Legal knowledge sharing platform for document reading

Abstract

The present invention discloses a legal knowledge sharing platform for document reading, which relates to the field of search engines. The legal knowledge sharing platform for document reading includes: a data acquisition module, a historical data processing module, an analysis module, and an output module; the data acquisition module is used to acquire historical data and document content information data to be analyzed; the historical data processing module is used to establish a historical legal knowledge database based on the acquired historical data; the analysis module is used to analyze and match the document content information data to be analyzed based on the historical legal knowledge database. The present invention can improve the accuracy of keyword matching through the establishment and update of the historical legal knowledge database, the historical keyword extraction unit can go deep into the historical document content and extract keyword information, and the historical legal knowledge database update unit ensures that the legal knowledge in the database is kept up to date, thereby increasing the accuracy and matching effect of the analysis module in analyzing the document content.

Description

Technical Field

[0001] The present invention relates to the field of search engines, and in particular to a legal knowledge sharing platform applied to document reading. Background Art

[0002] As the amount of information expands, manual processing of legal documents faces increasing challenges, and the need for efficiency and accuracy has become particularly urgent. Legal knowledge sharing platforms have emerged. The emergence of this platform is not only a reflection of technological progress, but also a precise response to the needs of legal information processing.

[0003] In the prior art, traditional retrieval systems usually have the problem of inaccurate keyword matching, which makes it difficult to understand legal texts, thereby reducing the accuracy of the application. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present invention provides a legal knowledge sharing platform for document reading, which solves the problem of inaccurate keyword matching commonly existing in traditional retrieval systems, making it difficult to understand legal texts, which in turn leads to reduced application accuracy.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a legal knowledge sharing platform applied to document reading, including: a data acquisition module, a historical data processing module, an analysis module, and an output module; the data acquisition module is used to acquire historical data and document content information data to be analyzed; the historical data processing module is used to establish a historical legal knowledge database based on the acquired historical data; the analysis module is used to analyze and match the document content information data to be analyzed based on the historical legal knowledge database; the output module is used to display the analysis and matching results of the analysis module.

[0006] Furthermore, the data acquisition module includes: a historical data acquisition unit and a document content information data acquisition unit; the historical data acquisition unit is used to acquire and preprocess historical data, and store the preprocessed historical data, and the historical data specifically includes historical document content text data, legal knowledge content text data involved in the historical document content text data, and case example data associated with the involved legal knowledge content text data; the document content information data acquisition unit is used to acquire and preprocess the document content information data to be analyzed, and store the preprocessed document content information data to be analyzed.

[0007] Furthermore, the historical data processing module includes: a historical keyword extraction unit, a historical legal knowledge database establishment unit, and a historical legal knowledge database update unit; the historical keyword extraction unit is used to read the historical document content text data after preprocessing and extract keyword information in the historical document content text data; the historical legal knowledge database establishment unit is used to establish a historical legal knowledge database; the historical legal knowledge database update unit is used to update the established historical legal knowledge database content based on the keyword information in the extracted historical document content text data, the legal knowledge content text data involved in the historical document content text data, and the case examples associated with the involved legal knowledge content text data.

[0008] Furthermore, the specific process of extracting keyword information from the text data of historical document content is as follows: read the historical document content text data after preprocessing; based on natural language processing tools, perform word segmentation and cutting on the historical document content text data after preprocessing; remove stop words based on the historical document content text data after word segmentation and cutting; perform part-of-speech tagging on the historical document content text data after the stop word removal; extract nouns and professional terms from the historical document content text data after the part-of-speech tagging, and mark them as keyword information.

[0009] Furthermore, the specific process of updating the content of the established historical legal knowledge database is as follows: reading keyword information, legal knowledge content text data involved in historical document content text data, and case examples associated with the involved legal knowledge content text data; establishing a correlation map among keyword information, legal knowledge content text data involved in historical document content text data, and case examples associated with the involved legal knowledge content text data based on natural language processing technology; based on keyword information, searching in the historical legal knowledge database whether there is already relevant legal knowledge; if so, determining whether the legal knowledge in the correlation map exists. Whether the legal knowledge is consistent with the existing legal knowledge; if so, determine whether the case examples in the association graph are consistent with the existing case examples; if so, do not take any measures; if not, add the case examples in the association graph to the historical legal knowledge database, and establish the association between the case examples in the association graph and the existing case examples based on natural language processing technology; if not, add the legal knowledge in the association graph and the corresponding case examples to the historical legal knowledge database; if no relevant legal knowledge is found, extract the legal knowledge; and add the newly extracted legal knowledge content and the association graph to the historical legal knowledge database.

[0010] Furthermore, the process of analyzing and matching the document content information data to be analyzed based on the historical legal knowledge database is as follows: read the document content information data to be analyzed and extract keyword information; based on the extracted keyword information, query the historical database legal knowledge database to see whether there is matching keyword information; if so, output the legal knowledge content text data and related case examples related to the matching keyword information; if not, further analyze the extracted keyword information.

