A legal database query system and method

Abstract

The embodiment of the application relates to the technical field of legal database, and specifically discloses a legal database query system and method. The embodiment of the application determines a legal query theme and a legal query purpose through initialization query interaction with a user, selects multiple related legal databases, constructs a target legal database, receives query key information input by the user, performs step-by-step retrieval in the target legal database, obtains a retrieval query result, determines multiple legal query information, identifies and evaluates the multiple legal query information, filters multiple main query information, and performs integration processing. The initialization query interaction can be performed, the multiple related legal databases can be selected, the target legal database can be constructed, the query key information input by the user can be received, step-by-step retrieval and identification and evaluation can be performed, the quality and efficiency of legal database query are improved, the error of query matching is reduced, the user can quickly filter truly valuable information, and the use experience of the user is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of legal database, and particularly relates to a legal database query system and method. BACKGROUND

[0002] A legal database is an important tool in the field of law, mainly used for storing, retrieving and managing data and information related to law, and usually contains a large amount of legal regulations, cases, legal documents and other contents, providing convenient data support for legal practitioners, researchers and scholars.

[0003] In the prior art, the legal database query method is usually simple, and cannot completely understand and process complex legal terms, article structures and semantic relationships, resulting in a matching error between the keywords input by the user and the actual required information, and the user may need to spend a lot of time in screening valuable information from a large number of search results, affecting the user experience. SUMMARY

[0004] The purpose of the embodiments of the application is to provide a legal database query system and method, which aims to solve the problems proposed in the background art.

[0005] To achieve the above-mentioned purpose, the embodiments of the application provide the following technical solutions:

[0006] A legal database query method, the method specifically comprises the following steps:

[0007] initializing query interaction with the user, determining a legal query theme and a legal query purpose, and obtaining a plurality of legal query elements;

[0008] According to the legal query theme, the legal query purpose and the plurality of legal query elements, a plurality of related legal databases are selected, and permission is obtained to build a target legal database;

[0009] receiving the query key information input by the user, performing step-by-step retrieval in the target legal database, and obtaining a retrieval query result;

[0010] According to the retrieval query result, a plurality of legal query information is determined, the plurality of legal query information is identified and evaluated, a plurality of main query information is screened and integrated.

[0011] As a further limitation of the technical solutions of the embodiments of the application, the initializing query interaction with the user, determining the legal query theme and the legal query purpose, and obtaining the plurality of legal query elements specifically comprises the following steps:

[0012] initializing query interaction, and recording query interaction information;

[0013] Subject identification is performed on the query interaction information to determine a legal query subject;

[0014] Purpose matching is performed on the query interaction information to determine a legal query purpose;

[0015] Element refinement analysis is performed on the query interaction information to obtain a plurality of legal query elements.

[0016] As a further limitation of the technical scheme of the embodiment of the present application, the selection of a plurality of related legal databases according to the legal query subject, the legal query purpose and a plurality of legal query elements, and the acquisition of access rights to construct a target legal database specifically comprises the following steps:

[0017] A plurality of demand legal databases are matched according to the legal query subject and the legal query purpose;

[0018] The plurality of demand legal databases are screened according to a plurality of legal query elements, and a plurality of related legal databases are marked;

[0019] Access channels of the plurality of related legal databases are acquired;

[0020] Database access rights of the plurality of related legal databases are acquired through the plurality of access channels;

[0021] The plurality of related legal databases are virtually integrated according to the plurality of database access rights to construct a target legal database.

[0022] As a further limitation of the technical scheme of the embodiment of the present application, the reception of user input query key information and the step-by-step retrieval in the target legal database to obtain a retrieval query result specifically comprises the following steps:

[0023] A precise query interface is created;

[0024] User input query key information is received in the precise query interface;

[0025] The query key information is identified to extract a plurality of query keywords and obtain a logical relationship between the plurality of query keywords;

[0026] Step-by-step retrieval is performed in the target legal database according to the plurality of query keywords and the corresponding logical relationship to obtain a retrieval query result.

