KR101118276B1 - Ubiquitous-learning middleware device for generating study emotion index related to study concentration from bio-signal emotion index and context information - Google Patents

Abstract

PURPOSE: A ubiquitous-learning middleware device for generating SEI of a learning concentration level is provided to increase learning effect by recommending content based on SEI. CONSTITUTION: A communication module receives BEI(Bio-signal Emotion Index) information from a SEAM(Student Emotion Acknowledgement Module)(210) and a LEAM(Learning Environment Acknowledge Module)(230). A standard information database(290) stores standard index data which indicates correlation between a BEI and an SEI(Study Emotion Index). An emotion/context index analysis processing module(250) generates the SEI of a user by analyzing standard index data.

Description

Ubiquitous-learning middleware device for generating study emotion index related to study concentration from bio-signal emotion index and context information}

The present invention relates to the ubiquitous-learning industry, and particularly, generates a learning emotion index related to the concentration of the user who is currently learning from biometric indicators related to the user's physical condition and contextual information indicating the user's surroundings. The present invention relates to a ubiquitous-learning middleware device for improving a learning effect by maintaining a user's concentration through a secondary environment change such as changing learning contents provided using a learning emotion index (SEI).

Ubiquitous-learning or u-learning means 'Ubiquitous Learning' and refers to an education system that can be learned anytime and anywhere using the Internet. In particular, ubiquitous-learning is a concept created by the evolution of e-learning using the Internet, and refers to learning based on ubiquitous computing that can be connected to a network anytime and anywhere to study freely through the development of information and communication technology. do. In particular, u-learning is gradually becoming a reality due to the operation of u-School pilot schools and digital textbooks provided by the Korea Education & Research Information Service.

The size of the ubiquitous-learning market is growing. In particular, due to the development of high-speed communication technology, a concentration improvement program using brain waves is rapidly spreading. For example, the total amount of domestic e-learning users' spending on e-learning in 2009 was estimated at KRW955.4 billion, an increase of about 17.5% from KRW836.8 billion in 2008. In particular, even considering only those countries such as the United States, Japan, Germany, the United Kingdom, France, and Italy, where ubiquitous-learning is expected to spread rapidly, it can be assumed that they determine the size of foreign markets. Then, the total population of these countries is about 680 million people (2003), and at the same time Korea has about 48 million people, so the population ratio is about 14. In other words, the foreign population involved in the ubiquitous-learning market is 14 times the domestic population. In addition, the global u-learning market continues to grow at an annual average growth rate of 20%.

Thanks to the development of ubiquitous-learning, it is possible to access various contents through various platforms. In particular, even those who have been exposed to a relatively poor educational environment can access good educational content through the spread of the network. This change may be called the realization of educational equality.

However, despite these advantages, there are some disadvantages to ubiquitous-learning.

First of all, while it is easier to access than the conventional method of teaching face-to-face, it is not easy for the ubiquitous-learning consumer to maintain a constant concentration during class. In other words, the school is face-to-face with the teacher because the class is tense, but when studying in front of the computer in his room is difficult to concentrate.

Even using a ubiquitous-learning system can be a huge effort in itself. In other words, while ubiquitous-learning has the advantage that the user can easily access the educational information, it is entirely dependent on the user, such as using the system itself or how concentrated the user is using the content. As a result, the early effects of ubiquitous-learning are not so good. Even Korean middle and high school students are ranked only 24th among 30 OECD countries (Korea Vocational Competency Development Institute, 2008). This suggests that it is far more effective to study in a smart way than just to study hard.

Therefore, there is an urgent need for a technique for improving the learning effect as a result of maintaining users' constant concentration in the ubiquitous-learning system. In this process, the ubiquitous system according to the present invention can induce efficient learning by utilizing emotional information based on individual biosignals in the learning process.

Furthermore, there is a need for a technology that provides learning contents by referring to the current situation information of the user, taking advantage of the U-learning that operates in the ubiquitous environment. For example, suppose that a user can monitor a user's listening attitude while listening to a lecture. Then, if the user is sleepy as a result of analyzing the situation information, it is possible to pause the content playback in progress.

Therefore, a technology for ultimately maximizing the learning effect of the user is urgently required by measuring the learning sensitivity index (SEI) of the user who is learning by using not only biometric information but also context information.

