Interactive breakthrough-breaking knowledge learning method and implementation system thereof

Abstract

The invention belongs to the technical field of knowledge learning software, and particularly relates to an interactive breakthrough-breaking knowledge learning method and an implementation system thereof, and the method comprises the steps: outputting appropriate learning knowledge bases and game levels related to safety production knowledge according to the development direction of an enterprise; setting related scenes according to the development direction of the enterprise, and linking the scenes with a learning knowledge base and game levels; learning progress, difficulty and weak links of participants are known through data analysis; training learning needed by an enterprise is divided into different levels and difficulty levels, participants complete a series of level challenges, multi-person online competition and team cooperation interaction links are set, the learning interest and enthusiasm of the participants are stimulated, and the learning efficiency of the participants is improved. Personalized customized knowledge competition learning is carried out on enterprise employees, safety production is carried out according to designed games, the employees are helped to learn knowledge related to safety production while playing games, and links of the enterprise employees which are weak for safety knowledge are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of knowledge learning software, and specifically to an interactive level-passing knowledge learning method and its implementation system. Background Art

[0002] With the increasing development of China's economic capacity, society has put forward higher standards for education work. The curriculum system is an important application field of education. Relevant mobile software (or APP) enables users to be less restricted by teaching time and location and learn knowledge in a more flexible way. The high popularity of the Internet has brought about an information explosion, and online learning has become an irresistible trend. With the increasing international exchanges, the need for Chinese people to learn foreign languages well and foreigners to learn Chinese well is getting stronger and stronger. The importance of language learning is increasing day by day, and there is a wide demand for language talents globally. Against this background, online language learning has become the general trend.

[0003] Based on the current development of enterprises, the learning and improvement of employees need to be specifically trained according to the characteristics of employees. At present, the training on the enterprise side is relatively general, concentrating on training talents, resulting in the inability to conduct targeted training and learning for the differences of talents or the weaknesses of enterprise employees, and the enthusiasm of employees in learning cannot be timely controlled, nor can the results of employees' learning be timely understood.

[0004] Generally speaking, the existing interactive learning curriculum systems still mainly have the following defects: 1. Lack of systematicness: The difficulty levels of the course content accessed by users are uneven and the knowledge points are relatively scattered. Even if they are graded according to difficulty, it cannot be guaranteed that users have achieved the corresponding learning goals for each lesson. 2. Lack of planning: The time users spend learning languages is relatively random, either skimming the surface of the learning content or not consolidating and reviewing in time. 3. Lack of goal-orientation: The learning part and the assessment part are often separated, and the assessment often deviates from the learning goals and cannot reflect the learning results. 4. Lack of diversity: There is still a problem of single form of courseware in the existing courseware systems. This solution makes courseware based on page template files with fixed formats and display orders. Courseware developers can only make extremely limited adjustments to the materials in the template files. Therefore, only the content of the courseware can be freely changed, and the flexible design of the courseware cannot be achieved as a whole;

[0005] In view of the above technical defects, a solution for an interactive level-passing knowledge learning method and its implementation system is proposed. Summary of the Invention

[0006] To solve the above problems, the present invention provides the following technical solutions:

[0007] An interactive level-passing knowledge learning implementation system, comprising:

[0008] A content customization module that outputs a learning knowledge base and game levels related to appropriate work safety knowledge according to the development direction of the enterprise;

[0009] A virtual reality module that formulates relevant scene settings according to the development direction of the enterprise and connects the scenes with the learning knowledge base and game levels for simulating the actual environment during employees' safety knowledge learning;

[0010] A data analysis module that collects employees' learning data, conducts in-depth analysis and mining, and through data analysis, understands the learning progress, difficulties, and weak links of the participants, providing a basis for formulating safety training strategies;

[0011] A level-based learning module that adopts a level-based mode, divides the training learning required by the enterprise into different levels and difficulty levels, and participants gradually master safety knowledge and improve safety awareness by completing a series of level challenges;

[0012] An interactive learning module that sets up multi-player online competitions and team collaboration interaction sessions to stimulate the learning interest and enthusiasm of the participants, and through interactive learning, promotes the communication and cooperation among the participants, and jointly improves their own technical levels.