[0027] As a further limitation of the technical scheme of the embodiment of the present application, the determination of a plurality of legal query information according to the retrieval query result, the identification and evaluation of the plurality of legal query information, the screening of a plurality of main query information and the integration processing specifically comprises the following steps:

[0028] According to the search query result, determine a plurality of legal query information;

[0029] Identify and evaluate the plurality of legal query information, and screen a plurality of main query information;

[0030] The plurality of main query information is arranged, summarized and compared to generate integrated comparison query information.

[0031] As a further limitation of the technical scheme of the embodiment of the application, the identification and evaluation of the plurality of legal query information, and the screening of the plurality of main query information specifically include the following steps:

[0032] According to the preset plurality of identification categories, the plurality of legal query information is browsed and identified, and a plurality of corresponding browsing identification information is recorded;

[0033] The browsing identification information is evaluated to generate an information evaluation score;

[0034] The information evaluation score is compared with the preset standard evaluation score to generate a score comparison result;

[0035] According to the score comparison result, the plurality of main query information is screened from the plurality of legal query information.

[0036] A legal database query system, the system includes an initialization query interaction unit, a target legal database construction unit, a database step-by-step search unit and a query identification and evaluation unit, wherein:

[0037] The initialization query interaction unit is used for initialization query interaction with the user, determines the legal query theme and the legal query purpose, and obtains a plurality of legal query elements;

[0038] The target legal database construction unit is used for selecting a plurality of related legal databases according to the legal query theme, the legal query purpose and a plurality of legal query elements, and obtaining permissions to construct a target legal database;

[0039] The database step-by-step search unit is used for receiving the query key information input by the user, and performing step-by-step search in the target legal database to obtain a search query result;

[0040] The query identification and evaluation unit is used for 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 performing integrated processing.

[0041] As a further limitation of the technical scheme of the embodiment of the application, the initialization query interaction unit specifically includes:

[0042] The query interaction module is configured to perform an initial query interaction and record query interaction information.

[0043] The subject identification module is configured to perform subject identification on the query interaction information and determine a legal query subject.

[0044] The purpose matching module is configured to perform purpose matching on the query interaction information and determine a legal query purpose.

[0045] The element refinement analysis module is configured to perform element refinement analysis on the query interaction information and obtain a plurality of legal query elements.

[0046] As a further limitation of the technical scheme of the embodiment of the present application, the target legal database construction unit specifically comprises:

[0047] The database matching module is configured to match a plurality of demand legal databases according to the legal query subject and the legal query purpose.

[0048] The database screening module is configured to screen a plurality of the demand legal databases according to a plurality of the legal query elements and mark a plurality of related legal databases.

[0049] The channel acquisition module is configured to acquire access permission channels of a plurality of the related legal databases.

[0050] The permission acquisition module is configured to acquire database access permissions of a plurality of the related legal databases through a plurality of the access permission channels.

[0051] The virtual integration module is configured to perform virtual integration on a plurality of related legal databases according to a plurality of the database access permissions and construct a target legal database.

[0052] As a further limitation of the technical scheme of the embodiment of the present application, the query identification and evaluation unit specifically comprises:

[0053] The information determination module is configured to determine a plurality of legal query information according to the search query result.

[0054] The identification and evaluation module is configured to identify and evaluate a plurality of legal query information and screen a plurality of main query information.

[0055] The information integration module is configured to integrate, summarize and compare a plurality of the main query information and generate integrated comparison query information.

[0056] Compared with the prior art, the present application has the following beneficial effects:

[0057] The embodiment of the application determines a legal query theme and a legal query purpose by carrying out an initial query interaction with a user, selects a plurality of relevant legal databases, constructs a target legal database, receives query key information input by the user, carries out step-by-step retrieval in the target legal database, obtains a retrieval query result, determines a plurality of legal query information, identifies and evaluates the plurality of legal query information, and filters and integrates a plurality of main query information. The initial query interaction, the selection of the plurality of relevant legal databases, the construction of the target legal database, the reception of the query key information input by the user, the step-by-step retrieval, the identification and evaluation, the improvement of the quality and efficiency of the legal database query, the reduction of the query matching error, the fast filtering of the truly valuable information for the user, and the improvement of the user experience are realized. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only show some of the embodiments of the application.

