WO2017092622A1 - 法律条文的搜索方法及装置 - Google Patents

法律条文的搜索方法及装置 Download PDF

Info

Publication number
WO2017092622A1
WO2017092622A1 PCT/CN2016/107311 CN2016107311W WO2017092622A1 WO 2017092622 A1 WO2017092622 A1 WO 2017092622A1 CN 2016107311 W CN2016107311 W CN 2016107311W WO 2017092622 A1 WO2017092622 A1 WO 2017092622A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
search
legal
candidate
query text
Prior art date
Application number
PCT/CN2016/107311
Other languages
English (en)
French (fr)
Inventor
何鑫
杜宁
Original Assignee
北京国双科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京国双科技有限公司 filed Critical 北京国双科技有限公司
Priority to US15/774,928 priority Critical patent/US20180246955A1/en
Publication of WO2017092622A1 publication Critical patent/WO2017092622A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/18—Legal services
    • 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
    • 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
    • G06F16/335—Filtering based on additional data, e.g. user or group profiles

Definitions

  • the present application relates to the field of information search, and in particular to a method and apparatus for searching for legal provisions.
  • the legal provisions refer to the current effective laws, administrative regulations, judicial interpretations, local regulations, local regulations, departmental rules and other normative documents, as well as from time to time to modify and supplement such laws and regulations.
  • the law refers to all normative documents.
  • the judgment document records the trial process and results of the people's courts, is the carrier of the outcome of the litigation activities, and is the only evidence that the people's courts determine and assign the rights and obligations of the parties.
  • Judgment documents are not only the evidence of the rights and burdens of the parties, but also an important basis for the people's courts at higher levels to supervise the civil trial activities of the people's courts at lower levels.
  • a referee document with complete structure, complete elements and logical rigor shall include the case description of the dispute case, the information of the plaintiff and the lawyer's parties and their clients, and the legal provisions on which the court may impose judgments on the case.
  • legal workers often need to look for laws and regulations similar to the ones currently being handled in litigation cases.
  • laws and regulations similar to their experience as a reference for legal recognition Therefore, it is possible to search for the query text by inputting the case description information, and obtain the judgment document of the effective judgment related to the input text, and thereby obtain the legal provisions for the court to judge the case.
  • the current search engine is mainly for the splitting and matching of words based on the search text input by the case.
  • a search term based on the case is a car, not enough to search the legal provisions, so it is difficult to search for legal provisions related to the case description.
  • the main purpose of the present application is to provide a method and apparatus for searching for legal provisions to solve the problem in the related art that it is difficult to obtain relevant legal provisions based on input search terms.
  • a search method of a legal provision includes: obtaining a search keyword in a search query text; acquiring a legal word that is similar to and/or identical to the search keyword; and expanding the search query text according to legal words with similar meanings and/or the same as the search keyword, The expanded search query text; searching according to the expanded search query text, obtaining the target judgment document collection; and obtaining the target legal provisions of the target judgment document collection.
  • target legal provisions for obtaining the target judgment document set include: segmentation analysis of each target judgment document in the target judgment document collection, obtaining candidate legal provisions of the target judgment document collection; candidate legal provisions for the target judgment document collection Screening is performed to obtain candidate legal provisions after screening; and the candidate legal provisions after screening are taken as the target legal provisions.
  • the candidate legal provisions after screening include a plurality of provisions, and the candidate legal provisions of the target judgment document collection are screened out, and after the screened candidate legal provisions are obtained, the screened candidate legal provisions are targeted Before the legal provisions, the method further comprises: determining the weight value of each target judgment document according to the preset condition; counting the number of occurrences of each clause in each target judgment document; according to the weight value of each target judgment document and each article The number of occurrences of each article in each target adjudication document sorts a plurality of articles, and obtains a plurality of articles after sorting; according to the plurality of articles after sorting, the target articles returned to the target address are determined, and the candidate law after screening is removed
  • the provisions as the target legal provisions include: the target provisions as the target legal provisions.
  • the method before performing the search according to the expanded search query text to obtain the target judgment document set, the method further includes: forming an inverted index on the candidate referee document, obtaining the first inverted list, and performing the extended search query text according to the expanded search query text.
  • Searching, obtaining the target judgment document set includes: inputting the expanded search query text in the first inverted list to perform a search, and obtaining a target judgment document collection.
  • the method further includes: performing segmentation analysis on the candidate referee document to determine a search segment in the candidate referee document, wherein the search segment is a candidate a paragraph describing the content of the case in the judgment document; establishing an inverted index on the search segments in the candidate judgment document and the candidate judgment document, obtaining a second inverted list, searching according to the expanded search query text, and obtaining a target judgment document collection
  • the method includes: inputting the expanded search query text in the second inverted list to perform a search, and obtaining a target judgment document collection.
  • a search apparatus for a legal provision includes: a first acquiring unit, configured to acquire a search keyword in the search query text; a second acquiring unit, configured to acquire a legal word that is similar to and/or the same as the search keyword; and an expansion unit, configured to search according to the search Keywords with similar meanings and/or the same legal words are expanded to the search query text to obtain an expanded search query text; a search unit is used to search according to the expanded search query text to obtain a target judgment document collection; and a third The obtaining unit is configured to obtain the target legal provisions of the target judgment document collection.
  • the third obtaining unit includes: an obtaining module, configured to perform segmentation analysis on each target referee document in the target referee document set, obtain candidate legal provisions of the target referee document set; and screen the module to use the target referee The candidate legal provisions of the collection of documents are screened out to obtain the candidate legal provisions after screening; and a determination module is used to select the candidate legal provisions after screening as the target legal provisions.
  • the candidate legal provisions after screening include a plurality of provisions
  • the device further includes: a first determining unit, A weighting value for determining each target judgment document according to a preset condition; a statistical unit for counting the number of occurrences of each clause in each target judgment document; and a sorting unit for weighting values according to each target judgment document And sorting the plurality of clauses by the number of occurrences of each clause in each target judgment document to obtain a plurality of sorted clauses; and the second determining unit is configured to determine the return to the target address according to the sorted plurality of clauses
  • the target clause, the determination module is also used to target the provisions as the target legal provisions.
  • the apparatus further includes: a first creating unit, configured to establish an inverted index on the candidate refereeing document, to obtain a first inverted row table, where the searching unit is further configured to input the expanded search query text in the first inverted row table Search and get a collection of target referee instruments.
  • a first creating unit configured to establish an inverted index on the candidate refereeing document, to obtain a first inverted row table
  • the searching unit is further configured to input the expanded search query text in the first inverted row table Search and get a collection of target referee instruments.
  • the apparatus further includes: a third determining unit, configured to perform segmentation analysis on the candidate refereeing document, and determine a search segment in the candidate refereeing document, where the search segment is a paragraph in the candidate refereeing document that describes the content of the case; a second creating unit, configured to establish an inverted index on the search segments in the candidate referee file and the candidate referee file, to obtain a second inverted table, where the search unit is further configured to input the expanded search query text in the second inverted table Search and get a collection of target referee instruments.
  • the following steps are taken: obtaining search keywords in the search query text; obtaining legal words that are similar to and/or identical to the search keywords; and searching for query texts according to similar and/or identical legal words of the search keywords Expanding, obtaining the expanded search query text; searching according to the expanded search query text, obtaining the target judgment document collection; and obtaining the target legal provisions of the target judgment document collection, and solving the related art is difficult to obtain according to the input search words
  • the related legal provisions firstly obtain the target legal document collection through the search query text, and then obtain the target legal provisions of the target judgment document collection, that is, establish the connection between the search query text and the legal provisions through the target judgment document collection, and then Achieve the effect of being able to obtain legal provisions related to the entered search query text.
  • FIG. 1 is a flowchart of a search method of a legal provision according to a first embodiment of the present application
  • FIG. 2 is a flowchart of a search method of a legal provision according to a second embodiment of the present application
  • FIG. 3 is a schematic diagram of a search apparatus of a legal provision according to a first embodiment of the present application
  • FIG. 4 is a schematic diagram of a search apparatus for a legal provision according to a second embodiment of the present application.
  • a search method of a legal provision is provided.
  • FIG. 1 is a flow chart of a search method of a legal provision according to a first embodiment of the present application. As shown in Figure 1, the method includes the following steps:
  • Step S101 Acquire a search keyword in the search query text.
  • the search query text in the first embodiment of the present application is a text input based on the dispute case when the party needs to obtain the judgment document of the effective judgment as a reference for handling the dispute.
  • the text of the search query entered by the parties based on the dispute being handled is: when a car is braking, it hits a normal passenger car and related compensation matters.
  • the parties enter the search query text to obtain the judgment document of the effective judgment related to the input text and the legal law of the court to judge the case as the reference for subsequent processing.
  • the search query text is: when a car is braking, it hits a normal passenger car, and related compensation matters.
  • the search keywords in the search query text are “brake” and “compensation”.
  • Step S102 Obtain a legal word that is similar to and/or the same as the meaning of the search keyword.
  • the so-called legal word refers to a word or phrase that has special or specific meaning in the judicial field.
  • the term “chasing racing” is a standard term in the legal literature, but in general, it means “brake car”.
  • the search keywords acquired in the above step S101 are "brake” and "compensation”. Obtain a legal word that is similar to and/or identical to the meaning of “brake car” as “chasing the race” and obtain the legal word that is similar to and/or the same as “compensation” as “compensation”.
  • Step S103 the search query text is expanded according to the legal words whose search keywords have similar meanings and/or the same, and the expanded search query text is obtained.
  • the search query text is augmented according to the legal words with similar meanings and/or the same meaning of the search keywords. For example, according to the "chasing race” with similar meaning or synonymous meaning of "catch”, “compensation” has similar and/or identical legal words. “Compensation” expands the search query text “When a car is driving, it hits a normal bus, relevant compensation matters”, and the expanded search query text is: “A car is hitting a normal bus when it is driving. , related compensation matters, "chasing the race”, "compensation”.
  • Step S104 performing a search according to the expanded search query text, and obtaining a target judgment document collection.
  • the target referee collection includes all target referee collections that match the expanded query text, may contain more than one target referee collection, or may be empty.
