Interactive law learning system based on Internet of Things

Abstract

The invention relates to the field of education, and discloses an internet of things-based interactive law learning system, which comprises a data acquisition module, a learning management module, a VR interaction module and a feedback analysis module, the data acquisition module acquires the physiological state, behavior data and environmental data of the learner in real time, and performs preprocessing and weighted fusion on the data; the learning management module provides case discussion and court simulation functions, realizes real-time interaction between learners and the system, and recommends personalized learning tasks; the VR interaction module provides an immersive law learning situation through a virtual reality technology, so that a learner can perform application practice of law knowledge in a virtual environment; the feedback analysis module dynamically adjusts a learning path and generates personalized feedback information based on an analysis result of the multi-source data; through cooperative work of multiple modules, personalized and immersive law learning experience is achieved, and the law knowledge mastering and practicing ability of learners is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and in particular to an interactive legal learning system based on the Internet of Things. Background Art

[0002] In existing legal education and training, traditional teaching methods such as classroom lectures, written case analysis, and moot courts have many limitations. Although classroom lectures can systematically impart legal knowledge, due to the lack of interactivity, it is difficult for learners to deeply understand complex legal concepts and practical application skills. In addition, written case analysis often only stays at the theoretical level, and learners lack the experience of real legal situations, making it difficult to effectively apply the knowledge they have learned in practice. Although traditional moot courts can provide certain practical opportunities, due to the limitations of scene layout and personnel arrangements, it is difficult to achieve high-frequency use, and there is a lack of real-time feedback, and it is impossible to make dynamic adjustments based on learners' performance.

[0003] In the context of informatization and intelligence, some educational institutions have tried to improve the effectiveness of legal education through online learning platforms or virtual teaching tools, but the interactivity and personalized support capabilities of most systems are still limited. These systems usually lack real-time monitoring of learners' status, cannot provide data-driven personalized learning paths, and are difficult to dynamically adjust learning tasks based on learners' real-time performance. In addition, many systems rely solely on video or text content and lack an immersive virtual learning environment. Learners cannot practice legal knowledge in realistic simulation scenarios, which makes it difficult to effectively improve their practical ability.

[0004] Therefore, the existing legal education system has obvious shortcomings in personalized learning support, enhanced interactivity, and practical ability cultivation. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides an interactive legal learning system based on the Internet of Things, which solves the problems of lack of personalized learning support, insufficient interactivity and limited practical ability training in existing legal education, and provides a personalized and immersive legal learning experience through real-time data collection and dynamic feedback.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an interactive legal learning system based on the Internet of Things, comprising:

[0007] A data acquisition module is used to collect learners' physiological status, behavioral data and environmental data through various sensors, and send the collected data to the system;

[0008] A learning management module, connected to the data collection module, is used to provide case discussion and moot court functions, realize real-time interaction between learners and the system, and recommend corresponding learning tasks based on learners' performance;

[0009] A VR interactive module, connected to the learning management module, for providing an immersive legal learning scenario through virtual reality technology, so that learners can practice legal knowledge in a virtual environment;

[0010] The feedback analysis module is connected to the data acquisition module, the learning management module and the VR interaction module, and is used to analyze the real-time status of the learner and generate personalized learning feedback and learning path adjustment suggestions.

[0011] Preferably, the data acquisition module includes:

[0012] Smart watches to collect learners’ heart rate and blood oxygen levels;

[0013] Smart glasses to track learners’ gaze;

[0014] Environmental sensors to monitor the temperature and humidity of the learning environment.

[0015] Preferably, the data acquisition module further includes:

[0016] The data preprocessing unit is used to perform denoising and standardization processing on the collected data to remove data noise and normalize the data.

[0017] Preferably, the learning management module includes:

[0018] Case discussion unit, which is used to support real-time online discussions among learners and extract key words of the discussion through natural language processing technology;

[0019] The moot court unit is used to create virtual court scenarios, support learners to play the role of judges, lawyers or jurors in a virtual court environment, and analyze and score learners' debate performance through speech recognition technology.

[0020] Preferably, the learning management module further includes:

[0021] The path recommendation unit dynamically analyzes the learner's learning status based on the Markov chain model and recommends corresponding learning tasks, including the following steps:

[0022] Analyze the learner's current learning status and establish a learning status set ;

[0023] Calculate the transition probability between learning states to form a state transfer matrix :

[0024]

[0025] in, Indicates the learning status from Transfer to The probability of

[0026] Based on the state transfer matrix and the current learning state, the optimal learning path is predicted, and learning tasks that meet the learner's current level and goals are recommended.