[0011] Furthermore, the specific process of further analyzing the extracted keyword information is as follows: read the extracted keyword information for analysis to obtain similar keyword information with similar meaning to the keyword; based on the similar keyword information, query the historical database legal knowledge database to see whether there is matching keyword information; if so, output the legal knowledge content text data and related case examples related to the matching keyword information; if not, calculate the similarity values ​​between the keyword information existing in the historical database legal knowledge database and the extracted keyword information and similar keyword information respectively, and output the keyword information existing in the historical database legal knowledge database with a similarity value higher than the threshold in descending order.

[0012] Furthermore, the number of characters in the keyword information and the similar keyword information is at least two, and the similarity value includes the keyword similarity value and the similar keyword similarity value. The specific process of calculating the similarity value between the keyword information existing in the historical database legal knowledge database and the extracted keyword information is as follows: read the number of characters in each keyword information existing in the historical database legal knowledge database and the extracted keyword information; add the number of characters of each keyword information existing in the historical database legal knowledge database to the number of characters of the extracted keyword information, respectively, to obtain multiple keyword character total values; match each keyword information existing in the historical database legal knowledge database with the extracted keyword information, respectively, to obtain multiple keyword character identical values; the keyword character identical value is specifically the number of characters that are identical between the keyword information existing in the historical database legal knowledge database and the extracted keyword information; read multiple keyword character identical values ​​and the corresponding keyword character total values ​​and perform comprehensive calculations in combination with keyword correction factors to obtain multiple keyword similarity values.

[0013] Furthermore, the specific process of calculating the keyword correction factor is as follows: obtain the keyword information existing in the legal knowledge database of the historical database for several times, and match them with the extracted keyword information to obtain the same keyword character measurement value and the same keyword character actual value; calculate the difference between the same keyword character measurement value and the same keyword character actual value obtained by each match, and calculate the average of each difference result in combination with the moving exponential mean method to obtain the keyword correction factor.

[0014] Furthermore, the formula for calculating the keyword similarity value is as follows: Among them, Gxs is the keyword similarity value, Gjx is the keyword character identical value, and Gjz is the total keyword character value corresponding to the keyword character identical value. is the keyword correction factor, Sz r-1 The actual value of the keyword characters obtained by matching the keyword information in the legal knowledge database of the historical database for the r-1th time with the extracted keyword information is the same as that obtained by Cz r-1 The same measurement value of keyword characters obtained by matching the keyword information in the legal knowledge database of the historical database with the extracted keyword information is obtained, and 1+ζ is Sz r-1 -Cz r-1 The proportionality factor, Sz r The actual value of the keyword characters obtained by matching the keyword information in the legal knowledge database of the rth historical database with the extracted keyword information is the same as that obtained by Cz r is the keyword character identical measurement value obtained by matching the keyword information existing in the legal knowledge database of the rth historical database with the extracted keyword information, ζ is Sz r -Cz r The proportional coefficient is r=1, 2, 3, …, D, where D is the total number of times the keyword information existing in the acquired historical database legal knowledge database is matched with the extracted keyword information.

[0015] The present invention has the following beneficial effects:

[0016] (1) The legal knowledge sharing platform applied to document reading can improve the accuracy of keyword matching by establishing and updating the historical legal knowledge database. The historical keyword extraction unit in the historical data processing module can go deep into the content of historical documents and extract keyword information, while the historical legal knowledge database update unit ensures that the legal knowledge in the database is kept up to date, thereby increasing the accuracy and matching effect of the analysis module in analyzing the content of the document.

[0017] (2) The legal knowledge sharing platform applied to document reading can optimize the relevance of legal knowledge by establishing and updating the association map of the historical legal knowledge database. The historical legal knowledge database establishment unit establishes the association between keywords and legal knowledge content and case examples, while the historical legal knowledge database update unit ensures the accuracy of the association by updating the association map, thereby improving the in-depth analysis of the document content to be analyzed and the matching effect of the related legal knowledge.

[0018] (3) The legal knowledge sharing platform applied to document reading can realize personalized recommendations by analyzing the user's historical query and reading behavior. The analysis module can make personalized legal knowledge recommendations based on the keyword information and similar keyword information extracted by the user. The establishment and updating of the historical legal knowledge database ensures that the recommended legal knowledge is comprehensive, accurate and relevant to user needs, thereby improving the accuracy of personalized recommendations.

[0019] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a framework diagram of the legal knowledge sharing platform applied to document reading according to the present invention.

[0021] Figure 2 This is a block diagram of a data acquisition module in a legal knowledge sharing platform for document reading according to the present invention.

[0022] Figure 3 This is a block diagram of the historical data processing module in the legal knowledge sharing platform applied to document reading of the present invention.

[0023] Figure 4 The present invention is a flowchart of the specific steps for calculating the similarity value between the keyword information existing in the historical database legal knowledge database and the extracted keyword information in the legal knowledge sharing platform for document reading.

