Big Data-Based Information Management System and Method for Legal Consultation Services

Abstract

The present invention relates to the technical field of legal consultation, specifically a legal consultation service information management system and method based on big data, including: a consultation zoning module for obtaining consultation information when a user consults, and judging the consultation zoning of the consultation information relative to legal services according to the intention of the user when consulting; a zoning mapping module for obtaining the legal zoning of the consultation information and constructing a mapping relationship between the consultation zoning and the legal zoning; a legal provision combination module for extracting key zoning from the consultation zoning and the legal zoning, and judging the combination matching degree between multiple legal provisions in the legal zoning according to the key zoning to obtain a legal provision preference combination; a case update module for, based on the legal provision preference combination, checking the information in the legal zoning, identifying the update situation of cases in the legal zoning, and updating the mapping relationship between the consultation zoning and the legal zoning according to the update situation of the cases, improving the accuracy and comprehensiveness of legal consultation services.

Description

Technical Field

[0001] The present invention relates to the technical field of legal consultation, specifically a legal consultation service information management system and method based on big data. Background Art

[0002] Legal consultation refers to the activity of legal service providers explaining, clarifying, giving suggestions and solutions on legal matters. It is not only limited to lawyers' answers to legal knowledge questions from legal seekers, but also involves more extensive legal workers' explanations on laws. However, with the rapid development of big data technology, it has become possible to process and utilize a large amount of legal data and case information. In order to better meet the needs of users for legal consultation and improve service efficiency and accuracy, it is necessary to combine various legal provisions, cases and corresponding user consultation content to complete a comprehensive answer to user consultations.

[0003] For example, Chinese Patent Publication No. CN117473074A discloses an intelligent information matching system and method for judicial cases based on artificial intelligence, belonging to the field of judicial information matching. The intelligent information matching system for judicial cases includes a case monitoring module, a database, a case analysis module and an intelligent matching module. The case monitoring module is used to collect the basic data information of historical judicial cases and the retrieval information of legal service personnel. The database is used to encrypt and store the collected data information and analysis results. The case analysis module is used to analyze the key concern content area and predicted stance angle of legal service personnel, and analyze and quote legal article information. The intelligent matching module is used to adjust the content of the retrieved historical judicial cases according to the analysis results and display the quoted legal articles extracted by the analysis.

[0004] For example, Chinese Patent Publication No. CN118113853A discloses a legal consultation service management method and system for assisting large language models, which relates to the technical field of intelligent language text processing. The method includes: obtaining legal consultation sample data, including user question-and-answer data, user question-and-answer audio data and legal knowledge data, performing data conversion to generate a structured text data set; constructing a seed instruction database according to the user question-and-answer data, and dividing the structured text data set into multiple basic legal knowledge bases and multiple stylized knowledge bases; training an auxiliary large language model according to the seed instruction database, multiple basic legal knowledge bases and multiple stylized knowledge bases, performing legal knowledge matching, and outputting knowledge question-and-answer information.

[0005] The prior art describes the method of selecting legal articles from the legal service personnel's solutions and the use of language models to set Q&A information. These methods represent the processing of legal consultations from two different perspectives. However, when the legal articles change or the user's consultation trend changes, it is difficult to identify the corresponding legal article combinations in these situations only through the above two methods. It is necessary to timely discover the legal article information required by the current user and use these legal articles to update the database set during the user's consultation to improve the efficiency and accuracy of the user's consultation. Summary of the Invention

[0006] To solve the above technical problems, the technical solution adopted by the present invention is: a legal consultation service information management system based on big data, including: a consultation partition module for obtaining the consultation information during the user's consultation and judging the consultation partition of the consultation information relative to legal services according to the intention during the user's consultation.

[0007] A partition mapping module for obtaining the legal partition of the consultation information and constructing a mapping relationship between the consultation partition and the legal partition.

[0008] A legal article combination module for extracting key partitions from the consultation partition and the legal partition and judging the combination matching degree between multiple legal articles in the legal partition according to the key partitions to obtain a legal article preference combination.

[0009] A case update module for, based on the legal article preference combination, checking the information in the legal partition, identifying the update situation of the cases in the legal partition, and updating the mapping relationship between the consultation partition and the legal partition according to the update situation of the cases.

[0010] A consultation management module for identifying the consultation target and consultation order of the consultation information and generating a consultation management database according to the updated mapping relationship between the consultation partition and the legal partition.

[0011] A legal consultation service information management method based on big data, including: S1. Obtain the consultation information submitted by the user, classify the consultation information using an intention classification model, and identify the intention category; analyze synonyms, polysemous words, and related words under the intention category to form a consultation partition.

[0012] S2. Call the legal articles and cases related to the consultation information, generate an unlabeled legal article recognition result, screen the legal article recognition result, and obtain the target legal article recognition result as the legal partition; construct a mapping relationship between the consultation partition and the legal partition according to the information representation in the consultation partition and the description information and category information of the legal partition.

[0013] S3. Perform clustering analysis on the consultation partition and the legal partition to determine the key partition; calculate the cosine similarity between keywords in the key partition, extract legal articles, and set a legal article preference combination.

[0014] S4. Extract the time distribution probability according to the legal provision bias combination, set the target path, and obtain the combination occurrence probability through fitting; compare the combination occurrence probability with the citation situation of cases in the legal partition, identify and update the cases, and update the mapping relationship between the consultation partition and the legal partition.

