KR101629084B1 - Apparatus and method for determining study plan for user - Google Patents

Abstract

An apparatus and method for determining a learning prescription for a user is disclosed.
A method of determining a learning prescription for a user includes collecting user's interval behavior information and user's interval learning performance information for each section of the learning video content; Grouping the users by matching the section behavior information and the learning performance information with the attribute information of the user; Analyzing the section behavior information, the user attribute information, and the learning performance information for each user cluster; And determining a learning prescription for a user included in the user community based on the analysis result of each user community.

Description

[0001] APPARATUS AND METHOD FOR DETERMINING STUDY PLAN FOR USER [0002]

The present invention relates to an apparatus and method for determining a learning prescription for a user, and more particularly, to an apparatus and method for determining a learning prescription for a user's learning according to a learning behavior of a user who watches video content for learning.

With the development of IT technology, user learning system using video contents for learning is expanding.

However, since the contents of learning video contents do not change according to the learning ability of the user, the user learning system using the learning video contents is difficult to optimize the learning for the user.

Also, unlike offline lectures by the educator who teaches the user's learning, the video content for learning can be repeatedly reproduced according to the user's intention. Therefore, the user can repeatedly reproduce a section that is difficult to understand or a section of high interest.

However, since the user learning system using the conventional learning video contents simply provides the learning video contents to the user, it provides the optimized learning to the user in consideration of the section that the user can not understand or the section in which the user's interest is high I could not.

Therefore, there is a demand for a method of providing learning optimized for a user using video contents for learning.
[Prior Art]
Published Patent No. 2008-0082070
Published Patent No. 2007-0068083

The present invention can provide an apparatus and a method for providing a learning prescription optimized for a user's interest and understanding ability to a user by analyzing a behavior of a user for each section of the learning video content and determining a learning prescription for the user.

In addition, the present invention provides a device for providing a user with a learning video content optimized for the user's interest and understanding ability by analyzing the behavior of the user for each section of the learning video content and correcting or deleting the content and difficulty of the learning video content And methods.

Also, the present invention generates user clusters by grouping the section behavior information and learning performance information matched with the attribute information of the user, and performs data mining of the section behavior information and the learning performance information matched with the attribute information of the user for each user cluster, It is possible to provide an apparatus and a method for predicting the cause of the gradation of the user and the grades of the user, thereby determining the optimum learning prescription for the user.

According to an embodiment of the present invention, there is provided a method of determining a learning prescription for a user, the method comprising: collecting interval behavior information of a user and interval learning performance information of a user for each interval of a learning video content; Grouping the users by matching the section behavior information and the learning performance information with the attribute information of the user; Analyzing the section behavior information, the user attribute information, and the learning performance information for each user cluster; And determining a learning prescription for a user included in the user community based on the analysis result of each user community.

The segment of the learning video content of the learning prescription decision method for the user according to the embodiment of the present invention can be classified according to the learning content and the learning method included in the design information of the learning video content.

The interval behavior information of the learning prescription decision method for the user according to an embodiment of the present invention includes at least one of the number of times the user repeatedly reproduces the section of the learning video content, the position where the user stopped at the section of the learning video content, One can be included.

The attribute information of the user of the learning prescription decision method for the user according to an embodiment of the present invention includes at least one of the identification information of the user, the cumulative score of the user, the goal of the user, the personality of the user, .

The step of analyzing the learning prescription decision method for the user according to an embodiment of the present invention analyzes the interval behavior information, the attribute information of the user, and the learning performance information to determine whether the user's performance included in the learning performance information The cause can be judged.

The step of determining a learning prescription of a learning prescription decision method for a user according to an embodiment of the present invention may include determining a learning prescription of a user based on a preferred learning strategy of the users included in the user community, A corresponding support strategy, or a facilitation strategy may be determined and provided to educators who guide the user's learning.

The step of determining the learning prescription of the learning prescription decision method for the user according to the embodiment of the present invention can determine the guidelines of the learning video contents to be provided to the user included in the user community based on the cause of the performance .