[0059] Figure 1 A flow chart of the method provided by the embodiment of the application is shown.

[0060] Figure 2 A flow chart of the initial query interaction in the method provided by the embodiment of the application is shown.

[0061] Figure 3 A flow chart of the construction of the target legal database in the method provided by the embodiment of the application is shown.

[0062] Figure 4 A flow chart of the obtaining of the retrieval query result in the method provided by the embodiment of the application is shown.

[0063] Figure 5 A flow chart of the identification and evaluation of the legal query information in the method provided by the embodiment of the application is shown.

[0064] Figure 6 A flow chart of the filtering of the plurality of main query information in the method provided by the embodiment of the application is shown.

[0065] Figure 7 An application architecture diagram of the system provided by the embodiment of the application is shown.

[0066] Figure 8 A structure block diagram of the initial query interaction unit in the system provided by the embodiment of the application is shown.

[0067] Figure 9 A structure block diagram of the target legal database construction unit in the system provided by the embodiment of the application is shown.

[0068] Figure 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

[0069] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to 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.

[0070] It is understandable that in the existing technology, the query method of legal database is usually relatively simple, and it is unable to 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 to screen truly valuable information from a large number of search results, affecting the user experience.

[0071] To solve the above problems, an 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 based on the legal query subject, legal query purpose and multiple legal query elements, obtains permissions, and constructs a target legal database; receives query key information input by the user, performs step-by-step retrieval in the target legal database, and obtains retrieval query results; determines multiple legal query information based on the retrieval query results, identifies and evaluates the multiple legal query information, screens multiple main query information, and integrates and processes them. It is capable of initializing query interaction, selecting multiple relevant legal databases, constructing a target legal database, and then receiving query key information input by the user, performing step-by-step retrieval, identification, and evaluation, thereby improving the quality and efficiency of legal database queries, reducing query matching errors, and quickly screening truly valuable information for users, thereby enhancing the user experience.

[0072] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0073] Specifically, a method for querying a legal database includes the following steps:

[0074] Step S101 : Initialize query interaction with the user, determine the legal query subject and legal query purpose, and obtain multiple legal query elements.

[0075] In the embodiment of the present application, when a user needs to make a legal database query, first, the user is interacted with for initialization query, query interaction information is recorded, the legal query theme is determined by subject recognition on the query interaction information, the legal query purpose is determined by purpose matching on the query interaction information, and a plurality of legal query elements are obtained by element refinement analysis on the query interaction information, wherein the legal query theme is a clear legal problem or research topic; the legal query purpose can be obtaining legal text, searching for judicial cases, obtaining academic viewpoints or obtaining practical guidelines; and the plurality of legal query elements can include legal keywords, legal provisions, time range, geographical range, and court level.

[0076] Specifically, Figure 2 A flowchart of the initialization query interaction in the method provided by the embodiment of the present application is shown.

[0077] In the preferred embodiment provided by the present application, the initialization query interaction with the user, the determination of the legal query theme and the legal query purpose, and the obtaining of the plurality of legal query elements specifically include the following steps:

[0078] Step S1011, initialization query interaction is performed, and query interaction information is recorded;

[0079] Step S1012, subject recognition is performed on the query interaction information, and the legal query theme is determined;

[0080] Step S1013, purpose matching is performed on the query interaction information, and the legal query purpose is determined;

[0081] Step S1014, element refinement analysis is performed on the query interaction information, and a plurality of legal query elements are obtained.

[0082] The element refinement analysis on the query interaction information to obtain the plurality of legal query elements specifically includes the following steps:

[0083] The query interaction information is preliminarily analyzed, and preliminary element keywords are identified and extracted;

[0084] The preliminary element keywords are subjected to semantic understanding by using natural language processing technology, and multi-level semantic relationships are identified;

[0085] According to the preliminary element keywords and the multi-level semantic relationships, relevant background information is extracted from known legal databases or public legal documents to supplement the background information of the user query theme;

[0086] The preliminary element keywords and the background information of the user query theme are classified according to a plurality of dimensions, and a plurality of elements are obtained.