[0024] Figure 5 The present invention is a flowchart of the specific steps of calculating keyword correction factors in a legal knowledge sharing platform for document reading. DETAILED DESCRIPTION

[0025] The embodiment of the present application solves the problem of inaccurate keyword matching commonly existing in traditional retrieval systems by applying a legal knowledge sharing platform to document reading, which makes it difficult to understand legal texts and leads to reduced application accuracy.

[0026] The overall idea of ​​the problem in the embodiment of this application is as follows:

[0027] First, the historical data acquisition unit and the document content information data acquisition unit are used to acquire and preprocess the historical data and the document content information data to be analyzed, and then the preprocessed historical data is stored, including the historical document content text data, the legal knowledge content text data involved, and the related case example data. Then, the historical keyword extraction unit is used to read the historical document content text data and extract the keyword information therein. Then, the historical legal knowledge database establishment unit is used to establish a historical legal knowledge database and update the database content to ensure that the keywords, legal knowledge content text data and the related case examples obtain the correct association map. Then, the document content information data to be analyzed is read and the keyword information therein is extracted. Then, based on the historical legal knowledge database, keyword matching is performed to acquire the related legal knowledge content text data and the related case examples, so as to realize the in-depth analysis and matching of the document content. Then, the results of the analysis module are displayed to show the matched legal knowledge content and the related case examples. Finally, a user interface and visualization means are provided to enable users to clearly and intuitively understand the matching results and effectively solve the problem of information overload.

[0028] See also Figure 1 The embodiment of the present invention provides a technical solution: a legal knowledge sharing platform applied to document reading, including: a data acquisition module, a historical data processing module, an analysis module, and an output module; the data acquisition module is used to acquire historical data and document content information data to be analyzed; the historical data processing module is used to establish a historical legal knowledge database based on the acquired historical data; the analysis module is used to analyze and match the document content information data to be analyzed based on the historical legal knowledge database; the output module is used to display the analysis and matching results of the analysis module.

[0029] Specifically, Figure 2 As shown, the data acquisition module includes: a historical data acquisition unit and a document content information data acquisition unit; the historical data acquisition unit is used to acquire and preprocess historical data, and store the preprocessed historical data, the historical data specifically includes historical document content text data, legal knowledge content text data involved in the historical document content text data, and case example data associated with the involved legal knowledge content text data; the document content information data acquisition unit is used to acquire and preprocess the document content information data to be analyzed, and store the preprocessed document content information data to be analyzed.

[0030] In this implementation, the historical data acquisition unit obtains a large amount of text data on the content of historical documents, including rulings, precedents, legal provisions, etc., through channels such as court databases, public documents, and legal journals, so that the platform can acquire and store a large amount of historical documents to ensure the comprehensiveness of legal knowledge. Due to the timely update of historical data, the timeliness of the legal knowledge database is guaranteed, and the acquired historical document content text data is preprocessed, including removing noise and non-critical information in the text, and performing text cleaning, format normalization and other operations to improve the efficiency of subsequent processing. In addition, when preprocessing historical data and document data to be analyzed, the text is normalized to improve the consistency and comparability of the data, which is helpful to establish a unified data format, store historical data, and ensure efficient management and rapid retrieval of data by storing the preprocessed historical data in the database, and acquire document content information data to be analyzed by acquiring document content information data to be analyzed from sources such as documents uploaded by users and court announcements, and preprocess the document content information data to be analyzed, including removing irregular formats, processing text encoding, segmentation, etc., to improve the accuracy of subsequent analysis, and store document content information data to be analyzed, and store the preprocessed document content information data to be analyzed in the database for rapid access by subsequent analysis modules.

[0031] Specifically, Figure 3 As shown, the historical data processing module includes: a historical keyword extraction unit, a historical legal knowledge database establishment unit, and a historical legal knowledge database update unit; the historical keyword extraction unit is used to read the historical document content text data after preprocessing and extract keyword information in the historical document content text data; the historical legal knowledge database establishment unit is used to establish a historical legal knowledge database; the historical legal knowledge database update unit is used to update the established historical legal knowledge database content based on the keyword information in the extracted historical document content text data, the legal knowledge content text data involved in the historical document content text data, and the case examples associated with the involved legal knowledge content text data.

