Law database query system and method

Abstract

The embodiment of the invention relates to the technical field of law databases, and particularly discloses a law database query system and method. According to the embodiment of the invention, the method comprises the steps: determining a law query theme and a law query purpose through the initialization query interaction with a user; selecting a plurality of related law databases, and constructing a target law database; receiving query key information input by a user, and performing step-by-step retrieval in the target law database to obtain a retrieval query result; and determining a plurality of pieces of law query information, identifying and evaluating the plurality of pieces of law query information, screening a plurality of pieces of main query information, and performing integration processing. Initialized query interaction, selection of a plurality of related law databases, construction of a target law database, receiving of query key information input by a user, and step-by-step retrieval, identification and evaluation can be performed, so that the quality and efficiency of law database query are improved, query matching errors are reduced, really valuable information is quickly screened for the user, and the user experience is improved. And the user experience is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of legal databases, and in particular to a legal database query system and method. Background Art

[0002] Legal database is an important tool in the field of law. It is mainly used to store, retrieve and manage law-related data and information. It usually contains a large amount of laws, regulations, case law, legal literature, etc., providing convenient data support for legal practitioners, researchers and scholars.

[0003] In the prior art, the query method of legal databases is usually relatively simple and cannot fully understand and process complex legal terms, legal structure and semantic relationships, resulting in matching errors between the keywords entered by users and the actual information required. Users may need to spend a lot of time screening truly valuable information from a large number of search results, affecting the user experience. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a legal database query system and method, aiming to solve the problems raised in the background technology.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions: A method for querying a legal database, the method specifically comprising the following steps: Initialize query interaction with the user, determine the legal query subject and legal query purpose, and obtain multiple legal query elements; According to the legal inquiry subject, the legal inquiry purpose and the legal inquiry elements, multiple relevant legal databases are selected, and permissions are acquired to construct a target legal database; Receiving key query information input by a user, performing a step-by-step search in the target legal database, and obtaining a search query result; According to the search query results, multiple legal query information are determined, the multiple legal query information are identified and evaluated, and multiple main query information are screened and integrated.

[0006] As a further limitation of the technical solution of the embodiment of the present invention, the initialization query interaction with the user, determining the legal query subject and the legal query purpose, and obtaining multiple legal query elements specifically include the following steps: Perform initial query interaction and record query interaction information; Performing subject identification on the query interaction information to determine the legal query subject; Performing purpose matching on the query interaction information to determine the purpose of the legal inquiry; The query interaction information is subjected to element refinement analysis to obtain a plurality of legal query elements.

[0007] As a further limitation of the technical solution of the embodiment of the present invention, the step of selecting multiple relevant legal databases based on the legal query subject, the legal query purpose and multiple legal query elements, and obtaining permissions to construct a target legal database specifically includes the following steps: According to the legal inquiry subject and the legal inquiry purpose, matching multiple required legal databases; According to the plurality of legal query elements, the plurality of required legal databases are screened and a plurality of relevant legal databases are marked; Obtaining access rights to multiple relevant legal databases; Obtaining database access rights to the plurality of relevant legal databases through the plurality of access rights channels; Based on the access rights of the plurality of databases, a plurality of related legal databases are virtually integrated to construct a target legal database.

[0008] As a further limitation of the technical solution of the embodiment of the present invention, the receiving of the query key information input by the user, performing step-by-step search in the target legal database, and obtaining the search query results specifically include the following steps: Create a precise query interface; In the precise query interface, receiving key query information input by a user; Identify the query key information, extract multiple query keywords, and obtain the logical relationship between the multiple query keywords; According to the plurality of query keywords and corresponding logical relationships, a step-by-step search is performed in the target legal database to obtain a search query result.

[0009] As a further limitation of the technical solution of the embodiment of the present invention, the determining of multiple legal query information according to the search query result, identifying and evaluating the multiple legal query information, screening multiple main query information and integrating them specifically include the following steps: Determining multiple legal query information according to the search query results; Identify and evaluate multiple legal inquiry information and screen multiple major inquiry information; Arrange, summarize and compare the plurality of main query information to generate integrated comparison query information.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the identifying and evaluating the multiple legal query information and screening the multiple main query information specifically include the following steps: According to a plurality of preset identification categories, multiple legal inquiry information is browsed and identified, and a plurality of corresponding browsing identification information is recorded; Evaluate the plurality of browsing identification information to generate information evaluation scores; Comparing the plurality of information evaluation scores with a preset standard evaluation score to generate a score comparison result; According to the score comparison result, a plurality of main query information is screened from the plurality of legal query information.

