Teaching training system and method based on Internet of Things

Abstract

The invention discloses a teaching practical training system and method based on the Internet of Things, and relates to the technical field of teaching management. According to the teaching practical training system and method based on the Internet of Things, the learning behavior data of the students are monitored in real time through the Internet of Things, the learning behavior characteristics of the students are extracted through clustering analysis, and the learning mode is recognized. And according to the learning mode of the student, behavior modes of other students are matched through a collaborative filtering algorithm, and a learning adaptability index is obtained, so that learning resources and task contents are dynamically adjusted. By comprehensively analyzing the learning mode and the adaptability index of the student, the learning progress and resource allocation of the student are coordinated, and the teaching task arrangement is optimized, so that the teaching efficiency and the learning experience of the student are improved. And based on the learning behavior data and the learning mode of the student, establishing an association relationship among the student, the learning resource and the task content through a graph construction algorithm, generating a knowledge graph between the student and the knowledge point, and realizing visual display of the learning state, progress and path.

Description

Technical Field

[0001] The present invention relates to the technical field of teaching management, and in particular to a teaching training system and method based on the Internet of Things. Background Art

[0002] With the rapid development of information technology, the Internet of Things technology has been widely used in all walks of life, especially in the field of education. The Internet of Things makes the teaching process more personalized, intelligent and precise through real-time monitoring and data analysis. At present, the education system is facing the differentiated learning needs of students, and traditional teaching methods are difficult to meet the personalized needs of students in learning progress, resource utilization and task allocation. Therefore, the application of Internet of Things technology in the teaching and training system can monitor the learning behavior of students in real time and analyze the learning mode, so as to achieve more accurate learning resource recommendation and task arrangement, improve teaching effect and promote the improvement of education quality.

[0003] Traditional teaching and training systems usually rely on static teaching plans and manually allocated resources, which makes it difficult to dynamically adjust according to the actual learning situation of students. Existing learning behavior analysis is mostly limited to a single dimension, such as test scores or study time, and lacks multi-dimensional and comprehensive analysis of student learning behavior, resulting in an incomplete judgment of students' learning situation. In addition, traditional teaching content recommendation methods are usually based on fixed rules or simple classification algorithms, which are difficult to dynamically adapt to changes in students' learning needs and learning patterns. The allocation of learning resources and task scheduling lack flexibility, and cannot effectively coordinate the differences in learning progress among students, resulting in some students lagging behind or ahead of schedule, affecting the overall teaching quality. Therefore, there is an urgent need for an intelligent teaching and training system based on Internet of Things technology that can obtain students' learning behavior data in real time, and dynamically adjust learning content and resources based on these data to achieve personalized teaching and intelligent management. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a teaching and training system and method based on the Internet of Things, which solves the problems of the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a teaching and training system and method based on the Internet of Things, including the following modules: a learning behavior analysis module, a learning content recommendation module, a collaborative management module, and a graph construction module; the learning behavior analysis module is used to monitor the behavioral data of students in the learning process in real time through the Internet of Things, extract the learning behavior characteristics of students through cluster analysis, and identify the learning patterns of students; the learning content recommendation module is used to match the learning patterns of students in the teaching database through a collaborative filtering algorithm according to the learning patterns of students, and obtain a learning adaptability index for measuring the adaptability of students to learning resources and dynamically adjusting learning resources and task content; the collaborative management module is used to comprehensively analyze the learning patterns and learning adaptability index of students, coordinate the learning progress and resource allocation among students, and optimize the arrangement of teaching tasks; the graph construction module is used to establish the association between students, learning resources, and task content based on the learning behavior data and learning patterns of students through a graph construction algorithm, and generate a knowledge graph between students' learning behaviors and knowledge points, which is used to visually display the learning status, learning progress, and learning path of students.

[0006] Furthermore, the specific process of real-time monitoring of students' behavioral data during the learning process through the Internet of Things is as follows: The behavioral data of students during the learning process are collected in real time through the wireless sensor network, including the completion of learning tasks, task start and end time, learning progress, interaction frequency, learning time, and students' use of different learning resources.

[0007] Furthermore, the learning behavior characteristics of students are extracted through cluster analysis. The specific process of identifying the learning patterns of students is as follows: based on the students' behavioral data, key features that reflect the students' learning behavior are selected, including task completion, learning time, learning progress, and interaction frequency; the data are clustered through the K-means clustering algorithm to identify different groups of students, set the number of clusters, extract the core behavioral characteristics of each group, such as learning time, interaction frequency, and task completion, and divide the students into different groups based on their learning behavior characteristics; based on the behavioral characteristics of the groups, the students' learning patterns are identified, including active, passive, and dependent; the students are divided into different learning patterns based on the results of cluster analysis to form a classification of learning behavior patterns.

