuracy is improved.

Description

Legal litigation case recognition method and device

Technical Field

The embodiment of the invention relates to the technical field of data processing, in particular to a method and a device for identifying legal litigation cases.

Background

For law litigation and judicial resolution related cases related to enterprises, corresponding case information exists in each law litigation case, and the corresponding case information is used for representing the case dispute type.

In the prior art, a complete case-by-text matching mode is adopted for extracting and recalling the completely satisfied case-by-information, but the problem that the case-by-case and legal case-by-case in the document are inconsistent can occur due to the fact that the case-by-case is numerous. Furthermore, different local courts can have different text descriptions on the same case, and the extraction of case information needs to be perfected and optimized to ensure the fairness of the data and improve the accuracy and the data quality of the data of the related legal litigation cases of enterprises.

Disclosure of Invention

In view of the foregoing, embodiments of the present invention have been developed to provide a method and apparatus for identifying legal litigation cases that overcome, or at least partially solve, the foregoing problems.

In accordance with one aspect of an embodiment of the present invention, there is provided a method of legal litigation cases recognition,

Acquiring legal document data, and dividing the legal document data to obtain specified domain block data; wherein the specified domain block comprises: a case number field block;

The method comprises the steps of extracting case-by-case information from case-by-case number field block data;

And carrying out multistage matching on the case-by-information and a plurality of preset case-by-information contained in the preset case-by-tree, and displaying the case-by-information contained in the matching result as a case-by-information.

Optionally, the preset case-by-tree includes a plurality of preset case-by-information, each preset case-by-information having a case-by-level;

The method further comprises the steps of:

Classifying the preset case information according to the case-by-level to obtain each preset case-by-information belonging to different case-by-levels;

The preset case tree is constructed in a grading mode according to the case level; wherein the preset case-by-tree comprises a plurality of different case-by-levels.

Optionally, the multi-level matching includes case-by-information full-text matching and/or case-by-keyword matching;

carrying out multistage matching on the case-by-information and a plurality of preset case-by-information contained in the preset case-by-tree, and showing the preset case-by-information contained in the matching result as the case-by-information further comprises:

Carrying out full-text matching on the case-by-case information and a plurality of preset case-by-case information contained in the preset case-by-case tree according to the case-by-case level from low to high to obtain a first matching result;

if the first matching result contains single preset case information, displaying by using the preset case information as a case information;

If the first matching result contains a plurality of preset case information or does not contain preset case information, case key words of the case information are obtained, the case key words are matched with the case key words of the plurality of preset case information contained in the preset case tree according to the case level from low to high, and a second matching result is obtained; the second matching result comprises a first matching result and a keyword matching result;

and displaying the preset case by information contained in the second matching result as a case by.

Optionally, matching the case-by-keyword with a plurality of preset case-by-information contained in the preset case-by-tree according to the case-by-level from low to high, and obtaining a second matching result further includes:

the case-by-keyword is precisely matched with a plurality of preset case-by-information contained in the preset case-by-tree according to the case-by-level from low to high;

if the matching is successful, using the single preset case information as a second matching result;

If the matching fails, carrying out fuzzy matching on the case-by-keyword and a plurality of preset case-by-information contained in the preset case-by-tree according to the case-by-level from low to high to obtain a fuzzy matching result; calculating fuzzy matching degree according to preset cases included in the fuzzy matching result; and according to the order of the fuzzy matching degree from high to low, acquiring the preset case information with the prior fuzzy matching degree order as a second matching result.

Optionally, calculating the fuzzy matching degree from the information for the preset case included in the fuzzy matching result further includes:

And calculating the number of matching words and/or matching proportion of the preset case information and the case keywords to obtain fuzzy matching degree.

Optionally, if the matching result includes a plurality of preset case information, the method further includes:

and merging a plurality of preset case information with the same upper-level case information level in the plurality of preset case information to obtain upper-level preset case information, and repeatedly executing the steps until single preset case information is obtained.

Optionally, if the matching result does not include the preset list information, the method further includes:

And displaying the case information as the case information.