[0032] In this implementation scheme, the historical keyword extraction unit first reads the pre-processed text data of the historical document content to ensure that the text data is clean and standardized, and then uses natural language processing technology to perform operations such as word segmentation and part-of-speech tagging on the historical document content, and then extracts keyword information. These keywords represent the core concepts and elements of the document, which helps to ensure the accuracy and comprehensiveness of the historical legal knowledge database. The historical legal knowledge database establishment unit is responsible for constructing the historical legal knowledge database based on the extracted keyword information. Keywords are used as the main index in the database, and the keywords are associated with the text data of the legal knowledge content involved and the related case examples to form the basic structure of the database. This module ensures that the structure of the database is clear, and a clear association is established between the keywords and the legal knowledge content and case examples, which provides strong support for subsequent matching and analysis. The historical legal knowledge database update unit updates the established historical legal knowledge database by reading the keyword information in the extracted historical document content text data, the legal knowledge content text data involved in the historical document content text data, and the case examples associated with the involved legal knowledge content text data, and establishes an association map between keywords and legal knowledge. Based on the keyword information, this module establishes an association map between keywords and legal knowledge content, while ensuring the association with case examples, judging and updating the database content, and through the existing Legal knowledge, judge whether the legal knowledge in the association map is consistent with the existing legal knowledge, and further judge whether the case examples in the association map are consistent with the existing case examples. If so, keep the database content unchanged; if not, add the legal knowledge and case examples in the association map to the historical legal knowledge database. Extraction and addition of legal knowledge, if no relevant legal knowledge is found, this module extracts legal knowledge and adds the newly extracted legal knowledge content and association map to the historical legal knowledge database. The historical legal knowledge database update unit is responsible for maintaining the real-time status of the database, ensuring that new legal knowledge can be added to the database in a timely manner. At the same time, by establishing an association map, the comprehensiveness of the database is improved. By continuously updating the historical legal knowledge database, the platform can better match the content of the document to be analyzed, improve the accuracy and practicality of the matching, and provide users with more accurate legal knowledge support.

[0033] Specifically, the specific process of extracting keyword information from the text data of historical document content is as follows: Read the text data of historical document content after preprocessing; Based on natural language processing tools, perform word segmentation on the text data of historical document content after preprocessing. Word segmentation is specifically the process of splitting the historical document text into individual words. Based on the text data of historical document content after word segmentation, perform stop word removal processing. Stop words are those that frequently appear in the text but usually do not make a substantial contribution to the text theme. For example, remove stop words such as "de", "shi", "zai", etc. Based on the text data of historical document content after stop word removal processing, perform part-of-speech tagging processing; Extract nouns and professional terms from the text data of historical document content after part-of-speech tagging processing and mark them as keyword information. Nouns and professional terms are usually key legal concepts. For example, extract "contract dispute" and "liability for breach of contract" from the sentence "Liability for breach of contract in a contract dispute".

[0034] In this implementation plan, the module first reads the text data of historical document content that has been preprocessed to ensure the quality and accuracy of the text data. Then, using natural language processing tools, it performs word segmentation on the text data of historical document content after preprocessing. This process splits the text into individual words for subsequent processing. This step helps improve the accuracy of keywords and ensures that the extracted keywords are important legal concepts in the document. After word segmentation, stop word removal processing is performed. Stop words are words that frequently appear in the text but usually do not make a substantial contribution to the text theme. For example, "de", "shi", "zai", etc. Removing these stop words helps extract more meaningful information from the text. Stop word removal processing helps remove redundant information from the text, making the extracted keywords more focused on the core content of the document and improving the compactness of the information. Perform part-of-speech tagging processing on the text data of historical document content after stop word removal processing. This step can mark the part of speech of each word and helps identify key information such as nouns and verbs in the text. Extract nouns and professional terms from the text data after part-of-speech tagging processing and mark them as keyword information. Nouns and professional terms are usually key legal concepts in the document. For example, in the sentence "Liability for breach of contract in a contract dispute", extract "contract dispute" and "liability for breach of contract" as keywords. Through part-of-speech tagging and professional term extraction, the module can adapt to different types and fields of legal documents and ensure that good results can be achieved for the processing of various texts. The extracted keyword information serves as the basis for subsequent matching, helps improve the accuracy of the analysis module, and effective keyword information will provide more targeted support for the matching of legal knowledge, improving the efficiency and practicality of the entire system.

[0035] Specifically, the specific process of updating the content of the established historical legal knowledge database is as follows: reading keyword information, legal knowledge content text data involved in the historical document content text data, and case examples associated with the involved legal knowledge content text data; establishing a correlation map among keyword information, legal knowledge content text data involved in the historical document content text data, and case examples associated with the involved legal knowledge content text data based on natural language processing technology; based on keyword information, searching in the historical legal knowledge database whether there is already relevant legal knowledge; if so, judging whether the legal knowledge in the correlation map is consistent with the existing legal knowledge; if so, judging whether the legal knowledge in the correlation map is consistent with the existing legal knowledge. Whether the case example is consistent with the existing case examples; if so, no action is taken; if not, the case examples in the association graph are added to the historical legal knowledge database, and the association between the case examples in the association graph and the existing case examples is established based on natural language processing technology; if not, the legal knowledge in the association graph and the corresponding case examples are added to the historical legal knowledge database. The existing legal knowledge content specifically refers to the legal knowledge content text data involved in the keyword information, and the current case specifically refers to the case example associated with the legal knowledge content text data involved. If no relevant legal knowledge is found, legal knowledge extraction will be established. The extraction of legal knowledge includes legal article citation, case analysis, etc.

