KR102598698B1 - User-customizing learning service system - Google Patents

Abstract

The present invention relates to a user-customized learning service system, which includes a digital content creation module that digitizes problems written in existing paper or electronic documents and creates digital problems by assigning tags, and problems created in the digital content creation module. A problem database that stores classifications, a learning service platform server that provides problems stored in the problem database to the learner's terminal and receives the learner's problem-solving results, and a scoring system that grades the learner's problem-solving results and creates an incorrect answer note. It may include a module and a learner management module that manages the learner's learning achievement by accumulating and storing the scoring results of the scoring module.

Description

User customized learning service system {User-customizing learning service system}

The present invention relates to a user-tailored learning service system, and more specifically, to a system that can provide an optimized learning service to users for efficient learning.

The purpose of educational evaluation activities in teaching and learning is to maximize the effectiveness of student learning and teachers' teaching activities by providing maximum help to the teaching and learning process. In relation to educational evaluation, many studies have been conducted on incorrect answer notes. Based on students' self-evaluation of the achievement test results, the causes that cause incorrect answers in mathematics achievement tests are classified and their structure is analyzed, or the learner can directly solve the evaluation problems. You can create and supplement learning through in-depth and supplementary learning functions, enable repeated evaluation through the incorrect answer note function, and enable immediate feedback through analysis of the results of your own evaluation and learning statistics. Research has been conducted to construct it.

A platform that allows writing and using incorrect answer notes online has been researched and developed. In relation to this, the prior art, Korean Patent No. 10-1049896 (announced on July 19, 2011) and Korean Patent No. 10-1720270 ( (Notice on April 10, 2017), students who enter the study room of the learning operation server online are provided with homework problems and answers that match their learning progress according to the offline schedule, and the problem-solving results that students enter online Analyzes and provides incorrect answer notes, configures the problem-solving results to be analyzed and presented, sets a pass rate for each step of the review program consisting of multiple steps, receives the step performance results of the review program from the user terminal, and steps A configuration for adjusting the pass rate set in a step when the performance result is less than the set pass rate is disclosed.

However, in actual academies, instructors and faculty create many problems themselves and hand them out to students to solve, and encourage them to review again in case of incorrect answers. However, many students are aware of the effect of incorrect answer notes, but they say that it takes a lot of time. I do not write incorrect answer notes because of the points. In addition, academies need to figure out for each student which questions he or she got wrong, which classes he or she is taking, and what progress he or she is making. However, since this is all done offline, it is a huge waste of manpower and time to check this one by one.

Accordingly, there is a need for research and development of a platform that allows the academy to input self-created problems, check incorrect answers separately for each textbook, and provide feedback on the student's progress and academic achievement rate.

In addition, in the case of existing digital online learning, information on individual learners' scores and weak subjects and courses is fed back, but it is difficult to analyze why the subject or course is weak or why weak courses occur in many learners. There was a problem that it was difficult to provide practical help in learning weak courses.

The technical problem that the present invention aims to solve in consideration of the above problems is to provide a system that can improve learning achievement by digitizing various paper workbooks and providing them to learners, automatically generating incorrect answer notes and recommending problems according to achievement level. It is in

In addition, the present invention includes tags such as subject, type, and question style for each digitized problem, and automatically analyzes high-achieving subjects or courses and weak subjects or courses using tags when analyzing correct and incorrect answers. Another purpose is to provide a system that allows learners to recognize vulnerabilities.

In addition, another task of the present invention is to provide a system that can recommend and provide recommended problems for individual learners' weak subjects and specific courses in those subjects.

The present invention uses artificial intelligence to analyze learners' weak learning processes, establishes patterns of learners showing weaknesses in similar processes, and recommends common problems to learners with similar patterns. The purpose is to provide.

The present invention system for solving the above problems includes a digital content creation module that digitizes problems written in existing paper or electronic documents and creates digital problems by assigning tags, and problems created in the digital content creation module. A problem database for classifying and storing problems, a learning service platform server for providing problems stored in the problem database to a learner terminal and receiving the learner's problem solving results, and grading the learner's problem solving results and generating an incorrect answer note. It may include a scoring module and a learner management module that manages the learner's learning achievement by accumulating and storing the scoring results of the scoring module.