[0015] S5. According to the updated mapping relationship between the consultation partition and the legal partition, extract the consultation targets, and sort them according to the occurrence probability to obtain the consultation order; combine the consultation targets and the consultation order to generate a consultation management library.

[0016] The beneficial effects of the present invention are as follows: First, through the classification and mapping construction of consultation information during user consultation, after identifying the user's intention, relevant data partitions can be set according to the synonyms, polysemous words, and related words of the user's consultation. Subsequently, relevant legal provisions and cases can be quickly matched for these partitions, improving the accuracy of the service.

[0017] Second, by constructing a mapping relationship between the consultation partition and the legal partition, legal provisions and cases closely related to the consultation information can be automatically invoked to generate legal provision recognition results, and legal provisions highly matching the target consultation information can be determined as the basis of the legal partition, realizing the intelligent mapping between the consultation partition and the legal partition; then, based on the information representation in the consultation partition and the detailed description and category information of the legal partition, a mapping relationship is constructed to ensure the accuracy and pertinence of legal consultation services; finally, through the construction of the mapping relationship, relevant legal knowledge and cases can be quickly located to provide timely and efficient legal consultation services for users.

[0018] Third, through in-depth clustering analysis of the consultation partition and the legal partition, key partitions are identified, and after calculating the similarity between keywords in the key partitions, the corresponding legal provisions of the keywords are extracted to set the legal provision bias combination, which can meet the user's consultation needs; the target path is set according to the time distribution probability of the legal provision bias combination, and the combination occurrence probability is obtained through fitting analysis and compared with the citation situation of cases in the legal partition to accurately identify and update the case information, ensuring the timeliness of legal consultation services. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention will be further described below in conjunction with the drawings and embodiments.

[0020] Figure 1 is the system framework diagram of the legal consultation service information management system based on big data.

[0021] Figure 2 is the process schematic diagram of the consultation partition module of the legal consultation service information management system based on big data.

[0022] Figure 3It is a flow diagram of the partition mapping module of the legal consultation service information management system based on big data.

[0023] Figure 4 It is a flow diagram of the legal provision combination module of the legal consultation service information management system based on big data.

[0024] Figure 5 It is a flow diagram of the legal consultation service information management method based on big data. Specific implementation manners

[0025] The embodiments of the present invention will be described in detail below. The described embodiments are exemplary and are only used to explain the present invention, and should not be construed as a limitation to the present invention. For those not specified in the embodiments about specific technologies or conditions, they shall be carried out according to the technologies or conditions described in the literature in this field or according to the product specifications.

[0026] Refer to Figure 1 , a legal consultation service information management system based on big data, includes: a consultation partition module, a partition mapping module, a legal provision combination module, a case update module, and a consultation management module; wherein, the output end of the consultation partition module is connected to the partition mapping module, the output end of the partition mapping module is connected to the legal provision combination module, the output end of the legal provision combination module is connected to the case update module, and the output end of the case update module is connected to the consultation management module.

[0027] The consultation partition module is used to obtain the consultation information when a user consults, and judge the consultation partition of the consultation information relative to legal services according to the intention when the user consults.

[0028] The partition mapping module is used to obtain the legal partition of the consultation information and construct the mapping relationship between the consultation partition and the legal partition.

[0029] The legal provision combination module is used to extract the key partitions from the consultation partition and the legal partition, and judge the combination matching degree between multiple legal provisions in the legal partition according to the key partitions to obtain the legal provision bias combination.

[0030] The case update module is used to perform information verification on the legal partition based on the legal provision bias combination, identify the update situation of the cases in the legal partition, and update the mapping relationship between the consultation partition and the legal partition according to the update situation of the cases.

[0031] The consultation management module is used to identify the consultation target and consultation order of the consultation information according to the updated mapping relationship between the consultation partition and the legal partition, and generate a consultation management library.

[0032] In one embodiment of the present invention, the consultation partition module sets multiple partitions according to the intentions of users during consultation, and sets multiple related partitions according to the synonyms, polysemous words, and related words existing in the consultation information, and combines these partitions to obtain the partition for the current consultation information of the user, so as to complete the overall processing of the corresponding data.

[0033] When users obtain corresponding legal services, due to the different educational levels and environments of users themselves, users will have different forms of descriptions for the laws and legal issues they want to understand. At this time, it is necessary to first perform intention recognition from the consultation information described by users to find out multiple different situations that users want to identify; then perform preliminary setting to complete the preliminary setting of the consultation partition; at this time, when obtaining the partition according to the user's intention, it is easy to have multiple similar but different descriptive answers for the current legal issues and terms to be consulted due to the proximity of a word or the interpretation of the intention itself. At this time, it is necessary to preliminarily obtain multiple consultation partitions. After that, for the synonyms and polysemous words that are likely to have multiple interpretations in the user's described vocabulary, further understand the user's own intention. At the same time, there are some users who may have disordered word order and incorrect word usage. These users do not want to explain directly because their own problems are relatively prominent. At this time, it is necessary to additionally obtain a related word to complete the setting of the consultation partition.