Optionally, dividing the legal document data to obtain the specified domain block data further includes:

According to a preset structured template, dividing the specified domain blocks from legal document data to obtain specified domain block data, and performing data cleaning processing on the specified domain block data.

Optionally, the extracting the case-by information from the case-by-case number field block data further includes:

and analyzing the case number field block data of the case by the preset analysis algorithm, and extracting to obtain the case by information.

According to another aspect of embodiments of the present invention, there is provided a legal litigation case by identification device, comprising:

the dividing module is suitable for acquiring legal document data and dividing the legal document data to acquire specified domain block data; wherein the specified domain block comprises: a case number field block;

The extraction module is suitable for extracting the case-by-case information from the case-by-case number field block data;

the matching module is suitable for carrying out multistage matching on the case information and a plurality of preset case information contained in the preset case tree, and displaying the case information by using the preset case information contained in the matching result as the case information.

According to yet another aspect of an embodiment of the present invention, there is provided a computing device including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;

the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the legal litigation case identification method.

According to yet another aspect of embodiments of the present invention, there is provided a computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of identifying legal litigation as described above.

According to the method and the device for identifying the legal litigation cases provided by the embodiment of the invention, according to the information of the case law case in the extracted legal document data, and carrying out multistage matching on the preset case information by utilizing a plurality of preset case information of the preset case tree, and accurately determining the preset case information through multistage matching, so that the case determination accuracy is improved.

The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and may be implemented according to the content of the specification, so that the technical means of the embodiments of the present invention can be more clearly understood, and the following specific implementation of the embodiments of the present invention will be more apparent.

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 designate like parts throughout the figures. In the drawings:

FIG. 1 illustrates a flow chart of a method of identifying legal litigation cases by which an embodiment of the invention is concerned;

FIG. 2 illustrates a flow chart of a method of identifying legal litigation cases according to another embodiment of the invention;

FIG. 3 illustrates a schematic diagram of legal document data partitioning into corresponding domain blocks;

FIG. 4 illustrates a schematic diagram of a legal litigation case recognition device in accordance with one embodiment of the invention;

FIG. 5 illustrates a schematic diagram of a computing device, according to one embodiment of the invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention 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 invention to those skilled in the art.

FIG. 1 shows a flow chart of a method of identifying legal litigation cases by which, as shown in FIG. 1, includes the steps of:

step S101, acquiring legal document data, and dividing the legal document data to obtain specified domain block data.

Legal documents are documents used by law administration authorities and parties, lawyers and the like in solving litigation and non-litigation cases, and also include non-normative documents of the law administration and the like, and can be obtained through a legal document search platform, a court website and the like. The legal document includes, for example, a decision document, an adjudication document, and a decision document, where in this embodiment, the legal document is described by taking the decision document as an example, and the legal document data is decision text data, where the decision document data includes, for example, a document type, a document title, a document body, a decision court, a decision result, a decision date, and the like, and specifically, the document body also includes, for example, a case related case, related to an enterprise, dispute details, and the like.

In consideration of the fact that the judgment document data contains more contents, in order to facilitate rapid and accurate positioning of the case, the judgment document data can be divided into different domain block data, such as a title domain block, a case number domain block, a text title domain block, a principal domain block, an aesthetic Cheng Yukuai and the like, when the judgment document data is divided, the specific domain block data is obtained based on the domain block data obtained by division. The specified domain blocks comprise case number domain blocks, so that follow-up case optimizing is facilitated.

Step S102, the case information is extracted from the case number field block data.

And analyzing the case number field block data according to characters, position information and the like contained in the case number field block data, wherein if the case number field block data contains 'case by', corresponding specific case information is recorded after 'case by'. During analysis, the 'case from' can be firstly located and found, and corresponding case from information can be obtained by extracting according to the found 'case from'.

Step S103, carrying out multistage matching on the case-by-case information and a plurality of preset case-by-case information contained in the preset case-by-tree, and displaying the case-by-case information contained in the matching result as a case-by-case.