[0027] Preferably, the VR interaction module includes:

[0028] a scenario design unit for creating virtual learning scenarios;

[0029] Behavior capture unit, used to record learners’ behavior data and reaction time in the virtual environment;

[0030] The difficulty adjustment unit predicts the learner's performance in a specific task and adjusts the difficulty of the task based on the Bayesian network model.

[0031] Preferably, the feedback analysis module includes:

[0032] A feature extraction unit, used to generate a feature vector of a learner based on the multi-source data of the data acquisition module;

[0033] The learning recommendation unit analyzes learners’ learning performance and feedback based on reinforcement learning algorithms and dynamically adjusts learning task recommendation strategies.

[0034] Preferably, the feedback analysis module further includes:

[0035] The real-time feedback unit displays learners’ progress information in real time, including knowledge mastery, mock court performance, and discussion participation. The specific steps are as follows:

[0036] Receive multi-source data from the data acquisition module and extract the learner's feature vector , where each is the comprehensive state value after weighted fusion;

[0037] Based on the extracted feature vector Interact with learners, evaluate learners' knowledge mastery, task completion, and performance in the moot court, and generate a comprehensive learning progress report;

[0038] Personalized feedback information is generated based on the analysis results of the performance evaluation unit, including knowledge mastery, participation and real-time suggestions, and the feedback information is displayed on the learning platform to help learners understand the current learning progress and adjust the learning strategy in time.

[0039] The present invention also provides an interactive legal learning method based on the Internet of Things, comprising the following steps:

[0040] Collect learners' physiological status, behavioral data and environmental data in real time through multiple sensors;

[0041] Preprocessing the collected data to obtain standardized data for analysis;

[0042] Generate comprehensive status information of learners and analyze the current learning status of learners;

[0043] Dynamically recommend appropriate learning tasks based on the learner's current learning status;

[0044] Providing an immersive legal learning scenario through a virtual reality environment, allowing learners to practice legal knowledge in a virtual scenario;

[0045] Analyze learners' interactive performance and dynamically adjust recommendation strategies based on learning feedback;

[0046] Display learners' learning progress and feedback information in real time to help learners optimize their learning process.

[0047] The present invention also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the above method is implemented.

[0048] The present invention also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0049] The present invention provides an interactive legal learning system based on the Internet of Things. It has the following beneficial effects:

[0050] 1. Through the multi-source sensors of the data acquisition module, the system can monitor the learner's physiological, behavioral and environmental status in real time, providing an accurate basis for learning path recommendation and learning feedback. Based on the analysis and feedback of real-time data, the system can dynamically adjust the learning content to make the learning process more in line with the individual needs of the learner.

[0051] 2. With the help of VR interactive modules, the system provides a more realistic legal learning scenario, allowing learners to practice legal knowledge and skills in a virtual court or legal consultation room. The highly realistic virtual scene increases learners' participation and immersion, allowing learners to get practical training in simulated legal scenarios, thereby deepening their understanding of knowledge and their ability to apply it.

[0052] 3. The learning management module of the present invention dynamically analyzes the learner's status based on the Markov chain model, recommends learning tasks that meet their current level and needs, and ensures the consistency and pertinence of the learning path. The system gradually increases the difficulty of tasks as the learner progresses, helping learners to steadily improve their legal skills and achieve a gradual learning effect.

[0053] 4. The feedback analysis module of the present invention dynamically generates personalized learning feedback through the reinforcement learning algorithm, and displays the learning progress and knowledge mastery in real time on the visual interface. Learners can timely understand their own weaknesses and make self-adjustments, thereby improving their legal knowledge mastery and practical ability in a targeted manner.

[0054] 5. Through case discussions and mock courts, the system enables learners to consolidate legal knowledge in interaction and improve practical skills such as debate and evidence analysis in practical situations, meeting the high requirements for practical application ability in legal education. This comprehensive learning process significantly enhances learners' legal practice ability and lays a solid foundation for future practical legal work. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a schematic diagram of the system architecture of the present invention;

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

[0057] Figure 3 It is a schematic diagram of the computer device structure of the present invention.