[0011] A legal database query system, the system comprises an initialization query interaction unit, a target legal database construction unit, a database step-by-step retrieval unit and a query identification evaluation unit, wherein: An initialization query interaction unit, used to perform initialization query interaction with the user, determine the legal query subject and legal query purpose, and obtain multiple legal query elements; A target legal database construction unit, used to select multiple relevant legal databases according to the legal query subject, the legal query purpose and multiple legal query elements, and obtain permissions to construct a target legal database; A database step-by-step search unit, used to receive key query information input by a user, perform step-by-step search in the target legal database, and obtain search query results; The query identification and evaluation unit is used to determine multiple legal query information based on the search query results, identify and evaluate the multiple legal query information, screen multiple main query information and integrate them.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the initialization query interaction unit specifically includes: The query interaction module is used to initialize the query interaction and record the query interaction information; A subject identification module, used to identify the subject of the query interaction information and determine the subject of the legal query; A purpose matching module, used to perform purpose matching on the query interaction information to determine the purpose of the legal inquiry; The element refinement analysis module is used to perform element refinement analysis on the query interaction information to obtain multiple legal query elements.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the target legal database construction unit specifically includes: A database matching module, used to match multiple required legal databases according to the legal query subject and the legal query purpose; A database screening module, used to screen the plurality of required legal databases according to the plurality of legal query elements, and mark the plurality of relevant legal databases; A channel acquisition module, used to obtain access permission channels for a plurality of the relevant legal databases; A permission acquisition module, used to acquire database access permissions of a plurality of the relevant legal databases through a plurality of the access permission channels; The virtual integration module is used to virtually integrate multiple related legal databases according to the multiple database access permissions to construct a target legal database.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the query identification and evaluation unit specifically includes: An information determination module, used to determine a plurality of legal inquiry information according to the search query result; The identification and evaluation module is used to identify and evaluate multiple legal inquiry information and screen multiple main inquiry information; The information integration module is used to organize, summarize and compare the plurality of main query information to generate integrated comparison query information.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The embodiment of the present invention determines the subject and purpose of legal query by initializing query interaction with the user; selects multiple relevant legal databases to construct a target legal database; receives key query information input by the user, performs step-by-step search in the target legal database, and obtains search query results; determines multiple legal query information, identifies and evaluates the multiple legal query information, and screens multiple main query information and performs integrated processing. It is capable of initializing query interaction, selecting multiple relevant legal databases, constructing a target legal database, and then receiving key query information input by the user, performing step-by-step search, identification and evaluation, improving the quality and efficiency of legal database queries, reducing query matching errors, and quickly screening truly valuable information for users, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0017] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0018] Figure 2 A flow chart of initializing query interaction in the method provided by an embodiment of the present invention is shown.

[0019] Figure 3 A flow chart of constructing a target legal database in the method provided by an embodiment of the present invention is shown.

[0020] Figure 4 A flow chart of obtaining search query results in the method provided in an embodiment of the present invention is shown.

[0021] Figure 5 A flow chart of the identification and evaluation of legal inquiry information in the method provided by an embodiment of the present invention is shown.

[0022] Figure 6 A flow chart of screening multiple main query information in the method provided by an embodiment of the present invention is shown.

[0023] Figure 7 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0024] Figure 8 A structural block diagram of an initialization query interaction unit in a system provided by an embodiment of the present invention is shown.

[0025] Fig. 9 The structure block diagram of the target legal database construction unit in the system provided by the embodiment of the present invention is shown.

[0026] Fig.10 The structure block diagram of the query identification and evaluation unit in the system provided by the embodiment of the present invention is shown. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0028] It is understandable that in the prior art, the query method of the legal database is usually relatively simple and cannot fully understand and process complex legal terms, legal structure and semantic relationships, resulting in a matching error between the keywords entered by the user and the actual information required. The user may need to spend a lot of time screening out truly valuable information from a large number of search results, affecting the user's experience.

[0029] To solve the above problems, the embodiment of the present invention performs initial query interaction with the user, determines the legal query subject and legal query purpose, and obtains multiple legal query elements; selects multiple relevant legal databases according to the legal query subject, legal query purpose and multiple legal query elements, obtains permissions, and constructs a target legal database; receives the query key information input by the user, performs step-by-step search in the target legal database, and obtains the search query results; determines multiple legal query information according to the search query results, identifies and evaluates the multiple legal query information, screens multiple main query information and integrates them. It is possible to perform initial query interaction, select multiple relevant legal databases, construct a target legal database, and then receive the query key information input by the user, perform step-by-step search, identification and evaluation, improve the quality and efficiency of legal database queries, reduce query matching errors, quickly screen truly valuable information for users, and enhance the user experience.

