KR102191671B1 - personalized learning method based on social learning and e-portfolio, and system - Google Patents

Abstract

The present invention relates to a personalized learning method based on an e-portfolio and social learning and a system thereof. According to an embodiment of the present invention, the personalized learning method based on an e-portfolio and social learning uses a server for education which builds a network with the web, an external server, and a terminal, and comprises: a first step in which a user uses the server for education to set a learning environment; a second step in which the learning environment of the user is shared based on the network and the social learning progresses; a third step in which the learning environment of the user is changed in the server for education in accordance with the learning progress; and a fourth step in which the server for education accumulates the changed learning environment of the user to generate the e-portfolio. The learning environment includes: a first environment to designate a learning style of the user; a second environment in which the user designates a goal condition; a third environment to show education content learned by the user; and a fourth environment to display learning content created by the user in connection with the education content.

Description

Personalized learning method based on social learning and e-portfolio, and system}

The present invention relates to a customized learning method and system based on social learning and ePortfolio.

Terminals such as personal computers, notebook computers, and mobile phones may be configured to perform various functions. Examples of such various functions include a data and voice communication function, a function of taking a picture or video through a camera, a function of recording a voice, a function of playing a music file through a speaker system, and a function of displaying an image or video. Some terminals include an additional function for playing a game, while others are implemented as multimedia devices. Furthermore, recent terminals can watch video or television programs by receiving broadcast or multicast signals.

In general, terminals can be divided into mobile/portable terminals and stationary terminals depending on whether or not they can be moved. Again, the mobile terminal can be divided into a handheld terminal and a vehicle mount terminal according to whether the user can directly carry it.

As the functions are diversified, such a terminal is in the form of a multimedia player with complex functions such as, for example, taking photos or videos, playing music or video files, and receiving games and broadcasts. It is being implemented.

In order to support and increase the function of the terminal, it may be considered to improve the structural part and/or the software part of the terminal.

Education for users is frequently performed based on contents provided through such terminals.

However, in the currently applied method and system, there is a problem that only educational content is provided to users in one direction, and education reflecting the user's feedback according to a learning event cannot be performed.

For example, in the conventional method, when you logged in and logged out/timed out. How are you using the test and evaluation questions, what are the test scores that are automatically scored, how much and how you are using today's learning, what video materials and how you are using them, what questions or tags are you using during training? There is a problem in that it is difficult to receive user-customized information about which content is being used in order, which data are being viewed, which applications are being used, accumulated status, character change, and search keyword.

This personalized learning is a technology that increases the learning effect conveniently and efficiently by intelligently providing contents and services according to the learner's ability and characteristics.

Conventionally, customized learning technologies that have been commercialized depend on linkage between learning contents or simply count the number of wrong problems to diagnose weak concepts, and thus, there is a problem in that the learning ability diagnosis of learners is not elaborate.

In other words, even in the case of providing personalized customized learning, there has been a limitation in that the efficiency and reliability of the customized learning system cannot be secured because it is based on an incorrect learning ability diagnosis.

Therefore, there is a growing need for learning methods and systems that can solve this problem.

(1) Korean Intellectual Property Office Application No. 10-2018-0002730 (2) Korean Intellectual Property Office Application No. 10-2016-0161796

The present invention proposes a social learning and e-portfolio-based customized learning method and system in order to solve the above conventional problems.

Specifically, the present invention is that when a user sets a learning environment using the education server, the user's learning environment is shared based on the network, so that the social learning progresses, and according to the learning progress, the user on the education server When the learning environment of is changed, it is intended to propose to a user a social learning and ePortfolio-based customized learning method and system in which the education server accumulates the changed learning environment of the user to generate the ePortfolio.

However, the technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems that are not mentioned are clearly to those of ordinary skill in the technical field to which the present invention belongs from the following description. It will be understandable.

In a customized learning method based on social learning and e-portfolio using a web, an external server, and an educational server having a terminal and a network related to an example of the present invention for realizing the above-described problems, the user learns using the educational server A first step of setting the environment; A second step of performing the social learning by sharing the learning environment of the user based on the network; A third step of changing the learning environment of the user on the education server according to progress of learning; And a fourth step of generating the ePortfolio by the education server accumulating the learning environment of the changed user, wherein the learning environment includes a first environment in which the learning style of the user is designated, and the user is a target It may include a second environment for specifying a condition, a third environment for indicating the educational content learned by the user, and a fourth environment for displaying the learning content created by the user in relation to the educational content.

In addition, the learning style in the first environment may be designated based on a profile and competency of the user's education content derived based on a pre-designated pre-test.

In addition, in the second environment, the target condition may be designated based on a learning time and an arrival target of the user in preparation for a test.

In addition, the learned educational content in the third environment includes a problem solved by the user, a problem previously specified by the user, and a lecture taken by the user, and the learning content in the fourth environment, The user may include at least one of a problem and lecture content produced by the user as a feedback from the third environment.

In addition, in the second step, at least one of the problem and the lecture content that the user directly produced is shared through the fourth environment, and between the second step and the third step, the shared user directly The method may further include step 2-1 in which information on views and ratings for at least one of the produced problem and lecture content is provided to the user.

In addition, the number of users may be plural, and the ePortfolio may include a learning level of a first user among the learning levels of the plurality of users and an analysis result of the changed learning environment of the first user.

Further, after the fourth step, a fifth step of determining, by the education server, an interest level of the first user based on the ePortfolio; And the education server, based on the learning level of the first user, an analysis result of the changed learning environment of the first user, and the determined interest level, to determine information related to the future job of the first user, and the first user A sixth step of providing the future job information to the user may further include.

On the other hand, in the education server having a network with a web, an external server, and a terminal according to another example of the present invention for realizing the above-described problem, when a user sets a learning environment using the education server, the network When the learning environment of the user is shared on the basis of the social learning and the learning environment of the user is changed on the education server according to the progress of the learning, the education server accumulates the changed learning environment of the user and the An ePortfolio is created, and the learning environment includes: a first environment for designating the learning style of the user, a second environment for designating a target condition by the user, a third environment indicating the contents of education learned by the user, and the education In relation to the content, it may include a fourth environment for displaying the learning content created by the user.

At least one embodiment of the present invention configured as described above may provide an artificial intelligence-based customized learning method and system.

Specifically, according to the present invention, customized learning services for each subject using big data and AI technology diagnose weaknesses of individual learners and give specific prescriptions, predict learning outcomes, establish an efficient learning plan, and generate interest. A new standard for subject-specific learning services can be proposed while adding elements to the subject.

That is, in the present invention, the concept of each subject can be subdivided into unit knowledge beyond the curriculum. For example, after systematizing the concept of mathematics into thousands of unit knowledge that can no longer be decomposed independently from the curriculum, the curriculum Service flexibility can be strengthened by linking the topics of the unit into a bundle of related unit knowledge.

In addition, according to the present invention, it is possible to change the standard information for vulnerability diagnosis to unit knowledge, and a detailed prescription can be made while analyzing the vulnerability with more detailed unit knowledge from the method of diagnosing the vulnerability based on the existing unit evaluation score. I can.

In addition, according to the present invention, the unit for designing the learning path can also be expressed as a knowledge map. Although it is possible to learn in the order of units and topics of the curriculum, unit knowledge for competency-based education (CBE) By designing a learning path centering on, it is possible to adjust different learning plans and quantities for each individual.

Next, according to the present invention, through educational services using big data and AI, components of an adaptive learning platform can be presented step by step.

Specifically, according to the present invention, the problem solving process can be analyzed in detail.

In other words, it is possible to provide information in the form of a dashboard by collecting the entire process as big data such as solving time, correct/incorrect answer, and replay of an explanation lecture whenever a learner solves a question on the test paper.

Currently, most of the system logs and metadata of a database are combined and analyzed using a data mining method, but in the present invention, it is possible to provide the cause of the incorrect answer, that is, the result of analyzing the achievement level for each subject including analysis of weak knowledge and mathematics. .

In addition, according to the present invention, it is possible to predict learning outcomes and the possibility of submitting correct/incorrect answers through the inference function of AI.

Specifically, the possibility of submitting correct/incorrect answers and learning outcomes can be predicted using the results of vulnerability analysis and accumulated learning data.

In addition, AI-optimized learning paths and content (questions) can be recommended.

According to the present invention, for individual vulnerability knowledge, it is possible to provide an interactive recommendation service that overcomes weaknesses in a short period of time with successive similar problems and twin problems.

In addition, according to the present invention, it is possible to provide a PoD (Print-on-Demand) service through a recommendation and questionnaire function capable of configuring a personal problem book.

In addition, according to the present invention, it is possible to upgrade to an interface that recognizes equations and characters using OCR (Optical Character Recognition) technology, an interface that expresses equations through handwriting recognition, and a service that simulates a graph.