[0034] As Figure 2 shown, the implementation method of the consultation partition module includes: for any consultation information during user consultation, obtaining the intention classification model corresponding to the consultation information; the intention classification model is adopted in ways such as logistic regression and deep learning model. For example, in logistic regression, after extracting the word vector of the current consultation information, the word vector is input into the logistic regression, and the intention probability, loss rate, and attention score of different words relative to the model for all texts during training are judged to obtain the possible intention categories included in the consultation information; the deep learning model is to use multiple convolutional layers and neurons to extract the intention categories existing in the information from the consultation information to obtain the general direction that the user wants to consult.

[0035] Using the intention classification model to classify the consultation information to obtain at least one intention category; the intention category can be a query, a request for help, a complaint, or other types of needs. At the same time, this category will also include the classification for a certain situation, such as specific classifications like criminal and civil, to determine the general intention of the current user.

[0036] Identify the synonyms, polysemous words, and related words in the consultation information under the corresponding intention category to form a text sample set; the text sample set will include the synonyms, polysemous words, and related words corresponding to the consultation information under the corresponding intention category. These words are the related words of some words in the consultation information that can directly represent the user's intention. At this time, it is necessary to analyze the text sample set, such as synonym analysis, polysemous word analysis, and related word extraction. For example, use the context of synonyms to analyze synonyms, use the meaning of polysemous words under context understanding, and use related words and co-occurring words to complete the analysis of the text sample set. Then verify the relationship between the relative entities of these three words to cover the content involved in the current user consultation. These contents will be represented as multiple data sets in the synonym area, polysemous word analysis area, and related word association area, that is, the described consultation partition. This represents being distributed into different types of data sets, aiming to clearly show the role of each word in its specific context. Finally, convert these data into a structured format for subsequent setting of mapping relationships.

[0037] Analyze the synonyms, polysemous words, and related words in the text sample set respectively, and sequentially obtain the synonym area, polysemous word analysis area, and related word association area corresponding to the text sample set, which are used as the consultation partitions of the consultation information with respect to legal services.

[0038] For the synonym area, in the form of a synonym dictionary, extract the synonyms of the corresponding words under the currently identified intention category to obtain a synonym area. This synonym area will list the common synonym pairs included in the current consultation information and explain the currently appearing synonym pairs, including word meaning, usage, differences, etc.; then provide examples to help users understand the usage of synonyms in different contexts.

[0039] The polysemous word analysis area lists the polysemous words in the current legal consultation, and details each sense of each polysemous word, including word meaning, usage, applicable objects, etc. At the same time, reveal the internal relationships between each sense, such as semantic cores, extended meanings, etc.; then provide examples to show the usage of polysemous words in different contexts.

[0040] The related word association area establishes an association network between words according to the semantic relationships of legal consultation words, that is, marks the associated words that appear in the current consultation to facilitate users to view the analysis of related words; then shows the common collocations and usages of related words in legal consultations. In this way, the required consultation partition is formed. The form of the consultation partition represents the corresponding words that may exist under the main intention of the user, and the content explained and described by these words forms a data set in a similar area. After the user completes the consultation, they can obtain sufficient content descriptions from these corresponding partition data. These partitions are also the subsequent processing parts to accurately screen out the text content required by the user.

[0041] When obtaining the near-synonym area, polysemy analysis area, and related-word association area corresponding to the text sample set, in order to distinguish the influence of different intention categories on these partitions, the implementation method also includes: merging the near-synonyms, polysemous words, and related words in the text sample set according to the intention categories to obtain multiple intention merging results. The intention merging result means merging the corresponding contents of the near-synonyms, polysemous words, and related words according to the intention categories to obtain all the data for one consultation information, and deleting the duplicate and missing contents therein.

[0042] Extract the near-synonym pairs in the intention merging result, and compare the near-synonym pairs with the near-synonym dictionary to obtain the near-synonym area.

[0043] Extract the definition change rate of polysemous words and the association strength of related words in the intention merging result, and divide the intention merging result according to the definition change rate of polysemous words and the association strength of related words to obtain the polysemy analysis area and the related-word association area.

[0044] The definition change rate of a polysemous word represents the degree to which the definition of the polysemous word will change after merging the consultation information of the user according to the intention category. At this time, the semantic distance between the definitions, such as cosine similarity, is used to quantify the degree of definition change at this time, and the ratio of this degree to the degree of definition change of all polysemous words currently is regarded as the definition change rate of the polysemous word, which reflects the degree of change in the meaning expressed by the polysemous word in the corresponding context after merging according to the intention category in a text segment. When the definition change rate of a polysemous word is large, it generally means that the meaning of such words depends to a large extent on the specific context. For example, the word "execute" may have different meanings in different legal backgrounds; these words need to be determined considering the context. When the definition change rate of a polysemous word is small, it generally represents a word with a fixed meaning, such as "will". Whether discussing inheritance distribution, inheritance law, or family disputes, the basic definition of "will" is a formal written statement of an individual's arrangements for their affairs after death. Then, according to the definition change rate of the polysemous word, the polysemous words at this time are divided to obtain the polysemy analysis area corresponding to the polysemous words.