[0058] Among them, 40, computer equipment; 41, processor; 42, memory; 43, storage medium. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments 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.

[0060] Please see attached Figure 1 The embodiment of the present invention provides an interactive legal learning system based on the Internet of Things, which combines Internet of Things devices and virtual reality technology, uses learning management and feedback analysis modules to provide learners with personalized legal learning experience, and significantly improves the mastery of legal knowledge and practical ability. The interactive legal learning system of the present invention mainly includes a data acquisition module, a learning management module, a VR interaction module, and a feedback analysis module. The following describes each module of the present invention in detail.

[0061] Data acquisition module

[0062] As the basic part of the whole system, the data acquisition module is used to collect the learner's physiological state, behavioral data and environmental data, and provide necessary data support for the recommendation and feedback analysis of subsequent learning paths. The data acquisition module in the present invention combines a variety of sensor devices and performs data preprocessing and fusion after collection, thereby ensuring the accuracy and consistency of the data, which is convenient for further analysis and application.

[0063] In this embodiment, the data acquisition module includes a variety of devices such as smart watches, smart glasses, and environmental sensors, which are used to obtain multi-source data of learners. Specifically, smart watches can be used to collect learners' heart rate, blood oxygen and other physiological index data, smart glasses are used to track learners' gaze point data, and environmental sensors collect external environmental parameters such as temperature and humidity in the learning environment. In some embodiments, each sensor in the data acquisition module is connected to the system through a low-power wireless communication protocol to achieve real-time data transmission.

[0064] In some embodiments, to ensure the validity and consistency of multi-source data, the data acquisition module performs necessary preprocessing on the collected raw data, including denoising and standardization. In this embodiment, the data acquisition module uses a sliding mean filter to denoise the collected data to eliminate high-frequency noise in the data, thereby ensuring the stability of the data. Taking the collected heart rate data as an example, the filtering processing formula is as follows:

[0065]

[0066] in, Indicates at time The filtered data, is the size of the sliding window, For the The sensor at the time The original data value of .

[0067] In addition, in order to facilitate the subsequent fusion of multi-source data, in this embodiment, the data acquisition module performs standardization processing on the filtered data, that is, converting the raw data of each sensor into dimensionless standardized data to eliminate the differences between different physical quantities. The specific operations of standardization are:

[0068]

[0069] in, represents the standardized data, and Respectively The above preprocessing steps ensure the stability and consistency of the data, facilitating the unified analysis of different data sources.

[0070] In this embodiment, the data acquisition module combines a variety of sensor devices, data preprocessing, and multi-source data fusion methods to achieve real-time acquisition and integration of learners' physiological status, behavioral data, and environmental data, providing a high-quality data foundation for the learning management module and feedback analysis module. By denoising and standardizing the data, the accuracy and stability of the data are guaranteed, which helps to improve the accuracy of subsequent personalized recommendations for learning paths and feedback analysis.

[0071] Learning Management Module

[0072] The learning management module enables real-time interaction between learners and the system, and provides personalized learning task recommendations based on the learner's status and performance. The learning management module works with the data collection module to dynamically adjust the learning content based on the learner's performance and needs, thereby improving the pertinence and interactivity of legal learning. This module specifically includes case discussion and moot court functions, which analyze the learner's learning status through a variety of technical means and recommend learning paths to ensure the consistency and effectiveness of the learning process.

[0073] In this embodiment, the learning management module includes a case discussion unit, a moot court unit, and a path recommendation unit.

[0074] In this embodiment, the case discussion unit is used to support learners' real-time online discussions. The unit implements real-time communication between learners and the system through the WebSocket protocol, allowing learners to have in-depth discussions during the legal case analysis process. In some embodiments, in order to improve the efficiency of the discussion, the case discussion unit also includes a natural language processing function, which extracts keywords from the learners' speeches through the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm to help learners understand and communicate key content more clearly. Specifically, the calculation formula for the TF-IDF value is:

[0075]

[0076] in, Indicates keywords In the documentation The frequency of occurrence in is the total number of documents, To contain keywords Through keyword extraction, the system can analyze the discussion content of learners and provide support for further content guidance and learning content recommendation.