[0013] Furthermore, the content customization module includes:

[0014] Learning goal setting, including users setting short-term and long-term learning goals, such as passing a certain exam and mastering knowledge in a certain field, and providing corresponding learning plans and level recommendations according to the users' goals;

[0015] A knowledge level assessment unit that, when the user uses it for the first time, evaluates the user's current knowledge level through a series of assessment tests such as multiple-choice questions and fill-in-the-blank questions;

[0016] According to the assessment results, the system automatically adjusts the level difficulty and content recommendations, generates a personalized learning path map according to the user's knowledge level and learning goals, displays the recommended learning levels and modules, and the user adjusts the learning path according to their own needs;

[0017] Dynamic content adjustment, the system real-time monitors the user's learning progress and task completion status, dynamically adjusts the content and difficulty of the levels, and provides more relevant exercises and detailed explanations for the knowledge points that the user repeatedly makes mistakes on;

[0018] Recommended learning resources, according to the user's learning situation and needs, the system recommends suitable learning resources, such as video tutorials, reference materials, and exercise questions, and the user selects learning resources according to their interests to improve the learning effect;

[0019] User feedback mechanism: Users provide feedback on the content and levels recommended by the system. The system continuously optimizes the content recommendation algorithm based on the feedback. Users can put forward the knowledge points they are interested in and the content they hope to learn, and the system will try its best to meet the users' needs.

[0020] Learn data analysis. The system analyzes the users' learning behavior data, such as learning time, accuracy rate, and completion rate, to generate personalized learning reports. Based on the learning data, the system provides users with detailed learning suggestions and improvement plans.

[0021] Furthermore, the content customization module also includes:

[0022] Design an intuitive user interface to facilitate users to set learning goals and view personalized learning paths.

[0023] Provide flexible content adjustment options for users to freely adjust their learning plans and the order of levels.

[0024] Use AI and machine learning algorithms to analyze users' learning behaviors and feedback, and optimize content recommendation and difficulty adjustment.

[0025] Adopt RESTful API to achieve data interaction between the front and back ends and ensure the efficient operation of the system.

[0026] Use a relational database to store users' basic information and learning goals.

[0027] Use a non-relational database to store users' learning records and feedback data.

[0028] Encrypt and store users' data, and adopt security authentication mechanisms such as OAuth2.0 to protect the security of users' data and the system.

[0029] Help users master knowledge and improve learning effects through personalized learning paths and resource recommendations.

[0030] Furthermore, the virtual reality module includes creating an immersive virtual classroom environment where users can participate in virtual courses and discussions. The virtual classroom is equipped with facilities such as interactive whiteboards, virtual desks, and books to provide a real classroom experience. Create corresponding 3D scenes according to different learning contents, such as historical sites, laboratories, and observatories, where users can conduct virtual exploration and interaction to intuitively understand the learning content. Provide virtual laboratories where users can perform various experimental operations in a safe virtual environment. The system provides real-time feedback to help users understand the experimental process and results. Design interactive learning tasks in the VR environment, such as puzzles and mission challenges, to increase the fun of learning. Users can only pass the levels by completing these tasks, and the system provides instant feedback and guidance.

[0031] Furthermore, the data analysis module includes:

[0032] Learning data collection, collecting users' learning behavior data, including login time, learning duration, answering record, and progress of breaking through levels, and recording users' performance in each learning session, such as accuracy rate, error rate, and completion time;

[0033] Data processing and storage, using the ETL process to clean, transform, and store data, and storing the processed data in a data warehouse for subsequent analysis and query;

[0034] Learning progress tracking, tracking users' learning progress in real time, generating learning progress reports, identifying users' learning bottlenecks and difficulties through data analysis, and providing targeted learning suggestions;

[0035] Learning effect evaluation, evaluating users' performance in each level and learning task, generating learning effect reports, and adjusting the level difficulty and content recommendation according to the evaluation results to optimize users' learning paths;

[0036] Personalized recommendation, based on the data analysis results, recommending personalized learning content and resources to users, and using machine learning algorithms to analyze users' learning habits and preferences to improve the accuracy and relevance of recommendations;

[0037] User behavior analysis, analyzing users' learning behavior patterns, such as high-frequency learning time periods and learning habits, identifying the behavior characteristics of different user groups, and providing group behavior analysis reports.

[0038] Furthermore, the data analysis includes users' learning data, analyzing and optimizing the data in the database through data processing, and the optimization algorithm includes existing in the form of finding the maximum or minimum value, or minimizing costs, maximizing profits, maximizing efficiency, or finding the best parameter configuration that meets specific conditions, including linear optimization. The linear optimization calculation formula is as follows:

[0039]

[0040] Among them, x is the abscissa value of the current pattern dataset, The i point in the feasible set is expressed as a convex combination of extreme points plus a non-negative combination of extreme directions, The j point in the feasible set is expressed as a convex combination of extreme points plus a non-negative combination of extreme directions. Through linear analysis based on the convex combination of extreme points plus a non-negative combination of extreme directions of the data points in the feasible set, the ideal coordinate value at the time point of the current user's learning data is calculated.