[1] Korean Intellectual Property Office, Application No. 10-2010-0024103, 'Human-mounted sensor set for human-machine interaction'

An object of the present invention is a middleware device for ubiquitous-learning, in particular, the emotion and situation information of a learner using information received from an emotion recognition module and a context recognition module capable of sensing biometric information and situation information such as a brain wave of a user It is to provide a middleware device that can be indexed.

One aspect of the present invention for achieving the above object is, from the bio-signal Emotion Index (BEI) related to the user's physical condition and the contextual information (context information) related to the user's surroundings from the user's concentration of learning The present invention relates to a middleware device for ubiquitous-learning (hereinafter referred to as 'u-learning') for generating a related learning emotion index (SEI). The middleware device for ubiquitous-learning according to the present invention is a communication for receiving a biosensitivity indicator (BEI) and context information, respectively, from a emotion recognition module (SEAM) and a learning environment acknowledgment module (LEAM). A module, a standard information database storing standard index data representing a correlation between a biosensibility index (BEI) and a learning sensitivity index (SEI) obtained from an experiment conducted on a plurality of users, and a received biometric And an emotional / situation index analysis processing module for analyzing the emotional index (BEI) and the situation information with reference to the standard index data, and generating the learning emotional index (SEI) of the user based on the analysis result. In particular, the communication module is configured to output at least one of the biosensitivity index BEI, the learning sensitivity index SEI, and the contextual information to the external learning apparatus. In addition, the ubiquitous-learning middleware device according to the present invention monitors the biosensitivity indicators (BEI) and situation information of users in real time, and measures the sensitivity / situation indicator monitoring module for measuring the amount of change in the biosensitivity indicators (BEI) and situation information. In addition, the emotional / situation indicator analysis processing module further analyzes the bio-sensitivity indicator (BEI) and the situation information with reference to the amount of change received from the emotional / situation indicator monitoring module, based on the analysis result of the user's learning emotional indicators Is adapted to generate (SEI). Furthermore, the ubiquitous-learning middleware device is generated through a communication module as a learning adapter for identifying content currently provided to the user by an external learning device and detecting the learning state and events of the user in real time. By sending the learning sentiment indicator SEI, it is adapted to cause the learning adapter to modify or change the content being learned based on the received learning sentiment indicator SEI. In particular, the emotional / situation indicator analysis processing module is adapted to generate at least one of concentration, distraction, and sleepiness as the learning emotional indicator (SEI). In addition, the emotion recognition module (SEAM) is adapted to calculate a user's biometric index (BEI) using a biosignal including at least one of EEG, safety (EOG), heart rate variability (HRV), The biosensitivity indicator (BEI) includes at least one of concentration, relaxation, load, attention, left brain activity, right brain activity, and left and right brain imbalance. Alternatively, the situation recognition module (LEAM) is adapted to measure at least one of temperature information, humidity information, user attitude information, and GPS location signal using a Ubiquitous Sensor Network (USN), and provide the measured information as situation information. The external learning apparatus according to the present invention may display a bio-sensitivity index (BEI), a learning-sensitivity index (SEI), and context information received along with the learning content provided to the user, a bio-sensitivity index (BEI), and a learning emotion index (SEI), and determining and displaying the concentration of the user based on the situation information, and providing an alert message to the user or changing the learning content provided when the determined concentration is less than or equal to a predetermined threshold.

According to the present invention, the learning effect enhancing apparatus for ubiquitous-learning may increase the learning effect by recommending content suitable for the user based on the learning sensitivity index (SEI) received from the middleware device according to the present invention.

In addition, since the middleware device according to the present invention includes a communication unit which is commonly operated with various devices, it is necessary to determine what type of learning effect enhancement device for ubiquitous-learning or emotion recognition module and situation recognition module are used by the user. It can be applied to the learning effect improvement system for ubiquitous-learning that operates on various platforms regardless.

Therefore, the development cost of the system for improving the learning effect for ubiquitous-learning using the middleware device according to the present invention can be reduced, and the middleware device according to the present invention can be applied to various application fields.

1 is a diagram conceptually illustrating a configuration and operation of a learning support system in which a middleware device according to the present invention operates.
2 is a block diagram conceptually illustrating a first embodiment of a learning support apparatus including a middleware apparatus according to the present invention.
3 is a block diagram conceptually illustrating a second embodiment of a learning support apparatus including the middleware apparatus according to the present invention.
4 is a view for explaining the operation of the learning support device including the middleware device according to the present invention.
FIG. 5 is a table illustrating bio sentiment indicators (BEIs), learning emotion indicators (SEIs), and contextual information used in the learning support apparatus according to the present invention.
6 is a diagram illustrating an experiment result for obtaining standard indicator data.
FIG. 7 is a screen shot illustrating an execution screen for measuring a biosensibility index BEI and a learning sensitivity index SEI in the learning support system according to the present invention.

