Intelligent law and regulation learning method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of law and regulation intelligent learning, and discloses a law and regulation intelligent learning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target state of each preset law and regulation category of a to-be-learned person according to label information, obtaining historical mastering states of each preset law and regulation category of the to-be-learned person at a plurality of time points, the method comprises the steps of obtaining a to-be-learned person, inputting the to-be-learned person into a preset learning time prediction model to obtain a first predicted learning duration of each preset regulation category, setting a historical fingerprint of the to-be-learned person according to the first predicted learning duration so as to set a learning time ratio of each preset regulation category, and making a learning plan of the to-be-learned person according to the learning time ratio. And the to-be-learned person can learn according to the learning plan. The method has the beneficial effects that the learning efficiency of learners is improved, effective support is provided for cultivating high-quality legal talents, and personalized learning planning is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of regulation intelligent learning, and particularly relates to a regulation intelligent learning method and device, electronic equipment and storage medium. BACKGROUND

[0002] Under the background of continuous updating and complication of current laws and regulations, legal learning is particularly important. With the increasing demand for legal professionals in society, how to improve learning efficiency and learning effect has become a problem to be solved. Traditional legal learning methods often rely on fixed teaching materials and teaching plans, and it is difficult to make individualized learning plans for individual differences, resulting in low efficiency and poor effect of learners in mastering legal knowledge. SUMMARY

[0003] Therefore, it is necessary to propose a regulation intelligent learning method, device, electronic equipment and storage medium for the existing regulation intelligent learning problem.

[0004] A regulation intelligent learning method, the method comprising:

[0005] obtaining label information of a to-be-learned person, and obtaining a target state of each preset regulation category of the to-be-learned person according to the label information;

[0006] obtaining a historical mastering state of each preset regulation category of the to-be-learned person at a plurality of time points in a learning process of the to-be-learned person;

[0007] inputting the target state of each preset regulation category and a plurality of historical mastering states into a preset learning time estimation model to obtain a first predicted learning time length of each preset regulation category;

[0008] setting a historical fingerprint map of the to-be-learned person according to the first predicted learning time length;

[0009] setting a learning time proportion of each preset regulation category according to the historical fingerprint map;

[0010] formulating a learning plan of the to-be-learned person according to the learning time proportion, so that the to-be-learned person learns according to the learning plan.

[0011] Further, after the step of formulating a learning plan of the to-be-learned person according to the learning time proportion, so that the to-be-learned person learns according to the learning plan, the method further comprises:

[0012] obtaining a current mastering state of each preset regulation category of the to-be-learned person after the to-be-learned person learns for a preset time length;

[0013] inputting the target state, the current mastering state and the plurality of historical mastering states of each preset regulation category into the preset learning time estimation model to obtain a second predicted learning time length of each preset regulation category;

[0014] updating the historical fingerprint atlas according to the second predicted learning time length to obtain a current fingerprint atlas;

[0015] setting a real-time learning time proportion of each preset regulation category according to the current fingerprint atlas;

[0016] formulating a current learning plan of the to-be-learned person according to the real-time learning time proportion, so that the to-be-learned person learns according to the current learning plan.

[0017] Further, before the step of obtaining the historical mastering state of each preset regulation category of the to-be-learned person at a plurality of time points during the learning process, the method further comprises:

[0018] obtaining a regulation database to be learned;

[0019] dissolving the regulation database according to a preset dissolution manner to obtain a plurality of pieces of target regulation data after dissolution;

[0020] classifying each target regulation data according to a preset classification rule to obtain a category sub-database corresponding to each preset regulation category; the category sub-database is used to detect the mastering state of the to-be-learned person and provide learning materials for the to-be-learned person.

[0021] Further, after the step of classifying each target regulation data according to a preset classification rule to obtain a category sub-database corresponding to each preset regulation category, the method further comprises

[0022] determining whether there is a new regulation;

[0023] if there is a new regulation, dissolving the new regulation according to a preset dissolution manner to obtain a plurality of pieces of target new regulation data after dissolution;

[0024] classifying each piece of target new regulation data according to a preset classification rule to update the corresponding category sub-database.

[0025] Further, the step of obtaining the label information of the to-be-learned person comprises:

[0026] obtaining the identity information, the holding information and the job information of the to-be-learned person;

[0027] generating an information vector of the to-be-learned person according to the identity information, the holding information and the job information;

[0028] mapping the information vector to obtain mapped label information.

[0029] Further, after the step of obtaining the label information of the to-be-learned personnel and obtaining the target state of each preset regulation category of the to-be-learned personnel according to the label information, the method further comprises:

[0030] monitoring whether the label information of the to-be-learned personnel is updated;

[0031] if the label information of the to-be-learned personnel is updated, obtaining the updated label information;

[0032] updating the target state of each preset regulation category of the to-be-learned personnel according to the updated label information.

[0033] Further, before the step of inputting the target state of each preset regulation category and a plurality of historical mastering states into a preset learning time estimation model to obtain a first predicted learning time length of each preset regulation category, the method further comprises:

[0034] obtaining a preset number of sample data from a preset sample database, and dividing the sample data into training data and verification data according to a preset proportion; wherein one set of sample data is composed of a plurality of training historical mastering states, a training target state and a corresponding comprehensive label; the comprehensive label comprises a time length label and a regulation category label;

[0035] inputting the training data into a preset support vector machine model for training, thereby obtaining a temporary support vector machine model;

[0036] verifying the temporary support vector machine model by using the verification data to obtain a verification result, and determining whether the verification result is verified to be passed;

[0037] if the verification result is verified to be passed, marking the temporary support vector machine model as a preset learning time estimation model.

