Method and system for carrying out safety training by utilizing behavior data of exerciser

Abstract

The invention discloses a method and system for performing safety training by using behavior data of an active person, and the method comprises a real-time behavior monitoring step: monitoring the operation behavior of the active person in real time through a sensor, a camera and other devices, capturing a potential safety risk point, deeply analyzing the behavior data by using big data and a machine learning technology, and carrying out the real-time behavior monitoring. And the safety risk identification mode is used for collecting behavior data of the exerciser in real time, transmitting and processing the behavior data, and providing personalized safety training contents and schemes for the exerciser. All the modules cooperate with one another, and all-around safety training services are provided for students together. For example, the community interaction and learning module can obtain information from other modules and recommend related communities and topics to students; the early warning and reminding mechanism module gives out early warning based on the real-time behavior monitoring and behavior data analysis result, and the safety of the activity person is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of cultural information management systems, and particularly relates to a method and a system for security training using the behavior data of actors. Background Art

[0002] In today's society, safety issues are of crucial importance in both industrial production, business activities and daily life. With the continuous development of technology and the increasing diversification of various activities, safety risks have become more complex and unpredictable. Traditional safety training methods often adopt general teaching materials and teaching methods, lacking pertinence and personalization, and it is difficult to meet the actual needs of different actors. The disadvantages of traditional safety training methods are mainly reflected in the following aspects: (1) Lack of pertinence. Traditional safety training usually adopts a one-size-fits-all approach, providing the same training content to all trainees. However, different actors may face different safety risks in different scenarios. For example, in industrial production, the safety risks faced by workers in different positions vary greatly. Some may mainly face mechanical operation risks, while others may be more likely to face chemical substance leakage risks. If general training content is adopted, it is impossible to effectively train each actor for their specific risk points. (2) Single training method. Most traditional safety training adopts the method of classroom lectures, where trainees passively receive knowledge, lacking interactivity and participation. This method is likely to make trainees feel bored, reducing their learning interest and effect. Moreover, pure theoretical explanations are difficult for trainees to truly understand and master safety knowledge, and they may not be able to apply it correctly in actual operations. (3) Difficult to evaluate the effect. Traditional safety training often lacks effective evaluation means and it is difficult to determine whether trainees have truly mastered safety knowledge and skills. Usually, only simple examinations or questionnaires are used to evaluate the training effect, and this method cannot comprehensively and accurately reflect the actual learning situation of trainees. Moreover, due to the lack of a continuous evaluation and feedback mechanism, it is impossible to timely adjust the training content and methods to improve the training effect. (4) Unable to monitor behaviors in real time. Traditional safety training mainly focuses on the imparting of knowledge and cannot monitor the actual behaviors of actors in real time. In actual work and life, the behaviors of actors are important sources of safety risks. If unsafe behaviors cannot be discovered and corrected in a timely manner, safety accidents may occur. (5) Knowledge update is not timely. Safety knowledge and technologies are constantly developing and changing, and traditional safety training often fails to update the training content in a timely manner, resulting in the knowledge learned by trainees may be outdated. For example, with the emergence of new safety threats and the progress of safety technologies, old safety knowledge and protection measures may no longer be applicable, and there is an urgent need for an innovative method to improve the performance of multi-dimensional pattern classification in cultural education. Summary of the Invention

[0003] The present invention provides a method and a system for safety training using the behavior data of actors. The innovative safety training method monitors the behavior of actors in real time, analyzes the behavior data by using big data and machine learning technologies, identifies safety risk points, and tailors personalized safety training content and programs for actors to improve safety awareness and protection capabilities.

[0004] The system includes:

[0005] (I) Real-time behavior monitoring module

[0006] 1. Components: Devices such as sensors and cameras, as well as behavior recognition algorithms.

[0007] 2. Main functions: Real-time collection of the behavior data of actors, and analysis and identification of different behavior patterns through behavior recognition algorithms.

