KR20120071055A - Learning page automatic composing system, apparatus and method therefor - Google Patents

Abstract

PURPOSE: A learning page automatic composing system, apparatus and method and a cloud computing service providing apparatus are provided to improve achievement of online learning by analyzing learner's contents use pattern and study result and mapping page information of a learner terminal with the analysis result. CONSTITUTION: A learning page automatic composing system comprises a learner terminal(110), a contents providing unit(120), and a learning page composing unit(130). The contents providing unit provides learning contents to the learner terminal connected through a network. The learning page composing unit composes a basic page of contents provided based on the terminal information of the learner terminal and a learner page by determining recommended items using learning information of a learner.

Description

Learning Screen Automatic Composing System, Learning Screen Automatic Composing Device, Cloud Computing Service Providing Device and Its Learning Screen Automatic Composing Method {Learning Page Automatic Composing System, Apparatus and Method therefor}

An embodiment of the present invention relates to a learning screen automatic configuration system, a learning screen automatic configuration apparatus, a cloud computing service providing apparatus, and a method for automatically configuring the learning screen. More specifically, online learning is performed by analyzing learner's content usage pattern and learning result and mapping the analysis result and the screen configuration information of the terminal device to be used for learning to construct and provide the learner with a learning screen optimized for learning. The present invention relates to a learning screen automatic configuration system, a learning screen automatic configuration apparatus, a cloud computing service providing apparatus, and a learning screen automatic configuration method for improving learner's learning achievement.

The contents described in this section merely provide background information on the embodiments of the present invention and do not constitute a prior art.

Recently, our educational environment is changing rapidly through various changes in the surrounding environment caused by the use of the Internet and computers. In particular, with the development of various educational media, learners can select and use a wider range of learning methods. Among them, the teaching service through the Internet overcomes the time and space constraints and the low-cost education enables the teaching and learning. It was established as one of the means.

In response to this trend, e-learning related technologies have been rapidly developed, and customized education services, which were not possible in offline education, are now possible with limited human and physical resources. For example, by providing the level-specific learning segmented according to the learner's personality and ability, it is possible to provide educational content according to the learner's individual competence, breaking away from the past uniform method.

However, even in such customized education services, most of the educational contents provided up to now take the form of unilateral infusion education. In other words, if the instructor first provides a lecture for the level of the learner, the learner can go through a separate learning process offline, then check the learning outcome through the evaluation process.

As such, the educational services provided through the Internet to date are not significantly different from the conventional offline teaching methods in that learning outcomes are dependent on the offline efforts of the learners who take the lectures. Accordingly, in order to improve the practical skills of the learners, there is a problem that the function is not properly utilized in the Internet education environment capable of interactive education.

Recently, interest in self-directed learning methods has been increasing as a form of active learning methods to respect the individuality of learners and maximize the individual's potential. Self-directed learning consists of exploring human and material resources for learning in order to satisfy the learning needs inspired by an individual in a specific learning process, and evaluating learning outcomes using appropriate approaches. To this end, the learner constructs personalized learning materials and registers / generates personalized learning information for each learner's terminal device by modifying his or her information whenever the learner's learning status changes or new learning contents are generated.

However, such self-directed learning is useful for learners who are accustomed to learning by themselves, but for learners who are not used to learning by themselves or learners whose learning status changes frequently, they modify their own information whenever they do so to register / create personalized learning information. The problem is that doing so is a cumbersome task.

An embodiment of the present invention has been devised to efficiently solve the above-described problem, and learns the learner by analyzing the content usage pattern and the learning result of the learner, and mapping the screen composition information of the terminal device to be used in learning. By constructing and providing the learning screen optimized for performance, the learning screen automatic configuration system, the learning screen automatic configuration device, the cloud computing service providing device, and the automatic configuration for customized learning that can improve the learner's learning achievement when performing online learning. It is an object to provide a method.

Learning screen automatic configuration system for customized learning according to an embodiment of the present invention for achieving the above object, the learner terminal connected via a network; A content providing unit providing content for learning to a learner terminal; And constructing a basic screen of contents provided based on terminal information of the learner terminal, and using the learning information of the learner using the learner terminal, priority learning content, learning order content, and menu providing content for the contents provided as the basic screen. The apparatus may include a learning screen configuration unit configured to configure a learner screen by determining a recommendation item including at least one of characteristic values.