In an embodiment of the present invention, an interface providing module that provides a user interface including a writing area according to the type of test question displayed on the learner terminal may be further included.

In an embodiment of the present invention, the learner's achievement information stored in the learner management module is analyzed, weak courses are selected and guided, and learning advice is generated and provided to the learner terminal.

In an embodiment of the present invention, the digital content creation module converts the problems written in the electronic document into HTML or XML format, divides the problems converted into HTML or XML format into problem content, view content, and pictures, and After creating a tag including subject, type, and question style according to the content, you can create a digitized problem by merging the created tag and the divided problems.

In an embodiment of the present invention, the artificial intelligence learning recommendation module forms a pattern for learners' weak subjects and courses, normalizes the pattern to identify relationships between courses, and provides recommendation problems. In addition to the course, problems belonging to other courses related to the course of the weak subject above can also be provided.

The present invention has the effect of shortening the time required to create incorrect answer notes by providing digitized problems, automatically scoring them, and automatically generating incorrect answer notes.

In addition, the present invention applies tags to digitized problems and cumulatively stores the tags according to the scoring results, automatically classifying subjects and courses with a high learning achievement rate and subjects and courses with a weak learner, and providing feedback to the learner. This has the effect of enabling efficient learning.

In addition, the present invention has the effect of improving the achievement rate by providing new problems that match the learner's weak subjects and courses using accumulated tag information, thereby enabling intensive learning on weak subjects and courses.

In addition, the present invention uses artificial intelligence to analyze the reasons why learners show weak learning achievement rates in specific subjects and courses, establish patterns of learners showing weaknesses in the same subjects and courses, and recommend problems according to the patterns for learning. The effect can be increased.

1 is a block diagram of the user-customized learning service system of the present invention.
Figure 2 is a flowchart of the problem conversion process of the digital content production module.
3 is an example diagram of a user interface.
Figure 4 is an example of a screen explaining a learner's individual weak subjects and courses.

Hereinafter, the user customized learning service system of the present invention will be described in detail with reference to the attached drawings.

The embodiments of the present invention are provided to more completely explain the present invention to those skilled in the art, and the embodiments described below may be modified into various other forms, and the embodiments of the present invention may be modified. The scope is not limited to the examples below. Rather, these examples are provided to make the present invention more faithful and complete and to fully convey the spirit of the present invention to those skilled in the art.

The terms used herein are used to describe specific embodiments and are not intended to limit the invention. As used herein, the singular forms include the plural forms unless the context clearly indicates otherwise. Additionally, when used herein, “comprise” and/or “comprising” means specifying the presence of stated features, numbers, steps, operations, members, elements and/or groups thereof. and does not exclude the presence or addition of one or more other shapes, numbers, operations, members, elements and/or groups. As used herein, the term “and/or” includes any one and all combinations of one or more of the listed items.

Although terms such as first, second, etc. are used herein to describe various members, regions, and/or portions, it is obvious that these members, parts, regions, layers, and/or portions are not limited by these terms. . These terms do not imply any particular order, superiority or inferiority, or superiority or inferiority, and are used only to distinguish one member, region or portion from another member, region or portion. Accordingly, a first member, region or portion described below may refer to a second member, region or portion without departing from the teachings of the present invention.

Hereinafter, embodiments of the present invention will be described with reference to drawings schematically showing embodiments of the present invention. In the drawings, variations of the depicted shape may be expected, for example, depending on manufacturing techniques and/or tolerances. Accordingly, embodiments of the present invention should not be construed as being limited to the specific shape of the area shown in this specification, but should include, for example, changes in shape resulting from manufacturing.

1 is a block diagram of a user-customized learning service system according to a preferred embodiment of the present invention.

Referring to Figure 1, the user-tailored learning service system of the present invention includes a digital content creation module 30 that digitizes problems written in existing paper or electronic documents and creates digital problems by assigning tags, and the digital content creation module A problem database 60 that classifies and stores the problems created in (30), and a learning service platform server that provides the problems stored in the problem database 60 to the learner terminal 20 and receives the learner's problem solving results ( 10), a scoring module 50 that scores the learner's problem solving results and creates an incorrect answer note, and a learner management module 70 that manages the learner's learning achievement by accumulating and storing the scoring results of the scoring module. and an interface providing module 80 that provides a user interface of the learner terminal 20 on the platform.