[0030] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0031] Specifically, a method for querying a legal database comprises the following steps: Step S101, initializing query interaction with the user, determining the legal query subject and legal query purpose, and obtaining multiple legal query elements.

[0032] In an embodiment of the present invention, when a user needs to conduct a legal database query, an initial query interaction is first performed with the user, and query interaction information is recorded. The legal query subject is determined by subject identification of the query interaction information, and the purpose of the query interaction information is matched to determine the legal query purpose. At the same time, the query interaction information is analyzed in element refinement to obtain multiple legal query elements, wherein the legal query subject is a clear legal issue or research topic; the legal query purpose may be obtaining legal texts, searching for judicial cases, obtaining academic opinions, or obtaining practical guidelines; and multiple legal query elements may include legal keywords, regulatory clauses, time ranges, geographical ranges, and court levels.

[0033] Specifically, Figure 2 A flow chart of initializing query interaction in the method provided by an embodiment of the present invention is shown.

[0034] Among them, in the preferred implementation mode provided by the present invention, the initialization query interaction with the user, determining the legal query subject and legal query purpose, and obtaining multiple legal query elements specifically include the following steps: Step S1011, initializing query interaction and recording query interaction information; Step S1012, performing subject identification on the query interaction information to determine a legal query subject; Step S1013, performing purpose matching on the query interaction information to determine the purpose of the legal query; Step S1014: performing element refinement analysis on the query interaction information to obtain multiple legal query elements.

[0035] The step of performing element refinement analysis on the query interaction information to obtain multiple legal query elements specifically includes the following steps: Preliminarily analyzing the query interaction information, identifying and extracting preliminary element keywords; Use natural language processing technology to understand the semantics of the preliminary element keywords and identify multi-level semantic relationships; Extract relevant background information from known legal databases or public legal documents based on preliminary element keywords and multi-level semantic relationships to supplement the background information of the user's query topic; Classify the preliminary factor keywords and the background information of the user query topic according to multiple dimensions to obtain multiple factors; Set weights for each factor and adjust the weight ratio of each factor based on the user's query intent and the background information of the user's query topic. Use graph database to analyze the correlation between various elements and construct a correlation matrix; In combination with the user's query purpose, related element combinations are selected from the relevance matrix, and multiple rounds of interactions are carried out through the user feedback mechanism. Through guided questions or option prompts, the degree of refinement of the elements is dynamically adjusted and optimized to ensure the accuracy and relevance of the query results, and to obtain legal query elements.

[0036] Furthermore, the legal database query method further includes the following steps: Step S102, according to the legal query subject, the legal query purpose and the plurality of legal query elements, multiple relevant legal databases are selected, and permissions are acquired to construct a target legal database.

[0037] In an embodiment of the present invention, an initial database match is performed based on the legal query subject and the legal query purpose to determine multiple required legal databases. Then, according to multiple legal query elements, the multiple required legal databases are screened, multiple selected related legal databases are marked, and access permission channels for the multiple related legal databases are obtained. Then, through the multiple access permission channels, database access permissions for the multiple related legal databases are obtained. Based on the multiple database access permissions, the multiple related legal databases are virtually integrated to construct a target legal database.

[0038] Specifically, Figure 3A flow chart of constructing a target legal database in the method provided by an embodiment of the present invention is shown.

[0039] Among them, in the preferred implementation mode provided by the present invention, the selection of multiple relevant legal databases according to the legal query subject, the legal query purpose and multiple legal query elements, and obtaining of permissions, and the construction of the target legal database specifically includes the following steps: Step S1021, matching multiple required legal databases according to the legal query subject and the legal query purpose; Step S1022, screening the plurality of required legal databases according to the plurality of legal query elements, and marking a plurality of relevant legal databases; Step S1023, obtaining access rights channels for the plurality of relevant legal databases; Step S1024, obtaining database access rights of a plurality of the relevant legal databases through a plurality of the access right channels; Step S1025, based on the plurality of database access permissions, virtually integrate the plurality of related legal databases to construct a target legal database.