Specifically, in the present invention, it is possible to search (OCR) a problem by taking a picture.

In other words, it is possible to provide a service that searches for the correct answer and problem solving process in the database accumulated with AI and provides it in real time by taking a picture of the printed or handwritten questions in the problem book.

Currently, the focus is on recognition and search competitiveness, and contextual service elements, such as prediction and recommendation, are insufficient. In the present invention, a formula expression through handwriting recognition can also be provided.

In other words, if a complex formula is written on the touch interface, the AI can recognize it, express it as a regular formula, and present the correct answer through real-time calculation.

In addition, the present invention provides an intuitive graph simulation.

Specifically, it is effective in overcoming weaknesses as you can immediately graph changes in graphs while controlling coefficients and variables and expressing complex functions directly.

In addition, the present invention establishes an item response model based on the data collection system, applies machine learning to provide personalized learning paths and contents/resources according to the achievement level (capacity), and is specific to learners, teachers, and parents. And provide personalized feedback (prescription), and provide users with learning analysis methods and systems that can detect and resolve problems early by diagnosing learners' learning outcomes.

In addition, the present invention accurately diagnoses whether or not the learner understands each concept from the result of the group test and the learner's solution for individual problems, and provides feedback, so that it is possible to identify the vulnerable concept and automatically select and recommend learning contents for the vulnerable concept. There is an effect of increasing the efficiency and reliability of customized learning.

In addition, the present invention enables the learner to participate in the online lecture with more efficient and immersion of the contents of the online lecture, and at the same time, it is possible to systematically take the online course by providing a course evaluation and feedback according to the class confirmation and immersion level. It has the effect of making it happen.

However, the effects obtainable in the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art from the following description. I will be able to.

1 is a diagram illustrating a change in private education expenses of elementary, middle and high school students in connection with the present invention.
2 is a diagram for explaining the average monthly private education cost per person per year and the average monthly private education cost per school level in connection with the present invention.
3 shows a block diagram of a learning analysis system related to the present invention.
4 is a diagram illustrating a method of describing components and services of a learning analysis system related to the present invention.
5 shows an example of a framework from a functional point of view in connection with the present invention.
6 shows an example of a framework from a system perspective in connection with the present invention.
7 shows an example of building a problem bank and a knowledge map in connection with the present invention.
8 shows another example of constructing a problem bank and a knowledge map in connection with the present invention.
9 shows another example of constructing a problem bank and a knowledge map in connection with the present invention.
10 shows an example of an item development strategy and automatic item generation in relation to the present invention.
11 shows another example of an item development strategy and automatic item generation in relation to the present invention.
12 shows an example of a customized learning environment and an ePortfolio in connection with the present invention.
13 shows an example of learning analysis and AI-based prediction and inference in relation to the present invention.
14 illustrates another example of learning analysis and AI-based prediction and inference in relation to the present invention.
15 shows an example of a flow chart for explaining learning analysis and AI-based prediction and inference in connection with the present invention.
16 shows an example of a prediction model in learning analysis and AI-based prediction and inference in relation to the present invention.
17 shows an example of a recommendation model in learning analysis and AI-based prediction and inference in relation to the present invention.
18 illustrates an example implementation of learning analysis and AI-based prediction and inference in connection with the present invention.

Market related to the invention

1 is a diagram illustrating a change in private education expenses of elementary, middle and high school students in connection with the present invention.

Referring to Figure 1, the total amount of private education expenses in 2017 was about 18 trillion 600 billion won, an increase of 562 billion won (3.1%↑) from 18 trillion 100 billion won in 2016.

Specifically, the total amount of private tutoring expenses for subject matters was 13,600 billion won, of which English was 5.42 trillion won, mathematics was 5,3931 billion won, and Korean was 1.257.7 trillion won.

In addition, the average monthly tuition for private tutoring for subjects is 79,000 won for English (0.5%↑), 78,000 won for mathematics (3.3%↑), 18,000 won for Korean (14.2%↑), and 11,000 won (8.5% for social sciences). ↑).

In addition, as for the growth characteristics of each subject, if the Korean language increased the most at 14.2%, and the mathematics increased by 3.3% and the English by 0.5%, respectively, although the size of the private English education market itself was still large, the growth seems to have stagnated compared to other subjects. , It is pointed out that in the 2018 University Academic Ability Test, only English was converted to absolute evaluation.

Mathematics accounts for about 29% of the total private education expenditure. Therefore, the total amount of private mathematics education expenses can be seen as about 5.4 trillion won.

Meanwhile, FIG. 4 is a diagram for explaining the average monthly private education cost per person per year and the average monthly private education cost per person per school level in relation to the present invention.

Referring to FIG. 4, the participation rate of private education by school level was the highest at 82.3% (2.4%p↑) for elementary school students, 66.4% (2.5%p↑) for middle school students, and 55.0% (2.6%p↑) for high school students.

In addition, as students and parents have recently increased their interest in the arts and sports field and their desire to learn, the proportion of private education for arts and sports, hobbies, and liberal arts out of the total private education expenditure rose 9%p in 5 years (18% in 2012 → 27 in 2017). %)did.

When looking at the average monthly private education expenses for arts and sports, hobbies, and culture by school level, elementary school students 107,000 won (7,000 won↑), middle school students 35,000 won (7,000 won↑), and high school students 45,000 won (8,000 won↑).

By detailed subject, the monthly average private education cost is music 24,000 won (1000 won, 5.3%↑), art 11,000 won (1000 won, 10.3%↑), physical education 28,000 won (4,000 won, 17.0%↑), hobbies It was 7,000 won for culture (2000 won, 31.2%↑).

For middle school students, music (23.3%↑) and art (67.0%↑), and high school students (77.4%↑) and liberal arts (54.9%↑), the average monthly private education cost per capita increased significantly.

The reasons for the overall increase in the total amount of private education expenses in the Ministry of Education are analyzed as an increase in private education expenses for arts and sports, hobbies and liberal arts due to increased interest in arts and sports, and diversification of private education purposes such as hobbies, liberal arts, talent development, and childcare.

For the purpose of taking private education, in the case of subject, supplementary/intensifying school classes (48.8%)> prior learning (20.9%)> preparation for further education (17.0%)> anxiety (5.2%)> other (3.0%). Private training for preparation is shown.

For households with an average monthly income of 7 million won or more, the average monthly private education expenditure is 455,000 won, and for those with less than 2 million won, 93,000 won, the participation rate of households with an average monthly income of 7 million won or more increased by 1.7%p from the previous year (81.9%) to 83.6. %, households with less than 2 million won showed 43.1%, up 2.9%p from the previous year (40.2%).

The amount of expenditure by region was in the order of Seoul (399,000 won), Daegu (30.0 million won), and Gyeonggi (286,000 won), followed by Jeollanam-do (177,000 won), and Seoul (76.7%) the highest in participation rate, and Sejong (74.0%), Daegu (73.6%) was followed.

Learning analysis system and service

First, it is intended to propose a learning analysis method and system related to the present invention.

Specifically, the present invention establishes an item response model based on a data collection system, applies machine learning to provide personalized learning paths and content/resource according to the achievement level (capacity), and is specific to learners, teachers, and parents. And provide personalized feedback (prescription), and provide a learning analysis method and system that can detect and resolve problems early by diagnosing learners' learning outcomes.

The suffixes "module" and "unit" for components used in the following description are given or used interchangeably in consideration of only the ease of preparation of the specification, and do not have meanings or roles that are distinguished from each other by themselves.

3 is a block diagram illustrating a learning analysis system according to an embodiment of the present invention.

Referring to FIG. 3, the learning analysis system 10 may include a terminal 100 and a server 200.

First, the terminal 100 includes a wireless communication unit 110, an audio/video (A/V) input unit 120, a user input unit 130, a sensing unit 140, an output unit 150, a memory 160, and an interface. The unit 170, the control unit 180, and the power supply unit 190 may be included.

However, since the components shown in FIG. 3 are not essential, a learning analysis system having more components or fewer components may be implemented.

Hereinafter, the components will be described in order.

The wireless communication unit 110 may include one or more modules that enable wireless communication between the learning analysis system and the wireless communication system or between the device and a network in which the device is located.

For example, the wireless communication unit 110 may include a mobile communication module 112, a wireless Internet module 113, a short-range communication module 114, a location information module 115, and the like.

The broadcast reception module 111 receives a broadcast signal and/or broadcast-related information from an external broadcast management server through a broadcast channel.

The broadcast channel may include a satellite channel and a terrestrial channel. The broadcast management server may mean a server that generates and transmits a broadcast signal and/or broadcast-related information, or a server that receives and transmits a previously-generated broadcast signal and/or broadcast-related information to a terminal. The broadcast signal may include not only a TV broadcast signal, a radio broadcast signal, and a data broadcast signal, but also a broadcast signal in a form in which a data broadcast signal is combined with a TV broadcast signal or a radio broadcast signal.