In consideration of the fact that inaccuracy of the case-by information affects the fairness of the data, the case-by information can be matched with the case-by information based on the preset case-by information, so that the corresponding preset case-by information is obtained to be used as an accurate case-by of legal documents for displaying, and the fairness of data display is guaranteed.

The preset case information comprises case information such as case information contained in case information rule, each preset case information has a respective case level, and the preset case information can be divided according to the respective case levels to obtain preset case information trees. The preset case list tree comprises a plurality of preset case list information with different case list levels. And (3) carrying out multistage matching on the case-by-information acquired in the step S102 and a plurality of preset case-by-information of different case-by-levels in the preset case-by-tree, and obtaining preset case-by-information matched with the case-by-information from the preset case-by-tree. Specifically, the multi-stage matching may include, for example, full-text matching of the case information, matching of the case keyword with the preset case information according to a full-text matching mode, or matching of the case keyword with the preset case information according to the keyword in the case information, for example, precision matching of the key frame, fuzzy matching of the key word, and the like, and determining the finally matched preset case information through multi-stage matching.

According to the legal litigation case law pattern recognition method provided by the embodiment of the invention, according to the case law pattern information in the extracted legal document data, the multi-level matching is carried out on the case law pattern information by utilizing a plurality of preset case law pattern information of the preset case law pattern tree, the preset case law pattern information is accurately determined through the multi-level matching, and the case law pattern determination accuracy is improved.

FIG. 2 shows a flow chart of a method of identifying legal litigation cases by which, as shown in FIG. 2, includes the steps of:

step S201, obtaining legal document data, dividing a specified domain block from the legal document data according to a preset structured template to obtain specified domain block data, and performing data cleaning processing on the specified domain block data.

The legal document can be obtained through searching and inquiring through a legal document searching platform, a court website and the like, in the embodiment, the legal document is illustrated by taking a judgment document as an example, the legal document data is judgment text data, the judgment document data comprises contents such as a document type, a document title, a document text, a judgment court, a judgment result, a judgment date and the like, and the specific document body also comprises details of cases such as a case related case, related enterprises, disputes and the like.

In order to conveniently, quickly and accurately position the scheme, legal document data can be divided according to a preset structural template. Here, the preset structured template may be obtained by pre-analyzing each part of the structural composition of the legal document and the position thereof in the legal document, and the preset structured template may be determined according to each part of the structural composition of the legal document and the position thereof. Different legal documents can be preset with different preset structuring modules, and the preset structuring modules correspond to specific contents of the legal documents. Taking a decision document as an example, the decision document data is divided according to a preset structural template to obtain a title domain block, a case number domain block, a text title domain block, a principal domain block, an aesthetic Cheng Yukuai and the like as shown in fig. 3, wherein the decision document data is divided into domain blocks such as a title domain block 301, a case number domain block 302, a text title domain block 303, a principal domain block 304, an aesthetic process domain block 305 and the like, and the data contained in the range of each domain block is the domain block data of the domain block. The specified field blocks in this embodiment include a case number field block 302. The case number field 302 includes case number, release date, browsing times, etc., and the embodiment mainly uses case number information corresponding to the case number.

Further, after the decision document is divided to obtain the data of each domain block, considering that the legal document is displayed in a webpage format, the obtained data of the domain block of the case number includes format data of the webpage, such as html tag symbols, and the like, besides the case number, the release date, the browsing times, and the like, the html tag symbols are used for aligning and setting the format of each data, such as the case number, the release date, the browsing times, and the like, in the domain block, the html tag symbols themselves belong to legal irrelevant data for the embodiment, therefore, data cleaning processing needs to be performed on the data of the domain block of the case number, such as data cleaning processing of removing the html tag symbols and removing abnormal data, so that the finally obtained data contained in the data of the domain block of the case number is legal relevant data, and subsequent extraction is convenient to obtain the information of the case number. The above is an illustration, and the corresponding legal irrelevant data such as symbols, abnormal data and the like related to the removal format is removed according to the display format of the legal document, so that the subsequent extraction based on the legal relevant data is convenient.

Step S202, analyzing the case number field block data according to a preset analysis algorithm, and extracting to obtain case number information.