[0008] Furthermore, according to the students' learning patterns, the specific process of matching the students' learning patterns in the teaching database through the collaborative filtering algorithm is as follows: based on the students' learning patterns and the students' behavioral characteristics, they are compared with the students' behavioral patterns in the teaching database; the similarity between the students and other students is calculated through the collaborative filtering algorithm, and students with similar learning patterns are selected as the reference group; based on the learning behavior and resource usage of the reference group, the most suitable learning resources and tasks for the students are inferred and recommended.

[0009] Furthermore, the specific process of obtaining the learning adaptability index and dynamically adjusting the learning resources and task content is as follows: based on the behavioral characteristics of the students, the similarity between the target students and other students in the teaching database is calculated through the Pearson correlation coefficient, and the behavioral consistency between the target students and the reference students is measured; according to the similarity between the target students and the reference students, combined with the students' learning behavior characteristics, the students' learning adaptability index is comprehensively evaluated; according to the learning adaptability index, the learning resources and task content are dynamically adjusted.

[0010] Furthermore, the specific process of comprehensively analyzing the students' learning patterns and learning adaptability indexes and coordinating the learning progress and resource allocation among the students is as follows: based on the students' learning pattern data and learning adaptability index, the students' learning progress is monitored in real time to identify students with deviations in learning progress; based on the students' learning adaptability index, the students' adaptability to different tasks and resources is evaluated, and the students are grouped according to their learning progress and adaptability index; and based on the differences in learning progress among the students, the priority of learning resources and the allocation of task content are adjusted.

[0011] Furthermore, based on the students' learning behavior data and learning patterns, the specific process of arranging the association relationship between students, learning resources, and task contents through a graph construction algorithm is as follows: according to the students' learning patterns and behavioral characteristics, the attributes of learning resources and task contents are determined, including difficulty, type, and related knowledge points; students, learning resources, and task contents are taken as nodes through knowledge graph algorithms, and edges between nodes are established to represent their association relationship; multi-dimensional association relationships between students and learning resources and task contents are established by calculating the similarity and weight between nodes in the graph; the weights of nodes and edges in the graph are dynamically updated according to the students' learning behavior and learning patterns to ensure that the graph can reflect the students' latest learning needs.

[0012] Furthermore, the specific process of generating a knowledge graph between students' learning behaviors and knowledge points is as follows: based on the association between students, learning resources, and task content, a mapping relationship graph between students' learning behaviors and knowledge points is generated, and the knowledge points mastered by students and the knowledge points to be mastered are represented by calculating the similarity between students and each knowledge point; the knowledge graph is dynamically updated, and the association between students and knowledge points is adjusted according to students' learning progress, learning needs, and task completion status, so as to reflect students' learning status in real time.

[0013] The teaching and training method based on the Internet of Things includes the following steps: S1. Real-time monitoring of students' behavioral data in the learning process through the Internet of Things, extracting students' learning behavior characteristics through cluster analysis, and identifying students' learning patterns; S2. According to students' learning patterns, matching students' learning patterns in the teaching database through collaborative filtering algorithms, obtaining learning adaptability indexes, which are used to measure students' adaptability to learning resources, and dynamically adjust learning resources and task content; S3. Comprehensively analyzing students' learning patterns and learning adaptability indexes, coordinating learning progress and resource allocation among students, and optimizing the arrangement of teaching tasks; S4. Based on students' learning behavior data and learning patterns, establishing the association between students, learning resources, and task content through a graph construction algorithm, generating a knowledge graph between students' learning behaviors and knowledge points, and visually displaying students' learning status, learning progress, and learning paths.

[0014] The present invention has the following beneficial effects: (1) This IoT-based teaching and training system can monitor students’ learning behavior data in real time and perform cluster analysis through the learning behavior analysis module and the learning content recommendation module, identify students’ learning patterns, and provide students with personalized learning resource recommendations. At the same time, through the collaborative filtering algorithm, it matches the students’ learning patterns and obtains the students’ learning adaptability index, thereby dynamically adjusting learning resources and task content, achieving precise teaching and resource optimization, and ensuring that each student obtains the most suitable learning support according to their characteristics.

[0015] (2) This teaching and training method based on the Internet of Things can comprehensively analyze the students' learning patterns and learning adaptability index through the collaborative management module and the graph construction module, coordinate the learning progress and resource allocation among students, optimize the arrangement of teaching tasks, and improve the overall teaching efficiency. At the same time, through the graph construction algorithm, the relationship between students, learning resources, and task content is established, and a knowledge graph between students' learning behaviors and knowledge points is generated, which intuitively displays the students' learning status, progress, and path, providing comprehensive data support and decision-making basis for teaching staff, and further improving the teaching quality and students' learning effects.