[0087] Set the weight of each element, adjust the weight proportion of each element according to the specific circumstances of the user query intention and the background information of the user query theme

[0088] Analyze the correlation between each element using a graph database, and construct a correlation matrix.

[0089] In combination with the query purpose of the user, select the associated element combination from the correlation matrix, and through a user feedback mechanism, carry out multiple rounds of interaction, dynamically adjust and optimize the refinement degree of the elements to ensure the accuracy and relevance of the query result, and obtain the legal query elements.

[0090] Further, the legal database query method further comprises the following steps:

[0091] Step S102, according to the legal query theme, the legal query purpose and a plurality of legal query elements, selecting a plurality of related legal databases, and performing permission acquisition, and constructing a target legal database.

[0092] In the embodiment of the application, according to the legal query theme and the legal query purpose, an initial database matching is performed to determine a plurality of required legal databases, and then a plurality of legal query elements are used to screen the plurality of required legal databases, mark a plurality of selected related legal databases, and acquire access permission channels of the plurality of related legal databases. Then, through the plurality of access permission channels, database access permissions of the plurality of related legal databases are acquired, and according to the plurality of database access permissions, the plurality of related legal databases are virtually integrated to construct a target legal database.

[0093] Specifically, Figure 3 A flow chart for constructing a target legal database in the method provided by the embodiment of the application is shown.

[0094] In the preferred embodiment provided by the application, the step of selecting a plurality of related legal databases according to the legal query theme, the legal query purpose and a plurality of legal query elements, and performing permission acquisition to construct a target legal database specifically comprises the following steps:

[0095] Step S1021, according to the legal query theme and the legal query purpose, matching a plurality of required legal databases;

[0096] Step S1022, according to a plurality of legal query elements, screening a plurality of required legal databases, and marking a plurality of related legal databases;

[0097] Step S1023, acquiring access permission channels of a plurality of related legal databases;

[0098] Step S1024, obtaining database access rights of the plurality of related legal databases through the plurality of access right channels;

[0099] Step S1025, according to the plurality of database access rights, virtually integrating the plurality of related legal databases to construct a target legal database.

[0100] Further, according to the plurality of database access rights, virtually integrating the plurality of related legal databases to construct a target legal database specifically includes the following steps:

[0101] Creating a virtual database dictionary for storing the integration results of each database;

[0102] Checking the access rights, if there is an access right, pre-processing the data in the database, and generating metadata according to the pre-processed data, wherein the metadata includes creation time, data volume and source information;

[0103] Based on the hash value of all databases, calculating the integration score, and integrating the pre-processed data, the generated metadata and the integration score into a dictionary;

[0104] Adding the processing result of each database to the virtual database dictionary; wherein the key is the database name, and the value is a dictionary containing the pre-processed data, metadata and integration score;

[0105] De-duplicating and index optimizing the virtual database dictionary to obtain the target legal database.

[0106] Further, the legal database query method further includes the following steps:

[0107] Step S103, receiving the query key information input by the user, and performing step-by-step retrieval in the target legal database to obtain a retrieval query result.

[0108] In the embodiment of the application, by creating a precise query interface, in the precise query interface, receiving the query key information input by the user, and then identifying the query key information, extracting a plurality of query keywords, and logically analyzing the plurality of query keywords to obtain the logical relationship between the plurality of query keywords, and then performing step-by-step retrieval in the target legal database according to the plurality of query keywords and the corresponding logical relationship to obtain a retrieval query result, wherein the query keyword must be a professional and accurate legal term; the logical relationship includes "and", "or", "not" and the like.

[0109] Specifically, Figure 4 A flowchart for obtaining a retrieval query result in the method provided by the embodiment of the application is shown.