According to an aspect of the present invention, there is provided an apparatus for automatically constructing a learning screen according to an embodiment of the present invention, including: a semantic DB storage unit configured to store metadata about screen configuration information and learning information for each learner; An algorithm performer which performs a mining algorithm; Call the classification algorithm of the mining algorithm based on the terminal information of the learner terminal and the screen configuration information corresponding thereto to configure a screen for the contents provided to the learner terminal, and the learning information about the learner using the learner terminal and the corresponding information. A learner screen generation unit configured to generate a learner screen for a screen configured by calling a correlation algorithm of a mining algorithm based on metadata; And a screen transmission unit which transmits the learner screen generated by the learner screen generation unit to the learner terminal.

Here, the learner screen generating unit may determine a recommendation item including at least one of priority learning content, learning order content, menu providing content, and characteristic values of the provided contents, and generate a learner screen based on the determined recommendation item. have.

The apparatus for automatically configuring learning screens may further include a mapping processor that maps information necessary for configuration of the learner screen according to a result of the mining algorithm.

The apparatus for automatically configuring learning screens described above may further include a data updater which generates metadata about the learner screen and updates the semantic DB storage based on the generated metadata.

In addition, the apparatus for automatically configuring the learning screen described above may further include a screen updating unit configured to detect and update the changed information on the learner screen provided to the learner terminal.

Cloud computing service providing apparatus according to an embodiment of the present invention for achieving the above object, in the cloud computing service providing apparatus for providing a learning screen to the learner terminal through a cloud computing environment, the screen for the screen for each type of learner terminal Semantic DB storage unit for storing the metadata for the configuration information and learning information for each learner; Compose a screen for the contents provided to the learner terminal based on the terminal information of the learner terminal and the corresponding screen configuration information, and based on the learning information about the learner using the learner terminal and the metadata corresponding thereto A learner screen generation unit generating a learner screen; And a screen transmission unit which transmits the learner screen generated by the learner screen generation unit to the learner terminal.

In accordance with another aspect of the present invention, there is provided a method for automatically configuring a learning screen, by calling a classification algorithm of a mining algorithm based on terminal information of a learner terminal and corresponding screen configuration information. Constructing a screen for the fields; Generating a learner screen for a screen configured by calling a correlation algorithm of a mining algorithm based on learning information about a learner using a learner terminal and corresponding metadata; And transmitting the generated learner screen to the learner terminal.

In addition, the learner screen generation step may determine a recommendation item including at least one of priority learning content, learning order content, menu providing content, and characteristic values for the provided contents, and generate a learner screen based on the determined recommendation item. Can be.

In addition, the above-described method for automatically configuring the learning screen may further include mapping information necessary for configuring the learner screen according to the result of performing the mining algorithm.

According to an embodiment of the present invention, by analyzing the learner's content usage pattern and learning results, by mapping the analysis results and the screen configuration information of the terminal device to be used in learning by constructing and providing the learner with the learning screen optimized for learning performance It is possible to improve the learner's learning achievement when performing online learning.

1 is a diagram schematically illustrating a system for automatically configuring a learning screen according to an embodiment of the present invention.
2 is a diagram schematically illustrating an apparatus for automatically constructing a learning screen according to an embodiment of the present invention.
3 is a flowchart illustrating a method of automatically configuring a learning screen according to an exemplary embodiment of the present invention.
4 is a diagram illustrating an example of signal processing between the learner terminal and the learner screen autoconfiguration device.
FIG. 5 is a diagram illustrating an example of generating a learning screen by the apparatus for automatically configuring learner screens.
FIG. 6 is a diagram illustrating an example of a screen service by an apparatus for automatically configuring learner screens.

Hereinafter, a learning screen automatic configuration system, a learning screen automatic configuration device, a cloud computing service providing device, and a learning screen automatic configuration method according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram schematically illustrating a system for automatically configuring a learning screen according to an embodiment of the present invention.

