KR102554239B1 - Online education system - Google Patents

Abstract

Embodiments include an evaluation management server 110 that evaluates and manages student abilities, a content creation server that generates coding content, sentence content, and melodic content, and a camera of a student terminal 30 to analyze a student's behavioral pattern for learning. A server 10 including any one or more of a learning management server 24 that manages and an aptitude test program server 250 that tests student temperament; A teacher terminal 20 that provides a blackboard screen, textbook screen, and student management screen on the first screen, and provides a virtual classroom screen and class attitude notification screen on the second screen; and a student terminal 30 providing a blackboard screen and textbook screen on a first screen and a virtual classroom screen on a second screen.

Description

Online education system {ONLINE EDUCATION SYSTEM}

Embodiments of the present invention perform diagnostic evaluation, academic evaluation, content creation, behavior pattern analysis, aptitude test, identify student's temperament, behavior, and aptitude, and provide learning contents corresponding to individual characteristics of each student. It's about the system.

Taking the prior art related to the online education system of the present invention as an example, the online education method of Patent Document 1 provides teaching material data only after a user logs on, thereby preventing illegal copying of online contents in advance.

In addition, the patent document 2 education system enhances the competitiveness and image of the academy by servicing the students belonging to the academy to study both online and offline, and generates revenue by joining online student members to famous teachers. Even academies that provide offline courses offer multiple courses to students online, register other academies as sister academies if necessary so that students can receive education online at other academies, , Selling to students, owning data derived from the learning of teachers and students belonging to the academy to prevent teachers and students from leaving, and generating revenue by buying and selling rental accounts, which are data storages for teachers and students who have left the school there is.

Conventional online education systems, like the present invention, have a problem in that they do not provide learning content suitable for individual students while performing any one or more of diagnostic evaluation, academic ability evaluation, content creation, behavior pattern analysis, and aptitude test.

As related prior art, there are Korean Patent Publication No. 10-2001-0050901 (title of invention: online education method) and Korean Patent Publication No. 10-2004-0088848 (name of invention: education system).

The background art described above is possessed or acquired by the inventor in the process of deriving the disclosure of the present application, and cannot necessarily be said to be known art disclosed to the general public prior to the present application.

Embodiments may provide an online education system that performs any one or more of diagnostic evaluation, academic ability evaluation, content creation, behavior pattern analysis, and aptitude test, and provides learning contents suitable for individual students.

In addition, the present invention performs the evaluation of any one or more of student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability, generates any one or more contents of sentences, coding, melodies, and learns Perform any one or more learning management of content provision, behavioral pattern learning, and behavioral pattern analysis, and conduct an aptitude test of any one or more of temperament determination, lunar conversion, color determination, relationship determination, shape determination, body care determination, and mind care determination An online training system can be provided.

In addition, it is possible to provide an online education system that calculates an aptitude test index corresponding to temperament, color, and figure items and provides learning contents corresponding to the calculated aptitude test index to a student terminal.

Technical tasks to be achieved in the embodiments are not limited to those mentioned above, and other technical tasks not mentioned will be considered by those skilled in the art from various embodiments to be described below. can

According to the embodiments, the online education system uses an evaluation management server 110 for evaluating and managing student abilities, a content creation server for generating coding content, sentence content, and melodic content, and a camera of the student terminal 30 to evaluate student performance. A server 10 including at least one of a learning management server 24 that analyzes behavior patterns and manages learning, and an aptitude test program server 250 that tests student temperament; A teacher terminal 20 that provides a blackboard screen, textbook screen, and student management screen on the first screen, and provides a virtual classroom screen and class attitude notification screen on the second screen; and a student terminal 30 providing a blackboard screen and textbook screen on the first screen and a virtual classroom screen on the second screen.

In addition, the evaluation management server 110 includes a reservation processing unit 120 for reserving an evaluation schedule and generating a reservation message so that capability evaluation is performed on the evaluation schedule; A question bank DB (130) for storing problems related to evaluation of student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, inquiry process ability, and academic ability diagnosis; Reading questions about student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability from the question bank DB (130), and providing them to the student terminal (30) to evaluate the student's ability diagnostic evaluation module 140; And the student's attitude, creative propensity, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability are read from the question bank DB (130), and provided to the student terminal (30), so that the student's It is characterized in that it includes; academic ability diagnosis evaluation module 150 for evaluating academic ability.

In addition, the content creation server, when an original content sentence is input (S10), analyzing one or more words among the words of the input sentence (S20); After the analysis step (S20), generating a new sentence by extracting words from the ontology-based database according to the analysis result (S30); and outputting the newly created sentence through a speaker or a screen (S40).

In addition, the content creation server, when the original content melody is input (S60), analyzing the chord for one or more bars of the chord of the input melody (S70); After the analysis step (S70), generating a new melody by extracting chords from the ontology-based database according to the analysis result (S80); and outputting the newly generated melody through a speaker or a screen (S90).

In addition, the learning management server 24 transmits predetermined learning content to the student terminal 30 upon request from the student terminal 30, and the student terminal 30 displays the learning content to the student. study (210); A behavior pattern learning unit 220 that performs artificial intelligence-based learning for predicting behavior patterns by collecting sensor data obtained from the student terminals 30 while a plurality of students are taking learning content as sensor data for learning. ; a behavior pattern analyzer 230 analyzing a behavior pattern based on the sensor data collected from the student terminal 30; and a learning management unit 240 controlling the learning content providing unit 210 to provide learning content corresponding to the analyzed behavior pattern.

In addition, the behavior pattern analyzer 230 includes a sensor data collection unit 231 that receives sensor data in which movement is detected from the student terminal 30 currently outputting learning content; and a behavior pattern prediction unit 232 that predicts a behavior pattern of a student who is learning learning content as one of viewing, writing, non-learning, and withdrawal by using the sensor data collected by the sensor data collection unit 231. It is characterized by including;

In addition, the learning management unit 240 determines whether the student's behavior pattern prediction result from the behavior pattern analysis unit 230 is any one of writing, non-learning, and leaving, while playing in the student terminal 30. a content control signal generating unit 241 generating a content control signal and transmitting the generated control signal to the student terminal 30; and when the student's behavior pattern prediction result from the behavior pattern analyzer 230 is either non-learning or leaving, task content to be output from the student terminal 30 is generated and sent to the student terminal 30. It is characterized in that it includes; a task content generator 242 to transmit.

