A management method for education and training information and related equipment

Abstract

The present invention provides a management method and related equipment for education and training information, which are applied to the field of data processing technology. The present application processes target user information to generate physiological parameter information of the target user; processes target class information to generate preset course information; processes preset course information and physiological parameter information of the target user based on a teaching hierarchical management model to generate course adjustment information; processes teaching purpose information matching the target class information and physiological parameter information of the target user based on a teaching hierarchical management model to generate course matching influence factors; processes target user information based on course adjustment information and course matching influence factors to generate course information of the target user; processes the course information of the target user and the authority level information of the target user to generate training warning information of the target user.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a management method for education and training information and related equipment. Background Art

[0002] In the traditional education and training model, teaching arrangements often lack precision and personalization. Usually, a unified curriculum setting and teaching progress are adopted, which is difficult to meet the diverse needs of different students. For example, in internal training of enterprises or large training institutions, facing many students with different knowledge backgrounds, learning abilities and interests, it is impossible to provide targeted training content according to individual differences. This leads to some students feeling that the course is too simple or difficult, and they cannot give full play to their learning potential, affecting the overall training effect. Although some training venues may conduct simple attendance records, there is a lack of effective monitoring methods for the actual learning status of students in class, such as concentration, emotional changes, and the degree of match between physiological status and course content. This makes it impossible for teachers to understand students' learning feelings and difficulties in a timely manner, and it is difficult to make timely adjustments during the teaching process, thus affecting the improvement of teaching quality. Environmental factors in the classroom, such as temperature, humidity, noise, etc., may interfere with students' learning attention and comfort, thereby affecting learning efficiency. However, there is currently a lack of effective methods to quantify the relationship between environmental factors and course content and student status, and it is impossible to optimize teaching arrangements according to environmental changes.

[0003] During the training process, the evaluation of trainees' learning outcomes often relies on periodic examinations or project completion, and the evaluation method is relatively simple. It is also difficult to discover the learning problems that trainees may face in advance during the training process, and it is impossible to provide timely intervention and guidance.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide a method for managing education and training information and related equipment and systems, which at least to a certain extent overcome the problems existing in the prior art, by obtaining various types of information of the target user, considering its dynamic class changes, and then generating physiological parameter information reflecting the physiological state of different classes, with the help of face images and identity information. Then, based on the target class and interest, a preset course is generated, and the teaching hierarchical management model is used to combine the course and physiological parameter information to calculate the course adjustment information (including synergy value calculation) and course matching influencing factors, and further obtain the course information containing multiple factors. Finally, training warning information is generated based on course information and authority level information, and the learning behavior pattern is obtained by calculating physiological indicators and other data through teaching resources and other information, and the deviation value warning information is determined in combination with the training learning information, so as to realize problem discovery and strategy adjustment, promote the improvement of education and training quality, ensure the accuracy and effectiveness of training, and adapt to the personalized needs of students.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0007] According to one aspect of the present application, a method for managing education and training information is provided, including: obtaining target user information, target user authority level information, target class information matching the target user information, teaching purpose information matching the target class information, and a teaching hierarchical management model matching the teaching purpose information, wherein the target user information includes user information to be monitored, and the users to be monitored are in different classes at different time periods; processing the target user information to generate physiological parameter information of the target user, wherein the physiological parameter information of the target user is used to characterize the physiological state of the target user at different time intervals; processing the target class information to generate preset course information, wherein the preset course information is based on the target user information. The target user's interests and hobbies are generated; based on the teaching hierarchical management model, the preset course information and the physiological parameter information of the target user are processed to generate course adjustment information; based on the teaching hierarchical management model, the teaching purpose information matching the target class information and the physiological parameter information of the target user are processed to generate a course matching influence factor; based on the course adjustment information and the course matching influence factor, the target user information is processed to generate the target user's course information; the target user's course information and the target user's authority level information are processed to generate the target user's training warning information, wherein the target user's training warning information is used to characterize the deviation value between the target user's training result and the target user's expected training effect.

[0008] Another aspect of the present application is a device for managing education and training information, characterized in that it includes: an acquisition module for acquiring target user information, target user authority level information, target class information matching the target user information, teaching purpose information matching the target class information, and a teaching hierarchical management model matching the teaching purpose information, wherein the target user information includes user information to be monitored, and the users to be monitored are in different classes at different time periods; a processing module for processing the target user information to generate physiological parameter information of the target user, wherein the physiological parameter information of the target user is used to characterize the physiological state of the target user at different time intervals; processing the target class information to generate preset course information, wherein the preset course The course information is generated based on the interests and hobbies of the target user; the preset course information and the physiological parameter information of the target user are processed based on the teaching hierarchical management model to generate course adjustment information; the teaching purpose information matching the target class information and the physiological parameter information of the target user are processed based on the teaching hierarchical management model to generate a course matching influencing factor; the target user information is processed based on the course adjustment information and the course matching influencing factor to generate the course information of the target user; the course information of the target user and the authority level information of the target user are processed to generate the training warning information of the target user, wherein the training warning information of the target user is used to characterize the deviation value between the training result of the target user and the expected training effect of the target user.

[0009] According to another aspect of the present application, an electronic device is characterized in that it includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-mentioned method for managing education and training information by executing the executable instructions.

[0010] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a second processor, the above-mentioned method for managing education and training information is implemented.

[0011] According to another aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a third processor, the above-mentioned method for managing education and training information is implemented.

[0012] The present application provides a method and related equipment for managing education and training information, which obtains various types of information of target users, considers their dynamic class changes, and then generates physiological parameter information reflecting the physiological state of different classes, which is achieved with the help of facial images and identity information. Then, based on the target class and interests, preset courses are generated, and the teaching hierarchical management model is used to combine the course and physiological parameter information to calculate the course adjustment information and course matching influencing factors, and further obtain course information containing multiple factors. Finally, training warning information is generated based on course information and authority level information, and the learning behavior pattern is obtained by calculating physiological indicators and other data through teaching resources and other information. The deviation value warning information is determined in combination with the training learning information, so as to realize problem discovery and strategy adjustment, promote the improvement of education and training quality, ensure the accuracy and effectiveness of training, and adapt to the personalized needs of students.

[0013] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flowchart showing a method for managing education and training information provided by an embodiment of the present application;

[0015] Figure 2 A schematic diagram of the structure of a device for managing education and training information provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0017] Combine the following Figure 1 To describe the management method of education and training information according to the exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the implementation of the present application is not limited in this respect. On the contrary, the implementation of the present application can be applied to any applicable scenario.

[0018] In one implementation, the present application also proposes a method for managing education and training information and related equipment. Figure 1 The following schematically shows a flow chart of a method for managing education and training information according to an embodiment of the present application. Figure 1 As shown, the method is applied to a server, comprising:

[0019] S101, obtaining target user information, target user authority level information, target class information matching the target user information, teaching purpose information matching the target class information, and a teaching graded management model matching the teaching purpose information.

[0020] In one implementation, the target user information includes information of users to be monitored, and the users to be monitored are in different classes at different time periods. In the field of enterprise skill training, in order to achieve efficient training and precise management, it is necessary to collect all kinds of information and build an effective teaching management model. This process involves obtaining relevant information of employees (target users), authority levels, training classes, class teaching purposes, and corresponding teaching grading management models. Through a series of data processing and model training links, it ultimately provides employees with personalized training courses and support, thereby improving the quality and effectiveness of enterprise skill training.

