Enterprise employee safety knowledge learning method based on AI intelligence and incentive mechanism

Abstract

The invention provides an enterprise employee safety knowledge learning method based on AI and an incentive mechanism. The method comprises the following steps: firstly, developing a safety knowledge learning platform by using uniapp and Node.js, and designing a recommendation system through an AI technology training model and a collaborative filtering algorithm to form an intelligent learning platform; the employees input work types after logging in, an AI model generates a safety knowledge learning graph, personalized learning is carried out through a mobile terminal, and the platform recommends related contents according to learning history and interests. Introducing an incentive mechanism, setting incentive measures such as learning milestone rewards and point ranking, and implementing positive and negative incentive according to the learning condition of the employees; the platform formulates a personalized learning plan and notifies through intelligent learning reminding in combination with learning habits of employees and social media use behaviors, and an enterprise establishes a perfect assessment mechanism and supervises the learning progress; the platform supports safe knowledge sharing and communication, a feedback mechanism is formed by using intelligent analysis, and learning results and suggestions are pushed regularly, so that a good continuous learning atmosphere is created.

Description

Technical Field

[0001] The present invention relates to a safety knowledge learning method for enterprise employees, and in particular to a learning method based on intelligent analysis and incentive mechanism. Background Art

[0002] Safety knowledge is an important factor affecting employees' unsafe behaviors. Data show that among the 861 unsafe actions and 12 types of unsafe habitual behaviors involved in coal mine fire accidents, the frequency of those related to insufficient safety knowledge is the highest, accounting for 56.0%. In addition, the occurrence of accidents is closely related to the lack of safety knowledge of employees. Therefore, insufficient safety knowledge is the common cause of all accidents. Safety knowledge is crucial for the safe production of enterprise employees. By learning safety knowledge, enterprise employees can directly and effectively improve the reserve of safety knowledge of employees and increase the mastery of safety skills of employees, thereby deepening the safety awareness of employees and effectively restraining the unsafe behaviors of employees to prevent accidents and ensure the safety of enterprise production.

[0003] Some scholars have pointed out that the key factors affecting the safety knowledge learning of enterprise employees are the lack of supervision and management, incentive mechanisms, and learning channels. In addition, the existing safety knowledge learning of enterprise employees is inseparable from traditional methods such as training courses, safety manuals, online learning platforms, safety drills, safety lectures, safety assessments, and safety culture construction. However, such methods are too cumbersome, old-fashioned, and ineffective. Therefore, a safety knowledge learning method for enterprise employees based on AI intelligence and incentive mechanisms is an integrated replacement of traditional learning methods, and it is also a learning method that makes the learning process more personalized, efficient and free, and makes enterprise supervision and management more convenient.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] The purpose of this invention is to provide a method for enterprise employee safety knowledge learning based on AI intelligence and incentive mechanism to solve the problems existing in the traditional learning process.

[0006] The objective of the present invention is achieved through the following technical solutions:

[0007] The present invention provides a method for enterprise employee safety knowledge learning based on AI intelligence and incentive mechanism. The method integrates traditional learning methods by developing a safety knowledge learning platform (such as a safety knowledge learning APP) and combines AI intelligent recognition technology and collaborative filtering algorithm to achieve personalized recommendations, intelligent learning reminders and analysis, and achieves incentives and supervision for enterprise employees' safety knowledge learning by signing in, learning safety materials, watching videos, sharing safety knowledge, and obtaining points after answering tests to form a ranking list.

[0008] The security knowledge learning method mainly includes a personal AI intelligent recognition and analysis module and an incentive mechanism module:

[0009] The personal AI intelligent recognition and analysis module includes an AI model module, a recommendation system module, an intelligent learning analysis module, and an intelligent learning reminder module, which are used to learn and analyze a large amount of safety knowledge data, extract the characteristics and laws of various safety knowledge, and then establish a personal safety knowledge recognition model. The model identifies various safety risks that individuals may face in life, work, and travel, such as accidents, traffic accidents, production accidents, etc. At the same time, AI intelligent recognition and analysis provides personalized safety knowledge and early warning information based on the actual situation of the individual, helping individuals to accurately learn the necessary safety knowledge to protect their own safety. In addition, AI technology and collaborative filtering algorithms are used to evaluate personal learning ability, analyze learning interests and learning behaviors, and provide personalized learning content recommendations. And combine the Internet of Things to regularly remind employees to learn safety knowledge and analyze employees' personal learning situation, and push learning results and learning suggestions at the end of the month and the end of the year;

[0010] The AI ​​model module is used to form and push a safety knowledge learning map according to the type of work and employee learning requirements;

[0011] The recommendation system module is used to recommend suitable learning content to employees based on their learning history, interests and hobbies;

[0012] The intelligent learning reminder module is used to select the appropriate time and method to remind employees to study according to their previous learning habits;

[0013] The intelligent learning analysis module establishes a learning analysis model based on the user's learning data, which is used to analyze the employee's learning behavior, evaluate the learning effect, and send the learning analysis results and suggestions to the employee by means of message push.