[0038] A regulation intelligent learning device, the device comprises:

[0039] a target state obtaining module, configured to obtain label information of to-be-learned personnel, and obtain target states of each preset regulation category of the to-be-learned personnel according to the label information;

[0040] a historical mastering state obtaining module, configured to obtain historical mastering states of each preset regulation category of the to-be-learned personnel at a plurality of time points in a learning process of the to-be-learned personnel;

[0041] a first predicted learning duration acquisition module, configured to input the target state of each preset regulation category and the plurality of historical mastering states into a preset learning time estimation model to obtain a first predicted learning duration of each preset regulation category;

[0042] a historical fingerprint setting module, configured to set a historical fingerprint of the to-be-learned person according to the first predicted learning duration;

[0043] a learning time proportion setting module, configured to set a learning time proportion of each preset regulation category according to the historical fingerprint;

[0044] a learning plan making module, configured to make a learning plan of the to-be-learned person according to the learning time proportion, so that the to-be-learned person learns according to the learning plan.

[0045] An electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the following steps:

[0046] acquiring label information of a to-be-learned person, and acquiring a target state of each preset regulation category of the to-be-learned person according to the label information;

[0047] acquiring historical mastering states of each preset regulation category of the to-be-learned person at a plurality of time points in a learning process of the to-be-learned person;

[0048] inputting the target state of each preset regulation category and the plurality of historical mastering states into a preset learning time estimation model to obtain a first predicted learning duration of each preset regulation category;

[0049] setting a historical fingerprint of the to-be-learned person according to the first predicted learning duration;

[0050] setting a learning time proportion of each preset regulation category according to the historical fingerprint;

[0051] making a learning plan of the to-be-learned person according to the learning time proportion, so that the to-be-learned person learns according to the learning plan.

[0052] A computer readable storage medium, storing a computer program, wherein the computer program is executed by a processor to make the processor execute the following steps:

[0053] acquiring label information of a to-be-learned person, and acquiring a target state of each preset regulation category of the to-be-learned person according to the label information;

[0054] In the learning process of the to-be-learned personnel, a plurality of time points of the historical mastering state of the to-be-learned personnel to each preset regulation category are acquired;

[0055] The target state and the plurality of historical mastering states of each preset regulation category are input into a preset learning time estimation model to obtain a first predicted learning time length of each preset regulation category;

[0056] The historical fingerprint spectrum of the to-be-learned personnel is set according to the first predicted learning time length;

[0057] The learning time proportion of each preset regulation category is set according to the historical fingerprint spectrum;

[0058] The learning plan of the to-be-learned personnel is formulated according to the learning time proportion, so that the to-be-learned personnel learns according to the learning plan.

[0059] The beneficial effects of the present application are: accurately identifying the mastering degree of individuals in different regulation categories, thereby tailoring the learning plan, ensuring that learners concentrate on the most needed improvement field in a short time, improving the pertinence and effectiveness of learning, using the preset learning time estimation model to predict the learning time, which can reasonably allocate learning time, so that learners obtain a reasonable learning proportion in different legal categories, avoid knowledge blind spots caused by improper time allocation, make legal learning more intelligent and personalized, not only improve the learning efficiency of learners, but also provide effective support for cultivating high-quality legal talents, and realize personalized learning planning. BRIEF DESCRIPTION OF DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0061] Among them:

[0062] Figure 1 It is an application environment diagram of the regulation intelligent learning method in one embodiment;

[0063] Figure 2 It is a flowchart of the regulation intelligent learning method in one embodiment;

[0064] Figure 3 It is a structural block diagram of the regulation intelligent learning device in one embodiment;

[0065] Figure 4 It is a structural block diagram of the electronic device in one embodiment. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0067] Figure 1 An application environment diagram of the regulation intelligent learning in an embodiment is shown in FIG. 1. Referring to FIG. 1, the regulation intelligent learning method is applied to a regulation intelligent learning system. The regulation intelligent learning system includes a terminal 110 and a server 120. The terminal 110 and the server 120 are connected through a network. The terminal 110 can be a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, a notebook computer, and the like. The server 120 can be implemented by an independent server or a server cluster composed of multiple servers. The terminal 110 is configured to acquire label information of a to-be-learned person. The server 120 is configured to formulate a learning plan for the to-be-learned person. Figure 1

[0068] As shown in FIG. 2, in an embodiment, a regulation intelligent learning method is provided. The method can be applied to a terminal or a server. In this embodiment, the method applied to a terminal is taken as an example for illustration. The regulation intelligent learning method specifically includes the following steps: Figure 2 S1: acquiring label information of a to-be-learned person, and acquiring a target state of each preset regulation category of the to-be-learned person according to the label information;

[0069] S2: acquiring a historical mastering state of each preset regulation category of the to-be-learned person at multiple time points in a learning process of the to-be-learned person;

[0070] S3: inputting the target state of each preset regulation category and the multiple historical mastering states into a preset learning time estimation model to obtain a first predicted learning time length of each preset regulation category;

[0071] S4: setting a historical fingerprint spectrum of the to-be-learned person according to the first predicted learning time length;

[0072] S5: setting a learning time proportion of each preset regulation category according to the historical fingerprint spectrum;

[0073] S6: formulating a learning plan for the to-be-learned person according to the learning time proportion, so that the to-be-learned person learns according to the learning plan.

[0074] S7: acquiring a learning state of the to-be-learned person at each time point in the learning process of the to-be-learned person, and inputting the learning state into the preset learning time estimation model to obtain a second predicted learning time length of each preset regulation category;S8: updating the historical fingerprint spectrum of the to-be-learned person according to the second predicted learning time length; and S9: updating the learning plan for the to-be-learned person according to the updated historical fingerprint spectrum.

[0075] As described in step S1 above, the tag information of the learners is obtained, and the target status of each learner in each preset legal category is obtained based on the tag information. Obtaining the tag information of the learners means classifying the learners by tags according to their different needs for laws and regulations. Next, based on this tag information, the target status of each learner in each preset legal category is set. The target status usually refers to the learning objectives that the learner needs to achieve in different legal knowledge areas, such as mastering a certain legal clause or understanding the application scenarios of laws and regulations.