In order to fully understand the present invention, the operational advantages of the present invention, and the objects achieved by the practice of the present invention, reference should be made to the accompanying drawings which illustrate preferred embodiments of the present invention and the contents described in the accompanying drawings.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. In addition, in order to clearly describe the present invention, parts irrelevant to the description are omitted, and the same reference numerals in the drawings indicate the same members.

Throughout the specification, when a part is said to "include" a certain component, it means that it may further include other components, without excluding the other components unless otherwise stated. In addition, the terms "... unit", "... unit", "module", "block", etc. described in the specification mean a unit for processing at least one function or operation, which means hardware, software, or hardware. And software.

1 is a diagram conceptually illustrating a configuration and operation of a learning support system in which a middleware device according to the present invention operates.

Referring to Figure 1 as follows. First, the user logs in to the learning support system via the web (step 1). Then, the learning support system transmits the learner information of the logged-in user to the middleware device (step 2).

The middleware device recognizes the learner device used by the logged-in user (step 3), and the learner device used by the user measures and transmits the biosensitivity indicator (BEI) and contextual information of the learner to the middleware device while the user learns ( Step 4). The learner device may include a sensor module for performing this operation. In the present invention, the bio-signal Emotion Index (BEI) indicates information related to the current physical state of the user who is learning, which will be described later in detail in the relevant part of the specification.

Also, in the present invention, context information refers to characteristics of a situation, such as a person, a place, an object, an object, and a time, which affect the interaction between a user and another user, system, or application in relation to ubiquitous computing. Points to regulatory information. More specifically, network connection status, computing situation such as communication bandwidth, user's profile, location, user situation including people around, lighting, noise level, traffic condition, temperature, etc. (Physical situation, time situation such as time, week, month, season, etc. are all included in the situation information. Such contextual information may be identified and collected through various sensing devices and applications and used to provide various application services, or may be used for inference to obtain a third conclusion by combining with other contextual information. In particular, the contextual information herein may include personal static contextual information, such as a user's health status, identity information, learning level, grades, and the like, and dynamic contextual information about how well a user currently follows content provided. That is, the static contextual information relates to the personality and characteristics of the individual, and the dynamic contextual information relates to information obtained in real time from the user's state.

In addition, in the present specification, a study emotion index (SEI) indicates an index directly related to learning, such as a user's current concentration level. The main operation of the middleware device according to the present invention is to measure the learning sensitivity indicator (SEI) according to the learning state of the user and to induce the user to actively change the service provided to the user based on this. Specific examples of the learning sensitivity index (SEI) will be described later in detail in the corresponding part of the specification.

Referring back to FIG. 1, an emotional headset is used as a Student Emotion Acknowledgement Module (SEAM), and an environment sensor is used as a Learning Environment Acknowledge Module (LEAM).

Then, the middleware device analyzes and processes the biosensitivity indicator (BEI) and the situation information received from the sensor module (step 5). In this process, standard index data received from the database may be used (step 6). In the present specification, 'standard indicator data' is data representing an average of relations between biometric information and concentration of various users. Therefore, the use of the standard indicator data has the advantage of easily and accurately measuring the user-specific learning emotion indicator (SEI) from the biosensitivity indicator (BEI). In FIG. 1, the standard indicator data is shown to include concentration, stability, immersion, pulse wave, stress, and situation information, but for convenience of description, it should be noted that the present invention is not limited thereto.

When the middleware device calculates the learning emotion index (SEI) of the user individual using the standard indicator data (step 7), the middleware device transmits the calculated learning emotion index (SEI) to the learning support agent (step 8). Then, the learning support agent may perform an operation such as changing the content provided to the user with reference to the received learning sensitivity index SEI.

As described above, the learning support system according to the present invention may prevent the concentration of the user from being reduced by referring to the biosensitivity index BEI of the current user who is learning, as well as the learning sensitivity index SEI.

In addition, according to the present invention, regardless of which learner device a user uses, a common emotional service may be used to provide a learning emotion index (SEI) providing service.

2 is a block diagram conceptually illustrating a first embodiment of an external learning apparatus including a middleware apparatus according to the present invention.

