CN111026836A - Legal and legal rule retrieval method and device - Google Patents
Legal and legal rule retrieval method and device Download PDFInfo
- Publication number
- CN111026836A CN111026836A CN201811108196.0A CN201811108196A CN111026836A CN 111026836 A CN111026836 A CN 111026836A CN 201811108196 A CN201811108196 A CN 201811108196A CN 111026836 A CN111026836 A CN 111026836A
- Authority
- CN
- China
- Prior art keywords
- legal
- regulations
- laws
- retrieval
- keyword
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Engineering & Computer Science (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Technology Law (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application discloses a retrieval method of laws and regulations, which determines a first keyword corresponding to a retrieval condition; determining a second keyword matched with the first keyword in an association library, and determining a first element associated with the second keyword, wherein the keyword and the associated element are stored in the association library, and the keyword can represent the semantic characteristics of the associated element; searching a referee document related to a first element in a referee document library as a target referee document, wherein the referee document library stores the element and the referee document related to the element, and the element can represent the semantic characteristics of the referee document related to the element; and determining the legal regulation retrieval result according to the legal regulation related to the target referee document. The method constructs the incidence relation among the key words, the key elements and the referee document based on the semantic features expressed on the legal practice operation level, and retrieves the legal regulations based on the semantic incidence relation among the key words, the key elements and the referee document, thereby ensuring higher reliability of retrieval results.
Description
Technical Field
The application relates to the technical field of information search, in particular to a legal and legal retrieval method and device.
Background
In daily work and life, application scenes in which laws and regulations need to be retrieved are ubiquitous. For example, a judge needs to legally handle a relevant case by retrieving relevant laws and regulations during case handling; when dealing with the affairs entrusted by the party, the lawyer needs to provide proper legal service for the party by retrieving the relevant legal rules; when maintaining the self rights, the common citizen needs to make clear the legal rights which the citizen should enjoy by retrieving the legal rules, and the like.
The conventional legal and legal regulations retrieval method is generally implemented by using a keyword library constructed based on a term frequency-inverse text frequency (TF-IDF) algorithm, and keywords corresponding to each legal and legal regulation determined based on the TF-IDF algorithm are stored in the keyword library. When the laws and regulations are searched specifically, keywords in the search conditions are determined by word segmentation processing search conditions; and then matching the keywords in the retrieval conditions with the keywords stored in the keyword library, and finally taking the legal regulations corresponding to the matched keywords as retrieval results.
Determining a corresponding keyword according to a certain law and regulation based on a TF-IDF algorithm, wherein words which are high in occurrence frequency in the law and regulation and low in occurrence frequency in other laws and regulations are used as the corresponding keyword of the law and regulation; thus, the keywords corresponding to each law and regulation are determined according to the mode, and a keyword library is constructed based on the keywords corresponding to each law and regulation.
However, when the keyword library constructed based on the TF-IDF algorithm is used for searching legal regulations, the search result is usually only some legal regulations with high text matching degree of the keywords corresponding to the search condition, that is, only the frequency of the keywords appearing in the legal regulations is concerned in the search process, but the essential meaning of the legal regulations is not concerned, thereby the search result cannot meet the search intention of the user.
Disclosure of Invention
The embodiment of the application provides a legal regulation retrieval method and a legal regulation retrieval device, which can ensure that the retrieved legal regulation meets the actual retrieval intention of a user.
In view of the above, the first aspect of the present application provides a method for retrieving laws and regulations, the method comprising:
determining a first keyword corresponding to a retrieval condition;
determining a second keyword matched with the first keyword in a correlation library, and determining a first element associated with the second keyword; the association library stores keywords and elements associated with the keywords, and the keywords can represent semantic features of the elements associated with the keywords;
searching a referee document library for the referee document associated with the first element as a target referee document; the referee document library is stored with elements and referee documents related to the elements, and the elements can represent semantic features of the referee documents related to the elements;
and determining a legal regulation retrieval result according to the legal regulation related to the target referee document.
Optionally, when there are a plurality of the first elements and the first element includes a crime name and a behavior feature corresponding to the crime name, the retrieving, in the official document library, an official document associated with the first element as a target official document includes:
merging the behavior characteristics in the first elements comprising the same crime name to generate a second element;
and searching the official document library for the official document associated with the second element as a target official document.
Optionally, the determining a legal rule retrieval result according to the legal rule related to the target official document includes:
counting the corresponding occurrence times of each legal rule related to the target referee document;
and taking the legal regulation with the occurrence number larger than a first preset threshold value as the retrieval result of the legal regulation.
Optionally, the determining a legal rule retrieval result according to the legal rule related to the target official document includes:
screening out a first referee document with the judgment time within a preset judgment time period according to the judgment time corresponding to the target referee document;
and taking the law and regulation involved in the first referee document as the law and regulation retrieval result.
Optionally, the determining a legal rule retrieval result according to the legal rule related to the target official document includes:
sequencing the laws and regulations according to the sequence of the occurrence times from large to small according to the occurrence times corresponding to the laws and regulations related to the target referee document;
and taking the law and regulations with the preset number ranked at the top as the retrieval result of the law and regulations.
Optionally, the method further includes:
determining a third key word matched with the first key word from a law and regulation database, and determining laws and regulations related to the third key word; the law and regulation database stores keywords and laws and regulations related to the keywords;
determining a legal regulation retrieval result according to the legal regulation related to the target referee document, comprising:
and determining a legal regulation retrieval result according to the legal regulation associated with the third key word and the legal regulation related to the target referee document.
Optionally, the determining a legal rule search result according to the legal rule associated with the third keyword and the legal rule related to the target referee document includes:
overlapping the corresponding occurrence times of the laws and regulations related to the third key words and the same laws and regulations in the laws and regulations related to the target referee document, and determining the corresponding occurrence times of the laws and regulations;
and taking the legal regulation with the occurrence number larger than a third preset threshold value as a legal regulation retrieval result.
