Personalized Learning Support Method and System with Artificial Intelligence-based Learning Experience Analysis and Point-to-Token Conversion Function

Abstract

The present invention provides a learning support method performed by an electronic system, comprising: a step of providing to a user in the form of a mock test composed of problems that are divided into at least one of a plurality of detailed areas of a subject, wherein the problems within the same detailed area have different difficulty levels and types; a step of determining whether the user has achieved a learning objective for each detailed area by inputting the score for each detailed area of ​​the mock test obtained from the user into a machine learning model trained on the types of problems, frequency of appearance, and scores for each detailed area of ​​mock tests of successful candidates; a step of determining a detailed area among the plurality of detailed areas in which the learning objective has not been achieved as a supplementary area based on the result of determining whether the learning objective has been achieved; and a step of providing to the user problems classified as supplementary areas and lectures corresponding to the supplementary areas.

Description

Technology Field

[0001] The present invention relates to a learning support method and an education system, and more specifically, to a technology that supports adult learners in acquiring certifications and improving job skills by combining a point-based reward mechanism and a blockchain-based token conversion function in an artificial intelligence (AI)-based learning experience platform.

[0002] The system according to the present invention analyzes a user's learning progress, scores, activity history, and log data to diagnose the learner's weak areas and awards points upon achievement of learning goals. The awarded points can be used as a payment method for educational courses, learning materials, textbooks, exam tickets, etc., within the platform, and can be exchanged for blockchain-based tokens and converted externally at the user's choice. Background Technology

[0003] Recently, the demand for online learning platforms has been rapidly increasing due to the spread of non-face-to-face education and adult certification exams and job training. Consequently, the development and utilization of learning support systems are also expanding significantly. Existing learning support systems for adult education are currently structured in the form of simple problem sets and lecture delivery.

[0004] However, online learning platforms have limitations compared to offline learning, such as a lack of immediate feedback, restricted interaction, and difficulty in maintaining concentration. Consequently, performance on online learning platforms varies significantly depending on the user's willpower, and since it is difficult to motivate users, there is a problem of low achievement rates for learning goals.

[0005] Therefore, research is continuously being conducted on methods and systems to encourage user learning motivation and provide continuous learning motivation on adult online learning platforms. The problem to be solved

[0006] The problem to be solved by the present invention is to provide a learning support method and system that supports personalized learning by determining whether a user has achieved learning goals in specific areas through AI-based learning experience analysis.

[0007] In particular, another objective of the present invention is to provide a learning support method and system that provides continuous learning motivation and incentives for participation to learners while avoiding legal and institutional risks associated with direct token payment, by awarding points upon achievement of learning goals and allowing the points to be used as a payment method for educational courses, learning materials, test tickets, etc. within the platform, or converted into blockchain-based tokens and transferred externally according to the user's choice.

[0008] The problems to be solved through the various embodiments of the present invention are not limited to those mentioned above, and other unmentioned problems will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0009] To solve the above problem, the technical concept of the present invention provides a learning support method that performs data analysis and recommendation functions by an electronic system, comprising: a step of continuously providing a user with a mock test containing questions on a topic corresponding to at least one of a plurality of detailed areas for each subject, while presenting questions of various types within the same detailed area so that the learner can fully master the area; a step of intelligently determining whether the user has achieved the learning goal for each detailed area by having a machine learning model analyze big data such as the types of questions, the frequency of question appearance, and the scores, correct / incorrect answer rates, learning activities, and log records of mock tests by detailed area of ​​successful candidates to derive a conclusion; a step of determining the detailed area among the plurality of detailed areas where the learning goal has not been achieved as a supplementary area based on the result of determining whether the learning goal has been achieved; and a step of providing the user with questions classified as the supplementary area, similar questions, and lectures corresponding to the supplementary area, and automatically saving feedback on the supplementary area.

[0010] To solve the above problem, the technical concept of the present invention provides an electronic system including an artificial intelligence analysis module that analyzes and recommends users through machine learning using big data collected from users, wherein the processor performs the learning support method by executing the above instruction.

[0011] In addition, the technical concept of the present invention further includes a step of providing points upon achievement of learning goals, using the provided points as a payment method for educational courses, learning materials, test tickets, etc. within the system, or converting them into blockchain-based tokens and transferring them externally according to the user's choice, thereby enhancing the learner's motivation and immersion through learning rewards and ultimately increasing the achievement rate of learning goals.