In addition, the aptitude test program server 250 includes a disposition determining unit 251 which determines the disposition of the student terminal 30 by providing aptitude test questions to the student terminal 30; If the student's birthday information is in the solar calendar, the lunar conversion unit 252 converts it into the lunar calendar; a color determination unit 253 that reads color decisions of other student terminals 30 designated by the student terminal 30 and collects color decisions of the first student terminal 30 and the second student terminal 30; a relationship determination unit 254 analyzing and displaying a relationship between the first to third colors of the first student terminal 30 and the second student terminal 30; a figure determining unit 255 that determines by matching the figure selection information selected by the student terminal 30; a body care determining unit 256 matching the temperament determining information of the temperament determining unit 251, the shape selection information of the figure determining unit 255, and the blood type information to determine a physical condition; and a mind care determination unit 257 matching the disposition determination information of the disposition determination unit 251, the figure selection information of the figure determination unit 255, and preference and non-preference determination information to determine the individual's state of mind. characterized by

In the online education system according to an embodiment, the temperament determination unit 251 includes a student's score for a plurality of temperament test items, an average score for a plurality of temperament test items, an average score for a plurality of color test items, and Based on the average score of a plurality of shape test items, the student's temperament test score is calculated, and the color determining unit 253 calculates the student's score on a plurality of color test items and the average score on the plurality of temperament test items. The student's color test score is calculated based on the score, the average score for the plurality of color test items, and the average score for the plurality of shape test items, and the shape determination unit 255 calculates the student's color test score for the plurality of shape test items. The student's shape test score is calculated based on the score of the student, the average score for the plurality of temperament test items, the average score for the plurality of color test items, and the average score for the plurality of shape test items, and the temperament test score , An aptitude test index of the student may be calculated based on the color test score and the shape test score.

The aptitude test program server 250 may calculate the student's aptitude test index by applying weights corresponding to each of the temperament test score, the color test score, and the shape test score, and summing the weighted results. there is.

The aptitude test program server 250 calculates the student's aptitude test index using the following equation,

[mathematical expression]

는 모든 사용자의 모든 기질 검사 항목에 대한 평균 점수이고,

는 모든 사용자의 모든 색상 검사 항목에 대한 평균 점수이고,

는 모든 사용자의 모든 도형 검사 항목에 대한 평균 점수일 수 있다.In the above equation, F(p) is an aptitude test function that outputs the aptitude test index of subject p, a is a temperament test weight constant, xi is the score for the temperament test item of p, and n is the number of temperament test items , b is the color test weight constant, yi is the score for the color test item of p, m is the number of color test items, c is the shape test weight constant, zi is the score for the shape test item of p, and l is the number of geometry inspection items,

is the average score for all temperament test items of all users,

is the average score for all color check items for all users,

may be an average score for all figure inspection items of all users.

In addition, the aptitude test program server 250 calculates the aptitude test index using Equation 1, and requests the learning content corresponding to the aptitude test index to the learning management server 24 so that it is provided to the student terminal 30. .

According to embodiments, the present invention may have an effect of providing learning content suitable for individual students by performing at least one of diagnostic evaluation, academic ability evaluation, content creation, behavior pattern analysis, and aptitude test.

In addition, the present invention performs the evaluation of any one or more of student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability, generates any one or more contents of sentences, coding, melodies, and learns Perform any one or more learning management of content provision, behavioral pattern learning, and behavioral pattern analysis, and conduct an aptitude test of any one or more of temperament determination, lunar conversion, color determination, relationship determination, shape determination, body care determination, and mind care determination By performing this, it is possible to have the effect of providing learning contents suitable for each student's abilities, behaviors, and aptitudes.

In addition, the present invention has the effect of increasing the utilization of the non-face-to-face online education system by calculating the aptitude test index corresponding to the temperament, color, and figure items and providing the learning content corresponding to the calculated aptitude test index to the student terminal. can

Effects obtainable from the embodiments are not limited to the effects mentioned above, and other effects not mentioned are clearly derived and understood by those skilled in the art based on the detailed description below. It can be.

BRIEF DESCRIPTION OF THE DRAWINGS Included as part of the detailed description to aid understanding of the embodiments, the accompanying drawings provide various embodiments and, together with the detailed description, describe technical features of the various embodiments.
1 is an exemplary view showing an application screen according to an embodiment of the online education system of the present invention.
2 is a block diagram showing the configuration of the online education system of the present invention.
Figure 3 is a block diagram showing the configuration of the evaluation system of the online education system of Figure 2;
4 is a flowchart showing an operation of generating sentence content in the online education system of FIG. 2 .
FIG. 5 is a flowchart showing an operation of creating melody contents in the online education system of FIG. 2 .
Figure 6 is a block diagram showing the configuration of the learning management system of the online education system of Figure 2.
Figure 7 is a block diagram showing the configuration of the aptitude test system of the online education system of Figure 2;
9 is an exemplary view illustrating a system authentication configuration that grants authority to execute hardware resources, an operating system, the operation of a control unit, which is a core, and an operation of a control unit of the online education system according to the present invention.
10 is an exemplary view showing application of a neural network implemented in the online education system of the present invention.

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form not combined with other components or features. In addition, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may be changed. Some components or features of one embodiment may be included in another embodiment, or may be replaced with corresponding components or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of various embodiments are not described, and procedures or steps that can be understood by those skilled in the art are not described. did

Throughout the specification, when a part is said to "comprising" or "including" a certain element, it means that it may further include other elements, not excluding other elements, unless otherwise stated. do. In addition, terms such as “… unit”, “… unit”, and “module” described in the specification mean a unit that processes at least one function or operation, which is hardware or software or a combination of hardware and software. can be implemented as Also, “a or an”, “one”, “the” and like terms are used herein in the context of describing various embodiments (particularly in the context of the claims below). Unless otherwise indicated or clearly contradicted by context, both the singular and the plural can be used.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The detailed description set forth below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of various embodiments, and is not intended to represent a single embodiment.

