Legal consultation report generation system and method based on legal knowledge graph

Abstract

The invention relates to the technical field of legal consultation, and discloses a legal consultation report generation system based on a legal knowledge graph, and the system comprises a data collection module which is used for collecting data from a legal database, a user behavior record and an interdisciplinary data source; the data cleaning and preprocessing module is used for carrying out standardization processing and abnormal value detection on the collected data; the invention also discloses a legal consultation report generation method based on the legal knowledge graph. The method comprises the following steps: collecting legal data, user behavior data and interdisciplinary data from a plurality of data sources; performing cleaning and standardization processing on the collected data, wherein the cleaning and standardization processing comprises text standardization and abnormal value detection. The user satisfaction is improved by analyzing user feedback, providing personalized consultation and adopting a dynamic adjustment mechanism to respond to requirements in real time, and meanwhile, the system integrates interdisciplinary data and combines psychological and sociological results, has continuous optimization and self-learning capabilities and realizes intelligent updating of the knowledge graph.

Description

Technical Field

[0001] The present invention relates to the field of legal consulting technology, and specifically to a legal consulting report generation system and method based on a legal knowledge graph. Background Art

[0002] With the rapid development of information technology, the legal service field is gradually transforming towards intelligence and automation. Traditional legal consulting services often rely on the experience and subjective judgment of lawyers, and cannot make full use of a large amount of legal data and user feedback information, resulting in low personalization and accuracy of consulting results. In addition, with the continuous updating of laws and regulations, how to obtain and apply the latest legal information in a timely manner has become an important challenge faced in legal consulting.

[0003] At present, most legal consulting systems still use static models and cannot be flexibly adjusted according to users' real-time needs. This traditional approach not only limits the system's ability to respond to users' personalized needs, but also reduces user experience satisfaction. At the same time, the lack of cross-disciplinary knowledge integration means that legal consulting often cannot provide comprehensive solutions when dealing with complex problems.

[0004] In this context, a legal consulting report generation system based on knowledge graphs came into being. By structuring legal clauses, cases and related information, knowledge graphs provide a more intuitive and systematic way to manage legal knowledge. However, existing knowledge graph applications still have some limitations, especially in terms of the use and dynamic adjustment of user feedback.

[0005] Therefore, there is an urgent need for a legal consulting system that can deeply analyze user feedback, dynamically adjust consulting content, support interdisciplinary knowledge integration, and have self-learning capabilities to meet the growing demand for personalized legal services. To this end, the present invention proposes a legal consulting report generation system and method based on a legal knowledge graph. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a legal consulting report generation system and method based on a legal knowledge graph, which solves the problems of the traditional legal consulting system in terms of personalized services, dynamic response to user needs and interdisciplinary knowledge integration.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: A legal consulting report generation system based on legal knowledge graph, comprising:

[0008] Data collection module, which is used to collect data from legal databases, user behavior records, and interdisciplinary data sources;

[0009] Data cleaning and preprocessing module, used to standardize the collected data and detect outliers;

[0010] The knowledge graph construction module is used to construct a graph-structured knowledge graph based on the extracted legal terms, cases, and user information;

[0011] The knowledge graph update module is used to update the nodes and edges in the knowledge graph regularly and in real time;

[0012] User interaction and feedback collection module, used to collect user input and feedback data;

[0013] Dynamic feedback optimization module, which adjusts edge weights and node features in the knowledge graph based on user feedback;

[0014] Legal consultation generation module, used to comprehensively analyze user input and generate legal consultation reports;

[0015] Report output module, used to output legal consulting reports in multiple formats and collect user feedback.

[0016] Preferably, the data collection module comprises:

[0017] Legal data collection unit, used to capture the latest legal clauses and cases from the legal database;

[0018] User behavior record collection unit, used to monitor and record user consultation behavior and interaction data in real time;

[0019] Interdisciplinary data collection unit for extracting relevant research results from the fields of psychology and sociology.

[0020] Preferably, the knowledge graph construction module includes:

[0021] A node extraction unit, used to extract nodes from legal clauses, cases and user information;

[0022] The edge construction unit is used to construct edges based on the reference relationship between legal clauses and user behaviors.