  • the search query text is expanded according to the legal words that are similar to and/or the same as the search keyword, and the referee documents are searched in a larger scope, thereby obtaining richer search results and returning more.
  • Target referee instruments collection When the input search keyword is not a legal word, it can also be compensated by expansion, so the search for a target judgment document collection that meets the demand is improved, and the recall rate of the target judgment document collection is improved.
  • the search method of the legal provision provided by the first embodiment of the present application further includes: forming an inverted index on the candidate referee file to obtain the first Inverting the table, searching according to the expanded search query text, and obtaining the target judgment document set includes: inputting the expanded search query text in the first inverted list to perform a search, and obtaining a target judgment document collection.
  • Inverted index that is, the actual application finds records based on the value of the attribute.
  • the principle of the inverted index is as follows:
  • the word segmentation device is used to perform word segmentation processing on each document in the input source database, and the keywords extracted in each document are linked with the document; when the keywords to be queried are input, all the inclusions can be reversely listed.
  • the document of the keyword eliminates the process of sequentially searching for keywords in each document, that is, by creating an inverted index to express the purpose of finding data sources by partial attributes.
  • the implementation of the inverted index can be a mature full-text search engine framework (Lucene) in the industry, or an enterprise search application server (Solr) or a full-text search engine (Elasticsearch) based on Lucene. In addition, you can develop a search engine that meets your needs.
  • the reverse indexing method the actual situation may be determined according to a specific problem, and the first embodiment of the present application is not limited thereto. Method to realize.
  • This step establishes an inverted index for the full text of each candidate referee document.
  • the search term is segmented using the same tokenizer as the search engine used in the inverted index, and one or more keys are obtained after the word segmentation. Words, query inverted table, return the corresponding target referee collection.
  • the searching method of the legal provision provided by the first embodiment of the present application after searching according to the expanded search query text, and obtaining the target judgment document collection, the method further includes: segmenting the candidate referee document, Determining a search segment in the candidate referee document, wherein the search segment is a paragraph describing the content of the case in the candidate referee document; and forming an inverted index on the search segment in the candidate referee document and the candidate referee document to obtain a second inverted table, Searching according to the expanded search query text, obtaining the target referee document set includes: inputting the expanded search query text in the second inverted list to perform a search, and obtaining a target referee document set.
  • a referee's instrument has a format that describes the various elements associated with the case in a particular paragraph. For example, at the beginning of the judgment document, it is necessary to specify the plaintiff party information and its principal information, and then write the information of the court's party and its principal information. Therefore, each paragraph of the candidate judgment document can be segmented by capturing the specific information in the candidate judgment document.
  • the subjective facts stated by the plaintiff when suing the court are mainly recorded; in addition, in the case ascertained in the trial, the court mainly records the combination of the plaintiff and the lawyer after combining the statements of the plaintiff and the court. The fact that the evidence was finally determined.
  • the case description paragraph in the judgment document such as the original telling paragraph and the tried-out paragraph (search section), can be used as the inverted index of the target content of the case content.
  • the inverted index is set for each case description paragraph of each candidate judgment document, which can reduce the storage space of the inverted list, and also reduce the keywords in the paragraphs related to the non-case description.
  • the redundant index brought.
  • Step S105 Acquire a target legal provision of the target judgment document collection.
  • the court has three legal provisions for the judgment of the case, namely Article 2 of the Labor Law of the People's Republic of China, Article 50 of the Labor Law of the People's Republic of China and Article 31 of the Labor Contract Law of the People's Republic of China finally submitted the judgment result to the case.
  • the legal text information contains the words "Article*" and "*" is a number.
  • the search method of the legal provision obtaineds a search keyword in the search query text; acquires a legal word that is similar to and/or the same as the search keyword; and has similar and/or the same meaning according to the search keyword.
  • the legal words expand the search query text to obtain the expanded search query text; search according to the expanded search query text, obtain the target judgment document collection; and obtain the target legal provisions of the target judgment document collection, and solve the related technology According to the input search term, it is difficult to obtain the relevant legal provisions.
  • the search query text is used to obtain the target judgment document collection, and then the target legal provisions of the target judgment document collection are obtained, that is, the search query text and the law are established through the target judgment document collection.
  • the link between the provisions achieves the effect of being able to obtain legal provisions related to the input search query text.
  • FIG. 2 is a flow chart of a search method of a legal provision according to a second embodiment of the present application.
  • Figure 2 can be taken as a preferred embodiment of the embodiment shown in Figure 1.
  • the method includes the following steps:
  • Step S201 Acquire a search keyword in the search query text.
  • step S101 of the first embodiment of the present application is the same as step S101 of the first embodiment of the present application, and details are not described herein again.
  • Step S202 obtaining legal words that are similar to and/or identical to the meaning of the search keyword.
  • step S102 is the same as step S102 of the first embodiment of the present application, and details are not described herein again.
  • Step S203 the search query text is expanded according to the legal words whose search keywords have similar meanings and/or the same, and the expanded search query text is obtained.
  • step S103 is the same as step S103 of the first embodiment of the present application, and details are not described herein again.
  • Step S204 performing a search according to the expanded search query text, and obtaining a target judgment document collection.
  • step S104 is the same as step S104 of the first embodiment of the present application, and details are not described herein again.
  • Step S205 performing segmentation analysis on each target judgment document in the target judgment document collection to obtain the target Candidates for the collection of referee documents.
  • the target judgment document collection is segmented according to the structure of the judgment document. Then, the legal law section is determined in the target judgment document collection of the paragraphs. Finally, the legal law section of the target judgment document collection is extracted, and the legal provisions of the target judgment document collection are obtained, in the second embodiment of the present application.
  • the Central Committee used it as a candidate for legal provisions.
  • the second embodiment of the present application does not limit the implementation manner of the information extraction method, which is the same as the information extraction method of step S105 in the first embodiment of the present application.
  • Step S206 screening the candidate legal provisions of the target judgment document collection to obtain the candidate legal provisions after screening.
  • the target judgment document collection includes multiple target judgment documents, and candidate legal provisions obtained after extracting information on all target judgment documents, so there is a high possibility that there are duplicate legal provisions in the candidate legal provisions. For example, enter a case description text (search query text) and get two relevant target judgment documents.
  • One of the target judgment documents is based on Article 2 of the Labor Law of the People's Republic of China in the final judgment.
  • another target judgment document is based on Article 2 of the Labor Law of the People's Republic of China and the Labor Law of the People's Republic of China.
  • step S207 the screened candidate legal provisions are taken as the target legal provisions.
  • the candidate legal provisions after the screening include a plurality of provisions, and the candidate legal provisions of the target judgment document collection are screened to obtain the candidate after screening.
  • the method further comprises: determining the weight value of each target judgment document according to the preset conditions; the statistical provisions appear in each target judgment document The number of times; sorting multiple articles according to the weight value of each target judgment document and the number of occurrences of each article in each target judgment document, and obtaining a plurality of sorted articles; determining according to the sorted multiple articles
  • the candidate legal provisions after screening are included as the target legal provisions: the target provisions are the target legal provisions.
  • the text is sorted, and the relevance of the candidate legal provisions to the input case of the parties is determined according to certain preset conditions.
  • the preset condition is a pre-set hit condition, the hit condition is predefined, and the manner of definition is not unique.
  • the degree of similarity between the searched judgment documents and the case description must be different. It can be seen that the candidate legal provisions corresponding to different target judgment documents and the case descriptions input by the parties. The degree of association is also different. Therefore, different target judgment documents need to be given different weights so that the order of the target legal provisions is related to the degree of association of the case description.
  • the implementation can be as follows:
  • the respective weight values may be expressed as w 1 , w 2 , . . . , w m , each
  • the weight value corresponding to the referee documents indicates the degree of similarity between the judgment document and the input case description.
  • the i-th legal provision is applied in the j-th sentence, or the i-th legal provision is not applied. Then, the score of the i-th legal provision (RankScore i ) in a specific case description can be expressed as:
  • the score of the i-th legal provision (RankScore i ) is the sum of the weight values of all the judging documents to which the legal provisions are applied.
  • the scores of the various legal provisions are sorted in descending order, and returned according to the current ranking or the top legal law. As for the fact that several legal provisions are taken, they can be pre-defined in the pre-set conditions.
  • the search method of the legal provision obtaineds a search keyword in the search query text; acquires a legal word that is similar to and/or the same as the search keyword; and has similar and/or the same meaning according to the search keyword.
  • the legal word expands the search query text to obtain the expanded search query text; searches according to the expanded search query text to obtain the target judgment document collection; and each target in each target judgment document of the target judgment document collection.
  • the judgment documents are segmented and analyzed, and the candidate legal provisions of the target judgment document collection are obtained; the candidate legal provisions of the target judgment document collection are screened out, and the selected candidate legal provisions are obtained; and the screened candidate legal provisions are targeted Legal provisions.
  • the invention solves the problem that the related technical articles are difficult to obtain relevant legal provisions according to the input search words, thereby achieving the effect of being able to obtain the legal provisions related to the input search query text, and screening the candidate legal provisions extracted by the target judgment document collection, After the screened legal provisions, the screened candidate legal provisions are taken as the target legal provisions, achieving the effect of eliminating the information redundancy caused by the same legal provisions.
  • the embodiment of the present application further provides a search device for the legal provisions. It should be noted that the search device for the legal provisions of the embodiments of the present application can be used to execute the search method for the legal provisions provided by the embodiments of the present application. The following describes the search device for the legal provisions provided by the embodiments of the present application.
  • FIG. 3 is a schematic diagram of a search apparatus of a legal provision according to a first embodiment of the present application.
  • the apparatus includes: a first acquisition unit 10, a second acquisition unit 20, an expansion unit 30, a search unit 40, and a third acquisition unit 50.
  • the first obtaining unit 10 is configured to obtain a search keyword in the search query text.
  • the second obtaining unit 20 is configured to acquire a legal word that is similar to and/or the same as the search keyword.