The learning support apparatus 200 illustrated in FIG. 2 includes an emotion recognition module 210, a situation recognition module 230, a middleware module 250, a learning adapter 270, and a standard indicator database 290.

First, when a user starts learning using an external learning device, the learning adapter 270 is executed in the external learning device. The learning adapter 270 communicates with the middleware module 250 to display the learning sensitivity indicator SEI on the external learning device. That is, the learning adapter 270 through the adapter can determine whether the learner is properly wearing the sensor devices, the state to start the emotional learning. The signal transmitted through the learning adapter 270 is transferred to the emotion / situation index analysis processing module of the middleware module 250. In the present invention, the external learning apparatus may refer to a content player that plays learning content.

When learning begins, the middleware module 250 receives various bio signals and situation information from the emotion recognition module 210 and the situation recognition module 230. Then, the middleware module 250 analyzes the received signals to generate a learning emotion indicator (SEI) and a situation indicator. In addition, the middleware module 250 may monitor in real time whether a change occurs in the biometrics indicator (BEI) and contextual information of the user during learning.

The standard indicator data stored in the standard indicator database 290 may be used by the middleware module 250 to generate the learning emotional indicators (SEI). Standard indicator data may include standard learning emotional indicator data and standard learning situation indicator data.

The middleware module 250 included in the learning support apparatus 200 illustrated in FIG. 2 is installed in a user terminal based on a user, and the standard learning indicators mapped to the extracted learner's emotion / situation information are ubiquitous through a communication module. It is delivered to the running system for use.

3 is a block diagram conceptually illustrating a second embodiment of a learning support apparatus including the middleware apparatus according to the present invention.

Referring to FIG. 3, the learning support apparatus 300 may include an emotion recognition module 310, a sensor set processor 320, an environment information processor 325, a situation recognition module 330, a middleware module 350, and a learning adapter ( 370 and standard indicator database 390.

The signals received from the emotion recognition module 310 and the situation recognition module 330 pass through the sensor set processor 320 and the environmental information processor 325, respectively, before being transmitted to the middleware module 350. Then, the sensor set processor 320 identifies the biometric signal for emotion recognition among the signals transmitted from the emotion recognition module 310. In addition, the environment information processor 325 processes the situation information indicating the current situation of the user from the signals received from the situation recognition module 330. The processed biosensitivity indicator (BEI) and contextual information are transmitted to the middleware module 350.

In FIG. 3, the emotion recognition module 310 may generate 21 EEG channels from two EEG signals. In addition, the sensor set processor 320 may generate seven biometric indicators (BEI) by using 21 EEG channels and transmit them to the middleware module 350. Then, the middleware module 350 may generate the learning sensitivity index SEI by using the received biosensitivity index BEI and contextual information. The learning sensitivity index (SEI) may be converted to a 100-point scale, for example, when the 'sleepiness' index exceeds 60 points, it may be determined to be sleepy. In order to determine the learning emotional index (SEI), the biological emotional index (BEI) and contextual information are considered together. For example, if it is determined that the user is sitting by analyzing posture information, the sleepiness index may be determined to be sleepy when the score exceeds 90. However, if it is determined that the user is lying down as a result of analyzing the posture information, even if the 'sleepiness' index exceeds 10 points, it may be determined to be sleepy. In FIG. 3, 'concentration', 'distraction', and 'sleepiness' are used as the learning emotion index (SEI), but the present invention is not limited thereto.

The middleware module 350 may include a learning adapter communication module 351, an emotion / situation device communication module 352, an agent communication module 353, an emotion / situation indicator analysis processing module 355, a learning indicator generation module 357, And emotion / situation change detection module 359. The learning adapter communication module 351 may communicate with the communication module of the learning adapter 370 in real time. In addition, the emotion / situation device communication module 352 may communicate with the emotion recognition apparatuses 310 and 330 in a wired or wireless manner. In this case, the wireless communication method may be Zigbee or Bluetooth. The agent communication module 353 is in charge of communicating with the external learning support agent. In this case, the agent communication module 353 may include modules of a client / server type, respectively.

The emotion / situation index analysis processing module 355 included in the middleware module 350 analyzes and processes the bio sentiment indicator BEI transmitted from the emotion recognition module 310 to generate the learning emotion index SEI. In addition, the emotion / situation indicator analysis processing module 355 analyzes the situation information received from the situation recognition module 330 to generate a learning situation indicator. Then, at this time, whether the fluctuations in the biometrics indicator (BEI) and the situation information is monitored by the emotion / situation change detection module 359. The monitoring result may be transmitted to the emotion / situation index analysis processing module 355 or the external learning device.