A second aspect of the present application provides a retrieval apparatus of laws and regulations, the apparatus including:
the keyword determining module is used for determining a first keyword corresponding to the retrieval condition;
the first retrieval module is used for determining a second keyword matched with the first keyword in an association library and determining a first element associated with the second keyword; the association library stores keywords and elements associated with the keywords, and the keywords can represent semantic features of the elements associated with the keywords;
a second retrieval module, configured to retrieve, in a referee document library, a referee document associated with the first element as a target referee document; the referee document library is stored with elements and referee documents related to the elements, and the elements can represent semantic features of the referee documents related to the elements;
and the retrieval result determining module is used for determining the retrieval result of the laws and regulations according to the laws and regulations related to the target referee document.
Optionally, when there are a plurality of first elements and the first element includes a crime name and a behavior feature corresponding to the crime name, the second retrieval module is specifically configured to:
merging the behavior characteristics in the first elements comprising the same crime name to generate a second element;
and searching the official document library for the official document associated with the second element as a target official document.
Optionally, the search result determining module is specifically configured to:
counting the corresponding occurrence times of each legal rule related to the target referee document;
and taking the legal regulation with the occurrence number larger than a first preset threshold value as the retrieval result of the legal regulation.
Optionally, the search result determining module is specifically configured to:
screening out a first referee document with the judgment time within a preset judgment time period according to the judgment time corresponding to the target referee document;
and taking the law and regulation involved in the first referee document as the law and regulation retrieval result.
Optionally, the search result determining module is specifically configured to:
sequencing the laws and regulations according to the sequence of the occurrence times from large to small according to the occurrence times corresponding to the laws and regulations related to the target referee document;
and taking the law and regulations with the preset number ranked at the top as the retrieval result of the law and regulations.
Optionally, the apparatus further comprises a third retrieving module;
the third retrieval module is used for determining a third key word matched with the first key word from a law and regulation database and determining a law and regulation related to the third key word; the law and regulation database stores keywords and laws and regulations related to the keywords;
the retrieval result determination module includes: a retrieval result determining submodule;
and the retrieval result determining submodule is used for determining a legal regulation retrieval result according to the legal regulation associated with the third key word and the legal regulation related to the target referee document.
Optionally, the retrieval result determining sub-module is specifically configured to:
overlapping the corresponding occurrence times of the laws and regulations related to the third key words and the same laws and regulations in the laws and regulations related to the target referee document, and determining the corresponding occurrence times of the laws and regulations;
and taking the legal regulation with the occurrence number larger than a third preset threshold value as a legal regulation retrieval result.
A third aspect of the present application provides a server for retrieving laws and regulations, the server comprising a processor and a memory:
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the method for retrieving laws and regulations according to the first aspect of the present invention according to instructions in the program code.
A fourth aspect of the present application provides a computer-readable storage medium for storing program code for executing the method for retrieving laws and regulations of the first aspect.
A fifth aspect of the present application provides a computer program product comprising instructions that, when run on a computer, cause the computer to perform the method for legal retrieval as described above in the first aspect.
According to the technical scheme, the embodiment of the application has the following advantages:
in the retrieval method of laws and regulations provided by the embodiment of the application, on the basis of a referee document containing laws and regulations, the association relation among a keyword, an element and the referee document is mined from the semantic perspective, and a referee document library and an association library are created, wherein the referee document library is used for storing the referee document and the associated element thereof, the association library is used for storing the keyword and the associated element thereof, and the referee document library and the association library are semantically associated through the element; therefore, in the searching process, first key words corresponding to the searching conditions are determined based on the association library and the referee document library, then the first key words are determined based on the first key words, the target referee document associated with the first key words is searched from the referee document library, and the legal and legal rules searching results meeting the searching intention of the user are determined according to the legal and legal rules related to the target referee document. Compared with the method for searching the laws and regulations by utilizing the keyword library constructed based on the TF-IDF algorithm in the prior art, the method provided by the application develops a new way from the laws and regulations, based on the semantic features expressed on the legal practice operation level, the incidence relation among the keywords, the elements and the referee document is constructed, further based on the incidence relation constructed based on the semantics among the keywords, the elements and the referee document, and the laws and regulations are searched according to the searching conditions, so that the searching result can accord with the actual searching intention of a user, namely, the reliability of the searching result is higher.
Drawings
Fig. 1 is a schematic application scenario diagram of a retrieval method for laws and regulations provided in an embodiment of the present application;
FIG. 2 is a flow chart illustrating a retrieval method of laws and regulations according to an embodiment of the present application;
FIG. 3 is a flow chart illustrating another legal retrieval method provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of a retrieval apparatus for legal regulations according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a server for retrieving laws and regulations according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the prior art, a keyword library constructed based on a TF-IDF algorithm is usually used as a retrieval basis, and legal regulations are retrieved according to keywords corresponding to retrieval conditions input by a user, and in this way, only the occurrence frequency of the keywords in each legal regulation is concerned in the retrieval process, but the essential meaning of each legal regulation is not concerned, so that the actually retrieved legal regulations may not meet the actual retrieval intention of the user.
In order to solve the above disadvantages in the prior art, the embodiments of the present application provide a retrieval method for legal regulations, which can ensure that the retrieved legal regulations meet the actual retrieval intention of the user. The following first introduces the core technical idea of the legal retrieval method provided in the embodiment of the present application:
in the retrieval method of laws and regulations provided by the embodiment of the application, a first keyword corresponding to a retrieval condition is determined, then the first keyword is matched with a keyword stored in an association library, a second keyword matched with the first keyword is determined, and a first element associated with the second keyword is further determined, wherein the keyword and elements associated with the keyword are stored in the association library, and the stored keyword can represent semantic features of the elements associated with the stored keyword; next, searching a referee document related to the first element in a referee document library as a target referee document, wherein the referee document library stores the elements and the referee documents related to the elements, and the stored elements can represent the semantic features of the referee documents related to the stored elements; and finally, determining a legal regulation retrieval result according to the legal regulation related to the target referee document.