The broadcast related information may mean information related to a broadcast channel, a broadcast program, or a broadcast service provider. The broadcast-related information may also be provided through a mobile communication network. In this case, it may be received by the mobile communication module 112.

The broadcast-related information may exist in various forms. For example, it may exist in the form of an Electronic Program Guide (EPG) of Digital Multimedia Broadcasting (DMB) or an Electronic Service Guide (ESG) of Digital Video Broadcast-Handheld (DVB-H).

The broadcast receiving module 111 includes, for example, Digital Multimedia Broadcasting-Terrestrial (DMB-T), Digital Multimedia Broadcasting-Satellite (DMB-S), Media Forward Link Only (MediaFLO), and Digital Video Broadcasting (DVB-H). -Handheld), DVB-CBMS, OMA-BCAST, ISDB-T (Integrated Services Digital Broadcast-Terrestrial), and other digital broadcasting systems can be used to receive digital broadcasting signals. Of course, the broadcast reception module 111 may be configured to be suitable for not only the digital broadcasting system described above, but also other broadcasting systems.

The broadcast signal and/or broadcast related information received through the broadcast reception module 111 may be stored in the memory 160.

The mobile communication module 112 transmits and receives a radio signal with at least one of a base station, an external terminal, and a server on a mobile communication network. The wireless signal may include a voice call signal, a video call signal, or various types of data according to transmission/reception of text/multimedia messages.

The wireless Internet module 113 refers to a module for wireless Internet access, and may be built-in or external to the terminal 100.

As the technology of the wireless Internet, wireless LAN (WLAN) (Wi-Fi), wireless broadband (Wibro), World Interoperability for Microwave Access (Wimax), and High Speed Downlink Packet Access (HSDPA) may be used.

The short-range communication module 114 refers to a module for short-range communication. As the technology of short range communication, Bluetooth, Radio Frequency Identification (RFID), infrared data association (IrDA), Ultra-Wideband (UWB), ZigBee, and the like may be used.

The location information module 115 is a module for obtaining the location of the terminal 100, and a representative example thereof is a GPS (Global Position System) module. According to the current technology, the GPS module 115 calculates distance information and accurate time information away from three or more satellites, and then applies a trigonometric method to the calculated information, thereby providing a three-dimensional string according to latitude, longitude, and altitude. Location information can be accurately calculated. Currently, a method of calculating location and time information using three satellites, and correcting an error of the calculated location and time information using another satellite is widely used. In addition, the GPS module 115 may calculate speed information by continuously calculating the current location in real time.

Referring to FIG. 3, an A/V (Audio/Video) input unit 120 is for inputting an audio signal or a video signal, and may include a camera 121 and a microphone 122.

The camera 121 may process an image frame such as a still image or a moving image obtained by an image sensor in the photographing mode, and the processed image frame may be displayed on the display unit 151.

The image frame processed by the camera 121 may be stored in the memory 160 or transmitted to the outside through the wireless communication unit 110.

Two or more cameras 121 may be provided depending on the use environment.

The microphone 122 receives an external sound signal by a microphone in a recording mode, a voice recognition mode, etc., and processes it as electrical voice data.

The processed voice data may be converted into a format transmittable to a mobile communication base station through the mobile communication module 112 and then output.

Various noise removal algorithms may be implemented in the microphone 122 to remove noise generated in the process of receiving an external sound signal.

Next, the user input unit 130 generates input data for the user to control the operation of the learning analysis system. The user input unit 130 may include a key pad, a dome switch, a touch pad (positive pressure/power failure), a jog wheel, a jog switch, and the like.

The sensing unit 140 detects the current state of the learning analysis system, such as the open/closed state of the learning analysis system, the location of the learning analysis system, the presence of user contact, the direction of the learning analysis system, and acceleration/deceleration of the learning analysis system. It generates a sensing signal to control the operation of.

The sensing unit 140 may sense whether the power supply unit 190 supplies power, whether the interface unit 170 is coupled to an external device, or the like.

On the other hand, the output unit 150 is for generating output related to visual, auditory or tactile sense, and includes a display unit 151, an audio output module 152, an alarm unit 153, a haptic module 154, and a projector. The module 155, a head-up display (HUD), a head mounted display (HMD), and the like may be included.

The display unit 151 displays (outputs) information processed by the learning analysis system.

The display unit 151 includes a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), and a flexible display. display) and a 3D display.

Some of these displays may be configured as a transparent type or a light-transmitting type so that the outside can be seen through them. This may be referred to as a transparent display, and a representative example of the transparent display is TOLED (Transparant OLED). The rear structure of the display unit 151 may also be configured as a light transmission type structure. With this structure, the user can see objects located behind the learning analysis system body through an area occupied by the display unit 151 of the learning analysis system body.

Two or more display units 151 may exist depending on the implementation form of the learning analysis system. For example, in the learning analysis system, a plurality of display units may be spaced apart or integrally disposed on one surface, or may be disposed on different surfaces, respectively.

When the display unit 151 and a sensor (hereinafter referred to as'touch sensor') for detecting a touch motion form a mutual layer structure (hereinafter, referred to as a'touch screen'), the display unit 151 It can also be used as an input device. The touch sensor may have, for example, a touch film, a touch sheet, a touch pad, or the like.

The touch sensor may be configured to convert a change in pressure applied to a specific portion of the display unit 151 or a capacitance generated at a specific portion of the display unit 151 into an electrical input signal. The touch sensor may be configured to detect not only a touched position and area, but also a pressure at the time of touch.

When there is a touch input to the touch sensor, a signal(s) corresponding thereto is transmitted to the touch controller. The touch controller processes the signal(s) and then transmits the corresponding data to the controller 180. As a result, the controller 180 can know whether an area of the display unit 151 is touched.

The proximity sensor 141 may be disposed in an inner area of the learning analysis system surrounded by the touch screen or near the touch screen. The proximity sensor refers to a sensor that detects the presence or absence of an object approaching a predetermined detection surface or an object existing in the vicinity using the force of an electromagnetic field or infrared rays without mechanical contact. Proximity sensors have a longer lifespan and higher utilization than contact sensors.

Examples of the proximity sensor include a transmission type photoelectric sensor, a direct reflection type photoelectric sensor, a mirror reflection type photoelectric sensor, a high frequency oscillation type proximity sensor, a capacitive type proximity sensor, a magnetic type proximity sensor, an infrared proximity sensor, and the like. When the touch screen is capacitive, it is configured to detect the proximity of the pointer by a change in an electric field according to the proximity of the pointer. In this case, the touch screen (touch sensor) may be classified as a proximity sensor.

Hereinafter, for convenience of explanation, an action of allowing the pointer to be recognized as being positioned on the touch screen by approaching the touch screen without contacting the pointer is referred to as "proximity touch", and the touch The act of actually touching the pointer on the screen is referred to as "contact touch". A position at which a proximity touch is performed by a pointer on the touch screen means a position at which the pointer corresponds vertically to the touch screen when the pointer is touched.

The proximity sensor detects a proximity touch and a proximity touch pattern (eg, a proximity touch distance, a proximity touch direction, a proximity touch speed, a proximity touch time, a proximity touch position, a proximity touch movement state, etc.). Information corresponding to the sensed proximity touch operation and proximity touch pattern may be output on the touch screen.

The sound output module 152 may output audio data received from the wireless communication unit 110 or stored in the memory 160 in a recording mode, a voice recognition mode, or a broadcast reception mode.

The sound output module 152 also outputs sound signals related to functions performed in the learning analysis system. The sound output module 152 may include a receiver, a speaker, a buzzer, and the like.

The alarm unit 153 outputs a signal for notifying the occurrence of an event of the learning analysis system.

The alarm unit 153 may output a signal for notifying the occurrence of an event in a form other than a video signal or an audio signal, for example, by vibration.

The video signal or audio signal may also be output through the display unit 151 or the audio output module 152, so that they 151 and 152 may be classified as part of the alarm unit 153.

The haptic module 154 generates various tactile effects that a user can feel. A typical example of the tactile effect generated by the haptic module 154 is vibration. The intensity and pattern of the vibration generated by the haptic module 154 can be controlled.

For example, different vibrations may be synthesized and output or may be sequentially output.

In addition to vibration, the haptic module 154 is used for stimulation such as an arrangement of pins that move vertically with respect to the contact skin surface, a blowing force or suction force of air through a jet or inlet, a grazing on the skin surface, contact of an electrode, electrostatic force, etc. It can generate various tactile effects, such as the effect by the effect and the effect by reproducing the feeling of cooling and warming using an endothermic or heat generating element.