In FIG. 3, the standard indicator database 390 stores situation and emotion standard information. More specifically, the standard indicator database 390 can include a database manager 395. The database manager 395 standardizes stored emotion / situation indicators and classifies learners. In addition, the database manager 395 may perform statistical verification of the extracted emotion / situation index and significant data extraction operation according to the analysis of the emotion / situation index. Through this, the database manager 395 may collect the learner's emotion / situation data.

The learning adapter 370 recognizes the learner information and the content information, detects a change in the learning state of the user, and transmits the changed state to the external learning device. In addition, the learning adapter 370 displays the emotion change state of the learner analyzed by the emotion recognition device in real time.

4 is a view for explaining the operation of the learning support device including the middleware device according to the present invention.

Referring to FIG. 4, the learning support apparatus 400 may include an emotion recognition module 410, a sensor set processor 420, a context information processor 425, a context recognition module 430, a middleware module 450, and a learning adapter ( 470 and standard indicator database 490. The learning sensitivity index (SEI) obtained by the middleware module 450 is transmitted to the agent connector module 460 via the I / O module.

The signals received from the emotion recognition module 410 and the situation recognition module 430 are transmitted to the sensor set processor 420 and the situation information processor 425 through the I / O module, respectively. The sensor set processor 420 extracts the learning emotion index SEI, and the context information processor 425 extracts the context information. Then, the extracted information is transferred to the middleware module 450. In particular, the learning adapter 470 monitors the learning progress after recognizing the learner information. If necessary, the learning adapter 470 may display the biosensitivity indicator (BEI) and the learning sensitivity indicator (SEI) in real time. The configuration and operation of the middleware module 450 included in the learning support apparatus 400 illustrated in FIG. 4 is similar to that of the middleware module 350 illustrated in FIG. 3. Therefore, duplicate description is omitted for simplicity of the specification.

The learning support apparatus 400 illustrated in FIG. 4 is different from FIG. 3 in that the emotion recognition module 410 and the context recognition module 430 are not included as components.

Then, the sensor set processor 420 identifies the biosignal for emotion recognition from the signal transmitted from the emotion recognition module 410 and transmits the biosignal to the middleware module 450. In addition, the contextual information processor 425 obtains contextual information representing the current situation of the user from the signals received from the contextual recognition module 430, and transfers the result to the middleware module 450.

The middleware module 450 includes an emotion / situation device communication module, a learning emotion / life indicator generation module, an emotion / situation indicator analysis processing module, and an emotion / situation change detection module. The emotional / situation device communication module may communicate with the communication module of the learning adapter 470 in real time. In addition, the emotion / situation device communication module may communicate with the emotion recognition devices 410 and 430 in a wired or wireless manner. In this case, the wireless communication method may be Zigbee or Bluetooth.

In FIG. 4, the standard indicator database 490 stores situation and emotional standard information. More specifically, the standard indicator database 490 can include a database administrator (not shown). In addition, the standard learning index may be stored in the standard indicator database 490. As described above, this standard learning indicator may be used to convert the biosensitivity indicator (BEI) into the learning sensitivity indicator (SEI).

The learning adapter 470 recognizes the learner information and the content information, detects a change in the learning state of the user, and transmits the changed state to the external learning device. In addition, the learning adapter 470 displays the emotion change state of the learner analyzed from the emotion recognition device in real time.

The middleware module 450 reads the raw signal data transmitted from the emotion / situation device, generates a learning standard indicator through mapping with the reference indicator collected / analyzed by the experiment, and delivers the learning standard indicator to the learning server.

In addition, the learning adapter module is applied to the web in the form of ActiveX, thereby transmitting the learning state of the learner to the middleware. Therefore, necessary information can be immediately displayed to the user during content playback. In addition, the middleware device is installed on the user's computer, but the standard learning indicators are delivered to the external learning system through the agent server module.

FIG. 5 is a table illustrating bio sentiment indicators (BEIs), learning emotion indicators (SEIs), and contextual information used in the learning support apparatus according to the present invention.

5A is a table illustrating biosignals that may be extracted from biometric information such as brain waves.

Some methods for analyzing EEG and vital signs are as follows.

1) Cross-Line Mapping: Cross-Correlation between each channel is represented by a line on the head surface.