  • the expansion unit 30 is configured to expand the search query text according to the legal words whose search keywords have similar meanings and/or the same, to obtain the expanded search query text.
  • the searching unit 40 is configured to perform a search according to the expanded search query text to obtain a target judgment document collection.
  • the third obtaining unit 50 is configured to obtain a target legal clause of the target judgment document collection.
  • the first acquiring unit 10, the second obtaining unit 20, the expanding unit 30, the searching unit 40, and the third obtaining unit 50 may be run in a computer terminal as part of the device, and may be in the computer terminal.
  • the processor is configured to perform the functions implemented by the above modules, and the computer terminal may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, an applause computer, and a mobile Internet device (MID), a PAD, and the like.
  • the search device of the legal provision of the referee document provided by the first embodiment of the present application acquires the search keyword in the search query text by the first obtaining unit 10; the second obtaining unit 20 obtains the similarity and/or the same meaning as the search keyword.
  • the legal unit expands the search query text according to the legal words whose search keywords have similar meanings and/or the same, and obtains the expanded search query text; the search unit 40 searches according to the expanded search query text to obtain the target referee.
  • the third acquisition unit 50 obtains the target legal provisions of the target judgment document collection, and solves the problem that the related technical articles are difficult to obtain the relevant legal provisions according to the input search words, and the third acquisition unit 50 acquires the target judgment document collection.
  • the target legal provisions in turn, achieve the effect of being able to obtain legal provisions related to the input search query text.
  • the apparatus further includes: a first creating unit, configured to establish an inverted index on the candidate refereeing document, to obtain a first inverted list, and the searching unit
  • the utility model is further configured to input the expanded search query text in the first inverted list to perform a search, and obtain a target judgment document collection.
  • the apparatus further includes: a third determining unit, configured to perform segmentation analysis on the candidate refereeing document, and determine a search segment in the candidate refereeing document, Wherein, the search segment is a paragraph describing the content of the case in the candidate referee document; and the second creating unit is configured to establish an inverted index on the search segment in the candidate referee document and the candidate referee document to obtain a second inverted table, the search unit
  • the utility model is further configured to input the expanded search query text in the second inverted list to perform a search, and obtain a target judgment document collection.
  • FIG. 4 is a schematic diagram of a search apparatus for a legal provision according to a second embodiment of the present application.
  • Figure 4 can be used as a preferred embodiment of the embodiment shown in Figure 3.
  • the device includes: a first obtaining unit 10, a second obtaining unit 20, an expanding unit 30, a searching unit 40, and a third obtaining unit 50, wherein the third obtaining unit 50 includes an obtaining module 501, screening Module 502 and determination module 503.
  • the first obtaining unit 10 is configured to obtain a search keyword in the search query text.
  • the second obtaining unit 20 is configured to acquire a legal word that is similar to and/or the same as the search keyword.
  • the expansion unit 30 is configured to expand the search query text according to the legal words whose search keywords have similar meanings and/or the same, to obtain the expanded search query text.
  • the searching unit 40 is configured to perform a search according to the expanded search query text to obtain a target judgment document collection.
  • the third obtaining unit 50 includes: an obtaining module 501, configured to perform segmentation analysis on each target referee document in the target refereeing document set, to obtain candidate legal provisions of the target refereeing document set; and a screening module 502, configured to target the referee The candidate legal provisions of the collection of documents are screened out to obtain the candidate legal provisions after screening; the determining module 503 is configured to use the screened candidate legal provisions as the target legal provisions.
  • the determining module 503 can be run in the computer terminal as part of the device, and the functions implemented by the above module can be performed by a processor in the computer terminal, and the computer terminal can also be a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer. , applause computers and mobile Internet devices (Mobile Internet Devices, MID), PAD and other terminal devices.
  • the search device of the legal provision of the referee document provided by the second embodiment of the present application acquires the search keyword in the search query text by the first obtaining unit 10; the second obtaining unit 20 obtains the similarity and/or the same meaning as the search keyword.
  • the legal unit expands the search query text according to the legal words whose search keywords have similar meanings and/or the same, and obtains the expanded search query text; the search unit 40 searches according to the expanded search query text to obtain the target.
  • the obtaining module 501 performs segmentation analysis on each target judgment document in the target judgment document collection to obtain candidate legal provisions of the target judgment document collection; the screening module 502 screens out candidate legal provisions of the target judgment document collection to obtain screening In addition to the candidate legal provisions; the determining module 503 regards the screened candidate legal provisions as the target legal provisions, and achieves the effect of eliminating information redundancy caused by the same legal provisions.
  • the filtered candidate legal clause includes a plurality of provisions
  • the apparatus further includes: a first determining unit, configured to determine, according to the preset condition, each The weight value of the target judgment document; the statistical unit is used to count the number of occurrences of each clause in each target judgment document; the ranking unit is used to calculate the weight value of each target judgment document and each article in each target
  • the number of occurrences in the judgment document sorts a plurality of clauses to obtain a plurality of sorted clauses; the second determining unit is configured to determine a target clause returned to the target address according to the sorted plurality of clauses, and the determining module is further used for Use the target provisions as the target legal provisions.
  • the various functional units provided by the embodiments of the present application may be operated in a mobile terminal, a computer terminal, or the like, or may be stored as part of a storage medium.
  • embodiments of the present invention may provide a computer terminal, which may be any computer terminal device in a group of computer terminals.
  • a computer terminal may also be replaced with a terminal device such as a mobile terminal.
  • the computer terminal may be located in at least one network device of the plurality of network devices of the computer network.
  • the computer terminal may execute the program code of the following steps in the search method of the legal provision: acquiring the search keyword in the search query text; acquiring legal words having similar meanings and/or the same as the search keyword; Key words with similar meanings and/or the same legal words expand the search query text to obtain the expanded search query text; search according to the expanded search query text to obtain the target judgment document collection; and obtain the target of the target judgment document collection Legal provisions.
  • the computer terminal can include: one or more processors, memory, and transmission means.
  • the memory can be used to store software programs and modules, such as the search method of the legal provisions in the embodiments of the present invention and the program instructions/modules corresponding to the devices, and the processor executes various programs by running software programs and modules stored in the memory. Functional application and data processing, that is, the search method for implementing the above-mentioned legal provisions. Save
  • the memory may include a high speed random access memory and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory.
  • the memory can further include memory remotely located relative to the processor, which can be connected to the terminal over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the above transmission device is for receiving or transmitting data via a network.
  • Specific examples of the above network may include a wired network and a wireless network.
  • the transmission device includes a Network Interface Controller (NIC) that can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network.
  • the transmission device is a Radio Frequency (RF) module for communicating with the Internet wirelessly.
  • NIC Network Interface Controller
  • RF Radio Frequency
  • the memory is used to store preset action conditions and information of the preset rights user, and an application.
  • the processor can call the memory stored information and the application by the transmitting device to execute the program code of the method steps of each of the alternative or preferred embodiments of the above method embodiments.
  • the computer terminal can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, an applause computer, and a mobile Internet device (MID), a PAD, and the like.
  • a smart phone such as an Android phone, an iOS phone, etc.
  • a tablet computer such as an iPad, Samsung Galaxy Tab, Samsung Galaxy Tab, etc.
  • MID mobile Internet device
  • PAD PAD
  • Embodiments of the present invention also provide a storage medium.
  • the foregoing storage medium may be used to save the program code executed by the search method of the legal provisions provided by the foregoing method embodiment and the device embodiment.
  • the foregoing storage medium may be located in any one of the computer terminal groups in the computer network, or in any one of the mobile terminal groups.
  • the storage medium is configured to store program code for performing the following steps: acquiring a search keyword in the search query text; acquiring a legal word that is similar to and/or identical to the search keyword; Expand the search query text according to the legal words with similar meanings and/or the same meaning of the search keywords, and obtain the expanded Searching for the query text; searching according to the expanded search query text, obtaining the target judgment document collection; and obtaining the target legal provisions of the target judgment document collection.
  • the storage medium may also be configured as program code for storing various preferred or optional method steps provided by the search method of the legal provision.
  • the search device of the legal provision includes a processor and a memory, and the first acquiring unit, the second obtaining unit, the expanding unit, the searching unit, and the third obtaining unit are all stored as a program unit in a memory, and are executed by the processor.
  • the above program units in the memory implement the corresponding functions.
  • the processor contains a kernel, and the kernel removes the corresponding program unit from the memory.
  • the kernel can be set to one or more, and the search for legal provisions can be achieved by adjusting the kernel parameters.
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory (flash RAM), the memory including at least one Memory chip.
  • RAM random access memory
  • ROM read only memory
  • flash RAM flash memory
  • the present application also provides a computer program product, when executed on a data processing device, adapted to perform program code initialization with the following method steps: obtaining a search keyword in a search query text; obtaining a meaning with the search keyword Similar and/or identical legal words; expanding the search query text according to legal words with similar meanings and/or the same as the search keyword, to obtain an expanded search query text; according to the expanded search query text Performing a search to obtain a target judgment document collection; and obtaining a target legal provision of the target judgment document collection.
  • the disclosed device may be through other parties.
  • the device embodiments described above are merely illustrative.
  • the division of cells is only a logical function division.
  • multiple units or components may be combined or may be integrated into Another system, or some features can be ignored or not executed.
  • the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • modules or steps of the present application can be implemented by a general computing device, which can be concentrated on a single computing device or distributed in a network composed of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device, such that they may be stored in a storage device by a computing device, or they may be fabricated into individual integrated circuit modules, or Multiple modules or steps are made into a single integrated circuit module. Thus, the application is not limited to any particular combination of hardware and software.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Computational Linguistics (AREA)
  • Tourism & Hospitality (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Primary Health Care (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Technology Law (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种法律条文的搜索方法及装置。该方法包括：获取搜索查询文本中的搜索关键词(S101)；获取与搜索关键词含义相近和/或相同的法律词(S102)；根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本(S103)；根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合(S104)；以及获取目标裁判文书集合的目标法律条文(S105)。通过本方法，解决了相关技术中根据输入的搜索词难以获取相关的法律条文的问题。