[0040] Furthermore, based on the plurality of database access permissions, a plurality of related legal databases are virtually integrated to construct a target legal database, specifically including the following steps: Create a virtual database dictionary to store the integration results of each database; Checking access rights, and if there is access rights, preprocessing the data in the database, and generating metadata based on the preprocessed data, wherein the metadata includes creation time, data volume, and source information; Calculate the integration score based on the hash values ​​of all databases, and integrate the preprocessed data, generated metadata and integration scores into a dictionary; Add the processing results of each database to the virtual database dictionary; where the key is the database name and the value is a dictionary containing pre-processed data, metadata, and integrated scores; The virtual database dictionary is deduplicated and index optimized to obtain the target legal database.

[0041] Furthermore, the legal database query method further includes the following steps: Step S103, receiving the query key information input by the user, performing a step-by-step search in the target legal database, and obtaining the search query results.

[0042] In an embodiment of the present invention, a precise query interface is created, in which query key information input by a user is received, the query key information is identified, multiple query keywords are extracted, and logical analysis is performed on the multiple query keywords to obtain the logical relationship between the multiple query keywords, and then a step-by-step search is performed in the target legal database according to the multiple query keywords and the corresponding logical relationships to obtain the search query results, wherein the query keywords must be professional and accurate legal terms; the logical relationships include "and", "or", "not", etc.

[0043] Specifically, Figure 4 A flow chart of obtaining search query results in the method provided in an embodiment of the present invention is shown.

[0044] Among them, in the preferred embodiment provided by the present invention, the receiving of the query key information input by the user, performing step-by-step search in the target legal database, and obtaining the search query results specifically include the following steps: Step S1031, creating a precise query interface; Step S1032, receiving key query information input by the user in the precise query interface; Step S1033, identifying the query key information, extracting multiple query keywords, and obtaining the logical relationship between the multiple query keywords; Step S1034, performing a step-by-step search in the target legal database according to the plurality of query keywords and corresponding logical relationships, and obtaining a search query result.

[0045] Further, according to the plurality of query keywords and corresponding logical relationships, performing step-by-step searches in the target legal database to obtain search query results specifically includes the following steps: Check whether a weight is provided for each query keyword. If not, assign a default weight to each keyword. The key is the keyword and the value is the weight. The default weight is 1.0. Create an empty list for storing query expression trees, add the first keyword directly to the query expression tree, and start from the second keyword to combine the current query expression tree, the logical relationship and the current keyword into a new query expression tree; wherein the query expression tree includes at least a left sub-query expression tree and a right sub-query expression tree; If the query expression tree is a single keyword, the keyword is searched in the target database and the matching results and corresponding weights are returned; If the query expression tree is a logical combination, recursively evaluate the left subquery expression tree and the right subquery expression tree to obtain their respective evaluation results and weights; The evaluation result list is sorted from high to low according to the score to ensure that the evaluation results with higher weights are displayed first to obtain the search query results.

[0046] For logical "and", the data items that appear in the evaluation results of both the left subquery expression tree and the right subquery expression tree are returned, and the weight is the sum of the weights of the left subquery expression tree and the right subquery expression tree; For logical "or", the evaluation results of the left subquery expression tree and the right subquery expression tree are merged and the weights are accumulated; For logical "not", the data items in the evaluation result of the left subquery expression tree that are not included in the evaluation result of the right subquery expression tree are returned, and the weight of the left subquery expression tree is retained.

[0047] Furthermore, the legal database query method further includes the following steps: Step S104, determining a plurality of legal query information according to the search query result, identifying and evaluating the plurality of legal query information, screening a plurality of main query information and integrating them.

[0048] In an embodiment of the present invention, based on the search query results, multiple legal query information are determined, and according to the preset multiple identification categories, the multiple legal query information are browsed and identified, and multiple corresponding browsing identification information are recorded. Then, the multiple browsing identification information is evaluated to generate information evaluation scores, and by comparing the multiple information evaluation scores with the preset standard evaluation scores, a score comparison result is generated. Then, based on the score comparison result, multiple main query information are screened from the multiple legal query information, and the multiple main query information are sorted, summarized and compared to generate integrated comparison query information, wherein browsing identification is the process of identifying the content of the titles, abstracts, sources, publication dates, etc. of the multiple legal query information; evaluating the multiple browsing identification information is to evaluate the reliability of the source, the professionalism of the author, the accuracy of the content, and the timeliness of the information.

[0049] Specifically, Figure 5 A flow chart of the identification and evaluation of legal inquiry information in the method provided by an embodiment of the present invention is shown.