[0012] To solve the above problem, the technical concept of the present invention provides an electronic system comprising an artificial intelligence analysis module that performs various analyses through big data collection and machine learning of the system and provides AI recommendations based thereon, wherein a processor performs the learning support method by executing the above instructions.

[0013] To solve the above problem, the technical concept of the present invention provides a computer-readable recording medium, wherein the recording medium has a program recorded thereon for executing the learning support method on a computer.

[0014] Specific details of other embodiments are included in the detailed description and drawings. Effects of the invention

[0015] A learning support method and system according to the technical concept of the present invention can effectively supplement a learner's weak areas by determining whether a user has achieved learning goals for each specific area through a machine learning model and providing various types of problems and customized learning content based on the results.

[0016] The learning support method and system according to the technical concept of the present invention can enhance learner motivation and immersion while ensuring legal stability by awarding points upon achievement of learning goals, using the points as a payment method for educational courses, learning materials, exam tickets, etc., within a platform, or converting them into blockchain-based tokens at the user's choice. Through this, learning outcomes can be continuously maintained and improved, and learning goals can be achieved. In addition, the quality of learning can be improved by providing subject matter experts with incentives in the form of points for learning support and the creation of learning content.

[0017] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description in the claims. Brief explanation of the drawing

[0018] FIG. 1 is a diagram schematically showing the overall configuration of a learning support system according to one embodiment of the present invention. FIG. 2 is a block diagram schematically illustrating an electronic system constituting a learning support system according to one embodiment of the present invention. FIG. 3 is a diagram schematically illustrating the accumulation and use of points in a learning support system according to one embodiment of the present invention. FIG. 4 is a block diagram schematically illustrating a learning support method according to one embodiment of the present invention. Specific details for implementing the invention

[0019] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components.

[0020] The embodiments described herein will be described with reference to cross-sectional and / or plan views, which are exemplary illustrations of the invention. In the drawings, the thicknesses of films and regions are exaggerated for effective description of the technical content. Accordingly, the regions illustrated in the drawings are schematic in nature, and the shapes of the regions illustrated in the drawings are intended to illustrate specific forms of regions of the device and are not intended to limit the scope of the invention. Although terms such as first, second, third, etc., have been used to describe various components in the various embodiments of this specification, these components should not be limited by such terms. These terms are used merely to distinguish one component from another. The embodiments described and illustrated herein also include their complementary embodiments.

[0021] The terms used herein are for describing the embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used herein, "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components, steps, actions, and / or elements to the mentioned components, steps, actions, and / or elements.

[0022] Unless otherwise defined, all terms used in this specification (including technical and scientific terms) may be used in a meaning that is commonly understood by those skilled in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. Hereinafter, the concept of the present invention and embodiments thereof will be described in detail with reference to the drawings.

[0023] FIG. 1 is a diagram schematically showing the overall configuration of a learning support system (10) according to one embodiment of the present invention.

[0024] Referring to FIG. 1, the learning support system (10) may include an electronic system (100), a user terminal device (200) operated by a user, and a content expert terminal device (300) operated by a content expert.

[0025] The electronic system (100) may be an integrated entity that includes physical equipment, such as servers and hardware, smart devices, software, and networks, that provides an online learning platform. The electronic system (100) may perform the role of a platform that collects and analyzes learner activity data to mediate learning content between users and subject matter experts and manages user accounts and subject matter expert accounts. In some embodiments, the electronic system (100) may be a computing device embedded in a user terminal device (200) or a subject matter expert terminal device (300).

[0026] The electronic system (100) may include a memory (101) containing instructions and a processor (102) configured to execute instructions. In some embodiments, the electronic system may further include a database and an artificial intelligence analysis module. By executing instructions, the processor (102) can perform the learning support method described below.

[0027] In some embodiments, the electronic system (100) may further include a communication unit. The communication unit may transmit and receive information from a user terminal device (200) and a content expert terminal device (300).

[0028] The electronic system (100) can communicate with a user terminal device (200) and a content expert terminal device (300) through a communication unit and can be implemented in the form of a web server, an application server, a cloud server, or a database server.