[0023] Preferably, the knowledge graph updating module includes:

[0024] The regular update unit is used to set the periodic fetching of the latest information from the database;

[0025] A real-time update unit is used to dynamically adjust nodes and edges in the knowledge graph based on user feedback.

[0026] Preferably, the dynamic feedback optimization module includes:

[0027] A feedback analysis unit, used to analyze user feedback data and identify user preferences;

[0028] The edge weight adjustment unit is used to dynamically adjust the edge weights and node features in the knowledge graph based on feedback information.

[0029] Preferably, the dynamic feedback optimization module adjusts the edge weights based on the following formula:

[0030]

[0031] Among them, E ij is the edge weight, R j Rating of legal terms by users.

[0032] Preferably, the report output module includes:

[0033] Formatted output unit, used to support multiple report output formats;

[0034] Feedback integration unit, used to integrate user feedback mechanism into the report and collect post-use evaluation.

[0035] A method for generating a legal consulting report based on a legal knowledge graph comprises the following steps:

[0036] Collect legal data, user behavior data, and cross-disciplinary data from multiple data sources;

[0037] Clean and standardize the collected data, including text standardization and outlier detection;

[0038] Constructing a knowledge graph, including extracting legal terms, cases, and user information, and establishing a graph structure based on reference relationships and user interaction relationships;

[0039] Update the knowledge graph regularly and in real time to reflect the latest legal information and user feedback;

[0040] Collect user input and feedback, analyze user behavior through dynamic feedback optimization steps, and adjust edge weights and node features;

[0041] Generate legal consulting reports, conduct comprehensive analysis based on user input and information in the knowledge graph, and output personalized consulting results;

[0042] Output legal consulting reports in multiple formats and collect follow-up feedback from users.

[0043] Preferably, the construction of the knowledge graph is based on the following formula:

[0044] E={T i ,C j |T i Citation C j}∪{U k ,T i |U kInteractive i}

[0045] Among them, T i For legal terms, C j For example, U k For users.

[0046] Preferably, the dynamic feedback optimization adjusts the edge weight based on the rating of user feedback, and the specific formula is:

[0047] E ij ′=E ij ·1+α·ΔR j

[0048] Among them, α is the learning rate, ΔR j For rating changes.

[0049] The present invention provides a legal consulting report generation system and method based on a legal knowledge graph.

[0050] It has the following beneficial effects:

[0051] 1. The legal consulting report generation system based on the legal knowledge graph of the present invention can deeply analyze user feedback data and identify user preferences, thereby generating more personalized legal consulting reports. By dynamically adjusting the nodes and edges in the knowledge graph, the system can respond to user needs in real time and improve the accuracy and relevance of legal consultation.

[0052] 2. The present invention introduces a dynamic adjustment mechanism based on user feedback into the legal consultation system. This innovation can reflect user preferences in real time and adjust the output of legal consultation. This mechanism is different from the traditional static model and has obvious adaptability and flexibility, which can effectively improve user satisfaction.

[0053] 3. The dynamic feedback optimization module of the present invention supports the integration of interdisciplinary data, so that legal consultation can combine the research results in the fields of psychology, sociology, etc. to provide users with more comprehensive legal solutions. This interdisciplinary integration can enhance the depth and breadth of legal consultation and meet the needs of solving complex legal problems.

[0054] 4. The system of the present invention has the ability of continuous optimization and self-learning. By continuously collecting and analyzing user feedback, it can realize the intelligent update of the knowledge graph. Compared with the previous fixed update method, this adaptive mechanism not only improves the intelligence level of the system, but also provides users with more targeted legal consulting services. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A perspective view of the present invention;

[0056] Figure 2It is a schematic diagram of the present invention;

[0057] Figure 3 It is a schematic diagram of the present invention;

[0058] Figure 4 It is a schematic diagram of the present invention;

[0059] Figure 5 It is a schematic diagram of the present invention;

[0060] Figure 6 It is a schematic diagram of the present invention;