[0045] The association strength of related words represents the probability of the occurrence of related words and corresponding words in the intention category, and measures whether the value of the association strength of related words will change after merging. That is, when two corresponding words in the intention category correspond to one related word, the association strength of the related word will increase, or when two related words correspond to one corresponding word in the intention category, it will also cause the association strength of the related word to increase. Then, calculate the co-occurrence probability of these merged words to change the original association strength value. Finally, divide the related words in the intention merging result according to the association strength of the related words to obtain related word association regions with different values. When the association strength of related words is large, generally it indicates that these related words represent more specific legal case details in the co-occurring legal provisions or specific legal issues; when the association strength of related words is small, generally it indicates some loose information, which may mean that from specific issues to broad backgrounds or overviews, these indicate that the key points of what the user expresses are more scattered, or the presentation of related issues is unclear. According to the correlation strength of these related words and the change rate of the interpretations of polysemous words, it is possible to improve the adjustment of the type of answers to users in the case where the user's description and key points change or are different, so as to improve the efficiency of communication with users.

[0046] In order to make the content displayed in the consultation partition more sufficient, when judging the consultation partition of the consultation information relative to legal services, it can also include: judging the consultation partition, analyzing the number of consultations and consultation time of users in the consultation partition. For the number of consultations and consultation time obtained here, the synonym region, polysemous word analysis region and related word association region existing in the consultation partition are used. According to the number of times the data in this partition is consulted by users and the corresponding time during consultation, the consultation partition is fitted according to the number of consultations and consultation time, so that the corresponding words in the consultation partition gradually approach the actual intention of the user; construct the mapping relationship from the consultation partition to the actual intention of the user to form the mapping situation existing between the current consultation partitions, and complete the judgment of the consultation partition of the consultation information relative to legal services.

[0047] When fitting the consultation partition according to the number of consultations and consultation time, it is necessary to generate data points for the consultation partition based on the distribution of consultation time, fit the data of the number of consultations changing with time, and obtain the trend of the number of consultations changing with time. Then, take the slope value in the trend of the number of consultations changing with time as the mapping situation existing between the current consultation partitions. This method is to show the changing trend of the user's behavior when consulting legal issues, which is convenient for predicting the information that the user wants to consult next.

[0048] In one embodiment of the present invention, the partition mapping module mainly partitions the French and cases that the current consultation information may correspond to, and forms a mapping relationship between the relevant content in this partition and the currently divided consultation partition, which is convenient for subsequent verification and adjustment, so as to find the accurate French and cases in the user's consultation, and complete the comprehensive classification management of the actual answers and relevant information for the user.

[0049] During partition mapping, it is actually to find cases and legal articles that may have the same intention as the current consultation partition, so as to determine the key issues that need to be described and solved in the current consultation partition.

[0050] When the partition mapping module constructs a legal partition, it will find the corresponding legal articles and cases from the consultation information, set this part of the corresponding content as the legal partition, and then set the mapping relationship between the content of the legal partition and the consultation partition in a structured formal language; at the same time, in order to improve the specific content of the division, it will generate multiple law identification results in a tagless form from the consultation information, and when the number of law identification results is greater than a certain threshold, combine the corresponding content into a legal partition; then calculate the similarity value for these tagless data, and adjust the law identification results according to the similarity value, and finally obtain a relatively comprehensive legal partition.

[0051] As Figure 3 shown, the implementation method of the partition mapping module includes: calling the legal articles and cases corresponding to the consultation information to generate multiple tagless law identification results, and the tagless law identification results represent legal articles and cases that are not associated with the vocabulary in the consultation partition.

[0052] Judge whether multiple tagless law identification results are target law identification results. If they are target law identification results, regard the target law identification results as the legal partition of the consultation information.

[0053] The implementation methods for determining whether multiple untagged legal provision recognition results are target legal provision recognition results include: sequentially determining whether the number of current legal provision recognition results is greater than the first quantity threshold. If it is greater than the first quantity threshold and the similarity value of the current legal provision recognition results is greater than the first similarity threshold, then the current legal provision recognition results are taken as the target legal provision recognition results. At this time, when judging that the number of legal provision recognition results is large, it means that there are sufficient independent results to form one or more meaningful legal partitions; when the number is small, it means that the recognized results are not sufficient to separately form a comprehensive or meaningful legal partition; at the same time, the similarity value will represent the similarity situation in the content of the legal provision recognition results. The similarity value will calculate the corresponding legal provisions and cases in the legal provision recognition results, and then judge the relationships between these data one by one, as the dataset corresponding to a required target legal provision recognition result. The similarity value of this legal provision recognition result will use the average value of the similarity values of the existing data in the whole result to represent the overall similarity situation. If the similarity value of the legal provision recognition results is greater than the first similarity threshold, it means that these results point to the same legal issue or solution; if it is less than the first similarity threshold, it means that these results involve different legal provisions, cases or interpretations, or although they are relevant but have different focuses; at this time, these results need to be screened to form the current required legal partitions. After the corresponding processing of these legal partitions, their mapping relationships will be used as a reference for future legal consultation processing to improve the overall processing effect. At the same time, the above-mentioned first quantity threshold and first similarity threshold will use historical data when generating or managing legal information for users, and use the average value of the quantity and similarity of the data sent to users as the first quantity threshold and first similarity threshold used at this time.

[0054] If it is greater than the first quantity threshold and the similarity value of the current legal provision recognition results is less than the first similarity threshold, then the intersection of the target legal provision recognition results generated last time and the current legal provision recognition results is regarded as the target legal provision recognition results. Here, the intersection is used to find the legal provisions or cases commonly recognized in the two results, and these legal provisions or cases are considered to be relevant to the consultation information in both recognitions. The existence of the intersection indicates that these legal provisions or cases have high relevance and importance because they have been confirmed in the recognition results of different batches.