[0041] Furthermore, the data analysis includes capturing data during the user's learning process and establishing a database, learning and calculating the data values of the user's learning through deep learning, comparing the real-time changing learning data with the calculated learning data to analyze the problems, including loading a learning model, as follows:

[0042]

[0043] 其中， L 为数据预测的差值， y 为当前节点的数据值， 为当前节点的 The average value of the data in the database, comparing and analyzing the data in the database according to the data value of the current node and by analyzing the deviation of the data, and patching and using the slightly deviated data.

[0044] Furthermore, the level-based learning module:

[0045] Level design: According to the difficulty and logical relationship of the learning content, it is divided into at least two levels, each level corresponding to a knowledge point or chapter of learning. Various learning tasks and challenges are set in each level, such as multiple-choice questions, fill-in-the-blank questions, interactive mini-games, and experimental operations; different learning paths are designed, and different levels and content are unlocked according to the user's learning achievements and choices;

[0046] Progress tracking: Display the user's current learning progress and the completed levels, and record the results of each level passed by the user, including scores, time used, and correct rates;

[0047] Feedback and rewards: After the user completes each level task, provide immediate feedback and explanations to help the user understand the mistakes and improve. Set up reward mechanisms such as points, badges, and virtual prizes to motivate the user's learning enthusiasm. According to the number and quality of levels completed by the user, upgrade their level and title to increase the sense of achievement;

[0048] Challenges and cooperation: Include setting daily or weekly learning challenges to attract users to continuously participate, providing leaderboards and competition functions. Users can have learning competitions with friends or other users, and support users to form teams to pass levels and complete tasks together to strengthen cooperation and communication;

[0049] Personalized recommendation: Include intelligently recommending suitable levels and tasks based on the user's learning progress and performance, identifying the user's weaknesses and knowledge blind spots, and recommending relevant exercises and reinforcement levels.

[0050] Furthermore, the interactive learning module includes an online classroom that provides real-time interaction. Users can communicate with other users in the forms of video, voice, and text. During the learning process, users can ask questions at any time, and the system will provide real-time answers. After users complete exercises or tasks, the system will give immediate feedback to help users understand and improve. Interactive elements such as pop-up questions, discussion areas, and notes are embedded in the video learning process to enhance users' sense of participation. A virtual laboratory is provided where users can conduct simulation experiments to enhance their practical ability and understanding. Small games related to the learning content are designed to deepen users' understanding and memory through gamification. Users can create or join study groups according to their needs to discuss and solve problems with other users.

[0051] According to another aspect of the present invention, there is provided a learning method applied to the above-mentioned interactive challenge-based knowledge learning implementation system, including:

[0052] Step 1: Content preparation. Modularize the learning content, design levels and tasks to ensure coverage of all key knowledge points, and prepare detailed task instructions and feedback information to ensure that learners can obtain immediate and useful guidance;

[0053] Step 2: Technical implementation. Develop or select a suitable learning management system that supports the level-based learning method, and use appropriate technical tools such as HTML5, JavaScript, and WebSocket to implement front-end and back-end functions;

[0054] Step 3: Testing and optimization. Conduct small-scale testing, collect feedback from learners, adjust the difficulty of levels and task design, and optimize the system performance and user experience according to the test results to ensure a smooth and efficient learning process;

[0055] Step 4: Promotion and application. Promote the challenge-based learning method to target users, provide necessary training and support, continuously monitor the system usage and learning effects, and make iterative improvements according to user feedback.

[0056] Compared with the prior art, the beneficial effects of the present invention are:

[0057] An interactive challenge-based knowledge learning method and its implementation system of the present invention output a learning knowledge base and game levels related to appropriate work safety knowledge according to the development direction of an enterprise; a virtual reality module formulates relevant scene settings according to the development direction of the enterprise and connects the scenes with the learning knowledge base and game levels; collects learning data of employees, conducts in-depth analysis and mining, and through data analysis, understands the learning progress, difficulties and weak links of participants; adopts a challenge-based mode, divides the training and learning required by the enterprise into different levels and difficulty levels, and participants improve their safety awareness by completing a series of level challenges; sets up a multi-player online competition and team collaboration interaction session to stimulate the learning interest and enthusiasm of participants, and has the effect of carrying out personalized customized knowledge competition learning for enterprise employees and realizing personalized improvement of the personal abilities of enterprise employees. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings;

[0059] Figure 1 is a framework schematic diagram of an interactive challenge-based knowledge learning implementation system of the present invention;

[0060] Figure 2 is a flow schematic diagram of a knowledge learning method based on a challenge-based mode of the present invention;

