Individual recommendation system and method for preschool education courses based on Internet of Things

Abstract

The invention discloses a pre-school education course personalized recommendation system and method based on the Internet of Things, and relates to the technical field of pre-school course design, and the system comprises a data collection module, a cloud server and a user module. According to the preschool education course personalized recommendation system and method based on the Internet of Things, by collecting behavior and performance data of children in different learning activities, the learning interest of each child can be analyzed, so that personalized preschool education courses are provided, the requirements of individual children are met, and the interestingness of the children is improved. The data collection module collects behavior and performance data of children, the behavior and performance data include learning data, interaction data and emotion data, the children can develop good interpersonal relation and emotion management ability, and along with increase of user feature data, recommendation can be automatically updated based on a collaborative filtering algorithm, and timeliness and correlation of recommendation can be kept.

Description

Technical Field

[0001] The present invention relates to the technical field of preschool curriculum design, and in particular to a personalized recommendation system and method for preschool education courses based on the Internet of Things. Background Art

[0002] Although existing preschool programs provide many supports for children's early development, they also have some generally recognized shortcomings. Some programs may rely too much on structured teaching and assessment, which may limit children's creativity and spirit of exploration; some programs may overemphasize the early learning of academic skills and neglect the development of social-emotional skills, which are equally important for children's all-round development; some programs may not be well adapted to children with different backgrounds and needs, especially for children with special needs or children from multicultural backgrounds.

[0003] Therefore, there is an urgent need for a personalized recommendation system and method for preschool education courses based on the Internet of Things, which aims to solve the above problems and better meet the diverse needs of children and families by recommending more efficient, targeted and inclusive preschool education courses. Summary of the invention

[0004] The purpose of the present invention is to provide a personalized recommendation system and method for preschool education courses based on the Internet of Things to solve the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a personalized recommendation system for preschool education courses based on the Internet of Things, comprising a data acquisition module, a cloud server and a user module;

[0006] The data collection module includes a behavior data collection unit, an interaction data collection unit, an emotion data collection unit, a learning achievement data collection unit and a physiological data collection unit, which are used to collect children's behavior data, interaction data, emotion data, learning achievement data and physiological data, and transmit the children's behavior data, interaction data, emotion data, learning achievement data and physiological data to the cloud server;

[0007] The cloud server includes a data integration and preprocessing unit and a feature extraction unit, which receives data from the data acquisition module and extracts feature data in the children's learning activities, and transmits the feature data in the children's learning activities to the user module;

[0008] The characteristic data of children's learning activities include the frequency of children's activity participation, task completion speed, reaction time, frequency of emotional changes, interaction type, children's heart rate changes and activity volume, and regular test scores;

[0009] The user module includes a user login terminal and a course recommendation engine, which receives and stores characteristic data in children's learning activities and recommends personalized courses.

[0010] Furthermore, the behavior data collection unit records the time and frequency of children's participation in various teaching activities, monitors the ability and efficiency of children in completing tasks, monitors the focus of children's attention through eye tracking technology, and transmits the children's behavior data to the data integration and pre-processing unit;

[0011] The interactive data collection unit records the child's response time to questions and tasks, the number and manner of the child's interaction with others, and the manner in which the child uses educational tools and equipment, and transmits the interactive data to the data integration and pre-processing unit;

[0012] The emotion data acquisition unit uses a camera and a microphone to capture the child's expression and voice, analyzes the emotional state, monitors the heart rate and skin electrical activity through a wearable device to assess the emotion and stress level, and transmits the emotion data to the data integration and preprocessing unit;

[0013] The learning achievement data collection unit collects the children's usual test scores and transmits the learning achievement data to the data integration and preprocessing unit;

[0014] The physiological data acquisition unit collects the child's health information and growth data, the health information includes sleep quality and activity level, and the growth data includes height and weight, and transmits the physiological data to the data integration and preprocessing unit.

[0015] Furthermore, the data integration and preprocessing unit integrates the collected data to establish a unified data warehouse, and cleans the data, including removing outliers, filling missing values, and normalizing the data to ensure data quality. The data integration and preprocessing unit transmits the processed data to the feature extraction unit;

[0016] The feature extraction unit extracts children's activity participation frequency and task completion speed from behavioral data, extracts children's reaction time, emotion change frequency and interaction type from interaction data and emotion data, extracts children's heart rate changes and activity amount from physiological data, and transmits feature data in children's learning activities to the user login terminal.