[0055] If it is less than the first quantity threshold and the similarity value of the current legal provision recognition results is greater than the first similarity threshold, then the current legal provision recognition results are superimposed with the adjacent legal provision recognition results as the target legal provision recognition results. The situation here is that when the number of recognized legal provisions or data is small, data is supplemented from the adjacent legal provision recognition results to form a relatively complete and comprehensive set of legal provisions.

[0056] If it is less than the first quantity threshold and the similarity value of the current legal provision recognition result is less than the first similarity threshold, it is determined that the current legal provision recognition result is not the target legal provision recognition result.

[0057] After obtaining the target legal provision recognition result here, the required legal partition is obtained. Then, the consultation partition and the legal partition are used to construct a mapping relationship according to legal logic. The legal logic described here refers to the types of legal provisions involved, such as substantive law, procedural law, administrative regulations, etc. According to these contents, the legal relationships involved in the consultation partition, such as contract relationships, tort relationships, labor relationships, etc., are gradually mapped to the legal partition to complete the mapping between the consultation partition and the legal partition.

[0058] Therefore, the implementation method of constructing the mapping relationship between the consultation partition and the legal partition includes: representing with the information in the synonym area, polysemy analysis area, and related word association area existing in the consultation partition, the description information and category of the legal partition, and constructing the mapping relationship between the consultation partition and the legal partition.

[0059] The information representation in the synonym area, polysemy analysis area, and related word association area existing in the consultation partition refers to the information corresponding to these synonyms, polysemes, and related words in the consultation partition. After mapping this information to the description of a certain legal provision and case in the legal partition, and then mapping it to the category of the legal partition, the mapping relationship between the consultation partition and the legal partition is completed.

[0060] In an embodiment of the present invention, the legal provision combination module is mainly used to extract key partitions from the consultation partition and the legal partition, and then judge the legal provisions that can correspond in these key partitions to identify multiple groups of combinable legal provisions. The combination matching degree is used to judge whether these legal provisions can be combined together and whether they can be used as the content for answering the same consultation information when combining the legal provisions in the legal partition. After finding these legal provision combinations, the consultation target under a certain matching degree is found to complete the recommendation and combination of legal provisions.

[0061] In the legal provision combination module, the key partition is the main content extracted from the consultation partition and the legal partition. This part of the content will represent the subsequent topic to be recognized, and judge the form of the combination of multiple legal provisions according to this topic to supplement the subsequent required legal provision information. Then, according to the information represented by these legal provisions, a relatively integrated and comprehensive combination is obtained as the embedded information for subsequent information verification, and the adjustment and update of the overall data are completed.

[0062] When calculating the combined matching degree, the length of the longest common subsequence between legal provision combinations is used for judgment to obtain the longest common subsequence for different data in the key partition, so as to obtain the existing legal provision bias combination at this time; at the same time, according to the keywords extracted under the key partition, multiple groups of data corresponding to the keywords can be processed by the cosine similarity method to obtain the common sequence, and then the corresponding common subsequence is obtained, thus completing the setting of the combined matching degree.

[0063] As Figure 4 shown, the implementation method of the legal provision combination module includes: clustering and analyzing the consultation partition and the legal partition according to the service type, legal type, and legal function, and setting the largest clustering center after clustering analysis as the key partition. Here, the service type mainly refers to the specific methods and contents of providing legal consultation services. For example, it may include face-to-face legal consultation, telephone consultation, online legal consultation, etc.; the legal type refers to legal consultations involving different legal fields, such as civil legal consultation, criminal legal consultation, administrative legal consultation, etc.; the legal function mainly refers to the role of legal consultation in solving legal problems, safeguarding legal rights and interests, preventing legal risks, etc., such as providing legal advice, drafting and reviewing contracts, representing litigation, etc.

[0064] Extract the keywords of the key partition, calculate the cosine similarity between each keyword, and set the common sequence related to the cosine similarity between each keyword; the common sequence related to the cosine similarity between each keyword refers to the data in the consultation partition and the legal partition corresponding to each keyword. Find the intersection of these data and use the intersection to describe the common sequence at this time; the acquisition of keywords will use the word frequency analysis technology, extract the words existing in the current key partition using the documents stored in the database, and mark multiple keywords according to the extracted word frequencies. The word frequency of the keywords will use the average value of the word frequencies marked as keywords in the documents stored in the database as the basis for extracting the keywords of the key partition at this time. Then, for the extracted keywords, calculate the cosine similarity between each pair; this step can be represented by vectorization, and the cosine similarity is used to complete the setting of the cosine similarity between the keywords. Then, select keywords according to the cosine similarity, find the intersection of the data corresponding to these keywords, and obtain the common sequence related to the cosine similarity between each keyword. At the same time, the cosine similarity between each keyword represents the similarity between two keywords, and this similarity needs to be greater than 0.6. Combine the data of each keyword with a cosine similarity greater than 0.6 to extract multiple common sequences. It should be noted that the common sequences extracted at this time can be the common sequences of the data combinations of two keywords with a cosine similarity greater than 0.6, or the common sequences of multiple groups of keywords with a cosine similarity greater than 0.6. Then, sort these combined common sequences according to the cosine similarity values of the keywords.