In addition, specific terms used in various embodiments are provided to help understanding of various embodiments, and the use of these specific terms may be changed into other forms without departing from the technical spirit of various embodiments. .

1 is an exemplary view showing an application screen according to an embodiment of the online education system of the present invention.

The online education system is implemented in the server 10, and terminals accessing the online education system implemented in the server 10 may be the teacher terminal 20 and the student terminal 30. As shown in FIG. 1, the application screen implemented in the terminal includes an online education system name, a menu bar, and a menu tile. The menu bar may include evaluation of the online education system, content creation, learning management, and aptitude test, and the menu tile displays sub-menus of the menu selected in the menu bar in the form of tiles.

In the online education system, evaluation includes any one or more of student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability, and content creation includes any one or more of sentences, coding, and melodies. And, the learning management includes any one or more of the provision of learning contents, behavioral pattern learning, and behavioral pattern analysis, and the aptitude test includes temperament determination, lunar conversion, color determination, relationship determination, shape determination, body care determination, and mind care determination. includes

2 is a block diagram showing the configuration of the online education system of the present invention. Referring to FIG. 2, the online education system includes a server 10, a teacher terminal 20, and a student terminal 30.

The server 10 includes an evaluation management server 110, a content creation server, a learning management server 24, and an aptitude test program server 250. The evaluation management server 110 reads questions about student attitude, creative inclination, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability from the DB and provides them to the student terminal 30 to evaluate and manage student abilities. , The content creation server generates coding content, sentence content, and melody content and provides them to the teacher terminal 20 and the student terminal 30, and the learning management server 24 uses the camera of the student terminal 30 Learning is managed by analyzing behavior patterns, and the aptitude test program server 250 reads questions about temperament determination, lunar conversion, color determination, relationship determination, figure determination, body care determination, and mind care determination from the DB, and the student Provided to the terminal 30 to test the student's temperament.

The teacher terminal 20 provides a blackboard screen, textbook screen, and student management screen on the first screen, and provides a virtual classroom screen and class attitude notification screen on the second screen. The blackboard screen displays the blackboard, the textbook screen displays textbook contents, the student management screen displays the student list, the virtual classroom screen displays the 3D space of the virtual classroom, and the class attitude notification screen informs students' class attitude. display a message The virtual classroom screen may be provided in the form of virtual reality content, and the class attitude notification screen may display a message about class attitude by analyzing student behavior collected from the student terminal 30 .

The student terminal 30 provides a blackboard screen and textbook screen on the first screen, and provides a virtual classroom screen on the second screen. The blackboard screen displays a blackboard, the textbook screen displays textbook content, and the virtual classroom screen displays a 3D space of a virtual classroom. The virtual classroom screen may be provided in the form of virtual reality content.

FIG. 3 is a block diagram showing the configuration of the evaluation system of the online education system of FIG. 2. The evaluation system includes an evaluation management server 110, a reservation processing unit 120, a question bank DB 130, a diagnosis evaluation module 140, and an academic background diagnosis. evaluation module 150 .

The evaluation management server 110 controls the reservation processing unit 120, the question bank DB 130, the diagnosis evaluation module 140, and the academic ability diagnosis evaluation module 150 to control student attitude, creative disposition, logical thinking ability, and subject concept problem-solving ability. , creative problem-solving ability, and inquiry process ability are evaluated.

The reservation processing unit 120 reserves an evaluation schedule to systematically evaluate student abilities, and generates a reservation message so that ability evaluation is performed in the evaluation schedule. The reservation processing unit 120 transmits a reservation message to the student terminal 30 according to the evaluation schedule so that the student terminal 30 performs the ability evaluation.

The question bank DB (130) stores problems related to the evaluation of student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, inquiry process ability, and academic diagnosis evaluation, and the diagnosis evaluation module 140, academic diagnosis evaluation The module 150 is presented with an assessment question.

The diagnostic evaluation module 140 reads questions about student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability from the question bank DB 130, and provides them to the student terminal 30. Evaluate student abilities.

The academic ability diagnosis evaluation module 150 reads the academic ability evaluation problems for student attitude, creative propensity, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability from the question bank DB 130, and the student terminal 30 provided to evaluate the student's academic ability.

FIG. 4 is a flow chart showing an operation of generating sentence content in the online education system of FIG. 2. Referring to FIG. 4, when an original content sentence is input (S10), the content creation server first inputs one or more words from among the words of the input sentence. Analyze (S20). In the analysis (S20) process, all words may be analyzed in order to variableize each word constituting the input sentence (variableization method), or only one word may be analyzed in order to classify the entire sentence into one semantic unit. (How to structure). And, as an analysis criterion, it can be classified based on the word information classification system of the ontology-based database described above. After the analysis (S20), a new sentence is created by extracting words from the ontology-based database according to the analysis result (S30). At this time, in the case of sentence generation through a variableization method, a sentence is generated by replacing each word constituting the input sentence with a new word, and word components not included in the input sentence may be further included. Meanwhile, in the case of generating a sentence through a structuring method, it is configured to include any one of words constituting an input sentence. In addition, the structuring method may further include generating another sentence including one or more of words constituting the generated sentence. As described above, each word constituting the new sentence may be extracted from an ontology-based database. The newly created sentence is output through a speaker or a screen (S40) so that the user can recognize it. As described above, the sentence content generation method according to the embodiment of the present invention can be largely divided into a parameterize method and a structure method. The variableization method analyzes each word component (noun, pronoun, adjective, verb, adverb, etc.) of sentences constituting existing content as an object (semantic unit and interrelationship between them), and converts each word into another word corresponding to it. By replacing, new sentence content is created. The structuring method is a method of classifying and storing a set of sentences (paragraphs) constituting content as one semantic unit object, and substituting them in paragraph units similar to the parameterization method when creating new content.