[0050] Among them, in the preferred embodiment provided by the present invention, the determining of multiple legal query information according to the search query result, identifying and evaluating the multiple legal query information, screening multiple main query information and integrating them specifically include the following steps: Step S1041, determining a plurality of legal inquiry information according to the search query result; Step S1042, identifying and evaluating multiple legal inquiry information, and screening multiple main inquiry information; Step S1043, sorting, summarizing and comparing the plurality of main query information to generate integrated comparison query information.

[0051] Specifically, Figure 6 A flow chart of screening multiple main query information in the method provided by an embodiment of the present invention is shown.

[0052] Among them, in the preferred implementation mode provided by the present invention, the identifying and evaluating the multiple legal query information and screening the multiple main query information specifically include the following steps: Step S10421, browsing and identifying the plurality of legal inquiry information according to the preset plurality of identification categories, and recording a plurality of corresponding browsing identification information; Step S10422, evaluating the plurality of browsing identification information to generate information evaluation scores; Step S10423, comparing the plurality of information evaluation scores with a preset standard evaluation score to generate a score comparison result; Step S10424, based on the score comparison result, filter multiple main query information from the multiple legal query information.

[0053] Among them, in the preferred implementation mode provided by the present invention, the step of evaluating the plurality of browsing identification information and generating information evaluation scores specifically comprises the following steps: Determine all query keywords provided by users and the importance weight of each query keyword; Analyze the semantic similarity between each browsing identification information and each query keyword to obtain the matching results between the browsing identification information and different query keywords; Perform a weighted summation of the matching results and the corresponding importance weights, and then obtain the average value of the weighted summation results to obtain the content relevance score; Obtain the source of each browsing identification information and set a basic trust score based on the authority of the source; The basic trust score is adjusted using the historical error information of the browsing identification information as an adjustment coefficient to obtain a trustworthy score; Obtain several key elements of legal information, including article citation, case support, analysis and argumentation, and conclusion and suggestion, and give corresponding weight to each key element; Scoring the coverage of key elements based on the browsing identification information to obtain element scores; Sum up all factor scores to get the completeness score; Obtain the publishing time of the browsing identification information and the current time of the user's query, and obtain the time difference between the publishing time and the current time; Each browsing identification information is given an initial score, and the corresponding initial score is adjusted by applying a decay coefficient according to the time difference to obtain a timeliness score; The content relevance score, trustworthiness score, factor score and timeliness score are weighted and summed to obtain the information evaluation score.

[0054] In the embodiment of the present invention, information is evaluated based on four dimensions: content relevance, source credibility, information integrity, and information timeliness, so that the scoring result is more comprehensive and can avoid the one-sidedness that may occur in traditional single-dimensional screening.

[0055] Furthermore, Figure 7 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0056] Among them, in another preferred embodiment provided by the present invention, a legal database query system includes: The initialization query interaction unit 101 is used to perform initialization query interaction with the user, determine the legal query subject and the legal query purpose, and obtain multiple legal query elements.

[0057] In an embodiment of the present invention, when a user needs to perform a legal database query, the initialization query interaction unit 101 first performs an initialization query interaction with the user, records the query interaction information, determines the legal query subject by subject identification of the query interaction information, and performs purpose matching on the query interaction information to determine the legal query purpose. At the same time, the query interaction information is subjected to element refinement analysis to obtain multiple legal query elements, wherein the legal query subject is a clear legal issue or research topic; the legal query purpose may be obtaining legal texts, searching for judicial cases, obtaining academic opinions, or obtaining practical guidelines, etc.; multiple legal query elements may include legal keywords, regulatory clauses, time ranges, geographical ranges, and court levels, etc.

[0058] Specifically, Figure 8 It shows a structural block diagram of the initialization query interaction unit 101 in the system provided by an embodiment of the present invention.

[0059] In a preferred embodiment of the present invention, the initialization query interaction unit 101 specifically includes: The query interaction module 1011 is used to initialize the query interaction and record the query interaction information; A topic identification module 1012 is used to perform topic identification on the query interaction information to determine a legal query topic; Purpose matching module 1013, used to perform purpose matching on the query interaction information to determine the purpose of the legal query; The element refinement analysis module 1014 is used to perform element refinement analysis on the query interaction information to obtain multiple legal query elements.

[0060] Furthermore, the legal database query system also includes: The target legal database construction unit 102 is used to select multiple relevant legal databases according to the legal query subject, the legal query purpose and multiple legal query elements, and obtain permissions to construct a target legal database.