[0061] Figure 7 It is a schematic diagram of the present invention;

[0062] Figure 8 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0063] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] Please see attached Figure 1 -Attached Figure 2 , an embodiment of the present invention provides a legal consulting report generation system based on a legal knowledge graph, comprising:

[0065] Data collection module, which is used to collect data from legal databases, user behavior records, and interdisciplinary data sources;

[0066] Data cleaning and preprocessing module, used to standardize the collected data and detect outliers;

[0067] The knowledge graph construction module is used to construct a graph-structured knowledge graph based on the extracted legal terms, cases, and user information;

[0068] The knowledge graph update module is used to update the nodes and edges in the knowledge graph regularly and in real time;

[0069] User interaction and feedback collection module, used to collect user input and feedback data;

[0070] Dynamic feedback optimization module, which adjusts edge weights and node features in the knowledge graph based on user feedback;

[0071] Legal consultation generation module, used to comprehensively analyze user input and generate legal consultation reports;

[0072] Report output module, used to output legal consulting reports in multiple formats and collect user feedback.

[0073] Specifically, in this embodiment, the data collection module is responsible for collecting necessary information from multiple data sources. Specifically, the module includes a legal data collection unit, which is used to capture the latest legal terms and cases from the legal database; a user behavior record collection unit, which monitors the user's consulting behavior and interaction data in real time to generate a user portrait; and an interdisciplinary data collection unit, which extracts relevant research results in the fields of psychology, sociology, etc. to support multi-dimensional analysis of legal consultation.

[0074] Next, the data cleaning and preprocessing module performs standardization and outlier detection on the collected data. In this embodiment, the text standardization unit of this module is responsible for formatting and deduplication of legal clauses and cases, while the outlier detection unit identifies and removes illogical user behavior data to ensure the accuracy of subsequent analysis.

[0075] On this basis, the knowledge graph construction module is responsible for structuring the collected legal information and user data. In this embodiment, the node extraction unit extracts important nodes from legal clauses, cases and user information, and the edge construction unit constructs edges based on the reference relationship between legal clauses and user behavior to form a complex knowledge network.

[0076] In order to maintain the timeliness and accuracy of the knowledge graph, the knowledge graph update module regularly and in real time updates the nodes and edges in the knowledge graph. In this embodiment, the regular update unit is set to regularly fetch the latest information from the database, while the real-time update unit dynamically adjusts the knowledge graph according to user feedback to ensure that the information obtained when the user queries is always the latest.

[0077] The user interaction and feedback collection module provides an input interface for users and collects user feedback data. In this embodiment, the module allows users to make consultation requests in natural language by designing a friendly natural language input box. At the same time, the feedback collection unit collects users' ratings and comments on the consultation results to form data that can be used for subsequent optimization.

[0078] Based on user feedback, the dynamic feedback optimization module analyzes user behavior and dynamically optimizes the knowledge graph. In this embodiment, the feedback analysis unit identifies user preferences, and the edge weight adjustment unit dynamically adjusts the edge weights in the knowledge graph according to the following formula:

[0079]

[0080] Among them, E ij is the edge weight, R j The user's rating of the legal terms. This formula ensures that the effectiveness of the feedback is reflected in the knowledge graph.

[0081] Subsequently, the legal consultation generation module comprehensively analyzes the user input and generates a legal consultation report. In this embodiment, the information analysis unit uses natural language processing technology to analyze the user input and extract key information, and the report generation unit summarizes relevant legal terms and cases to generate a personalized consultation report.

[0082] Finally, the report output module supports the output of legal consulting reports in multiple formats (such as PDF, HTML) and integrates a user feedback mechanism. In this embodiment, the formatted output unit ensures the diversity of report output, while the feedback integration unit integrates user feedback in the report and collects evaluations after use to provide a basis for further optimization.

[0083] Through the collaborative work of the above modules, the legal consulting report generation system of the present invention not only improves the efficiency of legal services, but also realizes the intelligence of the system through a dynamic feedback mechanism, so that legal consulting can be closer to user needs.