FIG. 5 is a flow chart showing an operation of generating melody content in the online education system of FIG. 2. Referring to FIG. 5, when an original content melody is first input by a user (S60), one of the chords of the input melody Chords are analyzed for the above bars (S70). That is, all chords can be analyzed (parameterization method) to variableize each chord constituting the input melody, or only chords included in one measure can be analyzed to classify the entire melody into one semantic unit. (how to structure). And, as an analysis criterion, it can be classified based on the chord storage information classification system of the ontology-based database described above. After the analysis (S70), a new melody is created by extracting chords from the ontology-based database according to the analysis result (S80). At this time, in the case of generating a melody through a variableization method, a melody is generated by replacing each chord constituting the input melody with a new chord. On the other hand, in the case of melody generation through a structuring method, it is configured to include any one of the chords constituting the input melody. In addition, the structuring method may further include generating another melody including one or more of the chords constituting the generated melody. As described above, each chord constituting the new melody can be extracted from an ontology-based database. The newly created melody is output through a speaker or screen (S90) so that the user can recognize it.

The content generation server may generate coded content for coded content, such as a method for generating sentence content and melody content. Coding content includes problem solving algorithms. In the problem-solving algorithm, the process of solving algorithmic problems is managed as a DB, and variables included in the problem are changed to other variables to transform into various algorithmic problems. In an algorithm problem, the logic flow has several patterns, and for each particular pattern, there is a variable range that can be changed. The content generation server generates coded content by performing one or more of algorithm problem selection, specific pattern selection, and variable selection.

6 is a block diagram showing the configuration of the learning management system of the online education system of FIG. 2. Referring to FIG. 6, the learning management server 24 includes a learning content providing unit 210, a behavior pattern learning unit 220, and a behavior pattern It includes an analysis unit 230 and a learning management unit 240 .

Upon request from the student terminal 30 , the learning content providing unit 210 transmits predetermined learning content to the student terminal 30 so that the student terminal 30 displays it to the student. Here, the learning content may include at least one of various forms including text, image, video, voice, etc., and in problem data of typical education services such as learning query information, simple explanation information, correct answer information, and classification information. information may be included.

The learning content provider 210 may provide a login function for using the learning content to the student terminal 30, and may provide the learning content only to students who have logged in. The learning content provider 210 may request and receive member information including ID, password, name, gender, age, phone number, etc. from the student terminal 30 to sign up as a member of the learning management solution, and member information can be stored to process the student's membership registration.

The learning content providing unit 210 may request and receive an ID and password from the student terminal 30 , compare the received ID and password with member information, and process login of the corresponding student. The learning content provider 210 may extract and transmit student-customized learning content to the student terminal 30 using member information. For example, the learning content providing unit 210 may extract learning content suitable for the student's age and transmit the extracted learning content to the student terminal 30 . The student terminal 30 outputs the learning content through the display unit so that the student can view the learning content.

The behavior pattern learning unit 220 collects sensor data obtained from each student terminal 30 while a plurality of students are taking learning content as learning sensor data to perform artificial intelligence-based learning for predicting behavior patterns. can Here, the sensor data may include first sensor data corresponding to a face image of a student gazing at the display unit and second sensor data corresponding to a distance to both shoulders of the student gazing at the display unit. Behavior patterns can be largely divided into watching, writing, non-learning, and leaving. This behavior pattern can be predicted from the first sensor data and the second sensor data. For example, a student's face area is detected from the first sensor data, and the distance between both shoulders of the student included in the second sensor data If the difference is within a predetermined distance, a behavior pattern may be predicted as being watched while the student is sitting in an upright posture and staring at the display unit. In addition, when the student's face region is detected from the first sensor data and the difference between the distances to both shoulders of the student included in the second sensor data is a predetermined distance or more, the behavior pattern is changed to a state in which the student is writing while staring at the display unit. Predictable. In addition, when the student's face region is not detected from the first sensor data and both shoulders of the student included in the second sensor data are detected, the learner is regarded as a dozing state and the behavior pattern can be predicted as non-learning. In addition, when the student's face region is not detected from the first sensor data and both shoulders of the student are not detected from the second sensor data, a behavior pattern may be predicted with the student separated.

When the behavior pattern learning unit 220 collects sensor data for learning from the student terminal 30, it extracts gender and age from member information of the student and generates learning data storing the sensor data for learning by gender and age. can The behavior pattern learning unit 220 determines whether or not the student's face region is detected from the first sensor data, whether both shoulders of the student are detected from the second sensor data, and the distance difference between both shoulders of the student from the second sensor data. A deep learning model can be built by defining whether or not within the distance as one segment, targeting four behavioral patterns of watching, writing, not learning, and leaving, and learning learning data. This deep learning model will be able to calculate any one of behavior patterns among viewing, writing, non-learning, and withdrawal with respect to input data. Here, the input data corresponds to member information corresponding to the age and gender of the student, first sensor data, and second sensor data.

The behavior pattern learning unit 220 detects eye blinking in the face image of the sensor data of the student terminal 30, and determines whether the eye blink is greater than or less than a certain threshold value among normal and slow to determine concentration or sleepiness as a behavior pattern. can For example, it may be determined that the student is concentrating on learning if the eye blink is a normal threshold, and the student is dozing off if the eye blink is a slow threshold.

The behavior pattern analysis unit 230 includes a sensor data collection unit 231 and a behavior pattern prediction unit 232 .

The sensor data collection unit 231 may receive sensor data from the student terminal 30 currently outputting learning content. The student terminal 30 photographs the student with a camera, and when motion is detected, the sensor data is transmitted to the sensor data collector 231, and the sensor data collector 231 detects the motion from the student terminal 30. receive data Here, the sensor data may include first sensor data corresponding to an image of a student staring at the display unit and second sensor data corresponding to a distance from the display unit to both shoulders of the student. The sensor data collector 231 may receive sensor data from the student terminal 30 according to a predetermined cycle while learning content is output.