[0110] In a preferred embodiment of the present invention, the receiving of the key query information input by the user, performing a step-by-step search in the target legal database, and obtaining the search query results specifically include the following steps:

[0111] Step S1031, creating a precise query interface;

[0112] Step S1032: receiving key query information input by the user in the precise query interface;

[0113] Step S1033: Identify the query key information, extract multiple query keywords, and obtain the logical relationship between the multiple query keywords;

[0114] Step S1034: performing a step-by-step search in the target legal database according to the plurality of query keywords and corresponding logical relationships to obtain a search query result.

[0115] Furthermore, performing a step-by-step search in the target legal database according to the plurality of query keywords and corresponding logical relationships to obtain the search query results specifically includes the following steps:

[0116] 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.

[0117] Create an empty list for storing query expression trees, directly add the first keyword to the query expression tree, and starting from the second keyword, 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;

[0118] 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;

[0119] 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;

[0120] 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.

[0121] 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;

[0122] For logical "or", the evaluation results of the left subquery expression tree and the right subquery expression tree are combined, and the weights are accumulated;

[0123] For logical "not", data items in the evaluation result of the left subquery expression tree that are not contained in the evaluation result of the right subquery expression tree are returned, and the weight of the left subquery expression tree is reserved.

[0124] Further, the legal database query method further includes the following steps:

[0125] Step S104, according to the search query result, determine a plurality of legal query information, identify and evaluate a plurality of the legal query information, filter a plurality of main query information and perform integration processing.

[0126] In the embodiment of the application, according to the search query result, a plurality of legal query information is determined, a plurality of legal query information is identified according to a plurality of preset identification categories, a plurality of corresponding browsing identification information is recorded, a plurality of browsing identification information is evaluated, an information evaluation score is generated, a score comparison result is generated by comparing a plurality of information evaluation scores with a preset standard evaluation score, and then according to the score comparison result, a plurality of main query information is filtered from a plurality of legal query information, a plurality of main query information is arranged, summarized and compared, and integrated comparison query information is generated. Wherein, the browsing identification is a process of identifying the content of the title, abstract, source, publication date, etc. of the plurality of legal query information; the evaluation of the plurality of browsing identification information is an evaluation of the source reliability, author professionalism, content accuracy and information timeliness, etc.

[0127] Specifically, Figure 5 A flowchart of legal query information identification and evaluation in the method provided by the embodiment of the application is shown.

[0128] In the preferred embodiment provided by the application, the determination of a plurality of legal query information according to the search query result, the identification and evaluation of a plurality of the legal query information, the filtering of a plurality of main query information and the integration processing of the main query information specifically include the following steps:

[0129] Step S1041, according to the search query result, determine a plurality of legal query information;

[0130] Step S1042, identify and evaluate a plurality of legal query information, filter a plurality of main query information;

[0131] Step S1043, arrange, summarize and compare a plurality of the main query information, and generate integrated comparison query information.

[0132] Specifically, Figure 6A flow chart of screening a plurality of main query information in the method provided by the embodiment of the application is shown.

[0133] In the preferred embodiments provided by the application, the identifying and evaluating the plurality of legal query information and screening the plurality of main query information specifically includes the following steps.

[0134] In step S10421, the plurality of legal query information is identified according to the preset identification categories, and the corresponding browsing identification information is recorded.

[0135] In step S10422, the browsing identification information is evaluated, and an information evaluation score is generated.

[0136] In step S10423, the information evaluation score is compared with a preset standard evaluation score, and a score comparison result is generated.

[0137] In step S10424, according to the score comparison result, the plurality of main query information is screened from the plurality of legal query information.

[0138] In the preferred embodiments provided by the application, the evaluating the plurality of browsing identification information and generating the information evaluation score specifically includes the following steps.

[0139] The query keywords provided by all users are determined, and the importance weight of each query keyword is determined.

[0140] The semantic similarity between each browsing identification information and each query keyword is analyzed to obtain the matching result of the browsing identification information and different query keywords.

[0141] The matching result is weighted and summed with the corresponding importance weight, and then the average value of the weighted sum result is obtained to obtain the content correlation score.

[0142] The source of each browsing identification information is obtained, and the basic trust score is set according to the authority of the source.

[0143] The historical error information of the browsing identification information is taken as an adjustment coefficient to adjust the basic trust score to obtain a trust score.