[0016] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the teaching and training system based on the Internet of Things of the present invention.

[0018] Figure 2 The present invention is a flow chart of the teaching and training method based on the Internet of Things. DETAILED DESCRIPTION

[0019] The embodiment of the present application solves the problems of insufficient personalized learning support, unreasonable allocation of teaching resources, difficulty in optimizing students' learning progress, and lack of visualization of learning status in traditional teaching models through a teaching and training system and method based on the Internet of Things. The system can monitor students' learning behavior in real time, dynamically adjust learning resources and task content, ensure that each student's learning needs are met, and optimize students' learning progress and task arrangements through graph construction and collaborative management, thereby improving teaching efficiency and personalization level.

[0020] The overall idea of ​​the solution in the embodiments of this application is as follows: The Internet of Things is used to monitor students' behavioral data in real time during the learning process, and cluster analysis is used to extract students' learning behavior characteristics and identify their learning patterns.

[0021] According to the students' learning patterns, the collaborative filtering algorithm is used to match the students' learning patterns in the teaching database to obtain the learning adaptability index, which is used to measure the students' adaptability to learning resources and dynamically adjust the learning resources and task content.

[0022] Comprehensively analyze students' learning patterns and learning adaptability index, coordinate learning progress and resource allocation among students, and optimize the arrangement of teaching tasks.

[0023] Based on students' learning behavior data and learning patterns, a graph construction algorithm is used to establish the relationship between students, learning resources, and task content, and a knowledge graph between students' learning behaviors and knowledge points is generated to visualize students' learning status, learning progress, and learning paths.

[0024] See also Figure 1 The embodiment of the present invention provides a technical solution: a teaching and training system and method based on the Internet of Things, including the following modules: a learning behavior analysis module, a learning content recommendation module, a collaborative management module, and a graph construction module; the learning behavior analysis module is used to monitor the behavior data of students in the learning process in real time through the Internet of Things, extract the learning behavior characteristics of students through cluster analysis, and identify the learning mode of students; the learning content recommendation module is used to match the learning mode of students in the teaching database through a collaborative filtering algorithm according to the learning mode of students, and obtain a learning adaptability index for measuring the adaptability of students to learning resources and dynamically adjusting learning resources and task content; the collaborative management module is used to comprehensively analyze the learning mode and learning adaptability index of students, coordinate the learning progress and resource allocation among students, and optimize the arrangement of teaching tasks; the graph construction module is used to establish the association relationship between students, learning resources, and task content based on the learning behavior data and learning mode of students through a graph construction algorithm, and generate a knowledge graph between students' learning behavior and knowledge points, which is used to visually display the learning status, learning progress, and learning path of students.

[0025] In this implementation scheme, the learning behavior analysis module: the core function of this module is to monitor the various behavioral data of students in the learning process in real time through the Internet of Things devices, such as learning time, interaction frequency, task completion, etc. By clustering these behavioral data, the system can identify the learning patterns of students, including their learning interests, learning methods and learning progress. Cluster analysis technology can group similar students into a group, thereby providing a basis for subsequent teaching content recommendations. Learning content recommendation module: this module matches students through collaborative filtering algorithms based on the learning patterns of students obtained from the "learning behavior analysis module". Collaborative filtering algorithms are a technology widely used in recommendation systems. It can provide personalized learning content and tasks for each student based on the student's historical learning data and similarity with other students. In addition, this module can also calculate the student's learning adaptability index, that is, measure the degree of matching between students and learning resources. When the student's adaptability index is low, the system will dynamically adjust the learning resources and task content to ensure that the student can learn in the most suitable learning environment for himself. Collaborative management module: this module comprehensively analyzes the student's learning pattern and learning adaptability index, with the aim of coordinating the learning progress and resource allocation between students. Through this module, the system can identify students who are lagging behind in progress, and adjust resource allocation to ensure that students can complete teaching tasks within the appropriate time. At the same time, the collaborative management module also helps to optimize the arrangement of teaching tasks and improve overall teaching efficiency, so that the learning progress of each student can be reasonably controlled, thereby improving the quality of teaching. Graph construction module: The graph construction module uses the students' learning behavior data and learning patterns to establish the relationship between students, learning resources and task content through the graph construction algorithm. The graph algorithm associates students with relevant learning content, tasks and knowledge points to form a dynamically updated knowledge graph. This graph can not only be used to display students' learning status and progress, but also to intuitively display students' learning paths, helping teaching staff understand each student's learning situation and adjust teaching strategies based on the graph information.