The retrieval method of laws and regulations provided by the embodiment of the application is based on the referee document containing laws and regulations as a retrieval basis, the incidence relation among the key words, the elements and the referee document is mined from the semantic perspective, the incidence library used for storing the key words and the elements relevant to the key words and the referee document library used for storing the elements and the referee document relevant to the elements are created, and therefore the laws and regulations which accord with the retrieval intention of a user are retrieved according to retrieval conditions based on the incidence library and the referee document library in the retrieval process. Compared with the method for searching the laws and regulations by utilizing the keyword library constructed based on the TF-IDF algorithm in the prior art, the method provided by the application develops a new way from the laws and regulations, based on the semantic features expressed on the legal practice operation level, the incidence relation among the keywords, the elements and the referee document is constructed, and then the laws and regulations are searched based on the semantic incidence relation among the keywords, the elements and the referee document, so that the search result can accord with the actual search intention of a user, namely, the reliability of the search result is higher.
It should be understood that the retrieval method for legal regulations provided in the embodiment of the present application may be applied to a server providing a retrieval service, where the server may specifically be an application server or a Web server, and when the server is deployed in actual application, the server may be an independent server or a cluster server, and the server may respond to the retrieval conditions sent by a plurality of terminal devices at the same time and correspondingly retrieve the legal regulation retrieval results corresponding to the respective retrieval conditions.
In order to facilitate understanding of the technical solution of the present application, a server is taken as an execution subject, and a retrieval method of laws and regulations provided in the embodiments of the present application is introduced in combination with an actual application scenario.
Referring to fig. 1, fig. 1 is a schematic view illustrating an application scenario of a retrieval method of laws and regulations provided in an embodiment of the present application. The application scene comprises a terminal device 101, a server 102, an association library 103 and a referee text library 104; wherein, the terminal device 101 is used for sending a retrieval condition to the server 102, so that the server 102 retrieves the laws and regulations according to the retrieval condition; the server 102 is configured to implement the retrieval method of the laws and regulations provided in the embodiment of the present application according to the retrieval condition sent by the terminal device 101, and determine the retrieval result of the laws and regulations corresponding to the retrieval condition, and the server 102 needs to refer to the keyword and the element associated with the keyword stored in the association library 102, and the element stored in the official document library 104 and the official document associated with the element in the process of retrieving the laws and regulations.
It should be understood that the association library 103 and the referee text library 104 can be stored in the server 102, or stored on other devices; if the association library 103 and the referee text library 104 are stored on other devices, when the server 102 needs to retrieve laws and regulations, the association library 103 and the referee text library 104 stored on other devices can be called, and then laws and regulations are retrieved based on data stored in the association library 103 and the referee text library 104.
When the user needs to retrieve the laws and regulations through the terminal apparatus 101, the user can input a retrieval condition related to the laws and regulations to be retrieved on the terminal apparatus 101, and thus, the terminal apparatus 101 transmits the retrieval condition to the server 102. After receiving the search condition from the terminal device 101, the server 102 determines a first keyword corresponding to the search condition; then, in a relational library 103 for storing keywords and elements semantically related thereto, a second keyword matching the first keyword and a first element related to the second keyword are determined; next, in a referee document library 104 for storing the elements and referee documents semantically associated therewith, retrieving a target referee document associated with the first element; finally, the server 102 determines a legal retrieval result according to the legal involved in the target official document.
It should be noted that, in the above retrieval method of laws and regulations, based on the semantic features expressed on the law enforcement operation level, the association relationship among the keyword, the element and the referee document is constructed, and then the laws and regulations are retrieved based on the semantic association relationship among the keyword, the element and the referee document, so that the retrieval result can meet the actual retrieval intention of the user, that is, the reliability of the retrieval result is higher.
It should be noted that the application scenario described in fig. 1 is only an example, and in practical applications, the retrieval method for legal regulations provided in the embodiment of the present application may also be applied to other application scenarios, and no specific limitation is made to the application scenario of the retrieval method for legal regulations.
The following describes a method for retrieving laws and regulations provided in the present application by way of example.
Referring to fig. 2, fig. 2 is a schematic flowchart of a retrieval method of laws and regulations provided in an embodiment of the present application. For convenience of description, the following embodiments are described with a server as an execution subject. As shown in fig. 2, the retrieval method of laws and regulations includes the following steps:
step 201: and determining a first keyword corresponding to the retrieval condition.
When a user needs to retrieve laws and regulations, the user can input sentences or words related to the laws and regulations needing to be retrieved as retrieval conditions in a retrieval condition input box provided by the terminal equipment by controlling the terminal equipment; in response to a search condition confirmation operation initiated by a user, the terminal device may send a current search condition in the search condition input box to the server, where the search condition confirmation operation specifically includes that the user triggers and clicks a search button, or the terminal device does not detect that the user continues to execute the search condition input operation within a preset time period, or may directly send the current search condition in the search condition input box to the server. Furthermore, the server determines a first keyword corresponding to the search condition after receiving the search condition from the terminal device.
It should be understood that when the retrieval condition input by the user is a word related to the law needing to be retrieved, the server may directly take the word input by the user as the first keyword; when the retrieval condition input by the user is a sentence related to the law needing to be retrieved, the server can firstly perform word segmentation processing on the retrieval condition, and then extract a word segmentation capable of reflecting the semantic meaning of the retrieval condition to a certain extent from each word segmentation obtained by the word segmentation processing as a first keyword, or the server can determine a word representing the semantic meaning of the retrieval condition as the first keyword by performing semantic analysis on the retrieval condition.
It should be noted that there may be one or more first keywords corresponding to the search condition, and the number of the first keywords corresponding to the search condition is not limited at all.
Step 202: a second keyword matching the first keyword is determined in a related library, and a first element associated with the second keyword is determined.
After determining the first keyword corresponding to the retrieval condition, the server matches the first keyword with keywords stored in the association library, specifically, if the server matches a keyword identical to the first keyword in the association library, the server may directly use the keyword as a second keyword, and if the server does not match a keyword identical to the first keyword in the association library, the server may determine a keyword, of which text and/or semantics are similar to the first keyword, as the second keyword in the association library based on the text similarity and/or the semantic similarity. Further, the server determines an element associated with the second keyword as the first element based on the keyword and the element having an association relationship stored in the association library.