The analyzing of the learning prescription decision method for the user according to an embodiment of the present invention may determine a prediction model for predicting the learning performance information by the section behavior information and the attribute information of the user for each user community.

The step of determining the learning prescription of the learning prescription decision method for the user according to an embodiment of the present invention includes comparing the average behavior information of the other users included in the user community with the interval behavior information, And provide at least one of the expected scores to the user.

An apparatus for determining a learning prescription for a user according to an exemplary embodiment of the present invention includes an information collection unit for collecting user's interval behavior information and interval learning performance information for each section of the learning video contents; A clustering unit for clustering users by matching the section behavior information and the learning performance information with attribute information of a user; An analysis unit for analyzing the section behavior information, the attribute information of the user, and the learning performance information for each user community; And a learning prescription deciding unit for deciding a learning prescription for a user included in the user community based on the analysis result of each user community.

The segment of the learning video content of the learning prescription decision device for the user according to an embodiment of the present invention can be classified according to the learning content and the learning method included in the design information of the learning video content.

The apparatus for determining a learning prescription for a user according to an exemplary embodiment of the present invention is characterized in that the section behavior information includes at least one of a number of times the user repeatedly reproduces the section of the learning video content, a position where the user stops at the section of the learning video content, One can be included.

The attribute information of the user of the learning prescription decision device for the user according to an embodiment of the present invention includes at least one of the identification information of the user, the cumulative score of the user, the goal of the user, the personality of the user, .

According to an embodiment of the present invention, the cluster-specific analysis unit of the learning prescription deciding apparatus analyzes the interval behavior information, the attribute information of the user, and the learning performance information to determine whether the user's performance included in the learning performance information The cause can be judged.

The learning and prescribing decision unit of the learning prescription deciding apparatus for a user according to an embodiment of the present invention may include a learning strategy of the users included in the user community based on the cause of the performance and a support corresponding to the preferred learning strategy Strategy, or facilitation strategy to provide educators who guide the user's learning.

In the apparatus for determining a learning prescription for a user according to an embodiment of the present invention, the learning prescription deciding unit may determine a guideline of learning video contents to be provided to a user included in the user community based on the cause of the performance.

According to an embodiment of the present invention, a cluster-specific analysis unit for a user may determine a prediction model for predicting the learning performance information using the interval behavior information and user attribute information for each user cluster.

The learning prescription deciding unit of the learning prescription deciding apparatus for the user according to an embodiment of the present invention may include a comparison result between the average behavior information of other users included in the user community and the section behavior information and the prediction result of the user according to the prediction model At least one can be provided to the user.

The present invention can provide a user with a learning prescription optimized for the user's interest and understanding ability by analyzing the behavior of the user for each section of the learning video content and determining the learning prescription for the user.

The present invention analyzes the behavior of a user for each section of the learning video content and corrects or eliminates the content and difficulty of the learning video content to provide the user with the video content optimized for the user's interest and understanding ability have.

Also, the present invention generates user clusters by grouping the section behavior information and learning performance information matched with the attribute information of the user, and performs data mining of the section behavior information and the learning performance information matched with the attribute information of the user for each user cluster, It is possible to determine the optimum learning prescription for the user by predicting the cause of the performance of the user and the result of the user.

FIG. 1 is a diagram illustrating a device for determining a learning prescription for a user according to an embodiment of the present invention. Referring to FIG.
2 is an example of information collected by the apparatus for determining a learning prescription for a user according to an embodiment of the present invention.
FIG. 3 is an example of analysis by cluster according to an embodiment of the present invention.
4 is an example of a prediction model in an embodiment of the present invention.
5 is an example of a learning prescription determined by a learning prescription deciding apparatus for a user according to an embodiment of the present invention.
6 is a flowchart illustrating a method of determining a learning prescription for a user according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. A method for determining a learning prescription for a user according to an embodiment of the present invention may be performed by a learning prescription deciding apparatus for a user.

FIG. 1 is a diagram illustrating a device for determining a learning prescription for a user according to an embodiment of the present invention. Referring to FIG.