2) 3-D Brain Mapping Analysis: The waveform or result graph of each channel can be expressed at each electrode location.

3) Time-Frequency Analysis: Analyze changes in power spectrum over time of biometric information.

4) Spectrum Analysis: Power Spectrum that shows power values by theta, alpha, beta, gamma.

5) Statistics, Correlation Analysis, and Filtering

6) Custom Analysis: Researchers can quickly and easily identify the characteristics of the EEG to be analyzed, saving a lot of time and energy. In other words, by combining the methods in the order desired by the developer, a new method can be created.

7) Multi-channel time series data analysis, including wavelet analysis, principal component analysis, modeling analysis, and chaos analysis.

In addition, refer to the cited patent document [1] for a method for analyzing an EEG and a biosignal.

5B is a table illustrating biosensitivity indicators (BEIs) that may be extracted from biometric information such as brain waves. The biosensitivity index (BEI) as shown in FIG. 5B is extracted by using a raw biosignal and a biosignal analysis index. The content of each indicator, the information used in the analysis, and the respective data attributes are shown in Table 5b. The biosensitivity indicator (BEI) illustrated in FIG. 5B has high reliability and importance as data for monitoring the learner's condition.

5C is a table illustrating context information extracted by the context awareness module. In FIG. 5C, only the temperature and humidity information is included as the learning situation indicator. In addition, posture information and the current location of the user may be provided as the situation information. For example, the posture information may be measured using a situation recognition module worn on a user's forearm, waist, thigh, or the like. Then, it is determined whether the data measured by the situation recognition module worn by the learner is taking the correct posture to improve the learner's concentration. For example, the posture of the user may be determined in five steps as follows.

1) Too straight posture for learners to learn

2) It is not too hard for a learner to learn, but it is a straight posture.

3) Good posture for learners

4) The learner is comfortable to learn but has an extended attitude.

5) postures that are too flat (distracted) for learners to learn

Finally, FIG. 5D is a table illustrating a learning emotion index (SEI) to be generated in the middleware device according to the present invention.

For each item, the definitions and judgment criteria are summarized.

In the present specification, the difference between the biosensitivity indicator (BEI) and the learning emotion indicator (SEI) is that the biosensitivity indicator (BEI) is information obtained directly from the biometric information, whereas the learning emotion indicator (SEI) is the biosensitivity indicator (BEI). And information obtained from the context information, which may be directly related to the learning effect of the user. Therefore, by using the learning sensitivity indicator (SEI) rather than the biosensitivity indicator (BEI), it is possible to more accurately measure the concentration of the current user, thereby maximizing the learning effect.

In the present invention, when the learning emotion indicator (SEI) is delivered to the external learning device, the learning adapter of the external learning device may take into consideration the content provided in consideration of the received biosensitivity indicator (BEI), the learning emotion indicator (SEI), and contextual information. Change to improve the user's concentration. In this case, a method of changing the content provided to the user is as follows.

First, the emotional / situation index analysis processing module determines the user's learning emotional index (SEI) in consideration of the bio emotional index (BEI) and context information. In addition, not only the determined learning emotion index SEI, but also the biosensitivity indicator BEI and the contextual information are transmitted to the external learning apparatus. The external learning device then provides new content as needed. In this case, the external learning apparatus may directly generate learning content suitable for the corresponding user by using a plurality of content units stored in an external content database (not shown). In this case, a content descriptor that is created by an indexing process and attached to the content unit when the content unit is generated may be used. The content descriptor may include one or more tags with a hierarchical structure. For example, assume that a content unit for a motion course of a camera is generated. Then, the name of the camera model and the associated lecture is given as a tag to the content unit. For example, the tag 'sx20is' is described. In addition, the tag 'camera function description' may include tags such as 'shooting mode description' and 'basic operation description' as a lower tag. As such, each tag constituting the content descriptor may have a hierarchical relationship with each other, and may have a parallel relationship with each other. In the present specification, a tag refers to an object having a parent-child concept and selectable by a user. That is, a tag is an object of interest of a user, and a tag belonging to a higher level corresponds to a concept of collectively managing a tag belonging to a lower level. On the other hand, a tag belonging to a lower level corresponds to a subset of tags belonging to a higher level. Tags belonging to the same level have a parallel relationship with each other. In other words, the tags belonging to the lower level are gradually subdivided. For example, under the tag 'human', there may be 'man' and 'woman' tags, and the tag 'man' may have subtags broken down by age. That is, a tag belonging to a higher level may be understood as a category that aggregates lower concepts related to each other. In the present specification, a 'high tag' means a tag belonging to a higher level, and a 'low tag' means a tag belonging to a lower level.