Referring to the drawings, the automatic learning screen configuration system may include a learner terminal 110, a content providing unit 120 and a learning screen configuration unit 130, each learner terminal 110, content providing unit 120 ) And the learning screen configuration unit 130 may be connected through the network 140. Here, the content providing unit 120 and the learning screen configuration unit 130 may be implemented to form an element in one server or to interact with each other as an independent server. In addition, the learner terminal 110 may be applied to various wired and wireless environments, and may include a personal digital assistant (PDA), a cellular phone, a smart phone, and the like, and a PCS (Personal Communication Service) phone, GSM, which is classified by communication type. (Global System for Mobile) phones, Wideband Code Division Multiple Access (WDMA) phones, CDMA-2000 phones, Mobile Broadband System (MBS) phones, and the like. MBS phone refers to a terminal to be used in the next generation system currently being discussed. In addition to the Internet network, the network 140 may include Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Global System for Mobile Communications (GSM), Long Term Evolution (LTE), and Evolved Packet Core (EPC). ), A network for accessing a next generation mobile communication system to be implemented in the future, and a cloud computing connection network between a cloud computing service providing apparatus and a terminal. Cloud computing refers to a computer environment where information is permanently stored on servers on the Internet and temporarily stored on client terminals such as desktops, tablet computers, laptops, netbooks, and smartphones. It refers to a computer-environmental access network that stores a server on a computer and makes this information available anytime, anywhere through various IT devices.

The learner terminal 110 is a terminal that can take a learning lecture online, and a program such as a video player, a tutor program, and a javascript is installed.

The content provider 110 provides learning content to the learner terminal 110. Here, the learning content includes a document, an image, etc. written in a language such as a video, flash, Extensible Markup Language (XML), Hypertext Markup Language (HTML), or the like.

The learning screen configuration unit 130 constructs a basic screen of learning contents provided to the learner terminal 110 based on the terminal information received from the learner terminal 110 connected through the network 140, and the learner terminal 110. Using the learner's learning information using the learning information to determine the recommendation item including at least one of the priority learning content, the learning order content, the menu providing content, the characteristic value for the contents provided as the base screen to configure the learner screen. To this end, the learning screen configuration unit 130 stores screen configuration information (for example, information on a screen size, resolution, response speed, contrast ratio, etc.) according to the terminal specifications for various types of terminals, and learner terminals ( Based on the screen configuration information mapped to the terminal information received from the 110 may generate a basic screen composed of the learning content selected by the learner using the learner terminal 110. In addition, the learning screen configuration unit 130 stores learning information (for example, information on subjects, progress, difficulty, class time, evaluation results, etc.) for each learning content previously learned by the learner, The stored learning information may be used to determine priority order, learning order, menu, and characteristic information of each learning content displayed on the current screen, and accordingly, different arrangements of the contents of the current screen may be set. .

2 is a diagram schematically illustrating an apparatus for automatically constructing a learning screen according to an embodiment of the present invention. Referring to FIG. 2, the apparatus 200 for automatically configuring a learning screen may include a semantic DB storage 210, an algorithm performing unit 220, a learner screen generating unit 230, a screen transmitting unit 240, and a mapping processing unit 250. The data updater 260 and the screen updater 270 may be included. The automatic learning screen apparatus 200 may operate as the learning screen configuration unit 130 of FIG. 1. At this time, each component of the automatic learning screen display device 200 may be implemented as an independent server. The automatic learning screen apparatus 200 may operate as a cloud computing service providing apparatus that provides a learning screen to the learner terminal 110 through a cloud computing environment.

The semantic DB storage unit 210 stores the screen configuration information of the screen for each terminal and metadata for the learner-specific learning information. At this time, the semantic DB storage unit 210 and information about the terminal type, use, capacity of the buffer for displaying information on the screen, screen size, resolution, response speed, contrast ratio, etc. of the pre-registered learner terminal 110 The learner's course, progress, difficulty, class time, and evaluation results of the learner's terminal 110 can be stored according to the learner's terminal 110 and the learner, and the information stored in this sense is stored in the semantic database. Name it.

The algorithm performing unit 230 performs a mining algorithm. The mining algorithm refers to an algorithm for data mining. Data mining refers to the process of discovering new data models derived from data from the database that have not been known in the past, extracting actionable information in the future, and using it in decision making. In other words, it finds patterns and relationships hidden in data and discovers information as if it were finding a vein. Information discovery is the process of applying advanced statistical analysis and modeling techniques to data to find useful patterns and relationships. It's a key technology in database marketing.

For example, a department store analyzes data from a sales database to find out what products are selling well on Friday mornings and how they relate to marketing items. Therefore, an essential element of data mining is sufficient data with high reliability. This is because sufficient reliable data make accurate predictions possible. Too much data, however, can reduce the ability of data mining to predict, so it is necessary to have meaningful data that can yield optimal results.