[0065] Using the common sequences related to the cosine similarity between keywords, extract the legal provisions existing in the common sequences, set the longest common subsequence between each legal provision, and set the length value of the longest common subsequence as the combined matching degree between each legal provision. After obtaining the common sequence, identify which legal provision the keyword under the current common sequence belongs to, and the data of this legal provision is included in the legal partition. Since the current key partition is extracted from the legal partition and the consultation partition, the keywords set at this time represent at least the content of one legal provision. Then, the essence of extracting the longest common subsequence between each legal provision at this time is to directly divide the common sequence into multiple common sequences calculated according to the cosine similarity of the keywords, extract the subsets of these common sequences, and finally obtain a longest common subsequence to know in what form of common sequence these legal provisions will exist. At this time, the longest common subsequence between each legal provision needs to be the longest common subsequence containing specific legal provisions, that is, when multiple specific legal provisions are included, how much data the longest common subsequence will contain, and these data will be calculated according to the total amount of relevant data.

[0066] According to the time distribution probability of each legal provision, set the legal provision bias combination for the combined matching degree between each legal provision. At this time, setting the legal provision bias combination divides the time distribution probability of the legal provision into multiple intervals. The time distribution probability of the legal provision is the probability of the appearance of multiple legal provisions at different time periods after combination. If the time distribution probability is different in a certain time period, it is considered that these legal provisions are commonly used in the most recent time period, which can reflect the evolution trend of the legal provisions over time. In this way, the form set by the legal provision bias combination under different time periods can be understood. At this time, set the legal provision bias combination according to the time distribution probability of multiple legal provisions corresponding to the combined matching degree between multiple legal provisions at different time periods, and combine these legal provisions into a legal provision bias combination according to the size of the time distribution probability; the legal provision bias combination will, in addition to including the common subsequence after the extraction process of multiple keywords for legal provisions, also include the corresponding legal provisions and time distribution probability to reflect the trends of different legal provision combinations at different times. It should be noted that the combined legal provision bias combination here does not modify the data according to the time distribution probability. At this time, the corresponding data is marked, and the combination situation between these multiple legal provisions is determined to complete the authentication of the combination form of these legal provisions.

[0067] In an embodiment of the present invention, the case update module is mainly used to compare the citation situation corresponding to the relevant cases in the legal partition based on the legal provision bias combination to verify whether the currently set legal provision combination is normally used in actual cases, and consider the classification of these situations in normal cases during user consultation to complete the mapping relationship established for user consultation.

[0068] The module set at this time is actually to solve legal consultation problems. During the process of promotion and update, the meaning of the vocabulary set for users may change, resulting in changes in the corresponding legal articles for some related words and synonyms. At this time, it is necessary to find the content that needs to be updated in the consultation area according to the keywords. After deleting and updating this part of the content, find the mapping of the updated cases, legal articles, and corresponding consultation content, so as to complete the processing and classification of various data. For example, due to the emergence of certain social cases, the cases of the legal articles corresponding to some related words have changed. Then, when consulting legal issues for this legal article, the legal articles mapped by some keywords and related words may change. At this time, it is necessary to adjust the corresponding case mapping to adjust the mapping relationship between the consultation area and the legal area in the current database.

[0069] In the current method of verifying the legal area and updating cases for the legal article bias combination, the combination and matching of relevant data are completed through the time distribution probability and combination matching degree set in the legal article bias combination. After that, the detailed situations in these data will be processed to adjust the relationship between the legal article and the user's consultation. Finally, it can be completed to adjust the legal article case mapping set for the user's language in the current database in real time according to the user's consultation, and improve the effect of the user's consultation.

[0070] The implementation method of the case update module includes: extracting the time distribution probability of each legal article from the legal article bias combination; setting the target path of the legal article bias combination according to the time period corresponding to the time distribution probability of each legal article; each path point on the target path represents the time distribution probability of the legal article bias combination at that point, and the specific legal article information existing at that point. According to the time distribution probability extracted in the previous step, the legal articles in the legal article bias combination are sorted or classified according to the time period they are in, and a path representing the change of the legal article bias combination over time is set accordingly. This path can be a time series graph or a curve graph, which is used to intuitively display the change trend of the legal article bias combination; through this step, the change of the legal bias in different time periods can be intuitively seen, which helps to understand the trend of the legal article bias combination in dealing with the user's consultation situation, so as to understand the change trend of the content biased in the user's consultation and the legal article given for explanation finally.

[0071] Fit the target paths of each legal provision in the legal provision bias combination to obtain the fitted target paths. Set the probability values of the fitted target paths in each time period as the combination occurrence probabilities of the legal provision bias combination. The target paths will adopt an interpolation form to combine the target paths corresponding to each legal provision in the legal provision bias combination to obtain a combined target path. The target paths will be connected according to the time distribution probabilities of different legal provisions in the corresponding time periods. Continuously connect these path points representing the target paths, and after connection, obtain a relatively smooth path to show a combined trend line of all legal provisions in the legal provision bias combination, which is convenient for predicting the biased consultation information of subsequent users when conducting service consultations, thereby improving the response speed and response accuracy for user consultations. At the same time, for the probability values of the fitted target paths in each time period, it represents the co-occurrence probability values of multiple legal provisions fitted by the current target path in each time period. This value represents the occurrence situation of multiple legal provisions in the current combination being consulted by users or provided in user cases at different time periods.