The haptic module 154 may not only transmit a tactile effect through direct contact, but may also be implemented so that a user can feel the tactile effect through muscle sensations such as a finger or an arm. Two or more haptic modules 154 may be provided depending on the configuration aspect of the learning analysis system.

The projector module 155 is a component for performing an image project function by using the learning analysis system, and is the same as or at least as an image displayed on the display unit 151 according to a control signal from the controller 180. Some may display different images on an external screen or wall.

Specifically, the projector module 155 generates an image to be output to the outside by using a light source (not shown) that generates light (for example, laser light) for outputting an image to the outside, and light generated by the light source. It may include an image generating means (not shown) for performing and a lens (not shown) for expanding the image to the outside at a predetermined focal length. In addition, the projector module 155 may include a device (not shown) capable of adjusting an image projection direction by mechanically moving a lens or the entire module.

The projector module 155 may be divided into a cathode ray tube (CRT) module, a liquid crystal display (LCD) module, a digital light processing (DLP) module, and the like according to the device type of the display means. In particular, the DLP module may be advantageous for miniaturization of the projector module 151 by expanding and projecting an image generated by reflecting light generated from a light source onto a digital micromirror device (DMD) chip.

Preferably, the projector module 155 may be provided on the side, front or rear of the learning analysis system in the longitudinal direction. Of course, it is natural that the projector module 155 may be provided at any position of the learning analysis system as needed.

In addition, the head-up display (HUD) 156 refers to a device that projects the current vehicle speed, fuel level, and navigation directions information as a graphic image on the windshield of the driver.

In addition, a head mounted display (HMD) 157 is a representative device capable of outputting virtual reality information.

Virtual reality is a human-computer that creates a specific environment or situation through a computer into 3D content with a three-dimensional effect, and makes it as if the person using the 3D content is interacting with the actual surrounding situation and environment. It refers to the interface of

In general, the three-dimensional effect perceived by humans is the degree of change in the thickness of the lens according to the position of the object being observed, the difference in the angle between both eyes and the object, the difference in the position and shape of the object visible to the left and right eyes, and the parallax caused by the motion of the object. , And other effects of various psychological and memory effects, etc.

Among them, the most important factor that a person feels a three-dimensional effect is binocular disparity that occurs when the human eyes are about 6.5 cm apart in the horizontal direction. In other words, by binocular parallax, the object is viewed with a difference in angle to the object, and due to this difference, images entering each eye have different images. When these two images are transmitted to the brain through the retina, the brain will You can feel the original 3D stereoscopic image by precisely fusion of each other.

These three-dimensional 3D contents have already been widely used in various media fields and are receiving favorable reviews from consumers. For example, 3D movies, 3D games and experiential displays are typical.

In addition to the generalization of virtual reality technology 3D contents, development of a technology capable of providing a more immersive virtual reality service is required in various ways.

In general, an image display device uses a precise optical device to focus image light generated at a location very close to the eye so that a large virtual screen can be formed at a distance, allowing users to view an enlarged virtual image. Refers to an image display device.

In addition, the image display device is a see-close type in which the surrounding environment can not be seen and only the image light emitted from the display device can be viewed, and the image light emitted from the display device can be viewed through a window at the same time. It can be divided into see-through.

The head mounted display (HMD, 157) according to the present invention refers to various digital devices that can be worn on the head like glasses to receive multimedia contents. According to the trend of lightening and miniaturization of digital devices, various wearable computers are being developed, and HMDs are also widely used. The HMD 157 goes beyond a simple display function and is combined with an augmented reality technology and an N screen technology to provide various conveniences to users.

For example, when a microphone and a speaker are mounted on the HMD 157, the user can make a phone call while wearing the HMD 157. In addition, for example, when the far-infrared camera 122 is mounted on the HMD 157, the user can capture an image in a direction desired by the user while wearing the HMD 157.

In addition, the memory unit 160 may store a program for processing and control of the controller 180, and temporarily store input/output data (eg, messages, audio, still images, moving pictures, etc.). It can also perform a function for. The memory unit 160 may also store a frequency of use of each of the data. In addition, the memory unit 160 may store data on vibrations and sounds of various patterns output when a touch input on the touch screen is performed.

The memory 160 is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory), and RAM. (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic It may include at least one type of storage medium among a disk and an optical disk. The learning analysis system may operate in connection with a web storage that performs a storage function of the memory 160 on the Internet.

The interface unit 170 serves as a path to all external devices connected to the learning analysis system. The interface unit 170 receives data from an external device, receives power, and transmits it to each component inside the learning analysis system, or transmits data inside the learning analysis system to an external device. For example, a wired/wireless headset port, an external charger port, a wired/wireless data port, a memory card port, a port for connecting a device equipped with an identification module, an audio input/output (I/O) port, A video input/output (I/O) port, an earphone port, etc. may be included in the interface unit 170.

The identification module is a chip that stores various types of information for authenticating the right to use the learning analysis system, and includes a user identification module (UIM), a subscriber identification module (SIM), and a universal user authentication module (Universal Subscriber). Identity Module, USIM), etc. may be included. A device equipped with an identification module (hereinafter,'identification device') may be manufactured in the form of a smart card. Therefore, the identification device can be connected to the learning analysis system through the port.

When the learning analysis system is connected to an external cradle, the interface unit serves as a path through which power from the cradle is supplied to the learning analysis system, or various command signals input from the cradle by a user are transmitted to the mobile device. It can be a passage. Various command signals or the power input from the cradle may be operated as signals for recognizing that the mobile device is correctly mounted on the cradle.

The controller 180 generally controls the overall operation of the learning analysis system.

The control unit 180 may include a data collection/storage unit 181, a data analysis unit 182, a dashboard unit 183, and the like.

Here, the collection/storage unit 181 collects item and course information metadata, stores metadata necessary for Caliper data conversion, merges files to improve analysis performance, and when other services requiring analysis come in, It provides functions such as creating a stream.

In addition, the data analysis unit 182 creates a data catalog from Caliper Data, inserts it into Redshift after data ETL work, and provides an augmentation function that analyzes data on a daily/weekly/monthly basis.

In addition, the dashboard unit 183 provides a function of providing education-related content to a user and information for generating feedback in connection with the display unit 151.

The functions of the data collection/storage unit 181, the data analysis unit 182, and the dashboard unit 183 will be described later in more detail with reference to FIG. 4.

Meanwhile, the power supply unit 190 receives external power and internal power under the control of the controller 180 to supply power necessary for the operation of each component.

Various embodiments described herein may be implemented in a recording medium that can be read by a computer or a similar device using, for example, software, hardware, or a combination thereof.

According to hardware implementation, the embodiments described herein include application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), It may be implemented using at least one of processors, controllers, micro-controllers, microprocessors, and electrical units for performing other functions, in some cases herein. The described embodiments may be implemented by the controller 180 itself.

According to software implementation, embodiments such as procedures and functions described in the present specification may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein. The software code can be implemented as a software application written in an appropriate programming language. The software code may be stored in the memory 160 and executed by the controller 180.

In addition, the server 200 may establish a database and exchange information with the terminal 100.

In this case, short-range communication or long-distance communication may be applied between the server 200 and the terminal 100.

As the wireless communication technology that can be used here, WLAN (Wireless LAN) (Wi-Fi), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed Downlink Packet Access), etc. may be used. have.

In addition, as a technology for short range communication, Bluetooth, Radio Frequency Identification (RFID), infrared data association (IrDA), Ultra-Wideband (UWB), ZigBee, and the like may be used.

4 is a diagram illustrating a method for describing components and services of the learning analysis system according to the present invention.

Referring to FIG. 4, a service flow performed by the server 200, the data collection/storage unit 181, the data analysis unit 182, and the dashboard unit 183 is illustrated in detail.

First, the server 200 may build a database (S10)

Next, the EC2 (Batch Server) of the data collection/storing unit 181 is a daily batch job, and collects item and course information metadata (S11).

In addition, the RDS (Aurora) of the data collection/storing unit 181 stores metadata necessary for Caliper data conversion (S12).

In addition, the Kinesis of the data collection/storage unit 181 from the API Gateway 210 generates a Home-Learn Lambda Stream, that is, generates a new stream when another service requiring analysis comes in (S14).

In addition, Lambda provides a Store_Raw_Data function, which stores raw data and, if necessary, corrects the event occurrence time (S15).

In addition, S3 (Data Lake) collects hl-analyticsraw-data (S16) and transmits it to Lambda (S17).

Thereafter, Lambda communicates with the RDS (Aurora) of the data collection/storage unit 181, and when a continuous Lambda function call fails, data is transmitted to the SQS (S18).

In addition, Caliper data, which is a JSON file, is stored through S3 (hl-analyticsraw-data) (S19).

In addition, S3 (hl-analyticsraw-data) exchanges data with EC2, and EC2 improves analysis performance.

