KR20220061384A - Apparatus and method for detecting learners' participation in an untact online class - Google Patents

Abstract

Disclosed are an apparatus and method for detecting the participation of a learner in a non-face-to-face online class to detect whether a learner taking a non-face-to-face online class is participating in accordance with the progress of the online class with a personal electronic device equipped with a gaze tracking device. According to one embodiment of the present invention, the apparatus comprises: a data collection unit receiving gaze tracking data acquired by a gaze tracking device from a personal electronic device of each learner participating in an online class; a calculation unit using the gaze tracking data collected by the data collection unit to calculate a gaze fixation point which is a location where each gaze of the learners is fixed; and a class participation state determination unit using the distribution of the gaze fixation points of the learners calculated by the calculation unit to determine whether each of the learners participates in the class.

Description

{Apparatus and method for detecting learners' participation in an untact online class}

The present invention relates to a technology for detecting whether a learner participates in a class, and to a technology for detecting whether a learner is participating in a non-face-to-face online class using eye tracking data and using the detected result .

Due to the recent Corona 19, online schools are being opened and interest in the non-face-to-face industry is increasing. Accordingly, there is a change in the trend towards the education industry in which education and information and communication (ICT) technology are grafted, in other words, Edu-Tech is taking place, and non-face-to-face online classes are being conducted or promoted not only in schools, but also in various national and public educational institutions and private educational institutions. is becoming

Current non-face-to-face online classes are conducted on the premise of the voluntary participation of learners who are not under the supervision or supervision of the teacher, and in many cases the teacher cannot control the class situation. In addition, learners are easily exposed to environments where they can use smartphones, game consoles, or computers even during online classes. As a result, in non-face-to-face online classes, the problem that learners' participation in learning is lowered is emerging.

To solve this problem, various technologies have been proposed to detect whether learners are normally participating in non-face-to-face online classes.

As an example, there is a method of displaying an interface for inputting a specific response on a learner's screen and determining whether or not to participate in learning according to whether an accurate response is inputted to the interface within a predetermined time. However, in this method, participation is detected only when the corresponding interface is displayed, and it is difficult to see that the teacher controls the class situation. In addition, the interface displayed on the class content interferes with the progress of the online class, and in some cases, an interface unrelated to the content of the class content is displayed.

As another example, there is a method of determining whether a learner is normally participating in a non-face-to-face online class using eye tracking technology. For example, in Korean Patent Application Laid-Open No. 10-2014-0146750, "Gaze-based educational content execution system" (Patent Document 1), the point of gaze is calculated based on the gaze information of the learner, and the calculated gaze position of the learner is Disclosed is a technology for controlling whether or not to continue the progress of the instructional content image according to whether the educational content image (eg, a screen on which the content is displayed). However, in this method, it is difficult to accurately determine whether the learner is participating in the current class flow because it is judged that the learner is participating in the class normally only when the learner is always watching the corresponding content. For example, according to the method of Patent Document 1, it is determined that the learner does not participate in the class while not watching the content while viewing the textbook or taking notes while taking notes, or unlike most learners who are viewing the textbook, the content is viewed alone. In the case of watching, it can be judged that most learners do not participate in class but participate in class alone. In addition, even if the learner is gazing at a part other than the part that is not being lectured (the area where the content is displayed) at the time of the entire video, it may be determined that the learner is participating in the class.

As another example, there is a method of determining whether a learner is normally participating in a non-face-to-face online class using an image captured by a camera. For example, in Korean Patent Application Laid-Open No. 10-2020-0050281, "Learning support system and method using artificial intelligence-based augmented reality and virtual reality" (Patent Document 2), the video from the teacher's point of view together with the teacher's voice information And, a technology for judging a student's learning state based on a virtual reality-based learning image generated using an image from a student's point of view together with the student's voice information is disclosed. However, this method requires a large amount of data processing because it is necessary to generate a virtual reality-based learning image by acquiring the teacher's image and the student image, respectively, and combining them. In addition, it is disclosed that information on the student's learning state is calculated based on the student's motion information collected during class, but does not disclose specific standards for judging the student's learning state.