[0077] In this embodiment, the moot court unit is used to create a virtual courtroom environment for learners, enabling them to play different roles and participate in interactions in legal situations. Learners can choose to serve as judges, lawyers, or jurors, and practice legal knowledge through activities such as debates and evidence presentations in moot courtroom scenarios. The unit uses speech recognition and language processing technology to analyze learners' speeches in real time, and analyzes and scores learners' debate performances using preset scoring criteria. In some embodiments, the system also compiles statistics on learners' performance based on the scoring results to help subsequent feedback analysis modules evaluate learners' knowledge mastery.

[0078] In some embodiments, in order to better recommend learning tasks, the learning management module also includes a path recommendation unit. The path recommendation unit dynamically analyzes the learner's learning state based on the Markov chain model, selects the optimal learning path, and recommends learning tasks that meet the learner's current state. Specifically, the path recommendation unit constructs a learning state set And the state transfer matrix , used to represent the transition probability between learning states. State transfer matrix is defined as follows:

[0079]

[0080] in, Indicates the learning status from Transfer to After detecting the learner's current learning state, the path recommendation unit predicts the learner's next state based on the state transition probability and recommends a learning task suitable for the state. In some embodiments, the path recommendation unit dynamically updates the transition probability in the state transition matrix based on historical data, so that the recommendation strategy can adapt to the learner's actual learning situation.

[0081] In summary, the learning management module dynamically adjusts the learning path based on the learner's real-time performance through functions such as case discussion, moot court and path recommendation, and provides relevant cases and simulation tasks when necessary, thereby providing learners with an interactive and personalized learning experience.

[0082] VR interactive module

[0083] The VR interactive module is used to provide learners with an immersive legal learning scenario through virtual reality technology, enabling learners to practice legal knowledge in a virtual environment. Based on the learner behavior data and status information obtained by the data acquisition module, the VR interactive module provides learners with personalized virtual scenes and task difficulty settings, so that learners can obtain a closer to real legal learning experience in scenarios such as moot courts and consulting rooms.

[0084] In this embodiment, the VR interaction module includes a situation design unit, a behavior capture unit and a difficulty adjustment unit.

[0085] In this embodiment, the scenario design unit is used to create highly simulated virtual legal scenarios, including scenarios such as moot courts and legal consultation rooms, and 3D scene modeling and animation are performed through the Unity engine or the Unreal engine, so that learners can enter virtual scenarios as judges, lawyers, or jurors. In these scenarios, learners can role-play and interact through virtual objects to further understand and apply legal knowledge. The scenario design unit can set the complexity of the scenario according to different legal learning tasks. For example, different evidence presentation links, debate links, etc. can be set in the moot court scenario to meet different teaching needs.

[0086] In some embodiments, the behavior capture unit in the VR interaction module is used to record the learner's behavior data in the virtual scene, including the learner's line of sight, operation object, and reaction time, etc. These data provide a real operation record for subsequent analysis. Specifically, the behavior capture unit captures the learner's behavior trajectory in the virtual scene in real time based on the sensor data provided by the VR device, such as handle movements, head rotations, etc., and generates behavior sequence data. These behavioral data can be used to analyze learners' performance and responses in specific tasks.

[0087] In this embodiment, the difficulty adjustment unit dynamically adjusts the difficulty of the VR task through the Bayesian network model based on the learner's behavior data and performance to adapt to the learner's ability level. Specifically, the difficulty adjustment unit uses the Bayesian network to predict the learner's behavior pattern based on the data recorded by the behavior capture unit to determine whether the learner encounters difficulties in the current task. The conditional probability distribution of the Bayesian network model is as follows:

[0088]

[0089] in, represents the behavioral state of the learner. is the observed variable, represents the probability distribution of observed data under a given behavior state, is the prior probability of the behavior state. Through this Bayesian network model, the difficulty adjustment unit can predict the learner's performance in a specific task. For example, if the learner pauses many times or takes a long time to react in the moot court, the system will judge that he or she is having difficulties in the current task and appropriately reduce the difficulty of the task.

[0090] In some embodiments, after detecting that the learner's performance meets the conditions for task reduction, the difficulty adjustment unit can provide simplified scenarios or prompt information, such as reducing interference factors in the evidence presentation phase, or providing simplified arguments in the complex debate phase, so as to improve the learner's task completion and confidence.

[0091] In summary, the VR interactive module creates realistic legal learning scenarios through the scenario design unit, and dynamically adjusts the difficulty of learners' tasks through the behavior capture unit and the difficulty adjustment unit, enabling learners to conduct practical exercises of legal knowledge in a highly adaptable virtual environment, providing important support for the dynamic optimization of learning paths and personalized learning.