Referring to FIG. 1, an apparatus 100 for determining a learning prescription for a user according to an embodiment of the present invention includes an information collecting unit 110, a clustering unit 120, a cluster-specific analyzing unit 130, (140). ≪ / RTI >

The information collecting unit 110 may collect user's interval behavior information and user's interval learning performance information for each section of the learning video content.

At this time, the segment of the learning video content may be classified according to the learning contents and the learning strategy included in the design information of the learning video content. In this case, the learning contents may include at least one of a concept to be taught to the user by the learning video contents, an application method of the concept, and contents that can induce the user's interest. In addition, the learning strategy may include at least one of examples of learning contents, problem solving of learning contents, lecture of learning contents, storytelling of learning contents, and practice of learning contents.

For example, the learning video content may provide the first concept to the user from the first time to the second time, and may provide the user with a second concept that is different from the first concept from the second time to the third time.

At this time, the information collecting unit 110 divides the learning video contents to be played back from the first time to the second time into the first section of the training video content, and stores the training video content, which is played from the second time to the third time, And a second section of the content. That is, the information collecting unit 110 can divide the duration of the moving picture based on the time at which the learning contents provided to the user by the learning moving picture contents are changed.

In addition, although the learning video contents provide the same concept from the first time to the third time, the concept of the learning video content is provided to the user from the first time to the second time, By the time, the user can present the problem and solve the problem related to the concept. At this time, the second time may be the time between the first time and the third time.

At this time, the information collecting unit 110 divides the learning video contents to be played back from the first time to the second time into the first section of the training video content, and stores the training video content, which is played from the second time to the third time, And a second section of the content. That is, in the case where the learning strategy of the learning video content is changed even if the learning content provided by the learning video content is the same, the information collecting unit 110 acquires, .

In addition, the section behavior information may include at least one of the number of times the user repeatedly reproduces the section of the learning moving image content, the position where the user stops the section of the learning moving image content, and the number of times the user stops.

At this time, the information collecting unit 110 may measure at least one of the number of times the user repeatedly reproduces the section of the learning video content, the position where the user stops at the section of the learning video content, have. For example, the information collecting unit 110 may measure the user's actions related to Play, Pause, and Replay of the moving picture learning contents.

The information collecting unit 110 may store the measurement result as the interval behavior information of the user. For example, the interval behavior information may be behavioral variables recorded in log file format.

In addition, the information collecting unit 110 may collect the user's scores, the quiz answer results, and the satisfaction questionnaire for each section of the learning video contents. The information collecting unit 110 may store the collection result as the interval learning performance information of the user. For example, the user's section learning performance information includes a performance variable including at least one of a user's score for each section of the learning video content, a quiz response result for each section of the learning video content, variables.

The clustering unit 120 may clusters users by matching the section activity information and the learning performance information collected by the information collection unit 110 with the attribute information of the user. At this time, the clustering unit 120 clusters users to create a user cluster including at least one user.

The attribute information of the user may include at least one of the identification information of the user, the cumulative score of the user, the goal of the user, the personality of the user, and the age and sex of the user. For example, the attribute information of the user may be attribute variables including at least one of the user's personal ID, gender, cumulative grade, and age.

The clustering unit 120 may select a cluster analysis technique to be used for clustering users among various cluster analysis techniques. Specifically, the clustering unit 120 can group users by various clustering analysis techniques to generate user clusters by cluster analysis. The cluster analysis unit 130 analyzes the user cluster according to the cluster analysis and extracts the best cluster analysis technique with the optimal cluster analysis technique. Then, the clustering unit 120 can cluster the users using an optimal cluster analysis technique.

The cluster analysis unit 130 may analyze the segment behavior information, the user attribute information, and the learning performance information for each user cluster generated by the clustering unit 120.

The cluster-specific analysis unit 130 can determine the cause of the user's performance included in the user's learning performance information by data mining the user's interval behavior information, the user's attribute information, and the user's learning performance information.

The prediction model for predicting the learning performance information of the user may be changed according to the user characteristics such as the user's interval behavior information, the user's attribute information, and the user's learning performance information. In addition, it is necessary to predict the learning performance information of the user in order to determine the learning prescription optimized for the user.