In addition, there are Non-Patent Document 1 and Non-Patent Document 2 as a study for detecting participation in online learning in relation to gaze movement, and Non-Patent Document 3 to Non-Patent Document 5 as a study on the learning participation behavior of learners.

Korean Patent Publication No. 10-2014-0146750 Korean Patent Publication No. 10-2020-0050281

S. Aslan, Z. Cataltepe, I. Diner, O. Dundar, A. A. Esme, R. Ferens, M. Yener, Learner Engagement Measurement and Classification in 1:1 Learning (International Conference on Machine Learning and Applications, Detroit, 2014) L.B. Krithika, P.G.G. Lakshmi, Student emotion recognition system (SERS) for e-learning improvement based on learner concentration metric. Procedia Computer Science 85, 767-776 (2016) N. Bosch, Detecting Student Engagement: Human Versus Machine (Conference on User Modeling Adaptation and Personalization, Halifax, 2016) N. Bosch, S. K. D'Mello, R.S. Baker, J. Ocumpaugh, V. Shute, M. Ventura, W. Zhao, Detecting Student Emotions in ComputerEnabled Classrooms (International Joint Conference on Artificial Intelligence, New York, 2016) J.A. Fredrick, P.C. Blumenfeld, A. H. Paris, School engagement: Potential of the concept, state of the evidence. Rev. Educ. Res. 74(1), 59-109 (2004)

One problem to be solved by the present invention is that learners' participation in non-face-to-face online classes can be more accurately determined by using the learner's eye tracking data in a situation where non-face-to-face real-time online classes are conducted. To provide a detection device and method.

Another problem to be solved by the present invention is the learner's participation in the non-face-to-face online class, in which the learner's learning participation status can be adaptively determined according to the progress of the class in a situation where the non-face-to-face real-time online class is conducted. To provide a detection device and method.

An embodiment of the present invention for solving the above problem is a device for detecting whether a learner receiving a non-face-to-face online class with a personal electronic device equipped with an eye tracking device is participating in accordance with the progress of the online class, A data collection unit that receives the eye tracking data obtained by the eye tracking device from the personal electronic device of each of the learners participating in the online class, and each of the learners using the eye tracking data collected by the data collection unit A calculation unit that calculates a gaze fixation point, which is a fixed position of the gaze of , and a class participation state determination unit that determines whether each of the learners participate in a class by using the distribution of the gaze fixation points of the learners calculated by the calculation unit include

According to one aspect of the embodiment, the class participation state determination unit determines the gaze fixation point corresponding to the most learners among the gaze fixation points of each of the learners as the gaze area, and then the gaze fixation point of the specific learner is in the gaze area Based on the inclusion, it is possible to determine whether the learner participates in the class.

According to another aspect of the embodiment, the calculation unit also calculates the fixed time at the gaze fixation point of each of the learners together, and the class participation state determination unit uses the gaze movement information by the gaze fixation point and the fixation time. Thus, it is determined whether each of the learners participates in the class. In this case, the class participation state determination unit may determine whether each of the learners participates in the class by using the content information of the online class including the type of class and the execution time as well.

And the class participation state determination unit may be implemented using an online class participation detection model based on unsupervised learning artificial intelligence.

According to another aspect of the embodiment, the class participation state determination unit may further include a feedback unit for transmitting a notification message to the personal electronic device of the learner who is determined not to participate in the class.

Another embodiment of the present invention for solving the above problem is a method for detecting whether a learner receiving a non-face-to-face online class with a personal electronic device equipped with an eye tracking device is participating in accordance with the progress of the online class, Receiving the eye tracking data obtained with the eye tracking device from the personal electronic device of each of the learners participating in the online class, using the eye tracking data collected in the collecting step, the gaze of each of the learners Calculating a fixed gaze fixation point, which is a fixed position, and determining whether each of the learners participates in a class by using the distribution of the gaze fixation points of the learners calculated in the calculating step.