[0021] Take Xiao Zhang, an employee of an enterprise, as an example. When registering for skill training organized by the enterprise, he needs to provide basic personal information, including name, work number, department, position, years of work experience, etc., which constitute the target user information. The enterprise determines the authority level of employees based on their positions and levels. For example, Xiao Zhang, a technical backbone, has a high demand for learning new technologies in his position. The enterprise sets higher authority for him and gives him priority to participate in advanced skill training courses, such as "artificial intelligence algorithm optimization training"; while new employees may have lower authority and start with basic skill training courses, such as "basic office software operation training". Xiao Zhang's high authority gives him an advantage in obtaining training resources. In terms of training materials, he can obtain cutting-edge technical materials developed internally by the enterprise, in-depth analysis reports from industry experts, etc.; in terms of the use of training equipment, he can make an appointment to use the company's advanced experimental equipment or simulation system for practical operation, while low-authority employees may have to wait in line or can only use basic equipment. Xiao Zhang signed up for the "Big Data Analysis Practical Class" based on his own skill improvement needs and the company's arrangements, and the company assigned him to the corresponding target class. The purpose of this class is to cultivate employees' practical ability in big data analysis, including data collection and cleaning, application of data analysis methods and tools (such as Python data analysis library, SQL query, etc.), data visualization display and case practice combined with enterprise business scenarios, so as to help employees improve their professional skills in the field of big data analysis and better support enterprise data-driven decision-making. In this class, teaching resources are closely centered on big data analysis. The company provides real business data for students to practice, equipped with professional big data analysis software licenses, and invites internal data experts and external industry lecturers to teach together. The teaching method combines theoretical explanation, case analysis, group project practice and enterprise actual business scenario simulation. For example, through group cooperation to complete data analysis tasks in actual enterprise projects, students can master skills in practice and understand enterprise business needs.

[0022] In the field of corporate office skills training, we are committed to building an effective teaching hierarchical management model. The training aims to improve employees' skills in office software use, communication and collaboration, time management, etc., in order to improve overall office efficiency. Data is collected from the company's past office skills training history to build a training sample set. The data covers employees' personal information (such as age, education, job category, etc.), training course participation details (course category, learning time, course assignment completion, etc.), actual office performance evaluation after training (such as project completion efficiency, file processing accuracy, team collaboration score, etc.), and various test scores during the training period (such as office software operation test score, communication ability test score, etc.). For example, a sample data may be: [28, undergraduate, "Administrative Post", "Advanced Excel Application Course", 60 hours, 85 points (homework average score), 90 points (project completion efficiency score), 92 points (Excel operation test), 80 points (team collaboration score)]. A preset teaching hierarchical management model based on a decision tree algorithm is selected as the basic framework. The decision tree model is easy to understand and explain, and can clearly show the impact path of different features on office skill levels. It is suitable for processing such data with clear characteristics and classification results.

[0023] Extract features from the training sample set to generate the original feature library. The extracted features are as follows: Numerical features of age. Classification coding features of educational background (e.g., undergraduate is 1, master is 2, etc.). Classification features of job categories (e.g., administrative positions are 1, technical positions are 2, etc.). Numerical features of course learning time. Quantitative features of homework completion (e.g., accuracy). Features related to office performance evaluation (e.g., project completion efficiency score, file processing accuracy score, etc.). Test score features (e.g., office software operation test score, communication ability test score, etc.). Each sample is represented in the original feature library as a feature vector. Divide the original feature library into a training set and a validation set at a ratio of 80%:20%. If there are 800 samples in the original feature library, the training set contains 640 samples and the validation set contains 160 samples. Divide the original feature library into various feature data sets to generate training sets and validation sets. Perform prediction processing on each validation set divided by the original feature library based on the classifier to generate prediction results. Use the naive Bayes classifier to predict the validation set. Input the feature vector of each sample in the validation set into the naive Bayes classifier to predict the employee's skill level after office skills training (for example, divided into three levels: skilled, intermediate, and elementary). Assume that for a sample in the validation set, its office performance evaluation and test scores are good, and the naive Bayes classifier predicts that its office skill level is "skilled".

[0024] Based on the preset algorithm, each training set divided by the original feature library is trained and processed to generate the prediction results of the validation set class. The C4.5 algorithm (an improved algorithm for decision trees) is used to train the training set. The C4.5 algorithm builds a decision tree model based on the feature vectors and actual office skill levels (known labels) of the samples in the training set to determine the importance of each feature in the classification and the decision rules. For example, for a sample in the training set that has a low score in the office software operation test but a high teamwork score, the C4.5 algorithm will consider how to classify based on these features during the decision tree construction process and adjust the branch structure and node conditions of the decision tree.

[0025] The prediction results and the prediction results of the validation set are processed to generate target feature data, which are used to characterize the risk factors that affect the training results. The preset teaching graded management model is processed based on the training sample set with the target feature data to generate the target teaching graded management model. The prediction results of the naive Bayes classifier on the validation set are compared with the prediction results of the validation set obtained by training the training set. The difference indicators between the two are calculated, such as the difference in accuracy and the difference in recall. It is found that for employees with younger age and lower education, when dealing with complex office tasks (such as file integration and communication and coordination in large project management), there is a large deviation between the prediction results and the actual results. This feature information (combination of age and education and features related to task complexity) and deviation conditions are combined to generate target feature data. These data characterize the risk factors that affect the results of office skills training, for example, it may mean that for such employees, more actual cases and targeted guidance need to be added in the training. The training sample set with the target feature data is input into the preset teaching graded management model (decision tree) again to further optimize the structure of the decision tree. By adjusting the node splitting conditions, feature selection order, etc., and after multiple iterative training, the model can better adapt to these target feature data, improve the prediction accuracy of different employees' office skill levels, and finally generate a target teaching grading management model for enterprise office skills training.

[0026] The model includes a decision tree structure, and the root node of the decision tree selects the feature with the largest information gain as the basis for splitting. For example, in the initial stage, it may be found that the feature of office software operation test score has the largest information gain for distinguishing different office skill levels, so the root node splits based on this feature. Each internal node splits according to different features, and the number of branches depends on the value category of the feature. For example, if the job category feature has administrative positions, technical positions, marketing positions and other categories, then the node will have a corresponding number of branches. The leaf node represents the final office skill level classification result (skilled, intermediate, primary).

[0027] During the model building process, the importance of each feature is evaluated by calculating its information gain rate. The higher the information gain rate, the more critical the feature is in the decision tree construction and classification process. For example, features such as office software operation test scores and project completion efficiency scores may have a high information gain rate, indicating that they have an important impact on the judgment of office skill levels. The decision tree model can intuitively show the role of each feature in the decision-making process at different levels, helping training managers understand which factors are most critical to improving employees' office skills, so as to design training content and improve training methods in a targeted manner. Through the above model building process and structural design, it is possible to provide accurate hierarchical management for corporate office skills training, provide personalized training programs according to the different situations of employees, and improve training effects and office efficiency.

[0028] After Xiao Zhang completes the training of the Big Data Analysis Practice Class and performs well, the company plans to arrange for him to attend the "Advanced Machine Learning Model Optimization Class" to further improve his skills. At this time, the company summarizes his learning results in the Big Data Analysis training (such as project completion quality, skill mastery assessment, etc.), updates his target user information and authority level (he may be given higher authority such as the opportunity to participate in the company's core project practice and in-depth exchanges with external experts due to his outstanding performance). At the same time, according to the teaching purpose of the Advanced Machine Learning Model Optimization Class (focusing on in-depth understanding of the principles of machine learning algorithms, model tuning techniques, model applications in complex business scenarios, etc.), the teaching hierarchical management model is rebuilt to provide Xiao Zhang with more suitable teaching resources and learning paths in the new training, such as assigning him challenging actual enterprise model optimization tasks, recommending professional academic research materials, etc., to help him continue to improve in the field of machine learning and create more value for the company.

[0029] S102: Process the target user information to generate physiological parameter information of the target user.