[0144] A plurality of key elements of the legal information are obtained, the plurality of key elements including article reference, case support, analysis and argumentation, and conclusion suggestion, and each key element is given a corresponding weight.

[0145] The coverage of the key elements by the browsing identification information is scored to obtain an element score.

[0146] All the element scores are summarized to obtain an integrity score.

[0147] obtain a time difference between the publishing time and the current time;

[0148] give an initial score to each browsing identification information, adjust the corresponding initial score by applying a decay coefficient according to the time difference to obtain a timeliness score;

[0149] weight and sum the content relevance score, the trust score, the element score and the timeliness score to obtain an information evaluation score.

[0150] In the embodiments of the present application, the content relevance, the source trustworthiness, the information integrity and the information timeliness are used to evaluate the information, so that the scoring result is more comprehensive, and the one-sidedness that may occur in the traditional single-dimension screening can be avoided.

[0151] Further, Figure 7 application architecture diagram of the system provided by the embodiments of the present application is shown.

[0152] In another preferred embodiment provided by the present application, a legal database query system comprises:

[0153] The initialization query interaction unit 101 is configured to perform initialization query interaction with the user, determine a legal query topic and a legal query purpose, and obtain a plurality of legal query elements.

[0154] In the embodiments of the present application, when the user needs to perform legal database query, the initialization query interaction unit 101 first performs initialization query interaction with the user, records query interaction information, determines a legal query topic by subject recognition on the query interaction information, determines a legal query purpose by purpose matching on the query interaction information, and obtains a plurality of legal query elements by element refinement analysis on the query interaction information. The legal query topic is a clear legal problem or research topic. The legal query purpose can be obtaining legal text, searching for judicial cases, obtaining academic viewpoints or obtaining practical guidelines, etc. The plurality of legal query elements can include legal keywords, legal provisions, time range, geographical range, court level, etc.

[0155] Specifically, Figure 8 application architecture diagram of the system provided by the embodiments of the present application is shown.

[0156] In the preferred embodiment provided by the present application, the initialization query interaction unit 101 specifically comprises:

[0157] The query interaction module 1011 is configured to perform initialization query interaction and record query interaction information.

[0158] The subject identification module 1012 is configured to perform subject identification on the query interaction information, and determine a law query subject.

[0159] The purpose matching module 1013 is configured to perform purpose matching on the query interaction information, and determine a law query purpose.

[0160] The element refinement analysis module 1014 is configured to perform element refinement analysis on the query interaction information, and obtain a plurality of law query elements.

[0161] Further, the law database query system further comprises:

[0162] The target law database construction unit 102 is configured to select a plurality of related law databases according to the law query subject, the law query purpose and the plurality of law query elements, and perform permission acquisition to construct a target law database.

[0163] In the embodiment of the application, the target law database construction unit 102 performs initial database matching according to the law query subject and the law query purpose, determines a plurality of demand law databases, and then filters the plurality of demand law databases according to the plurality of law query elements, marks a plurality of selected related law databases, and acquires access permission channels of the plurality of related law databases. Then, the target law database construction unit 102 acquires database access permissions of the plurality of related law databases through the plurality of access permission channels, virtually integrates the plurality of related law databases according to the plurality of database access permissions, and constructs a target law database.

[0164] Specifically, Figure 9 FIG. 1 shows a structure block diagram of the target law database construction unit 102 in the system provided by the embodiment of the application.

[0165] In the preferred embodiment provided by the application, the target law database construction unit 102 specifically comprises:

[0166] The database matching module 1021 is configured to match a plurality of demand law databases according to the law query subject and the law query purpose.

[0167] The database filtering module 1022 is configured to filter the plurality of demand law databases according to the plurality of law query elements, and mark a plurality of related law databases.

[0168] The channel acquisition module 1023 is configured to acquire access permission channels of the plurality of related law databases.

[0169] The permission acquisition module 1024 is configured to acquire database access permissions of the plurality of related law databases through the plurality of access permission channels.

[0170] The virtual integration module 1025 is configured to virtually integrate the related legal databases according to the database access permissions to construct a target legal database.