According to the above-described embodiment of the present invention, since the movement of the gaze including the fixing point of each gaze of the learners calculated based on the gaze tracking data of the learner or the fixing time at the fixing point is utilized, the learner's learning Participation status can be judged more accurately. In particular, by using the distribution of learners' gaze fixation points in a specific time range, each learner's learning participation status is determined based on whether some gaze fixation points are different from most learners or their gaze movement is outside the normal range, More accurate and adaptive judgment is possible. In addition, by providing appropriate feedback to students or teachers using the judgment results, it is possible to improve the participation rate of learners in non-face-to-face online classes.

1 is a block diagram schematically showing the schematic configuration of a non-face-to-face online class participation detection device according to an embodiment of the present invention.
2 is a schematic diagram for explaining an example of a method of calculating a fixed position of a gaze using a gaze coordinate value.
3 is an example of a diagram schematically illustrating a movement pattern of a specific learner's gaze.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments and examples of the present invention will be described with reference to the drawings. However, the following embodiments and examples are merely illustrative of preferred configurations of the present invention, and the scope of the present invention is not limited to these configurations. And in the following description, the hardware configuration and software configuration of the device, processing flow, manufacturing conditions, size, material, shape, etc. are not intended to limit the scope of the present invention to these unless specifically stated otherwise. .

According to the present invention, based on eye tracking data of learners participating in the non-face-to-face online class, it is determined whether each learner is normally participating in the online class. In general, the state of the learner's gaze (whether fixed or not, the position of the fixed point, fixed time, movement pattern, etc.) means not only visual movement but also selective and active perception for problem-solving. It is possible to obtain information that can understand the learner's cognitive process. In particular, if you know the fixed time at the point along with the point at which the gaze gazes, information such as how long to pay attention to which learning content and whether to skip reading can be inferred in real time.

However, depending on the content of the content or the teaching method of the instructor (teacher), the point (fixed point of gaze) or time (fixed time) at which the learner should take the test may vary. For example, when the instructor explains what is included in the content, the learner must stare at the corresponding content part of the display, but when the instructor explains with reference to the textbook, or when the learner solves problems or takes notes On the other hand, the learner has to gaze at the textbook or notes on the desk rather than the displayed content, so that it can be seen that the learner is participating in accordance with the progress of the class. That is, even if the learner is gazing at the display screen, if the learner is gazing at content from a different location that is not related to the part being explained by the instructor, or if the learner is gazing at the display screen or a third location despite having to gaze at the textbook or notes, the learner It is difficult to see that they are participating in the online class.

However, in the online class lasting for a predetermined time, the fixed time and the location where the learner should gaze (fixed point of gaze) may vary depending on the progress of the class, the instructor's class method, the content of displayed content, etc. . If an online class is conducted with recorded lecture video, it may be possible to determine in advance where the learner should take the exam at a specific time by referring to the contents or lecture contents. However, when conducting non-face-to-face online classes in real time , while the online class is in progress, the position where the learner should gaze is flexible, so it is almost impossible to predetermine the fixed time together with the fixed point of the learner's gaze at a specific time.

In the embodiment of the present invention, which will be described later, in consideration of these characteristics of non-face-to-face real-time online classes, it is premised that learners who participate in accordance with the progress of the class will usually occupy the majority among learners participating in the online class at a specific time. In this way, it is judged that the learner who responds to multiple gaze movements is participating in the class, but the learner who deviates from the multiple gaze movements is judged not to be participating in the class. .

More specifically, in an embodiment of the present invention, it is determined whether a specific learner is participating in an online class by using the distribution of learners at the fixed point of gaze (that is, how many learners correspond to the fixed point). . For example, if more than half, preferably 2/3 or more, of the learners of a predetermined group (eg, 30 people) stare at the same point, it is determined that the learner staring at the point is normally participating in the class, but A learner staring at a branch may be judged not to have participated in the class. Alternatively, depending on the embodiment, the gaze time (fixed time of the gaze) for the corresponding point as the judgment criterion may be additionally used as the judgment criterion. Alternatively, the movement of the gaze in consideration of the fixed points of the plurality of gazes, the fixing time at each fixing point, and the temporal change thereof, etc. may be used as a criterion for determination.