[0076] As described in step S2 above, during the learning process, the learner's historical mastery status of each preset legal category is acquired at multiple time points. Throughout the learning process, it is necessary to continuously track and record the learner's mastery status of each preset legal category. This can be achieved through regular testing, assessments, and other forms of feedback collection, acquiring historical mastery status at multiple time points, and evaluating the learner's performance at different learning stages (e.g., at the beginning, middle, and end). This dynamic monitoring method helps educators understand the learner's progress in a timely manner, identify their strengths and weaknesses, and provide a basis for adjusting subsequent learning plans. By collecting this historical data, a comprehensive learner profile can be formed, laying the foundation for subsequent analysis and learning plan development.

[0077] As described in step S3 above, the target state and multiple historical mastery states of each preset regulation category are input into the preset learning time estimation model to obtain the first predicted learning time for each preset regulation category. The target state and historical mastery states of the learner are input into the preset learning time estimation model. This model can be a statistical or machine learning-based algorithm that analyzes data and calculates an estimated learning time for each regulation category. This predicted learning time calculation is based not only on historical data but also on individual differences, thus making the prediction as accurate as possible. The calculated learning time provides an important basis for subsequent learning plan development, helping to rationally allocate learning time and ensure maximum learning efficiency for learners. It should be noted that the preset learning time estimation model can be obtained by training a pre-built initial SVM model based on a preset sample set. Each sample data in the preset sample set includes sample state data (including the target state and multiple historical mastery states) and the predicted learning time corresponding to that sample state data. When training the pre-built initial SVM model, the sample state data in each sample data is used as the input of the initial SVM model, and the predicted learning time corresponding to the sample state data in each sample data is used as the output of the initial SVM model. Through training, the initial SVM model can learn the correspondence between all possible sample state data and predicted learning time. The trained initial SVM model is used as the preset learning time prediction model.

[0078] As described in step S4 above, a historical fingerprint profile of the learner is set based on the first predicted learning duration. Using the obtained first predicted learning duration, a historical fingerprint profile of the learner is set. This fingerprint profile is a personalized representation of learning data, specifically a visualized or structured data map based on the learner's historical learning duration distribution across various regulatory categories. It visualizes the learner's learning situation in each regulatory category, reflecting information such as learning time, learning efficiency, and feedback results at different learning stages. Through this visualization, both learners and educators can more intuitively understand the learner's learning status and adjust learning strategies accordingly. The historical fingerprint profile not only facilitates the review and analysis of past learning behaviors but also provides data support for planning subsequent learning activities, helping learners identify areas that need strengthening and develop improvement measures.

[0079] As described in step S5 above, the learning time allocation for each of the preset regulatory categories is set based on the historical fingerprint map. In this stage, based on the formed historical fingerprint map, learners can set a reasonable learning time allocation for each preset regulatory category. The setting of the learning time allocation should comprehensively consider factors such as the learner's historical learning situation in each regulatory category, their target status, and their personal interests. By reasonably allocating the learning time allocation, learners can ensure that they invest more learning effort in key regulatory areas, thereby achieving better learning outcomes. Furthermore, these time allocations can be continuously adjusted based on learner feedback and learning effectiveness to dynamically optimize the learning plan and improve learning quality.

[0080] As described in step S6 above, a learning plan is formulated for the learners based on the learning time percentage, so that the learners can learn according to the learning plan. A detailed learning plan is formulated based on the previously set learning time percentage, and the learning plan should include specific details such as learning content, learning tasks, learning methods (e.g., self-study, discussion, case analysis, etc.), and learning progress.

[0081] In one embodiment, after step S6, which involves formulating a learning plan for the learner based on the learning time percentage so that the learner can study according to the learning plan, the method further includes:

[0082] S701: After the learner has studied for a preset duration, obtain the current mastery status of each preset legal category of the learner;

[0083] S702: Input the target state, the current mastery state, and multiple historical mastery states of each preset legal category into the preset learning time estimation model to obtain the second predicted learning time for each preset legal category;

[0084] S703: Update the historical fingerprint spectrum according to the second prediction learning duration to obtain the current fingerprint spectrum;

[0085] S704: Set the real-time learning time percentage for each of the preset regulatory categories based on the current fingerprint spectrum;

[0086] S705: Develop a current learning plan for the learner based on the real-time learning time percentage, so that the learner can learn according to the current learning plan.

[0087] As described in step S701 above, after the learner has studied for a preset duration, their current mastery status in each preset legal category is obtained. After completing a period of learning activities (i.e., the preset study duration), it is necessary to evaluate the learner's learning effectiveness in each preset legal category. Collecting and analyzing the learner's current mastery status is mainly achieved through various assessment methods, such as quizzes, questionnaires, and oral Q&A. These methods can assess the learner's understanding of legal knowledge and their practical application ability. When obtaining the current mastery status, efforts should be made to ensure the accuracy and objectivity of the assessment so as to truly reflect the learner's learning outcomes. This information not only helps to assess the learner's progress but also provides an important basis for adjusting subsequent learning plans. It can also provide feedback to the learner, helping them identify areas that need strengthening or improvement during the learning process, thereby more effectively adjusting their learning strategies.

[0088] As described in step S702 above, the target state, current mastery state, and multiple historical mastery states for each preset regulatory category are input into the preset learning time estimation model to obtain the second predicted learning time for each preset regulatory category. The collected current mastery state, target state, and multiple historical mastery states are input into the preset learning time estimation model. This input data provides the model with rich information, enabling it to more accurately assess the learning time required for each regulatory category. The calculation of the second predicted learning time considers not only the learner's current mastery and target state but also learning trends and changes reflected in historical data. Therefore, this model can help identify the learner's learning difficulties and progress in different regulatory categories. This process is crucial for developing subsequent learning plans because it ensures that learners master the necessary knowledge within an appropriate timeframe and provides a more targeted direction for subsequent learning, avoiding unnecessary waste in learning.