[0072] Compare the combination occurrence probability of the legal provision bias combination with the citation situation of cases in the legal division, identify the difference values that appear, and classify the cases in the legal division according to the difference values that appear to complete the update of the cases in the legal division.

[0073] At this time, it is to compare whether the combination occurrence probability of the legal provision bias combination is the same as the occurrence probability of these legal provision bias combinations in the cases to find out which parts need to be focused on. For example, classify the parts with differences between the combination occurrence probability and the citation situation of cases in the legal division according to the relative proportion values of the differences, such as the difference value of high-concern cases is greater than +10%, the difference value of low-concern cases is less than -10%, and the difference value of regular cases is between ±10%. And map the corresponding classifications of these classified cases to the legal division. The legal division marks the keywords corresponding to these classifications in the consultation division, and finally completes the update of the mapping relationship between the consultation division and the legal division.

[0074] In an embodiment of the present invention, the consultation management module is mainly used to generate a storage and classification situation for managing these updated data according to the updated mapping relationship between the consultation division and the legal division.

[0075] The consultation management library is used to update and adjust the relationship between different consultation information and relevant legal provisions and cases in real time, and obtain a management library according to these data, and use this management library to output the user demand information to complete the legal services required by the user.

[0076] After completing the update of the mapping relationship between the consultation partition and the legal partition, the corresponding data stored at this time can already represent the key points and areas that need attention in these consultations before and after the user's consultation. Then, at this time, it is to identify the key points in these areas and generate a consultation management library for these contents, so that when the user consults later, it can be directly called from the data in the currently set mapping relationship to improve the processing speed and efficiency of the data.

[0077] At this time, the implementation method of the consultation management module is as follows: According to the updated mapping relationship between the consultation partition and the legal partition, extract the consultation objectives in the consultation information. Here, in the updated mapping relationship between the consultation partition and the legal partition, find the updated partial data, and find the corresponding content in the consultation information from this partial data, and set this content as the consultation objective. Sort the consultation objectives according to the occurrence probability of the consultation objectives to obtain the consultation order in the consultation information; Combine the consultation objectives and the consultation order in a structured form to obtain the consultation management library.

[0078] The generated consultation management library at this time will contain multiple contents, such as consultation ID, user ID, legal partition, combination of relevant laws, consultation date, processing status, associated case ID, classification label, etc., to represent the consultation management library set after the user's consultation. This library will contain the comprehensive data content of synonyms, polysemous words, and related words when the current user consults to meet the user's needs for the corresponding laws.

[0079] As Figure 5 shown, the present invention also provides a method for managing legal consultation service information based on big data, including: S1. Obtain the consultation information submitted by the user, classify the consultation information using the intention classification model, and identify the intention category; Analyze synonyms, polysemous words, and related words under the intention category to form a consultation partition.

[0080] S2. Call the laws and cases related to the consultation information, generate a law recognition result without labels, screen the law recognition result, and obtain the target law recognition result as the legal partition; According to the information representation in the consultation partition and the description information and category information of the legal partition, construct a mapping relationship between the consultation partition and the legal partition.

[0081] S3. Perform clustering analysis on the consultation partition and the legal partition to determine the key partition; Calculate the cosine similarity between keywords in the key partition, extract laws, and set the law bias combination.

[0082] S4. Extract the time distribution probability according to the law bias combination, set the target path, and fit to obtain the combination occurrence probability; Compare the combination occurrence probability with the citation situation of cases in the legal partition, identify and update the cases, and update the mapping relationship between the consultation partition and the legal partition.

[0083] S5. Extract the consultation objectives according to the mapping relationship between the updated consultation partition and the legal partition, and sort them according to the occurrence probability to obtain the consultation order; combine the consultation objectives and the consultation order to generate a consultation management library.

[0084] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention, and still be covered by the protection scope of the present invention.

Claims

1. Legal consulting service information management system based on big data, characterized by: include: The consultation partitioning module is used to obtain the consultation information of the user during consultation and determine the consultation partition of the consultation information relative to the legal service according to the user's intention during consultation; A partition mapping module is used to obtain the legal partitions of consulting information and construct a mapping relationship between consulting partitions and legal partitions; The legal article combination module is used to extract key partitions from the consulting partition and the legal partition, and judge the combination matching degree between multiple legal articles in the legal partition according to the key partition to obtain the biased combination of legal articles; The implementation method includes: clustering the consulting partitions and legal partitions according to service type, legal type, and legal function, extracting key partitions and keywords, calculating the cosine similarity between keywords, extracting legal provisions in the common sequence and setting the longest common subsequence length as the combination matching degree, and creating a biased combination of legal provisions according to the time distribution probability of legal provisions; The case update module is used to verify the information of the legal partition based on the combination of legal provisions, identify the update of the cases in the legal partition, and update the mapping relationship between the consultation partition and the legal partition according to the update of the cases; its implementation method includes: extracting the time distribution probability from the combination of legal provisions, setting the target path and fitting the probability of combination occurrence, comparing it with the case citation situation, updating the case according to the difference value classification, and updating the mapping relationship between the consultation partition and the legal partition; The consultation management module is used to identify the consultation objectives and consultation sequence of the consultation information according to the mapping relationship between the updated consultation partitions and the legal partitions, and to generate a consultation management library.