[0061] Figure 3 is a schematic diagram of the structure of a computer device in an interactive challenge-based knowledge learning implementation system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0063] As Figures 1-3 , shown, an interactive challenge-based knowledge learning implementation system includes:

[0064] A content customization module, which outputs a learning knowledge base and game levels related to appropriate work safety knowledge according to the development direction of the enterprise;

[0065] A virtual reality module, which formulates relevant scene settings according to the development direction of the enterprise and connects the scenes with the learning knowledge base and game levels, and is used to simulate the actual environment when employees learn safety knowledge;

[0066] The data analysis module collects employees' learning data, conducts in-depth analysis and mining. Through data analysis, it understands the learning progress, difficulties, and weak links of the participants, providing a basis for formulating safety training strategies;

[0067] The level-by-level learning module adopts a level-by-level mode, dividing the training and learning required by the enterprise into different levels and difficulty levels. Participants gradually master safety knowledge and improve safety awareness by completing a series of level challenges;

[0068] The interactive learning module sets up multi-person online competitions and team collaboration interaction sessions to stimulate the learning interest and enthusiasm of the participants. Through interactive learning, it promotes the communication and cooperation among the participants, and jointly improves their own technical levels.

[0069] Specifically, the content customization module includes:

[0070] Learning goal setting, including users setting short-term and long-term learning goals, such as passing a certain exam and mastering knowledge in a certain field, and providing corresponding learning plans and level recommendations according to the users' goals;

[0071] Knowledge level assessment unit, including when the user uses it for the first time, through a series of assessment tests such as multiple-choice questions and fill-in-the-blank questions, and assessing the user's current knowledge level;

[0072] According to the assessment results, the system automatically adjusts the level difficulty and content recommendations. According to the user's knowledge level and learning goals, the system generates a personalized learning path map, showing the recommended learning levels and modules, and the user adjusts the learning path according to his own needs;

[0073] Dynamic content adjustment, the system monitors the user's learning progress and task completion in real time, dynamically adjusts the content and difficulty of the levels. For the knowledge points that the user repeatedly makes mistakes on, the system provides more relevant exercises and detailed explanations;

[0074] Recommended learning resources, according to the user's learning situation and needs, the system recommends suitable learning resources, such as video tutorials, reference materials, and exercise questions, and the user selects learning resources according to his interest to improve the learning effect;

[0075] User feedback mechanism, users give feedback on the content and levels recommended by the system, and the system continuously optimizes the content recommendation algorithm according to the feedback. Users put forward the knowledge points they are interested in and the content they hope to learn, and the system will try its best to meet the users' needs;

[0076] Learning data analysis, the system analyzes the user's learning behavior data, such as learning time, correct rate, and completion rate, generates a personalized learning report, and provides detailed learning suggestions and improvement plans for the user according to the learning data.

[0077] Specifically, the content customization module further includes:

[0078] Design an intuitive user interface to facilitate users to set learning goals and view personalized learning paths;

[0079] Provide flexible content adjustment options for users to freely adjust their learning plans and level sequences;

[0080] Use AI and machine learning algorithms to analyze users' learning behaviors and feedback, and optimize content recommendations and difficulty adjustments;

[0081] Adopt RESTful API to achieve front-end and back-end data interaction and ensure the efficient operation of the system;

[0082] Use a relational database to store users' basic information and learning goals;

[0083] Use a non-relational database to store users' learning records and feedback data;

[0084] Encrypt and store user data, and adopt security authentication mechanisms such as OAuth2.0 to protect user privacy and ensure the security of user data and the system;

[0085] Help users master knowledge and improve learning effects through personalized learning paths and resource recommendations.

[0086] Specifically, the virtual reality module includes creating an immersive virtual classroom environment where users can attend virtual courses and discussions. The virtual classroom is equipped with facilities such as interactive whiteboards, virtual desks, and books to provide a real classroom experience. Create corresponding 3D scenes according to different learning contents, such as historical sites, laboratories, and observatories, where users can conduct virtual explorations and interactions to intuitively understand the learning contents. Provide a virtual laboratory where users can perform various experimental operations in a safe virtual environment, and the system provides real-time feedback to help users understand the experimental process and results. Design interactive learning tasks in the VR environment, such as puzzles and mission challenges, to increase the fun of learning. Users need to complete these tasks to pass the levels, and the system provides instant feedback and guidance.