[0089] As described in step S703 above, the historical fingerprint spectrum is updated according to the second predicted learning duration to obtain the current fingerprint spectrum. After obtaining the second predicted learning duration, its information needs to be fed back into the historical fingerprint spectrum to update the current learning data. This step integrates the newly calculated learning duration data with the learner's historical data to form a new fingerprint spectrum. The current fingerprint spectrum can more accurately reflect the learner's learning progress and efficiency after adjustments based on new information and feedback. This dynamic fingerprint spectrum is not merely a simple summary of statistical data, but rather captures the learner's learning characteristics and changing needs by analyzing changes in the learning process. This update process provides learners with more timely feedback on their learning status and also provides a scientific basis for adjusting the next step of learning time allocation, enabling learners to more effectively adjust their learning strategies and priorities in their pursuit of knowledge mastery.

[0090] As described in step S704 above, the real-time learning time percentage for each of the preset regulatory categories is set based on the current fingerprint map. Using the currently updated fingerprint map, the real-time learning time percentage needs to be set according to the learner's learning status in different regulatory categories to ensure a better balance in the learner's learning across various regulatory areas, making the allocation of learning time match the learner's actual needs. The required time percentage for each regulatory category should be based on the learning situation reflected in the current fingerprint map. This ensures that learners can invest more time in areas that need strengthening, while also consolidating their existing knowledge. Dynamically adjusting the time percentage not only improves the targeting and effectiveness of learning but also enhances the learner's learning experience, making them feel that their learning is progressing, thereby strengthening their learning motivation.

[0091] As described in step S705 above, a current learning plan is formulated for the learner based on the real-time learning time percentage, so that the learner can study according to the current learning plan. The learning plan, tailored to the current learning state, should specify learning content, objectives, learning methods, and assessment methods. This plan should help learners focus on improving their mastery of the target legal category while also ensuring continuous review of knowledge in other areas. This learning plan should be flexible, allowing learners to fine-tune it according to their actual progress to suit their real-time learning needs. Furthermore, it is recommended that the plan include a feedback mechanism to allow learners to periodically self-check during the learning process and adjust their learning strategies. Through this method, learners can maintain efficiency and motivation throughout the learning process, thereby improving overall learning effectiveness.

[0092] In one embodiment, before step S2, which involves acquiring the learner's historical mastery status of each preset regulatory category at multiple time points during the learning process, the method further includes:

[0093] S101: Obtain the database of regulations to be studied;

[0094] S102: The regulatory database is disassembled according to a preset disassembly method to obtain multiple disassembled target regulatory data;

[0095] S103: Classify each of the target regulations data according to preset classification rules to obtain category sub-databases corresponding to each preset regulation category; the category sub-databases are used to detect the mastery status of the learners and to provide learning materials for the learners.

[0096] As described in step S101 above, the first step is to obtain the database of laws and regulations to be studied. This database forms the foundation of all learning resources, containing a wealth of legal texts, clauses, cases, and related regulations. This information may originate from legal documents, government-issued regulations, industry standards, or academic research. Obtaining this database means ensuring its completeness and authority to guarantee the accuracy and reliability of the information learners receive. When constructing this database, regulations from different fields, such as civil law, criminal law, administrative law, and commercial law, are typically considered. This step not only lays the foundation for subsequent learning but also helps learners gain a comprehensive perspective when mastering legal knowledge, enabling them to better understand the interrelationships and application scenarios of legal knowledge. By integrating information from multiple sources, the database ensures comprehensive coverage, providing learners with rich learning content. Natural language processing technology is used to learn the logic and categorize and label legal provisions. Due to the relatively standardized nature of legal texts, machine decomposition is quite effective. Common keywords at the beginning include: "first item," "item 1," "chapter 1," "I," "1," etc., and they end with markers such as carriage return, line break, and period. After a large amount of manual labeling, the machine's learning effect in automatically decomposing data will be greatly improved, eventually resulting in very good automatic decomposition capabilities.

[0097] As described in step S102 above, the regulatory database is decomposed according to a preset decomposition method to obtain multiple decomposed target regulatory data. After obtaining the regulatory database, the second step is to decompose it. This decomposition method usually involves logically breaking down legal clauses, regulations, and related content according to preset standards. This process may include breaking down regulations into specific clauses, chapters, or topics, thereby extracting more detailed and specific learning objectives. The decomposed target regulatory data not only includes the basic content of the original regulations but may also contain applicable case analyses, legal interpretations, and legal liabilities. Through this decomposition, learners can more clearly identify and understand the components of each regulation, thus laying a foundation for subsequent learning and mastery. This detailed approach allows learners to enhance learning efficiency and improve the relevance of their learning when mastering complex regulations through gradual understanding.

[0098] As described in step S103 above, the target regulatory data is classified according to preset classification rules to obtain category sub-databases corresponding to each preset regulatory category. After the target regulatory data is decomposed, classification is required. This process is mainly based on preset classification rules and aims to provide learners with efficient learning paths and resources. Classification rules can be set according to the nature of the regulations, application areas, or specific legal provisions, such as classifying regulations into civil regulations, criminal regulations, administrative regulations, etc. Each category sub-database will correspond to different regulatory category data. These databases will not only store relevant legal texts but also include learning resources, cases, and reference materials suitable for that category.

[0099] In one embodiment, after step S103, which involves classifying each target regulation data according to a preset classification rule to obtain a category sub-database corresponding to each preset regulation category, the method further includes:

[0100] S1031: Determine whether there are new regulations;

[0101] S1032: If there are new regulations, the new regulations are disassembled according to a preset disassembly method to obtain multiple disassembled target new regulations data;

[0102] S1033: Classify the target new regulations data according to the preset classification rules to update the corresponding category sub-database.