[0084] Please see attached Figure 3 , the data collection modules include:

[0085] Legal data collection unit, used to capture the latest legal clauses and cases from the legal database;

[0086] User behavior record collection unit, used to monitor and record user consultation behavior and interaction data in real time;

[0087] Interdisciplinary data collection unit for extracting relevant research results from the fields of psychology and sociology.

[0088] Specifically, in the legal data collection unit, first confirm the legal database that needs to be crawled and obtain the corresponding API access rights. Then, the system configures the data interface according to the API documentation of the legal database and sets the necessary request parameters to ensure that the latest legal information can be obtained. Periodic tasks will automatically trigger data crawling and send requests to the legal database at a predetermined frequency (such as daily or weekly) to extract the latest legal terms and cases.

[0089] The captured data will be cleaned and standardized to ensure the integrity and consistency of the information. This process includes format checking and unification, so that legal clauses and cases have a unified format in terms of numbering, title and content. Finally, the cleaned data will be stored in the system database for subsequent access and query.

[0090] The work of the user behavior record collection unit is mainly centered around monitoring user interactions. The system embeds monitoring functions in the user interface to record user input, clicks, and submission behaviors in real time. These behavior data are captured through front-end log collection tools and quickly stored in the database to ensure that the impact on user experience is minimized.

[0091] After the user behavior data is stored, the system will regularly analyze the data, extract the user's usage patterns and preferences, and generate a user profile. This analysis result will be used to adjust the system's consulting recommendations and provide more personalized services.

[0092] In the interdisciplinary data collection unit, research databases related to legal consultation, such as literature resources in psychology and sociology, are first selected and evaluated. By identifying appropriate data sources, the system can obtain interdisciplinary research results to enhance the depth and breadth of legal consultation.

[0093] Then, using the literature search strategy, the system crawls relevant research results from the selected platform, focusing on its keywords, themes and abstracts. After crawling, the system will clean and standardize the data to ensure the integrity and consistency of the information so that it can be smoothly integrated with legal data. Finally, these interdisciplinary data will be stored in the database and set up a regular update mechanism to keep it up to date.

[0094] Please see attached Figure 4 , the knowledge graph building modules include:

[0095] A node extraction unit, used to extract nodes from legal clauses, cases and user information;

[0096] The edge construction unit is used to construct edges based on the reference relationship between legal clauses and user behaviors.

[0097] Specifically, the main task of the node extraction unit is to identify and extract key nodes from legal clauses, cases and user information. These nodes can be legal clauses, case numbers, related legal topics, and user consulting needs.

[0098] Specific implementation steps:

[0099] Data preprocessing: Before node extraction, the input data is preprocessed, including text cleaning, word segmentation, and removal of stop words, etc. This can improve the accuracy of subsequent extraction.

[0100] Information extraction technology: Use natural language processing (NLP) technology, such as named entity recognition (NER), to identify legal terms and cases in text. For example, by training the model to identify legal terms such as "contract law" and "tort liability", we can ensure accurate extraction.

[0101] User information integration: Based on the user's consultation history and behavior data, extract the user's specific needs and interests, and this information will become nodes in the knowledge graph.

[0102] Node storage: The extracted node information is stored in a unified format in the database to provide support for subsequent edge construction.

[0103] The main function of the edge construction unit is to construct edges based on the reference relationship between legal clauses and user behavior to form a relationship network in the knowledge graph.

[0104] Specific implementation steps:

[0105] Citation relationship analysis: First, analyze the citation relationship between legal clauses and establish connections between clauses by parsing the citation tags in the legal text. For example, if “Clause A cites Clause B”, an edge from node A to node B is formed in the knowledge graph.

[0106] User behavior association: Based on the user's behavior data, identify the user's interactive relationship with legal clauses and cases. This can be achieved by analyzing the keywords of the user's query and the cases visited. For example, if a user frequently queries a specific legal clause, an edge related to the user's behavior can be added to the knowledge graph for that clause.

