KR20220142850A - Learning path recommendation system based on user characteristics and content analysis - Google Patents

Abstract

A learning path recommendation system based on user characteristics and content analysis comprises: a user analysis module which analyzes user metadata including a user's current level, target level, competency evaluation result, desired learning speed, and field of interest; a learning content analysis module which analyzes learning content metadata including job category, level, required status, instructor, related lecture, and required time information until completion; and a learning path design module which recommends a combination of a plurality of learning content to a user based on the analyzed learning content metadata according to the user metadata.

Description

{LEARNING PATH RECOMMENDATION SYSTEM BASED ON USER CHARACTERISTICS AND CONTENT ANALYSIS}

The present disclosure relates to a system for recommending a learning path through user characteristic analysis, and more particularly, to a system for recommending a learning path optimized according to a user's learning achievement and ability for music-related career education.

Unless otherwise indicated herein, the material described in this section is not prior art to the claims of this application, and inclusion in this section is not an admission that it is prior art.

The recommendation system is a type of information filtering (IF) technology, and recommends information that may be of interest to a specific user. Recommendation systems generally create a list of recommendations through collaborative filtering and content-based filtering (also called personality-based approach). Collaborative filtering techniques include recommending links to people on social bookmarking sites and recommending movies from the MovieLens dataset. Recommendation systems are useful alternatives to search algorithms. Because it allows users to discover things that they couldn't find in other ways. Interestingly enough, recommender systems are often implemented when using search engines by indexing non-traditional data.

Recently, various recommendation systems for recommending movies, music, books, news, images, web pages, etc. are emerging. The conventional recommendation system recommends things related to analysis results through simple user analysis, but there is no system that performs in-depth analysis of contents and users for career education in a specific field. In particular, the unilateral learning path recommendation method provided by the conventional learning system has a limitation in providing inefficient educational content to users with different individual situations.

1. Korean Patent Publication No. 10-2018-0046496 (May 09, 2018) 2. Korean Patent Registration No. 10-1157453 (June 12, 2012)

The learning path recommendation system through user characteristics and content analysis according to the embodiment is a customized learning path for career education in the music field by in-depth analysis of user metadata and content metadata including the user's overall ability and academic achievement. recommend

A system for recommending a learning path through user characteristics and content analysis according to an embodiment includes: a user analysis module for analyzing user metadata including a user's current level, a target level, a competency evaluation result, a desired learning rate, and an area of interest; a learning content analysis module for analyzing learning content metadata including job category, level, necessity, instructor, related lecture, and time required to complete; and a learning path design module for combining a plurality of learning contents according to user metadata based on the analyzed learning contents metadata and recommending them to the user. includes

The learning path recommendation system through user characteristics and content analysis as described above provides a customized learning path to users who want to build a career in the field of music that requires complex abilities, thereby providing learning appropriate to the user's individual situation and characteristics. make it possible to perform

In addition, the user's strengths and weaknesses can be objectively identified through the embodiment, and accordingly, the user can maximize the learning efficiency by receiving and learning a learning program optimized for the user.

The effects of the present invention are not limited to the above effects, and it should be understood to include all effects that can be inferred from the configuration of the invention described in the detailed description or claims of the present invention.

1 is a diagram for explaining the concept of a system for recommending a learning path through user characteristics and content analysis according to an embodiment;
2 is a diagram illustrating a data processing block of a system for recommending a learning path through user characteristics and content analysis according to an embodiment;
3 is a chart defining quantified levels and goals for own job competency according to the embodiment;
4 is a table in which quantitative profiles are defined for main indicators according to goals for each level according to the embodiment
5 is a data definition chart according to the embodiment;
Figure 6 is a diagram showing the analysis of the weight of the topic (Topic) according to the difference in the competency index for each step of the learning content according to the embodiment
7 and 8 are diagrams illustrating meta data design of learning content according to an embodiment;
9 is a diagram for determining learning content according to the embodiment;
10 is a result chart for generating a customized learning path according to the embodiment;
11 is a calculation chart of credits required to achieve a level according to the embodiment;
12 is an analysis chart showing whether the required lecture is achieved according to the embodiment;
13 is a table showing a priority consideration factor and a measurement method of a learning path module according to an embodiment
14 is an embodiment in which lectures with high relevance are sequentially listed.
15 is a view showing an embodiment of creating a learning path optimized for a user by inserting an additional recommended course for each lecture

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the art to which the present invention pertains. It is provided to fully inform the possessor of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout.

In describing the embodiments of the present invention, if it is determined that a detailed description of a well-known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, the terms to be described later are terms defined in consideration of functions in an embodiment of the present invention, which may vary according to intentions or customs of users and operators. Therefore, the definition should be made based on the content throughout this specification.