[0014] The incentive mechanism module includes a learning module, a question-answering test module, a notification and communication module, a points module, and a ranking module:

[0015] The learning module is used to provide various safety knowledge learning resources, including video cases, text materials, audio and other aspects of learning content;

[0016] The test module is used to provide functions such as exercises and simulated exams to help users test their learning outcomes and improve their learning effects;

[0017] The notification communication module is used to promote security knowledge sharing and communication interaction among users;

[0018] The points module is used for employees to obtain points through activities such as signing in, learning, answering questions, forwarding, communicating and sharing;

[0019] The ranking module is used to display the user score ranking, which is convenient for enterprise supervision and management and motivates users to actively learn.

[0020] The security knowledge learning platform (APP) consists of two parts: the front-end interface and the back-end server:

[0021] The front-end interface is developed using the uniapp front-end development framework, covering user interface design, user input validation, data display, network requests, and state management;

[0022] The back-end server is developed using the Node.js back-end framework, including data storage, business logic, interface design, AI model design, deployment and maintenance.

[0023] Compared with the existing safety learning model, this safety knowledge learning method has a broader application prospect. It can be combined with smart devices to provide more intelligent and personalized safety knowledge learning services, provide users with a better learning experience, and establish a safety early warning system through data analysis and mining, so as to timely discover safety hazards and risks and improve safety prevention capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0025] Figure 1 A flowchart of a method for learning safety knowledge for enterprise employees based on AI intelligence and incentive mechanisms is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present invention are described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention;

[0027] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments, which do not constitute a limitation of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of the present invention.

[0028] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. Figure 1The figure is a flow chart of a method for learning safety knowledge of enterprise employees based on AI intelligence and incentive mechanism provided by an embodiment of the present invention, the method comprising:

[0029] Step 1: Use the uniapp front-end development framework and the Node.js back-end framework to develop a security knowledge learning platform, train the AI ​​model through AI intelligent technology, and design a recommendation system through collaborative filtering algorithm to integrate it into the platform back-end server to form an intelligent learning platform;

[0030] In this step, it is determined that the target users are employees of various industrial and mining enterprises, and that the learning platform needs to have personalized recommendations, points mechanism, learning rankings, question testing, communication, learning path planning, learning progress tracking and other functions. Using collaborative filtering algorithms, recommend suitable learning content to users based on their learning history, industry, interests and hobbies. Intelligently generate personalized learning paths based on the user's learning goals and current level. According to the development framework, the front-end and back-end separation mode is adopted to develop the front-end interface and back-end system of the learning platform. In addition, the designed AI model and the trained recommendation model are integrated into the back-end server of the learning platform to ensure its normal operation. Finally, test whether the various functions of the learning platform are operating normally.

[0031] Step 2: After logging into the platform, employees enter their job type, and then the AI ​​intelligent model forms and pushes a safety knowledge learning map based on the job type and employee learning requirements. Employees use mobile terminals to personalize their learning, and the platform recommends appropriate learning content to employees based on their learning history, interests, and hobbies;

[0032] In this step, employees download and register for the safety knowledge learning APP, enter their own job type, and then the AI ​​intelligent platform forms and pushes a safety knowledge learning map based on the job type and personal learning requirements. The learning platform pushes learning content based on the collaborative filtering algorithm. Employees can learn anytime and anywhere through mobile terminals without being restricted by time and place, which improves the convenience and flexibility of learning. In addition, safety knowledge competitions, quiz activities and other activities are carried out through mobile terminals, allowing employees to actively participate in the interaction during learning, increasing the fun and attractiveness of learning;

[0033] In the specific implementation, after employees register and log in to the safety knowledge learning APP through mobile terminals, they enter their own types of work, and then the AI ​​intelligent platform forms and pushes safety knowledge learning maps according to the types of work. After employees intuitively understand the framework and internal logical relationship of safety knowledge through the map, they can enter the learning interface on the homepage and learn the safety knowledge required for their positions and earn points by browsing safety videos, articles, etc. Select the safety knowledge field of interest through the top navigation bar, click the search icon to quickly find the required knowledge, receive notifications from leaders at the message, and also communicate and share safety knowledge and earn points. You can view the learning points and sign in through the points interface. In my interface, you can get points by participating in answering questions and safety knowledge competitions, which increases the fun of learning. The learning platform uses collaborative filtering algorithms to design a recommendation system based on employees' learning history data to push suitable learning content.