[0107] Edge weight setting: Set weights for edges based on citation frequency and user interaction frequency to reflect the relative importance of various legal clauses and cases. The weight setting can be achieved through the following formula:

[0108] W ij =α·C ij +β·U ij

[0109] Among them, W ij is the edge weight, C ij is the number of citations between clauses, U ij is the number of user interactions on a term, and α and β are adjustment parameters.

[0110] Knowledge graph construction: The combination of nodes and edges forms a knowledge graph and stores it in a graph database, such as Neo4j, for subsequent query and analysis.

[0111] The knowledge graph construction module integrates legal information and user behavior into a structured knowledge graph through the synergy of node extraction units and edge construction units. The node extraction unit ensures the accurate identification of key entities, while the edge construction unit builds a dynamic relationship network through reference relationships and user behaviors. This knowledge graph provides strong data support for the generation of legal consulting reports and personalized services.

[0112] Please see attached Figure 5 , the knowledge graph update module includes:

[0113] The regular update unit is used to set the periodic fetching of the latest information from the database;

[0114] A real-time update unit is used to dynamically adjust nodes and edges in the knowledge graph based on user feedback.

[0115] Specifically, the main function of the regular update unit is to capture the latest legal terms, cases and other relevant information from the legal database to keep the knowledge graph up to date.

[0116] Specific implementation steps:

[0117] Update frequency setting: According to the update frequency of legal information, set a reasonable update cycle (such as daily, weekly or monthly) to ensure that the captured legal information remains up-to-date.

[0118] Data capture mechanism: Utilize the preset API interface to automatically initiate a request to the legal database to obtain the latest legal terms and case information. The request can include specific parameters, such as the update time range, to accurately obtain the required information.

[0119] Data integration and update:

[0120] Compare the captured new information with the existing knowledge graph to identify new, modified or deleted terms and cases.

[0121] For newly added information, key nodes are extracted and edges are established to dynamically expand the knowledge graph.

[0122] For existing clauses, check the changes in their content and update the node information if necessary.

[0123] Periodic storage: Store the updated knowledge graph back into the graph database to ensure that the latest legal information is stored in the system.

[0124] The function of the real-time update unit is to dynamically adjust the knowledge graph based on user feedback to improve the system's responsiveness and personalized service level.

[0125] Specific implementation steps:

[0126] User feedback collection: Collect user feedback on legal consultation during the user's use of the system, including ratings, suggestions and common consultation topics for generated reports. This can be achieved through the user interaction and feedback collection module.

[0127] Feedback analysis:

[0128] Analyze user feedback data to identify user preferences and needs for specific legal clauses or cases. This can be achieved through cluster analysis or sentiment analysis techniques to gain insight into users’ real needs.

[0129] Dynamic Adjustment:

[0130] Based on the results of feedback analysis, nodes and edges in the knowledge graph are adjusted in real time. For example, if users frequently report that a legal clause does not conform to the actual situation, the node can be marked as "needs to be reviewed" or its weight in the recommendation can be reduced.

[0131] The following formula is used to dynamically adjust the edge weight:

[0132] W ij ′=W ij +γ·ΔU ij

[0133] Among them, W′ ij is the updated edge weight, W ij is the current weight, ΔU ij is the amount of change based on user feedback, and γ is the adjustment coefficient.

[0134] Real-time storage and feedback: The dynamically adjusted knowledge graph is updated and stored in the database in a timely manner to ensure that the system can quickly respond to the changing needs of users.

[0135] The knowledge graph update module realizes dynamic maintenance and adjustment of the knowledge graph through the cooperation of the regular update unit and the real-time update unit. The regular update unit ensures the timeliness of legal information, while the real-time update unit continuously optimizes the accuracy and relevance of the graph through user feedback. This mechanism not only enhances the intelligence of the system, but also provides users with more personalized legal consulting services.

[0136] Please see attached Figure 6 , the dynamic feedback optimization module includes:

[0137] A feedback analysis unit, used to analyze user feedback data and identify user preferences;

[0138] The edge weight adjustment unit is used to dynamically adjust the edge weights and node features in the knowledge graph based on feedback information.