Accordingly, the cluster-specific analysis unit 130 can determine a prediction model for predicting the user's learning performance information on user's segment behavior information and user attribute information for each user cluster.

In this case, the cluster analysis unit 130 can determine the prediction model by applying the parametric and nonparametric statistical methods according to whether or not the parametric statistical assumptions such as normality are satisfied.

The learning and prescription decision unit 140 can determine the learning prescription for the user included in the user community based on the analysis result analyzed by the community analysis unit 130 for each user community.

At this time, the learning and prescribing decision unit 140 may determine the cause of the user's performance determined by the cluster-specific analysis unit 130 and the user's expected score according to the prediction model determined by the analysis unit 130 for each cluster, The user can determine the learning prescription for the users included in the community.

Then, the learning prescription deciding unit 140 can provide the strategy and information corresponding to the determined learning prescription to at least one of the user, the parents of the user, the educator who guides the learning of the user, and the producer who produces the learning video content have.

At this time, the learning and prescribing decision unit 140 may determine the cause of the user's performance determined by the cluster-specific analysis unit 130 and the user's expected score according to the prediction model determined by the analysis unit 130 for each cluster, The user may determine a preferred learning strategy included in the community and a support strategy or promotion strategy corresponding to the preferred learning strategy and provide the instruction to the educator who guides the user's learning.

For example, the learning and prescribing decision unit 140 can determine the learning strategies preferred by the users according to the learning strategy of the user with the highest expected score according to the prediction model determined by the cluster-specific analysis unit 130. If the learning strategy is set for each cause of the user's performance, the learning and prescription decision unit 140 can determine the learning strategy set for the cause of the user's grade determined by the community-based analysis unit 130.

At this time, the learning strategy is a strategy for determining how the user learns, and the support strategy may be a strategy for deciding how to support the user who learns according to the learning strategy. In addition, facilitation strategies can be strategies that encourage educators to engage learners. For example, a learning strategy may include at least one of a type of lecture of a concept to be taught to a user, a description type of a concept to be learned by the user, and a problem solving type related to a concept to be learned by the user have. In addition, the support strategy may include a parent report, and the facilitation strategy may include at least one of an interview between the educator and the user, or an encouraging email the educator sends to the user. Therefore, if the support strategy is a parent report, the educator can request a report from the user's parent.

In addition, the learning and prescribing decision unit 140 may determine the cause of the user's performance determined by the cluster-specific analysis unit 130 and the predicted user's performance according to the prediction model determined by the analysis unit 130 for each cluster, A guideline of the learning video content to be provided to the user included in the community can be determined and provided to the producer who produces the learning video content.

For example, if the cause of the user determined by the cluster-specific analysis unit 130 is 'having prior knowledge of the user', or if the predicted result of the user according to the prediction model determined by the cluster- The user may have a low learning need for the corresponding section of the video content. Therefore, the learning and prescribing decision unit 140 can minimize the time wasted by the user by explaining the concept that the user knows, by determining the guideline of the learning video content to be provided to the user as "minimum information ".

On the other hand, if the cause of the user's performance determined by the cluster-specific analysis unit 130 is 'lack of basic academic ability', or if the predicted score of the user according to the prediction model determined by the cluster-specific analysis unit 130 is lower than the threshold value, The necessity of learning the relevant section of the video contents may be high. Accordingly, the learning and prescription decision unit 140 can determine the guideline of the learning video content to be provided to the user as "basic learning content and practice problem addition ", allowing the user to easily learn the concept of the corresponding section.

That is, the learning prescription deciding apparatus 100 for a user analyzes the behavior of the user for each section of the learning video content and corrects or eliminates the content and difficulty of the learning video content, Video content can be provided to the user.

The learning and prescription decision unit 140 determines at least one of the comparison result between the average behavior information of other users included in the user community and the user's interval behavior information and the prediction result of the user according to the prediction model determined by the community- One can be provided to the user.