[0087] Specifically, the data analysis module includes:

[0088] Learning data collection, collecting users' learning behavior data, including login time, learning duration, answering records, and progress in passing levels, and recording users' performances in various learning links, such as accuracy rate, error rate, and completion time;

[0089] Data processing and storage, using the ETL process to clean, transform, and store the data, and storing the processed data in a data warehouse for subsequent analysis and query;

[0090] Learning progress tracking, which can track the user's learning progress in real time, generate a learning progress report, identify the user's learning bottlenecks and difficulties through data analysis, and provide targeted learning suggestions;

[0091] Learning effect evaluation, which can evaluate the user's performance in each level and learning task, generate a learning effect report, and adjust the level difficulty and content recommendation according to the evaluation results to optimize the user's learning path;

[0092] Personalized recommendation, which can recommend personalized learning content and resources to the user based on the data analysis results, use machine learning algorithms to analyze the user's learning habits and preferences, and improve the accuracy and relevance of the recommendation;

[0093] User behavior analysis, which can analyze the user's learning behavior patterns, such as high-frequency learning time periods and learning habits, identify the behavior characteristics of different user groups, and provide a group behavior analysis report.

[0094] Specifically, the data analysis includes the user's learning data, analyzes and optimizes the data in the database through data processing. The optimization algorithm includes forms such as finding the maximum or minimum value, or minimizing costs, maximizing profits, maximizing efficiency, or finding the best parameter configuration that meets specific conditions, including linear optimization. The linear optimization calculation formula is as follows:

[0095]

[0096] Among them, x is the abscissa value of the current pattern dataset, The i point in the feasible set is expressed as a convex combination of extreme points plus a non-negative combination of extreme directions, The j point in the feasible set is expressed as a convex combination of extreme points plus a non-negative combination of extreme directions. Through linear analysis based on the convex combination of extreme points plus a non-negative combination of extreme directions of the data points in the feasible set, the ideal coordinate value at the time point of the current user's learning data is calculated.

[0097] Specifically, the data analysis includes capturing the data during the user's learning process and establishing a database, learning and calculating the data values of the user's learning through deep learning, comparing the real-time changing learning data with the calculated learning data, and analyzing the problems, including loading a learning model, as follows:

[0098]

[0099] 其中， L 为数据预测的差值， y 为当前节点的数据值， 为当前节点的The average value of the data in the database, comparing and analyzing the data in the database based on the data value of the current node and by analyzing the deviation of the data, and patching and using the data with slightly deviations.

[0100] Specifically, the level-based learning module:

[0101] Level design: According to the difficulty and logical relationship of the learning content, it is divided into at least two levels. Each level corresponds to a knowledge point or chapter of learning. Various learning tasks and challenges are set in each level, such as multiple-choice questions, fill-in-the-blank questions, interactive mini-games, and experimental operations; different learning paths are designed. According to the learning results and choices of users, different levels and content are unlocked;

[0102] Progress tracking: Display the current learning progress and the completed levels of the user, record the results of each level passed by the user, including scores, time used, and correct rates;

[0103] Feedback and rewards: After the user completes each level task, provide immediate feedback and explanations to help the user understand the mistakes and improve. Set up reward mechanisms such as points, badges, and virtual prizes to motivate the user's learning enthusiasm. According to the number and quality of levels completed by the user, upgrade their level and title to increase the sense of achievement;

[0104] Challenges and cooperation: Include setting daily or weekly learning challenges to attract users to continuously participate, providing leaderboards and competition functions. Users can have learning competitions with friends or other users, support users to form teams to pass levels and complete tasks together to strengthen cooperation and communication;

[0105] Personalized recommendation: Include intelligent recommendations of suitable levels and tasks based on the user's learning progress and performance, identify the user's weaknesses and knowledge blind spots, and recommend relevant exercises and reinforcement levels.

[0106] Specifically, the interactive learning module includes providing an online classroom for real-time interaction. Users communicate with other users in the forms of video, voice, and text. During the learning process, users can ask questions at any time, and the system will give answers in real time. After the user completes the exercises or tasks, the system will give immediate feedback to help the user understand and improve. Interactive elements are embedded in the video learning process, such as pop-up questions, discussion areas, and notes, to enhance the user's sense of participation. Provide a virtual laboratory where users can conduct simulation experiments to enhance practical ability and understanding. Design small games related to the learning content to deepen the user's understanding and memory through gamification. Users can create or join learning groups according to their needs to discuss and solve problems with other users.

[0107] According to another aspect of the present invention, there is provided a learning method applied to the above-mentioned interactive level-based knowledge learning implementation system, including:

[0108] S1: Content preparation. Modularize the learning content, design levels and tasks to ensure coverage of all key knowledge points, and prepare detailed task instructions and feedback information to ensure that learners can receive immediate and useful guidance.