[0034] Step 3: Introduce an incentive mechanism and set up incentives such as learning milestone rewards and learning points rankings. After completing the learning, provide positive or negative incentives based on the employee's learning situation;

[0035] In this step, the company sets clear learning goals, establishes incentive mechanisms, rewards and recognizes learning outcomes, and continuously improves the incentive mechanisms. Through the orderly implementation of these steps, it can effectively stimulate the enthusiasm and motivation of learners, improve learning outcomes and performance levels, and promote the continuous development and innovation of the organization.

[0036] In the specific implementation, employees in the same organization can join a learning group through the safety knowledge learning platform. Employees earn points by studying text materials, watching audio and video, sharing safety knowledge, and answering questions and tests. Signing in can earn 5 points, and learning a document, watching a video, answering a question correctly, and sharing a piece of safety knowledge can earn 1 point each. The total learning points per person per day is capped at 60. The total points of group members will form a points ranking list. Enterprises can evaluate employees' safety knowledge learning status by their total learning points, and use points as one of the assessment indicators for employees' promotion and salary increase. Every quarter, the group will select points experts based on the number of points, and give praise and rewards. In addition, employees can redeem gifts after reaching a certain number of points, forming learning milestone rewards. Such an incentive mechanism encourages employees to actively learn safety knowledge by watching safety materials and videos, participating in question-answering competitions, etc.

[0037] Step 4: The platform formulates a learning plan based on the employee's own situation, and uses intelligent learning reminders to remind employees to study in a personalized way based on their previous learning habits or when they watch videos on WeChat, Douyin, etc. The company then establishes a complete assessment mechanism and monitors the learning progress;

[0038] In this step, the learning platform formulates a learning plan based on the employee's own situation. For example, the average score of safety managers cannot be less than 40 points per day, and the average score of other employees cannot be less than 30 points per day; or the average score of employees with less than two years of service is required to be no less than 40 points per day, and the average score of employees with more than two years of service is required to be no less than 30 points per day. Through the daily check-in function and score ranking function of the safety knowledge learning APP, the supervision of employees' safety knowledge learning is realized. In addition, a safety question-answering test is released in the system every quarter, and sufficient resources and financial support are provided. Timely recognition and reward of learning achievements for those with high scores or excellent assessments. Negative incentives are given to employees with low scores, poor assessment results, and those who have not learned safety knowledge for more than 24 hours. Through the machine learning algorithm, the intelligent learning reminder function is developed to analyze the employees' previous learning data to remind employees to learn in a personalized time period suitable for individuals.

[0039] Step 5: Use the learning platform to share and communicate safety knowledge, and form a feedback mechanism through intelligent learning analysis to automatically push learning analysis results and suggestions at the end of the month and year, so as to establish a good continuous learning atmosphere and habitual learning habits;

[0040] When browsing classic safety knowledge materials, employees can participate in comments and discussions to earn points, and share them to study groups or other platforms to earn points. Using machine learning algorithms or data mining technology, the system can analyze employees' personal safety knowledge learning and test scores. At the end of each month and the end of the year, the system will automatically push learning analysis results and suggestions to help employees better understand their learning situation and provide further learning guidance. This personalized learning analysis and guidance method can help employees more effectively improve their safety knowledge level and enhance overall safety awareness.

[0041] From the above, it can be seen that the enterprise employee safety knowledge learning method based on AI intelligence and incentive mechanism in the embodiment of the present invention integrates the learning methods such as course training, regular assessment, safety knowledge competition, supervision and feedback, rewards and punishments in traditional learning methods, making the learning process more comprehensive and optimized. Employees can use mobile terminals to study anytime and anywhere without being restricted by time and place, which improves the convenience and flexibility of learning. And through AI intelligent recognition methods, relevant safety knowledge is pushed to the corresponding people in a targeted manner and employees are provided with intelligent learning methods. In addition, through safety knowledge competitions, answering activities, knowledge sharing and other forms, employees are allowed to actively participate in the interaction in learning, which increases the fun and attractiveness of learning. The introduction of incentive mechanisms not only stimulates employees' learning motivation, but also effectively detects employees' mastery of safety knowledge.