As such, the external learning apparatus directly modifies the content provided to the user, thereby providing a service suitable for the user's interest and level to maximize the learning effect.

Using a hierarchical structure of tags has the advantage of describing in detail the field in which the content unit is related. For example, if a content unit contains a tag of "difficulty 1," it may be revealed by resolving another tag included in the content descriptor of that content unit to which content unit corresponds to "difficulty 1" in that field. Can be. For example, if the content descriptor further includes tags called 'differentiation' and 'practice problem', then by interpreting these tags, the content unit is assigned to 'education / learning-higher-math-differential-practice problem-difficulty 1' You can see that it belongs to the field of. Here, the 'a-b' display indicates that the 'a' tag is a parent tag of the 'b' tag. If a user wishes to watch content related to the field 'Education / Learning-Higher-Math-Differential-Practice Problem-Difficulty 1', the tags 'Difficulty 1', 'Practice Problem', and 'Derivative' Content units having a read from the content base (not shown). Then, the content unit arrangement unit arranges the read units according to a predetermined generation rule to generate user-customized content. The content unit reading unit does not necessarily read only the content unit having a content descriptor including only the same tag as the tag selected by the user. That is, the content unit reader may also read a content unit having a tag that is related to a tag selected by the user.

In addition, the content arrangement rules include user specific rules that apply only to specific users. For example, in the field of exercise, `` high intensity exercise is avoided in patients with hypertension '', `` cycle exercise is preferable to running in case of joint problems, '' `` oxygen concentration in the body is particularly important if you have chronic respiratory disease '' Sports medical rules, and the like. In the field of learning, there are rules that are specific to each user, such as 'A is more wrong in polynomials than a set' and 'B is poorly understood in the field of probability statistics'. Using this information, after analyzing the static situation information of a user, if he is a hypertensive patient, high-intensity exercise is not preferable. Can be generated. As such, user specific rules may be applied with reference to the dynamic context information of the current user. For example, if the current user's blood pressure is excessively high (dynamic situation information), user-specific content is created for such a user so that he or she can stop the exercise immediately and organize it through a breathing exercise. In addition, if the user's breathing condition is monitored and the breathing is abnormal (dynamic situation information), the breathing content may be inserted.

6 is a diagram illustrating an experiment result for obtaining standard indicator data.

The purpose of these experiments is to reveal the relationship between the learner's learning status and brain waves. Classify the learning situation that learner learns into several and measure the brain wave of individual learner according to learning situation to grasp the difference of brain wave by individual learner and learning situation. In particular, the purpose of the experiment is to clarify the correlation between EEG by individual learner and learning situation, focusing on the concentration determined to be closely related to learning among the various indicators that can be identified using EEG.

Referring to FIG. 6, after the game is judged to require concentration to verify the validity of the concentration among the EEG-related indicators, the learner records his concentration in the game. Then, the degree of concentration extracted from EEG and the degree of concentration determined by the learner are compared. As can be seen in FIG. 6, the concentration index obtained as the learning emotional index (SEI) has a pattern similar to the actual concentration, and as a result, the learning emotional index (SEI) can be used as a measure for determining the concentration of the user. It can be seen that.

Of course, the results of repeated experiments may show a slight difference for each learner in concentration, workload, left brain activity, right brain activity. While there are learners who show low concentrations in every experiment, students with concentrations above a certain level appear in each experiment. Therefore, in order to increase the accuracy of the experimental results, it is desirable to grasp the basic EEG information of the learner using the learning ability test. In particular, since there may be a difference depending on the learner's current state as a result of learning ability test results for each learner, it is preferable to set the default EEG value by executing the learning ability test for each experiment.

FIG. 7 is a screen shot illustrating an execution screen for measuring a biosensibility index BEI and a learning sensitivity index SEI in the learning support system according to the present invention.

Referring to FIG. 7, the bio-signal analysis index (BAI) and the learning emotion index (SEI) are displayed in the left and right sections 710 and 720 of the 'emotional learning index', respectively. In FIG. 7, the bioassay index BAI indicates biosignals extracted from an EEG signal, as illustrated in FIG. 5A.