[0061] In an embodiment of the present invention, the target law database construction unit 102 performs initial database matching according to the legal query subject and the legal query purpose, determines multiple required legal databases, and then screens the multiple required legal databases according to multiple legal query elements, marks multiple selected related legal databases, and obtains access permission channels for multiple related legal databases, and then obtains database access permissions of multiple related legal databases through multiple access permission channels, and virtually integrates multiple related legal databases according to multiple database access permissions to construct a target legal database.

[0062] Specifically, Fig. 9 It shows a structural block diagram of the target legal database construction unit 102 in the system provided by the embodiment of the present invention.

[0063] Among them, in the preferred embodiment provided by the present invention, the target legal database construction unit 102 specifically includes: A database matching module 1021 is used to match multiple required legal databases according to the legal query subject and the legal query purpose; A database screening module 1022, for screening the plurality of required legal databases according to the plurality of legal query elements, and marking a plurality of relevant legal databases; A channel acquisition module 1023, used to acquire access rights channels of a plurality of the relevant legal databases; The permission acquisition module 1024 is used to acquire database access permissions of the plurality of relevant legal databases through the plurality of access permission channels; The virtual integration module 1025 is used to virtually integrate multiple related legal databases according to the multiple database access permissions to construct a target legal database.

[0064] Furthermore, the legal database query system also includes: The database step-by-step search unit 103 is used to receive the query key information input by the user, perform step-by-step search in the target legal database, and obtain the search query results.

[0065] In the embodiment of the present invention, the database step-by-step retrieval unit 103 creates a precise query interface, receives the query key information input by the user in the precise query interface, identifies the query key information, extracts multiple query keywords, and performs logical analysis on the multiple query keywords to obtain the logical relationship between the multiple query keywords, and then performs a step-by-step search in the target legal database according to the multiple query keywords and the corresponding logical relationships to obtain the search query results, wherein the query keywords must be professional and accurate legal terms; the logical relationships include "and", "or", "not", etc.

[0066] The query identification and evaluation unit 104 is used to determine multiple legal query information according to the search query result, identify and evaluate the multiple legal query information, screen multiple main query information and perform integration processing.

[0067] In an embodiment of the present invention, the query identification and evaluation unit 104 determines multiple legal query information based on the retrieval query results, browses and identifies the multiple legal query information according to multiple preset identification categories, records multiple corresponding browsing identification information, and then evaluates the multiple browsing identification information to generate information evaluation scores, and generates score comparison results by comparing the multiple information evaluation scores with preset standard evaluation scores, and then based on the score comparison results, screens multiple main query information from the multiple legal query information, organizes, summarizes and compares the multiple main query information to generate integrated comparison query information, wherein browsing identification is the process of identifying the content of the titles, abstracts, sources, publication dates, etc. of the multiple legal query information; evaluating the multiple browsing identification information is to evaluate the reliability of the source, the professionalism of the author, the accuracy of the content and the timeliness of the information.

[0068] Specifically, Fig.10 It shows a structural block diagram of the query identification and evaluation unit 104 in the system provided by an embodiment of the present invention.

[0069] In a preferred embodiment of the present invention, the query identification and evaluation unit 104 specifically includes: An information determination module 1041, used to determine a plurality of legal inquiry information according to the search query result; The identification and evaluation module 1042 is used to identify and evaluate multiple legal inquiry information and screen multiple main inquiry information; The information integration module 1043 is used to organize, summarize and compare the plurality of main query information to generate integrated comparison query information.

[0070] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0071] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0072] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0073] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0074] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for querying a legal database, characterized in that: The method specifically comprises the following steps: Initialize query interaction with the user, determine the legal query subject and legal query purpose, and obtain multiple legal query elements; According to the legal inquiry subject, the legal inquiry purpose and the legal inquiry elements, multiple relevant legal databases are selected, and permissions are acquired to construct a target legal database; Receiving key query information input by a user, performing a step-by-step search in the target legal database, and obtaining a search query result; Determine multiple legal query information based on the search query results, identify and evaluate the multiple legal query information, screen multiple main query information and integrate them; The initialization query interaction with the user, determining the legal query subject and legal query purpose, and obtaining multiple legal query elements specifically includes the following steps: Perform initial query interaction and record query interaction information; Performing subject identification on the query interaction information to determine the legal query subject; Performing purpose matching on the query interaction information to determine the purpose of the legal inquiry; The query interaction information is subjected to element refinement analysis to obtain a plurality of legal query elements.