[0017] Furthermore, the user login terminal is used to verify the identity of the user and authorize him to access the course recommendation engine.

[0018] Furthermore, the course recommendation engine searches a large number of children on the Internet and their ratings of various courses, and stores them in a database, and then uses feature data in children's learning activities to recommend personalized courses based on a collaborative filtering algorithm to meet the unique needs of each child.

[0019] Furthermore, the collaborative filtering algorithm is specifically as follows:

[0020] Get user information:

[0021] The characteristic data in children's learning activities are converted into user ratings of various courses in the database through weighting, and a co-occurrence matrix is ​​generated;

[0022] Similarity comparison:

[0023] The Pearson coefficient is used to calculate the user similarity between logged-in user i and user j in the database. The Pearson coefficient is Among them, R i,p represents the rating of course p by user i, represents the rating of user i on all courses in the database, and p represents the set of all courses;

[0024] Generate recommendations:

[0025] Find a group of other users with the highest similarity for each logged-in user, namely the neighbor set, and predict the course ratings of the logged-in user through the neighbor set's course ratings, so as to recommend courses with higher prediction values ​​to the logged-in user.

[0026] A personalized recommendation method for preschool education courses based on the Internet of Things, which is applicable to the personalized recommendation system for preschool education courses based on the Internet of Things, specifically comprises the following steps:

[0027] First, the data collection module collects children’s behavior data, interaction data, emotional data, learning outcome data, and physiological data, and transmits them to the cloud server;

[0028] Secondly, the cloud server integration and pre-processing unit uses the received data to extract characteristic data from children’s learning activities and transmits it to the user module;

[0029] Finally, the user logs in to the system through the user login terminal, and the course recommendation engine recommends personalized courses to the user who logs in to the system.

[0030] Compared with the prior art, the present invention provides a personalized recommendation system and method for preschool education courses based on the Internet of Things:

[0031] 1. By collecting children’s behavior and performance data in different learning activities, the system can analyze each child’s learning interests and provide personalized preschool education courses to meet the needs of individual children;

[0032] Second, the data collection module collects children’s behavior and performance data, including not only learning data, but also interaction data and emotional data, which is conducive to children’s development of good interpersonal relationships and emotional management skills;

[0033] 3. As user feature data increases, collaborative filtering algorithms can automatically update recommendations to maintain their timeliness and relevance. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0035] Figure 1 A schematic diagram of the overall structure of the system provided by an embodiment of the present invention;

[0036] Figure 2 A first schematic diagram of a partial structure of a system provided by an embodiment of the present invention;

[0037] Figure 3 A second schematic diagram of a partial structure of a system provided by an embodiment of the present invention;

[0038] Figure 4 A flow chart of a method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0040] Embodiment 1:

[0041] See also Figure 1-Figure 3 ,A personalized recommendation system for preschool education courses based on the Internet of Things, including a data collection module, a cloud server and a user module;

[0042] The data collection module includes a behavior data collection unit, an interaction data collection unit, an emotion data collection unit, a learning achievement data collection unit and a physiological data collection unit, which are used to collect children's behavior data, interaction data, emotion data, learning achievement data and physiological data, and transmit the children's behavior data, interaction data, emotion data, learning achievement data and physiological data to the cloud server;

[0043] The cloud server includes a data integration and preprocessing unit and a feature extraction unit, which receives data from the data acquisition module and extracts feature data in the children's learning activities, and transmits the feature data in the children's learning activities to the user module;

[0044] The characteristic data of children's learning activities include the frequency of children's participation in activities, the speed of task completion, reaction time, the frequency of emotional changes, the type of interaction, the changes in children's heart rate and the amount of activity, and the usual test scores;

[0045] The user module includes a user login terminal and a course recommendation engine, which receives and stores feature data in children's learning activities and recommends personalized courses.