[0008] (II) Behavior data analysis engine module

[0009] 1. Components: Big data analysis platform, clustering algorithms, classification algorithms, regression algorithms.

[0010] 2. Main functions: Storage, processing, and analysis of behavior data, finding out potential safety risk points and predicting the probability of safety accidents.

[0011] (III) Personalized training program design module

[0012] 1. Components: Intelligent recommendation algorithms.

[0013] 2. Main functions: Recommend suitable training content and difficulty according to the behavior analysis results and the personal information of actors.

[0014] (IV) Interactive training experience module

[0015] 1. Components: Virtual reality (VR), augmented reality (AR) technologies, gamification algorithms, scenario-based algorithms.

[0016] 2. Main functions: Build interactive training scenarios to improve the participation and learning effects of trainees.

[0017] (V) Training effect evaluation module

[0018] 1. Components: Online test platform, evaluation index system, data analysis algorithms.

[0019] 2. Main functions: Evaluate the training effect through pre-tests and post-tests and online tests, and adjust the training content and methods.

[0020] (VI) Safety knowledge base construction module

[0021] 1. Components: Knowledge Base Management System, Knowledge Classification Algorithm, Knowledge Update Algorithm.

[0022] 2. Main Functions: Establish and manage a security knowledge base, provide learning resources and update them regularly.

[0023] (VII) Early Warning and Reminder Mechanism Module

[0024] 1. Components: Early Warning System, Risk Early Warning Algorithm, Early Warning Information Sending Algorithm.

[0025] 2. Main Functions: Monitor high-risk behaviors and send early warning information in a timely manner.

[0026] (VIII) Cross-Platform Support Module

[0027] 1. Components: Responsive Design Technology, Mobile Application Development Framework.

[0028] 2. Main Functions: Support multiple platforms to facilitate learners to study anytime and anywhere.

[0029] (IX) Community Interaction and Learning Module

[0030] 1. Components: Social Network Platform or Learning Community Management System, Community Recommendation Algorithm, Topic Popularity Algorithm.

[0031] Main Functions: Establish a learning community to promote communication and interaction among learners.

[0032] (X) Continuous Update and Optimization Module

[0033] Components: Update Strategy Algorithm, System Optimization Algorithm.

[0034] Main Functions: Regularly update training content and security knowledge base, and optimize the training system.

[0035] The method is as follows: The behavior data collected by the real-time behavior monitoring module is transmitted to the behavior data analysis engine module, providing the data basis for its analysis. The analysis results of the behavior data analysis engine module are passed to the personalized training plan design module for formulating a personalized training plan. The output of the personalized training plan design module serves as the input of the interactive training experience module, providing specific training content for the trainees. The performance data of the trainees in the interactive training experience module is fed back to the training effect evaluation module for effect evaluation. The results of the training effect evaluation module are used on the one hand to adjust the personalized training plan design module and the interactive training experience module, and on the other hand to be fed back to the continuous update and optimization module. The security knowledge base construction module provides knowledge resource support for each training module. The warning and reminder mechanism module issues a warning to the actors based on the results of the real-time behavior monitoring module and the behavior data analysis engine module. The cross-platform support module ensures that trainees can access each training module on different devices. The community interaction and learning module cooperates with other modules to provide a platform for trainees to communicate and interact, and can also obtain information from other modules, such as recommending relevant communities and topics according to the training content.

[0036] The present invention has the following beneficial effects:

[0037] I. Technical innovation

[0038] 1. Application of deep belief network: The deep belief network (DBN) model is introduced into the behavior data analysis engine module for security risk pattern recognition. The DBN can automatically learn the feature representation of behavior data. Compared with traditional methods, it can more effectively mine complex patterns in the data, improving the accuracy and efficiency of security risk identification.