[0029] For example, the communication unit may include a communication module that supports one of various wired and wireless communication methods. For example, the communication unit may be in the form of a chipset. Additionally, the communication unit may be a short-range communication module or a wired communication module. For example, the communication unit may support at least one of Wireless LAN, Wi-Fi (Wireless Fidelity), WFD (Wi-Fi Direct), Bluetooth, BLE (Bluetooth Low Energy), Wired LAN, NFC (Near Field Communication), Zigbee, Infrared (IrDA, Infrared Data Association), 3G, 4G, and 5G.

[0030] The user can receive learning content such as lectures, questions, and exams through the electronic system (100). For example, the user can access the electronic system (100) through a user terminal device (200) to use various learning content. The user terminal device (200) may include various devices such as smartphones, mobile phones, tablet PCs, desktops, and laptops, but is not limited thereto. For example, the user terminal device (200) may be an electronic device capable of network communication. For example, the user terminal device (200) may transmit and receive information with the electronic system (100) through a web browser or a dedicated application.

[0031] A content expert can produce learning content such as lectures, questions, educational materials, and assignments, and provide them to an electronic system (100). For example, a content expert can access the electronic system (100) through a content expert terminal device (300) to upload learning content, answer real-time lectures and questions, and grade assignments, thereby encouraging and managing learners. The content expert terminal device (300) may include various devices such as smartphones, mobile phones, tablet PCs, desktops, and laptops, but is not limited thereto. For example, the content expert terminal device (300) may be an electronic device capable of network communication. For example, the content expert terminal device (300) may transmit and receive information to and from the electronic system (100) through a web browser or a dedicated application.

[0032] In some embodiments, the electronic system (100) may provide a learning platform that provides learning content for obtaining various certifications to a user terminal device (200) or a subject matter expert terminal device (300). The exam for obtaining certifications may consist of multiple subjects, and each subject may consist of multiple detailed areas. The electronic system (100) may provide learning content such as lectures, summaries, mock exams, and assignments for each detailed area of ​​each subject.

[0033] For example, the Information Processing Engineer certification may consist of multiple subjects, including software design, software development, database construction, programming language utilization, information system construction and management, and practical information processing. Each subject can be further divided into detailed areas. For instance, the written exam for the Electrical Engineer certification may consist of subjects such as electromagnetics, electrical machinery, technical standards for electrical facilities, power engineering, circuit theory, and control engineering.

[0034] The learning content for obtaining the certification disclosed above is merely an example of learning content, and the learning content provided by the electronic system (100) is not limited thereto and may include language exams such as TOEIC, civil service exams, and job training for office workers.

[0035] FIG. 2 is a block diagram schematically illustrating an electronic system (100) constituting a learning support system (10) according to an embodiment of the present invention. FIG. 3 is a diagram schematically illustrating the accumulation and use of points in a learning support system (10) according to an embodiment of the present invention.

[0036] Referring to FIGS. 2 and FIGS. 3, the electronic system (100) may include a learning content module (110), a learning support module (120), and a motivation module (130).

[0037] The learning content module (110) may include a question database (111) in which multiple questions for mock exams are stored, and a lecture database (112) in which lectures for each subject's detailed area are stored. For example, the learning content module (110) may further include a reference database in which reference materials such as subject-specific summary materials, key concept summaries, formula collections, and glossaries are stored, and a learning database in which the user's previous mock exam scores and learning patterns, and the scores and learning patterns of successful candidates are stored.

[0038] Questions classified by certification exam, subject, and detailed area can be stored in the question database (111). For example, the question database (111) may include various types of questions, such as multiple-choice questions, short-answer questions, and descriptive questions. Additionally, the question database (111) may store multiple questions, such as past questions, predicted questions, and mock questions. For example, questions stored in the question database (111) may be uploaded by a subject matter expert.

[0039] Each question may be stored with metadata including difficulty level, frequency of appearance, similar topics, and correct answer rate. In some embodiments, the metadata of the question may include the year of appearance, the issuing organization, the question type, the estimated time required, and the main types of incorrect answers.

[0040] Lectures, lecture materials, and summary notes produced for each subject's detailed area can be stored in the lecture database (112). The lectures stored in the lecture database (112) are uploaded by subject matter experts and can be managed along with information such as lecture time, grades, and number of students. In some embodiments, the lecture database (112) may store lectures classified into theoretical lectures, problem-solving lectures, and practical lectures.