[0139] Specifically, the core task of the feedback analysis unit is to analyze user feedback data and extract user preferences and needs to guide the optimization of the knowledge graph.

[0140] Specific implementation steps:

[0141] Data collection: Obtain user ratings, comments, usage logs and other data from the user interaction and feedback collection module. These feedbacks can be structured (such as ratings) or unstructured (such as text comments).

[0142] Data preprocessing:

[0143] Clean and standardize the collected feedback data to remove noise and invalid information.

[0144] Perform word segmentation, stop word removal, and sentiment analysis on text comments to identify users' emotional inclinations towards specific legal clauses or consulting content.

[0145] Preference identification:

[0146] Use machine learning algorithms (such as cluster analysis, decision trees, or deep learning models) to analyze feedback data and identify users’ common preferences and individual needs.

[0147] User preferences are associated with nodes and edges in the knowledge graph to determine which terms or cases are favored by more users.

[0148] Result storage: The analysis results are stored in the form of user portraits or preference models to facilitate subsequent edge weight adjustment and personalized recommendations.

[0149] The main function of the edge weight adjustment unit is to dynamically adjust the edge weights and node features between nodes in the knowledge graph based on user feedback information to optimize the user experience.

[0150] Specific implementation steps:

[0151] Weight adjustment basis:

[0152] Based on the output of the feedback analysis unit, the edge weights that need to be adjusted are determined. For example, a certain legal clause receives high attention from users, while another is marked with a low score.

[0153] Edge weight calculation:

[0154] The edge weights are dynamically adjusted using the following formula:

[0155]

[0156] Among them, W′ ij is the updated edge weight, W ij is the weight of the current edge, R ij is the user's rating of the edge-related nodes, is the average score of the item, and α is the adjustment factor.

[0157] Node feature adjustment:

[0158] In addition to edge weights, node features can also be updated based on user feedback. For example, if a node (legal clause) receives poor feedback, the node's status can be updated to "needs review" and the reason can be marked for subsequent manual review or correction.

[0159] Update storage: The adjusted weights and node features are updated and stored in the knowledge graph database in a timely manner to ensure that users obtain optimized data every time they visit.

[0160] The dynamic feedback optimization module realizes the self-optimization and dynamic adjustment of the knowledge graph through the synergy of the feedback analysis unit and the edge weight adjustment unit. The feedback analysis unit helps the system understand user needs, while the edge weight adjustment unit optimizes the structure and weight of the graph according to these needs. This mechanism not only improves the intelligence level of the system, but also provides users with more accurate and personalized legal consulting services.

[0161] The dynamic feedback optimization module adjusts the edge weights based on the following formula:

[0162]

[0163] Among them, E ij is the edge weight, R j Rating of legal terms by users.

[0164] Please see attached Figure 7 , the report output modules include:

[0165] Formatted output unit, used to support multiple report output formats;

[0166] Feedback integration unit, used to integrate user feedback mechanism into the report and collect post-use evaluation.

[0167] Please see attached Figure 8 , a method for generating a legal consulting report based on a legal knowledge graph, comprising the following steps:

[0168] Collect legal data, user behavior data, and cross-disciplinary data from multiple data sources;

[0169] Clean and standardize the collected data, including text standardization and outlier detection;

[0170] Constructing a knowledge graph, including extracting legal terms, cases, and user information, and establishing a graph structure based on reference relationships and user interaction relationships;

[0171] Update the knowledge graph regularly and in real time to reflect the latest legal information and user feedback;

[0172] Collect user input and feedback, analyze user behavior through dynamic feedback optimization steps, and adjust edge weights and node features;

[0173] Generate legal consulting reports, conduct comprehensive analysis based on user input and information in the knowledge graph, and output personalized consulting results;

[0174] Output legal consulting reports in multiple formats and collect follow-up feedback from users.

[0175] The construction of the knowledge graph is based on the following formula:

[0176] E={T i ,C j |T i Citation C j}∪{U k ,T i |U k Interactive i}

[0177] Among them, T i For legal terms, C j For example, U k For users.