In the association library, a keyword and an element associated therewith are stored, wherein the keyword can represent a semantic feature of the element associated with the keyword, and the element can represent a semantic feature of the official document associated with the element.
Specifically, the above-mentioned elements are usually determined according to the scenario involved in the referee document by using a machine learning algorithm, which can correspondingly characterize the semantic features of the referee document, and the elements usually include a crime name and behavior features corresponding to the crime name, where the behavior features corresponding to the crime name include the illegal behaviors of a criminal, the judgment results received by the criminal due to a certain crime name, and the like; the keywords stored in the above-mentioned associative library are determined based on the semantics of the element, which can reflect the essential meaning of the element.
For example, for the key element dangerous driving crime, the criminal body is mainly responsible, and the keywords related to the key element dangerous driving crime comprise danger, driving and main responsibility, and the keywords are determined based on the semantic features of the key element and can reflect the essential meaning of the key element to a certain extent.
It should be understood that the number of keywords associated with one element may be one or more, and the number of keywords associated with an element is not limited at all; similarly, there may be one or more elements associated with a keyword, and the number of the elements associated with a keyword is not limited in any way. Accordingly, the number of the first elements associated with the second keyword may be one or more, and the specific number of the first elements is not limited at all.
Step 203: and searching the official document related to the first element in an official document library to obtain a target official document.
After determining the first element associated with the second keyword, the server continues to search the referee document associated with the first element in the referee document library, and takes the searched referee document associated with the first element as a target referee document.
The referee document library stores elements and referee documents related to the elements, wherein the referee documents are recorded with the process and the result of court trial cases, the elements can represent the semantic features of the referee documents related to the elements, the elements are determined according to the plots related to the referee documents by adopting a machine learning algorithm, and accordingly, the elements can embody the semantic features in the referee documents to a certain extent.
It should be understood that the official document associated with one element may be one or more, and the number of official documents associated with an element is not limited at all; similarly, there may be one or more elements associated with one official document, and the number of the elements associated with one official document is not limited in any way.
It should be understood that, since one or more referee documents may be associated with one element, one or more target referee documents may be associated with the first element, and the number of the target referee documents determined is not limited thereto.
In a possible implementation, since the number of first elements may be large, accordingly, the number of target official documents associated with each first element is also large, and in the case of a large number of target official documents, the server needs to perform a lot of work to determine the legal retrieval result from the large number of target official documents. In order to reduce the amount of work that the server needs to perform, in the case where there are a plurality of first elements, the server may merge the plurality of first elements into a second element, search for a more relevant target official document from the second element including more behavioral features, and reduce the number of target official documents.
Specifically, if there are a plurality of first elements determined in step 202, and the first elements each include a crime name and a behavior feature corresponding to the crime name, the server may merge the behavior features in the first elements including the same crime name to generate a second element when searching for the target referee document in the referee document library; and searching the official document library for the official document associated with the second element as a target official document.
For ease of understanding, the manner in which such a target referee document is retrieved is exemplified below:
assume that the first element associated with the second keyword comprises: dangerous driving crime-crime subject responsible for main responsibility, hit-dead 1 person, dangerous driving crime-more than 50% of the specified speed per hour and speed more than 60 km/h, hit-dead 1 person, combining the behavior characteristics in the first element including the same crime name, namely combining the behavior characteristics in the element "dangerous driving crime-crime subject responsible for main responsibility" and the element "dangerous driving crime-more than 50% of the specified speed per hour and speed more than 60 km/h" to obtain the second element "dangerous driving crime-crime subject responsible for main responsibility, more than 50% of the specified speed per hour and speed more than 60 km/h", combining the behavior characteristics in the element "hit-dead 1 person" and the element "hit-soft 1 person" including the traffic crime, obtaining a second element of crime of causing traffic offences-1 dead person and 1 light injury; further, according to a second element "dangerous driving crime-crime subject is responsible for the main responsibility, the speed exceeds 50% of the predetermined speed per hour and exceeds 60 km/h" and "culprit crime-death 1 person and minor injury 1 person", the referee document related to the second element is searched in the referee document library as a target referee document.
Similarly, there may be one or more target official documents associated with the second component, and the number of the target official documents associated with the second component is not limited at all.
Step 204: and determining a legal regulation retrieval result according to the legal regulation related to the target referee document.
After the target referee document related to the first element is searched, the server determines a legal regulation search result according to the legal regulation related to the target referee document. Specifically, the server may directly use the laws and regulations related to the target official document as the search result, or may screen the laws and regulations related to the target official document and use the screened laws and regulations as the search result. And then, returning the legal regulation retrieval result to the terminal equipment so as to display the retrieved legal regulation to the user through the terminal equipment.
In a possible implementation manner, the server may screen the laws and regulations related to the target referee document according to the occurrence times corresponding to the laws and regulations related to the target referee document, so as to determine the law and regulation retrieval result. Specifically, the server may count the number of occurrences corresponding to each law and regulation involved in the target official document, and then use the law and regulation whose number of occurrences is greater than the first preset threshold value as the law and regulation retrieval result.
It should be understood that the first preset threshold may be set according to actual situations, and no limitation is made to specific values corresponding to the first preset threshold.
In another possible implementation manner, the server may screen the target referee document according to the judgment time corresponding to the target referee document, and further take the laws and regulations in the screened target referee document as the laws and regulations retrieval result. Specifically, the server can screen out the first referee document with the judgment time within the preset judgment time period according to the judgment time corresponding to the target referee document; and further, the law and regulation involved in the first referee document are used as the law and regulation retrieval result.
It should be understood that the preset decision time period herein may be set according to actual situations, and the preset decision time period is not limited in any way herein. Since laws and regulations are often modified, a target referee document whose decision time is after a certain preset decision time may be generally screened as a first referee document, that is, a certain preset decision time is taken as a preset decision time period so far.