1 is a diagram for explaining the concept of a system for recommending a learning path through user characteristics and content analysis according to an embodiment.

Referring to FIG. 1 , a learning path system according to an embodiment provides a customized learning path to users who want to build a career in a music field requiring complex abilities. The route recommendation system according to the embodiment analyzes the user's capabilities and learning information, such as the user's level, the desired learning topic, and the desired learning period. In addition, it analyzes the subject, level, popularity, etc. of the course, which is the learning content registered in the system, and creates a user-customized learning program and recommends it to the user. In the embodiment, a learning path suitable for user characteristics and purposes is recommended. Specifically, the embodiment provides a first lecture recommendation and necessary lecture filtering function suitable for user learning purposes. In addition, the learning path recommendation system according to the embodiment provides an arrangement function for the order of learning content. Through the embodiment, the user can efficiently improve various abilities that help improve his/her career in the music field by learning by receiving a learning program optimized for him/herself.

2 is a diagram illustrating a data processing block of a system for recommending a learning path through user characteristics and content analysis according to an embodiment.

Referring to FIG. 2 , the learning path recommendation system according to the embodiment may include a user analysis module 100 , a learning content analysis module 200 , and a learning path design module 300 . As used herein, the term 'module' should be construed to include software, hardware, or a combination thereof, depending on the context in which the term is used. For example, the software may be machine language, firmware, embedded code, and application software. As another example, the hardware may be a circuit, a processor, a computer, an integrated circuit, an integrated circuit core, a sensor, a Micro-Electro-Mechanical System (MEMS), a passive device, or a combination thereof.

The user analysis module 100 analyzes user metadata including the user's current level, target level, competency evaluation result, desired learning rate, and field of interest. In an embodiment, the user analysis module 100 may generate user metadata through tests and surveys for individual users. In addition, in the embodiment, as shown in FIG. 3 , a quantified level and target data for job ability may be established to generate user metadata. In addition, it is possible to build index data for determining the capabilities required to generate user metadata. Specifically, in the embodiment, the following five main indicators of capability determination are defined, and user capabilities can be evaluated based on them.

1) Basic Competence: The degree of understanding of music-related basics

2) Working Process: The degree of understanding of one overall work process of the job

3) Quality Improvement: The degree of conformity to the work level required by the industry

4) Career Path Plan: Understanding how to prepare for and develop a career in a related job

5) Case Study: Possess understanding and ability to cope with various types of situations

In addition, as shown in FIG. 4 , the user analysis module 100 according to the embodiment may define a quantitative profile for a key indicator according to a goal for each level based on user metadata.

The learning content analysis module 200 analyzes learning content metadata including job category, level, necessity, instructor, related lecture, and time required to complete. 5 is a diagram illustrating a structure and elements of a learning content (course) according to an embodiment. In the embodiment, as shown in FIG. 5 , learning data may be defined according to the field, difficulty, and learning goal of the uploaded learning content. Also, in the embodiment, as shown in FIG. 6 , it is possible to analyze the weight of the topic according to the difference in the competency index for each stage of the learning content.

Also, the learning content analysis module 200 may design metadata for each learning content for analyzing individual learning content (course). 7 and 8 are diagrams illustrating a meta data design of learning content according to an embodiment. Referring to FIG. 7 , in the embodiment, metadata of each learning content may be divided into job category, goal level, whether a subject is essential to achieve a goal, competency index classification, etc., and each of the divided attribute values may be matched with the learning content data.

The user analysis module 100 according to an embodiment may analyze user characteristics through a survey. Specifically, the user analysis module according to the embodiment analyzes the current level and the target level of the user, and grasps the evaluation of the already known topic through the competency evaluation, the desired learning speed and the field of interest. Thereafter, the user analysis module 100 may generate user capability indicator analysis and level definition data as shown in <Table 1>.

Competency Indicators User metrics LEVEL 1 Attainment LEVEL 2 Attainment Basic 70 50 O 70 O Working Process 5 40 X 70 X Quality Improvement 10 30 X 70 X Career Path Plan 30 30 O 60 X case study 20 15 O 30 X

In addition, in an embodiment, the user analysis module 100 may determine whether the learning content is a required course for the user, as shown in FIG. 9 , based on the user analysis result. The learning path design module 300 recommends a combination of a plurality of learning contents according to the user metadata based on the analyzed learning contents metadata to the user. Thereafter, the learning path design module 300 performs other than the job category specified by the user. Filters job courses, steps outside the specified level, lectures related to competency indicators already met at that level, and courses with required topics already met at that level.