Merge the files for (S20). For example, a file may be merged every 10 minutes.

In addition, in connection with Lambda, S3 (hl-analyticsraw-data) provides a function of storing image/long text data as an image/text file when image/long text data is received (S21).

In addition, in connection with Lambda, it is also possible to store raw data that has failed conversion in hl-analyticsraw-data (S3) (temporary bucket, S22)).

Thereafter, the process of monitoring (S23), SNS notification service (S24), and Slack (S25) related to execution may be sequentially performed.

Meanwhile, the data analysis unit 182 allows Glue to (1) create a data catalog from Caliper Data (for example, in units of 3 hours), and (2) insert it into Redshift after data ETL work (for example, in units of 1 day). / 6 hours unit) provides a function (S26).

In addition, Redshift (Data Warehouse) can enable data search on the web for Athena (S27, S28).

In addition, Lambda, which is Step Functions, communicates with Redshift (Data Warehouse) and performs batch work by analyzing daily/weekly/monthly data (S29).

Thereafter, the role as a database (DB) analyzed by RDS (MySQL) is provided (S30).

Further, the dashboard unit 183 operates in conjunction with the display unit 151. First, data is transferred to the dashboard DB, RDS (MySQL) (S31), and EC2 (WAS) communicates with it to receive and feedback. (S32), the webin EC2 and data about it are communicated (S33).

Artificial intelligence-based customized learning method and system

Currently, education for users is frequently performed based on contents provided through terminals.

However, in the currently applied method and system, there is a problem that only educational content is provided to users in one direction, and education reflecting the user's feedback according to a learning event cannot be performed.

For example, in the conventional method, when you logged in and logged out/timed out. How are you using the test and evaluation questions, what are the test scores that are automatically scored, how much and how you are using today's learning, what video materials and how you are using them, what questions or tags are you using during training? There is a problem in that it is difficult to receive user-customized information about which content is being used in order, which data are being viewed, which applications are being used, accumulated status, character change, and search keyword.

This personalized learning is a technology that increases the learning effect conveniently and efficiently by intelligently providing contents and services according to the learner's ability and characteristics.

Conventionally, customized learning technologies that have been commercialized depend on linkage between learning contents or simply count the number of wrong problems to diagnose weak concepts, and thus, there is a problem in that the learning ability diagnosis of learners is not elaborate.

In other words, even in the case of providing personalized customized learning, there has been a limitation in that the efficiency and reliability of the customized learning system cannot be secured because it is based on an incorrect learning ability diagnosis.

Therefore, there is a growing need for learning methods and systems that can solve this problem.

In order to solve the above problems, the present invention proposes a customized learning method and system based on artificial intelligence.

The artificial intelligence-based customized learning method provided by the present invention can be classified as follows.

1. Content

2. Service

3. Big Data

4. AI (Artificial Intelligence)

First, the contents are (1) a question bank based on a knowledge map, (2) an evaluation question that can represent the contents of each unit of the curriculum, and (3) a'Print on Demand' that the learner can compose. It can be divided into'etc.

Here, (1) the knowledge map-based problem bank develops a detailed knowledge map and links it with the national curriculum, and transfers representative and similar questions to the problem bank to a level that can no longer be divided into (unit knowledge level). It includes registration and inspection, test paper composition function for each service function (manual and automatic), and search function for text and formulas of questions (manual and automatic).

Next, (2) development of representative items includes evaluation items and verification that can represent the curriculum by subject, grade, and difficulty that can measure the level of understanding, and development and verification of similar items that can be mechanically generated by AI. Includes lectures on basic concepts and representative questions for each subject.

In addition, (3) ‘My Problem Book (POD)’, which the learner can compose, includes the creation of my own (digital) question book composed of questions I solved and questions (curated), correct answers and explanations. It includes a function to automatically adjust the layout including options and a function to set print options.

Next, the services are (1) my learning style (diagnosing aptitude and learning disposition), (2) conquering challenging subjects (math, Korean, English, science, etc.) (setting duration and goals), (3) learning portfolio (4 ) Divided into DIY (Do It Yourself) learning.

First of all, (1) My learning style (diagnosing aptitude and learning disposition) is a pre-test for measuring comprehension and ability for each subject such as math, English, Korean, and science, and aptitude or intimacy for each subject can be diagnosed. (Psychology/Aptitude) It includes the type of learning agent that is comfortable and convenient through diagnosis of the learning style and the function/process assigned to the learner.

Next, (2) Conquering the challenging subject (set the study period and goal) is to set the study period and the goal to be reached in order to improve the skills of each subject in preparation for the exam or in a short period of time, and an optimized learning path to achieve the goal within the study period. And question/material composition.

In addition, (3) The learning portfolio provides learning guidance that allows learners to challenge by adding game elements to the knowledge map for each subject.Whenever their skills in each subject such as mathematics, English, Korean, science, etc. Each time) badges are given to certify competencies and provide an e-portfolio where you can see at a glance the process of improving your skills per subject by day, week, and month, and future jobs that you can expect when your skills per subject improve.

In addition, (4) DIY learning includes concepts or problem solving/interpretation lectures that students have effectively understood as the subject, subject-specific problems that students directly ask and answer, and (daily) phenomena related to the problem.

On the other hand, big data can be classified into (1) event-based collection system and (2) learning analysis.

First, (1) The event-based collection system designates the entire process of testing and problem solving in the form of learning events and develops a data collection system, and additional new events in addition to the events defined in the'AI Life Record Book' of Home Run Elementary School (100) It is possible to develop and apply API that collects and collects learning events seamlessly from web and mobile.

In addition, it is possible to develop and provide an API applicable to the learner of the home run elementary school 100 and the home run middle school 300.

Next, (2) learning analysis is to provide statistical analysis information such as learning time, service use patterns, and grades compared to peer groups, the cause of incorrect answers, that is, analysis results for weak knowledge and customized (prescription) learning paths, psychological/ It is possible to link the results of the aptitude test and the results of learning analysis and deliver them to the ePortfolio service.

On the other hand, AI (Artificial Intelligence) includes (1) Automatic Item Generator, (2) Learning Tutor (Inference and Guide Function), (3) Learning Curator (Inference and Recommendation Function), (4) Learning Support It can be categorized into chatbots (inference and counseling functions).

First, (1) Automatic Item Generator automatically generates twin questions according to the set conditions based on representative questions, and provides game-like elements with the'Compete against problems with artificial intelligence' function for learners' weak knowledge. Includes.

Next, (2) the learning tutor (inference and guide function) provides an artificial intelligence agent (AI learning tutor) that can infer the weak knowledge of learners through machine learning and predict learning outcomes to improve the efficiency of the learning process. It is possible to apply different styles of AI tutors (learning navigation function) according to the learning tendency and personality.

In addition, (3) the learning curator (inference and recommendation function) automatically curates the optimal learning process, set of questions, and (internal and external) learning materials as input values for the learning period set by the learner for each subject and the goal they want to reach. You can use an inference engine that does.

Through this, the entire learning process created by the learning curator is led and managed by an AI learning tutor.

In addition, (4) For learning support chatbots (reasoning and counseling functions), the chatbot provides real-time counseling on FAQs and effective service usage tips for each subject, and the main content of the homerun/schooling teacher's learning counseling guide is used by the learner. Includes consulting with

Through this, the present invention provides differentiated content services and new big data AI.

In other words, it is possible to develop a knowledge map for each subject for customized learning by level different from the content, and fully respond to learners of all grades of K-12 (Elementary 1 ~ High School 3) with high-quality representative questions.

In addition, it is possible to provide a simulation that manipulates figures and graphs, and you can compose your own problem book (PoD) composed of the problems I solved.

In addition, the present invention is a unique service, it is possible to establish a customized learning plan according to the intelligence of strengths and weaknesses in each subject and the learning style, and automatically generates a learning plan when the learning period and goal are set by themselves.

In addition, it is possible to give badges when the target competency is reached, create a'My Learning Growth Period' for each subject identified by ePortfolio, and provide DIY services that conquer subject-specific learning through peer learning.

In addition, the present invention is a different dimension of big data, applying the event-based big data collection system verified in the home run elementary school 100, and can propose a learning analysis that shows grades, habits, behaviors, and aptitudes at a glance. .

In addition, the present invention is a true AI, which can apply AI (AIG) that automatically generates twin problems, predict learning outcomes by analyzing weaknesses, and apply AI tutors (guides) to induce efficient learning. .

In addition, a learning process that is adjusted in real time according to the learning period, level, and goal is applied, and it is possible to solve the concerns and difficulties of peers' weaknesses in similar subjects with AI chatbots.

Meanwhile, FIG. 5 shows an example of a framework from a functional viewpoint in relation to the present invention.