[0026] Specifically, the specific process of real-time monitoring of students' behavioral data during the learning process through the Internet of Things is as follows: The behavioral data of students during the learning process are collected in real time through wireless sensor networks, including the completion of learning tasks, task start and end time, learning progress, interaction frequency, learning time, and students' use of different learning resources.

[0027] In this implementation scheme, wireless sensor network (WSN) application: This system uses wireless sensor network (WSN) technology to arrange various sensors in the learning environment to collect the behavioral data of students in the learning process in real time. Sensors can be deployed on students' personal devices (such as smart wearable devices, mobile phones, tablets, etc.) or in the classroom environment (such as desktop sensors, cameras, smart whiteboards, etc.). Through these sensors, students' learning behavior can be monitored in real time in all aspects. Collecting behavioral data: The system continuously collects students' learning behavior data through wireless sensor networks, mainly including the following categories: Completion of learning tasks: Record whether students have completed the specified learning tasks, and the quality or accuracy of task completion. Task start and end time: Record the time when students start and end tasks, which helps analyze the learning time and the progress of tasks. Learning progress: Track students' learning progress in real time based on indicators such as task completion and mastery of the content learned. Interaction frequency: Monitor the number of interactions between students and teaching platforms, classmates, teachers, etc. during the learning process, including asking questions, answering questions, participating in discussions, etc. Learning time: Record the actual learning time of students in different time periods, including classroom learning, online learning or self-study time. Students' use of different learning resources: Track the frequency and duration of students' use of various learning resources (such as courseware, video tutorials, exercise banks, laboratory equipment, etc.), and evaluate the students' dependence on resources. Real-time data transmission and processing: All collected behavioral data are transmitted to the data processing platform through the wireless sensor network, and the platform processes and analyzes the data in real time. The real-time nature of these data enables the teaching system to respond quickly to students' learning behavior and provide data support for subsequent learning recommendations, progress adjustments, etc.

[0028] Specifically, the specific process of extracting students' learning behavior characteristics through cluster analysis and identifying students' learning patterns is as follows: based on students' behavioral data, select key features that reflect students' learning behavior, including task completion, learning time, learning progress, and interaction frequency; cluster the data through the K-means clustering algorithm to identify different student groups, set the number of clusters, extract the core behavioral characteristics of each group, such as learning time, interaction frequency, and task completion, and divide students into different groups based on their learning behavior characteristics; based on the behavioral characteristics of the groups, identify students' learning patterns, including active, passive, and dependent; divide students into different learning patterns based on the results of cluster analysis to form a classification of learning behavior patterns.

[0029] In this implementation, the K-means algorithm is used to perform cluster analysis on the students’ behavior data. The goal is to minimize the distance between each student and the center point (centroid) of the cluster to which it belongs. ;in: Indicates the number of students, is the set number of clusters, For students Is it a cluster? The indicator function (if the student Belongs to cluster ,but , otherwise 0), For students behavioral data, Cluster The center of mass, Indicates students With cluster The Euclidean distance between the centroids of . Behavioral feature extraction: According to the clustering results, the core behavioral features of each cluster are extracted, including learning time, interaction frequency, and task completion. These features reflect the typical learning behavior of the students in this group. Learning pattern recognition, active type: students actively participate in learning, interact frequently, complete tasks well, and have a moderate learning time; passive type: students participate less, have a low interaction frequency, a short learning time, and poor task completion; dependent type: students rely on external prompts or support, have a slow learning progress, but can complete tasks through guidance. Classification and labeling: students are divided into different learning pattern groups according to the results of cluster analysis, and each student is assigned a corresponding learning pattern label. After this process is completed, the students will be labeled as active, passive, or dependent, forming a classification of learning behavior patterns.

[0030] Specifically, the specific process of matching the learning patterns of students in the teaching database through collaborative filtering algorithms according to their learning patterns is as follows: based on the students' learning patterns and their behavioral characteristics, they are compared with the behavioral patterns of students in the teaching database; the similarity between students and other students is calculated through collaborative filtering algorithms, and students with similar learning patterns are selected as the reference group; based on the learning behavior and resource usage of the reference group, the most suitable learning resources and tasks for students are inferred and recommended.