[0030] In one implementation, the target user information is processed to generate target facial image information and target user identity information, wherein the target facial image information is the facial information of the target user during the break. In the classroom environment of corporate office software skills training, high-definition cameras and wearable devices (such as smart bracelets) installed inside the classroom are used to collect relevant information of the target user (student), and then generate their physiological parameter information to monitor and analyze the learning status of the students, providing a basis for personalized teaching. During the break, the high-definition camera captures the facial image of the student at a frequency of 30 frames per second. Assuming that student Xiao Li sits in the third row and fifth column of the classroom, the camera can clearly capture his facial expressions and movements. For example, during a 10-minute break, the camera collected 18,000 frames of Xiao Li's facial image information. When entering the classroom, the student signs in by scanning the employee card, and the system associates his identity information (name: Xiao Li, work number: 12345, department: R&D department, etc.) with the location information collected by the camera. In this way, each collected facial image can correspond to a specific student identity.

[0031] The target face image information is processed to generate the influencing factors of the target user's expression characteristics. The influencing factors of the target user's expression characteristics are processed to generate the target user's physiological index change value, wherein the target user's physiological index change value is used to characterize the target user's expression change information. The facial image information of Xiao Li is processed using an advanced facial recognition algorithm. First, the facial key points are located to determine the positions of key parts such as eyes, eyebrows, and mouth. Then the motion trajectory and morphological changes of these key points are analyzed to extract the influencing factors of expression characteristics. For example, the algorithm detects that when Xiao Li communicates with his classmates during class, his eyebrows are raised, the corners of his mouth are raised, and his eyes are narrowed. These features are identified as happy expression features, and the corresponding expression feature influencing factors may be quantified as a vector [0.8, 0.7, 0.9] (representing the degree of expression of eyebrows, mouth, and eyes, respectively, and the larger the value, the more obvious the expression). By analyzing the influencing factors of the expression characteristics of continuous frame images, calculating their change rates, and generating the target user's physiological index change values ​​(here mainly physiological indicators related to expression changes are reflected). Suppose that during a break, Xiao Li's expression gradually changes from calm to happy and then to surprised, and the expression feature influencing factor vector changes from [0.1, 0.1, 0.1] to [0.8, 0.7, 0.9] and then to [0.6, 0.9, 0.8]. The calculated change value of the physiological index can reflect the degree of fluctuation and change trend of his emotions during this break. For example, the change value of the physiological index calculated by a specific formula is [0.35, 0.4, 0.3] (corresponding to the average value of the change degree of eyebrows, mouth, and eyes, respectively).

[0032] The target user's identity information is processed to generate the target user's real-time vital sign information. Based on the target user's real-time vital sign information and the influencing factors of the target user's expression characteristics, the target user's physiological parameter information is generated. The target user's physiological parameter information is used to characterize the target user's physiological state at different time intervals. The smart bracelet worn by Xiao Li collects his vital sign information in real time, including heart rate, skin conductivity, body temperature, etc. Data is collected every 5 seconds, and a total of 120 sets of data are collected within 10 minutes of class. For example, the heart rate data range fluctuates between 60-80 times / minute, the skin conductivity varies between 10-15 micro-Siemens, and the body temperature remains between 36.5-36.8℃. These data are transmitted to the central server of the classroom via Bluetooth and associated with Xiao Li's identity information. Based on Xiao Li's real-time vital sign information and the influencing factors of expression characteristics, comprehensive processing is performed to generate physiological parameter information. The vital sign data such as heart rate, skin conductivity, body temperature, etc. are fused and calculated with the vector of the influencing factors of expression characteristics [0.35, 0.4, 0.3]. For example, a weighted summation method can be used. According to the weights set by education experts, the weight of the expression feature influencing factor is 0.3, the weight of the heart rate is 0.4, the weight of the skin conductivity is 0.2, and the weight of the body temperature is 0.1. Assuming that at a certain moment, Xiao Li's heart rate is 70 beats / minute, the skin conductivity is 12 micro-Siemens, and the body temperature is 36.6℃, the physiological parameter information is calculated as follows: Physiological parameter information = 0.3×[0.35, 0.4, 0.3]+0.4×70+0.2×12+0.1×36.6=[0.105, 0.12, 0.09]+28+2.4+3.66=[0.105, 0.12, 0.09, 34.06] (here, the expression feature influencing factor and the physical sign information are combined into a vector form of physiological parameter information). The physiological parameter information generated in this way can fully characterize Xiao Li's physiological state during the break, including emotion-related facial expression changes and basic physical signs. The training teacher or system can use this information to determine whether Xiao Li's learning state during the break is good, whether intervention or adjustment of teaching methods is needed, etc. For example, if Xiao Li's physiological parameter information shows that he is emotionally excited during the break (the value of the facial expression feature influencing factor is large) and has a fast heart rate, it may be that he encountered difficulties in the break discussion or expressed strong opinions. The teacher can pay appropriate attention to his situation in subsequent teaching and guide him to participate in learning better.

[0033] S103: Process the target class information to generate preset course information.

[0034] In one implementation, the preset course information is generated based on the interests and hobbies of the target user. In a comprehensive corporate training center, various types of office skills training courses are provided, including project management, data analysis, business communication, advanced office software applications, etc. Employees can choose to participate in different training courses according to their interests and career development needs. The training center generates personalized preset course information for each class by processing the target class information.

[0035] When employees sign up for training, they are asked to fill out a detailed questionnaire on their interests and hobbies. The questionnaire covers many aspects. For example, in the field of office skills, employees are asked about their preferences for different types of software (such as project management tools: Microsoft Project, data analysis software: Excel advanced functions or Python data analysis libraries, office software: Microsoft Word typesetting skills, PowerPoint presentation design, etc.), and they are scored from "very interested" to "not interested". For business communication, employees are asked whether they are interested in cross-departmental communication skills, business negotiation strategies, public speaking skills, etc., and whether they have experience and willingness to participate in related activities (such as internal company speech competitions, project reports, etc.). It also includes curiosity and willingness to explore emerging office technologies (such as the application of artificial intelligence in office, the use of cloud computing office platforms, etc.). At the same time, the training center cooperates with the human resources department of the company to obtain performance data of employees in their daily work, which can indirectly reflect the interests of employees. For example, employees who often actively participate in data analysis projects may be more interested in data analysis skills training; employees who frequently organize or participate in team meetings and project reports may have a demand for business communication and presentation skills training.

[0036] For each target class that is about to start, the training center analyzes the distribution of interests and hobbies of the registered students. Assuming that a target class has 30 students, through statistical analysis of their interest survey data, it is found that: 12 students show a strong interest in improving data analysis skills. They have high interest scores in Excel advanced functions and Python data analysis libraries, and some employees have certain data processing experience at work and are eager to learn in depth. 8 students are interested in business communication skills training. Most of them have participated in cross-departmental projects within the company and realize that there is room for improvement in communication and collaboration. In particular, they have high expectations for improving business negotiation strategies and public speaking skills. 6 students are interested in advanced office software applications, such as proficient in Word typesetting skills and PowerPoint presentation design, and hope to learn more advanced functions and creative design methods to improve the quality of daily office documents and presentations. 4 students are interested in emerging office technologies, focusing on the application of artificial intelligence in office automation, intelligent data analysis, etc., and hope to understand how to integrate these new technologies into daily work to improve work efficiency.