5, the service proposed by the present invention is an independent learning service for each subject in the form of a customized learning platform (Adaptive Learning Platform), and service linkage is possible in the form of embedding in the home run elementary school 100 and the home run secondary school 300 Do.

Specifically, referring to Figure 5, the Adaptive Learning Platform (ALP, 1000) according to the present invention includes learning analysis (1100), AI inference (1200), content (1300), service (1400), data collection (1500), etc. Includes.

Here, the learning analysis 1100, as (1) a basic dashboard, displays usage status, learning patterns, problem solving habits, and changes in usage trends.

In addition, (2) as an analysis of achievement level, it presents changes in grades, causes of incorrect answers, and diagnosis of vulnerable knowledge.

In addition, (3) the results of the aptitude test and learning style diagnosis for each subject can be displayed/

Next, in the AI inference 1200, (1) the automatic question generator generates twin questions, and (2) the AI tutor predicts the correct answer, recommends appropriate questions, predicts learning outcomes, and recommends a learning path.

In addition, (3) an AI curator sets a short-term rapid course for exam preparation, and (4) an AI subject counseling chatbot is used.

Next, as the content 1300, knowledge map/curricular linkage for each subject, question bank, graphic/graph manipulation, and a problem book created by myself are applied.

In addition, for the service 1400, prior tests (proficiency and aptitude for each subject), study period/target setting (preparation for the test), learning portfolio, DIY learning (peer learning), and the like are applied.

In addition, in the data collection 1500, (1) learning events (IMS Caliper), (2) non-learning events (xAPI) are applied, and (3) as a database, user information, setting profile, question bank, metadata, LCMS (Learning Content Management System) information, LMS (Learning Management System) information, and diagnostic test information are used.

In addition, in accordance with LTI (310), an international standard that controls user authentication and execution remotely without installing third-party learning software on the learning platform, the service is linked in the form of embedding in home run elementary (100) and home run secondary (300). Is possible.

Meanwhile, FIG. 6 shows an example of a framework from a system perspective in connection with the present invention.

Referring to FIG. 6, the artificial intelligence-based customized learning service 1000 according to the present invention supports an N-device environment as a responsive web, and may be embedded in a home run elementary school and a schooling home run secondary as a learner profile.

Referring to FIG. 6, a web 1, a tablet 2, a mobile phone 3, a home run elementary service 100, a home run middle school 300, and the like are illustrated.

Here, through the responsive web interface 4, the artificial intelligence-based customized learning service 1000 according to the present invention interacts with the web 1, the tablet 2, and the mobile phone 3.

In particular, the web 1 receives contents/services from the customized learning service 1000 based on artificial intelligence, and provides events/data as customized learning services 1000 based on artificial intelligence.

In addition, through the learner profile interface 311 and Learning Tools Interoperability (LTI) service, the artificial intelligence-based customized learning service 1000 according to the present invention includes a home run elementary service 100, a home run secondary 300 Interact with

Meanwhile, the artificial intelligence-based customized learning service 1000 according to the present invention includes a learning analysis area 1100, an AI processing area 1200, a content processing area 1300, a service processing area 1400, and the like.

6, the learning analysis area 1100 includes data collection 1101, data storage (Data Lake, 1102), data processing (Data Mart, 1103), data analysis 1104, dashboard 1106, and database. (transaction, 1105), etc.

In addition, the AI processing area 1200 includes a learning agent (AI tutor, 1201), a subject counseling chatbot 1202, a learning recommendation (curation, 1203), a search engine 1204, a visual intelligence processing unit 1205, and an inference engine ( 1206), etc.

Here, AI data learning is applied between the learning analysis area 1100 and the AI processing area 1200.

Next, the content processing area 1300 is the process of the problem bank 1301, AIG 1302, video material 1303, learning material 1304, knowledge map 1305, curriculum/achievement criteria 1306 Go through.

In addition, the service processing area 1400 undergoes processes such as pre-test 1401, DIY learning (peer learning, 1402), personal learning environment (test preparation, etc., 1403), and learning portfolio 1404.

Here, AI data tagging may be applied between the AI processing area 1200 and the content processing area 1300.

In addition, content/data may be provided between the learning analysis area 1100 and the service processing area 1400.

Through this, in the present invention, it is possible to efficiently incorporate big data and AI into education.

Details are as follows.

-Event-based big data analysis

-Pattern analysis based on learning tendencies and habits

-Detailed vulnerability analysis using knowledge map

-Learning outcome/correct answer prediction

-Weak knowledge prediction

-Predict the risk of giving up learning

-Search using OCR/visual intelligence

-Recommend learning plans according to aptitude and personality

-Recommend optimal study schedule/quantity according to the time and goal set by the learner

-Automatic questions generated by artificial intelligence

In addition, in the present invention, competency-based education (CBE) may be implemented.

Details are as follows.

-Certification of competency by issuing badges when knowledge of each subject is fully acquired (can be disclosed on social networks, portfolio management with open badge backpack)

-Depending on the level of achievement, the study roadmap for short-term, mid-term, and long-term subjects is presented.

-According to the aptitude and achievement level of each subject, future jobs are recommended to motivate learning, and expanded to services in the form of gifted courses (math, science, mathematics science convergence gifted students, etc.)

-Promote global competency-based education by linking global curriculum/achievement standards to LOD (Linked Open Data)

In addition, in the present invention, social learning (peer learning) can be implemented.

Details are as follows.

-Produce/share/feedback the concepts/knowledges I understood as lecture videos (effective learning method for “teaching children”)

-Self-made learning problems and solutions (e.g., peer learning that solves math problems and everyday problems by themselves through DIY method)

-Creating a community for each subject-related field (community to foster gifted students in each field, such as coding, math, science, and math/science convergence)

-A growth diary in which a child and AI grow together while sharing career/advancing concerns with AI (the process of children learning AI together and developing them as peer helpers)

Hereinafter, the main functions of the service 1000 proposed by the present invention will be divided and described in detail.

Method and system for building a problem bank and knowledge map

This embodiment corresponds to the section of customized learning content based on artificial intelligence according to the present invention.

The establishment of the problem bank and the knowledge map is to optimize the knowledge map to suit the purpose of the service by introducing a commercial product with the problem bank and the knowledge map.

These services can be extended so that curriculum and achievement standards can be entered into a multilingual system for global service development.

7 shows an example of building a problem bank and a knowledge map in connection with the present invention.

Referring to FIG. 7A, problem banks such as home screen 1610, knowledge map management 1620, service management 1630, content management 1640, inspection report 1650, environment setting 1660, etc. An example system functional configuration 1600 is shown.

As a specific procedure, referring to Fig. 7(b), knowledge map management -> global curriculum management -> source (textbook) registration -> question authoring/creating -> question registration/connection -> question review -> test paper composition A process such as may be applied.

Meanwhile, FIG. 8 shows another example of constructing a problem bank and a knowledge map in connection with the present invention.

As shown in FIG. 8, by introducing a generalized workflow, the question registration and creation process can be quickly applied.

In addition, it is possible to link the addition of metadata elements for registration of achievement criteria, a multilingual input system, and an automatic question generator.

Meanwhile, FIG. 9 shows another example of building a problem bank and a knowledge map in connection with the present invention.

9 shows an example of a knowledge map for a mathematics curriculum.

As shown in FIG. 9, a method of recommending individual learning paths for intensively solving vulnerability analysis and vulnerability knowledge based on a knowledge map may be applied.

Item development strategy and automatic question creation method and system

In the question development and automatic question generation service according to the present invention, a representative question whose contents have been verified for automatic question generation can be developed through an external expert group for each service grade.

In addition, natural language processing and ontology technology can be applied to effectively implement the theory of automatic question generation.

Specifically, based on the revised curriculum and achievement standards, it is possible to derive evaluation standards related to mathematics, English, Korean, and science, and to develop questions and algorithms based on them.

The revised curriculum and achievement standards may include core competencies for each subject, defining aspects of learners, real life-oriented statistics, and realization of reduction of learning burden.

In addition, as the evaluation criteria, the achievement criteria of the evaluation criteria reorganized to be suitable for use as a reference in the actual evaluation situation are used as the achievement criteria of the curriculum, and the upper, middle, and lower evaluation criteria are used for each of the evaluation criteria achievement criteria. This is possible.

In addition, for item and algorithm development, an automatic item generator can be applied through item modeling based on representative items and item development that maintains a hierarchy between evaluation criteria achievement criteria and evaluation criteria according to grade and grade group.

10 shows an example of an item development strategy and automatic item generation in relation to the present invention.

Referring to FIG. 10, an example of a question dimension design based on the learning tags and evaluation criteria of the evaluation questions and achievement criteria according to five levels of difficulty, such as high, medium, medium, medium, and low, is shown for the representative questions.