[0092] Feedback Analysis Module

[0093] The feedback analysis module is used to analyze the learner's real-time status and generate personalized learning feedback, and optimize the learning process by dynamically recommending learning tasks and path adjustment suggestions. The feedback analysis module is connected with the data acquisition module, learning management module and VR interaction module, and comprehensively utilizes multi-source data and analysis models to ensure that the learning content can adapt to the learner's real-time performance and improve the accuracy and personalization of the learning path.

[0094] In this embodiment, the feedback analysis module includes a feature extraction unit, a learning recommendation unit and a real-time feedback unit.

[0095] In this embodiment, the feature extraction unit is used to generate a learner's feature vector based on the physiological data, behavioral data and environmental data provided by the data acquisition module. After denoising and standardization, the data acquisition module performs weighted fusion on the data from different sensors to form a comprehensive state value. In some embodiments, the feature extraction unit performs weighted processing on multi-source data, and the specific weighted fusion process is as follows:

[0096]

[0097] in, For the moment The comprehensive status value of For the The sensor at the time The standardized data, is the weight value of the sensor and satisfies In some embodiments, the weight It can be preset based on the degree of influence of different sensors on the learning effect, or it can be automatically adjusted through subsequent analysis to meet the needs of different learning scenarios. Through the above weighted fusion process, the feature vector generated by the feature extraction unit Can accurately reflect the learners' comprehensive status.

[0098] In this embodiment, the learning recommendation unit uses a reinforcement learning algorithm to dynamically analyze the learner's learning progress and feedback based on the feature vector provided by the feature extraction unit, so as to adjust the recommendation strategy in real time to provide a learning task suitable for the learner's current state. Specifically, the learning recommendation unit uses the Q-learning algorithm to select the optimal learning recommendation strategy by calculating the Q value. The update rules of the Q-learning algorithm are as follows:

[0099]

[0100] in, For the status Next action The Q value, is the learning rate, is the discount factor, For instant rewards, To perform actions In some embodiments, the learning recommendation unit calculates and updates the Q values ​​of different learning tasks based on the learner's historical behavior and current performance to select the next learning task that best suits the learner.

[0101] In this embodiment, the real-time feedback unit is used to display the analysis results to the learners in the form of feedback information, so as to help the learners understand the learning progress in a timely manner and make self-adjustments for the weak links. Specifically, the real-time feedback unit displays the learners' progress information through a visual interface, including the mastery of knowledge points, performance in the moot court, and the frequency of participation in discussions. In some embodiments, the real-time feedback unit can prompt the learners on the knowledge points that they should focus on in the next stage according to the recommendation strategy of the learning recommendation unit, or suggest participating in more moot court tasks to strengthen practical skills.

[0102] In summary, the feedback analysis module conducts in-depth analysis of the learner's status and generates a more adaptable learning path through units such as feature extraction, learning recommendation and real-time feedback, ensuring that the learning content meets the learner's current level and needs, making the learning process more targeted and effective.

[0103] As an example, the application of the interactive legal learning system of the present invention in the practical courses of the legal profession will be described below. The system provides students with an immersive and personalized legal learning experience through the collaborative work of the data collection module, the learning management module, the VR interaction module and the feedback analysis module.

[0104] In the legal practice course, students need to master practical skills such as court debate, evidence analysis, and application of legal provisions. Traditional teaching methods mainly rely on classroom lectures, and students lack real court experience and dynamic feedback, making it difficult for them to apply what they have learned in practice.

[0105] The system application process is as follows:

[0106] 1. Data collection and feature generation

[0107] In this embodiment, students wear smart watches and smart glasses to enter the learning system. Smart watches are used to monitor students' heart rate and blood oxygen level, and smart glasses are used to track students' gaze points to analyze their concentration. In addition, environmental sensors are also set up in the classroom to record external environmental data such as temperature and noise in real time.

[0108] The data acquisition module pre-processes all data, including denoising and standardization, to generate dimensionless data. Then, the system performs weighted fusion on these data according to preset weights to generate a comprehensive state value. , which is used to reflect the real-time status of students. For example, if a student's heart rate rises during a heated debate and his gaze is focused on the opposing lawyer, then This shows that students are focused and highly engaged, providing a basis for the system to recommend more complex debate tasks later.

