KR20120113573A - Method of providing customized learning contents based on brainwave information - Google Patents

Abstract

The present invention relates to a system for providing customized learning contents for each user using EEG information, and a method thereof, wherein the learning contents provided through the e-learning system are divided and divided according to a predetermined criterion for each round, and collected according to each individual's inclination and understanding degree. By selecting each part to be included in each learning content, we provide personalized learning contents. In particular, when the user's brain waves are monitored during the learning, but the concentration is lowered below a certain level, the user's feedback is collected through the user interface displayed on one side of the learning screen, and the portion where the concentration is low is analyzed. It is characterized by reconstructing the next learning content. In addition, depending on the EEG level and feedback of the user, only the corresponding portion of the learning content that is currently provided may be changed and provided in real time. According to the present invention, by using the brain wave information and feedback of the user can be provided by reconfiguring the learning content suitable for each user.

Description

How to provide customized learning contents for each user using EEG information {METHOD OF PROVIDING CUSTOMIZED LEARNING CONTENTS BASED ON BRAINWAVE INFORMATION}

The present invention relates to a method of collecting brain wave information of a learner in the process of providing learning content through an e-learning system, and selecting and providing customized learning content using the same.

Thanks to the expansion of Internet infrastructure and the development of computing technology, the so-called e-learning allows students to learn at the level of each learner without having to be confronted with the lecturer, teaching, and learning in the classroom. Electronic learning is widely used.

This e-learning has the advantage that learners can learn at the time and place they want, and they can take the initiative by determining the appropriate learning method and progress.

This e-learning not only solves the temporal and spatial constraints, but also enables the learners to learn in independent spaces at low cost.

In addition, compared to the conventional offline teaching method, the choice is wider and the learning effect can be greatly improved.

1 illustrates an e-learning system of a general server-client structure according to the prior art.

As shown in FIG. 1, the user accesses the server 20 through a network (internet, intranet, etc.) using the client 10 to receive and play contents for learning.

In this case, the client 10 may mainly assume a personal computer (PC), but in addition, the client 10 may be connected to the server 20 through the Internet, and may reproduce the provided learning content in a manner suitable for the format of the content. Various types of hardware may be used, such as tablets, smart phones, and netbooks.

The server 20 stores account information for each user, and reads user account information for the client 10 connected through the Internet, and provides appropriate learning contents according to the progress of the subject the user is taking.

However, unlike the case where the lecture is face-to-face with the instructor on-line, this e-learning is likely to be a form in which the contents of the lecture are unilaterally transmitted through the client 10 screen, and the user of the learning process It can be difficult to maintain the same level of concentration from start to finish.

In addition, since the whole process of learning depends on learner's autonomy, it may lead to sluggish learning effect if the learner's will and interest are not enough.

In particular, since each learner has different understandings, learning styles, concentration, interests, and aptitudes, there will be some learners who achieve high learning outcomes by matching their learning contents with the unified learning contents. There is also a lot to happen.

Therefore, there is an urgent need to find a methodology for providing customized learning contents for each individual by analyzing individual learners' tendencies for successful e-learning settlement.

The present invention has been made to solve the problems of the prior art as described above to collect the brain wave information of the learner during the learning through the e-learning system, the brain wave information when the user shows drowsiness, distraction or concentration decreases learning at that time The purpose of this study is to provide a methodology for grasping the learning tendency of users by receiving feedback from users about contents.

Furthermore, another object of the present invention is to provide a methodology for selecting the next learning content in real time by using the user learning tendency identified in the learning content provided in each unit.

Yet another object of the present invention is to provide a methodology for providing a real-time substitute of only the corresponding contents of the lecture video by the lecture video of another lecturer when the user shows drowsiness, distraction or concentration during the provision of the learning content provided in the form of the lecture video. Is in.