[0171] Further, the legal database query system further comprises:

[0172] The database step-by-step search unit 103 is configured to receive the query key information input by a user, perform step-by-step search in the target legal database, and obtain a search query result.

[0173] In the embodiment of the present application, the database step-by-step search unit 103 creates a precise query interface, receives the query key information input by a user in the precise query interface, identifies the query key information, extracts a plurality of query keywords, performs logical analysis on the plurality of query keywords to obtain the logical relationship between the plurality of query keywords, and then performs step-by-step search in the target legal database according to the plurality of query keywords and the corresponding logical relationship to obtain the search query result. The query keyword must be a professional and accurate legal term. The logical relationship includes "and", "or", "not", etc.

[0174] The query identification and evaluation unit 104 is configured to determine a plurality of legal query information according to the search query result, identify and evaluate the plurality of legal query information, filter a plurality of main query information, and perform integration processing.

[0175] In the embodiment of the present application, the query identification and evaluation unit 104 determines a plurality of legal query information according to the search query result, browses and identifies the plurality of legal query information according to a plurality of preset identification categories, records a plurality of corresponding browsing and identification information, evaluates the plurality of browsing and identification information to generate information evaluation scores, compares the plurality of information evaluation scores with preset standard evaluation scores to generate a score comparison result, and then filters a plurality of main query information from the plurality of legal query information according to the score comparison result, arranges, induces and compares the plurality of main query information to generate integrated comparison query information. The browsing and identification is a process of identifying the content of the title, abstract, source, publication date, etc. of the plurality of legal query information. The evaluation of the plurality of browsing and identification information is an evaluation of the reliability of the source, the professionalism of the author, the accuracy of the content, and the timeliness of the information, etc.

[0176] Specifically, Figure 10 The structure block diagram of the query identification and evaluation unit 104 in the system provided by the embodiment of the present application is shown.

[0177] In the preferred embodiment provided by the present application, the query identification and evaluation unit 104 specifically comprises:

[0178] The information determining module 1041 is configured to determine a plurality of legal query information according to the search query result.

[0179] The identification and evaluation module 1042 is configured to identify and evaluate the plurality of legal query information, and filter a plurality of main query information.

[0180] The information integration module 1043 is configured to arrange, summarize and compare the plurality of main query information, and generate integrated comparison query information.

[0181] It should be understood that, although each step in the flowchart of each embodiment of the present application is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least a part of the steps in each embodiment can include a plurality of sub-steps or a plurality of stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least a part of other steps or sub-steps or stages of other steps.

[0182] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The program can be stored in a non-volatile computer readable storage medium, and when the program is executed, it can include the processes of the above-mentioned embodiments of each method. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), 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).

[0183] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned 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.

[0184] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0185] 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 scope of protection of the present invention.

Claims

1. A legal database query method, 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 query subject, the legal query purpose and the plurality of legal query elements, multiple relevant legal databases are selected, and permissions are obtained to construct a target legal database; Receiving key query information input by the user, performing step-by-step searches in the target legal database, and obtaining search query results; Determining multiple legal inquiry information based on the search query results, identifying and evaluating the multiple legal inquiry information, screening multiple main inquiry information, and integrating 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 topic identification on the query interaction information to determine a legal query topic; Performing purpose matching on the query interaction information to determine the purpose of the legal inquiry; Performing element-refining analysis on the query interaction information to obtain multiple legal query elements; Performing element-refining analysis on the query interaction information to obtain multiple legal query elements specifically includes the following steps: Performing preliminary analysis on the query interaction information to identify and extract preliminary element keywords; Use natural language processing technology to understand the semantics of preliminary element keywords and identify multi-level semantic relationships; Based on the preliminary element keywords and multi-level semantic relationships, relevant background information is extracted from known legal databases or public legal documents 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; Combined with the user's query purpose, related element combinations are selected from the correlation matrix. 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.