[0036] In this implementation scheme, the module first reads the keyword information in the historical database, the legal knowledge content text data involved in the historical document content text data, and the case examples associated with the legal knowledge content text data involved, and establishes an association map: then uses natural language processing technology to establish an association map based on the keyword information, the legal knowledge content text data involved in the historical document content text data, and the associated case examples. This map records the relationship and connection between the three, and searches for existing legal knowledge: then searches the historical legal knowledge database to see if there is already relevant legal knowledge. If so, proceed to the next step of judgment, and then judge the information in the association map. If there is already relevant legal knowledge, judge whether the legal knowledge in the association map is consistent with the existing legal knowledge. If so, further judge whether the case examples in the association map are consistent with the existing case examples, and then update the database content. If it is consistent with the existing legal knowledge and case examples, no measures are taken. If it is not consistent with the existing case examples, the case examples in the association map are added to the historical legal knowledge database. And based on natural language processing technology, the association between these case examples and existing case examples is established. If it does not conform to the existing legal knowledge, the legal knowledge in the association map and the corresponding case examples are added to the historical legal knowledge database. If the relevant legal knowledge is not found, the legal knowledge is extracted, which includes processes such as legal article citation and case analysis. By establishing an association map and dynamically updating the database content, it is ensured that the information in the historical legal knowledge database can timely reflect the latest legal knowledge in the documents and maintain the real-time nature of the database. Using the association map, the module can more accurately determine whether the newly added case examples and legal knowledge are consistent with the existing relevant information, thereby improving the accuracy of matching. Due to the use of natural language processing technology, the system can adapt to legal documents of different types and fields, ensuring that good results can be achieved in the processing of various texts. When the relevant legal knowledge is not found in the historical legal knowledge database, legal knowledge is extracted, which enriches the content of the database and improves the comprehensiveness of the database.

[0037] Specifically, the process of analyzing and matching the document content information data to be analyzed based on the historical legal knowledge database is as follows: read the document content information data to be analyzed and extract keyword information; based on the extracted keyword information, query the historical database legal knowledge database to see whether there is matching keyword information; if so, output the legal knowledge content text data and related case examples related to the matching keyword information; if not, further analyze the extracted keyword information.

[0038] In this implementation scheme, first, the system reads the document content information data to be analyzed, and then performs natural language processing on the document to be analyzed to extract the keyword information therein. Based on the extracted keyword information, the system queries the historical database legal knowledge database to check whether there is matching keyword information and match the legal knowledge content. If there is a match, the legal knowledge content text data that matches the keyword information in the database is extracted. At the same time, the system also outputs the related case example information, which helps users to have a more comprehensive understanding of the context and practical application of the keywords. The matched legal knowledge content text data is output for users to view and refer to, and case examples related to the keywords are output to provide richer case support. If matching keyword information is not found in the historical database, the system can Further analysis is carried out to conduct a more in-depth contextual analysis of the extracted keyword information to understand its possible meaning and context, and then match similar keywords to find legal knowledge content similar to the extracted keyword information. Through the matching of keyword information in this step, the system can efficiently search the historical legal knowledge database to find legal knowledge related to the document content, improve the efficiency of information retrieval, and output related case examples, so that users can deeply understand the application scenarios of keywords in actual cases and provide comprehensive case support. If the content in the historical legal knowledge database is updated, the process can also be reflected in real time to ensure that the matched information is the latest. By outputting matching results and related case examples, users can better understand and apply legal knowledge, which improves user experience and learning effects.

[0039] Specifically, the specific process of further analyzing the extracted keyword information is as follows: read the extracted keyword information for analysis to obtain similar keyword information with similar meaning to the keyword; based on the similar keyword information, query the historical database legal knowledge database to see whether there is matching keyword information; if so, output the legal knowledge content text data and related case examples related to the matching keyword information; if not, calculate the similarity values ​​between the keyword information existing in the historical database legal knowledge database and the extracted keyword information and similar keyword information respectively, and output the keyword information in the historical database legal knowledge database whose similarity value is higher than the threshold in descending order.

[0040] In this implementation scheme, the system reads the previously extracted keyword information, and then performs semantic analysis to obtain similar keyword information with similar meanings to the extracted keywords. This can be done through natural language processing technology, such as word meaning similarity algorithm, to obtain the semantic association of vocabulary. Then, based on the similar keyword information, the system queries the historical database legal knowledge database to check whether there is matching keyword information, and then matches the legal knowledge content. If there is a match, the legal knowledge content text data in the database that matches the similar keyword information is extracted. At the same time, the system also outputs the associated case example information to provide more comprehensive case support, and then outputs the matched legal knowledge content text data for users to view and refer to, and then outputs case examples related to similar keywords to provide richer case support. If no matching information is found in the historical database, For similar keyword information, the system performs similarity calculation, and then calculates the similarity values ​​between the keyword information existing in the historical database legal knowledge database and the extracted keyword information and similar keyword information respectively, and then outputs the keyword information with a similarity value higher than the set threshold in descending order. Through the analysis of similar keyword information in this step, the system can expand the matching range, find more legal knowledge content related to the extracted keywords, and output case examples related to similar keywords, which helps users understand different application scenarios of keywords and provides richer case support. If no direct matching keywords are found in the historical database, the system provides alternative solutions through similarity calculation, which increases the flexibility of the system. According to the descending order of similarity values, users can more easily find legal knowledge content related to their areas of concern, thereby improving the personalized matching experience.