In order to achieve the above object, the method for providing customized learning content for each user using brain wave information according to an embodiment of the present invention stores a curriculum of learning content to be provided to the user according to a user's selection, and each learning content is Each learning content further comprises a plurality of sequential unit learning data and metadata for each unit learning data, wherein the curriculum is composed of a plurality of episodes, one or more of each session. Step 110 corresponding to the learning content;

Providing a learning content corresponding to a predetermined round of the curriculum through a display device, and providing the learning content and real-time monitoring of a user's biosignal;

Stopping provision of the learning content whenever the biosignal of the user has a predetermined range and specifying unit learning data at a corresponding time, and displaying a questionnaire on one side of the display device;

Step 140, after receiving an input value for the questionnaire from the user, resuming the provision of the learning content;

Generating a propensity information of the user by using the value of the user biosignal in operation 130 and the received user input value in operation 140; And

And a step 160 of selecting learning content corresponding to the next round of the curriculum by using the generated propensity information.

On the other hand, in order to achieve the above object, the method for providing customized learning content for each user using EEG information according to this embodiment of the present invention stores the curriculum of the learning content to be provided to the user according to the user's selection, each learning The content is composed of each unit, and each learning content further includes a plurality of sequential unit learning data and metadata for each unit learning data, and the curriculum is composed of a plurality of episodes, one for each session or Step 210 corresponding to the more learning content;

Step 220 of providing learning content corresponding to a predetermined round of the curriculum through a display device, and real-time monitoring of a user's bio-signal at the same time as providing the learning content;

Stopping the provision of the learning content whenever the biosignal of the user has a predetermined range and specifying unit learning data at a corresponding time, and displaying a questionnaire on one side of the display device;

Step 240 of receiving an input value for a questionnaire from a user;

A 250th step of generating propensity information of the user using the value of the user biosignal in operation 230 and the received user input value in operation 240;

A step 260 of changing the specified unit learning data into other unit learning data using the analysis result and providing the changed unit learning data through a display device; And

Step 270 of resuming the provision of the learning content by displaying on the display device from the next unit learning data of the interrupted unit learning data as the provision of the changed unit learning data is completed.

According to the present invention can be more directly and accurately grasp the propensity information for each user for the learning content provided through the e-learning system. In particular, when a user shows a physical change such as drowsiness or distraction, the user receives feedback immediately after the lecture playback of the corresponding section, and does not investigate general satisfaction or evaluation of the entire content as in a conventional survey, It has the effect of being able to get specific and direct information such as sleepiness and what improvement measures are needed.

In particular, there is an effect that the learning content of the next round can be dynamically selected in the learning content provided in each round by using the user tendency information thus identified.

Furthermore, when the lecture video is taken in real time, the user's brain wave information is collected in real time, and when the user becomes sleepy, distracted, or loses concentration, the user's learning efficiency is analyzed and then replaced by another lecturer's lecture video in real time. There is an effect that it can provide.

1 is a reference diagram showing a general form of an e-learning system according to the prior art,
2 is a reference diagram showing how to measure the EEG during the learning of the user,
3 is experimental data obtained by collecting brain wave information of a subject and calculating drowsiness, distraction, and concentration indicator values therefrom.
4 is an average index value of each of a plurality of subjects obtained as a result of the experiment,
5 is a reference diagram illustrating how a questionnaire is displayed on one side of a display device;
6 is a reference diagram for explaining the configuration of the learning content by way of example,
FIG. 7 is a conceptual diagram illustrating a process of identifying a learning propensity of a user by using a biosignal value of a user and input values of a question item for learning content.
8 is a flowchart illustrating a time-series description of a method for providing personalized learning content for each user using EEG information according to an embodiment of the present invention.
FIG. 9 is a reference diagram illustrating a process of generating learning content of a next round according to a curriculum in the method illustrated in FIG. 8.
10 is a flowchart illustrating a time-series description of a method for providing personalized learning content for each user using EEG information according to an embodiment of the present invention.
FIG. 11 is a reference diagram for explaining a process of providing a part of a lecture video in real time by replacing it with another lecturer's lecture in the invention shown in FIG. 10.

Hereinafter, with reference to the preferred embodiments of the present invention and the accompanying drawings will be described in detail the present invention. In order to clarify the present invention, contents which are not related to the configuration of the present invention will be omitted, and the same reference numerals are used for the same components.

On the other hand, when an element is referred to as being "comprising" another element in the description of the invention or in the claims, it is not interpreted as being limited to only that element, Elements may be further included.