[0037] According to the distribution of interests and hobbies of the students in the target class, preset course information is generated for the class. For the above-mentioned classes where many students are interested in data analysis, the preset course information may include: Data Analysis Basic Strengthening Module: In-depth explanation of advanced Excel functions, such as advanced applications of pivot tables, nested functions, and macro programming, while introducing the basic operations of Python data analysis libraries (such as Pandas, NumPy, and Matplotlib) and common data analysis methods (data cleaning, data analysis, and data visualization). Practical project-driven learning: Arrange actual enterprise data analysis project cases, and let students collect, organize, analyze, and write reports in groups to improve data analysis skills in practice. Project cases can choose enterprise sales data, customer satisfaction survey data, etc., so that students can apply what they have learned to actual work scenarios. Industry cutting-edge technology expansion: Invite industry experts to give lectures and share the latest trends and technical applications in the field of data analysis, such as the use of big data analysis platforms, simple application cases of machine learning algorithms in data analysis, etc., to broaden students' horizons and stimulate their interest in exploring emerging technologies. For classes with a large number of students interested in business communication, the preset course information may focus on: Communication theory and skills improvement: Systematically explain the basic principles of business communication, effective listening skills, the importance of non-verbal communication and other theoretical knowledge, and conduct practical exercises through role-playing, case analysis and other methods. Business negotiation strategy and simulation: In-depth analysis of the various stages and strategies of business negotiations, organize students to conduct simulated business negotiations, simulate different negotiation scenarios (such as negotiating purchase prices with suppliers, negotiating cooperation terms with customers, etc.), and improve students' negotiation ability and contingency skills. Public speaking ability training: Comprehensive training is carried out in terms of speech content planning, speech structure design, language expression skills, body language use, etc., arrange students to practice public speaking many times, and provide personalized feedback and guidance to enhance students' confidence and expressiveness in speaking.

[0038] Taking into account the students' interests and learning abilities, the course progress is arranged reasonably. Taking the data analysis course as an example, the total course duration is 40 hours, divided into 8 modules, each module is 5 hours. In the first 10 hours (2 modules), the content of the basic reinforcement module of data analysis is concentrated, including theoretical knowledge explanation and simple case exercises, so that students can quickly master basic tools and methods. In the middle 20 hours (4 modules), students are arranged to carry out practical projects. Each project cycle is 5 hours, including project introduction, group division of labor, data processing, result analysis and report presentation. During the project process, the training teachers provide guidance and answer questions at any time to ensure that students can successfully complete the project tasks. The last 10 hours (2 modules) are used for industry cutting-edge technology expansion lectures and student project results summary and reflection, guiding students to combine what they have learned with actual work and think about how to further apply and innovate in future work. For business communication courses, course time is also allocated according to the difficulty and importance of the content. For example, the communication theory and skills improvement section is scheduled for 12 hours, the business negotiation strategy and simulation section is scheduled for 16 hours, and the public speaking ability training section is scheduled for 12 hours. Each section is interspersed with theoretical explanations, case analysis, practical exercises and other teaching links to ensure that students can receive sufficient training and improvement in all aspects.

[0039] Through the above methods, the training center can generate targeted preset course information based on the interests and hobbies of the target class students, improve the attractiveness and practicality of the training courses, enable students to better meet their own learning needs during the training process, improve their office skills, and thus provide stronger talent support for the development of the enterprise.

[0040] S104: Process the preset course information and the physiological parameter information of the target user based on the teaching hierarchical management model to generate course adjustment information.

[0041] In one implementation, the preset course information and the physiological parameter information of the target user are processed based on the teaching hierarchical management model to generate the target user's physiological indicator change values ​​for different courses and the real-time environmental factors of the target class. In the training classroom within the enterprise, a series of office skills training courses are being carried out, including "Advanced Excel Application Skills Training", "Efficient Business Communication Skills Training" and "Project Management Practical Training". The training classroom is equipped with intelligent environmental monitoring equipment that can measure environmental factors such as temperature, humidity, and noise level in real time. At the same time, the trainees wear physiological monitoring equipment (such as smart bracelets) that can record physiological indicators such as heart rate and skin conductivity to achieve the analysis of the synergy between courses and environmental factors and course adjustments.

[0042] In the course of "Advanced Excel Application Skills Training", take student Xiao Zhang as an example. Before the course started, Xiao Zhang's heart rate was stable at about 70 beats per minute, and his skin conductivity was at a normal level. As the course progressed, when explaining the nested use of complex functions and the advanced application of pivot tables, Xiao Zhang needed to concentrate on thinking and operating, and his heart rate gradually rose to 80 beats per minute, and his skin conductivity also increased slightly, indicating that his body was in a relatively tense and focused state. The changes in these physiological indicators reflected his reaction when facing the difficulties of the course, forming his physiological indicator change values ​​for the course. In the course of "Efficient Business Communication Skills Training", especially in the simulated business negotiation session, Xiao Zhang actively participated in role-playing and had intense discussions and exchanges with other students. At this time, his heart rate further rose to 85 beats per minute, and his skin conductivity increased significantly, which may be due to his more excited and engaged emotions during the communication and interaction process. The change values ​​of his physiological indicators reflect his physiological state changes in a specific link of the course. The intelligent environmental monitoring equipment in the training classroom records environmental data in real time. During the "Advanced Excel Application Skills Training" course, the classroom temperature was maintained at 22°C, the humidity was 45%, and the noise level was low at about 30 decibels. These environmental factors are relatively stable, providing students with a relatively comfortable learning environment. However, during the simulated business negotiation session of the "Efficient Business Communication Skills Training" course, due to the loud discussions of the students, the noise level in the classroom rose to about 50 decibels, the temperature also rose slightly due to the activities of the personnel, reaching 23°C, and the humidity remained basically unchanged. These changes in real-time environmental factors may have an impact on the learning status of the students, and need to be analyzed together with the changes in the students' physiological indicators.

[0043] The target user's physiological indicator change values ​​for different courses and the real-time environmental factors of the target class are processed to generate the synergy value of the target course and the environmental factors, and the synergy value of the target course and the environmental factors is processed to generate course adjustment information. The method includes a calculation formula for obtaining the synergy value of the target course and the environmental factors, and the calculation formula is: ; Where S represents the synergy value between the target course and the environmental factors; n is the number of associated dimensions; Represents the weight coefficient of the i-th dimension; represents the adjustment factor of the i-th dimension; Represents the quantitative value of the specific characteristics of the i-th course-related dimension; Represents the actual measurement value of the i-th environmental factor dimension.

[0044] For the synergy value calculation of this office skills training, the number of associated dimensions n is set to 4, including the four dimensions of course content difficulty, course interactivity, classroom temperature and classroom noise level. For the course content difficulty dimension, according to the course outline and instructor evaluation, the course content difficulty of "Advanced Excel Application Skills Training" is quantified into Set to 7 (higher difficulty, 1-10 represents from easy to difficult), the quantitative value of the course content difficulty of "Efficient Business Communication Skills Training" The interactive dimension of the course is set to 6 (moderate difficulty). For the interactive dimension of the course, "Advanced Excel Application Skills Training" mainly consists of lecturers' explanations and students' operation exercises, and the interactiveness is relatively low. The quantitative value is Set as 3 (1-5 indicates low to high interactivity); "Efficient Business Communication Skills Training" has strong interactivity in simulated negotiations and group discussions, and the quantitative value is Set to 4. Classroom temperature dimension, actual measurement value during the "Advanced Excel Application Skills Training" ℃, during the "Efficient Business Communication Skills Training" ℃. Dimensions of classroom noise levels, during the “Advanced Excel Application Skills Training” decibel, during the "Efficient Business Communication Skills Training" Decibel. Determine the weight coefficient of each dimension based on the experience of education experts and data analysis and regulatory factors For example, for the course content difficulty dimension, the weight coefficient , the regulating factor ; Course interactivity dimension, weight coefficient , the regulating factor ; Classroom temperature dimension, weight coefficient , the regulating factor ; Dimension of classroom noise level, weight coefficient , the regulating factor For the "Advanced Excel Application Skills Training" course, calculate the synergy value S between the target course and the environmental factor: For the "Effective Business Communication Skills Training" course: .