[0103] As described in step S1031 above, it is necessary to determine whether new regulations exist. After completing the initial classification of the regulations database and generating category sub-databases, it is necessary to periodically determine whether new regulations have been issued. This determination step is a crucial step in maintaining the continuous updating of the regulations database. The emergence of new regulations may affect the construction and application of the existing legal system; therefore, timely identification and acquisition of these new regulations are essential to ensuring the timeliness and effectiveness of learning materials. Determining whether new regulations exist can be achieved in various ways, such as regularly scanning official legal websites, utilizing the notification functions of legal information service platforms, or subscribing to relevant legal information. Through these channels, one can obtain timely access to government-issued legal documents, new draft laws, and their passage progress.

[0104] As described in step S1032 above, if new regulations exist, they are disassembled according to a preset disassembly method to obtain multiple disassembled target new regulations. If new regulations are identified, the next step is to disassemble them. The disassembly process must follow the same preset disassembly method as the original regulations database to ensure that the clauses of the new regulations are consistent with the existing regulations in terms of structure and content. This disassembly should not only cover the legal clauses themselves but also consider applicable cases, interpretations, and examples related to the new regulations. The disassembled target new regulations should be systematically organized according to the logic and structure of the content to facilitate subsequent classification and learning. The reason for disassembly is that it helps learners understand the various components of the new regulations in a more nuanced way and clearly understand each clause and its application scenarios. At the same time, such structured information also provides basic data for the design of subsequent learning paths, ensuring the coherence and logic of the learning content and strengthening learning outcomes.

[0105] As described in step S1033 above, the target new regulations data are classified according to preset classification rules to update the corresponding category sub-database. After the new regulations are decomposed, this new regulations data needs to be classified according to preset classification rules to update the existing category sub-database. This classification step is an important step in incorporating new regulations into existing learning resources, ensuring that learners can access all relevant regulations in a unified database environment. The same rules and standards as before should be followed during classification to avoid inconsistencies and confusion in the data. The classified new regulations data will be integrated into the corresponding category sub-database, making it part of learners' acquisition of legal knowledge. This update process not only helps improve the completeness and authority of the regulations database but also enhances learners' adaptability and understanding of dynamic legal changes. Furthermore, by continuously updating the category sub-database, learners' systematic approach to legal learning can be enhanced, making them more adept at learning and applying legal knowledge.

[0106] In one embodiment, step S1 of obtaining the tag information of the learner includes:

[0107] S111: Obtain the identity information, shareholding information, and job position information of the person to be learned;

[0108] S112: Generate the information vector of the person to be learned based on the identity information, shareholding information and job position information;

[0109] S113: Map the information vector to obtain the mapped tag information.

[0110] As described in step S113 above, the identity information, shareholding information, and job position information of the learner are obtained. During the intelligent legal learning process, basic information about the learner is collected, including identity information, shareholding information, and job position information. Identity information typically involves the learner's name, age, education, and other personal background information, which helps in understanding their legal environment and potential legal issues. Shareholding information involves the learner's equity holdings in companies or other entities, which may affect their interests in certain legal matters, such as learning about company law or securities law. Job position information typically includes the learner's position, responsibilities, and professional field, which can guide the direction and focus of legal learning, as different positions may require mastering different laws and regulations. Comprehensive collection of this information helps educators better understand the learner's background and provides a basis for subsequently customizing personalized learning plans.

[0111] As described in step S112 above, an information vector for the learner is generated based on the identity information, shareholding information, and job position information. The key to this process is the numerical processing of multidimensional information for subsequent use in machine learning or data analysis. An information vector integrates identity information, shareholding information, and job position information into a unified expression, typically achieved through methods such as encoding and normalization to convert different types of data into numerical forms. For example, identity information might be labeled as a numerical category, shareholding percentages can be directly expressed as floating-point numbers, and job positions and functions can be mapped through label encoding. This information vectorization not only unifies various types of information during data processing but also facilitates subsequent model prediction and analysis. The information vector generated in this way allows for the identification and analysis of various information about the learner in a multidimensional space, helping educators objectively assess the learner's characteristics and needs.

[0112] As described in step S113 above, the information vector is mapped to obtain mapped label information. After generating the information vector, the mapping process can be achieved through a specific algorithm or model to transform the information vector into labels that better suit practical applications. This typically employs classification or clustering methods; specifically, the K-means clustering algorithm can be used to map the information vector to predefined label categories. The purpose of this mapping step is to facilitate subsequent classification, analysis, and personalized recommendations for learners. For example, through mapping, learners may be identified as "legal practitioners," "compliance personnel," or "investment experts," and these labels will influence their subsequent learning content and path. Furthermore, the mapped label information can help the system more efficiently retrieve and match relevant legal materials, improving learners' learning outcomes. In this way, the personalized needs of learners can be effectively matched with legal learning content, forming accurate learning recommendations, thereby improving learners' learning efficiency and satisfaction.

[0113] In one embodiment, after step S1 of obtaining the tag information of the learner and obtaining the target status of each preset regulatory category of the learner based on the tag information, the method further includes:

[0114] S201: Monitor whether the tag information of the person to be learned has been updated;

[0115] S202: If the tag information of the person to be learned is updated, then obtain the updated tag information;

[0116] S203: Update the target status of each preset regulation category of the learner based on the updated tag information.

[0117] As described in step S201 above, the tag information of the learner is monitored to see if it has been updated. After completing the initial acquisition of tag information and the corresponding target status setting, the learner's tag information is monitored to see if it has changed. This monitoring process typically involves periodically or in real-time confirmation of updates to the learner's identity information, shareholding information, and job position information. Changes in the learner's status, such as career advancement, job change, learning a new course, or changes in identity, directly affect their needs and target status during the legal learning process. By acquiring this information in a timely manner, it can be ensured that the set learning goals always match the learner's actual situation, thereby improving the effectiveness and relevance of learning. This proactive monitoring mechanism supports the dynamic adjustment of learning, helping to maintain the learner's up-to-date status and appropriate progress in legal knowledge acquisition.