Also, in the description of the invention or the claims, the components named as "means", "parts", "modules", "blocks" refer to units that process at least one function or operation, Each of which may be implemented by software or hardware, or a combination thereof.

In the user-specific learning content providing method using the EEG information according to the present invention collects the biometric information and feedback of the user during the learning in the e-learning system.

The collected biometric information includes at least a user's brain waves, and may further include various types of information that may be detected from the user's body, such as heart rate variability.

FIG. 2 exemplarily illustrates a process of collecting brain waves of a user using the EEG 2 while the user plays and learns the learning content through the display apparatus 1 of the client 10.

As shown in FIG. 2, the user reproduces the learning content to perform learning, and at this time, the brain wave measurement apparatus 2 is used to monitor the brain waves.

Human brain waves are a general idea that synaptic potentials are generated from neurons in the cerebral cortex, and they are detected by recording weak electrical activity from the cerebral cortex.

These brain waves are also classified according to their frequency and amplitude. The regular waves before and after 10 Hz are referred to as alpha waves, and waves faster than alpha waves are called short waves or beta waves.

According to the current technology, brain waves record very weak electric signals in frequency and amplitude. Jitter easily occurs, and it is difficult to detect higher mental activities such as emotions, thoughts, and wills. In general, only the level of information about whether the activity of the entire brain is open or asleep is obtained.

However, from a clinical medical point of view, efforts have been made to obtain patterns of brain waves by analyzing phases, waveforms, wave amounts, distributions, and continuity in addition to frequency and amplitude.

However, since such brain waves have a large individual difference, it is desirable to determine the amount of change from the average value based on the data accumulated for each individual.

Specifically, the abnormal brain wave detection algorithm may be set by a method of displaying a change in frequency above a threshold value or a brain wave of a high or low amplitude above a threshold value.

From this point of view, EEG information was collected from a large number of subjects, and the results were analyzed to produce meaningful indicators of learning status.

3 is experimental data obtained by collecting brain wave information of a test subject at intervals of 4 seconds and calculating drowsiness, distraction, and concentration indicator values therefrom. EEG information was collected and analyzed for a plurality of subjects, and FIG. 3 corresponds to data of any one of the subjects.

4 shows the average index value of 40 test subjects obtained as a result of the analysis performed as described above.

At this time, concentration corresponds to an indicator indicating whether or not the student is generally immersed in learning, drowsiness means whether or not he feels drowsy, and distraction means chatting or doing other actions regardless of learning.

As shown in FIGS. 3 and 4, since very different values are recorded for each test subject, it is very difficult to obtain a standard index value indicating concentration, drowsiness, and distraction from each test subject. I could conclude.

However, in case of concentration, the concentration was lowered than the usual level when the concentration was lowered by a certain level than the usual index value obtained for each subject. In the first test subject of FIG. 4, the average concentration index value of the video was 78.1, and in the second test subject, it was found that the difference was 56.62.

When the test subjects complained of difficulty in learning due to the decrease in concentration, the indicators also showed differences. However, when the test subjects dropped more than 30% of the average indicator, the concentration decreased.

Meanwhile, as shown in FIG. 4, the sleepiness index showed a difference in the mean index value for each test subject. However, when the index value increased more than 85, most of the test subjects felt drowsiness.

In addition, in the case of the distraction indicator, each subject showed a difference in the average value of the usual indicator, but it was confirmed that when receiving a telephone call or doing other actions irrelevant to learning during the learning, the instantaneous high value was more than 40.

In the actual experiment, a number of items were analyzed in addition to concentration, drowsiness, and distraction, but it was again confirmed that it was not easy to directly grasp the learning status of users by standardizing EEG information.

However, in the case of concentration, if the EEG information of each user's usual learning can be accumulated and collected, it can be seen that when the concentration is markedly decreased by more than a certain percentage, the concentration changes significantly.

On the other hand, in case of drowsiness and distractions, despite the large difference in the usual EEG values among users, it was confirmed that they showed significant changes in EEG when they were sleepy or distracted. It was possible to confirm.