[0041] The learning support module (120) may include a mock test production unit (121), a learning goal achievement determination unit (122), a supplement area determination unit (123), and a supplement content provision unit (124).

[0042] The mock test production department (121) can produce mock tests that include past exam questions and questions classified by subject area. For example, the mock test production department (121) can produce mock tests using past exam questions stored in the question database (111) and predicted questions produced by subject matter experts. For example, the mock test may include multiple-choice questions, subjective questions, and descriptive questions. For example, the mock test may be produced in various formats such as quizzes given after a lecture, midterm evaluations, mock tests in a format substantially identical to that of a regular exam, subject-specific tests consisting only of questions classified by specific area, and assignments.

[0043] In some embodiments, the mock test production unit (121) can produce an adaptive mock test based on the user's correct / incorrect answer rate. For example, the mock test production unit (121) can analyze the user's previous mock test performance to increase the weight of questions in weak sub-areas, or select questions of similar topics to determine whether the user has mastered the material, thereby configuring the mock test. The mock test production unit (121) can produce the mock test by utilizing the metadata of each question stored in the question database (111).

[0044] For example, the metadata of the problem may include past users' correct / incorrect answer rates, frequency of appearance, time taken, and problem type. The mock test production department (121) can generate a mock test optimized for the user's target score and test schedule based on this metadata of the problem.

[0045] The electronic system (100) can provide the user with mock exams produced by the mock exam production department (121) in various ways, repeatedly, by past year and round. The user can repeatedly select and participate in (take) mock exams of the desired past year and round through the user terminal device (200), and the electronic system (100) can obtain the answers to the mock exams in which the user participated. The electronic system (100) can record the test results, such as scores of the mock exams in which the user participated, in a database and learn from them.

[0046] The learning goal achievement determination unit (122) can determine whether learning goals have been achieved, such as by the user's specific area or the possibility of obtaining a certification, through a trained machine learning model. The machine learning model can be trained using the learning data of successful candidates and metadata of the problems.

[0047] The learning data of successful candidates may include learning pattern data of those who successfully obtained the certification, trends in mock exam scores, score distributions by detailed subject area, and correct / incorrect answer rates. A machine learning model can be constructed to learn metadata containing the frequency of question appearances, correct / incorrect answer rates, and related keywords, along with the learning data of successful candidates, so that it can determine whether learning objectives have been achieved by considering the characteristics of the questions rather than simply comparing scores.

[0048] In some embodiments, the machine learning model may additionally learn from the user's training data. The user's training data may include the scores by subject area of ​​the most recent mock test the user participated in, the scores by subject area of ​​previous mock tests, the rate of change in scores, error patterns, test completion time, and the number of times the user participated in mock tests.

[0049] For example, a user's learning data can be stored in a big data repository. A machine learning model can learn from the user's learning data stored in the big data repository to analyze the user's weak areas, learning patterns, and changes in achievement. Based on the results analyzed by the machine learning model, an artificial intelligence model can suggest personalized learning directions and supplementary learning strategies tailored to the user.

[0050] As user learning data accumulates in the machine learning model, the accuracy of determining whether learning goals for each detailed area of ​​the electronic system (100) have been achieved can be improved. For example, it can be configured to enable self-correction by continuously analyzing the correlation between the result of determining a new user's learning goal achievement and whether they actually passed the certification exam.

[0051] In some embodiments, the determination unit (122) for determining whether a learning objective has been achieved may use a combination of a statistical analysis method and a machine learning model, and may apply statistical criteria first when sample data is insufficient, and increase the weight of the machine learning model after sufficient data has been accumulated.

[0052] In some embodiments, the machine learning model initially determines whether learning objectives have been achieved based on basic criteria provided by the certification issuing body, and can gradually transition to machine learning-based judgments as user learning data is accumulated.

[0053] The machine learning model may be implemented using at least one of algorithms such as Random Forest, Gradient Boosting, Neural Network, Support Vector Machine, Decision Tree, Logistic Regression, Naive Bayes, XGBoost, LightGBM, and Ensemble Model. In some embodiments, the machine learning model may be implemented using deep learning-based Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTMs), Convolutional Neural Networks (CNNs), etc. For example, Recurrent Neural Networks or LSTMs may be effective for analyzing a user's time-series learning patterns and score changes.