In yet another possible implementation manner, the server may filter the laws and regulations with a larger number of occurrences as the retrieval result of the laws and regulations by sorting the number of occurrences corresponding to the laws and regulations involved in the target referee document. Specifically, the server may sort the laws and regulations according to the order of the occurrence times from large to small according to the occurrence times corresponding to the laws and regulations related to the target referee document, and then take the preset number of laws and regulations in the top order as the retrieval result of the laws and regulations; similarly, the server may also sort the laws and regulations in order of the occurrence times from small to large, and then use the preset number of laws and regulations after sorting as the retrieval result of laws and regulations.
It should be understood that the preset number can be set according to actual situations, and no limitation is made to specific values corresponding to the preset number.
It should be noted that, when screening the legal and legal retrieval results, the server may use any one or more of the three implementation manners to screen the legal and legal related in the target referee document, so as to determine the legal retrieval results.
It should be noted that, if the server merges the first elements including the same crime name into the second elements in step 203, and searches the target official document according to the second elements, when determining the legal rule search result according to the legal rules related to the target official document, the server may first count the number of occurrences corresponding to each legal rule related to each official document related to the second element, that is, count the number of occurrences corresponding to each legal rule related to the target official document under each crime name; screening the laws and regulations related under each crime name, specifically screening the laws and regulations with the occurrence frequency corresponding to the laws and regulations related under each crime name larger than a preset threshold value, and taking the screened laws and regulations as the retrieval result of the laws and regulations corresponding to each crime name; furthermore, the server can continue to superpose the corresponding occurrence times of the same laws and regulations in the law and regulation retrieval result corresponding to each crime name to serve as the corresponding occurrence times of the laws and regulations, the laws and regulations are sequenced according to the descending order of the corresponding occurrence times of the laws and regulations, the sequenced laws and regulations serve as the law and regulation retrieval result and are sent to the terminal equipment as the law and regulation retrieval result, and the terminal equipment displays the laws and regulations in the law and regulation retrieval result to the user according to the corresponding order.
It should be understood that the specific value of the preset threshold may be set according to actual conditions, and the value is not limited to any specific value, and in general, the preset threshold may be determined according to the number of target official documents related to each crime name.
To facilitate understanding of the above-described implementation of determining legal retrieval results, the following examples of such implementation are provided:
assuming that there are three target referee documents related to the second element a, namely, there are three target referee documents related to the crime name a, and the laws and regulations related to the three target referee documents include law a, law b and law c, wherein the occurrences of law a, law b and law c in the three target referee documents are 1, 3 and 3 times, respectively; the target referee documents related to the second element B have four in common, that is, the target referee documents related to the crime name B have four, and the laws and regulations related to the four target referee documents include law B, law c, law d and law f, wherein the number of occurrences of law B, law c, law d and law f in the four target referee documents is 3, 4, 1 and 3, respectively.
It is assumed that the preset threshold value for screening the laws and regulations is half of the number of target referee documents related to each crime name, that is, the preset threshold value for screening the laws and regulations related to the crime name a is 1.5, and the preset threshold value for screening the laws and regulations related to the crime name B is 2.
In the laws and regulations related to the crime name A, the occurrence frequency of the law b and the law c is greater than the preset threshold value 1.5 corresponding to the crime name A, and correspondingly, the law b and the law c can be used as the retrieval result of the laws and regulations corresponding to the crime name A; in the legal regulations related to the crime name B, the occurrence times of the law B, the law c and the law f are all larger than the preset threshold value 2 corresponding to the crime name B, and accordingly, the law B, the law c and the law f can be used as the legal regulation retrieval result corresponding to the crime name B. The method includes the steps of performing superposition processing on the occurrence times of the same laws and regulations in law and regulation retrieval results corresponding to a crime name A and a crime name B to obtain the occurrence times corresponding to each law and regulation, namely superposing the occurrence times of a law B related to the crime name A and the occurrence times of a law B related to the crime name B to obtain the actual occurrence times of the law B for 6 times, superposing the occurrence times of a law c related to the crime name A and the occurrence times of a law c related to the crime name B to obtain the actual occurrence times of the law c for 7 times, wherein the occurrence times corresponding to the law f related to the crime name B are actually the occurrence times corresponding to the law f and are 3 times. And sequencing the legal and legal retrieval results corresponding to the crime name A and the legal retrieval results corresponding to the crime name B according to the sequence of the actual occurrence times from large to small, namely sequencing the legal retrieval results into a law c, a law B and a law f in sequence, and taking the legal retrieval results which are sequenced according to the sequencing as final legal retrieval results.
Optionally, in order to ensure that the finally obtained legal and legal rule retrieval result is more comprehensive, the server may further search the legal and legal rules in a legal and legal rule database for storing the keywords having the association relationship and the legal and legal rules according to the first keyword corresponding to the retrieval condition determined in step 201, and determine the legal and legal rule retrieval result according to the searched legal and legal rules and the legal and legal rules related to the target referee document.
During specific implementation, the server can match the first keyword with keywords stored in a legal regulation database, and determine a third keyword matched with the first keyword; specifically, if the keyword identical to the first keyword is matched in the law and regulation database, the keyword may be directly used as the third keyword, and if the keyword identical to the first keyword is not matched in the law and regulation database, the keyword having a higher semantic similarity and/or text similarity to the first keyword may be searched in the law and regulation database as the third keyword according to the semantic similarity and/or text similarity. Further, the server determines a legal regulation retrieval result according to the legal regulation associated with the third key word and the legal regulation related to the target referee document; specifically, the server may directly use the laws and regulations associated with the third keyword and the laws and regulations related to the target referee document as the law and regulation retrieval result, or the server may screen the laws and regulations associated with the third keyword and the laws and regulations related to the target referee document and use the screened laws and regulations as the law and regulation retrieval result.
It should be noted that the above-mentioned legal regulation database stores the keywords and the legal regulations associated therewith, and the legal regulation database may be a database constructed based on the TF-IDF algorithm, or may be a database constructed by other methods.
In one possible implementation, the server may superimpose the times corresponding to the same laws and regulations among laws and regulations related to the third keyword and laws and regulations related to the target referee document, thereby determining the number of occurrences that each laws and regulations actually correspond to; and then, taking the legal regulation with the occurrence frequency larger than a third preset threshold value as a legal regulation retrieval result.