However, in this determination, the content of the learning content or the teaching method of the instructor (teacher) may be additionally considered. And this determination may be performed using a predetermined model (eg, class participation detection model) based on artificial intelligence. According to an embodiment of the present invention, which will be described later, the class participation detection model clusters states of similar situations based on unsupervised learning and repeats the modification (update) of the cluster by adapting to a new experience to obtain a classified optimal value. It may be to perform reinforcement learning as a method.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.

1 is a block diagram schematically showing the schematic configuration of a non-face-to-face online class participation detection device according to an embodiment of the present invention. Referring to FIG. 1 , the non-face-to-face online class participation detection device 100 (hereinafter, referred to as 'detection device') includes a data collection unit 110 , a calculation unit 120 , and a class participation state determination unit 130 . . In addition, the detection apparatus 100 may further include a feedback unit 140 .

The detection apparatus 100 may be implemented through, for example, a computer program executable by a computer processor and a recording medium storing the program (ie, a computer readable recording medium). There is no particular limitation on the type of recording medium in which the computer program is stored, and it may be permanently or temporarily stored in the corresponding medium. In addition, individual components constituting the detection apparatus 100 are logically divided based on their respective functions, and may be implemented as separate function modules, or two or more components may be implemented as a single function module.

In addition, the detection apparatus 100 may further include a database (not shown) for storing data input to each component and/or data generated as a result of processing in each component. Alternatively, the detection apparatus 100 may use as a database a storage means of a computer in which a computer processor that executes this is installed. Therefore, the flow of data indicated by the arrows in FIG. 1 is only for intuitively understanding the technical features of the present invention, and actually through the input/output of data that occurs between each component and the database, the data indicated by the arrows in FIG. A flow can be implemented.

The detection device 100 of FIG. 1 indicates that a predetermined number of class participants (N, for example, N is the number of members of a predetermined group participating in the same online class such as 30, 100, etc.) of a specific online class (eg, content 1, etc.) It is a device for detecting whether you are participating according to the progress, that is, the state of participation in the class. Here, learners participate in non-face-to-face online classes by using personal electronic devices such as personal computers, notebook computers, tablet computers, smart phones, etc. that can be integrated with or connected to the monitor, respectively. In addition, an eye tracking device (eg, an application that can be installed in the personal electronic device) is installed in the personal electronic device together with one or more cameras.

The gaze tracking device is a means capable of calculating coordinates (hereinafter, 'gay coordinates') of a point to which a learner's gaze is directed from an image acquired by a camera of a personal electronic device. The gaze tracking apparatus may output, for example, the position of the learner's gaze (ie, the gaze position on the gazed display), which is gazing at the display of the learner's personal electronic device, as a coordinate value. In addition, when the learner's gaze is directed to a place other than the display, a relative position with respect to the display may be output as a coordinate value.

According to the embodiment of the present invention, there is no particular limitation on the type of the gaze tracking device or the gaze tracking method thereof, and any means capable of generating the gaze coordinates of the learner from the camera image as an output is sufficient. The gaze tracking device may be, for example, ITU Gaze Tracker distributed by IT University in Denmark. ITU Gaze Tracker is a gaze tracking program developed as an open source project for building a low-cost eye tracking system that uses pupil and corneal light tracking for gaze tracking. However, this is an example, and may be another type of gaze tracking device that is currently commercialized and used, or a more improved device that is newly developed and used later for gaze tracking.

The data collection unit 110 receives eye tracking data for each of the N learners participating in the online class. More specifically, the data collection unit 110 receives, from the personal electronic device, the eye tracking data acquired by the eye tracking device installed in the personal electronic device of each of the N learners. Here, the eye tracking data refers to a set of temporal coordinate values for the gaze position of the learner obtained by the gaze tracking device. That is, the eye tracking data indicates a series of coordinate values for the gaze position measured at a predetermined time interval, and there is no particular limitation on the size of the measurement time interval. In addition, the time interval does not always need to be constant during the course of the online class, and may be changed according to the progress of the class.