[0039] 2. Multi-module algorithm fusion: Each module adopts a variety of advanced algorithms and models, such as the hidden Markov model and principal component analysis in the real-time behavior monitoring module; the ant colony algorithm and genetic algorithm in the personalized training plan design module; the reinforcement learning algorithm and generative adversarial network in the interactive training experience module, etc. Different algorithms cooperate in different modules, providing more powerful functional support for the security training system.

[0040] 3. Incremental learning and simulated annealing: The continuous update and optimization module adopts the incremental learning algorithm and the simulated annealing algorithm. Incremental learning can quickly update the model according to new data, improving the adaptability of the system; the simulated annealing algorithm is used to optimize the system parameters, enhancing the system performance and user experience.

[0041] II. Functional innovation

[0042] 1. Personalized Training Plan: The personalized training plan design module customizes the safety training content and difficulty for the actor according to the behavior analysis results and the actor's personal information by using intelligent recommendation algorithms. This personalized training plan can better meet the specific needs of the actor and improve the training effect.

[0043] 2. Interactive Training Experience: The interactive training experience module adopts interactive training methods such as gamification and scenario-based training. For example, it uses virtual reality (VR) and augmented reality (AR) technologies to construct training scenarios, and enables trainees to learn safety knowledge and skills through interactive learning with the reinforcement learning algorithm. This method improves the trainees' participation and learning interest, making the training more vivid and effective.

[0044] 3. Early Warning and Reminder Mechanism: The early warning and reminder mechanism module can timely warn of high-risk behaviors and remind the actor to pay attention to safety. By real-time monitoring of behavior data, combined with risk warning algorithms and warning information sending algorithms, it ensures that the actor can take timely measures to avoid safety accidents.

[0045] 4. Cross-Platform Support and Community Interaction: The cross-platform support module ensures that trainees can access training content on different devices, improving the convenience and flexibility of learning. The community interaction and learning module establishes a learning community, encourages trainees to share experiences and learn from each other, provides a platform for trainees to communicate and interact, and further improves the learning effect.

[0046] III. Process Innovation

[0047] 1. Closed-Loop Feedback System: The entire safety training system forms a closed-loop feedback system. From real-time behavior monitoring to behavior data analysis, to personalized training plan design, interactive training experience, and training effect evaluation, each module is interconnected and mutually feedback. According to the training effect evaluation results, continuously adjust the training content and methods, and at the same time continuously update and optimize the system to ensure that the system always operates efficiently.

[0048] 2. Knowledge Resource Support: The safety knowledge base construction module provides comprehensive and systematic safety knowledge learning resources for each training module. Through knowledge classification algorithms and knowledge update algorithms, it ensures the timeliness and accuracy of knowledge, providing rich learning materials for trainees.

[0049] 3. Multi-Module Cooperative Coordination: Each module cooperates with each other to jointly provide all-round safety training services for trainees. For example, the community interaction and learning module can obtain information from other modules to recommend relevant communities and topics for trainees; the early warning and reminder mechanism module issues warnings based on real-time behavior monitoring and behavior data analysis results to ensure the safety of the actor. Description of the Drawings

[0050] Figure 1 System principle flowchart; Specific implementation manners

[0051] The following further describes in detail the implementation manners of the present invention in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0052] Embodiment 1