Description

法律条文的搜索方法及装置 技术领域
本申请涉及信息搜索领域，具体而言，涉及一种法律条文的搜索方法及装置。
背景技术
法律条文，是指现行有效的法律、行政法规、司法解释、地方法规、地方规章、部门规章及其他规范性文件以及对于该等法律法规的不时修改和补充。广义上讲，法律泛指一切规范性文件。裁判文书记载着人民法院审理过程和结果，是诉讼活动结果的载体，也是人民法院确定和分配当事人实体权利义务的惟一凭证。裁判文书，既是当事人享有权利和负担义务的凭证，也是上级人民法院监督下级人民法院民事审判活动的重要依据。一份结构完整、要素齐全、逻辑严谨的裁判文书，应当包括该纠纷案件的案情描述，原告与被告当事人及其委托人的信息，以及法院对案件实施判决所依据的法律条文等。当今，法律工作者在诉讼案件中经常需要寻找与当前正在处理的案情相似的法律法规。对普通人而言，在遇到纠纷时，也希望能够寻找到类似其遭遇的法律法规作为法律认定的参考。因此，可以通过输入包括案情描述信息在内搜索查询文本，得到与输入的文本相关的生效判决的裁判文书，并由此得到法院对案件实施判决依据的法律条文。然而当前法律法规的搜索过程中，当前的搜索引擎主要是针对基于案情输入的搜索文本进行字词的拆分和匹配。例如，基于案情输入的搜索词为飙车，并不足以对法律条文进行搜索，因此很难搜索到与案情描述相关的法律条文。
针对相关技术中根据输入的搜索词难以获取相关的法律条文的问题，目前尚未提出有效的解决方案。
发明内容
本申请的主要目的在于提供一种法律条文的搜索方法及装置，以解决相关技术中根据输入的搜索词难以获取相关的法律条文的问题。
为了实现上述目的，根据本申请的一个方面，提供了一种法律条文的搜索方法。该方法包括：获取搜索查询文本中的搜索关键词；获取与搜索关键词含义相近和/或相同的法律词；根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本；根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及获取目标裁判文书集合的目标法律条文。
进一步地，获取目标裁判文书集合的目标法律条文包括：对目标裁判文书集合中的每份目标裁判文书进行分段解析，获取目标裁判文书集合的候选法律条文；对目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文；以及将筛除后的候选法律条文作为目标法律条文。
进一步地，筛除后的候选法律条文包括多条条文，在对目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文之后，在将筛除后的候选法律条文作为目标法律条文之前，该方法还包括：根据预设条件确定每份目标裁判文书的权重值；统计各条条文在每份目标裁判文书中出现的次数；根据每份目标裁判文书的权重值和各条条文在每份目标裁判文书中出现的次数对多条条文进行排序，得到排序后的多条条文；根据排序后的多条条文，确定返回至目标地址的目标条文，将筛除后的候选法律条文作为目标法律条文包括：将目标条文作为目标法律条文。
进一步地，在根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合之前，该方法还包括：对候选裁判文书建立倒排索引，得到第一倒排表，根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合包括：在第一倒排表中输入扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
进一步地，在根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合之前，该方法还包括：对候选裁判文书进行分段解析，确定候选裁判文书中的搜索段，其中，搜索段是候选裁判文书中对案情内容进行描述的段落；对候选裁判文书和候选裁判文书中的搜索段建立倒排索引，得到第二倒排表，根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合包括：在第二倒排表中输入扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
为了实现上述目的，根据本申请的另一方面，提供了一种法律条文的搜索装置。该装置包括：第一获取单元，用于获取搜索查询文本中的搜索关键词；第二获取单元，用于获取与搜索关键词含义相近和/或相同的法律词；扩充单元，用于根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本；搜索单元，用于根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及第三获取单元，用于获取目标裁判文书集合的目标法律条文。
进一步地，第三获取单元包括：获取模块，用于对目标裁判文书集合中的每份目标裁判文书进行分段解析，获取目标裁判文书集合的候选法律条文；筛除模块，用于对目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文；以及确定模块，用于将筛除后的候选法律条文作为目标法律条文。
进一步地，筛除后的候选法律条文包括多条条文，该装置还包括：第一确定单元， 用于根据预设条件确定每份目标裁判文书的权重值；统计单元，用于统计各条条文在每份目标裁判文书中出现的次数；排序单元，用于根据每份目标裁判文书的权重值和各条条文在每份目标裁判文书中出现的次数对多条条文进行排序，得到排序后的多条条文；第二确定单元，用于根据排序后的多条条文，确定返回至目标地址的目标条文，确定模块还用于将目标条文作为目标法律条文。
进一步地，该装置还包括：第一创建单元，用于对候选裁判文书建立倒排索引，得到第一倒排表，搜索单元还用于在第一倒排表中输入扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
进一步地，该装置还包括：第三确定单元，用于对候选裁判文书进行分段解析，确定候选裁判文书中的搜索段，其中，搜索段是候选裁判文书中对案情内容进行描述的段落；第二创建单元，用于对候选裁判文书和候选裁判文书中的搜索段建立倒排索引，得到第二倒排表，搜索单元还用于在第二倒排表中输入扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
通过本申请，采用以下步骤：获取搜索查询文本中的搜索关键词；获取与搜索关键词含义相近和/或相同的法律词；根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本；根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及获取目标裁判文书集合的目标法律条文，解决了相关技术中根据输入的搜索词难以获取相关的法律条文的问题，首先通过搜索查询文本获取到目标裁判文书集合，再获取目标裁判文书集合的目标法律条文，即通过目标裁判文书集合建立了搜索查询文本与法律条文之间的联系，进而达到能够获取与输入的搜索查询文本相关的法律条文的效果。
附图说明
构成本申请的一部分的附图用来提供对本申请的进一步理解，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是根据本申请第一实施例的法律条文的搜索方法的流程图；
图2是根据本申请第二实施例的法律条文的搜索方法的流程图；
图3是根据本申请第一实施例的法律条文的搜索装置的示意图；以及
图4是根据本申请第二实施例的法律条文的搜索装置的示意图。
具体实施方式
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
根据本申请的实施例，提供了一种法律条文的搜索方法。
图1是根据本申请第一实施例的法律条文的搜索方法的流程图。如图1所示，该方法包括以下步骤：
步骤S101，获取搜索查询文本中的搜索关键词。
本申请第一实施例中的搜索查询文本即是在当事人需要获得生效判决的裁判文书作为处理纠纷的参考时，基于纠纷案情输入的文本。例如，当事人基于正在处理的纠纷案情输入的搜索查询文本为：一车正在飙车时，撞上正常行驶的客车，相关补偿事宜。当事人通过输入搜索查询文本希望获取到与输入的文本相关的生效判决的裁判文书及法院对案件实施判决依据的法律法条作为后续处理的参考。
获取搜索查询文本中的搜索关键词。例如，搜索查询文本为：一车正在飙车时，撞上正常行驶的客车，相关补偿事宜。获取到搜索查询文本中的搜索关键词为“飙车”、“补偿”。
步骤S102，获取与搜索关键词含义相近和/或相同的法律词。
所谓法律词是指在司法领域有专门或特定意义的词或词组，例如“追逐竞驶”一词，是法律文献中的标准用语，但通常而言，就是“飙车”的意思。
例如，上述步骤S101获取到的搜索关键词为“飙车”、“补偿”。获取与“飙车”含义相近和/或相同的法律词为“追逐竞驶”，获取与“补偿”含义相近和/或相同的法律词为“赔偿”。
步骤S103，根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本。
根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，例如，根据“飙车”含义相近或同义的“追逐竞驶”，“补偿”含义相近和/或相同的法律词“赔偿”对搜索查询文本“一车正在飙车时，撞上正常行驶的客车，相关补偿事宜”进行扩充，得到扩充后的搜索查询文本为：“一车正在飙车时，撞上正常行驶的客车，相关补偿事宜”，“追逐竞驶”，“赔偿”。
步骤S104，根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
目标裁判文书集合包括与扩充后的查询文本匹配的所有目标裁判文书集合，可以包含一份以上目标裁判文书集合，也可以为空。