Considerations Filtering method Specified job category Filter job courses outside of the specified job category starting level Filter steps outside of the specified level Metrics of competency to meet Filtering lectures related to competency indicators already met at that level Required Topic Filter Courses from required topics that have already been met at that level Required Course Filter required courses already met at that level

In addition, the learning path design module 300 includes, in order to reflect the user's learning priority, the degree to which the user's competency index is insufficient to achieve the level, the degree of similarity to the field of interest, the popularity of the learning content, and whether the learning content is essential. By reflecting weights on each of the in-depth analysis information, a customized score for each user is calculated. In the embodiment, the learning path design module 300 reflects a weight to each of the in-depth analysis information, as shown in Table 3, and the user through Equation 1 It is possible to calculate a customized score for each learning content.

Considerations How to measure The degree to which the competency indicator is insufficient to achieve the level A*X(A: weight, X: |insufficient number|) Are you close to your area of interest? B*Y(B: weight, Y: number of meta tags with interest Overall First Class Preference C*Z*100 (C: weight, Z: percentage of selection as first lecture) Popular lectures for the job/level D*W (D: weight, W: popularity index) W = index considering the number of views and read rate Required Topic/Course? E*P(E: Weight, P: Required Course = 1, Required Topic & Non-Required Course = 0.5, if neither = 0.1)

Equation 1: Score = A*X+B*Y+C*Z*100+D*W+E*P (see Table 3)

The learning path design module 300 converts the calculated score into user result data as shown in FIG. 10 and generates a customized learning path accordingly. For example, the learning path design module 300 may convert the user score calculated through Equation 1 into an algorithm score to calculate the credit required for the user to achieve the level, as shown in FIG. 11 . Thereafter, as shown in FIG. 12 , it is possible to analyze whether the required lecture has been achieved.

In addition, the learning path design module 300 filters the learning content according to the priority by reflecting the required credit for each user. In the embodiment, as shown in Table 3, the learning path design module prioritizes lectures based on the degree to which the user competency index is insufficient to achieve the level, the degree of similarity to the field of interest, the overall first lecture preference, the popularity of the lecture, and whether it is a required course. can be selected.

13 is a table showing factors for consideration of priorities and a measurement method of a learning path module according to an embodiment.

Thereafter, the learning path design module 300 may sequentially align lectures with high relevance as shown in FIG. 14 through a relevance analysis between the filtered learning contents. Thereafter, as shown in FIG. 15 , the wet path design module 300 may insert an additional recommended course for each lecture to generate a learning path optimized for the user and recommend it.

The learning path recommendation system through user characteristics and content analysis as described above provides a customized learning path to users who want to build a career in the field of music that requires complex abilities, thereby providing learning appropriate to the user's individual situation and characteristics. make it possible to perform

In addition, the user's strengths and weaknesses can be objectively identified through the embodiment, and accordingly, the user can maximize the learning efficiency by receiving and learning a learning program optimized for the user.

The disclosed content is merely an example, and since various changes can be made by those skilled in the art without departing from the gist of the claims claimed in the claims, the protection scope of the disclosed content is limited to the specific It is not limited to an Example.

Claims (7)

Learning path recommendation system through user characteristics and content analysis
a user analysis module for analyzing user metadata including the user's current level, target level, competency evaluation result, desired learning speed, and interest;
a learning content analysis module for analyzing learning content metadata including job category, level, necessity, instructor, related lecture, and time required to complete; and
a learning path design module for combining a plurality of learning contents according to user metadata based on the analyzed learning contents metadata and recommending them to a user; A learning path recommendation system that includes.
According to claim 1, The learning path design module; silver
A learning path recommendation system characterized by filtering job courses outside the job category specified by the user, steps outside the specified level, lectures related to competency indicators already met at the corresponding level, and courses of required topics already satisfied at the corresponding level.
According to claim 2, The learning path design module; silver
In order to reflect the user's learning priority, weight is reflected in each of the in-depth analysis information including the degree to which the user's competency index is insufficient to achieve the level, the degree of similarity to the field of interest, the popularity of the learning content, and whether the learning content is essential. Learning path recommendation system, characterized in that it further comprises calculating a score tailored to each learning content.
4. The method of claim 3, further comprising: the learning path design module; silver
A learning path recommendation system, characterized in that it recommends a learning path according to user characteristics according to user goals and whether to take required lectures.
The method of claim 4, further comprising: the learning path design module; silver
In order to extract the necessary learning contents according to the learning results for each user
A learning path recommendation system, characterized in that extracting necessary lectures for achieving learning goals for each level, and sequentially extracting highly relevant lectures based on the extracted lectures.
The method of claim 1 , further comprising: the user analysis module; silver
Through user survey and testing, the user's desired job, target level, and competency index are identified, and user learning data including understanding of competency index, understanding of essential topics, and main topics and interests are generated. Learning path recommendation system, characterized in that.
[Claim 7] The system of claim 6, wherein the user's level and required learning content are determined according to the user learning data, and the required learning topic and content are filtered.

Images