For example, the learning prescription deciding unit 140 may visualize the user's expected score and provide the user with the expected score, thereby allowing the user to recognize to what extent the user is performing compared with other users similar to him / her. In addition, the learning and prescription decision unit 140 compares the learning behavior of the user with the average behavior of other users included in the user community, and provides the comparison result to the user along with the expected performance, Can be recognized.

That is, the learning and prescribing decision unit 140 compares the user's performance and behavior with other users having a similar tendency so that the user can recognize a necessary part of his / her behavior and prompt the user to promote self-directed learning can do.

In addition, when the user is a minor learner with less self-directed learning ability, the learning and prescribing decision unit 140 also feeds the comparison results and the user's expected scores to the user's parents so that the parents take necessary measures for learning the user .

The learning and prescribing decision unit 140 may provide the user group classified according to the grade and the cause of the user's grade included in the user group having the grades below the threshold to the operation manager such as the school and the institute. At this time, the learning and prescribing decision unit 140 can help the operating manager to select a criterion for student selection by providing the operating clusters classified according to the grades. The learning and prescribing decision unit 140 also provides the operation manager with the cause of the user's grades included in the user community whose grades are less than or equal to the threshold value, thereby helping the operating manager to determine how to support the users with low grades .

The learning prescription deciding apparatus 100 for a user analyzes a behavior of a user for each section of the learning video contents and determines a learning prescription for the user so that a learning prescription optimized for the user's interest and understanding ability can be provided to the user have.

In addition, the learning prescription deciding apparatus 100 for a user generates user clusters by clustering the section behavior information and the learning performance information matched with the user's attribute information, and generates section activity information, which is matched with the attribute information of the user, The learning result information can be data mined to predict the cause of the user's performance and the user's performance, so that the optimum learning prescription can be determined for the user.

2 is an example of information collected by the apparatus for determining a learning prescription for a user according to an embodiment of the present invention.

Learning video content can be made to achieve learning goals unlike video content for entertainment such as movies and dramas. Therefore, the learning video contents can be developed so that the selected learning contents, learning strategies and evaluation tools are linked with each other to achieve the learning goals.

That is, as shown in FIG. 2, at least one of the learning content and the learning strategy may be different for each predetermined section of the learning video content. Accordingly, the learning prescription deciding apparatus 100 for a user can divide the learning video contents into a plurality of sections based on learning contents and learning strategies included in the design information. 2, the learning prescription deciding apparatus 100 collects user's behavior information and learning performance information for each section of the learning video contents, thereby enabling the user to learn the learning contents and the learning strategy The learning result can be determined.

At this time, the learning prescription deciding apparatus 100 for a user divides the user's behavior into sections of the learning video contents for reproduction, stop, and repeated reproduction and records them as behavioral variables in the form of a log file, A viewing frequency per section such as a bar, and a viewing time. In addition, the learning prescription deciding apparatus 100 for a user can collect performance variables such as grades, quiz answer results, satisfaction questionnaires, etc. for each section of the learning video contents. Then, the learning prescription deciding apparatus 100 for a user constructs statistical analysis data by combining attribute variables such as personal ID, sex, cumulative grade, and age with action variables and performance variables, And the learning result.

For example, in the case of the interval 1 of FIG. 2, since the user has repeatedly watched the interval 1, the learning prescription deciding apparatus 100 for the user has difficulty understanding the concept 1 that the user learns in the interval 1, .

Since the user's score is higher in the interval 1, the learning and decision-making apparatus 100 for the user can determine that the learning strategy of the interval 1 is effective for the user. However, since the satisfaction level of the user is low in the interval 1, the learning prescription deciding apparatus 100 for the user can determine that the learning strategy of the interval 1 is effective for the user but is not the method preferred by the user.

Accordingly, the learning prescription deciding apparatus 100 for the user can change the learning strategy of the section, and can determine the learning prescription preferred by the user while the learning effect is high.

In addition, the learning prescription deciding apparatus 100 for a user groups clusters based on the demographic and past scores of the user in relation to the attributes of the user, so that the user can select the clusters having similar sex, age, personality, It is possible to determine the degree of the level among the users and to provide it to the user so as to increase the learning desire of the user.