[0118] As described in step S202 above, if the tag information of the learner is updated, the updated tag information is obtained. If the tag information of the learner is found to have been updated during the monitoring process, the next step is to obtain this updated tag information. This acquisition process may be implemented through an automated system or may require manual intervention, such as seamlessly connecting through information update requests submitted by the learner. When obtaining the updated tag information, it is necessary to ensure that the acquired data is accurate and complete. This usually requires verification of the information source to ensure the authority and reliability of the information. Obtaining the updated tag information will directly affect the previous learning status and the set learning objectives.

[0119] As described in step S203 above, the target status of each preset legal category for the learner is updated based on the updated tag information. After obtaining the latest tag information, the target status of each preset legal category for the learner must be updated according to this information. For example, if a learner needs to learn a new legal field due to a job change, the system needs to quickly adjust the corresponding legal learning objectives, including the new regulations that may need to be mastered, applicable case analyses, and related legal concepts. During the dynamic updating of the target status, learners can obtain the learning resources they need in a timely manner, ensuring the effectiveness and continuity of learning. The smooth execution of this step helps to achieve a truly personalized learning experience, enabling learners to receive timely support and assistance in a constantly changing environment, thereby effectively improving their mastery of legal knowledge.

[0120] In one embodiment, before step S3, which involves inputting the target state of each preset regulatory category and multiple historical mastery states into a preset learning time estimation model to obtain the first predicted learning duration for each preset regulatory category, the method further includes:

[0121] S211: Retrieve a preset number of sample data groups from a preset sample database, and divide the sample data into training data and validation data according to a preset ratio; wherein one set of the sample data consists of multiple historical mastery states for training, target states for training, and corresponding comprehensive tags; the comprehensive tags include duration tags and regulatory category tags;

[0122] S212: Input the training data into a preset support vector machine model for training, thereby obtaining a temporary support vector machine model;

[0123] S213: Use the verification data to verify the temporary support vector machine model to obtain the verification result, and determine whether the verification result is a successful verification;

[0124] S214: If the verification result is successful, the temporary support vector machine model is marked as the preset learning time prediction model.

[0125] As described in step S211 above, a preset number of sample data sets are retrieved from a preset sample database, and the sample data is divided into training data and validation data according to a preset ratio. Before estimating learning time, a set of preset sample data needs to be retrieved from the sample database. This sample data should include multiple historical mastery states, target states, and corresponding comprehensive labels. Comprehensive labels typically include duration labels and regulatory category labels, which will provide the necessary context for creating and training the model. The selection of sample data is crucial to the training quality of the model; therefore, when retrieving the data, the diversity and representativeness of the sample data should be ensured to cover different learner backgrounds and learning situations. Dividing the sample data into training data and validation data according to a preset ratio is usually to ensure the generalization ability of the model. Training data is used to train the model so that it can understand the relationship between learners' mastery states and learning time, while validation data is used to evaluate the model's performance on unseen data. This division can effectively detect overfitting of the model, ensuring that the constructed learning time estimation model can be effectively applied in real-world environments, thereby improving its accuracy.

[0126] As described in step S212 above, the training data is input into a preset support vector machine (SVM) model for training, thereby obtaining a temporary SVM model. After completing the partitioning of the sample data, the next step is to input the training data into a preset SVM model for training. Support vector machines are a commonly used supervised learning algorithm that can effectively handle classification and regression problems. During training, the model learns patterns and features in the training data through the algorithm, i.e., how to predict the required learning time based on historical mastery states and target states. In this process, the model continuously adjusts its parameters through optimization algorithms to minimize prediction errors and models the relationship between the learner's historical data and its target state. The output is a temporary SVM model, which has preliminary learning capabilities, meaning it can predict the learning time to some extent.

[0127] As described in step S213 above, the temporary support vector machine model is validated using the validation data to obtain validation results, and it is determined whether the validation is successful. After training, the obtained temporary support vector machine model needs to be validated to evaluate its predictive performance and generalization ability. To this end, validation data is input into the temporary support vector machine model, and the model will predict the learning time based on the historical mastery state and target state in the validation data. We will obtain a series of prediction results, which will be compared with the true labels in the validation data to calculate the model's prediction accuracy and error, among other metrics. Judging the validation results is crucial. If the validation results show that the model's prediction accuracy reaches a preset standard, it can be considered a successful validation. Through this validation process, it is ensured that the model can still provide high accuracy even with unseen data, avoiding overfitting on the training data and improving its reliability and effectiveness in practical applications. If the validation results fail, it is necessary to return to the training phase for optimization, adjusting feature selection, parameter settings, or re-collecting sample data to improve the model's performance.

[0128] As described in step S214 above, if the verification result is successful, the temporary support vector machine model is marked as the preset learning time prediction model. During the verification process, if the result shows that it meets the criteria, the temporary support vector machine model is transformed into a formal learning time prediction model. This model has demonstrated good predictive ability through verification data and can be reliably used in practical learning scenarios, such as personalized learning time prediction for learners. This result not only provides quantitative time planning for legal studies but also provides a scientific basis for developing personalized learning plans. Ultimately, the successful construction and application of this learning time prediction model aims to improve learners' learning efficiency and effectiveness through data-driven methods, making their legal learning process more targeted and effective.

[0129] Reference Figure 3 The present invention also provides a regulatory intelligent learning device, the device comprising:

[0130] The target status acquisition module 902 is used to acquire the tag information of the person to be learned, and to acquire the target status of the person to be learned for each preset legal category based on the tag information.

[0131] The historical mastery status acquisition module 904 is used to acquire the historical mastery status of the learner on each preset legal category at multiple time points during the learning process.

[0132] The first predicted learning duration acquisition module 906 is used to input the target state of each preset legal category and multiple historical mastery states into the preset learning time estimation model to obtain the first predicted learning duration of each preset legal category.

[0133] The historical fingerprint spectrum setting module 908 is used to set the historical fingerprint spectrum of the person to be learned according to the first predicted learning duration.

[0134] The learning time percentage setting module 910 is used to set the learning time percentage for each of the preset regulatory categories based on the historical fingerprint map.