[0109] S2: Technical implementation. Develop or select a suitable learning management system to support the level-based learning method, and use appropriate technical tools such as HTML5, JavaScript, and WebSocket to implement front-end and back-end functions.

[0110] S3: Testing and optimization. Conduct small-scale tests, collect feedback from learners, adjust the level difficulty and task design, and optimize the system performance and user experience based on the test results to ensure a smooth and efficient learning process.

[0111] S4: Promotion and application. Promote the level-based learning method to target users, provide necessary training and support, continuously monitor the system usage and learning effects, and make iterative improvements based on user feedback.

[0112] In one embodiment, a computer-readable storage medium is provided, storing a computer program which, when executed by a processor, implements the steps in the above-described embodiment of the knowledge learning method based on the level-based mode.

[0113] In one embodiment, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions which are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to execute the steps in the above-described embodiment of the knowledge learning method based on the level-based mode.

[0114] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0115] As a preference of this embodiment, questions are set according to the training needs of the enterprise and the types of safety accidents, and the application scenarios are combined with the questions and the game. The types of safety accidents in this embodiment include: object strike accidents, vehicle injury accidents, mechanical injury accidents, lifting injury accidents, electric shock accidents, fire accidents, scalding accidents, drowning accidents, falling from height accidents, collapse accidents, roof fall and rib spalling accidents, water inrush accidents, blasting accidents, gunpowder explosion accidents, gas explosion accidents, boiler explosion accidents, container explosion accidents, other explosion accidents, poisoning and asphyxiation accidents, other injury accidents.

[0116] As a preference of this embodiment, the safety accident application scenarios include campus safety education, family safety education, enterprise safety training, special operation training, public safety event emergency education: natural disaster response, public health event response, safety skill training: fire fighting skill training, first aid skill training, network safety education, legal education.

[0117] Preferably in this embodiment, a Convolutional Neural Network (CNN) is dedicated to processing image and visual data. Support Vector Machines (SVM) are applied to text classification and image classification. Deep reinforcement learning combines deep learning and reinforcement learning, such as Deep Q-Network (DQN) and Deep Deterministic Policy Gradient (DDPG), etc., which are applied to game AI. And as an extension of this embodiment, mathematical models are adopted: elementary models, linear algebra models, probability and statistics models, graph theory models, planning models, differential equation models, regression models, discrete models, fuzzy mathematics models, grey theory models, etc.

[0118] Common algorithms: 1. Monte Carlo algorithm; 2. Data processing algorithms such as data fitting, parameter estimation, interpolation, etc.; 3. Planning algorithms such as linear programming, integer programming, multi-objective programming, quadratic programming, etc.; 4. Graph theory algorithms; 5. Computer algorithms such as dynamic programming, backtracking search, divide-and-conquer algorithm, branch and bound, etc.; 6. Three non-classical algorithms of optimization theory: simulated annealing method, neural network algorithm, genetic algorithm; 7. Grid algorithm and exhaustive method; 8. Method for discretizing continuous data; 9. Numerical analysis algorithms; 10. Image processing algorithms.

[0119] Common software: For learning mathematical modeling, common software includes: matlab, lingo, l indo, Mathematica, Maple, Spass, and SAS, etc. Among them, Lingo and Lindo software are often used for nonlinear programming and quadratic programming to solve optimization models. Spass is often used for statistical models, and Matlab is more comprehensive and often used for programming.

[0120] The working principle of an interactive level-passing knowledge learning method and its implementation system of the present invention: Output a learning knowledge base and game levels related to appropriate work safety knowledge according to the development direction of the enterprise; the virtual reality module formulates relevant scene settings according to the development direction of the enterprise and connects the scenes with the learning knowledge base and game levels; collect the learning data of employees, conduct in-depth analysis and mining, and through data analysis, understand the learning progress, difficulties and weak links of the participants; adopt a level-passing mode, divide the training and learning required by the enterprise into different levels and difficulty levels, and the participants improve their safety awareness by completing a series of level challenges; set up a multi-player online competition and team collaboration interaction session to stimulate the learning interest and enthusiasm of the participants, and have the function of customizing personalized knowledge competitions for enterprise employees and combining with the designed game for work safety, so as to help employees learn the knowledge related to work safety while playing games and improve the weak links of enterprise employees in safety knowledge.