Looking specifically at the indexing of concentration, drowsiness and distraction, first, in case of "concentration", the pattern of brain waves accumulated cumulatively after the user starts learning is averaged, and then the threshold value (30% in the experiment example) is higher than the average value. If there was a change, the concentration could be judged to be low.

On the other hand, in case of "sleepiness", EEG values are different for each subject, but according to sleepiness, the frequency of EEG decreases and the amplitude tends to increase, and as a result of the experiment, it was determined that the individual deviation is lower than "concentration".

The average value and normal distribution were calculated using the EEG information obtained from the drowsiness of the subjects to sleep, and then converted into t-score (100) as the "sleepiness" index value. .

At this time, when the value converted from the EEG detected by the user by the same method is 80 or more, it could be determined to be generally sleepy.

On the other hand, in the case of "distraction", as in "drowsiness," the average value and the normal distribution are obtained by using the EEG information obtained during the process from the time of drowsiness to the fall asleep from a plurality of subjects, and then to t-score (100) The converted value was used as an "distraction" index.

Brain waves, on the other hand, are sensitive enough to cause undulation even in the case of very small stimuli, even in the case of blinking, which are significant because "distraction" indicators indicate a case of doing other work or thinking differently during learning. In order to make a payment, the stalks were sufficiently removed, and then the indicator was set.

At this time, when the value converted from the EEG detected by the user is equal to or greater than 40, it could be determined as a generally distracting state.

In the method for providing customized learning contents for each user using EEG information according to the present invention, as illustrated in FIGS. 2 to 4, the EEG of the user is detected during the learning process of the user, and the threshold values are indexed by the method as described above. It monitors in real time whether you are decent, sleepy, or distracted, depending on whether you are passing over.

On the other hand, with reference to Figures 5 to 9 will be described in time series a user-specific learning content providing method using the EEG information according to an embodiment of the present invention.

FIG. 5 illustrates a form in which a questionnaire is displayed on one side of a display device on which learning content is displayed, and FIG. 6 exemplarily illustrates a configuration of learning content having a plurality of unit learning data and metadata. Meanwhile, FIG. 7 illustrates a process of determining a learning tendency of a user by using a user biosignal value and an input value for a questionnaire, and FIG. 9 illustrates a process of generating learning content of the next round according to a curriculum.

According to the flowchart shown in FIG. 8, first, a curriculum of learning content to be provided to the user according to a user's selection is stored (S110).

The user may access the server 20 by using the client 10 and select a course to be taken. Accordingly, the server 20 stores the curriculum of the selected course in the user's account.

At this time, the curriculum is composed of a plurality of rounds divided based on the content as shown in FIG. 9, and the server 20 provides the learning content corresponding to each round to the client 10.

For example, if a lecturer's lecture on a particular subject is recorded in 50 sessions, divided by 1 hour unit for each session, the curriculum of the subject is preferably 50 sessions, and each session is for 1 hour. Is provided in the form of learning content.

Meanwhile, the learning content provided as described above corresponds to each round of the curriculum, and has a structure as shown in FIG. 6. As shown in FIG. 6, the learning content is a combination of a plurality of sequential unit learning data.

On the other hand, each unit learning data has metadata such as what subject, what content, what teaching method is included, the degree of difficulty, and the lecturer's lecture.

In particular, in the case of a video lecture that is produced in the form of one video file per one lecture by dividing each learning content composed of each unit into a plurality of unit learning data and including metadata about each of these units In addition, it is possible to specify the contents of the lecture when the user changes the EEG.

For example, if a series of learning content is produced as an hour-long video file, it is divided into unit learning data based on the content, and once from the beginning of the video to 10 minutes, once from 10 minutes to 15 minutes. 2, 15 minutes to 50 minutes, 3 times, 50 minutes to 1 hour, 4 units can be divided into learning data, each metadata can be created and included in the learning content, thereby the contents of the entire video Each part can be specified by reference.

On the other hand, the learning content corresponding to the predetermined round of the curriculum provided to the client 10 is provided by displaying through the display device (1). In this case, the bio signal of the user is monitored in real time by the method as described above (S120).

At this time, the bio-signal includes at least the EEG signal of the user collected through the EEG 2, it is possible to determine one or more of drowsiness, distraction, concentration by indexing by the method described above.