The behavior pattern prediction unit 232 may predict the behavior pattern of the student who is learning the learning content as one of viewing, writing, non-learning, and departure by using the sensor data collected by the sensor data collection unit 231. . The behavior pattern prediction unit 232 may predict a student's behavior pattern by inputting the sensor data collected by the sensor data collection unit 231 to the deep learning model generated by the behavior pattern learning unit 220 . At this time, the behavior pattern prediction unit 232 extracts the student's age and gender from the member information of the student who generated the sensor data, inputs the sensor data as input data of the deep learning model, and outputs the deep learning model to the student. It can be calculated as a result of predicting the behavior pattern of

In addition, when sensor data is received through the sensor data collection unit 231, the behavior pattern prediction unit 232 may predict a student's behavior pattern by analyzing the first sensor data and the second sensor data, respectively. For example, the behavior pattern prediction unit 232 may determine whether a student's face region is detected from the first sensor data through image processing. The behavior pattern predictor 323 may determine whether both shoulders of the student are detected in the second sensor data when the student's face region is detected in the first sensor data.

The behavior pattern predictor 232 determines the distance difference between both shoulders of the student detected in the second sensor data when the student's face region is detected in the first sensor data and both shoulders of the student are detected in the second sensor data. can be calculated and compared with the reference distance. The behavior pattern prediction unit 232 may predict a behavior pattern while watching, when the distance difference between the student's both shoulders is less than or equal to the reference distance. The behavior pattern prediction unit 232 may predict a behavior pattern during writing when a distance difference between the student's both shoulders exceeds a reference distance. The behavior pattern predictor 232 may predict a learner's behavior pattern as non-learning when the student's face region is not detected in the first sensor data and both shoulders of the student are detected in the second sensor data.

The behavior pattern predictor 232 may predict the behavior pattern as a deviation state when the student's face region is not detected in the first sensor data and both shoulders of the student are not detected in the second sensor data.

The behavior pattern predictor 232 may determine whether eye blinking in the student's face region of the sensor data is greater than or less than a predetermined threshold, and predicts the behavior pattern as concentration or sleepiness.

The learning management unit 240 includes a content control signal generator 241 and a task content generator 242 .

The content control signal generating unit 241 reproduces in the student terminal 30 when the behavior pattern prediction result of the student from the behavior pattern analysis unit 230 is any one of writing, non-learning, disengagement, concentration, and drowsiness. A control signal of the content being played may be generated and transmitted to the student terminal 30 . The student terminal 30 may temporarily stop playback of the currently playing content or adjust the playback speed according to the content control signal. For example, the content control signal generation unit 241 adjusts the reproduction signal of the content being played in the student terminal 30 by 0.8 when the result of predicting the student's behavior pattern in the behavior pattern analysis unit 230 is being written. A content control signal may be generated and transmitted to the student terminal 100 . This is to help the student take notes comfortably without a separate manipulation by slowing down the reproduction speed of the content while the student is taking notes.

The content control signal generation unit 241 pauses the content being played in the student terminal 30 when the behavior pattern prediction result of the student from the behavior pattern analysis unit 230 is any one of non-learning, disengagement, and sleepiness. A content control signal to be generated may be transmitted to the student terminal 30 . This is to temporarily suspend the content when the learner is not learning or leave, and to output task content to improve the student's concentration.

The task content generation unit 242 generates task content to be output from the student terminal 30 when the behavior pattern prediction result of the student from the behavior pattern analysis unit 230 is any one of non-learning, disengagement, and sleepiness. It can be transmitted to the student terminal 30 . At this time, the student terminal 30 may first receive the content control signal to temporarily suspend reproduction of the learning content currently being output, and then output the task content. For example, the task content generator 242 may generate a voice file that induces students to view the learning content as task content. Hereinafter, such task content is referred to as first task content. The student terminal 30 allows the student to view the learning content by outputting the first task content. The student terminal 30 may play the learning content again when the reproduction of the first assignment content ends.

The task content generator 242 may request and receive a panoramic image obtained from the surrounding image acquiring module from the student terminal 30 . The task content generator 242 may detect at least one object of a predetermined size or less in the panoramic image. The task content generation unit 242 may generate task content requesting movement of an object detected in the panoramic image and transmit it to the student terminal 30 . Hereinafter, such task content is referred to as second task content. The student terminal 100 may output second task content, and the student may perform the task by moving an object according to the second task content. That is, the second task content may induce a student's movement. The task content generator 242 monitors the panoramic image to determine whether the second task content has been performed, and when it is determined that the second task content has been performed, by transmitting a playback signal of the learning content to the student terminal 30. , the learning content is played again.

The task content generation unit 242 may create task content that is matched with the learning content currently being played in the student terminal 30 and stored, and may transmit the generated task content to the student terminal 30 . Hereinafter, such task content is referred to as third task content. The student terminal 30 may output third task content and may receive an answer to the third task content. When the answer input through the student terminal 30 is a correct answer, the task content generator 242 transmits a reproduction signal of the learning content to the student terminal 30 so that the learning content is reproduced again.

7 is a block diagram showing the configuration of the aptitude test system of the online education system of FIG. 2. The aptitude test program server 250 includes a temperament determiner 251, a sound power converter 252, a color determiner 253, a relationship It includes a determination unit 254, a figure determination unit 255, a body care determination unit 256, and a mind care determination unit 257.

The temperament determination unit 251 determines the temperament of the student terminal 30 by providing aptitude test items to the student terminal 30, and determines and displays first to third colors based on the determined temperament.

If the student's birthday information is positive, the lunar conversion unit 252 converts it into a lunar calendar.