[0053] Detailed Introduction of Each Module, Introduction of Algorithm Model and Parameter Definition (I) Real-time Behavior Monitoring Module 1. Function Description: Real-time monitoring of the operator's operation behaviors, including operations in the workplace, behaviors in daily life, etc. Collect behavior data through devices such as sensors and cameras, and perform real-time transmission and processing. 2. Technical Implementation: Adopt Internet of Things technology, deploy sensors in the operator's working environment or on the operator's body to collect behavior data in real time. For example, an acceleration sensor can be used to monitor the amplitude and frequency of a worker's movements, and a camera can be used to monitor the operation specifications in the workplace. 3. Algorithm Model: Behavior recognition algorithm, which analyzes the collected behavior data to identify different behavior patterns. For example, deep learning algorithms can be used to analyze video data to identify whether the operation actions of workers are standardized. 4. Parameter Definition: Behavior data collection frequency: Represents the frequency at which the sensor collects behavior data, with the unit of Hertz (Hz). The higher the collection frequency, the more accurate the monitoring of behaviors, but at the same time, it will increase the difficulty and cost of data processing. Behavior recognition accuracy: Represents the recognition accuracy of the behavior recognition algorithm for different behavior patterns, usually expressed as a percentage. The higher the accuracy, the more accurate the capture of safety risk points. (II) Behavior Data Analysis Engine Module 1. Function Description: Utilize big data and machine learning technologies to deeply analyze behavior data and identify safety risk patterns. Through the analysis of a large amount of behavior data, find potential safety risk points and predict possible safety accidents. 2. Technical Implementation: Adopt a big data analysis platform to store, process, and analyze the collected behavior data. Use machine learning algorithms to establish a safety risk prediction model to classify and predict behavior data. 3. Algorithm Model: Clustering algorithm: Perform clustering analysis on behavior data to find different behavior patterns and safety risk types. For example, the K-Means clustering algorithm can be used to classify the operation behaviors of workers into different categories such as standard operations, potential risk operations, and violation operations. Classification algorithm: Classify behavior data to determine whether there are safety risks in the behavior. For example, the support vector machine (SVM) algorithm can be used to classify the operation behaviors of workers to determine whether there is a risk of mechanical injury. Regression algorithm: Predict the probability of a safety accident occurring. For example, a linear regression algorithm can be used to predict the probability of a safety accident based on behavior data. 4. Parameter Definition: Number of clusters: Represents the number of clusters in the clustering algorithm, usually adjusted according to the actual situation. The more clusters there are, the more detailed the division of behavior patterns, but it will also increase the computational complexity. Classification accuracy: Represents the accuracy of the classification algorithm in classifying behavior data, usually expressed as a percentage. The higher the accuracy, the more accurate the judgment of safety risks. Regression model error: Represents the error of the regression algorithm in predicting the probability of a safety accident occurring, usually expressed as the root mean square error (RMSE). The smaller the error, the more accurate the prediction result.(3) Personalized Training Program Design Module 1. Function Description: Based on the behavior analysis results, customize the safety training content and difficulty for the participants. According to the specific safety risk points and learning abilities of the participants, develop a personalized training program to improve the training effect. 2. Technical Implementation: Adopt intelligent recommendation algorithms. Based on the behavior analysis results and the personal information of the participants, recommend suitable training content and difficulty. For example, collaborative filtering algorithms can be used to recommend training content for the current participant according to the training records of other participants with similar safety risk points. 3. Algorithm Model: Intelligent Recommendation Algorithm: Based on the behavior data and personal information of the participants, recommend suitable training content and difficulty. For example, content-based recommendation algorithms can be used to recommend relevant training courses according to the safety risk points of the participants; collaborative filtering algorithms can also be used to recommend training content according to the training records of other participants with similar safety risk points. 4. Parameter Definition: Recommendation Accuracy: Represents the degree of compliance between the training content recommended by the intelligent recommendation algorithm and the actual needs of the participants, usually expressed as a percentage. The higher the accuracy, the better the effect of the personalized training program. (4) Interactive Training Experience Module 1. Function Description: Adopt interactive training methods such as gamification and scenario-based training to improve the participation and learning effect of the trainees. By simulating actual scenarios, let the trainees learn safety knowledge and skills in interaction, and improve the learning interest and effect. 2. Technical Implementation: Adopt technologies such as virtual reality (VR) and augmented reality (AR) to build an interactive training scenario. For example, VR technology can be used to simulate safety accident scenarios in industrial production sites, allowing trainees to learn how to deal with safety accidents in a virtual environment. 