On the other hand, when the collected EEG is indexed by the above method and the value has a certain range of values-that is, when the concentration is low, sleepy or distracted, the provision of learning content is suspended. The questionnaire is displayed on one side of the display apparatus 1 (S130), and an input value for the questionnaire is received from the user (S140).

Even if the concentration is temporarily lowered, judged to be sleepy, or distracted by EEG analysis, first, the detection of EEG does not necessarily guarantee a drop in concentration, drowsiness, or distraction in all situations. Second, there is a limit that it is difficult to grasp the relationship between the contents of the corresponding learning content and the learning pattern, achievement, and aptitude of the corresponding learning contents simply by being drowsy, distracted, or having low concentration.

Therefore, if the EEG detection result is low concentration, sleepy or distracting, whether the user thinks that the teaching method of the learning content does not suit him, does the composition of the content feel difficult to concentrate, or is simply bad or sleepy? Receive direct feedback from the user by displaying a questionnaire asking questions.

It is important to note that this is not a feedback on the entire learning contents provided, but a specific questionnaire about the contents of contents when concentration is low or sleepy.

Conventionally, there have been methods for collecting feedback from users in the same manner as offline lecture evaluation or online content evaluation, but some contents of the learning contents-in particular, learning contents when the concentration of the user becomes low, sleepy or distracted- We couldn't get user feedback on.

In this way, since feedback is obtained from the user regarding specific contents of the learning contents, instead of always asking the same questions even when selecting a questionnaire, the contents of the learning contents provided or whether the user is sleepy or temporary concentration Depending on whether it is a decline or an overall distraction, it is possible to select and display the appropriate question from the pre-stored questionnaire.

Accordingly, it is possible to collect the learning propensities, learning patterns, and understandings and achievements of the contents for each field with a very high level of accuracy.

In this way, upon receiving feedback from the user, playback of the learning content is resumed.

Meanwhile, the propensity information of the user is generated using the value of the user biosignal collected in step S130 and the received user input value in step S140 (S150).

As shown in FIG. 7, the propensity information of the user indicates whether the user has decreased concentration, distraction, or drowsiness with respect to what metadata value (ie, unit learning data having what metadata value and learning content). In addition, it is information indicating the reason for doing so, and can be detected by accumulating and adding the number of occurrences of the biosignal value and the input value of the user to the metadata value of the unit learning data specified in step S130, respectively.

In the example of FIG. 7, the user feels drowsiness three times for the unit learning data having the values of "Category: Physics" and "Instructor: Hong Gil-dong" as metadata values, and inputs "Difficult" for the reason. It can be seen that.

If the number of occurrences is large, the user is likely to feel sleepy for the same reason for the same unit learning data or the learning content including the unit learning data.

Therefore, the learning content corresponding to the next round of the curriculum is selected using the propensity information of the user generated as described above (S160).

That is, the propensity information of the user generated while providing the training data of the current round is reflected in the selection of the learning content corresponding to the next round on the curriculum.

Of course, the user's propensity information is accumulated over several times and several subjects, and as the accumulation information is accumulated, more precise learning content match making is possible.

On the other hand, look at the process in more detail first to retrieve the metadata value corresponding to the next round of the curriculum.

Referring to the example of FIG. 9, it can be seen that the first round of the curriculum has metadata of "content: understanding of atoms 1-1", and the second round has metadata of "content: understanding of atoms 1-2".

In this way, after extracting the metadata of the corresponding curriculum, unit learning data having corresponding metadata values are distinguished from the database (S161).

Next, unit learning data having metadata corresponding to the generated user propensity information is selected (S162). That is, the unit learning that matches the user orientation information by excluding the unit learning data having the metadata that the user frequently feels sleepy or the unit learning data having the metadata when the user felt too difficult. Data can be selected.

Learning content is generated by sequentially connecting the selected unit learning data as shown in FIG. 9 (S163).

The learning content generated as described above is provided when the next learning content is provided according to a user's request.

On the other hand, with reference to Figures 5 to 7, 10 and 11 will be described in time series a user-specific learning content providing method using the EEG information according to this embodiment of the present invention.