The color determination unit 253 reads the color decision of another student terminal 30 designated by the student terminal 30 to determine the relationship between the students, and determines the first student terminal 30 and the second student terminal 30 ( 30) to collect the color crystals. Red color is vitality and action, orange color is sociable and open, green color is stability, blue color is responsibility, truth, understanding, indigo color is logical, decisiveness, insight, violet color is creative, intuition, self Blue-green represents perseverance, innocence, and high ideals. Pink represents love, delicacy, and charm. Gold represents insight, wisdom, and fruition. Turquoise represents communication, ideas, and potential. Magenta represents humanity. , indicates tolerance.

The relationship determination unit 254 analyzes and displays the relationship between the first to third colors of the first student terminal 30 and the second student terminal 30 .

The figure determination unit 255 matches and determines the figure selection information selected by the student terminal 30 . The shape determination unit 255 can grasp the temperament, aptitude analysis, and psychological state by drawing a picture using only the four shapes of circle, triangle, square, and S.

The body care determining unit 256 matches the temperament determining information of the temperament determining unit 251 , the shape selection information of the shape determining unit 255 , and the blood type information to determine the physical condition.

The mind care determination unit 257 matches the disposition determination information of the temperament determination unit 251, the shape selection information, and the preference and non-preference determination information of the shape determination unit 255 to determine the individual's state of mind, for example, stability, anxiety, judge depression, etc.

The aptitude test program server 250 includes a temperament determination unit 251, a sound conversion unit 252, a color determination unit 253, a relationship determination unit 254, a figure determination unit 255, and a body care determination unit 256. ), the judgment information of the mind care determination unit 257 is integrated, the aptitude test is performed, and the aptitude test result is transmitted to the learning management server 24 so that learning content suitable for the aptitude is provided. The learning management server 24 stores the aptitude test result in the learning content provider 210, and the learning content provider 210 generates a learning curriculum so that learning content suitable for the student terminal 30 is provided, and the learning curriculum The teacher terminal 20 and the student terminal 30 are connected so that the teacher terminal 20 according to is assisted.

The aptitude test result of the aptitude test program server 250 is reflected in the online education system, and the learning management server 24, teacher terminal 20, and student terminal 30 constituting the online education system determine the aptitude of the student terminal 30. It operates organically so that the learning content suitable for is provided to the student terminal 30 .

In the online education system according to an embodiment, the temperament determination unit 251 includes a student's score for a plurality of temperament test items, an average score for a plurality of temperament test items, an average score for a plurality of color test items, and Based on the average score of a plurality of shape test items, the student's temperament test score is calculated, and the color determining unit 253 calculates the student's score on a plurality of color test items and the average score on the plurality of temperament test items. The student's color test score is calculated based on the score, the average score for the plurality of color test items, and the average score for the plurality of shape test items, and the shape determination unit 255 calculates the student's color test score for the plurality of shape test items. The student's shape test score is calculated based on the score of the student, the average score for the plurality of temperament test items, the average score for the plurality of color test items, and the average score for the plurality of shape test items, and the temperament test score , An aptitude test index of the student may be calculated based on the color test score and the shape test score.

The aptitude test program server 250 may calculate the student's aptitude test index by applying weights corresponding to each of the temperament test score, the color test score, and the shape test score, and summing the weighted results. there is.

는 모든 사용자의 모든 기질 검사 항목에 대한 평균 점수이고,

는 모든 사용자의 모든 색상 검사 항목에 대한 평균 점수이고,

는 모든 사용자의 모든 도형 검사 항목에 대한 평균 점수이다.F(p) is the aptitude test function that outputs the aptitude test index of object p, a is the temperament test weight constant, xi is the score for the temperament test item of p, n is the number of temperament test items, and b is the color is the test weight constant, yi is the score for the color test item of p, m is the number of color test items, c is the shape test weight constant, zi is the score for the shape test item of p, and l is the shape test item number,

is the average score for all temperament test items of all users,

is the average score for all color check items for all users,

is the average score for all shape test items of all users.

The aptitude test program server 250 calculates the aptitude test index using Equation 1 and requests the learning content corresponding to the aptitude test index from the learning management server 24 to be provided to the student terminal 30 . The aptitude test index is affected by the temperament test item, the color test item, the shape test item, the temperament test weight, the color test weight, and the shape test weight, and shows the change trend for each specific item. The aptitude test program server 250 receives the learning content from the learning management server 24 and provides it to the student terminal 30 in consideration of the aptitude test index of the temperament, color, and figure indicating the trend of change.

FIG. 8 is an exemplary diagram illustrating a system authentication configuration that grants authority to execute hardware resources, an operating system, an operation of a control unit, which is a core, and an operation of a control unit of an online education system according to the present invention. Referring to FIG. 8, the present invention is a processor (1) ), memory 2, input/output device 3, operating system 4, and control unit 5.

The processor 1 is a CPU (Central Processing Units), a GPU (Graphic Processing Unit), an FPGA (Field Programmable Gate Array), and an NPU (Neural Processing Unit). ) executes the executable code.

The memory 2 includes a permanent mass storage device such as random access memory (RAM), read only memory (ROM), disk drive, solid state drive (SSD), flash memory, etc. can do.

The input/output device 3 is an input device, such as a camera, keyboard, microphone, mouse, etc., including an audio sensor and/or an image sensor, and an output device, such as a display, speaker, haptic feedback device, etc. device may be included.

The operating system 4 may include Windows, Linux, IOS, a virtual machine, a web browser, and an interpreter.

The control unit 5 determines the state of the input/output device 3 by sensor, key, touch, and mouse input under the support of the operating system 4, and performs an operation according to the determined state. The control unit 5 performs task scheduling using a timer and thread as a parallel execution routine.

The control unit 5 determines a state using the sensor value of the input/output device 3 and performs an algorithm according to the determined state. The input/output device 3 may be a display, a camera, a mouse, a keyboard, or an electronic pen, and the control unit 5 uses the sensor value of the input/output device 3 to play or stop learning content, play audio, or play a video, You can determine the value to be fed back to each control.