[0135] The learning plan formulation module 912 is used to formulate a learning plan for the person to be learned based on the proportion of learning time, so that the person to be learned can learn according to the learning plan.

[0136] In one embodiment, the regulatory intelligent learning device further includes:

[0137] The current mastery status acquisition module is used to acquire the current mastery status of the learner for each preset category of regulations after the learner has studied for a preset period of time.

[0138] The second predicted learning duration acquisition module is used to input the target state, the current mastery state and multiple historical mastery states of each preset legal category into the preset learning time estimation model to obtain the second predicted learning duration of each preset legal category.

[0139] The fingerprint acquisition module is used to update the historical fingerprint spectrum according to the second prediction learning duration to obtain the current fingerprint spectrum;

[0140] The real-time learning time percentage setting module is used to set the real-time learning time percentage for each of the preset regulatory categories based on the current fingerprint spectrum.

[0141] The learning module is used to formulate a current learning plan for the learner based on the proportion of real-time learning time, so that the learner can learn according to the current learning plan.

[0142] In one embodiment, the regulatory intelligent learning device further includes:

[0143] The regulatory database acquisition module is used to acquire the regulatory database to be studied;

[0144] The target regulation data acquisition module is used to disassemble the regulation database according to a preset disassembly method to obtain multiple disassembled target regulation data.

[0145] The category sub-database acquisition module is used to classify each target regulation data according to preset classification rules to obtain a category sub-database corresponding to each preset regulation category; the category sub-database is used to detect the mastery status of the learner and to provide learning materials for the learner.

[0146] In one embodiment, the regulatory intelligent learning device further includes:

[0147] The judgment module is used to determine whether there are new regulations;

[0148] The target new regulation data acquisition module is used to disassemble the new regulation according to a preset disassembly method if there is a new regulation, so as to obtain multiple disassembled target new regulation data.

[0149] The category sub-database update module is used to classify each of the target new regulations data according to preset classification rules in order to update the corresponding category sub-database.

[0150] In one embodiment, the target state acquisition module 902 includes:

[0151] The identity information acquisition submodule is used to acquire the identity information, shareholding information, and job position information of the person to be learned;

[0152] The information vector generation submodule is used to generate the information vector of the person to be learned based on the identity information, shareholding information and job position information.

[0153] The tag information acquisition submodule is used to map the information vector to obtain the mapped tag information.

[0154] In one embodiment, the regulatory intelligent learning device further includes:

[0155] The monitoring module is used to monitor whether the tag information of the learner has been updated;

[0156] The tag information acquisition module is used to acquire the updated tag information if the tag information of the person to be learned is updated.

[0157] The target status update module is used to update the target status of each preset legal category of the learner based on the updated tag information.

[0158] In one embodiment, the regulatory intelligent learning device further includes:

[0159] The sample data retrieval module is used to retrieve a preset number of sample data groups from a preset sample database, and divide the sample data into training data and validation data according to a preset ratio; wherein one set of the sample data consists of multiple historical mastery states for training, target states for training, and corresponding comprehensive tags; the comprehensive tags include duration tags and regulatory category tags;

[0160] The training module is used to input the training data into a preset support vector machine model for training, thereby obtaining a temporary support vector machine model;

[0161] The verification module is used to verify the temporary support vector machine model using the verification data to obtain the verification result and determine whether the verification result is a successful verification.

[0162] The preset module is used to mark the temporary support vector machine model as a preset learning time prediction model if the verification result is successful.

[0163] Figure 4 An internal structural diagram of an electronic device in one embodiment is shown. This electronic device can specifically be a terminal or a server, and more specifically, a computer device. Figure 4 As shown, the electronic device includes a processor, a memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement a regulatory intelligent learning method. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to execute the regulatory intelligent learning method. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0164] In one embodiment, an electronic device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps:

[0165] Obtain the tag information of the person to be learned, and obtain the target status of each preset legal category of the person to be learned based on the tag information;

[0166] During the learning process, the historical mastery status of the learner on each preset legal category is obtained at multiple time points.

[0167] The target state and multiple historical mastery states of each preset regulation category are input into the preset learning time prediction model to obtain the first predicted learning time of each preset regulation category.

[0168] The historical fingerprint profile of the person to be learned is set according to the first predicted learning duration;

[0169] The learning time percentage for each of the preset regulatory categories is set based on the historical fingerprint map;

[0170] A learning plan is formulated for the person to be learned based on the percentage of learning time, so that the person to be learned can learn in accordance with the learning plan.

[0171] Accurately identifying an individual's level of mastery in different legal categories allows for the creation of personalized learning plans. This ensures learners can focus their efforts on the areas most in need of improvement within a short period, enhancing the relevance and effectiveness of learning. By utilizing a pre-defined learning time prediction model to forecast learning duration, learning time can be allocated rationally, ensuring learners receive a reasonable learning weight across different legal categories. This avoids knowledge gaps caused by improper time allocation, making legal learning more intelligent and human-centered. It not only improves learners' learning efficiency but also provides effective support for cultivating high-quality legal professionals, achieving personalized learning planning.

[0172] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the following steps:

[0173] Obtain the tag information of the person to be learned, and obtain the target status of each preset legal category of the person to be learned based on the tag information;

[0174] During the learning process, the historical mastery status of the learner on each preset legal category is obtained at multiple time points.

[0175] The target state and multiple historical mastery states of each preset regulation category are input into the preset learning time prediction model to obtain the first predicted learning time of each preset regulation category.

[0176] The historical fingerprint profile of the person to be learned is set according to the first predicted learning duration;

[0177] The learning time percentage for each of the preset regulatory categories is set based on the historical fingerprint map;

[0178] A learning plan is formulated for the person to be learned based on the percentage of learning time, so that the person to be learned can learn in accordance with the learning plan.