Data mining is largely based on large volumes of data, ranging from tens of megabytes to tens of gigabytes. But looking at vast amounts of data can be a task that requires a lot of patience in terms of time. The process to consider is sampling. Sampling is the extraction of large amounts of data (samples) from small amounts of data (samples) divided by a population. This is a procedure to reduce the time and cost of data mining to help efficient work progress, thereby lightening the weight of data mining work a little. Therefore, ask if the sampling is appropriate and generate sample data using the appropriate method if necessary. In statistics, several methodologies have already been developed for sampling, the most popular of which is the Simple Random Sampling, which is simply a random mixture of populations and randomly extracted as desired. In addition, Stratified Sampling and Systematic Sampling are frequently discussed, and sampling methods suitable for each situation are used. The most significant point in the sampling process is when a sample is biased to a side that does not resemble a population. This must be confirmed after searching some basic data after sampling.

In the process of exploring the data, it is a step to identify and quantify the facts that are already known, and to examine the relationships among the numerous variables. For example, department A's buyers are mainly focused on a specific day of the week, B's buyers are mainly women, etc. In some cases, you may find that the facts that people in your business were convinced were wrong.

For example, if a female customer's credit card is used for a large amount of money in a reunion pub, it is revealed that the stereotype that it is mainly a stolen card is actually different from the data mining process of a domestic card company. In fact, in such a case, the use by the normal card was more frequent. As such, the exploration phase is a process of grasping the shape of data and laying the foundation for information.

In the exploration step, you might divide two or more things into what you already know as a population, or you can reduce dozens or more of them to a few variables that really give you important information, and create new variables in addition to the existing ones. You may find it necessary.

The transformation and adjustment step is a step of considering a variable to be newly created by using an existing variable. Variables created or modified at this stage can be used as important information in later modeling stages.

The modeling step is the most important step in the data mining process, in which various models (such as traditional network models such as neural network, CHAID, CART, generalized linear models, etc.) are fitted using the main variables selected in the preceding steps. . Techniques for creating models include techniques such as associations, clustering, decision trees, and neural networks.

You can choose the best model by comparing two or more suitable model effects. The chosen model can then be reflected in the actual population and reassessed its effectiveness, thereby raising new problems and repeating previous work.

Each of these steps should be taken into consideration in order to perform data mining tasks, and in some cases, may be repeated two or more times or fed back to the previous step.

The learner screen generation unit 230 calls the classification algorithm of the mining algorithm based on the terminal information of the learner terminal 110 and the screen configuration information corresponding thereto to configure a screen for the contents provided to the learner terminal 110. Can be. That is, the learner screen generation unit 230 performs a classification algorithm of the mining algorithm on the screen configuration information for each terminal stored in the semantic DB storage 210 to configure a screen corresponding to the terminal information of the learner terminal 110. In addition, the learner screen generation unit 230 generates a learner screen for the screen configured by calling the correlation algorithm of the mining algorithm based on the learning information about the learner using the learner terminal 110 and the corresponding metadata. That is, the learner screen generation unit 230 extracts learning information from the semantic DB storage unit 210 corresponding to the connected learner terminal 110, and correlates the mining algorithm with respect to the extracted learning information and metadata corresponding thereto. A learner screen is created by performing a relational algorithm. In this case, the learner screen generation unit 230 includes at least one of priority learning, content, learning order content, menu providing content, and characteristic values for contents provided for the configuration of the screen corresponding to the learner terminal 110. The recommendation item may be determined, and a learner screen may be generated based on the determined recommendation item. That is, the learner screen generation unit 230 determines, as a recommendation item, content to be preferentially learned according to learning information on each of the contents of the screen configured to correspond to the learner terminal 110, or a learning order for each content. The content may be determined as a recommendation item, or menu provision content for each content may be determined as a recommendation item. Alternatively, the recommendation item may be determined according to a characteristic value of each of the contents (for example, it may be a value of the number of times, the time of attendance, etc. for each of the contents to be taken during a predetermined period).

The screen transmitter 240 transmits the learner screen generated by the learner screen generator 230 to the learner terminal 110 through the network 140.

The mapping processor 250 maps information necessary for constructing the learner screen according to the result of the mining algorithm performed by the algorithm performing unit 220. That is, the mapping processor 250 collects metadata information necessary for screen configuration from the semantic DB storage 210 and according to the collected information and the result of performing the mining algorithm according to the service page request from the learner terminal 110. Map information necessary for configuration of the screen of the learner terminal 110.