After the case number field block data of the case is obtained, the case number field block data of the case is further analyzed to extract the case information.

Specifically, a preset analysis algorithm applicable to the case number field block data is determined according to the data text, the position and the like contained in the case number field block data, for example, as shown in fig. 3, the preset analysis algorithm can analyze and locate the "case number" text in the case number field block data, and the "labor dispute" after the "case number" text position is extracted can obtain the case number information, namely the labor dispute. The preset parsing algorithm is set according to the specific format of each legal document, which is not limited herein.

Step S203, classifying the plurality of preset case information according to the case-by-level to obtain each preset case-by-information belonging to different case-by-levels, and constructing a preset case-by-tree according to the case-by-level classification.

The preset case information can be collected in advance, for example, according to the published case rule, the preset case information is obtained from the preset case information, and the case level corresponding to each preset case information is obtained at the same time. The case-by-level comprises a level 1, a level 2, a level 3, a level 4 and the like, wherein the case-by-level gradually decreases from the level 1 to the level 4, the level 1 is a high-level case-by-level, and the level 4 is a low-level case-by-level. The preset case information can be classified according to the case-by-level, so that the preset case-by-information belonging to different case-by-levels can be obtained, for example, the 1-level case-by-level comprises such as labor disputes/personnel disputes, the 2-level case-by-level comprises such as labor disputes, personnel disputes, and the like, the 3-level case-by-level comprises such as labor contract disputes, social insurance disputes, and the like, and the 4-level case-by-level comprises such as confirmation of labor relationship disputes, pursuit of labor reward disputes, and the like. Classifying each preset case information according to the respective case information level, classifying the preset case information belonging to the same case information level into one category, and constructing a preset case information tree according to the association relation among the preset case information, such as from a low-level case information level to a high-level case information level, and classifying according to the case information levels. Taking preset case information of 4 case-by-level as an example for confirming labor relationship disputes and pursuing labor compensation disputes, taking the preset case-by-level information of the upper 3 case-by-level as labor contract disputes, taking the preset case-by-level information of 2 case-by-level as labor disputes, taking the preset case-by-level information of 1 case-by-level as labor disputes/personnel disputes and the like as an example, wherein the preset case-by-tree comprises a plurality of different branches, each branch can comprise 1 case-by-level to 4 case-by-level, wherein certain case-by-level can be also absent, such as absence of preset case-by-level information of 4 case-by-level, only preset case-by-level information of 3 case-by-level and the like, and the invention is not limited herein.

The preset case tree can be non-fixed data, and can be updated according to different preset case information, and the preset case tree is reconstructed according to the case level of each preset case information during updating so as to ensure the accuracy of the matched preset case information.

Further, this step may be performed before step S201, and the execution order is not limited herein. If the preset tree has been constructed, this step may not be performed.

Step S204, carrying out multistage matching on the case-by-information and a plurality of preset case-by-information contained in the preset case-by-tree, and displaying the case-by-information contained in the matching result as the case-by-information.