通过上述步骤，根据与搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充后，在更大的范围内对裁判文书进行搜索，从而得到更丰富的搜索结果即返回更多的目标裁判文书集合。当输入的搜索关键词不是法律词时，也可以通过扩充对其进行弥补，因此搜索到符合需求的目标裁判文书集合，提高了目标裁判文书集合的召回率。
可选地，在根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合之前，本申请第一实施例提供的法律条文的搜索方法还包括：对候选裁判文书建立倒排索引，得到第一倒排表，根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合包括：在第一倒排表中输入扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
倒排索引，即实际应用中根据属性的值来查找记录。倒排索引的原理如下：
采用分词器对输入的源数据库中每个文档执行分词处理，将每个文档中提取出的关键词与该文档建立链接；当输入要查询的关键词后，便可反向的列出所有包含该关键词的文档，省去了在每个文档中顺序地寻找关键词的过程，即通过建立倒排索引表达到了由部分属性查找数据来源的目的。
倒排索引的具体实现方式可以是业内比较成熟的全文搜索引擎框架(Lucene)，也可以是基于Lucene开发的企业级搜索应用服务器(Solr)或全文搜索引擎(Elasticsearch)。除此之外，也可以开发一套满足需求的搜索引擎。至于究竟采用何种倒排索引方式，在实际情况中可以根据具体问题而定，本申请第一实施例不限定其 实现方式。
此步骤对每个候选裁判文书的全文建立倒排索引，输入搜索查询文本后，使用与倒排索引采用的搜索引擎中相同的分词器对搜索查询文本进行分词，分词后得到一个或多个关键词，查询倒排表，返回对应的目标裁判文书集合。
可选地，本申请第一实施例提供的法律条文的搜索方法，在根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合之前，该方法还包括：对候选裁判文书进行分段解析，确定候选裁判文书中的搜索段，其中，搜索段是候选裁判文书中对案情内容进行描述的段落；对候选裁判文书和候选裁判文书中的搜索段建立倒排索引，得到第二倒排表，根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合包括：在第二倒排表中输入扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
一般而言，裁判文书具有一定格式，即需要在特定段落中描述案件相关的各种要素。例如，在裁判文书开始，需要写明原告当事人信息及其委托人信息，然后写明被告当事人信息及其委托人信息等。因此，可以通过对候选裁判文书中特定信息的捕捉，将候选裁判文书的各个段落进行分段。再如，在原告诉称段落中，主要记录原告在状告被告时所陈述的主观事实；另外在经审理查明段落中，主要记录了法院在综合原告与被告的陈述之后，结合原告与被告双方举证最终认定的事实。裁判文书中的案情描述段落，如原告诉称段落与经审理查明段落(搜索段)等，可以作为案情内容关键词的倒排索引目标裁判文书集合。
相对于对候选裁判文书的全文进行分词，对每个候选裁判文书的各个案情描述段落建立倒排索引，能够减少倒排表的存储空间，同时也减轻了非案情描述相关的段落中含有关键词带来的冗余索引。
步骤S105，获取目标裁判文书集合的目标法律条文。
分好段落的裁判文书中，有一个段落描述的是法院对案件实施判决的法律依据，通常称之为法律法条段。法律法条段包含有法院具体使用了哪些法律法条作为判决依据的信息。例如，一篇裁判文书中法律法条段的摘要如下：
“综上所述，依据《中华人民共和国劳动法》第二条、第五十条，《中华人民共和国劳动合同法》第三十一条之规定，判决如下：”
通过该裁判文书中法律法条段的摘要可知，法院对该案件的判决依据有三条法律条文，即《中华人民共和国劳动法》第二条，《中华人民共和国劳动法》第五十条和《中华人民共和国劳动合同法》第三十一条，最终对案件提出了判决结果。通常，法律条文信息含有“第*条”的字样，且“*”为数字。
在分好段落的裁判文书中，需要对裁判文书的法律法条段进行信息抽取，得到法律条文。信息抽取的方式有多种，例如通过正则表达式搜索，或基于有限状态机的规则匹配的方法等搜索方式。其实质是当裁判文书满足了一定的预设条件时，如本实施例中的预设条件为“第*条”，系统会按照预设规则返回相应的信息，如本实施例中的预设规则为，将“第*条”及其前文中距“第*条”最近的书名号(《》)中的全部内容组合为“《》第*条”的格式，作为搜索的返回信息。至于究竟采用何种信息抽取方式，在实际情况中可以根据具体问题而定，本申请第一实施例不限定其实现方式。
将所有裁判文书与各个裁判文书通过信息抽取得到的所有法律条文建立链接。对裁判文书进行分段、信息抽取与建立链接的处理后，当指定一篇裁判文书时，就可以得到法院在该裁判文书中作为判决依据的法律条文。
本申请第一实施例提供的法律条文的搜索方法，通过获取搜索查询文本中的搜索关键词；获取与搜索关键词含义相近和/或相同的法律词；根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本；根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及获取目标裁判文书集合的目标法律条文，解决了相关技术中根据输入的搜索词难以获取相关的法律条文的问题，首先通过搜索查询文本获取到目标裁判文书集合，再获取目标裁判文书集合的目标法律条文，即通过目标裁判文书集合建立了搜索查询文本与法律条文之间的联系，进而达到能够获取与输入的搜索查询文本相关的法律条文的效果。
图2是根据本申请第二实施例的法律条文的搜索方法的流程图。图2可以作为图1所示实施例的一种优选实施方式。如图2所示，该方法包括如下的步骤：
步骤S201，获取搜索查询文本中的搜索关键词。
此步骤与本申请第一实施例的步骤S101相同，在此不再赘述。
步骤S202，获取与搜索关键词含义相近和/或相同的法律词。
此步骤与本申请第一实施例的步骤S102相同，在此不再赘述。
步骤S203，根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本。
此步骤与本申请第一实施例的步骤S103相同，在此不再赘述。
步骤S204，根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
此步骤与本申请第一实施例的步骤S104相同，在此不再赘述。
步骤S205，对目标裁判文书集合中的每份目标裁判文书进行分段解析，获取目标 裁判文书集合的候选法律条文。
首先，在得到目标裁判文书集合后，按照裁判文书的结构对目标裁判文书集合进行分段。然后，在分好段落的目标裁判文书集合确定出法律法条段，最后，对目标裁判文书集合的法律法条段进行信息抽取，得到目标裁判文书集合的法律条文，在本申请第二实施例中将其作为候选法律条文。与本申请第一实施例中步骤S105的信息抽取方法相同，本申请第二实施例不限定信息抽取方法的实现方式。
步骤S206，对目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文。
其中，目标裁判文书集合包括多份目标裁判文书，对所有目标裁判文书进行信息抽取后得到的候选法律条文，因此在候选法律条文中极有可能会存在重复的法律条文。例如，输入一条案情描述文本(搜索查询文本)，得到两份相关的目标裁判文书，其中一份目标裁判文书在最终判决时依据了《中华人民共和国劳动法》第二条，《中华人民共和国劳动法》第五十条和《中华人民共和国劳动合同法》第三十一条，另一份目标裁判文书在最终判决时依据了《中华人民共和国劳动法》第二条和《中华人民共和国劳动法》第三十九条，那么在对目标裁判文书进行信息抽取后会显示两条“《中华人民共和国劳动法》第二条”信息，而这两条信息是相同的，因此需要对这两条相同的法律条文信息进行筛除，只保留一条“《中华人民共和国劳动法》第二条”信息，即可以消除相同法律条文造成的信息冗余。
步骤S207，将筛除后的候选法律条文作为目标法律条文。
当事人想要查询类似的纠纷案件采用了哪些法律条文，在输入案情描述(搜索查询文本)后，经过对输入信息的扩充得到所有目标裁判文书。对所有目标裁判文书抽取所有的候选法律条文进行筛除，筛除后的候选法律条文中，每一条候选法律条文只出现一次，因此可以将筛除后的候选法律条文作为目标法律条文，供当事人参考。
可选地，本申请第二实施例提供的法律条文的搜索方法，筛除后的候选法律条文包括多条条文，在对目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文之后，在将筛除后的候选法律条文作为目标法律条文之前，该方法还包括：根据预设条件确定每份目标裁判文书的权重值；统计各条条文在每份目标裁判文书中出现的次数；根据每份目标裁判文书的权重值和各条条文在每份目标裁判文书中出现的次数对多条条文进行排序，得到排序后的多条条文；根据排序后的多条条文，确定返回至目标地址的目标条文，将筛除后的候选法律条文作为目标法律条文包括：将目标条文作为目标法律条文。
在将筛除后的候选法律条文作为目标法律条文之前，可以对筛除后的候选法律条 文进行排序，按照一定的预设条件确定候选法律条文对当事人输入案情的相关度。该预设条件是预先设置的命中条件，预先定义该命中条件，并且定义的方式并不唯一。通过案情描述搜索与该案情相似的裁判文书时，搜索到的裁判文书与案情描述的相似程度必然有所不同，由此可知，不同的目标裁判文书对应的候选法律条文与当事人输入的案情描述的关联程度也不同，因此，需要赋予不同的目标裁判文书以不同的权重，以使目标法律条文的排序与该案情描述的关联程度相关。例如，实现方式可以如下：
若输入的案情描述匹配到了m个裁判文书，并且根据预设条件分别赋予了该m个裁判文书各自的权重值，其各自的权重值可以表示为w1，w2，…，wm，每个裁判文书对应的权重值表示该裁判文书与输入的案情描述的相似程度。该m个裁判文书经过分段解析与筛除后得到了n个候选的法律条文，并且第j篇裁判文书中应用了第i个法律条文的条件满足yij，