The data updater 260 generates new metadata for the learner screen generated by the learner screen generator 230 and updates the semantic DB storage 210 based on the newly generated metadata. That is, the previously generated learner screen and the currently generated learner screen with respect to the learner terminal 110 may be different. In this case, since the metadata of the learner screen may be changed, the data updater 260 may be a current learner. Metadata is generated based on the screen to update metadata about previous learning information.

The screen updater 270 detects a change from the previous learner screen with respect to the learner screen provided to the learner terminal 110 and updates the current learner screen. That is, the screen updater 270 detects the changed part of the learner screen displayed on the learner terminal 110 so that the learner screen can be updated quickly.

3 is a flowchart illustrating a method of automatically configuring a learning screen by the apparatus for automatically configuring a learning screen of FIG. 2.

2 and 3, the learner screen generation unit 230 calls the classification algorithm of the mining algorithm based on the terminal information of the learner terminal 110 and the screen configuration information corresponding thereto, and provides the learner terminal 110 to the learner terminal 110. A screen of the contents may be configured (S301). That is, the learner screen generation unit 230 performs a classification algorithm of the mining algorithm on the screen configuration information for each terminal stored in the semantic DB storage 210 to configure a screen corresponding to the terminal information of the learner terminal 110.

In addition, the learner screen generation unit 230 generates a learner screen for the screen configured by calling the correlation algorithm of the mining algorithm based on the learning information about the learner using the learner terminal 110 and the metadata corresponding thereto ( S303). That is, the learner screen generation unit 230 extracts learning information from the semantic DB storage unit 210 corresponding to the connected learner terminal 110, and correlates the mining algorithm with respect to the extracted learning information and metadata corresponding thereto. A learner screen is created by performing a relational algorithm. In this case, the learner screen generation unit 230 includes at least one of priority learning, content, learning order content, menu providing content, and characteristic values for contents provided for the configuration of the screen corresponding to the learner terminal 110. The recommendation item may be determined, and a learner screen may be generated based on the determined recommendation item. That is, the learner screen generation unit 230 determines, as a recommendation item, content to be preferentially learned according to learning information on each of the contents of the screen configured to correspond to the learner terminal 110, or a learning order for each content. The content may be determined as a recommendation item, or menu provision content for each content may be determined as a recommendation item. Alternatively, the recommendation item may be determined according to a characteristic value of each of the contents (for example, it may be a value of the number of times, the time of attendance, etc. for each of the contents to be taken during a predetermined period).

The screen transmitter 240 transmits the learner screen generated by the learner screen generator 230 to the learner terminal 110 through the network 140 (S305).

4 is a diagram illustrating an example of signal processing between the learner terminal and the learner screen autoconfiguration device.

Referring to FIG. 4, the learner terminal 110 may access the driving gateway 150 through a login process to receive an automatic configuration service of the learner screen, and through this process, terminal information and user information of the learner terminal 110. Is sent.

The driving gateway 150 requests an automatic configuration service of the learner's screen to the learning screen autoconfiguration device 200, and accordingly, the user information and the terminal information received from the learner terminal 110 are transmitted to the learning screen autoconfiguration device 200. To pass.

In this case, the apparatus 200 for automatically configuring the learning screen extracts screen configuration information corresponding to the terminal information from the semantic database, extracts learning information corresponding to the user information, and generates a learner screen corresponding to the learner terminal 110 accordingly. You can do it.

FIG. 5 is a diagram illustrating an example of generating a learning screen by the apparatus for automatically configuring learner screens.

The learner screen generator 230 may be provided with an attribute mapped to the screen configuration information of the learner terminal 110 through the mapping processor 250.

In addition, the learner screen generator 230 performs a classification algorithm of the mining algorithm through the algorithm performer 220 to configure a screen corresponding to the terminal information of the learner terminal 110, and performs a correlation algorithm to perform the learner's operation. The learner screen may be generated according to the learning information. Such a learner screen may be implemented as a promotion map as shown.

FIG. 6 is a diagram illustrating an example of a screen service by an apparatus for automatically configuring learner screens.