When carrying out multistage matching on preset case information, carrying out case information full-text matching on case information and a plurality of preset case information contained in a preset case information tree from low to high according to case information level, for example, carrying out case information full-text matching on case information from 4-stage case information of the preset case information tree, then carrying out case information full-text matching on the preset case information of 3-stage case information level, carrying out case information full-text matching on the preset case information of 2-stage case information level, and carrying out case information full-text matching on the preset case information of 1-stage case information level from low to high, thereby obtaining a first matching result. If the first matching result only includes a single preset case information, for example, after case information full-text matching is performed on the preset case information tree, the obtained first matching result is only a certain preset case information, and the preset case information can be directly utilized to replace case information in legal documents to be displayed as case information. Or if the first matching result includes a plurality of preset case information, for example, taking case information "labor dispute" as an example, performing case information full-text matching, and then obtaining preset case information including 2-level case information-by-level preset case information labor disputes, 1-level case information-by-level preset case information labor disputes/personnel disputes, and the like, taking the obtained preset case information as alternative case information for further matching. Or if the first matching result does not include the preset case information, for example, taking case information "labor dispute" as an example, if each preset case information in the preset case information tree does not have the preset case information matched with the full text of the preset case information, further multi-stage matching needs to be executed. When matching is further carried out, the case-by-case keywords in the case-by-case information are acquired firstly, for example, labor disputes are taken as an example, wherein the case-by-case keywords are labor, the case-by-case keywords can be acquired according to semantic analysis and the like, and the case-by-case keywords are not limited herein. And matching the case-by-keyword with a plurality of preset case-by-information contained in the preset case-by-tree according to the case-by-level from low to high, and obtaining a second matching result. The second matching result comprises keyword matching results obtained by matching information and keywords of a plurality of presets in the first matching result. The keyword matching specifically includes: and carrying out the accurate matching of the case-by-keyword according to the case-by-level from low to high on the case-by-keyword and a plurality of preset case-by-information contained in the preset case-by-tree, for example, carrying out the accurate matching of the keyword by taking labor as the case-by-keyword. Accurately matching the labor with a plurality of preset case information in the preset case tree, searching the preset case information containing the labor in the preset case information, and if the matching is successful, taking the matched preset case information as a second matching result to replace the case information in the legal document for display; if the matching fails, if the matching is performed on a plurality of pieces of preset case information or the matching is not performed on the preset case information, the matching fails. If the matching failure is that a plurality of pieces of preset case information are matched, the matched pieces of preset case information can be used as alternative case information and added into a second matching result, so that further matching is facilitated. If the matching fails, if the matching fails to match the preset case information, further matching needs to be executed. And carrying out fuzzy matching on the case-by-keyword based on the further matching, specifically carrying out fuzzy matching on the case-by-keyword and a plurality of preset case-by-information contained in the preset case-by-tree from low to high according to the case-by-level, carrying out fuzzy matching on the preset case-by-information with a plurality of hit words of the matched keyword according to the case-by-level from 4 to 1, obtaining a fuzzy matching result, and calculating fuzzy matching degree of the preset case-by-information contained in the fuzzy matching result. The fuzzy matching degree is obtained by calculating the matching word number and matching proportion of preset case information and case keywords. If the case is "contract disputes for buying and selling" in the case, the case is "contract for buying and selling" in the case, and if the case is "contract for buying and selling" in the preset case, the number of matched keywords is 2, and the ratio is 2/4=50%. When the fuzzy matching result contains a plurality of preset case information, the fuzzy matching degree of each preset case information can be calculated in sequence, the preset case information with the prior fuzzy matching degree ordered is obtained as a second matching result according to the order of the fuzzy matching degree from high to low, namely, the preset case information with the maximum matching word number and the highest matching proportion is selected. Or setting a preset matching word number threshold value, a preset matching proportion threshold value and the like, wherein a preset scheme with the number of the preset matching words and the preset matching proportion threshold value higher than the preset matching word number threshold value is used as a second matching result by information.

Further, if the second matching result still includes a plurality of preset case routing information, a plurality of preset case routing information having the same upper case routing level in the plurality of preset case routing information may be combined to obtain upper preset case routing information, for example, the second matching result includes a plurality of preset case routing information A, B, C, D, where the case routing level of A, B is 4 levels, and A, B has the same upper case routing level, A, B is combined to obtain upper (3) case routing level of preset case routing information E, and the case routing level of C, D is 3 levels, and E has the same upper case routing level, then the combination is continued to obtain upper (2) case routing information F, where F is single preset case routing information, and F is displayed as a case routing.

Further, if the preset case information is not contained in the matching result after the multi-stage matching, the case information is displayed as the case of the legal document.

According to the legal litigation case list identification method provided by the embodiment of the invention, through multistage matching, full text matching of case list information, accurate matching of case list keywords, fuzzy matching of case list keywords, increasing of the number of matched preset case list information, fuzzy matching degree is obtained through calculation of the number of matched words and matching proportion, matching accuracy of the preset case list information is improved based on the fuzzy matching degree, preset case list information with better matching is obtained, matching accuracy and accuracy are improved, and matching data quality is improved.