The control unit 5 applies the interval difference to the sensor value of the input/output device 3 and performs a detection algorithm according to the increase/decrease setting. In the detection algorithm, the sensor value is detected, and the reliability of the secondary sensor value detection is increased by setting an increase/decrease by applying an interval differential for the secondary detection to the primary sensor value level. The sensor value may be output when the sensor value is sensed, and when the sensor value gradually increases or decreases, when the trend of the sensor value increases or decreases although there is an increase or decrease.

When the detection algorithm is not applied to the input/output device 3, the control unit 5 may monitor the trend and change of the sensor value over time and generate a detection message according to the monitoring result.

Referring to FIG. 8 , the system authentication configuration includes a terminal 6 including a control unit 5 and an authentication server 7 . The terminal 6 may be implemented as a teacher terminal 20 or a student terminal 30 .

The terminal 6 duplicates the data channels, receives the key value and biometric information of the terminal 6, and requests user authentication from the authentication server 7 through the first data channel. It is displayed on the display and transmitted to the authentication server (7).

The terminal 6 inputs the kit value displayed on the display of the terminal 6 and transmits it to the authentication server 7 through the second data channel along with user information. The terminal 6 requests the authentication server 7 to authenticate the system installed in the terminal 6 using the kit value and user information. The kit value of the terminal 6 can be generated from computer-specific information such as the CPU manufacturing number and the address of the Ethernet chip. The terminal 6 may obtain user information through face recognition using a camera, voice recognition using a microphone, and handwriting recognition using a display, and may use it for authentication.

The authentication server 7 receives the kit value from the terminal 6, receives the kit value and user information from the terminal 6 through a duplicated data channel, compares the kit value of the terminal 6 with the user information, and returns the user information Correspondingly, authentication for system use of the terminal 6 is processed. The authentication server 7 transmits the authentication result to the terminal 6 to allow the user to use the system. Due to the duplicated data channel of the terminal 6, loss of kit value can be minimized.

The authentication server 7 performs a history analysis of user information, and compares and determines consistency and change of user information over time. In the history analysis, if the user information shows consistency, the user's use is permitted, and if it shows change, the user's use is not permitted. When the user information shows consistency, the user's use of the system is permitted, thereby strengthening security to prevent a user whose user information has been altered from accessing the system.

The terminal 6, which is a means of authenticating the use of the system, does not directly connect to the system, but forms a detour through the authentication server 7, so that the network constituting the Internet network is composed of an internal network and an external network, and the IP address setting process When this is cumbersome, there is an advantage in that the authentication process using the terminal 6 is smoothly performed. At this time, the system is mounted on the terminal 6, the terminal 6 serves as an authentication terminal means, and the authentication server 7 serves as an authentication server means.

9 is an exemplary view showing application of a neural network implemented in the online education system of the present invention.

Neural network learning selects a model through feature selection and algorithm selection from time-series data collected from input devices such as various sensors such as temperature, altitude, and fingerprints, cameras such as images and infrared rays, and LIDAR, and then repeats learning and performance verification processes. Repeat model selection through trial and error. After performance verification is complete, an artificial intelligence model is selected.

The control unit 5 performs a deep learning algorithm using a neural network to determine the sensor value, uses training data to learn the neural network, and verifies the performance of the neural network with test data.

In the online education system, the control unit 5 equipped with a neural network collects user experience information on learning content playback, video playback, and audio playback of the terminal 6, statistical analysis based on the collected use experience information, neural network learning, and pattern Analysis is performed, and learning content recommendation according to the analysis result is provided to the terminal 6 . The terminal 6 can use the learning content recommendation of the online education system and improve the user experience of the online education system.

Statistical analysis, neural network learning, pattern analysis includes linear discriminant analysis (LDA), logistic regression (LR), support vector machine (SVM), decision tree (DT), k-nearest neighbor (KNN), random forest (RF), etc. Six machine learning algorithms can be applied. Linear discriminant analysis (LDA) makes predictions by estimating the probability that a new set of inputs belongs to each class. The class that gets the highest probability is the output class and predictions are made. Logistic regression (LR) is the probability for two possible classification problems.

Support vector machines (SVMs) find the hyperplanar decision boundary that best splits the examples into two classes. The division is made smooth using margins where some points may be misclassified. A decision tree (DT) involves growing a tree to classify examples from a training data set. A tree can be thought of as dividing a training data set. Here, the example proceeds through the decision points of the tree until it reaches the leaves of the tree and is assigned a class label. A k-nearest neighbor (KNN) stores all available data and classifies new data points based on similarity. That is, when new data appears, it can be easily classified into well-sweet categories using k-Nearest Neighbors (KNN). Finally, a random forest (RF) consists of many decision trees for the final output, and is considered a very accurate and powerful method because the number of decision trees participating in the process is large.

The control unit 5 may use a machine learning algorithm to analyze the user experience of learning content playback, video playback, and audio playback of the terminal 6, and may also analyze a correlation related to payment for using the learning content.

The control unit 5 removes data noise by applying filtering to the sensor values of the input/output device 3 and preprocesses them so that the noise is not applied to the neural network. The control unit 5 increases the performance of the online education service by preventing noise from affecting the performance of the neural network. For example, the controller 5 may use a digital filter to filter sensor values. The control unit 5 converts the sensor value into a digital value, calculates a frequency spectrum, and applies the sensor value of a certain frequency interval to the neural network.