3. Algorithm Model: Gamification Algorithm: Design safety training content in the form of games, and improve the participation and learning effect of trainees by setting up levels, rewards and other mechanisms. For example, game engines can be used to develop safety training games, allowing trainees to learn safety knowledge and skills in the games. Scenario-based Algorithm: According to different safety risk scenarios, design corresponding training content and interaction methods. For example, AR technology can be used to overlay safety prompt information in the actual workplace, allowing trainees to learn safety knowledge in the actual scenario. 4. Parameter Definition: Game Difficulty Coefficient: Represents the difficulty level of the safety training game, usually adjusted according to the learning progress and ability of the trainees. The higher the difficulty coefficient, the greater the challenge of the game, but it may also reduce the participation of the trainees. Scenario Restoration Degree: Represents the degree of restoration of the interactive training scenario to the actual safety risk scenario, usually expressed as a percentage. The higher the restoration degree, the better the learning effect of the trainees in the interaction. (5) Training Effect Evaluation Module 1. Function Description: Evaluate the training effect through pre-and post-tests, online tests, etc., and continuously optimize the training program. By testing the safety knowledge and skill levels of the trainees before and after training, and analyzing the participation and feedback of the trainees during the training process, evaluate the training effect, and adjust the training content and methods according to the evaluation results.2. Technical implementation: An online testing platform is adopted to conduct pre-tests and post-tests as well as online tests for trainees. The test scores and feedback information of trainees are collected for data analysis and evaluation. 3. Algorithm model: Evaluation index system: A scientific evaluation index system is established, including indicators such as knowledge mastery, skill level, participation, and satisfaction. Through the quantitative evaluation of these indicators, the training effect can be comprehensively and accurately reflected. Data analysis algorithm: Analyze the test scores and feedback information of trainees to identify problems and deficiencies in the training. For example, statistical analysis algorithms can be used to analyze the test scores of trainees to find out their weak links; text analysis algorithms can also be used to analyze the feedback information of trainees to understand their needs and opinions. 4. Parameter definition: Evaluation index weight: It represents the importance of each index in the evaluation index system and is usually adjusted according to the actual situation. The higher the weight, the greater the impact of the index in the evaluation. Data analysis accuracy rate: It represents the accuracy rate of the data analysis algorithm in analyzing the test scores and feedback information of trainees, usually expressed as a percentage. The higher the accuracy rate, the more accurate the evaluation of the training effect. (VI) Safety knowledge base construction module 1. Function description: Build a rich safety knowledge base covering various security threats and protection measures. Provide trainees with comprehensive and systematic safety knowledge learning resources for them to consult and learn at any time. 2. Technical implementation: Adopt a knowledge base management system to classify, store, and manage safety knowledge. Regularly update the safety knowledge base to ensure the timeliness and accuracy of the knowledge. 3. Algorithm model: Knowledge classification algorithm: Classify safety knowledge to facilitate trainees' search and learning. For example, it can be classified according to security risk types, industry fields, etc. Knowledge update algorithm: Regularly collect new safety knowledge and technologies from various channels to update the safety knowledge base. For example, web crawler technology can be used to collect new safety knowledge from relevant websites. 4. Parameter definition: Number of knowledge classifications: It represents the number of knowledge classifications in the safety knowledge base and is usually adjusted according to the actual situation. The more classifications, the more detailed the management of safety knowledge, but it will also increase the difficulty of searching and learning. Knowledge update frequency: It represents the frequency of updating the safety knowledge base, with the unit of time period (such as days, weeks, months, etc.). The higher the update frequency, the stronger the timeliness of the safety knowledge base. (VII) Early warning and reminder mechanism module 1. Function description: For behaviors with high risks, give early warnings in a timely manner and remind the actors to pay attention to safety. By real-time monitoring the behaviors of actors, when high-risk behaviors are found, early warning information is sent out in a timely manner to remind the actors to take measures to avoid safety accidents. 2. Technical implementation: Adopt an early warning system to monitor and analyze the behaviors of actors in real time. When high-risk behaviors are found, send early warning information to the actors via text messages, emails, APP push, etc. 3. Algorithm model: Risk early warning algorithm: According to the results of behavioral data analysis, judge whether the behavior has high risks. For example, risk thresholds can be set, and when the behavioral data exceeds the threshold, it is judged as a high-risk behavior.Early warning information sending algorithm: Select an appropriate method to send early warning information according to the contact information and preferences of the actor. For example, according to the actor's mobile phone settings, choose to send early warning information by text message or APP push.