Through this, it is possible to develop personalized questions for each level by optimizing the relationship between the questions and the questions.

In the end, through the question development and automatic question generator, it is possible to provide information such as (1) the correct answer rate (2) the question discrimination rate (3) the question response rate to the user.

First, (1) Regarding the question correct rate, express the percentage (%) of the candidates who answered a certain question correctly, check the target difficulty level and achievement of difficulty level, and spread the level of difficulty of the question widely so that the level of ability is high. For the subject, it is possible to create challenging questions and set a goal of 50-60% (example value) for correct answer rates.

Next, (2) Regarding the question discrimination degree, it is checked whether the question discriminates well between the upper and lower groups of the ability to be measured, encourages the number of correct answers in the upper group to be greater than the number of correct answers in the lower group, and the discrimination degree is 0.2 Value) You can set an ideal goal.

In addition, (3) With regard to the item response rate, the distribution status of the response to the answer sheet of the question is checked, the criteria for diagnosis on wrong understanding and interpretation of the subject are applied, applied to the production of multiple-choice questions, and 40% (example Value) or less.

Also, in the present invention, a twin item generator can be applied.

11 shows another example of an item development strategy and automatic item generation in relation to the present invention.

As shown in FIG. 11, it is possible to register and utilize twin items generated based on verified representative items as a question bank.

Social learning method and system

The social learning service according to the present invention is to self-knowledge through the process of self-learning concepts and problems that I have understood, and to induce peer learning in the language of children.

The biggest difference is that the top 1% children know what they don't know, as introduced in the EBS documentary'What is a school?' Therefore, the customized learning 1000 based on artificial intelligence aims to provide a service to increase metacognition.

Specifically, according to the present invention, it is possible to learn mathematics DIY learning by making oneself and solving together by referring to the math problems in daily life and the previously presented problems on the test.

In addition, it is possible to cultivate talented individuals who converge coding, mathematics, and mathematics/science through a community culture in which not only children but also adults (mentors) participate.

In the end, it is possible to provide a service that embeds a method that can motivate students to learn why they need to learn school study (especially subject learning) and deep learning factors that can lead to gifted education.

Customized learning environment and ePortfolio

Next, according to the present invention, a customized learning environment and ePortfolio construction service can be provided.

12 shows an example of a customized learning environment and an ePortfolio in connection with the present invention.

As shown in Fig. 12, this is to increase a sense of achievement by connecting a personalized learning environment with a social network, and to preserve a growth record through portfolio management.

Referring to FIG. 12, based on a social network 2010, my learning style for each subject (2020), challenge learning for each subject (2030), a collection of problems (PoD, 2040), DIY learning (2050), and the like may be shared. .

Specifically, my learning style 2020 may include a proficiency test for each subject, an aptitude test for each subject, and a learning style test.

Next, the challenge-learning conquest 2030 for each subject may include setting a learning time and reaching goal for the test.

In addition, the collection of problems (PoD, 2040) that I have created may include problems that I have solved, problems that I have liked.

Also, my DIY learning 2050 includes videos of my lectures, learning problems I created, and so on.

Through this, my learning environment (personalization area, 2060) can be set and an ePortfolio 2070 can be built. At this time, future job information 2080 may also be provided.

My learning environment (personalization area, 2060) includes learner profile, learning analysis dashboard, my competency (badge backpack), study room for exam preparation, my national ranking by subject, online problem book, print my problem book, lecture list I uploaded, study problem I created , Views, ratings, etc. can be included.

In addition, ePortfolio (2070) is based on my current position, open badge backpack, my learning growth record by subject (day, week, monthly growth record), and my ability/interest by subject. And the like.

Further, according to the present invention, it is possible to design customized learning environment functions and ePortfolio functions for each unit function.

Learning analysis and AI-based prediction and inference methods and systems

Next, a learning analysis and AI-based prediction and inference method proposed by the present invention will be described.

13 shows an example of learning analysis and AI-based prediction and inference in relation to the present invention.

Referring to FIG. 13, in the customized learning 1000 based on artificial intelligence proposed by the present invention, learning analysis and AI are performed as a series of processes consisting of “analysis-prediction-recommendation”.

In other words, the recommended method can be applied through machine learning technology that links cooperative filtering and logistic regression models, which have been verified several times in the field of learning analysis.

Referring to FIG. 13A, as a learning pattern/characteristic analysis, it is possible to analyze the current situation using result data such as a learner's pattern and characteristics, learning outcomes, correct answers, and incorrect answers.

In addition, referring to (b) of FIG. 13, as a test/item analysis, predictive analysis that links the test and item difficulty and characteristics based on learning analysis is possible.

In addition, referring to (c) of FIG. 13, as a learning recommendation, an optimal learning path and resource recommendation using a learner classification and a regression model are possible.

Through (a) and (b) of Fig. 13, services such as creating a learner profile, analyzing a dashboard on the learning status, predicting performance reflecting aptitude and interest, predicting correct/incorrect answers for each question, and clustering similar items can be provided. have.

In addition, through (b) and (c) of Fig. 13, design/recommend learning paths by learner level, recommend questions and learning materials by learner level, peer lecture/problem recommendation according to learning style/propensity, future considering aptitude and math skills Services such as job recommendations may be provided.

Meanwhile, FIG. 14 shows another example of learning analysis and AI-based prediction and inference in relation to the present invention.

14 shows an efficient learning process that intensively solves question-solving and weak knowledge by level through basic conceptual learning, and is an example of the learning process planned in the process of planning customized mathematics services for each level in the home run secondary school 300. .

Referring to FIG. 14, starting from basic learning (2110), “type learning + weak type lecture + twin questions” step (2120), AI recommended customized questions (2130), “vulnerable type lecture + similar questions” step (2040) And a feedback step 2050 is performed.

Specifically, in basic learning (2110), different contents are applied according to the learner's previous learning results, and if vulnerable A is found in the “type learning + weak type lecture + twin question” step (2120), AI recommended customized learning The primary prescription for vulnerable types is made according to the results of basic learning.

Thereafter, when the vulnerability B is found in the step 2040 of the "Vulnerable type lecture + similar question" step 2040, a secondary prescription for the vulnerable type according to the customized learning result is given, and a feedback step 2050 is performed accordingly.

15 shows an example of a flow chart for explaining learning analysis and AI-based prediction and inference in connection with the present invention.

Referring to FIG. 15, an efficient learning process for intensively solving question-solving and weak knowledge for each level is shown through basic conceptual learning.

Referring to FIG. 15A, first, a basic learning step S100 is performed.

Thereafter, a step (S110) of checking whether the vulnerable type is found is performed.

If the vulnerable type is found, the step of performing learning on the vulnerable part A (S140) is performed, and if there is no vulnerable type, AI recommended customized learning is performed (S120).

After performing the AI recommendation personalized learning (S120), a step (S130) of checking whether a vulnerable type is found is performed again.

If there is no vulnerable type, the feedback step (S160) is immediately entered.

If there is a vulnerable type, it is determined whether it is the same type as the vulnerable type found in step S110 (S150).

In the case of the other type, the feedback step (S160) is entered, but in the case of the same type, B learning to supplement the vulnerable type is performed (S170), and then the feedback step (S160) is entered.

Further, referring to (b) of FIG. 15, after entering the feedback step S160, a step S170 of checking whether learning about the vulnerable A has been performed is performed.

When learning A is performed, a step (S180) of confirming whether the problem is correct is performed, and if it is correct, a step (S190) of confirming an item similar to the vulnerable type is performed.

If not, the step of solving the representative question again (S200) is performed, and a step (S190) of confirming the question similar to the vulnerable type is performed.

If the learning A is not performed in step S170, it is checked once again whether the learning B has been performed (S210).

When learning B is performed, a step (S240) of confirming whether the problem is correct is performed, and when it is correct, a step (S190) of confirming an item similar to the vulnerable type is performed.

If it does not match, it goes through the step (S200) of solving the representative question again, and then goes through the step (S190) of confirming the question similar to the weak type.

If the B learning is not performed in step S210, a report is output (S220), and then learning is performed on the next concept (S230).

If all of the steps for checking the placebo-type similar item (S190) are passed, the learning is terminated and a report is output (S260).

Meanwhile, FIG. 16 shows an example of a prediction model in learning analysis and AI-based prediction and inference in relation to the present invention.

As shown in FIG. 16, by predicting learning outcomes in advance, it is possible to present an immediate alternative so as not to abandon mathematics as well as service departure.

That is, in the present invention, it is possible to respond in real time, such as recommending weakness overcomers of peers belonging to a similar group and presenting artificial intelligence and problem competition using game elements.

In addition, FIG. 17 shows an example of a recommendation model in learning analysis and AI-based prediction and inference in relation to the present invention.

17A shows a static learning path based on a rule, and (b) shows a dynamic learning path based on machine learning.