[0031] In this implementation scheme, the learning mode and behavior characteristics of students: First, the system will analyze the learning mode of students based on the real-time collected learning behavior data of students (such as learning time, task completion, interaction frequency, learning progress, etc.). Common learning modes include active, passive, dependent, etc. Each student will be classified into a learning mode, and the behavior characteristics related to the mode will be recorded. Comparison with the student behavior mode in the teaching database: Then, the system compares the student's learning mode with the learning mode of other students in the teaching database. The teaching database stores a large number of students' learning mode and behavior data. By comparing with the student behavior patterns in these databases, a reference group similar to the target student's learning mode can be found. Collaborative filtering algorithm: Collaborative filtering algorithm is a commonly used recommendation algorithm that can predict user preferences or behaviors based on the similarities between users. In this system, the specific steps of the collaborative filtering algorithm are as follows: First, the system calculates the similarity between students based on the learning behavior characteristics of the target student and other students (such as learning time, learning progress, interaction frequency, etc.). For example, assuming that the data similarity between student A and student B in terms of study time, task completion, etc. is relatively high, it means that the learning patterns of the two may also be relatively similar. Based on the calculated similarity, the system will select students with similar learning patterns to the target students as the reference group. The learning patterns and behavioral characteristics of these reference groups will serve as the basis for recommendations. Recommended learning resources and tasks: Finally, the system will infer the most suitable learning resources and tasks for the target students based on the learning behavior and resource usage of the reference group. For example, if most of the students in the reference group use a certain type of learning resource (such as video tutorials, online exercises, etc.) and perform well in task completion, the system will recommend these learning resources and tasks to the target students to optimize the students' learning path.

[0032] Specifically, the specific process of obtaining the learning adaptability index and dynamically adjusting the learning resources and task content is as follows: based on the behavioral characteristics of the students, the similarity between the target students and other students in the teaching database is calculated through the Pearson correlation coefficient, and the behavioral consistency between the target students and the reference students is measured; based on the similarity between the target students and the reference students, combined with the students' learning behavior characteristics, the students' learning adaptability index is comprehensively evaluated; based on the learning adaptability index, the learning resources and task content are dynamically adjusted.

[0033] In this implementation scheme, first, based on the behavioral characteristics of the students, the similarity between the target student and other students is calculated using the Pearson correlation coefficient. The Pearson correlation coefficient calculation formula is: ;in: : Pearson correlation coefficient between student A and student B. and : The values ​​of student A and student B on the j-th behavioral characteristic (learning time, task completion status). and : The mean of the behavioral characteristics of students A and B, calculated as: ;k: The total number of student behavior characteristics. After calculating the similarity between students through the Pearson correlation coefficient, the system compares the target student with multiple reference students, and then conducts a comprehensive evaluation based on the similarity to obtain the target student's learning adaptability index. The learning adaptability index is used to measure the degree of match between the target student and the reference group in the learning process. The comprehensive evaluation formula is as follows: ;in: : Learning adaptability index of target student A :Target student A and reference student The similarity. :Reference students The learning behavior weight is used to reflect the influence of the student in the group, which is usually related to the student's learning effect (such as task completion, learning progress, etc.). Represents the cth reference student. :Reference to the total number of students. Dynamically adjust learning resources and task content: Based on the learning adaptability index of the target students, the system can dynamically adjust the learning resources and task content of the students. The higher the learning adaptability index, the more the target students are adapted to the current learning resources and task arrangements during the learning process; otherwise, it is necessary to adjust the task content or recommend different learning resources. The specific adjustments are: ;in: : The intensity of recommended learning resources for target student A under the current learning task. : Initial learning resource intensity (number of recommended tasks, type of learning resources). λ: Adjustment factor, which controls the influence of learning adaptability index on learning resource adjustment. :The threshold of the learning adaptability index, usually a critical value is set. Students below this value need to adjust their learning resources. : The learning adaptability index of target student A.

[0034] Specifically, the specific process of comprehensively analyzing the students' learning patterns and learning adaptability index and coordinating the learning progress and resource allocation among the students is as follows: Based on the students' learning pattern data and learning adaptability index, the students' learning progress is monitored in real time to identify students with deviations in learning progress; Based on the students' learning adaptability index, the students' adaptability to different tasks and resources is evaluated, and the students are grouped according to their learning progress and adaptability index; and based on the differences in learning progress among students, the priority of learning resources and the allocation of task content are adjusted.

[0035] In this implementation scheme, learning progress is monitored in real time: the system tracks the learning progress of each student in real time through the student's learning pattern data and adaptability index. If some students' progress is slow or deviates from the planned progress, the system will mark it for further adjustment. Evaluate adaptability: Through the student's learning adaptability index, the system evaluates the student's adaptability to different tasks and resources. For example, some students may be more adaptable to certain learning resources, while other students may need more coaching or simplified task content. Grouping and resource adjustment: The system groups students according to their progress and adaptability index. For students with slower learning progress or weaker adaptability, the system will assign them more supportive resources and tasks; for students with faster learning progress, more challenging tasks may be assigned. This ensures that each student can learn with resources and tasks that suit their needs, thereby improving learning efficiency.