[0042] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for learning safety knowledge for enterprise employees based on AI intelligence and incentive mechanism, characterized in that: The method comprises: Step 1: Use the uniapp front-end development framework and the Node.js back-end framework to develop a security knowledge learning platform, train the AI ​​model through AI intelligent technology, and design a recommendation system through collaborative filtering algorithm to integrate it into the platform back-end server to form an intelligent learning platform; Step 2: After logging into the platform, employees enter their job type, and then the AI ​​intelligent model forms and pushes a safety knowledge learning map based on the job type and employee learning requirements. Employees use mobile terminals to personalize their learning, and the platform recommends appropriate learning content to employees based on their learning history, interests, and hobbies; Step 3: Introduce an incentive mechanism, set up incentives such as learning milestone rewards and learning points rankings, and provide positive or negative incentives based on employees’ learning performance after they have completed their studies; Step 4: The platform formulates a learning plan based on the employee's own situation, and uses intelligent learning reminders to remind employees to study in a personalized way based on their previous learning habits or when they watch videos on WeChat, Douyin, etc. The company then establishes a complete assessment mechanism and monitors the learning progress; Step 5: Use the learning platform to share and communicate safety knowledge, and form a feedback mechanism through intelligent learning analysis to automatically push learning analysis results and suggestions at the end of the month and the end of the year, thereby establishing a good continuous learning atmosphere and habitual learning habits.

2. According to claim 1, the enterprise employee safety knowledge learning method based on AI intelligence and incentive mechanism is characterized in that: In step 1, The target users of the safety knowledge learning platform are employees of various industrial and mining enterprises. The learning platform needs to have functions such as personalized recommendations, scoring mechanism, learning rankings, question testing, communication, learning path planning, and learning progress tracking. Based on the uniapp front-end development framework and the Node.js back-end framework, the front-end and back-end separation mode is adopted to develop the front-end interface and back-end system of the learning platform; The AI ​​model is used to form and push a safety knowledge learning map based on the type of work and employee learning requirements. First, collect relevant data such as employee job information, learning needs, and safety knowledge classification, knowledge points and other data. Then perform operations such as data extraction, encoding, standardization, and dimensionality reduction on the data, and then use a model architecture that combines CNN and LSTM / Transformer to build a model based on the specific needs of the learning platform and the data characteristics. In addition, use the prepared data to train the deep learning model, and then deploy the evaluated and optimized model to the learning platform; The recommendation system is used to recommend suitable learning content to employees based on their learning history, interests and hobbies. First, the user's historical behavior data is collected, including the user's clicks on knowledge points, viewing time, forwarding and sharing, collection and other information. The data is then converted into a user-knowledge point rating matrix, and the similarity is calculated using the cosine similarity calculation method. Secondly, based on the user's historical behavior data and the similarity calculation results, a collaborative filtering algorithm is used to generate recommendation results to recommend knowledge points that are relevant to the user or may be of interest to the user; The intelligent learning platform forms an intelligent learning platform by training the AI ​​model through AI intelligent technology and designing the recommendation system through collaborative filtering algorithm and integrating it into the back-end server of the security knowledge learning platform.

3. According to claim 1, the enterprise employee safety knowledge learning method based on AI intelligence and incentive mechanism is characterized in that: In step 2, After employees register and log in to the safety knowledge learning APP through mobile terminals, they enter their own types of work, and then the AI ​​intelligent platform forms and pushes safety knowledge learning maps based on the types of work. After employees intuitively understand the framework and internal logical relationship of safety knowledge through the map, they can enter the learning interface on the homepage and learn the safety knowledge required for their positions and obtain points by browsing safety videos, articles, etc. Select the safety knowledge field of interest through the top navigation bar, click the search icon to quickly find the required knowledge, and receive notifications from leaders on the information interface. At the same time, you can also communicate and share safety knowledge and obtain points. You can view the learning points and sign in through the points interface. In my interface, you can get points by participating in answering questions and safety knowledge competitions, which increases the fun of learning. Finally, the learning platform uses collaborative filtering algorithms to design a recommendation system based on employees' learning history data to push suitable learning content. The security knowledge learning graph first determines the subject and scope of the knowledge graph, clarifies the required security field knowledge, and then collects and extracts relevant data from multiple sources (such as literature, network, expert knowledge, etc.); then, nodes and edges are constructed through natural language processing technologies such as entity recognition and relationship extraction to form a preliminary graph; then, ontology design is used to define concept levels and rules to ensure the structuring and semantic clarity of the graph.