The learner screen generator 230 transmits the promotion map by the algorithm performer 220 to the data updater 260 and may configure menus and contents accordingly. The configured menu and content configuration information may be delivered to the mapping processor 250, and the mapping processor 250 requests the screen updater 270 to configure the screen and menu configuration accordingly, so that the screen autoconfiguration service is driven by the gateway 150. Through the learner terminal 110 can be implemented.

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. It should be noted that the embodiments disclosed in the present invention are not intended to limit the scope of the present invention and are not intended to limit the scope of the present invention. Therefore, the scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of the same shall be construed as being included in the scope of the present invention.

As described above, the embodiment of the present invention analyzes the learner's content usage pattern and the learning result, and maps the analysis result and the screen configuration information of the terminal device to be used in the learning to provide the learner with the learning screen optimized for performing the learning. It is a very useful invention that generates an effect that can improve the learning achievement of learners when performing online learning by configuring.

110: learner terminal
120: content provider
130: learning screen composition
200: automatic configuration of the learning screen
210: semantic DB storage unit
220: algorithm execution unit
230: learner screen generation unit
240: screen transmission unit
250: mapping processing unit
260: data update unit
270: screen update unit

Claims (10)

A learner terminal connected via a network;
A content providing unit providing content for learning to the learner terminal; And
Constructing a basic screen of the contents provided based on the terminal information of the learner terminal, and using the learning information of the learner using the learner terminal, priority learning content, learning order content for the contents provided as the basic screen Learning screen configuration unit configured to configure a learner screen by determining a recommendation item including at least one of a menu provision content and a characteristic value.
Automatic learning screen configuration system comprising a. A semantic DB storage unit configured to store screen configuration information on screens for each terminal and metadata about learning information for each learner;
An algorithm performer which performs a mining algorithm;
Call the classification algorithm of the mining algorithm based on the terminal information of the learner terminal and the screen configuration information corresponding thereto to configure a screen for the contents provided to the learner terminal, the learning for the learner using the learner terminal A learner screen generation unit configured to generate a learner screen for the screen configured by calling a correlation algorithm of the mining algorithm based on information and the metadata corresponding thereto; And
A screen transmitter configured to transmit the learner screen generated by the learner screen generator to the learner terminal;
Automatic learning screen device comprising a. The method of claim 2,
The learner screen generation unit,
The method may further include determining a recommendation item including at least one of priority learning content, learning order content, menu providing content, and characteristic values of the provided contents, and generating the learner screen based on the determined recommendation item. Screen autoconfiguration device. The method of claim 2,
Mapping processing unit for mapping the information necessary for the configuration of the learner screen according to the result of the mining algorithm
Automatic learning screen device, characterized in that it further comprises. The method of claim 2,
A data updater which generates metadata about the learner screen and updates the semantic DB storage based on the generated metadata
Automatic learning screen device, characterized in that it further comprises. The method of claim 2,
Screen update unit for detecting and updating the changes to the learner screen provided to the learner terminal
Automatic learning screen device, characterized in that it further comprises. In the cloud computing service providing apparatus for providing a learning screen to the learner terminal through a cloud computing environment,
A semantic DB storage unit configured to store screen configuration information on the screen for each type of the learner terminal and metadata about the learner-specific learning information;
Comprising a screen for the contents provided to the learner terminal based on the terminal information of the learner terminal and the screen configuration information corresponding to the learner terminal, the learning information for the learner using the learner terminal and the metadata corresponding thereto A learner screen generator configured to generate a learner screen for the screen based on the learner screen; And
A screen transmitter configured to transmit the learner screen generated by the learner screen generator to the learner terminal;
Cloud computing service providing apparatus comprising a. Constructing a screen for contents provided to the learner terminal by calling a classification algorithm of a mining algorithm based on the terminal information of the learner terminal and screen configuration information corresponding thereto;
Generating a learner screen for the screen configured by calling a correlation algorithm of the mining algorithm based on learning information about a learner using the learner terminal and corresponding metadata; And
Transmitting the generated learner screen to the learner terminal;
Automatic learning screen configuration method comprising a. The method of claim 8,
The learner screen generation step,
The method may further include determining a recommendation item including at least one of priority learning content, learning order content, menu providing content, and characteristic values of the provided contents, and generating the learner screen based on the determined recommendation item. How to auto configure screens. The method of claim 8,
Mapping information required to construct the learner's screen according to a result of performing the mining algorithm;
Learning screen automatic configuration method characterized in that it further comprises.

Images