[0121] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only the specific embodiments. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An interactive level-breaking knowledge learning implementation system, characterized in that: include: A content customization module, which outputs appropriate game modes related to production safety knowledge according to the training needs of the enterprise and combines production safety knowledge with games; A virtual reality module, which formulates relevant scene settings according to the development direction of the enterprise and connects the scenes with the learning knowledge base and game levels, is used to simulate the actual environment when employees learn safety knowledge, and combines the application scenarios of safe production with games and virtualizes the scene mode of safe production in the game; The data analysis module collects employees’ learning data and conducts in-depth analysis and mining. Through data analysis, it understands the learning progress, difficulties and weak links of participants, and provides a basis for formulating safety training strategies; The level-breaking learning module adopts a level-breaking mode to divide the training and learning required by the enterprise into different levels and difficulty levels. Participants can gradually master safety knowledge and improve safety awareness by completing a series of level challenges; The interactive learning module sets up multi-person online competition and team collaboration interaction sessions to stimulate the learning interest and enthusiasm of participants, and through interactive learning, promote communication and cooperation among participants to jointly improve their own technical level.

2. The interactive level-breaking knowledge learning implementation system according to claim 1, characterized in that: The content customization module includes: Learning goal setting, including users setting short-term and long-term learning goals, such as passing a certain exam, mastering knowledge in a certain field, and providing corresponding learning plans and level recommendations based on the user's goals; The knowledge level assessment unit includes a series of assessment tests such as multiple-choice questions and fill-in-the-blank questions when the user uses the app for the first time, and assesses the user's current knowledge level; Based on the evaluation results, the system automatically adjusts the level difficulty and content recommendations. Based on the user's knowledge level and learning goals, the system generates a personalized learning path map, showing recommended learning levels and modules, and users can adjust the learning path according to their needs. Dynamic content adjustment: the system monitors the user's learning progress and task completion in real time, dynamically adjusts the content and difficulty of the level, and provides more relevant exercises and detailed analysis for knowledge points where users repeatedly make mistakes; Recommend learning resources. Based on the user's learning situation and needs, the system recommends suitable learning resources, such as video tutorials, reference materials, and exercises. Users can choose learning resources based on their interests to improve learning outcomes. User feedback mechanism: users provide feedback on the content and levels recommended by the system. The system continuously optimizes the content recommendation algorithm based on the feedback. Users propose the knowledge points they are interested in and the content they want to learn, and the system will try its best to meet their needs. Learning data analysis: The system analyzes users’ learning behavior data, such as learning time, accuracy, and completion, and generates personalized learning reports. Based on the learning data, the system provides users with detailed learning suggestions and improvement plans.

3. The interactive level-breaking knowledge learning implementation system according to claim 2 is characterized in that: The content customization module also includes: Design an intuitive user interface that makes it easy for users to set learning goals and view personalized learning paths; Provide flexible content adjustment options, allowing users to freely adjust learning plans and level order; Use AI and machine learning algorithms to analyze user learning behavior and feedback, and optimize content recommendations and difficulty adjustments; Adopt RESTful API to realize front-end and back-end data interaction to ensure efficient operation of the system; Use a relational database to store users’ basic information and learning goals; Use non-relational databases to store users’ learning records and feedback data; Encrypt user data for storage and protect user privacy. Use security authentication mechanisms such as OAuth2.0 to ensure the security of user data and the system. Through personalized learning paths and resource recommendations, we help users master knowledge and improve learning outcomes.

4. The interactive level-breaking knowledge learning implementation system according to claim 3 is characterized in that: The virtual reality module includes creating fire scenes, accident scenes, safe operation sites, and rescue sites. Users learn safety production knowledge in the game and create corresponding 3D scenes according to different learning contents, such as different safety-related application scenarios. Users conduct virtual exploration and interaction in these scenes to intuitively understand the learning content. Users conduct various experimental operations in a safe virtual environment. The system provides real-time feedback to help users understand the experimental process and results. Interactive learning tasks are designed in the VR environment, such as puzzles and task challenges, to increase the fun of learning. Users can pass the level only after completing these tasks. The system provides instant feedback and guidance.

5. The interactive level-breaking knowledge learning implementation system according to claim 4 is characterized in that: The data analysis module includes: Learning data collection: collects users’ learning behavior data, including login time, learning time, answer records, and level progress, and records users’ performance in each learning link, such as accuracy, error rate, and completion time; Data processing and storage: Use ETL processes to clean, transform and store data, and store the processed data in a data warehouse for subsequent analysis and query; Learning progress tracking: real-time tracking of users’ learning progress, generating learning progress reports, identifying users’ learning bottlenecks and difficulties through data analysis, and providing targeted learning suggestions; Learning effect evaluation: evaluate the user's performance in each level and learning task, generate a learning effect report, adjust the level difficulty and content recommendation based on the evaluation results, and optimize the user's learning path; Personalized recommendations: Based on data analysis results, personalized learning content and resources are recommended to users. Machine learning algorithms are used to analyze users’ learning habits and preferences to improve the accuracy and relevance of recommendations. User behavior analysis: analyze users’ learning behavior patterns, such as high-frequency learning time periods and learning habits, identify the behavioral characteristics of different user groups, and provide group behavior analysis reports.