The calculation unit 120 calculates a gaze fixation point, which is a position at which each learner's gaze is fixed, by using the gaze tracking data collected by the data collection unit 120 . This is to identify the area in which the learner is learning, such as whether the learner is watching the content and/or what part of the content, etc., through the position of the gaze. According to one aspect of the present embodiment, the calculator 120 includes the gaze coordinate values included in the gaze tracking data within a predetermined area for a predetermined time (eg, a predetermined number of time-continuous gaze coordinate values). If there is, the corresponding area may be determined as the gaze fixation point.

2 is a schematic diagram for explaining an example of a method of calculating a fixed position of a gaze using a gaze coordinate value. In FIG. 2 , numbers ① to ⑭ indicate positions of gaze fixation points sequentially collected by the data collection unit 110 .

Referring to FIG. 2 , first, when four consecutive gaze coordinate values (① to ④) are included in a square of a predetermined size (eg, 30×30 pixel size) in a rectangular display, the corresponding area is defined as a gaze fixation point. to decide Here, four are exemplary, and the number may vary. And when the subsequent gaze coordinate values (⑤ to ⑭) are new positions outside the corresponding gaze fixation point, the gaze coordinate values (⑤ ~ ⑦, ⑩), these new positions are merged into the current gaze anchor point, and the extension area becomes the new gaze anchor point. On the other hand, if the gaze coordinate values (⑧, ⑨, ⑪ ~ ⑭) are not included in the extended area (eg, 50×50 pixel size) including the position of the current gaze fixation point, these new positions are ignored (⑧, ⑨) Alternatively, when four consecutive eye fixation points are located within a new square of a predetermined size, that is, 30×30 pixels, this new square is used as a reference (⑪ to ⑭) for a new eye fixation point.

According to an aspect of the present embodiment, the calculator 120 may also calculate the fixation time at each gaze fixation point by using the eye tracking data collected by the data collection unit 120 . The fixed time indicates the time the learner looked at the corresponding gaze fixation point (content in the corresponding area), and it can be used to grasp the learner's attention level or learning state.

In addition, the fixation time helps to understand the movement pattern of the gaze. 3 is an example of a diagram schematically illustrating a movement pattern of a specific learner's gaze. Referring to FIG. 3 , in order to show the movement pattern of the gaze, the fixing time of the gaze at each gaze fixation point is shown in the size of a circle. That is, the larger the size of the circle, the longer the fixing time.

Using this gaze movement pattern is to use the fact that the number of fixation points and the fixation time among gaze information show a deep correlation with the learner's learning degree and cognitive load. Therefore, if the movement pattern of the gaze is used, it can be used as an element to grasp the learning state of the learner, and through this, the degree of the learner's visual attention to the corresponding area of the content can be grasped.

The class participation state determination unit 130 determines whether each of the learners is normally participating in accordance with the progress of the class by using the distribution of the fixed gaze points of the learners calculated by the calculation unit 120 .

Here, 'distribution of learners' gaze fixation points' refers to the number of learners at each gaze fixation point obtained at an arbitrary time. More specifically, the calculator 120 calculates a gaze fixation point for each of the N learners at a specific time. In this case, some or all of the gaze fixation points of each of the N learners may overlap, and the gaze fixation points of some learners may not overlap with other learners. Here, the 'distribution of the gaze fixation points of the learners' is statistical data indicating how many learners correspond to each of the gaze fixation points obtained by the calculator 120 .

As an example, the class participation state determination unit 130 determines that this area is a gaze area when there are relatively many learners whose gaze fixation point corresponds to a specific area among a group of learners (eg, N learners); Based on whether the gaze fixation point of each learner corresponds to the gaze region, the class participation state of the corresponding learner may be determined. That is, when the gaze fixation point of a specific learner falls under the gaze area, it is determined that the learner is normally participating in the class, but when the gaze fixation point does not correspond to the gaze area, it can be determined that the learner does not normally participate in the class. In this case, it may be determined that a learner whose gaze fixation point is not calculated does not normally participate in the class, but this is only an example.