[0045] According to the calculation results, the synergy value of the "Advanced Excel Application Skills Training" course is , which is relatively high, indicating that in the current environment, the course content difficulty, interactivity and environmental factors such as classroom temperature and noise level have good synergy. When students study this course in such an environment, their physiological state is highly matched with the course and environment, and they can better adapt to the course content and teaching methods. At the same time, environmental factors do not cause obvious interference to students. The synergy value of the "Efficient Business Communication Skills Training" course is , which is relatively low. This may be because in the simulated business negotiation session, although the course is highly interactive, the increased noise level in the classroom has a certain impact on the students' physiological state, resulting in a decrease in the synergy between the changes in students' physiological indicators and the course and environment. At this time, it may be necessary to make appropriate adjustments to the course environment, such as reminding students to control the discussion volume, or optimizing the sound insulation facilities in the classroom, so as to improve the synergy between the course and the environment and enhance the students' learning effect.

[0046] According to the calculation results and analysis of the synergy value, the course adjustment information is generated for the "Efficient Business Communication Skills Training" course. Since the noise level has a great impact on the synergy value, it is possible to consider adding noise control measures in subsequent courses, such as using sound-absorbing equipment in the simulated negotiation session, or arranging this session in a classroom with better sound insulation. At the same time, the course content and interaction methods can also be fine-tuned according to the changes in the students' physiological indicators. For example, if it is found that some students are too excited in the interactive session, causing excessive fluctuations in physiological indicators, it may be necessary to adjust the interaction rhythm and add some short breaks so that students can better adjust their physiological state and maintain good learning effects. For the "Advanced Excel Application Skills Training" course, although the synergy value is high, it can still be continuously monitored, and the course content and environment settings can be continuously optimized based on student feedback and further data analysis to maintain good synergy. In this way, the synergy analysis of courses and environmental factors based on the teaching hierarchical management model can provide a scientific basis for the optimization and adjustment of corporate training courses and improve the quality and effect of training.

[0047] S105, processing the teaching purpose information matched with the target class information and the physiological parameter information of the target user based on the teaching hierarchical management model to generate a course matching influencing factor.

[0048] In one implementation, the teaching purpose information matching the target class information is processed to generate preset course information, wherein the preset course information is used to characterize the course information to be learned by the target user. In the employee skill improvement training project carried out by the enterprise, there are different courses such as "time management skills training", "teamwork ability training" and "leadership improvement training". The training center collects the physiological parameter information of employees during the learning process, and analyzes the correlation between the course and the physiological state of employees in combination with the characteristics of the course, so as to provide employees with more suitable training courses and teaching methods. For the "time management skills training" course, its teaching purpose is to help employees master effective time management methods and improve work efficiency. Based on this, the preset course information includes theoretical explanations (such as the four quadrants of time management, the Pomodoro method, etc.), practical exercises (making personal time plans, simulating work scenarios to arrange tasks, etc.) and case analysis (sharing successful time management cases and reflecting on failed cases). The teaching purpose of the "teamwork ability training" course focuses on cultivating employees' teamwork awareness and communication and collaboration skills. The preset course information includes team building activities (such as outdoor development, indoor team games, etc.), group project cooperation (completing specific tasks, such as market research, product planning, etc.) and team collaboration theory learning (team role theory, communication model, etc.). The "Leadership Improvement Training" course aims to improve employees' leadership and decision-making capabilities. The preset course information includes leadership theory learning (such as situational leadership theory, etc.), leadership practice simulation (simulating leadership decision-making scenarios, resolving team conflicts, etc.) and leadership case studies (analyzing the successful experiences and lessons of well-known corporate leaders).

[0049] Based on the real-time physiological parameter information of the target user, the preset course information is processed to generate course relevance information. In the "Time Management Skills Training" course, employee Xiao Wang wore physiological monitoring equipment (such as a smart bracelet and a heart rate monitoring chest strap). When the course explained the time management theory, Xiao Wang's heart rate was stable between 70-75 beats per minute, his skin conductivity remained at a normal level, and his brain waves showed mainly relaxed alpha waves. When the practical exercises were carried out, requiring employees to make complex time plans within the specified time, Xiao Wang's heart rate rose to 80-85 beats per minute, his skin conductivity increased slightly, and more beta waves related to thinking and concentration appeared in his brain waves. The actual observation values ​​of these physiological parameter indicators were recorded in real time. In the "Team Collaboration Ability Training" course, especially in the fierce competition of team building activities, Xiao Wang actively participated and worked closely with team members. At this time, his heart rate rose sharply to 90-95 beats per minute, his skin conductivity increased significantly, and his brain waves showed an active gamma wave state, reflecting his high level of involvement and excitement in the team collaboration process. These physiological parameter indicators were also continuously collected. In the "Leadership Enhancement Training" course, when conducting a leadership practice simulation, Xiao Wang needed to make decisions and lead a team in a simulated scenario. His heart rate remained at 85-90 beats per minute, his skin conductivity was moderate, and his brain waves showed certain characteristics related to concentration and decision-making. These data became an important basis for analyzing the relevance of the course.

[0050] The course relevance information is processed to generate course matching influencing factors, where the course matching influencing factors are used to characterize the physiological parameter information matched by different learning course information of the target users. For the "Time Management Skills Training" course, based on educational experts and past research experience, the preset ideal physiological parameter index values ​​are as follows: in the theoretical explanation part, it is expected that the employee's heart rate will remain at 65-75 beats per minute (a more relaxed state is conducive to knowledge absorption), the skin conductivity will be relatively stable (indicating a stable mood), and the brain waves will be mainly alpha waves (relaxed and focused); in the practical practice session, the expected heart rate will rise appropriately to 75-85 beats per minute (indicating active thinking and action), the skin conductivity will increase slightly (reflecting a certain tension and concentration), and the brain waves will have more beta waves (focused thinking state). The ideal physiological parameter index values ​​of the "Team Collaboration Ability Training" course are set as follows: in team building activities, it is expected that the employee's heart rate will rise to 85-95 beats per minute (reflecting active participation and investment), the skin conductivity will increase significantly (indicating emotional excitement and active interaction), and the brain waves will be mainly gamma waves (highly active and collaborative state). The “Leadership Enhancement Training” course presets that during decision-making simulation, the ideal heart rate range is 80-90 beats per minute (stay calm and focus on decision-making), the skin conductivity is moderate (not too tense or relaxed), and the brain waves have decision-making-related characteristics (such as specific frequencies and waveforms).

[0051] The method includes a calculation formula for obtaining course relevance information, and the calculation formula is:

[0052] ; Among them, r represents the course association value; Represents the actual observed value of the i-th physiological parameter indicator when the target user is learning a certain course; Represents the value of the ideal physiological parameter index value preset for the course in the i-th dimension; N represents the total number of physiological parameter indicators; M represents the normalization constant.

[0053] Take Xiao Wang's "Time Management Skills Training" course as an example to calculate the course relevance value r. Assume that three physiological parameter indicators (N=3) of heart rate, skin conductivity and brain wave are collected, and the normalization constant M=50 is determined based on the normal range and expected change range of the physiological parameters (this is just an example). In the theoretical explanation part, Xiao Wang's actual observed heart rate The average is 72 times / minute, the ideal value The range is 65-75 times / minute, with a median of 70 times / minute; actual observed value of skin conductivity Assuming the quantification is 5 microSiemens ( S), ideal value For a stable state, assume 4-6 S, take the middle value 5 S; EEG waves are mainly alpha waves, the actual observed value In the normal range of relaxation, assuming the quantification is 8 (according to the quantification standard of the EEG monitoring device), the ideal value To achieve a relaxed and focused state, assume it is 7-9, with the middle value of 8.

[0054] .