6. The interactive level-breaking knowledge learning implementation system according to claim 5, characterized in that: The data analysis includes the user's learning data. The data in the database is analyzed and optimized through data processing. The optimization algorithm includes finding the maximum or minimum value, or minimizing costs, maximizing profits, maximizing efficiency, or finding the best parameter configuration that meets specific conditions, including linear optimization. The linear optimization calculation formula is as follows: in, x is the horizontal coordinate value of the current pattern data set, The i point in the feasible set is represented as a convex combination of the extreme points plus a non-negative combination of the extreme directions, The j point in the feasible set is represented as the convex combination of the poles plus the non-negative combination of the pole directions. Linear analysis is performed based on the convex combination of the poles of the data points in the feasible set plus the non-negative combination of the pole directions, and the ideal coordinate value of the time point of the current user's learning data is calculated.

7. The interactive level-breaking knowledge learning implementation system according to claim 6, characterized in that: The data analysis includes capturing the data in the user learning process and establishing a database, learning and calculating the data value of the user learning through deep learning, comparing the learning data that changes in real time with the calculated learning data and analyzing the problem, including carrying a learning model, as follows: 其中， L 为数据预测的差值， y 为当前节点的数据值， 为当前节点的 The average value of the data in the database is compared and analyzed based on the data value of the current node and by analyzing the data deviation, and the data with slight deviation is repaired and used.

8. The interactive level-breaking knowledge learning implementation system according to claim 6, characterized in that: The level-breaking learning module: Level design: divide the learning content into at least two levels according to its difficulty and logical relationship. Each level corresponds to a knowledge point or chapter to be learned. Set various learning tasks and challenges in each level, such as multiple-choice questions, fill-in-the-blank questions, interactive mini-games, and experimental operations. Design different learning paths to unlock different levels and content based on the user's learning outcomes and choices. Progress tracking, showing the user's current learning progress and completed levels, and recording the user's results for each level, including score, usage time, and accuracy; Feedback and rewards: After users complete each level task, they will be provided with immediate feedback and explanations to help them understand their mistakes and make improvements. Reward mechanisms such as points, badges, and virtual prizes will be set up to motivate users to learn more. Users will be upgraded to higher levels and titles based on the number and quality of levels they complete, thus increasing their sense of achievement. Challenges and cooperation, including setting daily or weekly learning challenges to attract users to participate continuously, providing leaderboards and competition functions, allowing users to compete with friends or other users in learning, supporting users to form teams to complete tasks together, and strengthening cooperation and communication; Personalized recommendations include intelligently recommending suitable levels and tasks based on the user's learning progress and performance, identifying the user's weaknesses and knowledge blind spots, and recommending relevant exercises and reinforcement levels.

9. The interactive level-breaking knowledge learning implementation system according to claim 8, characterized in that: The interactive learning module includes providing real-time interactive online classrooms where users communicate with other users through video, voice, and text. During the learning process, users can ask questions at any time and the system will provide answers in real time. After the user completes an exercise or task, the system will immediately give feedback to help the user understand and improve. Interactive elements are embedded in the video learning process, such as pop-up questions, discussion areas, and notes, to enhance user participation. A virtual laboratory is provided where users can conduct simulation experiments to enhance practical skills and understanding. Small games related to the learning content are designed to deepen users' understanding and memory through gamification. Users can create or join study groups based on their needs to discuss and solve problems with other users.

10. A learning method applied to the interactive level-breaking knowledge learning implementation system according to any one of claims 1 to 9, characterized in that it comprises: Step 1: Content preparation: modularize the learning content, design levels and tasks to ensure that all key knowledge points are covered, and prepare detailed task instructions and feedback information to ensure that learners can receive immediate and useful guidance; Step 2: Technical implementation: developing or selecting a suitable learning management system that supports the level-based learning approach and using appropriate technical tools such as HTML5, JavaScript, and WebSocket to implement front-end and back-end functions; Step 3: Testing and optimization: Conduct small-scale testing, collect learners’ feedback, adjust level difficulty and task design, and optimize system performance and user experience based on test results to ensure a smooth and efficient learning process. Step 4: Promotion and application: Promote the level-breaking learning method to target users, provide necessary training and support, continuously monitor system usage and learning outcomes, and make iterative improvements based on user feedback.

Images