2. The legal database query method according to claim 1, characterized in that: Performing element refinement analysis on the query interaction information to obtain multiple legal query elements specifically includes the following steps: Preliminarily parsing the query interaction information, identifying and extracting preliminary element keywords; Use natural language processing technology to understand the semantics of the preliminary element keywords and identify multi-level semantic relationships; Extract relevant background information from known legal databases or public legal documents based on preliminary element keywords and multi-level semantic relationships to supplement the background information of the user's query topic; Classify the preliminary factor keywords and the background information of the user query topic according to multiple dimensions to obtain multiple factors; Set weights for each factor and adjust the weight ratio of each factor based on the specific circumstances of the user's query intent and the background information of the user's query topic; Use graph database to analyze the correlation between various elements and construct a correlation matrix; According to the user's query purpose, a combination of related elements is selected from the correlation matrix, and multiple rounds of interaction are carried out through the user feedback mechanism. The degree of refinement of the elements is dynamically adjusted and optimized to ensure the accuracy and relevance of the query results, and the legal query elements are obtained.

3. The legal database query method according to claim 2, characterized in that: The step of selecting multiple relevant legal databases according to the legal query subject, the legal query purpose and multiple legal query elements, and obtaining permissions to construct a target legal database specifically includes the following steps: According to the legal inquiry subject and the legal inquiry purpose, matching multiple required legal databases; According to the plurality of legal query elements, the plurality of required legal databases are screened and a plurality of relevant legal databases are marked; Obtaining access rights to multiple relevant legal databases; Obtaining database access rights to the plurality of relevant legal databases through the plurality of access rights channels; Based on the access rights of the plurality of databases, a plurality of related legal databases are virtually integrated to construct a target legal database.

4. The legal database query method according to claim 3, characterized in that: Based on the access rights of the plurality of databases, a plurality of relevant legal databases are virtually integrated to construct a target legal database, specifically comprising the following steps: Create a virtual database dictionary to store the integration results of each database; Checking access rights, and if there is access rights, preprocessing the data in the database, and generating metadata based on the preprocessed data, wherein the metadata includes creation time, data volume, and source information; Calculate the integration score based on the hash values ​​of all databases, and integrate the preprocessed data, generated metadata and integration scores into a dictionary; Add the processing results of each database to the virtual database dictionary; where the key is the database name and the value is a dictionary containing pre-processed data, metadata, and integrated scores; The virtual database dictionary is deduplicated and index optimized to obtain the target legal database.

5. The legal database query method according to claim 4, characterized in that: The receiving of the query key information input by the user, performing step-by-step search in the target legal database, and obtaining the search query results specifically include the following steps: Create a precise query interface; In the precise query interface, receiving key query information input by a user; Identify the query key information, extract multiple query keywords, and obtain the logical relationship between the multiple query keywords; According to the plurality of query keywords and corresponding logical relationships, a step-by-step search is performed in the target legal database to obtain a search query result.

6. The method for querying a legal database according to claim 5, characterized in that: According to the plurality of query keywords and corresponding logical relationships, performing step-by-step searches in the target legal database to obtain search query results specifically includes the following steps: Check whether a weight is provided for each query keyword. If not, assign a default weight to each keyword. The key is the keyword and the value is the weight. Create an empty list for storing query expression trees, add the first keyword directly to the query expression tree, and start from the second keyword to combine the current query expression tree, the logical relationship and the current keyword into a new query expression tree; wherein the query expression tree includes at least a left sub-query expression tree and a right sub-query expression tree; If the query expression tree is a single keyword, the keyword is searched in the target database and the matching results and corresponding weights are returned; If the query expression tree is a logical combination, recursively evaluate the left subquery expression tree and the right subquery expression tree to obtain their respective evaluation results and weights; Sort the evaluation result list from high to low according to the score, ensuring that the evaluation results with higher weights are displayed first, and obtain the search query results; Among them, the logical combination includes logical "and", logical "or", and logical "not"; For logical "and", the data items that appear in the evaluation results of both the left subquery expression tree and the right subquery expression tree are returned, and the weight is the sum of the weights of the left subquery expression tree and the right subquery expression tree; For logical "or", the evaluation results of the left subquery expression tree and the right subquery expression tree are merged and the weights are accumulated; For logical "not", the data items in the evaluation result of the left subquery expression tree that are not included in the evaluation result of the right subquery expression tree are returned, and the weight of the left subquery expression tree is retained.