[0055] In the practical exercises, Xiao Wang's actual observed heart rate averaged 82 beats / minute, the ideal value was 75-85 beats / minute, and the median value was 80 beats / minute; the actual observed value of skin conductivity increased slightly, assuming 7, the ideal value was a slightly increased state, assuming 6-8, and the median value was 7; there were more beta waves in the brain waves, and the actual observed value was assumed to be 10 (indicating enhanced focused thinking), and the ideal value was a focused thinking state, assuming 9-11, and the median value was 10. For the "Team Collaboration Ability Training" course, in the team building activities, Xiao Wang's actual observed heart rate averaged 92 beats / minute, the ideal value was 85-95 beats / minute, and the median value was 90 beats / minute; the actual observed value of skin conductivity increased significantly, assuming 10, the ideal value was a significantly increased state, assuming 8-12, and the median value was 10; the brain waves showed mainly gamma waves, and the actual observed value was assumed to be 12 (indicating high activity), and the ideal value was a highly active and collaborative state, assuming 11-13, and the median value was 12. In the "Leadership Enhancement Training" course, during the decision-making simulation, Xiao Wang's actual observed heart rate averaged 87 beats / minute, the ideal value was 80-90 beats / minute, and the middle value was 85 beats / minute; the actual observed value of skin conductivity was moderate, assuming 6, the ideal value was moderate, assuming 5-7, and the middle value was 6; brain waves have decision-making-related characteristics, the actual observed value was assumed to be quantified to 9 (indicating focused decision-making), the ideal value was decision-making-related, assuming 8-10, and the middle value was 9. The specific calculation process is referred to above, and will not be repeated here.

[0056] From the calculation results, Xiao Wang's course relevance information is close to 0.99 in the theoretical explanation and practical exercises of the "Time Management Skills Training" course, the team building activities of the "Team Collaboration Ability Training" course, and the decision-making simulation of the "Leadership Enhancement Training" course. This shows that the course content and teaching methods are highly correlated with Xiao Wang's physiological state in the corresponding learning process. That is, the course design can better guide Xiao Wang into the expected learning state, his physiological response matches the expected effect of the course, and the course content and teaching rhythm are relatively reasonable, which can effectively promote his learning and skill improvement. If the value calculated in a certain course link is low, for example, less than 0.8, this may mean that the course content is too difficult or too low, the teaching method is not suitable for the employee's learning style, or environmental factors interfere with the employee's physiological state, resulting in a large difference between his physiological parameter indicators and the ideal state preset by the course. At this time, it is necessary to adjust the course content, teaching methods or environment to improve the course relevance and optimize the training effect. For example, the course difficulty can be adjusted, interactive links can be added, or the learning environment can be improved, so that employees can better adapt to the course requirements during the learning process and improve their learning efficiency and skill mastery.

[0057] S106: Process the target user information based on the course adjustment information and the course matching influencing factor to generate course information of the target user.

[0058] In one implementation, the target user information is processed based on the course adjustment information to generate an environmental factor adjustment factor and the target user's emotional value. The series of professional skills improvement training courses held by the company include courses such as "Business English Communication Skills Training", "Project Management Practical Training" and "Data Analysis Advanced Training". During the training process, the relevant information of the trainees is collected through various monitoring methods, and personalized course information for each trainee is generated based on the course adjustment information and course matching influencing factors to achieve precise teaching and optimize the learning experience. In the "Business English Communication Skills Training" course, the training classroom is equipped with environmental monitoring equipment that can monitor environmental factors such as temperature, humidity, and noise in real time. Suppose that during the course, it is found that the noise level in the classroom is high, reaching 55 decibels (the normal noise level suitable for learning should be less than 45 decibels). According to the course adjustment information, the environmental factor adjustment factor is calculated. For example, it is set that for every 5 decibels that the noise exceeds the appropriate range, the environmental factor adjustment factor increases by 0.1 (the calculation method here can be determined based on actual conditions and research). Then the environmental factor adjustment factor for this classroom is . At the same time, the emotional state of the students is evaluated by facial expression recognition and physiological parameter monitoring (such as heart rate, skin conductivity, etc.). If it is found that the student Xiao Li is slightly irritable in this noisy environment, his heart rate is slightly higher than the normal learning state, and his skin conductivity has also increased, it means that his emotions have been affected to a certain extent. Through the emotion evaluation model (a model trained based on a large amount of data, which can quantify the emotion value based on physiological parameters and expression characteristics), it is calculated that Xiao Li's emotion value is 0.6 (assuming that the emotion value range is 0-1, 0 represents extremely negative, 1 represents extremely positive, and 0.5 represents a calm state).

[0059] The target user information is processed based on the course matching influence factor to generate the target user's learning progress value. In the "Project Management Practical Training" course, the student's learning progress is evaluated based on the previously calculated course matching influence factor (assuming that it is calculated based on multiple factors such as the degree of matching between the student's physiological parameters during the learning process and the ideal physiological parameters preset in the course). For example, student Xiao Wang has a high course matching influence factor in the project management knowledge explanation session, indicating that his physiological state and learning performance match the course content well. According to the predefined rules, his learning progress value in this session can be increased by 0.3 (assuming that the increase in the learning progress value is set according to the size of the course matching influence factor and the course stage). In the practical project operation session, if his course matching influence factor decreases, the increase in the learning progress value may decrease, such as an increase of 0.1.

[0060] The environmental factor adjustment factor, the target user's emotional value, and the target user's learning progress value are processed to generate the target user's course information. For the "Advanced Data Analysis Training" course, assume that during the course learning process, the environmental factor adjustment factor of student Xiao Zhang is 0.1 (caused by a slightly high classroom temperature), the emotional value is 0.7 (the overall emotion is relatively positive, but still affected by a certain environment), and the learning progress value is 0.5 (indicating the learning progress in the course). The training system will generate personalized course information for Xiao Zhang based on these values. If the environmental factor adjustment factor is high, the system may recommend adjusting the classroom environment, such as lowering the temperature or adding ventilation equipment. For the emotional value, if it is at a low level, the system may recommend some motivational learning materials or arrange group interactive activities to improve emotions. According to the learning progress value, the system can provide Xiao Zhang with a personalized learning path. For example, if the learning progress is slow, some basic review materials may be pushed or a tutor may be arranged for one-on-one Q&A; if the learning progress is normal, the subsequent content will continue to be promoted according to the course outline; if the learning progress is fast, some extended learning tasks may be provided, such as advanced data analysis case studies or application exploration of new technologies in data analysis.

[0061] Throughout the training process, these indicators of the trainees will be continuously monitored, and the course information will be adjusted dynamically. For example, as the course progresses, the environment of Xiao Zhang's classroom improves, the environmental factor adjustment factor drops to 0, his emotional value rises to 0.8, and his learning progress value reaches 0.7. At this time, the training system will adjust his course resources accordingly, such as providing more challenging data analysis projects for him to participate in, recommending relevant professional books and online course resources to meet his learning needs and further improve his skills in the field of data analysis. At the same time, according to his learning progress and emotional state, the rhythm of the course is reasonably arranged to ensure that he can complete the training course efficiently in a positive learning state and achieve the expected training effect. In this way, the course can be precise and personalized according to the specific situation of each trainee, improving the quality of training and the learning outcomes of the trainees.

[0062] S107: Process the course information of the target user and the authority level information of the target user to generate training warning information of the target user.

[0063] In one implementation, the course information of the target user is processed to generate teaching resource information and teaching activity type information. In the course of "Marketing Strategy Training", teaching resources include rich market case analysis documents, videos of well-known corporate marketing activities, and electronic versions of professional marketing theory books, etc. These resources provide students with a variety of learning materials. The types of teaching activities include classroom lectures, group discussion cases, simulated marketing planning projects, and on-site visits and surveys of enterprises. For example, during the learning process, student Xiao Zhao has a high degree of participation in teaching activities such as simulated marketing planning projects. He frequently consults market case analysis documents to provide a basis for his own planning scheme. In a simulation project, he spent a lot of time studying documents and actively discussing with group members. The group discussion lasted 90 minutes, the document consultation time accumulated 60 minutes, and the total duration of the simulation project was 180 minutes. By analyzing Xiao Zhao's learning behavior in this course, teaching resource information (such as the frequency and duration of Xiao Zhao's use of different types of resources) and teaching activity type information (such as Xiao Zhao's participation and performance in various activities) are generated.