[0054] 4. Parameter Definitions: Risk Threshold: Represents the standard for judging high-risk behaviors, usually adjusted according to the actual situation. The higher the threshold, the stricter the judgment of high-risk behaviors. Success Rate of Sending Warning Messages: Represents the proportion of successfully sent warning messages, usually expressed as a percentage. The higher the success rate, the greater the likelihood that the participants will receive the warning messages. (VIII) Cross-Platform Support Module 1. Function Description: Supports multiple platforms such as PCs and mobile devices, facilitating students to learn anytime and anywhere. Regardless of the device used by the students, they can conveniently access the safety training content, improving the convenience and flexibility of learning. 2. Technical Implementation: Adopts responsive design technology to enable the safety training system to adapt to different device screen sizes and operating systems. Develops mobile applications to facilitate students to learn on mobile devices. 3. Algorithm Models: Responsive Design Algorithm: Automatically adjusts the page layout and display effects according to the screen sizes and resolutions of different devices. For example, media query technology can be used to adjust the page layout according to the screen width of the device. Mobile Application Development Framework: Selects a suitable mobile application development framework to develop the safety training mobile application. For example, the Flutter framework can be used to develop cross-platform mobile applications. 4. Parameter Definitions: Responsive Design Compatibility: Represents the compatibility degree of responsive design with different devices, usually expressed as a percentage. The higher the compatibility, the better the display effect of the safety training system on different devices. Mobile Application Performance Metrics: Include metrics such as startup time, response speed, and memory occupancy, which are used to measure the performance of mobile applications. The better the metrics, the better the learning experience of students on mobile devices. (IX) Community Interaction and Learning Module 1. Function Description: Establishes a learning community to encourage students to share experiences and learn from each other. Through community interaction, students can exchange learning experiences, solve problems, and make progress together, improving the learning effect. 2. Technical Implementation: Adopts a social networking platform or a dedicated learning community management system to establish a safety training learning community. Provides functions such as forums, Q&A, and group discussions to facilitate communication and interaction among students. 3. Algorithm Models: Community Recommendation Algorithm: Recommends relevant communities and topics according to the interests and learning needs of students. For example, collaborative filtering algorithms can be used to recommend suitable communities and topics based on the learning records and interests of students. Topic Popularity Algorithm: Calculates the popularity of different topics in the community to facilitate students to understand popular topics and focus of attention. For example, the popularity of topics can be calculated based on indicators such as the number of discussions, likes, and replies of the topics. 4. Parameter Definitions: Community Activity: Represents the activity level of the learning community, usually measured by indicators such as the number of participants, the number of discussions, and the number of posts. The higher the activity, the better the interaction and learning effect among students. Topic Popularity Weight: Represents the weight of different indicators in the topic popularity algorithm, usually adjusted according to the actual situation. The higher the weight, the greater the influence of this indicator in the calculation of topic popularity.(10) Continuous Update and Optimization Module 1. Function Description: Regularly update training content and safety knowledge base to maintain the timeliness and forward-looking of training content. As safety knowledge and technologies continue to develop, update training content and safety knowledge base in a timely manner to ensure that the knowledge and skills learned by trainees are always up-to-date. 2. Technical Implementation: Establish an update mechanism to regularly collect new safety knowledge and technologies and update training content and safety knowledge base. At the same time, optimize and improve the training system based on trainees' feedback and evaluation results. 3. Algorithm Model: Update Strategy Algorithm: Develop a reasonable update strategy to determine the update frequency, content, and method. For example, the update frequency of different content can be determined according to the update speed and importance of safety knowledge. System Optimization Algorithm: Optimize the functions, performance, and user experience of the training system based on trainees' feedback and evaluation results. For example, improve the design of interactive training scenarios according to trainees' feedback; or optimize algorithms and data structures based on system performance indicators to improve the operation efficiency of the system. 4. Parameter Definition: Update Frequency: Represents the frequency of updating training content and safety knowledge base, with the unit of time period (such as days, weeks, months, etc.). The higher the update frequency, the stronger the timeliness of training content. System Optimization Metrics: Include metrics such as response time, throughput, and resource utilization to measure the effect of system optimization. The better the metrics, the better the performance and user experience of the training system.