[0046] The behavioral data collection unit records the time and frequency of children's participation in various teaching activities, monitors children's ability and efficiency in completing tasks, monitors children's attention focus through eye tracking technology, and transmits children's behavioral data to the data integration and pre-processing unit;

[0047] The interactive data collection unit records the children's response time to questions and tasks, the number and manner of children's interactions with others, and the manner in which children use educational tools and equipment, and it transmits the interactive data to the data integration and pre-processing unit;

[0048] The emotional data collection unit uses a camera and a microphone to capture the child's expression and voice, analyzes the emotional state, monitors the heart rate and skin electrical activity through wearable devices to assess emotions and stress levels, and transmits the emotional data to the data integration and pre-processing unit;

[0049] The learning achievement data collection unit collects children's usual test scores, and transmits the learning achievement data to the data integration and pre-processing unit;

[0050] The physiological data acquisition unit collects children's health information and growth data, the health information includes sleep quality and activity level, and the growth data includes height and weight, and transmits the physiological data to the data integration and preprocessing unit.

[0051] The data integration and preprocessing unit integrates the collected data, establishes a unified data warehouse, and cleans the data, including removing outliers, filling missing values, and normalizing the data to ensure data quality. The data integration and preprocessing unit transmits the processed data to the feature extraction unit;

[0052] The feature extraction unit extracts children's activity participation frequency and task completion speed from the behavioral data, extracts children's reaction time, frequency of emotional changes and interaction type from the interactive data and emotional data, extracts children's heart rate changes and activity volume from the physiological data, and transmits the feature data of children's learning activities to the user login terminal.

[0053] The user login terminal is used to verify the user's identity and authorize them to access the course recommendation engine.

[0054] The course recommendation engine searches a large number of children on the Internet and their ratings of various courses, stores them in the database, and then uses the feature data in children's learning activities to recommend personalized courses based on collaborative filtering algorithms to meet the unique needs of each child.

[0055] The specific details based on collaborative filtering algorithm are as follows:

[0056] Get user information:

[0057] The characteristic data in children's learning activities are converted into user ratings of various courses in the database through weighting, and a co-occurrence matrix is ​​generated;

[0058] Similarity comparison:

[0059] The Pearson coefficient is used to calculate the user similarity between logged-in user i and user j in the database. The Pearson coefficient is Among them, R i,p represents the rating of course p by user i, represents the rating of user i on all courses in the database, and p represents the set of all courses;

[0060] Generate recommendations:

[0061] Find a group of other users with the highest similarity for each logged-in user, namely the neighbor set, and predict the course ratings of the logged-in user through the neighbor set's course ratings, so as to recommend courses with higher prediction values ​​to the logged-in user.

[0062] Specific implementation method: According to different experimental equipment, the user collects children's behavior data, interaction data, emotional data, learning outcome data and physiological data through the data collection module, and transmits the children's behavior data, interaction data, emotional data, learning outcome data and physiological data to the data integration and preprocessing unit of the cloud server. The data integration and preprocessing unit cleans the data, including removing outliers, filling missing values, and normalizing the data to ensure data quality. The data integration and preprocessing unit transmits the processed data to the feature extraction unit. The feature extraction unit extracts feature data from the processed data, namely, children's activity participation frequency, task completion speed, reaction time, emotional change frequency, interaction type, children's heart rate changes and activity volume, and regular test scores, and transmits the feature data to the user login end of the user module. At the same time, the user logs in to the system from the user login end and enters his or her identity information. After verifying the identity information, the login end authorizes the user to access the course recommendation engine. The course recommendation engine uses the feature data in children's learning activities to recommend personalized courses based on the collaborative filtering algorithm to meet the unique needs of each child.

[0063] Embodiment 2:

[0064] See also Figure 4 A personalized recommendation method for preschool education courses based on the Internet of Things is applicable to a personalized recommendation system for preschool education courses based on the Internet of Things, and specifically includes the following steps:

[0065] First, the data collection module collects children’s behavior data, interaction data, emotional data, learning outcome data, and physiological data, and transmits them to the cloud server;

[0066] Secondly, the cloud server integration and pre-processing unit uses the received data to extract characteristic data from children’s learning activities and transmits it to the user module;

[0067] Finally, the user logs in to the system through the user login terminal, and the course recommendation engine recommends personalized courses to the user who logs in to the system.