Figure PCTCN2016107311-appb-000001
也即，第j篇裁判文书中要么应用了第i个法律条文，要么未应用第i个法律条文。那么，在特定案情描述下第i个法律条文的得分(RankScorei)可以表示为：
Figure PCTCN2016107311-appb-000002
也即，第i个法律条文的得分(RankScorei)是所有应用了该法律条文的裁判文书的权重值之和。最后，对各个法律条文的得分进行降序排列，按照当前排列返回或取排名靠前的法律法条进行返回。至于究竟取几条法律条文，可以在预设条件中预先定义。
本申请第二实施例提供的法律条文的搜索方法，通过获取搜索查询文本中的搜索关键词；获取与搜索关键词含义相近和/或相同的法律词；根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本；根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；对目标裁判文书集合的每份目标裁判文书中的每份目标裁判文书进行分段解析，获取目标裁判文书集合的候选法律条文；对目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文；以及将筛除后的候选法律条文作为目标法律条文。解决了相关技术中根据输入的搜索词难以获取相关的法律条文的问题，进而达到能够获取与输入的搜索查询文本相关的法律条文的效果，通过筛除目标裁判文书集合抽取出的候选法律条文，得到筛除后的法律条文，将筛除后的候选法律条文作为目标法律条文，达到了消除相同法律条文造成的信息冗余的效果。
需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的 计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
本申请实施例还提供了一种法律条文的搜索装置，需要说明的是，本申请实施例的法律条文的搜索装置可以用于执行本申请实施例所提供的用于法律条文的搜索方法。以下对本申请实施例提供的法律条文的搜索装置进行介绍。
图3是根据本申请第一实施例的法律条文的搜索装置的示意图。如图3所示，该装置包括：第一获取单元10、第二获取单元20、扩充单元30、搜索单元40和第三获取单元50。
第一获取单元10，用于获取搜索查询文本中的搜索关键词。
第二获取单元20，用于获取与搜索关键词含义相近和/或相同的法律词。
扩充单元30，用于根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本。
搜索单元40，用于根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
第三获取单元50，用于获取目标裁判文书集合的目标法律条文。
此处需要说明的是，上述第一获取单元10、第二获取单元20、扩充单元30、搜索单元40和第三获取单元50可以作为装置的一部分运行在计算机终端中，可以通过计算机终端中的处理器来执行上述模块实现的功能，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
本申请第一实施例提供的裁判文书的法律条文的搜索装置，通过第一获取单元10获取搜索查询文本中的搜索关键词；第二获取单元20获取与搜索关键词含义相近和/或相同的法律词；扩充单元30根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本；搜索单元40根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及第三获取单元50获取目标裁判文书集合的目标法律条文，解决了相关技术中根据输入的搜索词难以获取相关的法律条文的问题，通过第三获取单元50获取目标裁判文书集合的目标法律条文，进而达到能够获取与输入的搜索查询文本相关的法律条文的效果。
可选地，在本申请第一实施例提供的法律条文的搜索装置中，该装置还包括：第一创建单元，用于对候选裁判文书建立倒排索引，得到第一倒排表，搜索单元还用于在第一倒排表中输入扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
可选地，在本申请第一实施例提供的法律条文的搜索装置中，该装置还包括：第三确定单元，用于对候选裁判文书进行分段解析，确定候选裁判文书中的搜索段，其中，搜索段是候选裁判文书中对案情内容进行描述的段落；第二创建单元，用于对候选裁判文书和候选裁判文书中的搜索段建立倒排索引，得到第二倒排表，搜索单元还用于在第二倒排表中输入扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
图4是根据本申请第二实施例的法律条文的搜索装置的示意图。图4可以作为图3所示实施例的一种优选实施方式。如图4所示，该装置包括：第一获取单元10、第二获取单元20、扩充单元30、搜索单元40和第三获取单元50，其中，第三获取单元50包括获取模块501、筛除模块502和确定模块503。
第一获取单元10，用于获取搜索查询文本中的搜索关键词。
第二获取单元20，用于获取与搜索关键词含义相近和/或相同的法律词。
扩充单元30，用于根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本。
搜索单元40，用于根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
第三获取单元50包括：获取模块501，用于对目标裁判文书集合中的每份目标裁判文书进行分段解析，获取目标裁判文书集合的候选法律条文；筛除模块502，用于对目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文；确定模块503，用于将筛除后的候选法律条文作为目标法律条文。
此处需要说明的是，上述第一获取单元10、第二获取单元20、扩充单元30、搜索单元40和第三获取单元50，其中，第三获取单元50包括获取模块501、筛除模块502和确定模块503可以作为装置的一部分运行在计算机终端中，可以通过计算机终端中的处理器来执行上述模块实现的功能，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
本申请实第二施例提供的裁判文书的法律条文的搜索装置，通过第一获取单元10获取搜索查询文本中的搜索关键词；第二获取单元20获取与搜索关键词含义相近和/或相同的法律词；扩充单元30根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本；搜索单元40根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；获取模块501对目标裁判文书集合中的每份目标裁判文书进行分段解析，获取目标裁判文书集合的候选法律条文；筛除模块502对目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文；确定模块 503将筛除后的候选法律条文作为目标法律条文，解决了相关技术中根据输入的搜索词难以获取相关的法律条文的问题，进而达到能够获取与输入的搜索查询文本相关的法律条文的效果，通过获取模块501对目标裁判文书集合中的每份目标裁判文书进行分段解析，获取目标裁判文书集合的候选法律条文；筛除模块502对目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文；确定模块503将筛除后的候选法律条文作为目标法律条文，达到了消除相同法律条文造成的信息冗余的效果。
可选地，在本申请第二实施例提供的法律条文的搜索装置中，筛除后的候选法律条文包括多条条文，该装置还包括：第一确定单元，用于根据预设条件确定每份目标裁判文书的权重值；统计单元，用于统计各条条文在每份目标裁判文书中出现的次数；排序单元，用于根据每份目标裁判文书的权重值和各条条文在每份目标裁判文书中出现的次数对多条条文进行排序，得到排序后的多条条文；第二确定单元，用于根据排序后的多条条文，确定返回至目标地址的目标条文，确定模块还用于将目标条文作为目标法律条文。
本申请实施例所提供的各个功能单元可以在移动终端、计算机终端或者类似的运算装置中运行，也可以作为存储介质的一部分进行存储。
由此，本发明的实施例可以提供一种计算机终端，该计算机终端可以是计算机终端群中的任意一个计算机终端设备。可选地，在本实施例中，上述计算机终端也可以替换为移动终端等终端设备。
可选地，在本实施例中，上述计算机终端可以位于计算机网络的多个网络设备中的至少一个网络设备。
在本实施例中，上述计算机终端可以执行法律条文的搜索方法中以下步骤的程序代码：获取搜索查询文本中的搜索关键词；获取与搜索关键词含义相近和/或相同的法律词；根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的搜索查询文本；根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及获取目标裁判文书集合的目标法律条文。
可选地，该计算机终端可以包括：一个或多个处理器、存储器、以及传输装置。
其中，存储器可用于存储软件程序以及模块，如本发明实施例中的法律条文的搜索方法及装置对应的程序指令/模块，处理器通过运行存储在存储器内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的法律条文的搜索方法。存 储器可包括高速随机存储器，还可以包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器可进一步包括相对于处理器远程设置的存储器，这些远程存储器可以通过网络连接至终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