[0055] Example 2

[0056] Synergistic experiment comparison: To verify the effectiveness of the method, system, and program for safety training using actors' behavior data, a series of synergistic experiment comparisons were conducted.

[0057] (1) Experiment Design 1. Select two groups of actors, one group using traditional safety training methods and the other group using the safety training method of the present invention. 2. Conduct the same safety knowledge and skills test on both groups of actors as the pre-test. 3. Conduct safety training on both groups of actors separately. The traditional group uses general teaching materials and teaching methods, and the invention group uses the method, device, and program for safety training using actors' behavior data. 4. After the training, conduct the same safety knowledge and skills test on both groups of actors as the post-test. 5. Compare the improvement of the scores of both groups of actors in the pre-test and post-test, as well as indicators such as participation and satisfaction during the training process.

[0058] (2) Test Results 1. In terms of performance improvement, the average performance improvement of the inventors group is significantly higher than that of the traditional group. Through behavioral data analysis and personalized training, the inventors group can learn safety knowledge and skills more targeted, improving the learning effect. 2. In terms of participation, the participation of the inventors group is significantly higher than that of the traditional group. Interactive training experiences and community interactive learning methods have improved the learning interest and participation of the trainees. 3. In terms of satisfaction, the satisfaction of the inventors group is also significantly higher than that of the traditional group. Personalized training programs and timely warning reminder mechanisms have enabled the participants to feel a better learning experience and safety guarantee.

[0059] The embodiments of the present invention are given for purposes of illustration and description, and are not exhaustive or limit the invention to the disclosed form. Many modifications and variations are obvious to those of ordinary skill in the art. The embodiments are chosen and described in order to better explain the principles of the invention and its practical application, and to enable those of ordinary skill in the art to understand the invention and design various embodiments with various modifications suitable for a particular purpose.

Claims

1. A method for safety training using actor behavior data, characterized in that: It includes real-time behavior monitoring steps, which uses sensors, cameras and other equipment to monitor the participants' operating behaviors in real time and capture potential safety risk points.

2. The safety training method according to claim 1, characterized in that: It also includes a behavioral data analysis step, which uses big data and machine learning technology to deeply analyze behavioral data and identify security risk patterns.

3. A device for conducting safety training using participant behavior data, characterized in that: It contains a real-time behavior monitoring module, which is used to collect, transmit and process the behavior data of the participants in real time.

4. The safety training device according to claim 3, characterized in that: There is also a behavioral data analysis engine module that uses machine learning algorithms to analyze behavioral data and identify security risk points.

5. A method for safety training using actor behavior data, characterized in that: It can realize real-time behavior monitoring and behavior data analysis functions, and provide personalized safety training content and plans for participants.

6. The method according to claim 5, characterized in that It includes a personalized training program design function, which can tailor the safety training content and difficulty for participants based on the results of behavioral analysis.

7. A method, device and program for safety training using actor behavior data, characterized in that: It has an interactive training experience function and adopts interactive training methods such as gamification and scenario-based training to improve student participation and learning effects.

8. The safety training method, device and program according to claim 7, characterized in that: It includes a training effectiveness evaluation function, which evaluates the training effect through pre- and post-tests, online tests, etc., and continuously optimizes the training plan.

Images