[0068] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A personalized recommendation system for preschool education courses based on the Internet of Things. It is characterized in that Includes data acquisition module, cloud server and user module; The data collection module includes a behavior data collection unit, an interaction data collection unit, an emotion data collection unit, a learning achievement data collection unit and a physiological data collection unit, which are used to collect children's behavior data, interaction data, emotion data, learning achievement data and physiological data, and transmit the children's behavior data, interaction data, emotion data, learning achievement data and physiological data to the cloud server; The cloud server includes a data integration and preprocessing unit and a feature extraction unit, which receives data from the data acquisition module and extracts feature data in the children's learning activities, and transmits the feature data in the children's learning activities to the user module; The characteristic data of children's learning activities include the frequency of children's activity participation, task completion speed, reaction time, frequency of emotional changes, interaction type, children's heart rate changes and activity volume, and regular test scores; The user module includes a user login terminal and a course recommendation engine, which receives and stores characteristic data in children's learning activities and recommends personalized courses.

2. According to claim 1, a personalized recommendation system for preschool education courses based on the Internet of Things, It is characterized in that The behavior data collection unit records the time and frequency of children's participation in various teaching activities, monitors the ability and efficiency of children to complete tasks, monitors the focus of children's attention through eye tracking technology, and transmits children's behavior data to the data integration and pre-processing unit; The interactive data collection unit records the child's response time to questions and tasks, the number and manner of the child's interaction with others, and the manner in which the child uses educational tools and equipment, and transmits the interactive data to the data integration and pre-processing unit; The emotion data acquisition unit uses a camera and a microphone to capture the child's expression and voice, analyzes the emotional state, monitors the heart rate and skin electrical activity through a wearable device to assess the emotion and stress level, and transmits the emotion data to the data integration and preprocessing unit; The learning achievement data collection unit collects the children's usual test scores and transmits the learning achievement data to the data integration and preprocessing unit; The physiological data acquisition unit collects the child's health information and growth data, the health information includes sleep quality and activity level, and the growth data includes height and weight, and transmits the physiological data to the data integration and preprocessing unit.

3. According to claim 2, a personalized recommendation system for preschool education courses based on the Internet of Things, It is characterized in that The data integration and preprocessing unit integrates the collected data to establish a unified data warehouse, and cleans the data, including removing outliers, filling missing values, and normalizing the data to ensure data quality. The data integration and preprocessing unit transmits the processed data to the feature extraction unit; The feature extraction unit extracts children's activity participation frequency and task completion speed from behavioral data, extracts children's reaction time, emotion change frequency and interaction type from interaction data and emotion data, extracts children's heart rate changes and activity amount from physiological data, and transmits feature data in children's learning activities to the user login terminal.

4. According to claim 1, a personalized recommendation system for preschool education courses based on the Internet of Things, It is characterized in that The user login terminal is used to verify the identity of the user and authorize him to access the course recommendation engine.

5. According to claim 4, a personalized recommendation system for preschool education courses based on the Internet of Things, It is characterized in that The course recommendation engine searches a large number of children on the Internet and their ratings of various courses, and stores them in a database, and then uses feature data in children's learning activities to recommend personalized courses based on a collaborative filtering algorithm to meet the unique needs of each child.

6. According to claim 5, a personalized recommendation system for preschool education courses based on the Internet of Things, It is characterized in that The collaborative filtering algorithm is as follows: Get user information: The characteristic data in children's learning activities are converted into user ratings of various courses in the database through weighting, and a co-occurrence matrix is ​​generated; Similarity comparison: The Pearson coefficient is used to calculate the user similarity between logged-in user i and user j in the database. The Pearson coefficient is Among them, R i,p represents the rating of course p by user i, represents the rating of user i on all courses in the database, and p represents the set of all courses; Generate recommendations: Find a group of other users with the highest similarity for each logged-in user, namely the neighbor set, and predict the course ratings of the logged-in user through the neighbor set's course ratings, so as to recommend courses with higher prediction values ​​to the logged-in user.

7. A personalized recommendation method for preschool education courses based on the Internet of Things. It is characterized in that It is applicable to a personalized recommendation system for preschool education courses based on the Internet of Things as described in any one of claims 1 to 6, specifically The following steps are involved: First, the data collection module collects children’s behavior data, interaction data, emotional data, learning outcome data, and physiological data, and transmits them to the cloud server; Secondly, the cloud server integration and pre-processing unit uses the received data to extract characteristic data from children’s learning activities and transmits it to the user module; Finally, the user logs in to the system through the user login terminal, and the course recommendation engine recommends personalized courses to the user who logs in to the system.

Images