It should be understood that the third preset threshold may be set according to actual situations, and the specific value of the third preset threshold is not limited in any way.
For example, assuming that the laws and regulations related to the third keyword include law a, law b and law c, the laws and regulations related to the target referee document include law b, law c and law d, the number of occurrences corresponding to law b related to the third keyword and the number of occurrences corresponding to law b in the target referee document are superimposed to obtain the number of occurrences actually corresponding to law b, the number of occurrences corresponding to law c and the number of occurrences corresponding to law c in the target referee document are superimposed to obtain the number of occurrences actually corresponding to law c, the number of occurrences corresponding to law a related to the third keyword is the number of occurrences actually corresponding to law a, and the number of occurrences corresponding to law d related to the target referee document is the number of occurrences actually corresponding to law d. And determining the legal regulation larger than a third preset threshold value as a legal regulation retrieval result according to the actual corresponding occurrence times of the law a, the law b, the law c and the law d.
It should be understood that, in practical application, the server may also sequence the laws and regulations according to the actual occurrence times of the laws and regulations, and push the laws and regulations of the preset number at the top of the sequence to the terminal device as the retrieval result of the laws and regulations; in addition, the server can also directly push the laws and regulations related to the target referee document in priority and push the laws and regulations related to the third key words later.
The retrieval method of laws and regulations provided by the embodiment of the application is based on the referee document containing laws and regulations as a retrieval basis, the incidence relation among the key words, the elements and the referee document is mined from the semantic perspective, the incidence library used for storing the key words and the elements relevant to the key words and the referee document library used for storing the elements and the referee document relevant to the elements are created, and therefore the laws and regulations which accord with the retrieval intention of a user are retrieved according to retrieval conditions based on the incidence library and the referee document library in the retrieval process. Compared with the method for searching the laws and regulations by utilizing the keyword library constructed based on the TF-IDF algorithm in the prior art, the method provided by the application develops a new way from the laws and regulations, based on the semantic features expressed on the legal practice operation level, the incidence relation among the keywords, the elements and the referee document is constructed, and then the laws and regulations are searched based on the semantic incidence relation among the keywords, the elements and the referee document, so that the search result can accord with the actual search intention of a user, namely, the reliability of the search result is higher.
In order to further understand the retrieval method of laws and regulations provided in the embodiments of the present application, a specific implementation manner of the retrieval method of laws and regulations in practical application is described below with reference to fig. 3:
referring to fig. 3, fig. 3 is a schematic flowchart of a retrieval method of laws and regulations provided in an embodiment of the present application, where an execution subject of the method is a server, and as shown in fig. 3, the method includes:
step 301: and performing word segmentation processing on the search condition to obtain a first keyword.
Step 302: and determining a second keyword matched with the first keyword in the association library, and determining a first element associated with the second keyword.
Step 303: merging the first elements containing the same crime name to generate a second element; and searching the referee documents related to the second elements in the referee document library, and screening the referee documents with judgment time after preset judgment time as target referee documents.
Step 304: counting the occurrence times corresponding to the laws and regulations related to the target referee document, and screening the laws and regulations with the occurrence times larger than a preset threshold value in the laws and regulations related to each crime name as the laws and regulations retrieval results corresponding to each crime name; and then, overlapping the occurrence times corresponding to the same laws and regulations in the law and regulation retrieval results corresponding to the criminal names to serve as actual occurrence times corresponding to the laws and regulations, sequencing the laws and regulations according to the actual occurrence times of the laws and regulations to serve as the law and regulation retrieval results corresponding to the target referee document.
Step 305: and determining a third key word matched with the first key word in a law and regulation database, and determining the law and regulation related to the third key word.
Step 306: and combining the laws and regulations related to the third key words with the laws and regulations in the laws and regulations retrieval result corresponding to the target referee document to determine the laws and regulations retrieval result.
Step 307: and sending the legal and legal retrieval result to the terminal equipment so that the terminal equipment displays the legal and legal retrieval result.
Aiming at the retrieval method of the laws and regulations described above, the application also provides a retrieval device of the corresponding laws and regulations so as to facilitate the application and implementation of the methods in practice.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a legal retrieval device 400 corresponding to the method shown in fig. 2, wherein the legal retrieval device 400 comprises:
a keyword determining module 401, configured to determine a first keyword corresponding to a search condition;
a first retrieval module 402, configured to determine a second keyword matching the first keyword in a related library, and determine a first element associated with the second keyword; the association library stores keywords and elements associated with the keywords, and the keywords can represent semantic features of the elements associated with the keywords;
a second retrieval module 403, configured to retrieve, in a referee document library, a referee document associated with the first element as a target referee document; the referee document library stores the elements and the referee documents related to the elements, and the elements can represent semantic features of the referee documents related to the elements;
and a retrieval result determining module 404, configured to determine a legal and legal retrieval result according to the legal and legal regulations related to the target referee document.
Optionally, when there are a plurality of first elements and the first element includes a crime name and a behavior feature corresponding to the crime name, the second retrieving module 403 is specifically configured to:
merging the behavior characteristics in the first elements comprising the same crime name to generate a second element;
and searching the official document library for the official document associated with the second element as a target official document.
Optionally, the retrieval result determining module 404 is specifically configured to:
counting the corresponding occurrence times of each legal rule related to the target referee document;
and taking the legal regulation with the occurrence number larger than a first preset threshold value as the retrieval result of the legal regulation.
Optionally, the retrieval result determining module 404 is specifically configured to:
screening out a first referee document with the judgment time within a preset judgment time period according to the judgment time corresponding to the target referee document;
and taking the law and regulation involved in the first referee document as the law and regulation retrieval result.
Optionally, the retrieval result determining module 404 is specifically configured to:
sequencing the laws and regulations according to the sequence of the occurrence times from large to small according to the occurrence times corresponding to the laws and regulations related to the target referee document;
and taking the law and regulations with the preset number ranked at the top as the retrieval result of the law and regulations.