In addition, an artificial intelligence learning recommendation module (40) that analyzes the learner's achievement information stored in the learner management module (70), selects and guides weak courses, generates learning advice, and provides it to the learner terminal (20). More may be included.

Hereinafter, the configuration and operation of the user-customized service system according to a preferred embodiment of the present invention configured as described above will be described in more detail.

First, the digital content production module 30 converts problems from known paper workbooks or problems recorded in electronic documents into digitized problems used in the present invention and stores them in the problem DB 60.

Figure 2 is a flowchart of the problem conversion process of the digital content production module 30.

Referring to Figure 2, problems recorded in electronic documents are converted into HTML or XML format.

This format conversion can be understood as converting the format so that it can be clearly viewed in the screen ratio of the learner terminal 20.

Problems printed in paper workbooks can be converted into electronic documents using physical scanning and text recognition technology. The format of the electronic document may be, for example, PDF format, or it may be another electronic document format such as HWP.

Problems or workbooks recorded in electronic documents are simply recorded text information, and can be converted to HTML format to more easily perform processing such as adding or editing information.

The present invention has the characteristic that, unlike e-book services that provide electronic document problem sets, each problem is converted into 'data'.

An example of converting an electronic document file into HTML format is the PDF to HTML technology, which converts a PDF file into HTML code.

Next, the problems converted to HTML code are divided into elements. The elements at this time may be problem content, example content, or picture (image).

Additionally, determine a tag for each problem.

Tags include the unit, type, topic, etc. to which the problem belongs.

Tags are determined using artificial intelligence to learn existing problems, units, types, and topic information, and automatically create tags according to the content of the problem.

At this time, the artificial intelligence process for tag creation is assumed to include a natural language recognition process.

Next, the problem and tags are combined to create digital content, which is stored in the problem DB 60.

Through this process, it is possible to provide a digitized workbook that can directly check and solve problems on the learner terminal 20, such as a tablet.

The learning service platform server 10 provides an environment in which the results of each module can be shared, as well as providing problems to the learner terminal 20 of the subscribed learner through a wired or wireless Internet network or a broadband communication network, and providing scoring results. It can provide generated incorrect answer notes and provide recommended problems for future study.

The learning service platform server 10 may provide problems stored in the problem DB 60 to the connected learner terminal 20.

At this time, the question DB 60 may be provided according to the number of questions set in the learner terminal 20, or may be provided according to the average number of questions for the test prepared by the learner.

In addition, when solving problems on the learner terminal 20, such as a tablet PC, a user interface similar to solving problems in an actual paper workbook can be provided.

This user interface is provided by the interface providing module 80.

For example, as shown in FIG. 3, when a solution process is required due to the nature of the problem, the interface providing module 80 provides a space where the user can write and check the content of the handwriting in addition to the problem display area on the left side of FIG. 3. By providing a solution area on the right, solving problems using a tablet PC can provide the same effect as solving an actual paper test paper.

Next, the learner terminal 20 provides the selected answer for each question selected by the learner to the learning service platform server 10, which is scored in the scoring module 50.

The scoring module 50 stores the correct answer information for the problems provided to the learner terminal 20, compares the correct answer information with the selected answer selected by the learner, and distinguishes correct answers from incorrect answers.

In addition, the scoring module 50 does not simply distinguish between correct and incorrect answers, but separates and stores the tags of correct and incorrect problems. In particular, for questions with incorrect answers, tags are stored cumulatively to obtain information about subjects or courses in which the learner is weak.

These scoring results are provided to the learner terminal 20 and are stored in the learner management module 70. The learner management module 70 stores learning achievement information for each learner.

In addition, the scoring module 50 extracts only the questions with incorrect answers from the scoring results, generates an incorrect answer note, and posts it on the learning service platform server 10, so that the incorrect answer note can be downloaded and checked from the learner terminal 20. do.

Therefore, since grading and creation of incorrect answer notes are possible immediately after solving the problem on the learner terminal 20, learners can reduce the time and effort of writing separate incorrect answer notes, and can conveniently learn while checking the incorrect answer notes. , can improve learning performance.