FIG. 3 is an example of analysis by cluster according to an embodiment of the present invention.

As shown in FIG. 3, the cluster-by-cluster analyzing unit 130 of the learning prescription deciding apparatus 100 for a user may be provided with information such as interval learning performance information such as a grade, interval behavior information such as viewing time, The first user community 310 and the second user community 320 may be created by clustering similar users.

The cluster analysis unit 130 may analyze the first user cluster 310 and the second user cluster 320, respectively. In this case, the cluster-specific analysis unit 130 may include a cause model of a user's performance of the users included in the first user community 310, a prediction model for predicting the users' expected performance included in the first user community 310, A prediction model for predicting the cause of the user's performance of the users included in the user community 320 and the prediction results of the users included in the second user community 320 may be determined.

4 is an example of a prediction model according to an embodiment of the present invention.

The grouping analysis unit 130 of the learning prescription deciding apparatus 100 for a user uses a behavior variable and an attribute variable X such as a viewing time and a viewing frequency for each user group to calculate a performance variable Y) can be determined. 4, the circles having the black circles and hatching are users included in different user communities. The analysis unit 130 according to the clusters includes a prediction model corresponding to the users indicated by black circles in FIG. 4, In FIG. 4, prediction models corresponding to users indicated by hatching circles can be respectively determined.

For example, the cluster-by-cluster analyzing unit 130 determines the prediction capability of the prediction model by comparing the prediction result with the prediction performance model and the interval learning performance information collected by the information collection unit 110, The prediction model can be determined as a prediction model of the corresponding section.

5 is an example of a learning prescription determined by a learning prescription deciding apparatus for a user according to an embodiment of the present invention.

The learning prescription deciding unit 140 of the learning prescription deciding apparatus 100 for the user can determine the learning prescription for the user on the basis of the cause of the user's performance analyzed by the clustering analysis unit 130. [

For example, when the user's score is high and the user's viewing frequency is high in the interval, the cluster-specific analyzing unit 130 repeatedly watches the user, It can be judged that the design of the content is appropriate enough for the ability to be excellent and the user's score to be improved. At this time, the cluster-specific analysis unit 130 can determine the cause of the user's performance as the A type. At this time, the type A may mean that the user's performance is improved by the learning video contents. Therefore, the learning prescription corresponding to the type A may consistently stir up the learning motivation of the user.

Next, when the cause of the user's performance in the interval is Type A, the learning and prescription decision unit 140 determines a learning prescription corresponding to the type A as shown in FIG. 5 and instructs the learning of the user and the user Educators, and producers who produce video content for learning.

In addition, when the user's score is high in the interval and the user's viewing frequency is low, the cluster-specific analyzing unit 130 has a high score even though the user does not repeatedly watch the interval. Therefore, Or it can be judged that the design of the content is excellent enough to improve the user's score with a small number of times of repeated viewing. At this time, the cluster-specific analysis unit 130 can determine the cause of the user's performance as the B type. In this case, the type B may mean that the user has sufficiently learned the contents of the corresponding section. Therefore, the learning prescription corresponding to the B type may be to change the contents to be the learning target.

Next, when the cause of the user's performance in the interval is the B type, the learning and prescription deciding unit 140 decides the learning prescription corresponding to the B type as shown in Fig. 5 and instructs the learning of the user and the user Educators, and producers who produce video content for learning. At this time, the educator or the producer can change the user of the section or the user to provide the section, so that the user can provide other learning contents necessary for the user.

When the user's score is low and the user's viewing frequency is high in the interval, the cluster-specific analyzing unit 130 has a low score even though the user repeatedly watches the interval. Therefore, even if the user repeatedly watches the interval, , Or the design of the content may be judged to be inadequate enough that the user can not learn sufficiently. At this time, the cluster-specific analysis unit 130 can determine the cause of the user's performance as the C type. At this time, the C type may mean that the user's performance is not improved by the learning video contents. Therefore, the learning prescription corresponding to the C type may be to enhance the user's score by learning the supplementary data for the corresponding section.