Optionally, the apparatus further comprises a third retrieving module;
the third retrieval module is used for determining a third key word matched with the first key word from a law and regulation database and determining a law and regulation related to the third key word; the law and regulation database stores keywords and laws and regulations related to the keywords;
the retrieval result determination module 404 includes: a retrieval result determining submodule;
and the retrieval result determining submodule is used for determining a legal regulation retrieval result according to the legal regulation associated with the third key word and the legal regulation related to the target referee document.
Optionally, the retrieval result determining sub-module is specifically configured to:
overlapping the corresponding occurrence times of the laws and regulations related to the third key words and the same laws and regulations in the laws and regulations related to the target referee document, and determining the corresponding occurrence times of the laws and regulations;
and taking the legal regulation with the occurrence number larger than a third preset threshold value as a legal regulation retrieval result.
The retrieval device for laws and regulations provided by the embodiment of the application takes the referee document containing laws and regulations as a retrieval basis, mines the incidence relation among the key words, the elements and the referee document from the semantic perspective, and creates the association library for storing the key words and the elements associated with the key words and the referee document library for storing the elements and the referee document associated with the elements, thereby retrieving the laws and regulations meeting the retrieval intention of a user according to retrieval conditions based on the association library and the referee document library in the retrieval process. The retrieval device of laws and regulations provided by the application constructs the incidence relation among the key words, the elements and the referee documents based on the semantic features expressed on the law enforcement operation level, and then retrieves the laws and regulations based on the semantic incidence relation among the key words, the elements and the referee documents, so that the retrieval result can accord with the actual retrieval intention of a user, namely the retrieval result is higher in reliability.
The embodiment of the present application further provides a server for retrieving laws and regulations, referring to fig. 5, fig. 5 is a schematic structural diagram of a server provided in the embodiment of the present application, and the server 500 may have relatively large differences due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 522 (e.g., one or more processors) and a memory 532, and one or more storage media 530 (e.g., one or more mass storage devices) storing an application program 542 or data 544. Memory 532 and storage media 530 may be, among other things, transient storage or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 522 may be configured to communicate with the storage medium 530, and execute a series of instruction operations in the storage medium 530 on the server 500.
The server 500 may also include one or more power supplies 526, one or more wired or wireless network interfaces 550, one or more input-output interfaces 558, and/or one or more operating systems 541, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, and so forth.
The steps performed by the server in the above embodiments may be based on the server structure shown in fig. 5.
The CPU 522 is configured to perform the following steps:
determining a first keyword corresponding to a retrieval condition;
determining a second keyword matched with the first keyword in a correlation library, and determining a first element associated with the second keyword; the association library stores keywords and elements associated with the keywords, and the keywords can represent semantic features of the elements associated with the keywords;
searching a referee document library for the referee document associated with the first element as a target referee document; the referee document library stores the elements and the referee documents related to the elements, and the elements can represent semantic features of the referee documents related to the elements;
and determining a legal regulation retrieval result according to the legal regulation related to the target referee document.
Optionally, CPU 522 may also perform method steps of any particular implementation of the retrieval method for laws and regulations in the embodiments of the present application.
The embodiments of the present application also provide a computer-readable storage medium for storing a program code for implementing any one of the embodiments of a legal retrieval method described in the foregoing embodiments.
The embodiments of the present application also provide a computer program product including instructions, which when run on a computer, cause the computer to execute any one implementation of a retrieval method of laws and regulations described in the foregoing embodiments.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A retrieval method of laws and regulations, said method comprising:
determining a first keyword corresponding to a retrieval condition;
determining a second keyword matched with the first keyword in a correlation library, and determining a first element associated with the second keyword; the association library stores keywords and elements associated with the keywords, and the keywords can represent semantic features of the elements associated with the keywords;
searching a referee document library for the referee document associated with the first element as a target referee document; the referee document library is stored with elements and referee documents related to the elements, and the elements can represent semantic features of the referee documents related to the elements;
and determining a legal regulation retrieval result according to the legal regulation related to the target referee document.
2. The method according to claim 1, wherein when there are a plurality of the first components and the first component includes a crime name and a behavior feature corresponding to the crime name, the retrieving, as a target referee document, a referee document associated with the first component in a referee document library includes:
merging the behavior characteristics in the first elements comprising the same crime name to generate a second element;
and searching the official document library for the official document associated with the second element as a target official document.
3. The method according to claim 1 or 2, wherein said determining a legal retrieval result according to the legal involved in the target official document comprises:
counting the corresponding occurrence times of each legal rule related to the target referee document;
and taking the legal regulation with the occurrence number larger than a first preset threshold value as the retrieval result of the legal regulation.
4. The method according to claim 1 or 2, wherein said determining a legal retrieval result according to the legal involved in the target official document comprises:
screening out a first referee document with the judgment time within a preset judgment time period according to the judgment time corresponding to the target referee document;
and taking the law and regulation involved in the first referee document as the law and regulation retrieval result.
5. The method according to claim 1 or 2, wherein said determining a legal retrieval result according to the legal involved in the target official document comprises:
sequencing the laws and regulations according to the sequence of the occurrence times from large to small according to the occurrence times corresponding to the laws and regulations related to the target referee document;
and taking the law and regulations with the preset number ranked at the top as the retrieval result of the law and regulations.
6. The method of claim 1, further comprising:
determining a third key word matched with the first key word from a law and regulation database, and determining laws and regulations related to the third key word; the law and regulation database stores keywords and laws and regulations related to the keywords;
determining a legal regulation retrieval result according to the legal regulation related to the target referee document, comprising:
and determining a legal regulation retrieval result according to the legal regulation associated with the third key word and the legal regulation related to the target referee document.
7. The method according to claim 6, wherein the determining a legal retrieval result according to the legal associated with the third keyword and the legal involved in the target official document comprises:
overlapping the corresponding occurrence times of the laws and regulations related to the third key words and the same laws and regulations in the laws and regulations related to the target referee document, and determining the corresponding occurrence times of the laws and regulations;
and taking the legal regulation with the occurrence number larger than a third preset threshold value as a legal regulation retrieval result.