4. According to claim 1, the enterprise employee safety knowledge learning method based on AI intelligence and incentive mechanism is characterized in that: In step 3, Employees in the same organization join a learning group through the safety knowledge learning platform. Employees can earn points by learning text materials, watching audio and video, and answering questions on the platform. The platform limits each sign-in to 5 points, and 1 point is earned for learning one material, watching one video, and answering one question. The platform limits the total learning points of each person to 60 points per day. The total points earned by group members through learning form the total points ranking and the annual points ranking. The company evaluates the safety knowledge learning of employees by the total points they have learned, and uses the total points as an assessment requirement for employees to be promoted and have their salaries increased. In addition, the group selects points masters every quarter based on the points, and gives them certain praise and rewards. In addition, when the learning points reach a certain amount, they can be exchanged for gifts to form learning milestone rewards, thereby motivating employees to continue to actively learn safety knowledge by watching relevant safety materials and videos, answering questions, and so on.

5. According to claim 1, the enterprise employee safety knowledge learning method based on AI intelligence and incentive mechanism is characterized in that: In step 4, The learning platform formulates learning plans based on the employees' own situations, and formulates different learning schedules for different types of employees. Then, through the daily sign-in and points ranking functions of the safety knowledge learning APP, effective supervision of employees' safety knowledge learning is achieved, and negative incentives are implemented for employees who have not conducted safety knowledge learning for more than 24 hours. Every quarter, the system will issue a safety question-answering test and provide necessary resources and financial support. Timely recognition and rewards will be given to those with outstanding performance, and negative incentives will be given to those with low points or poor performance. Set learning plans and schedules in conjunction with the learning APP, and use the gradient boosting tree to analyze employees' previous learning data to develop an intelligent learning reminder function to remind employees to study in a personalized time period that suits them; The learning plan formulation is that the learning platform formulates different learning plans for employees with different cultural levels, different positions, and length of service. In the back-end system of the learning platform, a variety of learning plans are formulated according to different cultural levels, positions, and length of service. These learning plans can include different courses, training content, learning goals, etc. Next, the employee enters the "My" interface, clicks the "Settings" button, and then clicks the "Personal Information" interface to fill in his or her relevant information such as length of service, rank, cultural level, etc. The back-end system of the learning platform automatically matches learning plans suitable for employees based on the personal information filled in by the employees. This can be achieved through a collaborative filtering algorithm, which matches the employee's information and the requirements of the learning plan. Employees can view the personalized learning plans formulated for them on the personal interface and choose to accept or reject them. If the employee accepts the learning plan, the system will automatically arrange the relevant training plan; The intelligent learning reminder first uses the application of the learning platform to set up a background monitoring system to monitor employees' application usage, including the applications opened and the duration of use. When employees are detected to be using Douyin or WeChat during work, the learning reminder function is triggered, and a reminder window or notification pops up to prompt employees to learn safety knowledge. The learning platform then collects employees' learning data, such as learning time, learning content, and learning progress, to help the software better understand employees' learning habits and needs, thereby providing a more intelligent learning reminder service. Based on employees’ learning habits and needs, sequence prediction algorithms are used to determine when to send reminders, the content of the reminders, and the method of reminders.

6. According to claim 1, the enterprise employee safety knowledge learning method based on AI intelligence and incentive mechanism is characterized in that: In step 5, when browsing classic safety knowledge materials, employees can participate in comments and discussions to earn points, and share to study groups or other platforms to earn points rewards. Through the K-means clustering algorithm, the system can analyze employees' personal safety knowledge learning and test scores. At the end of each month and the end of the year, the system will automatically push learning analysis results and suggestions to help employees better understand their own learning situation and provide further learning guidance. This personalized learning analysis and guidance method can help employees more effectively improve their safety knowledge level and enhance overall safety awareness; The intelligent learning analysis uses the K-means clustering algorithm to establish a learning analysis model based on the user's learning data to analyze the user's learning behavior and evaluate the learning effect. The learning analysis results and suggestions are sent to the user through message push and personalized learning suggestions are sent to the user through the message notification function of the learning software; The automatic push function can be implemented by using the API of the push service provider. First, select a push service provider, such as Firebase CloudMessaging (FCM) or OneSignal. Then integrate the SDK in the backend of the security knowledge learning platform and configure the application to receive and process push notifications.

Images