[0064] According to the teaching resource information and teaching activity type information, Xiao Zhao's relevant data is further calculated. The physiological index change values ​​of Xiao Zhao during the learning process are recorded through physiological monitoring equipment (such as smart bracelets). In the simulated marketing planning project, when the discussion entered the white-hot stage, Xiao Zhao actively spoke and his mind was active. At this time, his heart rate rose from the normal 70 times per minute to 85 times, and his skin conductivity also increased, indicating that he was in a state of high concentration and excitement. The physiological index change values ​​at this stage were recorded. At the same time, according to Xiao Zhao's completion progress in the simulation project (such as the completion of the preliminary framework construction of the plan, market positioning analysis, etc., accounting for 40% of the entire project task), his learning progress value is calculated to be 0.4. In addition, the cumulative learning time in the course, including classroom lectures, group discussions, independent learning, etc., is assumed to be 10 hours in the "Marketing Strategy Training" course so far.

[0065] Based on the teaching resource information and teaching activity type information, the target user is processed to generate the target user's physiological index change value, the target user's learning progress value and the target user's learning time. The target user's physiological index change value, the target user's learning progress value and the target user's learning time are processed to generate the target user's learning behavior pattern information. Combining Xiao Zhao's physiological index change value, learning progress value and learning time, his learning behavior pattern information is generated. When facing challenging and interactive teaching activities (such as simulated marketing planning projects), Xiao Zhao shows high excitement and concentration physiologically, and his learning progress is at a medium level, but the learning time is long, which may indicate that he needs to further optimize his learning methods or that he needs more time to understand the course content. This learning behavior pattern information can provide a reference for subsequent teaching interventions. For example, teachers can provide more efficient learning method guidance for his situation, or adjust the way of explaining the teaching content to help him improve his learning efficiency. Xiao Zhao's company sets different authority levels according to employee positions and performance. Assuming that Xiao Zhao is an employee with intermediate authority level, his training learning information in training will be affected by the authority level. Intermediate-level employees may enjoy certain priority access to learning resources, such as early access to some advanced case analysis materials, but they also face higher training requirements, such as the need to complete more complex project assignments after training and meet certain assessment standards. According to Xiao Zhao's level of authority, his training and learning information is determined, including the learning goals to be achieved (such as being able to independently develop a complete marketing plan and pass the company's internal assessment after the "Marketing Strategy Training" course), the scope of available training resources (such as being able to attend specific online expert lectures, but not being able to participate in certain high-end external training courses), etc.

[0066] The target user's permission level information is processed to generate the target user's training and learning information. The target user's learning behavior pattern information and the target user's training and learning information are processed to generate the target user's training warning information. The target user's training warning information is used to characterize the deviation value between the target user's training result and the target user's expected training effect. As the training course progresses, Xiao Zhao's learning behavior pattern information and training and learning information are compared and processed to generate training warning information. Assuming that according to the training plan, Xiao Zhao should achieve 50% of the learning progress at the current stage, but the actual progress is only 40%, and the learning time also exceeds the expected average time. The deviation value between the training result and the expected training effect is calculated by a specific algorithm. For example, the deviation value calculation formula is set as follows: where is the deviation value, is the actual learning progress value, is the expected learning progress value, is the actual learning time, and is the expected learning time (the expected learning progress value and time can be set according to the course outline and previous experience). Substituting the data, we can get (here we assume that the expected learning time is 8 hours). The larger the deviation value, the more Xiao Zhao's training situation deviates from expectations, and it needs to be paid attention to.

[0067] According to the calculated deviation value, the corresponding training warning information is generated. If the deviation value exceeds a certain threshold (such as 1.5), the system will automatically send a warning notification to Xiao Zhao and his training instructor. The training instructor can communicate with Xiao Zhao based on the warning information to understand the difficulties he encountered in the learning process, which may be unclear understanding of certain marketing concepts, or problems in group collaboration. Then, the instructor can develop a personalized coaching plan for Xiao Zhao, such as arranging additional coaching courses, adjusting the difficulty of learning tasks, and providing more targeted learning resources, etc., to help Xiao Zhao return to the normal training track, improve the training effect, ensure that he can achieve the expected training goals, improve his professional skills in the field of marketing, and provide stronger support for the company's market promotion work. The same process also applies to other trainees and courses. Through real-time monitoring and early warning, the refined management and high-quality delivery of corporate training can be achieved.

[0068] This application obtains multiple aspects of target user information, including their own information, authority level, target class, corresponding teaching purpose information, and adapted teaching graded management model, and takes into account that users may be in different classes at different time periods. Then, the target user information is processed to generate physiological parameter information, and the influencing factors of expression characteristics and corresponding physiological index change values ​​are obtained by using their facial images, and the real-time vital sign information obtained by combining the identity information is used to comprehensively obtain the physiological parameter information that characterizes the physiological state at different moments between classes.

[0069] Then, the preset course information based on the user's interests and hobbies is generated based on the target class information. The teaching hierarchical management model is used to generate course adjustment information by combining the preset course information and physiological parameter information. The course and environmental factor synergy value is calculated by a specific formula to measure the matching degree between the course and the environment; at the same time, the teaching purpose information and physiological parameter information are processed to obtain the course matching influencing factor to reflect the association between the course and the user's physiological parameters. The target user information is further processed based on the course adjustment information and the course matching influencing factor to obtain course information containing environmental factor adjustment factors, emotional values, and learning progress values. Finally, training warning information is generated by processing course information and authority level information. First, the teaching resources and activity type information are obtained from the course information, and the user's physiological indicator changes, learning progress and duration are calculated based on this, and then the learning behavior pattern information is obtained. Combined with the training learning information determined by the authority level, the warning information used to characterize the deviation value between the training results and the expected value is finally generated, so as to timely discover problems and adjust teaching strategies to improve the effect of education and training.

[0070] In one embodiment, if Figure 2 As shown, the present application also provides a management device for education and training information, including:

[0071] The acquisition module 201 is used to acquire target user information, target user authority level information, target class information matching the target user information, teaching purpose information matching the target class information, and a teaching hierarchical management model matching the teaching purpose information, wherein the target user information includes user information to be monitored, and the users to be monitored are in different classes at different time periods;

[0072] The processing module 202 is used to process the target user information to generate physiological parameter information of the target user, wherein the physiological parameter information of the target user is used to characterize the physiological state of the target user at different time intervals between classes; process the target class information to generate preset course information, wherein the preset course information is generated based on the interests and hobbies of the target user; process the preset course information and the physiological parameter information of the target user based on the teaching hierarchical management model to generate course adjustment information; process the teaching purpose information matched with the target class information and the physiological parameter information of the target user based on the teaching hierarchical management model to generate a course matching influence factor; process the target user information based on the course adjustment information and the course matching influence factor to generate the course information of the target user; process the course information of the target user and the authority level information of the target user to generate training warning information of the target user, wherein the training warning information of the target user is used to characterize the deviation value between the training result of the target user and the expected training effect of the target user.

[0073] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method for managing education and training information provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0074] Each embodiment in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the management method, electronic device, electronic device, and readable storage medium embodiment for evaluating education and training information, since they are basically similar to the above-mentioned education and training information management method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the above-mentioned education and training information management method embodiment.