[0036] Specifically, based on the students' learning behavior data and learning patterns, the specific process of arranging the association relationship between students, learning resources, and task content through a graph construction algorithm is as follows: According to the students' learning patterns and behavioral characteristics, the attributes of learning resources and task content are determined, including difficulty, type, and related knowledge points; students, learning resources, and task content are used as nodes through knowledge graph algorithms, and edges between nodes are established to represent their association relationship; multi-dimensional association relationships between students and learning resources and task content are established by calculating the similarity and weight between nodes in the graph; according to the students' learning behavior and learning patterns, the weights of nodes and edges in the graph are dynamically updated to ensure that the graph can reflect the students' latest learning needs.

[0037] In this implementation scheme, the attributes of learning resources and task contents are determined: First, by analyzing the learning behavior and learning patterns of students, various attributes of learning resources and task contents are determined, such as the difficulty and type (video, document, test, etc.) of learning resources and the knowledge points involved in the task content. These attributes help the system understand the characteristics of each resource and task, and facilitate the subsequent establishment of associations. Construct the association relationship between nodes and edges: In the graph, students, learning resources and task contents are regarded as nodes of the graph. The association relationship between nodes is represented by "edges". For example, there may be a learning relationship between students and a certain task content, and the task content is also related to a specific learning resource (such as a textbook or video). Through the knowledge graph algorithm, the relationship between nodes will be dynamically calculated. Calculate similarity and weight: The similarity and weight between nodes are calculated based on the learning behavior and learning pattern of students. For example, if a student frequently uses a resource or completes a task many times, the system will consider the resource and task to be more important to the student, thereby increasing the weight between the nodes. The higher the weight, the stronger the association between the student and the resource or task. Dynamically update the graph: As students' learning behaviors change, the weights of nodes and edges in the graph will also be adjusted dynamically. For example, if a student's learning progress accelerates, the system will adjust the relationship between the student and the resources or tasks based on their latest behavior patterns to better suit the student's current learning needs. In this way, the graph is always kept up to date and can reflect the student's learning needs and resource matching in real time.

[0038] Specifically, the specific process of generating a knowledge graph between students' learning behaviors and knowledge points is as follows: based on the association between students, learning resources, and task content, a mapping relationship graph between students' learning behaviors and knowledge points is generated, and the similarity between students and each knowledge point is calculated to represent the knowledge points mastered by students and the knowledge points to be mastered; the knowledge graph is dynamically updated to adjust the association between students and knowledge points according to students' learning progress, learning needs, and task completion, so as to reflect students' learning status in real time.

[0039] In this implementation scheme, the association between students, learning resources, task content and knowledge points is determined: First, by establishing the association between students, learning resources and task content (such as which learning resources students use when learning a certain task), the system can infer the connection between students and related knowledge points. For example, completing a task may involve multiple knowledge points, and the system establishes a preliminary association between students and these knowledge points through the record of learning behavior. Calculate the similarity between students and knowledge points: Next, by analyzing the learning behavior of students (such as task completion, learning time, etc.), the system calculates the similarity between students and each knowledge point. This process usually uses collaborative filtering or other similarity calculation algorithms, such as cosine similarity or Pearson correlation coefficient. For example, if a student performs well on a task, it is considered that the student has mastered the knowledge points related to the task. The system will calculate the similarity between the student and these knowledge points and generate a mapping relationship diagram. Knowledge points mastered by the student and knowledge points to be mastered: Through the calculated similarity, the system can identify the knowledge points that the student has mastered and the knowledge points to be mastered. The mastered knowledge points have a higher similarity value, while the knowledge points to be mastered are relatively low. This mapping relationship helps the system clearly understand the students' current knowledge mastery and provides a basis for personalized learning resource recommendations. Dynamic update of knowledge graph: As students' learning progress, task completion, and learning needs change, the knowledge graph will be continuously updated. For example, when students complete a new learning task, the system will automatically update the association between the students and the relevant knowledge points, and recalculate the similarity between the students and each knowledge point. If a student has made significant progress in a certain field, the system will increase the weight of the knowledge points in that field. Otherwise, the system will mark them as knowledge points to be mastered. This real-time update mechanism ensures that the graph reflects the students' latest learning status. Real-time reflection of students' learning status: Through this dynamic knowledge graph construction process, the system can accurately display the students' learning progress on different knowledge points, help teachers or systems monitor students' learning situation in real time, and provide targeted resource recommendations and learning support.