This embodiment of the present invention, unlike the above embodiment, provides a method of changing only a specific part of the lecture in real time according to the user's feedback instead of selecting the next learning content.

In particular, when a user falls behind in learning a lecture video and the learning efficiency is reduced, only a portion of the video is replaced by a video provided by another instructor, and when the playback is finished, the method reverts back to the original lecture video. .

In this embodiment of the present invention, the learning content is preferably in the form of a lecture video of a lecturer, and includes unit learning data in which a lecture video of one round is divided into a plurality of sections by time.

For example, if a series of learning content is produced as an hour-long video file, it is divided into unit learning data based on the content, and once from the beginning of the video to 10 minutes, once from 10 minutes to 15 minutes. 2, 15 minutes to 50 minutes 3 times, 50 minutes to 1 hour can be divided into four unit learning data.

FIG. 10 is a flowchart illustrating a method of providing personalized learning content for each user using EEG information according to an embodiment of the present invention, and FIG. 11 is a part of another lecturer who teaches the contents of a lecture video in the invention shown in FIG. This is a reference diagram explaining the process of providing real-time replacement by lecture.

According to the flowchart shown in FIG. 10, a curriculum of learning content to be provided to the user is stored according to a user's selection (S210).

Thereafter, at the request of the user, learning contents corresponding to a predetermined round of the curriculum are provided, and the provided learning contents are displayed on the display device.

Meanwhile, since the learning content is displayed, the bio signal of the user is monitored in real time while learning is performed (S220).

As described above, the biosignal of the user includes brain wave information of the user.

On the other hand, whenever the user's bio-signal has a predetermined range of values, the provision of the learning content is stopped and the unit learning data of the corresponding time point is specified, and a questionnaire is displayed on one side of the display apparatus (S230). The input value for the questionnaire is received (S240).

The unit learning data at this point of time may correspond to a certain section of the video of the lecture (for example, a section corresponding to 10 minutes to 20 minutes).

As such, the value of the user biosignal is collected, and when the input value is received from the user, the user's propensity information is generated using the input value (S250).

The specified unit learning data is changed to other unit learning data using the analysis result, and the changed unit learning data is displayed through a display device (S260).

According to the example of FIG. 11, the unit learning data having the metadata “Instructor: Hong Gil-dong” was provided, but the display of the learning content was stopped after the display of the learning content was stopped due to the user's drowsiness in the second unit learning data of the learning content. It can be seen that it is replaced with other unit learning data with the meta data "Herbyun".

That is, the interrupted unit learning data is omitted and only the corresponding section is displayed among the lecture videos of other instructors.

For example, the user may feel drowsy, for example, at a time point of about 13 minutes while playback of a 10 to 20 minute interval is being performed in a learning content having a metadata value of “Instructor: Hong Gil-dong” that has been provided. If you input an arbitrary input value, the appropriate unit learning data is selected according to the value, but the unit learning data belonging to the video lecture of another instructor is provided.

The unit learning data replaced in the example of FIG. 11 may be a predetermined period (eg, 15 minutes to 25 minutes) of a lecture video having meta data “Instructor: Huh Kyun”.

Then, as the provision of the changed unit learning data is completed, the provision of the learning content is resumed by displaying the next unit learning data of the interrupted unit learning data through the display device (S270). Interrupted unit learning data is omitted.

Meanwhile, the method for providing user-specific learning content using EEG information according to the present invention may be implemented as a computer readable code and stored in a computer readable recording medium.

The computer-readable recording medium may include any type of medium in which data readable by a computer system is stored. Examples of the medium include a DVD-ROM, a CD-ROM, a hard disk, a USB memory, a flash memory And the like.

On the other hand, the expression contained in the recording medium encompasses both the case of being recorded on the recording medium in large quantities and distributed in a package form as well as being provided through the network in the form of data packets and stored in the recording medium.

While the present invention has been described with reference to the accompanying drawings and embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. . Accordingly, the scope of the present invention should be determined only by the technical idea of the appended claims, and is not limited to the above embodiments.