[0041] Specifically, Figure 4 , Figure 5 As shown, the number of characters in the keyword information and the similar keyword information is at least two, and the similarity value includes the keyword similarity value and the similar keyword similarity value. The specific process of calculating the similarity value between the keyword information existing in the historical database legal knowledge database and the extracted keyword information is as follows: read the number of characters in each keyword information existing in the historical database legal knowledge database and the extracted keyword information; add the number of characters of each keyword information existing in the historical database legal knowledge database to the number of characters of the extracted keyword information, respectively, to obtain multiple keyword character total values; match each keyword information existing in the historical database legal knowledge database with the extracted keyword information, respectively, to obtain multiple keyword character identical values; the keyword character identical value is specifically the number of characters that are identical between the keyword information existing in the historical database legal knowledge database and the extracted keyword information; read multiple keyword character identical values ​​and the corresponding keyword character total values ​​and perform comprehensive calculations in combination with keyword correction factors to obtain multiple keyword similarity values.

[0042] The specific process of calculating the keyword correction factor is as follows: obtain the keyword information existing in the legal knowledge database of the historical database for several times, and match them with the extracted keyword information to obtain the same keyword character measurement value and the same keyword character actual value; calculate the difference between the same keyword character measurement value and the same keyword character actual value obtained by each match, and calculate the average of each difference result in combination with the moving exponential mean method to obtain the keyword correction factor.

[0043] The formula for calculating the keyword similarity value is as follows: Among them, Gxs is the keyword similarity value, Gjx is the keyword character identical value, and Gjz is the total keyword character value corresponding to the keyword character identical value. is the keyword correction factor, Sz r-1 The actual value of the keyword characters obtained by matching the keyword information in the legal knowledge database of the historical database for the r-1th time with the extracted keyword information is the same as that obtained by Cz r-1 The same measurement value of keyword characters obtained by matching the keyword information in the legal knowledge database of the historical database with the extracted keyword information is obtained, and 1+ζ is Sz r-1 -Cz r-1 The proportionality factor, Sz r The actual value of the keyword characters obtained by matching the keyword information in the legal knowledge database of the rth historical database with the extracted keyword information is the same as that obtained by Cz r is the keyword character identical measurement value obtained by matching the keyword information existing in the legal knowledge database of the rth historical database with the extracted keyword information, ζ is Sz r -Cz r The proportional coefficient is r=1, 2, 3, …, D, where D is the total number of times the keyword information existing in the acquired historical database legal knowledge database is matched with the extracted keyword information.

[0044] Read each keyword information existing in the historical database legal knowledge database and the number of characters in the extracted similar keyword information; add the number of characters of each keyword information existing in the historical database legal knowledge database with the number of characters of the extracted similar keyword information to obtain multiple similar keyword total values; match each keyword information existing in the historical database legal knowledge database with the extracted similar keyword information to obtain the same value of similar keywords; the similar keyword same value is specifically the number of characters that are the same between the keyword information existing in the historical database legal knowledge database and the extracted similar keyword information; read multiple similar keyword same values ​​and the corresponding similar keyword total values ​​and perform comprehensive calculations in combination with similar keyword correction factors to obtain multiple similarity values ​​of similar keywords.

[0045] The formula for calculating the similarity value of similar keywords is as follows: Among them, Xjs is the similarity value of similar keywords, Xjx is the same value of similar keyword characters, Xjz is the total value of similar keyword characters corresponding to the same value of similar keyword characters, and ξ is the correction factor of similar keywords.

[0046] The specific process of calculating the similar keyword correction factor is as follows: obtain the keyword information existing in the legal knowledge database of the historical database for several times, and match them with the extracted similar keyword information to obtain the similar keyword character identical measurement values ​​and similar keyword character identical actual values; perform difference calculation on the similar keyword character identical measurement values ​​and similar keyword character identical actual values ​​obtained by each match, and perform mean calculation on the difference results each time by combining the harmonic mean method and the weighted average method to obtain the similar keyword correction factor, and the calculation formula is as follows: Among them, Xsz t The actual value of the same characters of similar keywords obtained by matching the keyword information existing in the legal knowledge database of the tth historical database with the extracted similar keyword information, Xcz t The measurement value of similar keyword characters obtained by matching the keyword information existing in the historical database legal knowledge database with the extracted similar keyword information for the tth time, t = 1, 2, 3, ..., U, U is the total number of times the keyword information existing in the historical database legal knowledge database is matched with the extracted similar keyword information.

[0047] The calculation of similar keyword correction factors can also be combined with the geometric mean method, and the calculation formula is as follows: Among them, Xsz k The actual value of the same similar keyword characters obtained by matching the keyword information existing in the legal knowledge database of the kth historical database with the extracted similar keyword information, Xcz kThe measurement value of similar keyword characters obtained by matching the keyword information existing in the historical database legal knowledge database with the extracted similar keyword information for the kth time, k = 1, 2, 3, ..., M, M is the total number of times the keyword information existing in the historical database legal knowledge database is matched with the extracted similar keyword information.