[0179] Accurately identifying an individual's level of mastery in different legal categories allows for the creation of personalized learning plans. This ensures learners can focus their efforts on the areas most in need of improvement within a short period, enhancing the relevance and effectiveness of learning. By utilizing a pre-defined learning time prediction model to forecast learning duration, learning time can be allocated rationally, ensuring learners receive a reasonable learning weight across different legal categories. This avoids knowledge gaps caused by improper time allocation, making legal learning more intelligent and human-centered. It not only improves learners' learning efficiency but also provides effective support for cultivating high-quality legal professionals, achieving personalized learning planning.

[0180] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0181] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0182] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method of learning regulations intelligently, the method comprising: The method comprises: acquiring label information of a to-be-learned person, and acquiring a target state of each preset regulation category of the to-be-learned person according to the label information; acquiring historical mastering states of each preset regulation category of the to-be-learned person at multiple time points in a learning process of the to-be-learned person; inputting the target state of each preset regulation category and the multiple historical mastering states into a preset learning time estimation model to obtain a first predicted learning time length of each preset regulation category; setting a historical fingerprint spectrum of the to-be-learned person according to the first predicted learning time length; setting a learning time proportion of each preset regulation category according to the historical fingerprint spectrum; formulating a learning plan of the to-be-learned person according to the learning time proportion, so that the to-be-learned person learns according to the learning plan.

2. The regulatory intelligent learning method of claim 1, wherein, After the step of formulating the learning plan of the to-be-learned person according to the learning time proportion, so that the to-be-learned person learns according to the learning plan, the method further comprises: acquiring a current mastering state of each preset regulation category of the to-be-learned person after the to-be-learned person learns for a preset time length; inputting the target state, the current mastering state and the multiple historical mastering states of each preset regulation category into the preset learning time estimation model to obtain a second predicted learning time length of each preset regulation category; updating the historical fingerprint spectrum according to the second predicted learning time length to obtain a current fingerprint spectrum; setting a real-time learning time proportion of each preset regulation category according to the current fingerprint spectrum; formulating a current learning plan of the to-be-learned person according to the real-time learning time proportion, so that the to-be-learned person learns according to the current learning plan. 3.The regulatory intelligent learning method of claim 1, wherein, Before the step of acquiring the historical mastering states of each preset regulation category of the to-be-learned person at multiple time points in a learning process of the to-be-learned person, the method further comprises: acquiring a regulation database to be learned; disassembling the regulation database according to a preset disassembling manner to obtain multiple pieces of disassembled target regulation data; classifying each piece of the target regulation data according to a preset classification rule to obtain a category sub-database corresponding to each preset regulation category; the category sub-database is used for detecting a mastering state of the to-be-learned person and providing learning materials for the to-be-learned person.

4. The regulatory intelligent learning method of claim 3, wherein, After the step of classifying each piece of the target regulation data according to a preset classification rule to obtain a category sub-database corresponding to each preset regulation category, the method further comprises: determining whether there is a new regulation; if there is a new regulation, disassembling the new regulation according to a preset disassembling manner to obtain multiple pieces of disassembled target new regulation data; classifying each piece of the target new regulation data according to a preset classification rule to update the corresponding category sub-database.

5. The regulatory intelligent learning method of claim 1, wherein, The step of acquiring label information of a to-be-learned person comprises: acquiring identity information, holding information and job information of the to-be-learned person; generating an information vector of the to-be-learned person according to the identity information, the holding information and the job information; mapping the information vector to obtain mapped label information.

6. The regulatory intelligent learning method of claim 1, wherein, The step of acquiring the label information of the to-be-learned personnel and acquiring the target state of each preset regulation category of the to-be-learned personnel according to the label information further comprises: monitoring whether the label information of the to-be-learned personnel is updated; if the label information of the to-be-learned personnel is updated, acquiring the updated label information; updating the target state of each preset regulation category of the to-be-learned personnel according to the updated label information.

7. The regulatory intelligent learning method of claim 1, wherein, The step of inputting the target state of each preset regulation category and the plurality of historical mastering states into the preset learning time estimation model to obtain the first predicted learning time length of each preset regulation category further comprises: fetching a preset number of sample data from a preset sample database, and dividing the sample data into training data and verification data according to a preset proportion; wherein one set of sample data is composed of a plurality of training historical mastering states, training target states, and corresponding comprehensive labels; the comprehensive label includes a time length label and a regulation category label; inputting the training data into a preset support vector machine model for training, thereby obtaining a temporary support vector machine model; verifying the temporary support vector machine model using the verification data to obtain a verification result, and determining whether the verification result is verified; if the verification result is verified, marking the temporary support vector machine model as a preset learning time estimation model.

8. A regulation intelligent learning device, characterized by, The device comprises: a target state acquisition module configured to acquire label information of a to-be-learned personnel and acquire a target state of each preset regulation category of the to-be-learned personnel according to the label information; a historical mastering state acquisition module configured to acquire historical mastering states of each preset regulation category of the to-be-learned personnel at a plurality of time points during learning of the to-be-learned personnel; a first predicted learning time length acquisition module configured to input the target state of each preset regulation category and the plurality of historical mastering states into a preset learning time estimation model to obtain a first predicted learning time length of each preset regulation category; a historical fingerprint spectrum setting module configured to set a historical fingerprint spectrum of the to-be-learned personnel according to the first predicted learning time length; a learning time proportion setting module configured to set a learning time proportion of each preset regulation category according to the historical fingerprint spectrum; a learning plan formulation module configured to formulate a learning plan of the to-be-learned personnel according to the learning time proportion, so that the to-be-learned personnel learns according to the learning plan.

9. A computer-readable storage medium, characterized in that, A computer program is stored, and when executed by a processor, causes the processor to perform the steps of the regulation intelligent learning method according to any one of claims 1 to 7.

10. An electronic device, comprising: The device comprises a memory and a processor, and the memory stores a computer program which, when executed by the processor, causes the processor to perform the steps of the regulation intelligent learning method according to any one of claims 1 to 7.

Images