Next, when the cause of the user's performance in the section is the C type, the learning and prescribing decision unit 140 determines the learning prescription corresponding to the C type as shown in Fig. 5 and instructs the learning of the user and the user Educators, and producers who produce video content for learning. At this time, the educator can learn supplementary materials to the user according to the learning prescription, and the creator can add supplementary materials to the learning video contents according to the learning prescription.

In addition, when the user's score is low and the user's viewing frequency is low in the interval, the cluster-specific analyzing unit 130 does not view the interval and the score is low, so that the user repeatedly watches the interval , It can be judged that the interest in learning is degraded or the contents of the corresponding section are not valid. At this time, the cluster-specific analysis unit 130 can determine the cause of the user's score as the D type. At this time, the D type may mean that the user's performance is not improved by the learning video contents while the user can not induce the user to watch the corresponding section. Therefore, the learning prescription corresponding to the D type may minimize the waste of the user by examining deletion of the corresponding section.

Next, in the case where the cause of the user's performance in the interval is type D, the learning and prescription decision unit 140 determines a learning prescription corresponding to the type D as shown in FIG. 5 and instructs the learning of the user and the user Educators, and producers who produce video content for learning. At this time, the educator can review whether or not the section is deleted, and allow the author to delete the section from the learning video content according to the review result.

6 is a flowchart illustrating a method of determining a learning prescription for a user according to an embodiment of the present invention.

In operation 610, the information collecting unit 110 may collect the section behavior information of the user and the interval learning performance information of the user for each section of the learning video contents.

At this time, the information collecting unit 110 may measure the user's actions related to Play, Pause, and Replay of the moving learning content and store the user's activity information. In addition, the information collection unit 110 may collect the user's scores, quiz answer results, and satisfaction questionnaires for each section of the learning video contents, and store the collected results as user's section learning performance information.

In step 620, the clustering unit 120 may group the users by matching the section behavior information and the learning performance information collected in step 610 with the attribute information of the user. At this time, the clustering unit 120 clusters users to create a user community including at least one user.

In step 630, the cluster-specific analysis unit 130 may analyze the interval behavior information, the attribute information of the user, and the learning performance information for each user cluster generated in step 620. At this time, the cluster-specific analysis unit 130 may determine the cause of the user's performance included in the user's learning performance information by data mining the user's interval behavior information, the user's attribute information, and the user's learning performance information.

In addition, the cluster-specific analysis unit 130 may determine a prediction model for predicting the learning performance information of the user based on the user's interval behavior information and the user's property information for each user cluster generated in step 620.

In step 640, the learning and prescription decision unit 140 may determine a learning prescription for the user included in the user community based on the analysis result analyzed for each user community in step 630. [

At this time, the learning and prescription decision unit 140 determines whether the user included in the user community is included in the user community based on at least one of the cause of the user's performance determined in step 630 and the expected performance of the user based on the prediction model determined in step 630 You can decide on the prescription of the study.

Then, the learning prescription deciding unit 140 can provide the strategy and information corresponding to the determined learning prescription to at least one of the user, the parents of the user, the educator who guides the learning of the user, and the producer who produces the learning video content have.

The present invention can provide a user with a learning prescription optimized for the user's interest and understanding ability by analyzing the behavior of the user for each section of the learning video content and determining the learning prescription for the user.

In addition, the present invention analyzes the behavior of the user for each section of the learning video content and corrects or eliminates the content and difficulty of the learning video content to provide the user with the video content optimized for the user's interest and understanding ability have.

The present invention creates user clusters by grouping the section behavior information and the learning performance information matched with the attribute information of the user, and performs data mining on the section behavior information and the learning performance information matched with the attribute information of the user for each user cluster, It is possible to determine the optimum learning prescription for the user by predicting the cause of the performance of the user and the result of the user.

While the invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. This is possible.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined by the equivalents of the claims, as well as the claims.