[0048] In this implementation scheme, firstly, each keyword information and the number of characters in the historical database legal knowledge database are read, and at the same time, the number of characters in the extracted keyword information is read. Then, for each keyword, its character identity value is calculated, that is, the number of characters that are the same as the keyword information in the historical database legal knowledge database and the extracted keyword information. Then, the total number of characters of each keyword information is calculated, including the keywords in the historical database legal knowledge database and the extracted keywords. The keyword correction factor is calculated. First, the keyword character identity measurement value and the character identity actual value obtained by several matches are obtained, and the difference is calculated. Then, the keyword correction factor is obtained by combining the moving exponential mean method. Then, the keyword similarity value is calculated in combination with the keyword correction factor. The specific process of calculating the similarity value of similar keywords is as follows: first, each keyword information and the number of characters in the historical database legal knowledge database are read, and at the same time, the number of characters of the extracted similar keyword information is read. Then, for each keyword, its similar keyword identity value is calculated, that is, the keyword information in the historical database legal knowledge database. The number of characters that are identical between the information and the extracted similar keyword information is then calculated, and the total number of characters in each keyword information is then calculated, including the keywords existing in the historical database legal knowledge database and the extracted similar keywords, and the similar keyword correction factor is calculated. First, the similar keyword character identical measurement values ​​and the actual character identical values ​​of the similar keywords obtained by several matches are obtained, and the difference is calculated. Then, the similar keyword correction factor is obtained by combining the harmonic mean method and the weighted average method. Then, the similar keyword similarity value is calculated based on the similar keyword correction factor. By considering the character identical value and the total character value, the system can more accurately calculate the keyword similarity and improve the matching accuracy. Through the keyword correction factor, the system can consider the historical matching situation, further optimize the similarity calculation, and improve the matching stability and reliability. Considering the similarity of similar keywords, the system expands the matching range and provides more comprehensive support, especially when the keywords provided by the user are not clear enough. By adopting different mean calculation methods, the system can more flexibly adapt to the matching needs in different scenarios, thereby improving the versatility and adaptability of the system.

[0049] In summary, this application has at least the following effects:

[0050] This legal knowledge sharing platform applied to document reading can improve the accuracy of keyword matching by establishing and updating the historical legal knowledge database. The historical keyword extraction unit in the historical data processing module can go deep into the content of historical documents and extract keyword information, while the historical legal knowledge database update unit ensures that the legal knowledge in the database is kept up to date, thereby increasing the accuracy and matching effect of the analysis module in analyzing the content of the document.

[0051] This legal knowledge sharing platform applied to document reading can optimize the relevance of legal knowledge by establishing and updating the association map of the historical legal knowledge database. The historical legal knowledge database establishment unit establishes the association between keywords and legal knowledge content and case examples, while the historical legal knowledge database update unit ensures the accuracy of the association by updating the association map, thereby improving the in-depth analysis of the document content to be analyzed and the matching effect of related legal knowledge.

[0052] This legal knowledge sharing platform applied to document reading can realize personalized recommendations by analyzing users' historical queries and reading behaviors. The analysis module can make personalized legal knowledge recommendations based on keyword information and similar keyword information extracted by users. The establishment and updating of the historical legal knowledge database ensures that the recommended legal knowledge is comprehensive, accurate and relevant to user needs, thereby improving the accuracy of personalized recommendations.