The environmental indicator and attitude information of the situation information is displayed in the 'status signal' section 750, and the biosensitivity indicator (BEI) is displayed in the 'status bar' section 730. The real-time change of the bioanalytical index is displayed in section 740, and temperature, humidity, gyro data, and the like among the contextual information is displayed in section 760. As described above, the user may easily grasp various biometric information and situation information, as well as the biosensitivity index BEI and the learning sensitivity index SEI through the execution screen illustrated in FIG. 7.

As such, the learning support system according to the present invention can be utilized for brain training to promote healthy brain activity. It can also be used for EEG analysis of EEG-related research institutes.

Although the present invention has been described with reference to the embodiments shown in the drawings, this is merely exemplary, and it will be understood by those skilled in the art that various modifications and equivalent other embodiments are possible.

In addition, the method according to the present invention can be embodied as computer readable codes on a computer readable recording medium. The computer-readable recording medium may include all kinds of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROMs, RAMs, CD-ROMs, magnetic tapes, floppy disks, optical data storage devices, and the like, and may also be implemented in the form of carrier waves (for example, transmission over the Internet). Include. The computer readable recording medium can also store computer readable code that can be executed in a distributed fashion by a networked distributed computer system.

Therefore, the true technical protection scope of the present invention will be defined by the technical spirit of the appended claims.

The present invention can be applied to a learning support system for ubiquitous-learning.

Claims (7)

Generating a Study Emotion Index (SEI) related to the user's learning concentration from the Bio-signal Emotion Index (BEI) related to the user's physical condition and context information related to the user's surroundings. In the middleware device for ubiquitous-learning (hereinafter referred to as 'u-learning'),
A communication module for receiving the bio-sensitivity indicator (BEI) and the contextual information, respectively, from a emotion recognition module (SEAM) and a learning environment acknowledgment module (LEAM);
A standard information database for storing standard index data indicating a correlation between the biometric emotional index (BEI) and the learning emotional index (SEI) obtained from experiments performed on a plurality of users;
An emotion / situation index analysis processing module configured to analyze the received biosensibility index (BEI) and the situation information with reference to the standard index data and to generate the learning emotional index (SEI) of the user based on an analysis result; And
A learning adapter for identifying content currently provided to a user by an external learning device and detecting a learning state and an event of the user in real time,
The communication module outputs at least one of the biometrics indicator (BEI), the learning sensitivity indicator (SEI), and the contextual information to the external learning device,
The learning adapter,
The middleware device for ubiquitous-learning, wherein the learning sensitivity indicator (SEI) is received through the communication module and the content being learned is modified or changed based on the received learning sensitivity indicator (SEI). According to claim 1, The ubiquitous middleware device for learning,
And a emotion / situation indicator monitoring module for monitoring the biometrics indicator (BEI) and context information of the users in real time and measuring a change amount of the biometrics indicator (BEI) and the context information, and analyzing the emotion / situation index. The processing module is
The bio-sensitivity indicator (BEI) and context information are further analyzed with reference to the amount of change received from the emotion / situation indicator monitoring module, and the learning sensitivity index (SEI) of the user is generated based on an analysis result. Middleware device for ubiquitous-learning. delete According to claim 1, wherein the emotional / situation indicator analysis processing module,
A middleware device for ubiquitous-learning, which generates at least one of concentration, distraction, and sleepiness as the learning sensitivity index (SEI). The method of claim 1, wherein the emotion recognition module (SEAM),
Computing the biosensitivity indicator (BEI) of the user using a biosignal including at least one of EEG, safety (EOG), heart rate variability (HRV),
The biosensitivity indicator (BEI) is a ubiquitous-learning middleware device comprising at least one of concentration, relaxation, loading, attention, left brain activity, right brain activity, and left and right brain imbalance. The method of claim 1, wherein the situation recognition module (LEAM),
A middleware device for ubiquitous-learning, comprising measuring at least one of temperature information, humidity information, user posture information, and GPS location signal using a USN (Ubiquitous Sensor Network), and providing the measured information as the situation information. The apparatus of claim 1, wherein the external learning device comprises:
Displaying the biosensitivity indicator (BEI), the learning emotion indicator (SEI), and contextual information received together with the learning content provided to the user,
Determining and displaying the concentration of the user based on the biosensibility index BEI, the learning sensitivity index SEI, and contextual information; and
The middleware device for ubiquitous-learning, if the determined concentration is less than a predetermined threshold, providing a warning message to the user or changing the provided learning content.

Images