上述的传输装置用于经由一个网络接收或者发送数据。上述的网络具体实例可包括有线网络及无线网络。在一个实例中，传输装置包括一个网络适配器(Network Interface Controller，NIC)，其可通过网线与其他网络设备与路由器相连从而可与互联网或局域网进行通讯。在一个实例中，传输装置为射频(Radio Frequency，RF)模块，其用于通过无线方式与互联网进行通讯。
其中，具体地，存储器用于存储预设动作条件和预设权限用户的信息、以及应用程序。
处理器可以通过传输装置调用存储器存储的信息及应用程序，以执行上述方法实施例中的各个可选或优选实施例的方法步骤的程序代码。
本领域普通技术人员可以理解，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令终端设备相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
本发明的实施例还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以用于保存上述方法实施例和装置实施例所提供的法律条文的搜索方法所执行的程序代码。
可选地，在本实施例中，上述存储介质可以位于计算机网络中计算机终端群中的任意一个计算机终端中，或者位于移动终端群中的任意一个移动终端中。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：获取搜索查询文本中的搜索关键词；获取与搜索关键词含义相近和/或相同的法律词；根据搜索关键词含义相近和/或相同的法律词对搜索查询文本进行扩充，得到扩充后的 搜索查询文本；根据扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及获取目标裁判文书集合的目标法律条文。
可选地，在本实施例中，存储介质还可以被设置为存储法律条文的搜索方法提供的各种优选地或可选的方法步骤的程序代码。
如上参照附图以示例的方式描述了根据本发明的法律条文的搜索方法及装置。但是，本领域技术人员应当理解，对于上述本发明所提出的法律条文的搜索方法及装置，还可以在不脱离本发明内容的基础上做出各种改进。因此，本发明的保护范围应当由所附的权利要求书的内容确定。
所述法律条文的搜索装置包括处理器和存储器，上述第一获取单元、第二获取单元、扩充单元、搜索单元和第三获取单元等均作为程序单元存储在存储器中，由处理器执行存储在存储器中的上述程序单元来实现相应的功能。
处理器中包含内核，由内核去存储器中调取相应的程序单元。内核可以设置一个或以上，通过调整内核参数来实现对法律条文的搜索。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。
本申请还提供了一种计算机程序产品，当在数据处理设备上执行时，适于执行初始化有如下方法步骤的程序代码：获取搜索查询文本中的搜索关键词；获取与所述搜索关键词含义相近和/或相同的法律词；根据所述搜索关键词含义相近和/或相同的法律词对所述搜索查询文本进行扩充，得到扩充后的搜索查询文本；根据所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及获取所述目标裁判文书集合的目标法律条文。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方 式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
显然，本领域的技术人员应该明白，上述的本申请的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本申请不限制于任何特定的硬件和软件结合。
以上仅为本申请的优选实施例，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种法律条文的搜索方法，其特征在于，包括：
    获取搜索查询文本中的搜索关键词；
    获取与所述搜索关键词含义相近和/或相同的法律词；
    根据所述搜索关键词含义相近和/或相同的法律词对所述搜索查询文本进行扩充，得到扩充后的搜索查询文本；
    根据所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及
    获取所述目标裁判文书集合的目标法律条文。
  2. 根据权利要求1所述的方法，其特征在于，获取所述目标裁判文书集合的目标法律条文包括：
    对所述目标裁判文书集合中的每份目标裁判文书进行分段解析，获取所述目标裁判文书集合的候选法律条文；
    对所述目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文；以及
    将所述筛除后的候选法律条文作为所述目标法律条文。
  3. 根据权利要求2所述的方法，其特征在于，所述筛除后的候选法律条文包括多条条文，在对所述目标裁判文书集合的候选法律条文进行筛除，得到筛除后的候选法律条文之后，在将所述筛除后的候选法律条文作为所述目标法律条文之前，所述方法还包括：
    根据预设条件确定所述每份目标裁判文书的权重值；
    统计各条条文在所述每份目标裁判文书中出现的次数；
    根据所述每份目标裁判文书的权重值和所述各条条文在所述每份目标裁判文书中出现的次数对所述多条条文进行排序，得到排序后的多条条文；
    根据所述排序后的多条条文，确定返回至目标地址的目标条文，
    将所述筛除后的候选法律条文作为所述目标法律条文包括：
    将所述目标条文作为所述目标法律条文。
  4. 根据权利要求1所述的方法，其特征在于，
    在根据所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合之前， 所述方法还包括：
    对候选裁判文书建立倒排索引，得到第一倒排表，
    根据所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合包括：
    在所述第一倒排表中输入所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
  5. 根据权利要求1所述的方法，其特征在于，
    在根据所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合之前，所述方法还包括：
    对候选裁判文书进行分段解析，确定所述候选裁判文书中的搜索段，其中，所述搜索段是所述候选裁判文书中对案情内容进行描述的段落；
    对所述候选裁判文书和所述候选裁判文书中的搜索段建立倒排索引，得到第二倒排表，
    根据所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合包括：
    在所述第二倒排表中输入所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
  6. 一种法律条文的搜索装置，其特征在于，包括：
    第一获取单元，用于获取搜索查询文本中的搜索关键词；
    第二获取单元，用于获取与所述搜索关键词含义相近和/或相同的法律词；
    扩充单元，用于根据所述搜索关键词含义相近和/或相同的法律词对所述搜索查询文本进行扩充，得到扩充后的搜索查询文本；
    搜索单元，用于根据所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合；以及
    第三获取单元，用于获取所述目标裁判文书集合的目标法律条文。
  7. 根据权利要求6所述的装置，其特征在于，所述第三获取单元包括：
    获取模块，用于对所述目标裁判文书集合中的每份目标裁判文书进行分段解析，获取所述目标裁判文书集合的候选法律条文；
    筛除模块，用于对所述目标裁判文书集合的候选法律条文进行筛除，得到筛 除后的候选法律条文；以及
    确定模块，用于将所述筛除后的候选法律条文作为所述目标法律条文。
  8. 根据权利要求7所述的装置，其特征在于，所述筛除后的候选法律条文包括多条条文，所述装置还包括：
    第一确定单元，用于根据预设条件确定所述每份目标裁判文书的权重值；
    统计单元，用于统计各条条文在所述每份目标裁判文书中出现的次数；
    排序单元，用于根据所述每份目标裁判文书的权重值和所述各条条文在所述每份目标裁判文书中出现的次数对所述多条条文进行排序，得到排序后的多条条文；
    第二确定单元，用于根据所述排序后的多条条文，确定返回至目标地址的目标条文，
    所述确定模块还用于将所述目标条文作为所述目标法律条文。
  9. 根据权利要求6所述的装置，其特征在于，所述装置还包括：
    第一创建单元，用于对候选裁判文书建立倒排索引，得到第一倒排表，
    所述搜索单元还用于在所述第一倒排表中输入所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
  10. 根据权利要求6所述的装置，其特征在于，所述装置还包括：
    第三确定单元，用于对候选裁判文书进行分段解析，确定所述候选裁判文书中的搜索段，其中，所述搜索段是所述候选裁判文书中对案情内容进行描述的段落；
    第二创建单元，用于对所述候选裁判文书和所述候选裁判文书中的搜索段建立倒排索引，得到第二倒排表，
    所述搜索单元还用于在所述第二倒排表中输入所述扩充后的搜索查询文本进行搜索，得到目标裁判文书集合。
PCT/CN2016/107311 2015-12-01 2016-11-25 法律条文的搜索方法及装置 WO2017092622A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/774,928 US20180246955A1 (en) 2015-12-01 2016-11-25 Method and device for searching legal provision