Fig. 4 shows a schematic structural diagram of a legal litigation case recognition device provided by an embodiment of the present invention.

As shown in fig. 4, the apparatus includes:

The dividing module 410 is adapted to acquire legal document data, and divide the legal document data to obtain specified domain block data; wherein the specified domain block comprises: a case number field block;

the extracting module 420 is adapted to extract the case-by-case information from the case-by-case number field block data;

the matching module 430 is adapted to perform multi-level matching on the case information and a plurality of preset case information contained in the preset case tree, and display the case information contained in the matching result as a case.

The apparatus further comprises:

the construction module 440 is adapted to classify the plurality of preset case information according to the case level, so as to obtain each preset case information belonging to different case levels; the preset case tree is constructed in a grading mode according to the case level; wherein the preset case-by-tree comprises a plurality of different case-by-levels.

The matching module 430 is further adapted to:

Optionally, the matching module 430 is further adapted to:

Optionally, if the matching result includes a plurality of preset case information, the apparatus further includes: the merging module 450 is adapted to merge the plurality of preset case information having the same upper case information level in the plurality of preset case information to obtain upper preset case information, and repeatedly execute the step until a single preset case information is obtained.

Optionally, if the matching result does not include the preset list information, the apparatus further includes: the display module 460 is adapted to display the case-by-case information as a case-by-case.

Optionally, the partitioning module 410 is further adapted to:

Optionally, the extraction module 420 is further adapted to:

The above descriptions of the modules refer to the corresponding descriptions in the method embodiments, and are not repeated herein.

According to the legal litigation case recognition device provided by the embodiment of the invention, according to the case information in the extracted legal document data, and carrying out multistage matching on the preset case information by utilizing a plurality of preset case information of the preset case tree, and accurately determining the preset case information through multistage matching, so that the case determination accuracy is improved.

The embodiment of the invention also provides a nonvolatile computer storage medium, and the computer storage medium stores at least one executable instruction, and the executable instruction can execute the legal litigation case recognition method in any method embodiment.

FIG. 5 illustrates a schematic diagram of a computing device, according to an embodiment of the invention, the particular embodiment of which is not limiting of the particular implementation of the computing device.

As shown in fig. 5, the computing device may include: a processor 502, a communication interface (Communications Interface) 504, a memory 506, and a communication bus 508.

Wherein:

processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508.

A communication interface 504 for communicating with network elements of other devices, such as clients or other servers.

Processor 502 is configured to execute program 510, and may specifically perform the relevant steps in the above-described legal litigation scheme by identification method embodiment.

In particular, program 510 may include program code including computer-operating instructions.

The processor 502 may be a central processing unit CPU, or an Application-specific integrated Circuit ASIC (Application SPECIFIC INTEGRATED Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.

A memory 506 for storing a program 510. Memory 506 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

Program 510 may be specifically operable to cause processor 502 to perform the legal litigation scheme by identification method in any of the method embodiments described above. The specific implementation of the steps in procedure 510 may be found in the corresponding descriptions of the corresponding steps and elements in the identified embodiments of the legal litigation cases described above, and are not repeated here. It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and modules described above may refer to corresponding procedure descriptions in the foregoing method embodiments, which are not repeated herein.

The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It should be appreciated that the teachings of embodiments of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of preferred embodiments of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., an embodiment of the invention that is claimed, requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). Embodiments of the present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the embodiments of the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.

Claims

1. A method of legal litigation case identification, comprising:

Classifying the preset case information according to the case-by-level to obtain each preset case-by-information belonging to different case-by-levels, and constructing a preset case-by-tree according to the case-by-level classification;

carrying out multistage matching on the case-by-case information and a plurality of preset case-by-case information contained in a preset case-by-case tree, and displaying the case-by-case information contained in a matching result as a case-by-case; the multi-level matching comprises case-by-information full-text matching and/or case-by-keyword matching;