[0178] Dynamic feedback optimization adjusts edge weights based on user feedback scores. The specific formula is:

[0179] E ij ′=E ij ·(1+α·ΔR j )

[0180] Among them, α is the learning rate, ΔR j For rating changes.

[0181] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A legal consulting report generation system based on legal knowledge graph, characterized in that: include: Data collection module, which is used to collect data from legal databases, user behavior records, and interdisciplinary data sources; Data cleaning and preprocessing module, used to standardize the collected data and detect outliers; The knowledge graph construction module is used to construct a graph-structured knowledge graph based on the extracted legal terms, cases, and user information; The knowledge graph update module is used to update the nodes and edges in the knowledge graph regularly and in real time; User interaction and feedback collection module, used to collect user input and feedback data; Dynamic feedback optimization module, which adjusts edge weights and node features in the knowledge graph based on user feedback; Legal consultation generation module, used to comprehensively analyze user input and generate legal consultation reports; Report output module, used to output legal consulting reports in multiple formats and collect user feedback.

2. According to claim 1, a legal consulting report generation system based on legal knowledge graph is characterized in that: The data collection module comprises: Legal data collection unit, used to capture the latest legal clauses and cases from the legal database; User behavior record collection unit, used to monitor and record user consultation behavior and interaction data in real time; Interdisciplinary data collection unit for extracting relevant research results from the fields of psychology and sociology.

3. According to claim 1, a legal consulting report generation system based on legal knowledge graph is characterized in that: The knowledge graph construction module includes: A node extraction unit, used to extract nodes from legal clauses, cases and user information; The edge construction unit is used to construct edges based on the reference relationship between legal clauses and user behaviors.

4. According to claim 1, a legal consulting report generation system based on legal knowledge graph is characterized in that: The knowledge graph updating module includes: The regular update unit is used to set the periodic fetching of the latest information from the database; A real-time update unit is used to dynamically adjust nodes and edges in the knowledge graph based on user feedback.

5. According to claim 1, a legal consulting report generation system based on legal knowledge graph is characterized in that: The dynamic feedback optimization module comprises: A feedback analysis unit, used to analyze user feedback data and identify user preferences; The edge weight adjustment unit is used to dynamically adjust the edge weights and node features in the knowledge graph based on feedback information.

6. A legal consulting report generation system based on legal knowledge graph according to claim 5, characterized in that: The dynamic feedback optimization module adjusts the edge weights based on the following formula: Among them, E ij is the edge weight, R j Rating of legal terms by users.

7. According to claim 1, a legal consulting report generation system based on legal knowledge graph is characterized in that: The report output module includes: Formatted output unit, used to support multiple report output formats; Feedback integration unit, used to integrate user feedback mechanism into the report and collect post-use evaluation.

8. A method for generating a legal consulting report based on a legal knowledge graph, characterized in that: The following steps are involved: Collect legal data, user behavior data, and cross-disciplinary data from multiple data sources; Clean and standardize the collected data, including text standardization and outlier detection; Constructing a knowledge graph, including extracting legal terms, cases, and user information, and establishing a graph structure based on reference relationships and user interaction relationships; Update the knowledge graph regularly and in real time to reflect the latest legal information and user feedback; Collect user input and feedback, analyze user behavior through dynamic feedback optimization steps, and adjust edge weights and node features; Generate legal consulting reports, conduct comprehensive analysis based on user input and information in the knowledge graph, and output personalized consulting results; Output legal consulting reports in multiple formats and collect follow-up feedback from users.

9. The method for generating a legal consulting report based on a legal knowledge graph according to claim 8 is characterized in that: The construction of the knowledge graph is based on the following formula: E={9T i ,C j )|T i Citation C j }∪{(U k ,T i )|U k Interactive i } Among them, T i For legal terms, C j For example, U k For users.

10. The method for generating a legal consulting report based on a legal knowledge graph according to claim 8 is characterized in that: The dynamic feedback optimization adjusts the edge weight based on the user feedback score. The specific formula is: IN ij ′=E ij ·(1+α·ΔR j ) Among them, α is the learning rate, ΔR j For rating changes.

Images