2. The legal database query method according to claim 1, characterized in that: The step of selecting multiple relevant legal databases based on the legal query subject, the legal query purpose, and the multiple legal query elements, and obtaining permissions to construct a target legal database specifically includes the following steps: Matching multiple required legal databases according to the legal query subject and the legal query purpose; screening the plurality of required legal databases according to the plurality of legal query elements, and marking a plurality of relevant legal databases; Obtaining access rights to multiple relevant legal databases; Obtaining database access rights to the plurality of relevant legal databases through the plurality of access permission 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.

3. The legal database query method according to claim 2, characterized in that: 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, specifically comprising the following steps: Create a virtual database dictionary to store the integration results of each database; Checking access rights. If the access rights are granted, 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 combine 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.

4. The legal database query method according to claim 3, characterized in that: The receiving of 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 specifically include the following steps: Create a precise query interface; In the precise query interface, receiving key query information input by the user; Identifying the query key information, extracting multiple query keywords, and obtaining logical relationships 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.

5. The legal database query method according to claim 4, 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, directly add the first keyword to the query expression tree, and starting from the second keyword, 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, returns the data item in the evaluation result of the left subquery expression tree that is not included in the evaluation result of the right subquery expression tree, and retains the weight of the left subquery expression tree.

6. The legal database query method according to claim 5, characterized in that: The determining of a plurality of legal inquiry information based on the search query results, identifying and evaluating the plurality of legal inquiry information, screening a plurality of main inquiry information and integrating them specifically includes the following steps: Determining multiple legal query information based on the search query results; Identify and evaluate multiple legal inquiry information and screen multiple key inquiry information; Arrange, summarize and compare the plurality of main query information to generate integrated comparative query information.

7. The legal database query method according to claim 6, characterized in that: The identification and evaluation of multiple legal inquiry information and screening of multiple main inquiry information specifically include the following steps: According to a plurality of preset identification categories, browsing and identifying the plurality of legal inquiry information, and recording a plurality of corresponding browsing identification information; Evaluate the plurality of browsing identification information to generate an information evaluation score; Comparing the plurality of information evaluation scores with a preset standard evaluation score to generate a score comparison result; Based on the score comparison result, a plurality of main query information is screened from the plurality of legal query information.

8. The legal database query method 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 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 the trustworthiness score; Obtain several key elements of legal information, including article citations, case support, analysis and argumentation, and conclusions and suggestions, and assign corresponding weights to each key element; Score the coverage of key elements based on the browsing identification information to obtain the element score; Summarize all factor scores to obtain 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.

9. A legal database query system, said system applying the legal database query method according to any one of claims 1 to 8, characterized in that: The system includes an initialization query interaction unit, a target legal database construction unit, a database step-by-step retrieval unit, and a query identification and 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, configured to select a plurality of relevant legal databases according to the legal query subject, the legal query purpose, and the plurality of legal query elements, and to obtain permissions to construct a target legal database; A database step-by-step search unit, configured to receive key query information input by a user, perform a step-by-step search in the target legal database, and obtain search query results; A query identification and evaluation unit, configured to determine a plurality of legal query information based on the search query results, 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: Query interaction module, used to initialize query interaction and record query interaction information; A subject identification module, configured to perform subject identification on the query interaction information and determine a legal query subject; A purpose matching module, configured to perform purpose matching on the query interaction information to determine the purpose of the legal inquiry; An element refinement analysis module, configured to perform element refinement analysis on the query interaction information to obtain a plurality of legal query elements; The target legal database construction unit specifically includes: A database matching module, configured to match a plurality of required legal databases according to the legal query subject and the legal query purpose; A database screening module, configured to screen the plurality of required legal databases according to the plurality of legal query elements, and mark a plurality of relevant legal databases; A channel acquisition module, used to obtain access rights channels for a plurality of the relevant legal databases; an authority acquisition module, configured to acquire database access rights to a plurality of the relevant legal databases through a plurality of the access permission channels; A virtual integration module, configured to virtually integrate multiple related legal databases based on the access rights of the multiple databases to construct a target legal database; The query identification and evaluation unit specifically includes: An information determination module, configured to determine a plurality of legal inquiry information based on the search query results; Identification and evaluation module, 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