The step of carrying out multistage matching on the case information and a plurality of preset case information contained in the preset case tree, and the step of utilizing the preset case information contained in the matching result as the case information for showing further comprises the steps of:

carrying out full-text matching on the case-by-case information and a plurality of preset case-by-case information contained in a preset case-by-case tree according to the case-by-case level from low to high to obtain a first matching result;

If the first matching result contains single preset case information, displaying by using the preset case information as a case;

If the first matching result contains a plurality of preset case information or does not contain preset case information, obtaining case keywords of the case information, and matching the case keywords with the case keywords of the plurality of preset case information contained in the preset case tree according to the case level from low to high to obtain a second matching result; the second matching result comprises the first matching result and a keyword matching result;

2. The method of claim 1, wherein the preset project tree comprises a plurality of preset project information, each preset project information having a project level; the preset case-by-tree includes a plurality of different case-by-levels.

3. The method of claim 1, wherein matching the case-by-keyword with a plurality of preset case-by-information included in a preset case-by-tree according to a case-by-level from low to high, to obtain a second matching result further comprises:

accurately matching the case-by-keyword with a plurality of preset case-by-information contained in a preset case-by-tree according to the case-by-level from low to high;

If the matching fails, carrying out fuzzy matching on the case-by-keyword and a plurality of preset case-by-information contained in the preset case-by-tree according to the case-by-level from low to high to obtain a fuzzy matching result; calculating fuzzy matching degree according to preset case information contained in the fuzzy matching result; and according to the order of the fuzzy matching degree from high to low, acquiring the preset case information with the prior fuzzy matching degree order as a second matching result.

4. The method of claim 3, wherein calculating the fuzzy matching degree from information for a preset case included in the fuzzy matching result further comprises:

and calculating the number of matching words and/or the matching proportion of the preset case-by-information and the case-by-keyword to obtain fuzzy matching degree.

5. The method of any one of claims 1-4, wherein if the matching result includes a plurality of preset list information, the method further comprises:

And merging the plurality of preset case information with the same upper case by level in the plurality of preset case by information to obtain upper preset case by information, and repeatedly executing merging of the plurality of preset case by information with the same upper case by level until obtaining single preset case by information.

6. The method according to any one of claims 1-4, wherein if the matching result does not contain preset list information, the method further comprises:

And displaying the case by information as a case by.

7. The method of any of claims 1-4, wherein the partitioning the legal document data into specified domain block data further comprises:

and dividing the specified domain blocks from the legal document data according to a preset structured template to obtain specified domain block data, and performing data cleaning processing on the specified domain block data.

8. The method of any of claims 1-4, wherein the extracting the case by information from the case number field block data further comprises:

And analyzing the case number field block data of the case by the preset analysis algorithm, and extracting to obtain case by information.

9. A legal action case recognition device, comprising:

The dividing module is suitable for acquiring legal document data and dividing the legal document data to obtain specified domain block data; wherein the specified domain block comprises: a case number field block;

The construction module is suitable for classifying the preset case information according to the case list level to obtain each preset case list information belonging to different case list levels, and constructing the preset case list tree according to the case list levels in a grading manner;

The matching module is suitable for carrying out multistage matching on the case-by-case information and a plurality of preset case-by-case information contained in the preset case-by-case tree, and displaying the case-by-case information contained in the matching result as a case-by-case; the multi-level matching comprises case-by-information full-text matching and/or case-by-keyword matching;

The matching module is further adapted to: carrying out full-text matching on the case-by-case information and a plurality of preset case-by-case information contained in a preset case-by-case tree according to the case-by-case level from low to high to obtain a first matching result; if the first matching result contains single preset case information, displaying by using the preset case information as a case; if the first matching result contains a plurality of preset case information or does not contain preset case information, obtaining case keywords of the case information, and matching the case keywords with the case keywords of the plurality of preset case information contained in the preset case tree according to the case level from low to high to obtain a second matching result; the second matching result comprises the first matching result and a keyword matching result; and displaying the preset case by information contained in the second matching result as a case by.

10. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;

The memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the legal action case by recognition method of any one of claims 1-8.

11. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method of identifying legal litigation cases of any of claims 1-8.