Referring to FIG. 17, instead of following a predefined learning path (process), the next learning process may be dynamically changed for each situation and question.

In other words, the knowledge of vulnerability is different for each individual and depending on the difference in flood power, less or more problem solving and skills may be required, so prediction and recommendation can be closely linked.

Specifically, since the target score is different for each learner and the shortest learning condensation to reach the target score is different, the problem is solved so that the learner can reach the target position with the shortest possible movement, taking into account the learner's current score, target score, and vulnerability type. I recommend you.

Thereafter, it is possible to improve learning efficiency, accelerate the learning path, and provide an optimized learning curriculum by providing customized content according to the type of vulnerability.

In addition, the service according to the present invention, as a learning agent, the AI tutor may play a role of a facilitator so that the learner can actively perform learning paths and resources designed based on the inferred learner's weak knowledge and learning outcomes.

In other words, the AI tutor's style can be applied differently according to the learning tendency and personality (learning navigation function).

18 illustrates an example implementation of learning analysis and AI-based prediction and inference in connection with the present invention.

Referring to FIG. 18, since the artificial intelligence-based customized learning service 1000 according to the present invention is basically operated as an unmanned system, the chatbot performs service use inquiries and subject counseling, and the chatbot operates the customer counseling center during the day. Responses to excessive inquiries and customers who need emotional response can be performed in the conventional way.

Effects according to the invention

At least one embodiment of the present invention configured as described above may provide an artificial intelligence-based customized learning method and system.

Specifically, according to the present invention, customized learning services for each subject using big data and AI technology diagnose weaknesses of individual learners and give specific prescriptions, predict learning outcomes, establish an efficient learning plan, and generate interest. A new standard for subject-specific learning services can be proposed while adding elements to the subject.

That is, in the present invention, the concept of each subject can be subdivided into unit knowledge beyond the curriculum. For example, after systematizing the concept of mathematics into thousands of unit knowledge that can no longer be decomposed independently from the curriculum, the curriculum Service flexibility can be strengthened by linking the topics of the unit into a bundle of related unit knowledge.

In addition, according to the present invention, it is possible to change the standard information for vulnerability diagnosis to unit knowledge, and a detailed prescription can be made while analyzing the vulnerability with more detailed unit knowledge from the method of diagnosing the vulnerability based on the existing unit evaluation score. I can.

In addition, according to the present invention, the unit for designing the learning path can also be expressed as a knowledge map. Although it is possible to learn in the order of units and topics of the curriculum, unit knowledge for competency-based education (CBE) By designing a learning path centering on, it is possible to adjust different learning plans and quantities for each individual.

Next, according to the present invention, through educational services using big data and AI, components of an adaptive learning platform can be presented step by step.

Specifically, according to the present invention, the problem solving process can be analyzed in detail.

In other words, it is possible to provide information in the form of a dashboard by collecting the entire process as big data such as solving time, correct/incorrect answer, and replay of an explanation lecture whenever a learner solves a question on the test paper.

Currently, most of the system logs and metadata of the database are combined and analyzed using a data mining method, but in the present invention, it is possible to provide an analysis of the cause of an incorrect answer, that is, vulnerability knowledge and achievement analysis results for each subject.

In addition, according to the present invention, it is possible to predict learning outcomes and the possibility of submitting correct/incorrect answers through the inference function of AI.

Specifically, the possibility of submitting correct/incorrect answers and learning outcomes can be predicted using the results of vulnerability analysis and accumulated learning data.

In addition, AI-optimized learning paths and content (questions) can be recommended.

According to the present invention, for individual vulnerability knowledge, it is possible to provide an interactive recommendation service that overcomes weaknesses in a short period of time with successive similar problems and twin problems.

In addition, according to the present invention, it is possible to provide a PoD (Print-on-Demand) service through a recommendation and questionnaire function capable of configuring a personal problem book.

In addition, according to the present invention, it is possible to upgrade to an interface that recognizes equations and characters using OCR (Optical Character Recognition) technology, an interface that expresses equations through handwriting recognition, and a service that simulates a graph.

Specifically, in the present invention, it is possible to search (OCR) a problem by taking a picture.

In other words, it is possible to provide a service that searches for the correct answer and problem solving process in the database accumulated with AI and provides it in real time by taking a picture of the printed or handwritten questions in the problem book.

Currently, the focus is on recognition and search competitiveness, and contextual service elements, such as prediction and recommendation, are insufficient. In the present invention, a formula expression through handwriting recognition can also be provided.

In other words, if a complex formula is written on the touch interface, the AI can recognize it, express it as a regular formula, and present the correct answer through real-time calculation.

In addition, the present invention provides an intuitive graph simulation.

Specifically, it is effective in overcoming weaknesses as you can immediately graph changes in graphs while controlling coefficients and variables and expressing complex functions directly.

In addition, the present invention establishes an item response model based on the data collection system, applies machine learning to provide personalized learning paths and contents/resources according to the achievement level (capacity), and is specific to learners, teachers, and parents. And provide personalized feedback (prescription), and provide users with learning analysis methods and systems that can detect and resolve problems early by diagnosing learners' learning outcomes.

In addition, the present invention accurately diagnoses whether or not the learner understands each concept from the result of the group test and the learner's solution for individual problems, and provides feedback, so that it is possible to identify the vulnerable concept and automatically select and recommend learning contents for the vulnerable concept. There is an effect of increasing the efficiency and reliability of customized learning.

In addition, the present invention enables the learner to participate in the online lecture with more efficient and immersion of the contents of the online lecture, and at the same time, it is possible to systematically take the online course by providing a course evaluation and feedback according to the class confirmation and immersion level. It has the effect of making it happen.

However, the effects obtainable in the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art from the following description. I will be able to.

In addition, according to an embodiment of the present invention, the above-described method can be implemented as code that can be read by a processor in a medium on which a program is recorded. Examples of media that can be read by the processor include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, etc., and may be implemented in the form of a carrier wave (for example, transmission over the Internet). Include.

The method and system described above are not limitedly applicable to the configuration and method of the above-described embodiments, but the embodiments are configured by selectively combining all or part of each embodiment so that various modifications can be made. It could be.

Claims (8)

In the education server that has built a network with web, external server and terminal,

When a user sets a learning environment using the education server, the user's learning environment is shared with at least some of the web, an external server, and a terminal based on the network, so that social learning proceeds,

When the learning environment of the user changes on the education server according to the progress of learning,
The education server generates an ePortfolio by accumulating the learning environment of the changed user,

The learning environment,
A first environment for designating the learning style of the user, a second environment for designating a target condition by the user, a third environment for indicating the education contents learned by the user, and the learning contents created by the user in relation to the education contents. Including a fourth environment to display,

In the first environment, the learning style,
It is designated based on the user's profile and competencies for the training content derived based on a pre-specified pre-test,

The target condition in the second environment,
It is designated on the basis of the user's learning time and reaching goal for the test,

The educational content learned in the third environment,
Including a problem solved by the user, a problem previously specified by the user, and a lecture taken by the user,

The learning content in the fourth environment,
The user includes at least one of a problem and lecture content directly produced by the user based on the feedback of the third environment,

Through the fourth environment, at least one of the problem and lecture content created by the user is shared,

Information on views and ratings for at least one of the problems and lecture contents created by the shared user are provided to the user,

The user is plural,
The ePortfolio above,
Including an analysis result of the learning level of the first user and the changed learning environment of the first user among the learning levels of the plurality of users,

The education server,
Based on the ePortfolio, grasp the level of interest of the first user,
Information related to the future job of the first user is determined based on the learning level of the first user, the analysis result of the changed learning environment of the first user, and the determined interest level, and the future job information is provided to the first user. And

The education server,
Determine a plurality of items applied to the user's learning by using the learning level of the first user among the learning levels of the plurality of users on the ePortfolio and the analysis result of the changed learning environment of the first user,
Based on the terminal, learning for the first user is performed by applying the plurality of items,

The education server, after the learning is finished,
Through the terminal, providing the first user's learning vulnerability overcome information and the user's learning plan information to the user,

The user's learning vulnerability overcome information,
Among the plurality of questions in the learning step, the error rate is related to a weakness question that is equal to or greater than a predetermined value, and is information on a plurality of pre-designated supplementary questions,

The learning plan information of the user,
It is a learning target and learning time information customized for the first user,

The education server continuously provides information on the plurality of pre-designated supplementary items to the first user to perform additional learning of the first user,

The education server,
When the user receives an image of the first item taken through a camera among the plurality of items,
Social learning, characterized in that based on OCR (Optical Character Recognition) technology, grasping the first question through the first question image and providing pre-designated commentary information related to the first question to the user Education server for customized learning based on ePortfolio. delete delete delete delete delete delete delete

Images