[0054] The electronic system (100) can determine whether the learning objectives for each detailed area have been achieved by inputting the scores of the user's mock test into a trained machine learning model. For example, the electronic system (100) can determine whether the learning objectives for each detailed area have been achieved by inputting metadata of the questions included in the mock test into the trained machine learning model.

[0055] For example, a machine learning model can calculate the probability that a user will obtain a certification based on the user's scores for each detailed area, and if the probability is above a preset probability threshold, determine that the relevant detailed area is in a state where the learning goal has been achieved, and if it is below the threshold, determine that the relevant detailed area is in a state where the learning goal has not been achieved.

[0056] For example, if a user obtains 60 points in the first detailed area of ​​the written exam for electrical engineers, the machine learning model may not make a judgment based solely on that score but may also consider the metadata of the questions.

[0057] For example, if the user's accuracy rate in the relevant sub-area is less than 60%, the electronic system (100) learns the user's learning data and compares it with the pass / fail status of past learners with similar patterns to derive the conclusion that "circuit theory needs supplementation," and can display a learning guide on the dashboard such as "try solving similar problems in the sub-area and intensive lectures on circuit theory repeatedly for two weeks."

[0058] For example, even if the correct answer rate is 60% or higher, the electronic system (100) may additionally present similar problems to determine whether complete learning has been achieved, and if the correct / incorrect answer rate is 60% or higher and complete learning has been achieved, it may determine that the learning goal has been achieved.

[0059] In some embodiments, the machine learning model may determine whether the learning objective has been achieved based on the following criteria. For example, if the average score of a specific area is above the passing threshold (e.g., 60%), the score of the area in the last three mock exams is on an upward trend, and the error rate is below the threshold (e.g., 40%), the area in question may be determined to have achieved the learning objective.

[0060] In some embodiments, the machine learning model may determine that the learning objective has not been achieved if the score is lower than the average score of past successful candidates, if the weighted score reflecting problem metadata is below a threshold, or if the latest test score has dropped by more than a preset percentage (e.g., 20%) compared to the previous average.

[0061] The supplementary area determination unit (123) can determine the detailed area determined as the user's learning goal not achieved as a supplementary area based on the result determined by the learning goal achievement determination unit (122). For example, the supplementary area determination unit (123) can identify the detailed areas determined as the learning goal not achieved among a plurality of detailed areas and determine them as supplementary areas.

[0062] In some embodiments, the supplementary area determination unit (123) may determine the priority of the supplementary areas according to the importance of the detailed areas determined to be in a state of not achieving the learning objectives. For example, a higher priority may be assigned to a detailed area that has a high proportion of questions in the actual certification exam, a detailed area with a large score gap with successful candidates, or a detailed area where scores continuously decline.

[0063] The supplementary content provision unit (124) can provide learning content corresponding to the supplementary area determined by the supplementary area determination unit (123) to the user. For example, the supplementary content provision unit (124) can select problems and lectures classified in the corresponding supplementary area from the problem database (111) and lecture database (112) and provide them to the user.

[0064] In some embodiments, the supplementary content provider (124) may adjust the subject matter and scope of the supplementary content according to the user's weaknesses. For example, in the corresponding supplementary area, it may first provide basic concept lectures and similar problems according to the user's weakness area and determine whether complete learning has been achieved.

[0065] In some embodiments, the supplementary content provider (124) may establish a learning plan according to the priority of the supplementary areas and present it to the user. For example, it may provide a personalized learning roadmap that allows the user to proceed sequentially to the second-priority supplementary area after completing the lectures and problem-solving of the first-priority supplementary area.

[0066] The learning support module (120) of the electronic system (100) can provide customized learning to the user by determining whether individual learning goals have been achieved through a machine learning model. For example, by comprehensively analyzing the learning data of successful candidates and the user's learning data to determine whether relatively accurate learning goals have been achieved according to individual characteristics, the user can receive an objective and reliable learning diagnosis and establish an efficient learning plan. In addition, the learning support module (120) can promote systematic learning improvement according to the user's ability by providing customized content in stages that matches the user's learning level in supplementary areas.

[0067] The motivation module (130) may include a point accumulation unit (131), a learning activity storage unit (132), and a learning standard provision unit (133).