8. A retrieval apparatus of laws and regulations, characterized in that said apparatus comprises:
the keyword determining module is used for determining a first keyword corresponding to the retrieval condition;
the first retrieval module is used for determining a second keyword matched with the first keyword in an association library and determining a first element associated with the second keyword; the association library stores keywords and elements associated with the keywords, and the keywords can represent semantic features of the elements associated with the keywords;
a second retrieval module, configured to retrieve, in a referee document library, a referee document associated with the first element as a target referee document; the referee document library is stored with elements and referee documents related to the elements, and the elements can represent semantic features of the referee documents related to the elements;
and the retrieval result determining module is used for determining the retrieval result of the laws and regulations according to the laws and regulations related to the target referee document.
9. A computer-readable storage medium for storing a program code for executing the retrieval method of laws and regulations according to any one of claims 1-7.
10. A computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of legal retrieval recited in any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811108196.0A CN111026836A (en) | 2018-09-21 | 2018-09-21 | Legal and legal rule retrieval method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811108196.0A CN111026836A (en) | 2018-09-21 | 2018-09-21 | Legal and legal rule retrieval method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111026836A true CN111026836A (en) | 2020-04-17 |
Family
ID=70190270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811108196.0A Pending CN111026836A (en) | 2018-09-21 | 2018-09-21 | Legal and legal rule retrieval method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111026836A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783449A (en) * | 2020-06-24 | 2020-10-16 | 鼎富智能科技有限公司 | Method and device for extracting elements of judgment result in judgment document |
| CN113177106A (en) * | 2021-05-19 | 2021-07-27 | 苏州黑云智能科技有限公司 | Similar decision book retrieval method based on element extraction |
| CN115525837A (en) * | 2022-09-27 | 2022-12-27 | 北京红蓝律信息技术有限公司 | Method and device for associating legal community with legal library |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100257197A1 (en) * | 2007-12-03 | 2010-10-07 | Pioneer Corporation | Information retrieval apparatus, information retrieval method and information retrieval processing program |
| CN106815263A (en) * | 2015-12-01 | 2017-06-09 | 北京国双科技有限公司 | The searching method and device of legal provision |
| CN106815262A (en) * | 2015-12-01 | 2017-06-09 | 北京国双科技有限公司 | The searching method and device of judgement document |
| CN108038091A (en) * | 2017-10-30 | 2018-05-15 | 上海思贤信息技术股份有限公司 | A kind of similar calculating of judgement document's case based on figure and search method and system |
-
2018
- 2018-09-21 CN CN201811108196.0A patent/CN111026836A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100257197A1 (en) * | 2007-12-03 | 2010-10-07 | Pioneer Corporation | Information retrieval apparatus, information retrieval method and information retrieval processing program |
| CN106815263A (en) * | 2015-12-01 | 2017-06-09 | 北京国双科技有限公司 | The searching method and device of legal provision |
| CN106815262A (en) * | 2015-12-01 | 2017-06-09 | 北京国双科技有限公司 | The searching method and device of judgement document |
| CN108038091A (en) * | 2017-10-30 | 2018-05-15 | 上海思贤信息技术股份有限公司 | A kind of similar calculating of judgement document's case based on figure and search method and system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783449A (en) * | 2020-06-24 | 2020-10-16 | 鼎富智能科技有限公司 | Method and device for extracting elements of judgment result in judgment document |
| CN111783449B (en) * | 2020-06-24 | 2023-09-22 | 鼎富智能科技有限公司 | Element extraction method and device for judgment result in judge document |
| CN113177106A (en) * | 2021-05-19 | 2021-07-27 | 苏州黑云智能科技有限公司 | Similar decision book retrieval method based on element extraction |
| CN113177106B (en) * | 2021-05-19 | 2024-04-12 | 苏州黑云智能科技有限公司 | Similar decision book retrieval method based on element extraction |
| CN115525837A (en) * | 2022-09-27 | 2022-12-27 | 北京红蓝律信息技术有限公司 | Method and device for associating legal community with legal library |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11514701B2 (en) | System and method for global identification in a collection of documents | |
| KR101644817B1 (en) | Generating search results | |
| US9965459B2 (en) | Providing contextual information associated with a source document using information from external reference documents | |
| US20040049499A1 (en) | Document retrieval system and question answering system | |
| KR101565759B1 (en) | Method and system for detecting related topics and competition topics based on topic templates and association words, related topics and competition topics detecting device | |
| CN111259660B (en) | Keyword extraction method, device, equipment and storage medium based on text pairs | |
| CN109299235A (en) | Knowledge base searching method, apparatus and computer readable storage medium | |
| KR20120087058A (en) | Apparatus, method and computer readable recording medium for providibg related contents | |
| CN111026836A (en) | Legal and legal rule retrieval method and device | |
| JP3584848B2 (en) | Document processing device, item search device, and item search method | |
| Vavliakis et al. | Event Detection via LDA for the MediaEval2012 SED Task. | |
| CN118364174A (en) | Content recommendation method, device, equipment and medium | |
| US10474700B2 (en) | Robust stream filtering based on reference document | |
| CN108132941B (en) | Method and device for processing association relationship of legal documents | |
| CN110727850B (en) | Network information filtering method, computer readable storage medium and mobile terminal | |
| CN110851560A (en) | Information retrieval method, device and equipment | |
| KR20190134230A (en) | Method for providing contents recommended word and apparatus for providing contents thereof | |
| CN110888877A (en) | Event information display method and device, computing equipment and storage medium | |
| US9507855B2 (en) | System and method for searching index content data using multiple proximity keyword searches | |
| Mentzingen et al. | Automation of legal precedents retrieval: findings from a rapid literature review | |
| CN113515631A (en) | Method, device, terminal equipment and storage medium for predicting criminal name | |
| KR102677884B1 (en) | Apparatus and method for providing service of consultation matching loss adjuster and labor attorney based on ai | |
| CN117093601B (en) | Recall method, device, equipment and medium for structured data | |
| CN112307293B (en) | Device function search method and device | |
| US12197482B2 (en) | Method and computer system for determining the relevance of a text |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200417 |
|
| RJ01 | Rejection of invention patent application after publication |