As one of the other features of the present invention, the artificial intelligence learning recommendation module 40 can learn the information stored in the learner management module 70 to suggest reasons why the learner is weak in a specific subject or process and ways to increase learning performance. there is.

The artificial intelligence learning recommendation module 40 learns the tag information of incorrect answers stored in the learner management module 70 and identifies weak subjects and courses (units).

Additionally, it is possible to check whether problems with the same tag information are repeatedly incorrect.

In addition, the artificial intelligence learning recommendation module 40 can determine whether the fingerprint of an incorrect answer is positive or negative and confirm the number of positive incorrect answers and the number of negative incorrect answers.

Through this process, it is possible to check whether the learner has read and understood the passage accurately and whether he or she has repeatedly submitted incorrect answers to the same type of problem.

The artificial intelligence learning recommendation module 40 can recommend problems regarding weak subjects and courses identified for the learner. In other words, the artificial intelligence learning recommendation module 40 searches and extracts problems corresponding to weak processes and types from the problem DB 60, uses the extracted problems as recommendation problems, and sends them to the learner terminal through the learning service platform server 10. It can be provided in (20).

Figure 4 is an example of a screen explaining a learner's weak subjects and courses (units).

Additionally, the artificial intelligence learning recommendation module 40 can generate and output learning advice to the learner. Study advice may include instructions to read the problem passage accurately or to use an error note when repeatedly submitting incorrect answers.

And the artificial intelligence learning recommendation module 40 can generate vulnerable course patterns for multiple learners.

For example, if a learner named A is judged to be the weakest among courses a to d in a specific subject, and course d is the next weakest, learner A's pattern can be defined as a-d-b,c.

By expanding this definition of learner patterns to a large number of learners, patterns in which learners are commonly weak can be defined.

For example, pattern analysis can be performed to show that learners who are weak in course a are also weak in course d, and course b follows a pattern of high learning achievement.

Through this pattern analysis, it is possible to determine the relationship between course a and course d, and it is possible to identify relationships such as how the learning achievement of course a becomes weak due to the lack of learning achievement of course d.

Therefore, if it is determined from the scoring results of the scoring module 50 that a new learner is weak in course a, the artificial intelligence learning recommendation module 40 recommends not only the problem of course a but also the problem of course d as a recommendation problem for the new learner. It can also be provided as a recommended problem.

In this way, in order to improve the learning achievement of the weak course, the present invention can improve the learner's learning achievement more quickly by solving problems of other courses related to the weak course and encouraging learning.

It is obvious to those skilled in the art that the present invention is not limited to the above-mentioned embodiments and can be implemented with various modifications and variations without departing from the technical gist of the present invention. will be.

10: Learning service platform server 20: Learner terminal
30: Digital content production module 40: Artificial intelligence learning recommendation module
50: Scoring module 60: Problem database
70: Learner management module 80: User interface provision module

Claims (5)

Convert the problems written on existing paper into electronic documents or problems written in the produced electronic documents into HTML or XML format, divide the problems converted into HTML or XML format into problem content, example content, and pictures, and A digital content production module that generates tags including subjects, types, and question styles according to content, and then merges the generated tags with the divided problems to create digitized problems;
a problem database that classifies and stores problems created in the digital content production module;
A learning service platform server that provides problems stored in the problem database to the learner terminal and receives the learner's problem solving results;
A scoring module that scores the learner's problem solving results and creates an incorrect answer note;
an interface providing module that provides a user interface including a writing area according to the type of test question displayed on the learner terminal; and
A system including a learner management module that manages the learner's learning achievement by accumulating and storing the scoring results of the scoring module. delete According to paragraph 1,
The system further includes an artificial intelligence learning recommendation module that analyzes the learner's achievement information stored in the learner management module, selects and guides weak courses, generates learning advice, and provides it to the learner terminal. delete According to paragraph 3,
The artificial intelligence learning recommendation module is,
Forming patterns for learners’ weak subjects and courses,
Normalize the above patterns to identify relationships between processes,
When providing recommended problems, a system that provides problems from other courses related to the weak subject course in addition to the weak subject course.

Images