[0040] The teaching and training method based on the Internet of Things includes the following steps: S1. Real-time monitoring of students' behavioral data in the learning process through the Internet of Things, extracting students' learning behavior characteristics through cluster analysis, and identifying students' learning patterns; S2. According to students' learning patterns, matching students' learning patterns in the teaching database through collaborative filtering algorithms, obtaining learning adaptability indexes, which are used to measure students' adaptability to learning resources, and dynamically adjust learning resources and task content; S3. Comprehensively analyzing students' learning patterns and learning adaptability indexes, coordinating learning progress and resource allocation among students, and optimizing the arrangement of teaching tasks; S4. Based on students' learning behavior data and learning patterns, establishing the association between students, learning resources, and task content through a graph construction algorithm, generating a knowledge graph between students' learning behaviors and knowledge points, and visually displaying students' learning status, learning progress, and learning paths.

[0041] In this implementation scheme, step S1: monitor the behavioral data of students in the learning process in real time through the Internet of Things device, such as the completion of learning tasks, learning time, etc. Then extract the learning behavior characteristics of students through the cluster analysis method, so as to identify the learning patterns of different students. For example, students are divided into different groups such as active and passive. Step S2: According to the learning pattern of the students, use the collaborative filtering algorithm to compare with the learning patterns of other students in the teaching database to obtain an index that measures the adaptability of students to learning resources. This learning adaptability index is used to dynamically adjust the learning resources and task content to adapt to the learning needs and progress of different students. Step S3: Based on the comprehensive analysis of the learning pattern and learning adaptability index of the students, monitor the learning progress of the students in real time, and coordinate the learning progress and resource allocation among the students. By optimizing the arrangement of teaching tasks, ensure that each student receives appropriate learning resources and tasks at the right time to avoid lagging learning progress or waste of resources. Step S4: Through the graph construction algorithm, based on the learning behavior data and learning pattern of the students, establish the association between students, learning resources, and task content, and generate a knowledge graph between the learning behavior of the students and the knowledge points. These maps help visualize students' learning status, learning progress, and learning paths, thereby providing teachers with accurate learning feedback.

[0042] In summary, this application has at least the following effects: The teaching and training system and method based on the Internet of Things can dynamically adjust the learning content and tasks and provide personalized learning paths by real-time monitoring of students' learning behavior, combined with cluster analysis and collaborative filtering algorithms, so as to better meet the learning needs of different students and improve learning efficiency. Based on the students' learning patterns and adaptability indexes, the system can optimize the allocation of teaching resources and tasks, coordinate the students' learning progress, avoid waste of resources, and ensure that students complete learning tasks at a reasonable pace. By generating the relationship between students, learning resources, task content and knowledge points through the graph construction algorithm, the system can display the students' learning progress and knowledge mastery in real time, provide teachers with intuitive learning status feedback, and help teachers adjust teaching strategies in a timely manner. The system can continuously track students' learning behavior, dynamically optimize learning resources and task arrangements, help students master knowledge points more efficiently, and ultimately improve overall learning effects and efficiency.

[0043] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0044] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0045] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0047] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0048] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. The teaching and training system based on the Internet of Things is characterized by: It includes the following modules: learning behavior analysis module, learning content recommendation module, collaborative management module, and graph construction module; The learning behavior analysis module is used to monitor the behavior data of students in the learning process in real time through the Internet of Things, extract the learning behavior characteristics of students through cluster analysis, and identify the learning mode of students; The learning content recommendation module is used to match the learning patterns of students in the teaching database through a collaborative filtering algorithm according to the learning patterns of students, obtain a learning adaptability index, and measure the adaptability of students to learning resources, and dynamically adjust learning resources and task content; The collaborative management module is used to comprehensively analyze the learning patterns and learning adaptability indexes of students, coordinate the learning progress and resource allocation among students, and optimize the arrangement of teaching tasks; The graph construction module is used to establish the relationship between students, learning resources, and task content based on the students' learning behavior data and learning patterns through a graph construction algorithm, and generate a knowledge graph between students' learning behaviors and knowledge points, which is used to visualize the students' learning status, learning progress, and learning path.

2. The teaching and training system based on the Internet of Things according to claim 1 is characterized in that: The specific process of real-time monitoring of students’ behavioral data during the learning process through the Internet of Things is as follows: Through wireless sensor networks, students' behavioral data during the learning process are collected in real time, including the completion of learning tasks, task start and end time, learning progress, interaction frequency, learning time, and students' use of different learning resources.