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510869254.1A CN106815263B (zh) 2015-12-01 2015-12-01 法律条文的搜索方法及装置
CN201510869254.1 2015-12-01

Publications (1)

Publication Number Publication Date
WO2017092622A1 true WO2017092622A1 (zh) 2017-06-08

Family

ID=58796297

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/107311 WO2017092622A1 (zh) 2015-12-01 2016-11-25 法律条文的搜索方法及装置

Country Status (3)

Country Link
US (1) US20180246955A1 (zh)
CN (1) CN106815263B (zh)
WO (1) WO2017092622A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110647504A (zh) * 2018-06-25 2020-01-03 阿里巴巴集团控股有限公司 司法文书的检索方法及装置

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108549697A (zh) * 2018-04-16 2018-09-18 北京百度网讯科技有限公司 基于语义关联的信息推送方法、装置、设备以及存储介质
CN108573057A (zh) * 2018-04-25 2018-09-25 王慧 一种法律文书与法律法规对应性检索方法
CN109213925B (zh) * 2018-07-10 2021-08-31 深圳价值在线信息科技股份有限公司 法律文本搜索方法
CN111026836A (zh) * 2018-09-21 2020-04-17 北京国双科技有限公司 一种法律法规检索方法和装置
CN110968689A (zh) * 2018-09-30 2020-04-07 北京国双科技有限公司 罪名及法条预测模型的训练方法以及罪名及法条预测方法
CN109241505A (zh) * 2018-10-09 2019-01-18 北京奔影网络科技有限公司 文本去重方法及装置
CN111291152A (zh) * 2018-12-07 2020-06-16 北大方正集团有限公司 案例文书的推荐方法、装置、设备及存储介质
CN109783640A (zh) * 2018-12-20 2019-05-21 广州恒巨信息科技有限公司 一种类案推荐方法、系统及装置
CN110532229B (zh) * 2019-06-14 2023-06-20 平安科技（深圳）有限公司 证据文件检索方法、装置、计算机设备和存储介质
CN112559674A (zh) * 2019-09-25 2021-03-26 北京国双科技有限公司 裁判文书中法条内容的查询方法及相关装置
CN110851584B (zh) * 2019-11-13 2023-12-15 成都华律网络服务有限公司 一种法律条文精准推荐系统和方法
CN111178072A (zh) * 2019-12-31 2020-05-19 北京明略软件系统有限公司 一种法律条文的确定方法、装置及存储介质
CN111737302A (zh) * 2020-06-23 2020-10-02 中国银行股份有限公司 关键点信息查询方法及装置
CN112579743A (zh) * 2020-12-25 2021-03-30 深圳市英威腾电气股份有限公司 一种说明书内容查询方法、装置、电子设备及存储介质
CN113377906B (zh) * 2021-06-08 2022-11-01 四川大学 一种相似法条智能搜索系统及方法
CN114757267A (zh) * 2022-03-25 2022-07-15 北京爱奇艺科技有限公司 识别噪声query的方法、装置、电子设备和可读存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101145153A (zh) * 2006-09-13 2008-03-19 阿里巴巴公司 一种搜索信息的方法及系统
US20080270384A1 (en) * 2007-04-28 2008-10-30 Raymond Lee Shu Tak System and method for intelligent ontology based knowledge search engine
CN103425742A (zh) * 2013-07-16 2013-12-04 北京中科汇联信息技术有限公司 一种网站的搜索方法和装置
CN104240164A (zh) * 2014-09-29 2014-12-24 南京提坦信息科技有限公司 一种基于大数据分析的法律咨询方法及系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030065519A1 (en) * 2001-10-01 2003-04-03 Henry Gibson Method and system for generating legal agreements
US7747629B2 (en) * 2006-08-23 2010-06-29 International Business Machines Corporation System and method for positional representation of content for efficient indexing, search, retrieval, and compression
KR20160068913A (ko) * 2013-10-11 2016-06-15 노키아 솔루션스 앤드 네트웍스 오와이 사용자 포기 검증을 위한 방법, 시스템 및 장치
US20160140232A1 (en) * 2014-11-18 2016-05-19 Radialpoint Safecare Inc. System and Method of Expanding a Search Query

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101145153A (zh) * 2006-09-13 2008-03-19 阿里巴巴公司 一种搜索信息的方法及系统
US20080270384A1 (en) * 2007-04-28 2008-10-30 Raymond Lee Shu Tak System and method for intelligent ontology based knowledge search engine
CN103425742A (zh) * 2013-07-16 2013-12-04 北京中科汇联信息技术有限公司 一种网站的搜索方法和装置
CN104240164A (zh) * 2014-09-29 2014-12-24 南京提坦信息科技有限公司 一种基于大数据分析的法律咨询方法及系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110647504A (zh) * 2018-06-25 2020-01-03 阿里巴巴集团控股有限公司 司法文书的检索方法及装置
CN110647504B (zh) * 2018-06-25 2023-03-21 阿里巴巴集团控股有限公司 司法文书的检索方法及装置

Also Published As

Publication number Publication date
US20180246955A1 (en) 2018-08-30
CN106815263B (zh) 2019-04-12
CN106815263A (zh) 2017-06-09

Similar Documents

Publication Publication Date Title
WO2017092622A1 (zh) 法律条文的搜索方法及装置
CN106874279B (zh) 生成应用类别标签的方法及装置
US10423648B2 (en) Method, system, and computer readable medium for interest tag recommendation
CN106709040B (zh) 一种应用搜索方法和服务器
JP5575902B2 (ja) クエリのセマンティックパターンに基づく情報検索
CN111105209B (zh) 适用于人岗匹配推荐系统的职位简历匹配方法及装置
KR101508260B1 (ko) 문서 특징을 반영하는 요약문 생성 장치 및 방법
US10353925B2 (en) Document classification device, document classification method, and computer readable medium
CN107301171A (zh) 一种基于情感词典学习的文本情感分析方法和系统
CN104199833B (zh) 一种网络搜索词的聚类方法和聚类装置
WO2015149533A1 (zh) 一种基于网页内容分类进行分词处理的方法和装置
WO2011112236A1 (en) Categorizing products
CN102495892A (zh) 一种网页信息抽取方法
CN107943792B (zh) 一种语句分析方法、装置及终端设备、存储介质
CN106815265B (zh) 裁判文书的搜索方法及装置
CN104778283B (zh) 一种基于微博的用户职业分类方法及系统
CN106569996B (zh) 一种面向中文微博的情感倾向分析方法
CN108388556B (zh) 同类实体的挖掘方法及系统
CN110019556B (zh) 一种话题新闻获取方法、装置及其设备
CN109344232A (zh) 一种舆情信息检索方法及终端设备
CN111339778B (zh) 文本处理方法、装置、存储介质和处理器
CN108509449A (zh) 一种信息处理的方法及服务器
JP2008065468A (ja) テキスト多重分類装置、テキストを多重分類する方法、プログラムおよび記憶媒体
CN106934007B (zh) 关联信息的推送方法及装置
WO2019192122A1 (zh) 文档主题参数提取方法、产品推荐方法、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16869932

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15774928

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16869932

Country of ref document: EP

Kind code of ref document: A1