According to an embodiment of the present invention, there is no particular limitation on how many learners the corresponding area should be the gaze fixation point in order to determine the gaze area. For example, if more than half of the total N learners stare at the same area (ie, the gaze fixation points coincide or overlap), or preferably 2/3 or more or 3/4 or more of the learners stare at the same area , the corresponding area may be determined as the gaze area.

As another example, the class participation state determination unit 130 may use the distribution of the learners' gaze fixation points and the fixed time at the corresponding gaze fixation points to determine the class participation status. In this case, the class participation state determination unit 130 determines the class participation state of the student by comprehensively considering whether the fixed point of each learner's gaze corresponds to the gaze region, as well as the fixed time for which the gaze is fixed in the gaze region. You may.

As another example, the class participation state determination unit 130 may use, along with the distribution of the learner's gaze fixation points, the fixed time at the corresponding gaze fixation point and its change over time to determine the class participation status. In this case, the class participation state determination unit 130 considers the movement of the learner's gaze, such as whether the fixed point of each learner's gaze corresponds to the gaze region, the fixation time at which the gaze is fixed in the gaze region, and the change of the gaze fixation point. Thus, it is possible to determine the student's class participation status.

According to one aspect of the present embodiment, the class participation state determination unit 130 may also use the online class content information displayed on the screen to determine the class participation state of the learner. To this end, the class participation state determination unit 130 may receive content information about content used in an online class from the outside or collect content information from data displayed on the screen. Such content information may be a subject, execution (lecture) time, content ID, etc., but is not limited thereto. In addition, when a plurality of contents are mixed on one screen, information on each content may be collected in units of individual areas (learning areas) of the screen. Accordingly, in determining the class participation state of the learner, by considering the content information together, it is possible to more adaptively determine the class participation state according to the type of class subject, school age, or the like.

The class state participation determination unit 130 may be implemented using an online class participation detection model based on unsupervised learning artificial intelligence. According to this, more effective and accurate judgment is possible because AI technology is used to judge class status participation. And, since unsupervised learning is used, there is no need to prepare a considerable amount of training data in advance for artificial intelligence learning, and no prior knowledge for initialization is required. also small In addition, since the corresponding model can be updated with the actually performed judgment data, more accurate judgment is possible as the actual use continues.

To construct an online class participation detection model based on unsupervised learning artificial intelligence, first, an unsupervised learning-based class participation map is created. The class participation map is a key algorithm that can generate various learning participation behaviors of learners participating in non-face-to-face online classes using unsupervised learning. To this end, first, a class participation pattern is generated based on unsupervised learning, and unsupervised learning algorithms such as Self-Organizing Map (SOM) and Generative Adversarial Networks (GAN) can be used. Accordingly, it is possible to generate a class participation map by first extracting feature values for candidate variables from the acquired data, and then clustering the extracted feature values according to the non-face-to-face online class participation behavior for each class subject classification. Accordingly, it is possible to reduce the cost of creating a database.

In the feature extraction step, feature values are extracted from the candidate variables obtained from the collected data, such as the location of the gaze fixation point, the gaze fixation time, the content gaze frequency, and whether the gaze is fixed. value can be extracted. At this time, the calculated measured values are normalized to a range of [-1, 1] or [0, 1] because the ratio of the maximum value and the minimum value is different from each other and the value may be very large. Accordingly, in the normalized measured values, the ratio of the maximum value to the minimum value is standardized, and the measured value out of the corresponding range can be determined as an error, which helps to remove data noise.

Then, the process of removing duplicates of the feature values and reducing the dimension is performed. More specifically, since features that are not related to the gaze movement feature or highly correlated with each other may be mixed among the features, the dimension is reduced by removing duplicates of the selected candidate variables (features). In this case, in order to extract a core feature from among the plurality of features, a dimension reduction algorithm such as principal component analysis (PCA) may be used, or a principal component analysis and a feature selection algorithm may be combined.