[0053] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0054] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A legal knowledge sharing platform for document reading, characterized by: include: Data acquisition module, historical data processing module, analysis module, output module; The data acquisition module is used to acquire historical data and document content information data to be analyzed; The historical data processing module is used to establish a historical legal knowledge database based on the acquired historical data; The analysis module is used to analyze and match the document content information data to be analyzed based on the historical legal knowledge database; The output module is used to display the analysis and matching results of the analysis module; The specific process of analyzing and matching the document content information data to be analyzed based on the historical legal knowledge database is as follows: Read the document content information data to be analyzed and extract keyword information; Based on the extracted keyword information, query the historical database and legal knowledge database to see whether there is matching keyword information; If so, the legal knowledge content text data and related case examples related to the matching keyword information are output; If not, further analysis is performed on the extracted keyword information; The specific process of further analyzing the extracted keyword information is as follows: Read the extracted keyword information for analysis to obtain similar keyword information with similar meaning to the keyword; Based on similar keyword information, query the historical database and legal knowledge database to see whether there is matching keyword information; If so, the legal knowledge content text data and related case examples related to the matching keyword information are output; If not, then respectively calculate the similarity values ​​between the keyword information existing in the historical database legal knowledge database and the extracted keyword information and the similar keyword information, and output the keyword information existing in the historical database legal knowledge database with similarity values ​​higher than the threshold in descending order; The similarity value includes a keyword similarity value and a similar keyword similarity value. The specific process of calculating the similarity value between the keyword information existing in the historical database legal knowledge database and the extracted keyword information is as follows: Read each keyword information existing in the legal knowledge database of the historical database and the number of characters in the extracted keyword information; The number of characters of each keyword information existing in the historical database legal knowledge database is respectively added to the number of characters of the extracted keyword information to obtain a total value of multiple keyword characters; Match each keyword information existing in the historical database legal knowledge database with the extracted keyword information respectively to obtain multiple keyword character identical values; the keyword character identical values ​​are specifically the number of identical characters between the keyword information existing in the historical database legal knowledge database and the extracted keyword information; Read the same values ​​of multiple keyword characters and the corresponding total values ​​of keyword characters and perform comprehensive calculations in combination with keyword correction factors to obtain multiple keyword similarity values; The specific process of calculating the keyword correction factor is as follows: Obtain keyword information existing in the legal knowledge database of the historical database for several times and match them with the extracted keyword information to obtain the keyword character identical measurement value and the keyword character identical actual value; The difference between the measured values ​​of the keyword characters with the same characters and the actual values ​​of the keyword characters obtained in each match is calculated, and the difference result of each match is combined with the moving exponential mean method to calculate the average value to obtain the keyword correction factor; The formula for calculating keyword similarity value is as follows: Among them, Gxs is the keyword similarity value, Gjx is the keyword character identical value, and Gjz is the total keyword character value corresponding to the keyword character identical value. is the keyword correction factor, Sz r-1 The actual value of the keyword characters obtained by matching the keyword information in the legal knowledge database of the historical database for the r-1th time with the extracted keyword information is the same as that obtained by Cz r-1 The same measurement value of keyword characters obtained by matching the keyword information in the legal knowledge database of the historical database with the extracted keyword information is obtained, and 1+ζ is Sz r-1 -Cz r-1 The proportionality factor, Sz r The actual value of the keyword characters obtained by matching the keyword information in the legal knowledge database of the rth historical database with the extracted keyword information is the same as that obtained by Cz r is the keyword character identical measurement value obtained by matching the keyword information existing in the legal knowledge database of the rth historical database with the extracted keyword information, ζ is Sz r -Cz r The proportional coefficient is r=1, 2, 3, …, D, where D is the total number of times the keyword information existing in the acquired historical database legal knowledge database is matched with the extracted keyword information.

2. The legal knowledge sharing platform for document reading according to claim 1 is characterized in that: The data acquisition module includes: a historical data acquisition unit and a document content information data acquisition unit; The historical data acquisition unit is used to acquire and preprocess historical data, and store the preprocessed historical data, wherein the historical data specifically includes historical document content text data, legal knowledge content text data involved in the historical document content text data, and case example data associated with the involved legal knowledge content text data; The document content information data acquisition unit is used to acquire the document content information data to be analyzed and pre-process it, and store the document content information data to be analyzed after the pre-processing.

3. The legal knowledge sharing platform for document reading according to claim 1 is characterized in that ,The historical data processing module includes: a historical keyword extraction unit, a historical legal knowledge database establishment unit, and a historical legal knowledge database updating unit; The historical keyword extraction unit is used to read the pre-processed historical document content text data and extract keyword information from the historical document content text data; The historical legal knowledge database establishing unit is used to establish a historical legal knowledge database; The historical legal knowledge database updating unit is used to update the content of the established historical legal knowledge database based on the keyword information in the extracted historical document content text data, the legal knowledge content text data involved in the historical document content text data, and the case examples associated with the involved legal knowledge content text data.

4. The legal knowledge sharing platform for document reading according to claim 3 is characterized in that ,The specific process of extracting keyword information from the text data of ,historical documents is as follows: Read the pre-processed text data of historical documents; Based on natural language processing tools, the pre-processed text data of historical documents is segmented and cut into words; Remove stop words from the text data of historical documents after word segmentation; Perform part-of-speech tagging based on the text data of historical documents after removing stop words; Nouns and professional terms are extracted from the historical document content text data after part-of-speech tagging and marked as keyword information.

5. The legal knowledge sharing platform for document reading according to claim 3 is characterized in that ,The specific process of updating the content of the established historical legal knowledge database is as follows: Read keyword information, legal knowledge content text data related to historical document content text data, and case examples associated with the legal knowledge content text data involved; Based on natural language processing technology, a correlation map is established between keyword information, legal knowledge content text data involved in historical document content text data, and case examples associated with the legal knowledge content text data involved; Based on the keyword information, search the historical legal knowledge database to see if there is any relevant legal knowledge; If it already exists, then determine whether the legal knowledge in the association graph is consistent with the existing legal knowledge; If the legal knowledge in the association graph is consistent with the existing legal knowledge, then determine whether the case examples in the association graph are consistent with the existing case examples; If the case examples in the association graph match the existing case examples, no action will be taken; If the case examples in the association graph do not match the existing case examples, the case examples in the association graph are added to the historical legal knowledge database, and the association between the case examples in the association graph and the existing case examples is established based on natural language processing technology; If the legal knowledge in the association graph does not match the existing legal knowledge, the legal knowledge in the association graph and the corresponding case examples are added to the historical legal knowledge database; If no relevant legal knowledge is found, the extraction of legal knowledge will be established; The newly extracted legal knowledge content and association maps are added to the historical legal knowledge database.

Images