7. The method for querying a legal database according to claim 6, characterized in that: The step of determining a plurality of legal inquiry information according to the search query results, identifying and evaluating the plurality of legal inquiry information, screening a plurality of main inquiry information and integrating them specifically comprises the following steps: Determining multiple legal query information according to the search query results; Identify and evaluate multiple legal inquiry information and screen multiple major inquiry information; Arrange, summarize and compare the plurality of main query information to generate integrated comparison query information.

8. The method for querying a legal database according to claim 7, characterized in that: The identification and evaluation of multiple legal inquiry information and the screening of multiple main inquiry information specifically include the following steps: According to a plurality of preset identification categories, multiple legal inquiry information is browsed and identified, and a plurality of corresponding browsing identification information is recorded; Evaluate the plurality of browsing identification information to generate information evaluation scores; Comparing the plurality of information evaluation scores with a preset standard evaluation score to generate a score comparison result; According to the score comparison result, a plurality of main query information is screened from the plurality of legal query information.

9. The method for querying a legal database according to claim 7, characterized in that: Evaluating the plurality of browsing identification information to generate information evaluation scores specifically includes the following steps: Determine all query keywords provided by users and the importance weight of each query keyword; Analyze the semantic similarity between each browsing identification information and each query keyword to obtain the matching results between the browsing identification information and different query keywords; Perform a weighted summation of the matching results and the corresponding importance weights, and then obtain the average value of the weighted summation results to obtain the content relevance score; Obtain the source of each browsing identification information and set a basic trust score based on the authority of the source; The basic trust score is adjusted using the historical error information of the browsing identification information as an adjustment coefficient to obtain a trustworthy score; Obtain several key elements of legal information, including article citation, case support, analysis and argumentation, and conclusion and suggestion, and give corresponding weight to each key element; Scoring the coverage of key elements based on the browsing identification information to obtain element scores; Sum up all factor scores to get the completeness score; Obtain the publishing time of the browsing identification information and the current time of the user's query, and obtain the time difference between the publishing time and the current time; Each browsing identification information is given an initial score, and the corresponding initial score is adjusted by applying a decay coefficient according to the time difference to obtain a timeliness score; The content relevance score, trustworthiness score, factor score and timeliness score are weighted and summed to obtain the information evaluation score.

10. A legal database query system, the system applying the legal database query method according to any one of claims 1 to 9, characterized in that: The system includes an initialization query interaction unit, a target law database construction unit, a database step-by-step retrieval unit, and a query identification evaluation unit, wherein: An initialization query interaction unit, used to perform initialization query interaction with the user, determine the legal query subject and legal query purpose, and obtain multiple legal query elements; A target legal database construction unit, used to select multiple relevant legal databases according to the legal query subject, the legal query purpose and multiple legal query elements, and obtain permissions to construct a target legal database; A database step-by-step search unit, used to receive key query information input by a user, perform step-by-step search in the target legal database, and obtain search query results; A query identification and evaluation unit, used to determine a plurality of legal query information according to the search query result, identify and evaluate the plurality of legal query information, screen a plurality of main query information and perform integration processing; The initialization query interaction unit specifically includes: The query interaction module is used to initialize the query interaction and record the query interaction information; A subject identification module, used to identify the subject of the query interaction information and determine the subject of the legal query; A purpose matching module, used to perform purpose matching on the query interaction information to determine the purpose of the legal inquiry; An element refinement analysis module, used to perform element refinement analysis on the query interaction information to obtain multiple legal query elements; The target legal database construction unit specifically includes: A database matching module, used to match multiple required legal databases according to the legal query subject and the legal query purpose; A database screening module, used to screen the plurality of required legal databases according to the plurality of legal query elements, and mark the plurality of relevant legal databases; A channel acquisition module, used to obtain access permission channels for a plurality of the relevant legal databases; A permission acquisition module, used to acquire database access permissions of a plurality of the relevant legal databases through a plurality of the access permission channels; A virtual integration module, used to virtually integrate multiple related legal databases according to the multiple database access permissions to construct a target legal database; The query identification and evaluation unit specifically includes: An information determination module, used to determine a plurality of legal inquiry information according to the search query result; The identification and evaluation module is used to identify and evaluate multiple legal inquiry information and screen multiple main inquiry information; The information integration module is used to organize, summarize and compare the plurality of main query information to generate integrated comparison query information.

Images