2. The legal consulting service information management system based on big data according to claim 1 is characterized in that: The implementation of the consultation partition module includes: For any consultation information during user consultation, obtain the intent classification model corresponding to the consultation information; Use the intent classification model to classify the consultation information and obtain at least one intent category; Identify synonyms, polysemous words and related words in the consultation information under the corresponding intent category to form a text sample set; The synonyms, polysemous words and related words in the text sample set are analyzed respectively, and the synonym area, polysemous word analysis area and related word association area corresponding to the text sample set are obtained in turn, and used as the consulting partition of the consulting information relative to the legal service.

3. The legal consulting service information management system based on big data according to claim 2 is characterized in that: The implementation method of obtaining the synonym area, the polysemous word analysis area and the related word association area corresponding to the text sample set also includes: The synonyms, polysemous words and related words in the text sample set are merged according to the intent category to obtain multiple intent merging results; Extract synonym pairs from the intention merging result, compare the synonym pairs with the synonym dictionary, and obtain the synonym area; The meaning change rate of polysemous words and the association strength of related words in the intention merging results are extracted, and the intention merging results are divided according to the meaning change rate of polysemous words and the association strength of related words to obtain the polysemous word analysis area and the related word association area.

4. The legal consulting service information management system based on big data according to claim 1 is characterized in that: The consultation partitioning implementation methods for judging consultation information relative to legal services also include: Judge the consultation partitions, analyze the number of consultations and consultation time of users in the consultation partitions, fit the consultation partitions according to the number of consultations and consultation time, and build a mapping relationship from the consultation partitions to the users' actual intentions.

5. The legal consulting service information management system based on big data according to claim 1 is characterized in that: The implementation of the partition mapping module includes: Call the legal provisions and cases corresponding to the consultation information to generate multiple unlabeled legal provision recognition results, where the unlabeled legal provision recognition results represent legal provisions and cases that are not associated with the vocabulary in the consultation partition; It is determined whether multiple unlabeled legal article recognition results are target legal article recognition results. If they are target legal article recognition results, the target legal article recognition results are regarded as legal partitions of the consulting information.

6. The legal consulting service information management system based on big data according to claim 3 is characterized in that: The implementation method of constructing the mapping relationship between the consultation partition and the legal partition includes: using the information representation of the synonym area, polysemous word resolution area and related word association area existing in the consultation partition, the description information of the legal partition and the category of the legal partition to construct a mapping relationship between the consultation partition and the legal partition.

7. The legal consulting service information management system based on big data according to claim 1 is characterized in that: The implementation methods of the legal article combination module include: Set the maximum cluster center after cluster analysis as the key partition; Set a common sequence related to the cosine similarity between keywords; Using the common sequence related to the cosine similarity between the keywords, extract the legal provisions in the common sequence, set the longest common subsequence between the legal provisions, and set the length value of the longest common subsequence as the combined matching degree between the legal provisions; The combination matching degree between each legal provision is determined according to the time distribution probability of each legal provision, and the biased combination of legal provisions is set.

8. The legal consulting service information management system based on big data according to claim 7 is characterized in that: The implementation of the case update module specifically includes: The biased combination of legal provisions is combined according to the time period corresponding to the time distribution probability of each legal provision, and the target path of the biased combination of legal provisions is set; Fitting the target path of each legal provision in the legal provision bias combination to obtain a fitted target path, and setting the probability value of the fitted target path in each time period as the combined occurrence probability of the legal provision bias combination; The probability of occurrence of the combination of law-biased combinations is compared with the citation of cases in the legal partition, the difference values ​​that appear are marked, and the cases in the legal partition are classified according to the difference values ​​that appear, thereby completing the update of the cases in the legal partition.

9. The legal consulting service information management system based on big data according to claim 1 is characterized in that: The implementation of the consultation management module is as follows: According to the updated mapping relationship between the consultation partition and the legal partition, the consultation targets in the consultation information are extracted, and the consultation targets are sorted according to the occurrence probability of the consultation targets to obtain the consultation order in the consultation information; The consulting objectives and consulting sequences are combined in a structured form to obtain a consulting management library.

10. A method for managing legal consulting service information based on big data, characterized in that: include: S1. Obtain consultation information submitted by users, classify the consultation information using the intent classification model, and identify the intent category; Analyze synonyms, polysemous words and related words under the intent category to form consultation partitions; S2. Call the laws and cases related to the consultation information, generate unlabeled law recognition results, filter the law recognition results, and obtain the target law recognition results as the legal partition; According to the information representation in the consultation partition and the description information and category information of the legal partition, a mapping relationship between the consultation partition and the legal partition is constructed; S3. Perform cluster analysis on the consulting and legal partitions to determine the key partitions; Calculate the cosine similarity between keywords in the key partition, extract legal provisions, and set the legal provision bias combination; S4. Extract the time distribution probability according to the bias combination of legal provisions, set the target path, and fit the combination occurrence probability; compare the combination occurrence probability with the citation of the case in the legal partition, identify and update the case, and update the mapping relationship between the consultation partition and the legal partition; S5. Extract the consultation targets according to the updated mapping relationship between the consultation partitions and the legal partitions, and obtain the consultation order by sorting them according to the probability of occurrence; Combine consultation objectives and consultation sequence to generate a consultation management library.

Images