In particular, the above description has been made on the assumption of an e-learning system having a server-client structure illustrated in FIG. 1. However, the present invention is not limited thereto, and the present invention is not limited to the embodiment, such as the case of being manufactured in the form of a software package and running at the client end or through the CBT (Computer Based Teaching) equipment.

1: display device 2: EEG measuring device
10: client 20: server

Claims (8)

Store the curriculum of the learning content to be provided to the user according to the user's selection, each learning content is composed of a series of units, each of the learning content is a plurality of sequential unit learning data and metadata for each unit learning data The curriculum may include a plurality of cycles, wherein the curriculum corresponds to one or more learning contents for each cycle;
Providing a learning content corresponding to a predetermined round of the curriculum through a display device, and providing the learning content and real-time monitoring of a user's biosignal;
Stopping provision of the learning content whenever the biosignal of the user has a predetermined range and specifying unit learning data at a corresponding time, and displaying a questionnaire on one side of the display device;
Step 140, after receiving an input value for the questionnaire from the user, resuming the provision of the learning content;
Generating a propensity information of the user by using the value of the user biosignal in operation 130 and the received user input value in operation 140; And
And a step 160 of selecting learning content corresponding to the next round of the curriculum by using the generated propensity information.
The method of claim 1,
In step 120, the biosignal includes a value obtained by analyzing the brainwave signal of the user and converting it into one or more indicator values of drowsiness, distraction, and concentration.
The predetermined range in step 130 refers to a case in which the EEG signal of the user indicates one or more of drowsiness, distractions, or concentration decrease.
The method of claim 1,
In step 150, EEG information is generated by integrating the user's biosignal value and the number of occurrences of the input value with respect to the metadata value of the unit learning data. How to provide customized learning content for each user.
The method of claim 3, wherein
Step 160 may include determining unit learning data having metadata corresponding to a next round of the curriculum;
Step 162 of selecting unit learning data having metadata corresponding to the user tendency information among the determined unit learning data; And
And step 163 of generating learning content by sequentially connecting the selected unit learning data.
Store the curriculum of the learning content to be provided to the user according to the user's selection, each learning content is composed of a series of units, each of the learning content is a plurality of sequential unit learning data and metadata for each unit learning data In addition, the curriculum comprises a plurality of rounds, each step 210 corresponding to one or more learning content for each round;
Step 220 of providing learning content corresponding to a predetermined round of the curriculum through a display device, and real-time monitoring of a user's bio-signal at the same time as providing the learning content;
Stopping the provision of the learning content whenever the biosignal of the user has a predetermined range and specifying unit learning data at a corresponding time, and displaying a questionnaire on one side of the display device;
Step 240 of receiving an input value for a questionnaire from a user;
A 250th step of generating propensity information of the user using the value of the user biosignal in operation 230 and the received user input value in operation 240;
A step 260 of changing the specified unit learning data into other unit learning data using the propensity information, and providing the changed unit learning data by displaying the changed unit learning data through a display device; And
A step 270 of resuming the provision of the learning content by displaying the next unit learning data of the interrupted unit learning data on the display device as the changed unit learning data is provided; How to provide customized learning content for each user.
The method of claim 5, wherein
In step 220, the biosignal includes a value obtained by analyzing the brain wave signal of the user and converting the signal into one or more indicator values of "sleepiness,""distraction," and "concentration."
The predetermined range in step 230 refers to a case in which at least one indicator value of "sleepiness", "distraction", or "concentration" indicates that the concentration is decreased, drowsiness, or distraction based on the EEG signal of the user. Method for providing customized learning contents for each user using EEG information.
The method of claim 5, wherein
In step 250, EEG information is generated by generating the user's propensity information on the metadata value by integrating the user's bio signal value and the number of occurrences of the input value with respect to the metadata value of the unit learning data. How to provide customized learning content for each user.
The method of claim 5, wherein
In step 210, the learning content is provided in the form of a lecture video of an instructor, and the unit learning data is obtained by dividing the lecture video into a plurality of sections.
In step 260, the user-specific learning using EEG information is provided by selecting a lecture video of a lecturer different from the instructor of the interrupted unit learning data, and providing a corresponding section of the lecture video of the selected other lecturer. How to provide content.

Images