[0075] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. A method for managing education and training information, characterized in that: include: Obtaining target user information, target user authority level information, target class information matching the target user information, teaching purpose information matching the target class information, and a teaching hierarchical management model matching the teaching purpose information, wherein the target user information includes user information to be monitored, and the users to be monitored are in different classes at different time periods; Processing the target user information to generate physiological parameter information of the target user, wherein the physiological parameter information of the target user is used to characterize the physiological state of the target user at different time intervals; Processing the target class information to generate preset course information, wherein the preset course information is generated based on the interests and hobbies of the target user; Processing the preset course information and the physiological parameter information of the target user based on the teaching hierarchical management model to generate course adjustment information; Based on the teaching hierarchical management model, the teaching purpose information matched with the target class information and the physiological parameter information of the target user are processed to generate a course matching influencing factor; Processing the target user information based on the course adjustment information and the course matching influencing factor to generate the course information of the target user; Processing the course information of the target user and the authority level information of the target user to generate training warning information of the target user, wherein the training warning information of the target user is used to represent the deviation value between the training result of the target user and the expected training effect of the target user; Processing the target user information to generate physiological parameter information of the target user, including: processing the target user information to generate target facial image information and target user identity information, wherein the target facial image information is the facial information of the target user during class time; processing the target facial image information to generate the target user's expression feature influencing factors; processing the target user's expression feature influencing factors to generate the target user's physiological indicator change value, wherein the target user's physiological indicator change value is used to characterize the target user's expression change information; processing the target user's identity information to generate the target user's real-time vital sign information; processing based on the target user's real-time vital sign information and the target user's expression feature influencing factors to generate the target user's physiological parameter information; The preset course information and the physiological parameter information of the target user are processed based on the teaching hierarchical management model to generate course adjustment information, including: processing the preset course information and the physiological parameter information of the target user based on the teaching hierarchical management model to generate physiological indicator change values ​​of the target user for different courses and real-time environmental factors of the target class; processing the physiological indicator change values ​​of the target user for different courses and the real-time environmental factors of the target class to generate a synergy value between the target course and the environmental factors; processing the synergy value between the target course and the environmental factors to generate course adjustment information; the method includes a calculation formula for obtaining the synergy value between the target course and the environmental factors, and the calculation formula is: Among them, S represents the synergy value between the target course and the environmental factors; n is the number of associated dimensions; α i represents the weight coefficient of the i-th dimension; β i represents the adjustment factor of the i-th dimension; P i represents the specific characteristic quantitative value of the i-th course-related dimension; E i Represents the actual measurement value of the i-th environmental factor dimension.

2. The method according to claim 1, characterized in that Obtain a teaching grading management model that matches the teaching purpose information, including: Acquire a training sample set and a preset teaching hierarchical management model, wherein the training sample set is used to characterize training samples that match the teaching purpose information; Extract features from the training sample set to generate an original feature library; Dividing the original feature library into various feature data sets to generate a training set and a validation set; Based on the classifier, each verification set divided by the original feature library is predicted and processed to generate a prediction result; Based on the preset algorithm, each training set divided by the original feature library is trained and processed to generate the prediction results of the validation set class; Processing the prediction results and the validation set prediction results to generate target feature data, wherein the target feature data is used to characterize risk factors that affect the training results; The preset teaching grading management model is processed based on a training sample set with target feature data to generate a target teaching grading management model.

3. The method according to claim 1, characterized in that Process the teaching purpose information that matches the target class information to generate course matching influencing factors, including: Processing the teaching purpose information that matches the target class information to generate preset course information, wherein the preset course information is used to represent the course information to be learned by the target user; Processing the preset course information based on the real-time physiological parameter information of the target user to generate course relevance information; Processing the course relevance information to generate a course matching influence factor, wherein the course matching influence factor is used to characterize physiological parameter information matched by different learning course information of the target user; The method includes a calculation formula for obtaining course relevance information, and the calculation formula is: Among them, r represents the course association value; X i represents the actual observed value of the i-th physiological parameter indicator when the target user is learning a certain course; Y i Represents the value of the ideal physiological parameter index value preset for the course in the i-th dimension; N represents the total number of physiological parameter indicators; M represents the normalization constant.

4. The method according to claim 3, characterized in that The target user information is processed based on the course adjustment information and the course matching influencing factor to generate the course information of the target user, including: processing the target user information based on the course adjustment information to generate an environmental factor adjustment factor and an emotion value of the target user; Processing the target user information based on the course matching influence factor to generate a learning progress value for the target user; The environmental factor adjustment factor, the target user's emotion value and the target user's learning progress value are processed to generate the target user's course information.

5. The method according to claim 4, characterized in that Processing the course information of the target user and the authority level information of the target user to generate training warning information of the target user includes: Processing the course information of the target user to generate teaching resource information and teaching activity type information; processing the target user based on the teaching resource information and the teaching activity type information to generate a physiological indicator change value of the target user, a learning progress value of the target user, and a learning time of the target user; Processing the physiological indicator change value of the target user, the learning progress value of the target user and the learning time of the target user to generate learning behavior pattern information of the target user; Processing the authority level information of the target user to generate training and learning information for the target user; The learning behavior pattern information of the target user and the training learning information of the target user are processed to generate training warning information of the target user.

6. A device for managing education and training information, characterized in that: The device comprises: an acquisition module, used to acquire target user information, target user authority level information, target class information matching the target user information, teaching purpose information matching the target class information, and a teaching hierarchical management model matching the teaching purpose information, wherein the target user information includes user information to be monitored, and the users to be monitored are in different classes at different time periods; A processing module, used to process the target user information to generate physiological parameter information of the target user, wherein the physiological parameter information of the target user is used to characterize the physiological state of the target user at different time intervals between classes; process the target class information to generate preset course information, wherein the preset course information is generated based on the interests and hobbies of the target user; process the preset course information and the physiological parameter information of the target user based on the teaching hierarchical management model to generate course adjustment information; process the teaching purpose information matched with the target class information and the physiological parameter information of the target user based on the teaching hierarchical management model to generate a course matching influence factor; process the target user information based on the course adjustment information and the course matching influence factor to generate the course information of the target user; process the course information of the target user and the authority level information of the target user to generate training warning information of the target user, wherein the training warning information of the target user is used to characterize the deviation value between the training result of the target user and the expected training effect of the target user; Processing the target user information to generate physiological parameter information of the target user, including: processing the target user information to generate target facial image information and target user identity information, wherein the target facial image information is the facial information of the target user during class time; processing the target facial image information to generate the target user's expression feature influencing factors; processing the target user's expression feature influencing factors to generate the target user's physiological indicator change value, wherein the target user's physiological indicator change value is used to characterize the target user's expression change information; processing the target user's identity information to generate the target user's real-time vital sign information; processing based on the target user's real-time vital sign information and the target user's expression feature influencing factors to generate the target user's physiological parameter information; The preset course information and the physiological parameter information of the target user are processed based on the teaching hierarchical management model to generate course adjustment information, including: processing the preset course information and the physiological parameter information of the target user based on the teaching hierarchical management model to generate physiological indicator change values ​​of the target user for different courses and real-time environmental factors of the target class; processing the physiological indicator change values ​​of the target user for different courses and the real-time environmental factors of the target class to generate a synergy value between the target course and the environmental factors; processing the synergy value between the target course and the environmental factors to generate course adjustment information; the method includes a calculation formula for obtaining the synergy value between the target course and the environmental factors, and the calculation formula is: Among them, S represents the synergy value between the target course and the environmental factors; n is the number of associated dimensions; α i represents the weight coefficient of the i-th dimension; β i represents the adjustment factor of the i-th dimension; P i represents the specific characteristic quantitative value of the i-th course-related dimension; E i Represents the actual measurement value of the i-th environmental factor dimension.

7. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the method for managing education and training information as described in any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the method for managing education and training information described in any one of claims 1 to 5 is implemented.

Images