[0109] 2. Case discussion and learning task recommendation

[0110] In the learning management module, the system provides students with a legal case discussion platform. Students can participate in discussions and share their views on the platform. The case discussion unit uses natural language processing technology to automatically extract key legal clauses or case keywords in students' speeches and record the frequency of students' discussions and the depth of their views.

[0111] The path recommendation unit in the learning management module uses the Markov chain model to dynamically adjust the learning path based on the student's performance. For example, when the system detects that the student has a good understanding of the key legal terms of a criminal case, it will transfer his status to a more difficult case analysis task to help the student gradually deepen the application of legal knowledge.

[0112] 3. VR interactive learning and task difficulty adaptation

[0113] Students enter the mock court scene in the VR interactive module and use VR equipment to play the role of lawyers in debates. In the mock court, students need to analyze evidence, question witnesses and make legal statements. The system creates a realistic court atmosphere through the scenario design unit and records students' behavior data in real time.

[0114] The system's difficulty adjustment unit predicts students' behavior through a Bayesian network model to determine whether students encounter challenges in the task. If it detects that students have a long reaction time or multiple pauses in a certain link, the system will appropriately reduce the difficulty of the task. For example, in the witness questioning link, the system can reduce the amount of non-critical evidence to help students better focus on key content, thereby improving task completion.

[0115] 4. Feedback and progress display

[0116] After the course is over, the system's feedback analysis module generates a student's learning progress report and displays it on a visual interface. The report includes the student's performance in case discussion, the completion of the moot court task, the mastery of key knowledge points, etc. At the same time, the system provides personalized learning suggestions. For example, for students with good debate performance, the system recommends more difficult debate tasks to strengthen their practical ability.

[0117] Students can understand their own weaknesses through feedback information, and conduct targeted review or participate in recommended tasks to continuously improve their ability to apply legal knowledge and skills in practice.

[0118] In this embodiment, the system uses a data-driven personalized feedback mechanism to enable students to gain an immersive courtroom experience in the legal practice course. The system combines real-time physiological and behavioral data to dynamically recommend learning paths, and improves students' participation and expressiveness through interactive learning in a simulated courtroom. The feedback analysis module provides students with clear learning progress information and personalized suggestions, allowing them to review and strengthen their learning content in a more targeted manner, thereby effectively improving the effectiveness of legal learning.

[0119] The data acquisition module of the present invention acquires learners' physiological, behavioral and environmental data in real time through multiple sensors, the learning management module provides case discussion and mock court functions, the VR interaction module simulates real legal scenarios through virtual reality technology, and the feedback analysis module dynamically adjusts the learning path based on multi-source data and generates personalized learning feedback. The system can effectively improve learners' legal practice ability and knowledge mastery depth, and provides an innovative digital solution for legal education.

[0120] Please see attached Figure 2 The present invention also provides an interactive legal learning method based on the Internet of Things. The method is based on the same concept as the above system and aims to provide learners with comprehensive legal learning support through multi-source data collection, personalized learning task recommendation and virtual reality interaction. Specifically, the method includes the following steps:

[0121] S1, collect learners' physiological status, behavioral data and environmental data in real time through multiple sensors;

[0122] S2. preprocessing the collected data to obtain standardized data for analysis;

[0123] S3, generating comprehensive status information of learners and analyzing the current learning status of learners;

[0124] S4. Dynamically recommend appropriate learning tasks based on the learner’s current learning status;

[0125] S5. Provide immersive legal learning scenarios through virtual reality environments, allowing learners to practice legal knowledge in virtual scenarios;

[0126] S6. Analyze learners’ interactive performance and dynamically adjust recommendation strategies based on learning feedback;

[0127] S7. Display learners’ learning progress and feedback information in real time to help learners optimize their learning process.

[0128] Since the steps of the method correspond to the functions of the above-mentioned system, they will not be described in detail in the repeated parts.

[0129] Please see attached Figure 3 The present invention further provides a computer device 40, comprising: a processor 41 and a memory 42, wherein the memory 42 stores a computer program executable by the processor, and when the computer program is executed by the processor, the above method is executed.

[0130] The present invention further provides a storage medium 43 on which a computer program is stored. When the computer program is run by the processor 41, the above method is executed.