The controller 5 may measure the performance of the neural network and change the filtering frequency range of the sensor value to a frequency range having high neural network performance. For example, the control unit 5 may use PID control to select an optimal filtering frequency range by calculating a correlation between the performance of the neural network and the filtering frequency range. In PID control, it is possible to differentially control the I value corresponding to the leading and trailing integral components of the I value to adapt to the preceding and following sensor values. For example, when a sensor value leads or lags, a change in the I value corresponding to the preceding and a change in the I value corresponding to the following may be applied differently. This is to adapt to the change in performance of the neural network when the sensor value leads and the change in performance of the neural network when the sensor value lags behind.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (10)

An evaluation management server 110 that evaluates and manages student abilities, a content creation server that generates coding content, sentence content, and melodic content, and learning that analyzes student behavior patterns using the camera of the student terminal 30 to manage learning. a server 10 including any one or more of a management server 24 and an aptitude test program server 250 that tests a student's temperament;
A teacher terminal 20 that provides a blackboard screen, textbook screen, and student management screen on the first screen, and provides a virtual classroom screen and class attitude notification screen on the second screen; and
A student terminal 30 providing a blackboard screen and textbook screen on a first screen and a virtual classroom screen on a second screen;
The aptitude test program server 250,
a disposition determination unit 251 for determining the disposition of the student terminal 30 by providing an aptitude test item to the student terminal 30;
If the student's birthday information is in the solar calendar, the lunar conversion unit 252 converts it into the lunar calendar;
a color determination unit 253 that reads color decisions of other student terminals 30 designated by the student terminal 30 and collects color decisions of the first student terminal 30 and the second student terminal 30;
a relationship determination unit 254 analyzing and displaying a relationship between the first to third colors of the first student terminal 30 and the second student terminal 30;
a figure determining unit 255 that determines by matching the figure selection information selected by the student terminal 30;
a body care determining unit 256 matching the temperament determining information of the temperament determining unit 251, the shape selection information of the figure determining unit 255, and the blood type information to determine a physical condition; and
A mind care determination unit 257 that matches the disposition determination information of the disposition determination unit 251, the figure selection information of the figure determination unit 255, and preference and non-preference determination information to determine the individual's state of mind;
The temperament determination unit 251 determines the student's scores for a plurality of temperament test items, the average score for the plurality of temperament test items, the average score for the plurality of color test items, and the average score for the plurality of shape test items. Calculate the student's temperament test score on the basis of;
The color determination unit 253 determines the student's scores for a plurality of color test items, the average score for the plurality of temperament test items, the average score for the plurality of color test items, and the average score for the plurality of shape test items. Calculate the student's color test score as a basis;
The shape determination unit 255 determines the student's scores for a plurality of shape test items, the average score for the plurality of temperament test items, the average score for the plurality of color test items, and the average score for the plurality of shape test items. Calculate the student's figure test score as a basis,
Characterized in that the student's aptitude test index is calculated based on the temperament test score, the color test score, and the shape test score using Equation 1,
[Equation 1]

F(p) is the aptitude test function that outputs the aptitude test index of object p, a is the temperament test weight constant, xi is the temperament test score of p, n is the number of temperament test items, and b is the color test weight constant where yi is the color check score of p, m is the number of color check items, c is the shape check weight constant, zi is the shape check score of p, l is the number of shape check items,

is the average score for all temperament test items of all users,

is the average score for all color check items for all users,

is the average score for all shape inspection items of all users,
online education system.
According to claim 1,
The evaluation management server 110,
a reservation processing unit 120 that reserves an evaluation schedule and generates a reservation message so that capability evaluation is performed on the evaluation schedule;
A question bank DB (130) for storing problems related to evaluation of student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, inquiry process ability, and academic ability diagnosis;
Reading questions about student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability from the question bank DB (130), and providing them to the student terminal (30) to evaluate the student's ability diagnostic evaluation module 140; and
Academic evaluation questions on student attitude, creative disposition, logical thinking ability, subject concept problem solving ability, creative problem solving ability, and inquiry process ability are read from the question bank DB (130) and provided to the student terminal (30) to determine the student's academic ability Characterized in that, the online education system including; academic diagnosis evaluation module (150) for evaluating the ability. According to claim 1,
The content creation server,
When an original content sentence is input (S10), analyzing one or more words among words of the input sentence (S20);
After the analysis step (S20), generating a new sentence by extracting words from the ontology-based database according to the analysis result (S30); and
A step (S40) of outputting the newly generated sentence through a speaker or a screen; characterized in that performing, an online education system. According to claim 1,
The content creation server
When the original content melody is input (S60), analyzing the chord for one or more bars among the chords of the input melody (S70);
After the analysis step (S70), generating a new melody by extracting chords from the ontology-based database according to the analysis result (S80); and
Characterized in that performing, the online education system; outputting the newly created melody through a speaker or a screen (S90). According to claim 1,
The learning management server 24,
Upon a request from the student terminal 30, a learning content providing unit 210 that transmits predetermined learning content to the student terminal 30 and displays it to the student at the student terminal 30;
A behavior pattern learning unit 220 that performs artificial intelligence-based learning for predicting behavior patterns by collecting sensor data obtained from the student terminals 30 while a plurality of students are taking learning content as sensor data for learning. ;
a behavior pattern analyzer 230 analyzing a behavior pattern based on the sensor data collected from the student terminal 30; and
A learning management unit 240 controlling the learning content providing unit 210 to provide learning content corresponding to the analyzed behavior pattern; Characterized in that it comprises an online education system. According to claim 5,
The behavior pattern analysis unit 230,
a sensor data collection unit 231 that receives motion-detected sensor data from the student terminal 30 currently outputting learning content; and
a behavior pattern prediction unit 232 that predicts a behavior pattern of a student who is learning learning content to one of viewing, writing, non-learning, and withdrawal by using the sensor data collected by the sensor data collection unit 231; Characterized in that it comprises a, online education system. According to claim 5,
The learning management unit 240,
When the student's behavior pattern prediction result from the behavior pattern analyzer 230 is any one of writing, non-learning, and leaving, a control signal for the content being played in the student terminal 30 is generated to generate the student terminal a content control signal generator 241 that transmits to (30); and
When the behavior pattern prediction result of the student in the behavior pattern analyzer 230 is either non-learning or leaving, task content to be output from the student terminal 30 is generated and transmitted to the student terminal 30 Characterized in that, the online education system comprising a; assignment content generator 242 to. delete delete According to claim 1,
The aptitude test program server 250,
Applying a weight corresponding to each of the temperament test score, the color test score, and the shape test score;
Calculating the student's aptitude test index by summing the weighted results,
online education system.

Images