And, using an unsupervised learning algorithm including SOM or GAN, the extracted feature values are clustered according to the non-face-to-face online class participation behavior for each class class, and an 'unsupervised learning-based class participation map' is created for reinforcement learning. carry out During reinforcement learning, several episodes must be experienced, and since the target state does not transition to the next state at the end of one episode, it cannot be treated like other clustered states, so by adding a cluster centered on the goal state, The number of nodes constituting the 'unsupervised learning-based class participation map' becomes "the number of clusters × the number of possible actions + 1". By continuously updating the model through comparison with the previously generated unsupervised learning-based class participation map by reinforcement learning, it is possible to increase the accuracy of judgment.

The feedback unit 140 provides feedback, such as a notification message, to learners based on the determination result of the class participation state determination unit 130 . For example, the feedback unit 140 may transmit a notification message including contents such as an attention warning, current status, and penalty information only to learners determined by the class participation status determination unit 130 not to participate in the class. In this case, the notification message may be transmitted to a personal electronic device used by the learner for online class and displayed in a pop-up form on the screen or may be transmitted to a mobile terminal such as a smart phone of the learner. Depending on the embodiment, the feedback unit 140 may transmit the determination result of the class participation status determination unit 130 such as a notification message not only to individual learners but also to teachers (instructors) or parents in the form of a predetermined message.

The above description is merely an example and should not be construed as being limited thereto. The technical idea of the present invention should be specified only by the invention described in the claims to be described later, and all technical ideas within an equivalent range should be interpreted as being included in the scope of the present invention. Therefore, it is apparent to those skilled in the art that the above-described embodiment can be modified and implemented in various forms.

Claims (7)

In the device for detecting whether a learner receiving a non-face-to-face online class with a personal electronic device having a gaze tracking device is participating in accordance with the progress of the online class,
a data collection unit for receiving the eye tracking data obtained by the eye tracking device from the personal electronic device of each of the learners participating in the online class;
a calculation unit for calculating a gaze fixation point, which is a position at which the gaze of each of the learners is fixed, by using the gaze tracking data collected by the data collection unit; and
and a class participation state determination unit configured to determine whether each of the learners participates in a class by using the distribution of the gaze fixation points of the learners calculated by the calculation unit.
The method of claim 1,
The class participation state determination unit determines the gaze fixation point corresponding to the most learners among the gaze fixation points of each of the learners as the gaze area, and then, based on whether the gaze fixation point of a specific learner is included in the gaze area, the learner's A non-face-to-face online class participation detection device, characterized in that it is determined whether or not to participate in the class.
The method of claim 1,
The calculation unit also calculates the fixation time at the gaze fixation point of each of the learners together,
The class participation state determination unit, a non-face-to-face online class participation detection device, characterized in that it determines whether the class participation of each of the learners by using the gaze movement information according to the gaze fixation point and the fixed time.
4. The method of claim 3,
The class participation state determination unit, non-face-to-face online class participation detection device, characterized in that by using the content information of the online class including the type of class and the execution time as well to determine whether each of the learners participate in the class .
5. The method of claim 4,
The class participation state determination unit is a non-face-to-face online class participation detection device, characterized in that it is implemented using an online class participation detection model based on unsupervised learning artificial intelligence.
The method of claim 1,
Non-face-to-face online class participation detection device, characterized in that it further comprises a feedback unit for transmitting a notification message to the personal electronic device of the learner who has determined that the class participation status determination unit is not participating in the class.
In the method for detecting whether a learner receiving a non-face-to-face online class with a personal electronic device having an eye tracking device is participating in accordance with the progress of the online class,
receiving the eye tracking data obtained by the eye tracking device from the personal electronic device of each of the learners participating in the online class;
calculating a gaze fixation point, which is a position at which the gaze of each of the learners is fixed, by using the gaze tracking data collected in the collecting step; and
and determining whether each of the learners participates in a class by using the distribution of the gaze fixation points of the learners calculated in the calculating step.

Images