[0131] Among them, the storage medium 43 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0132] 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. An interactive legal learning system based on the Internet of Things, characterized in that: include: A data acquisition module is used to collect learners' physiological status, behavioral data and environmental data through various sensors, and send the collected data to the system; A learning management module, connected to the data collection module, is used to provide case discussion and moot court functions, realize real-time interaction between learners and the system, and recommend corresponding learning tasks based on learners' performance; A VR interactive module, connected to the learning management module, for providing an immersive legal learning scenario through virtual reality technology, so that learners can practice legal knowledge in a virtual environment; The feedback analysis module is connected to the data acquisition module, the learning management module and the VR interaction module, and is used to analyze the real-time status of the learner and generate personalized learning feedback and learning path adjustment suggestions.

2. The interactive legal learning system based on the Internet of Things according to claim 1 is characterized in that: The data acquisition module comprises: Smart watches to collect learners’ heart rate and blood oxygen levels; Smart glasses to track learners’ gaze; Environmental sensors to monitor the temperature and humidity of the learning environment.

3. The interactive legal learning system based on the Internet of Things according to claim 1 is characterized in that: The data acquisition module also includes: The data preprocessing unit is used to perform denoising and standardization processing on the collected data to remove data noise and normalize the data.

4. The interactive legal learning system based on the Internet of Things according to claim 1 is characterized in that: The learning management module includes: Case discussion unit, which is used to support real-time online discussions among learners and extract key words of the discussion through natural language processing technology; The moot court unit is used to create virtual court scenarios, support learners to play the role of judges, lawyers or jurors in a virtual court environment, and analyze and score learners' debate performance through speech recognition technology.

5. The interactive legal learning system based on the Internet of Things according to claim 4 is characterized in that: The learning management module also includes: The path recommendation unit dynamically analyzes the learner's learning status based on the Markov chain model and recommends corresponding learning tasks, including the following steps: Analyze the learner's current learning status and establish a learning status set ; Calculate the transition probability between learning states to form a state transfer matrix : in, Indicates the learning status from Transfer to probability; Based on the state transfer matrix and the current learning state, the optimal learning path is predicted, and learning tasks that meet the learner's current level and goals are recommended.

6. The interactive legal learning system based on the Internet of Things according to claim 1 is characterized in that: The VR interaction module includes: a scenario design unit for creating virtual learning scenarios; Behavior capture unit, used to record learners’ behavior data and reaction time in the virtual environment; The difficulty adjustment unit predicts the learner's performance in a specific task and adjusts the difficulty of the task based on the Bayesian network model.

7. The interactive legal learning system based on the Internet of Things according to claim 1 is characterized in that: The feedback analysis module comprises: A feature extraction unit, used to generate a feature vector of a learner based on the multi-source data of the data acquisition module; The learning recommendation unit analyzes learners’ learning performance and feedback based on reinforcement learning algorithms and dynamically adjusts learning task recommendation strategies.

8. The interactive legal learning system based on the Internet of Things according to claim 1 is characterized in that: The feedback analysis module also includes: The real-time feedback unit displays learners’ progress information in real time, including knowledge mastery, mock court performance, and discussion participation. The specific steps are as follows: Receive multi-source data from the data acquisition module and extract the learner's feature vector , where each is the comprehensive state value after weighted fusion; Based on the extracted feature vector Interact with learners, evaluate learners' knowledge mastery, task completion, and performance in the moot court, and generate a comprehensive learning progress report; Personalized feedback information is generated based on the analysis results of the performance evaluation unit, including knowledge mastery, participation and real-time suggestions, and the feedback information is displayed on the learning platform to help learners understand the current learning progress and adjust the learning strategy in time.

9. An interactive legal learning method based on the Internet of Things, applied to the system as claimed in any one of claims 1 to 8, characterized in that: The following steps are involved: Collect learners' physiological status, behavioral data and environmental data in real time through multiple sensors; Preprocessing the collected data to obtain standardized data for analysis; Generate comprehensive status information of learners and analyze the current learning status of learners; Dynamically recommend appropriate learning tasks based on the learner's current learning status; Providing an immersive legal learning scenario through a virtual reality environment, allowing learners to practice legal knowledge in a virtual scenario; Analyze learners' interactive performance and dynamically adjust recommendation strategies based on learning feedback; Display learners' learning progress and feedback information in real time to help learners optimize their learning process.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to claim 9 is implemented.

Images