3. The teaching and training system based on the Internet of Things according to claim 2 is characterized in that: The specific process of extracting students’ learning behavior characteristics through cluster analysis and identifying students’ learning patterns is as follows: Based on the students’ behavioral data, select key features that reflect the students’ learning behavior, including task completion, learning time, learning progress, and interaction frequency; The K-means clustering algorithm is used to cluster the data, identify different groups of students, set the number of clusters, extract the core behavioral characteristics of each group, such as learning time, interaction frequency, and task completion, and divide the students into different groups based on their learning behavior characteristics; Based on the behavioral characteristics of the group, identify the learners' learning patterns, including active, passive, and dependent; According to the results of cluster analysis, the students are divided into different learning modes to form a classification of learning behavior patterns.

4. The teaching and training system based on the Internet of Things according to claim 3 is characterized in that: According to the students' learning patterns, the specific process of matching the students' learning patterns in the teaching database through the collaborative filtering algorithm is as follows: According to the students' learning patterns and behavioral characteristics, they are compared with the students' behavioral patterns in the teaching database; The similarity between the student and other students is calculated through collaborative filtering algorithm, and students with similar learning patterns are selected as the reference group; Based on the learning behavior and resource usage of the reference group, the most suitable learning resources and tasks for the students are inferred and recommended.

5. The teaching and training system based on the Internet of Things according to claim 4 is characterized in that: The specific process of obtaining the learning adaptability index and dynamically adjusting learning resources and task content is as follows: Based on the behavioral characteristics of the students, the similarity between the target students and other students in the teaching database is calculated through the Pearson correlation coefficient to measure the behavioral consistency between the target students and the reference students; Based on the similarity between the target students and the reference students, combined with the students' learning behavior characteristics, the students' learning adaptability index is comprehensively evaluated; Dynamically adjust learning resources and task content based on the learning adaptability index.

6. The teaching and training system based on the Internet of Things according to claim 5 is characterized in that: The specific process of comprehensively analyzing the students' learning patterns and learning adaptability indexes and coordinating the learning progress and resource allocation among the students is as follows: Based on the students’ learning mode data and learning adaptability index, the students’ learning progress is monitored in real time, and students with deviations in learning progress are identified; Based on the learning adaptability index, the students' adaptability to different tasks and resources is evaluated, and the students are grouped according to their learning progress and adaptability index. In addition, the priority of learning resources and the distribution of task content are adjusted based on the differences in learning progress among students.

7. The teaching and training system based on the Internet of Things according to claim 6 is characterized in that: Based on the students’ learning behavior data and learning patterns, the specific process of establishing the relationship between students, learning resources, and task content through the graph construction algorithm is as follows: Determine the attributes of learning resources and task content, including difficulty, type, and related knowledge points, based on the learners’ learning patterns and behavioral characteristics; Through knowledge graph algorithms, students, learning resources, and task contents are taken as nodes, and edges between nodes are established to represent their associations; By calculating the similarity and weight between nodes in the graph, a multi-dimensional relationship between students and learning resources and task content is established; According to the students' learning behaviors and learning patterns, the weights of nodes and edges in the graph are dynamically updated to ensure that the graph can reflect the students' latest learning needs.

8. The teaching and training system based on the Internet of Things according to claim 7 is characterized in that: The specific process of generating a knowledge graph between students’ learning behaviors and knowledge points is as follows: Based on the relationship between students, learning resources, and task content, a mapping relationship diagram between students' learning behaviors and knowledge points is generated. By calculating the similarity between students and each knowledge point, the knowledge points that students have mastered and the knowledge points that need to be mastered are represented. The knowledge graph is updated dynamically to adjust the relationship between students and knowledge points according to their learning progress, learning needs and task completion, reflecting the students' learning status in real time.

9. A teaching and training method based on the Internet of Things, applied to a teaching and training system based on the Internet of Things as claimed in any one of claims 1 to 8, characterized in that: The following steps are involved: S1. Use the Internet of Things to monitor students’ behavior data in real time during the learning process, extract students’ learning behavior characteristics through cluster analysis, and identify students’ learning patterns; S2. According to the learning patterns of students, the collaborative filtering algorithm is used to match the learning patterns of students in the teaching database to obtain the learning adaptability index, which is used to measure the adaptability of students to learning resources and dynamically adjust learning resources and task content; S3. Comprehensively analyze students’ learning patterns and learning adaptability index, coordinate learning progress and resource allocation among students, and optimize the arrangement of teaching tasks; S4. Based on the students’ learning behavior data and learning patterns, the relationship between students, learning resources, and task content is established through a graph construction algorithm, and a knowledge graph between students’ learning behaviors and knowledge points is generated to visualize the students’ learning status, learning progress, and learning path.

Images