100: a learning prescription decision device for the user
110: Information collecting unit
120: Clustering part
130: Analysis by cluster
140:

Claims (18)

A method of determining a learning prescription for a user performed by a learning prescription deciding apparatus for a user including an information collecting unit, a clustering unit, a cluster-specific analyzing unit, and a learning prescription deciding unit,
Collecting section activity information of a user and section learning performance information of a user for each section of learning video contents;
Clustering the users by matching the section behavior information and the learning performance information with the attribute information of the user;
Analyzing the section behavior information, the attribute information of the user, and the learning performance information for each user community; And
A step of determining a learning prescription for a user included in a user community based on an analysis result of each user community,
Lt; / RTI >
Wherein the section of the learning video content comprises:
Learning contents including at least one of the concepts to be taught to the user by the learning video contents, the application methods of the concepts, and contents that can cause the user's interest, or examples of the learning contents, A story of learning contents, and an exercise of learning contents,
Wherein the analyzing comprises:
And analyzing a user's score included in the learning frequency information and the learning performance information included in the interval behavior information to determine a cause of the user's performance. delete The method according to claim 1,
The section behavior information includes:
The number of times the user repeatedly reproduces the section of the learning video content, the position at which the user stops at the section of the learning video content, and the number of times the user stops. The method according to claim 1,
The attribute information of the user,
A method for determining a learning prescription for a user including at least one of a user's identification information, a cumulative score of a user, a goal of a user, a personality of a user, and an age and sex of a user. delete The method according to claim 1,
Wherein the step of determining the learning prescription comprises:
Wherein the learning and prescription decision unit determines a learning strategy preferred by the users included in the user community and a support strategy corresponding to the preferred learning strategy or an acceleration strategy based on the cause of the performance, To determine the learning prescription for the user. The method according to claim 1,
Wherein the step of determining the learning prescription comprises:
Wherein the learning prescription decision unit determines a guideline of the learning video contents to be provided to the user included in the user community based on the cause of the performance. The method according to claim 1,
Wherein the analyzing comprises:
And determining a prediction model for predicting the learning performance information from the section behavior information and the user attribute information for each user community by the cluster-by-analysis unit. 9. The method of claim 8,
Wherein the step of determining the learning prescription comprises:
Wherein the learning prescription decision unit provides the user with at least one of a comparison result between the average behavior information of other users included in the user community and the interval behavior information and an expected result of the user according to the prediction model. An information collecting unit for collecting user's interval behavior information and interval learning performance information of a user for each section of the learning video contents;
A clustering unit for clustering users by matching the section behavior information and the learning performance information with attribute information of a user;
An analysis unit for analyzing the section behavior information, the attribute information of the user, and the learning performance information for each user community; And
A learning prescription deciding unit for deciding a learning prescription for a user included in the user community based on the analysis result of each user community,
Lt; / RTI >
Wherein the section of the learning video content comprises:
Learning contents including at least one of the concepts to be taught to the user by the learning video contents, the application methods of the concepts, and contents that can cause the user's interest, or examples of the learning contents, A story of learning contents, and an exercise of learning contents,
The cluster-
And determining a cause of the user's performance by analyzing the user's viewing frequency included in the section behavior information and the user's performance included in the learning performance information. delete 11. The method of claim 10,
The section behavior information includes:
The number of times the user repeatedly reproduces the section of the learning video content, the position at which the user stops at the section of the learning video content, and the number of times the user stops. 11. The method of claim 10,
The attribute information of the user,
A user's identification information, a cumulative score of a user, a goal of a user, a personality of a user, an age and a gender of a user. delete 11. The method of claim 10,
Wherein the learning /
A user who determines a learning strategy preferred by the users included in the user community and a support strategy corresponding to the preferred learning strategy or an acceleration strategy based on the cause of the performance, A decision - making device for learning. 11. The method of claim 10,
Wherein the learning /
And determines a guide line of the learning video contents to be provided to the user included in the user community based on the cause of the performance. 11. The method of claim 10,
The cluster-
And determining a prediction model for predicting the learning performance information from the section behavior information and the user attribute information for each user cluster. 18. The method of claim 17,
Wherein the learning /
And provides at least one of a comparison result between the average behavior information of other users included in the user community and the section behavior information and an expected result of the user according to the prediction model to the user.

Images