[0068] Referring together with FIG. 3, the point accumulation unit (131) can accumulate points for the user based on the user's activities and accumulate management points for the content expert based on the content expert's activities. Hereinafter, points and management points may be collectively referred to as points.

[0069] In some embodiments, the point accumulation unit (131) may accumulate points in the user account when the user participates in a mock test or takes a lecture. For example, points may be accumulated in the user account when the user completes a mock test, and points may be accumulated in the user account when the user takes a lecture to the end. Additionally, the point accumulation unit (131) may accumulate points in the user account for platform participation activities, such as the user writing a review for a lecture or continuously logging in.

[0070] The point accumulation unit (131) can accumulate points in the user account based on the user's learning performance. For example, points may be accumulated when the supplementary area is re-evaluated as having achieved the learning goal, and points may be accumulated when the mock test score increases compared to the previous one.

[0071] The point accumulation unit (131) can accumulate points in the content expert account for the content expert's content creation and management activities. For example, the point accumulation unit (131) can accumulate points in the content expert account when the content expert uploads new problems or provides new lectures. Additionally, the point accumulation unit (131) can accumulate points in the content expert account when the content expert updates existing lectures or writes answers to users' questions regarding problems and lectures. In some embodiments, the point accumulation unit (131) can accumulate points in the content expert's account when the evaluation received by the content expert from users is higher than a preset rating (e.g., 4.0 points) or when the highest sales rate is recorded.

[0072] For example, the activities eligible for point accumulation by users and content experts are not limited to the activities mentioned above, and may include various learning-related activities and content creation-related activities carried out within the learning platform.

[0073] For example, accumulated points can be used to purchase products on the site through the token conversion module (140), and can be exchanged into blockchain tokens through the product payment module (150) and traded on an exchange. The token conversion module (140) can convert points into blockchain-based tokens and transfer them to an external wallet according to the user's choice. The product payment module (260) can process payments for products such as educational courses, learning materials, and exam tickets using the points.

[0074] In some embodiments, it may be operated as an ERC-20 token based on the Ethereum network or implemented as a custom token issued on an independent blockchain network and exchanged for points. Due to the nature of the token, its value may rise or fall, so the decision can be made based on the user's willingness to exchange.

[0075] In some embodiments, points may be exchanged in the form of blockchain tokens linked to the electronic system (100) at the request of the user or content expert and transferred to an external payment service or withdrawn to the user or content expert's personal cryptocurrency wallet. For example, the user may transfer points accumulated within the electronic system (100) to an external payment service to use them like fiat currency, or transfer them to a personal cryptocurrency wallet to use them in other blockchain-based services. Additionally, the user may directly use the accumulated points within the platform provided by the electronic system (100) for purposes such as purchasing additional lectures or discounting exam fees.

[0076] The learning experience storage unit (132) can collect and store information regarding the user's learning activities and performance. For example, the learning experience storage unit (132) can store information determining whether learning goals for each detailed area have been achieved by analyzing user learning activities, including the user's log activity, total learning time, learning time by detailed area, mock test participation activity, and learning goal achievement activity, using a machine learning-based analysis module.

[0077] In some embodiments, the learning activity information stored by the learning experience storage unit (132) may further include objectively verifiable learning performance data, such as the user's mock test scores, records of course completion, and whether a certificate has been obtained. For example, the content included in the user learning experience information is not limited to the aforementioned contents and may include various records related to learning activities.

[0078] The learning standard provision unit (133) can provide the user with learning standard information of successful candidates who have succeeded in obtaining a certificate and passing standard information provided by the certificate issuing institution to motivate the user to learn. For example, the learning standard provision unit (133) can provide the user with the average score of successful candidates by detailed area, the average total study time of the successful candidates for the relevant subject, the average study time of the successful candidates for the relevant subject once, or the passing standard score provided by the certificate issuing institution.

[0079] In some embodiments, the learning standard providing unit (133) may provide the user with various learning standard information, such as the number of times successful candidates took mock exams, the learning order of successful candidates by detailed subject area, the learning method mainly used by successful candidates (lecture-based, problem-solving-based, etc.), and the period of intensive study before the exam for successful candidates.

[0080] For example, the learning standard provision unit (133) may also provide information such as the learning distribution of successful candidates by time of day (morning, afternoon, evening, etc.), the average number of study days per week of successful candidates, and the average period taken for successful candidates to reach the state of achieving the learning goal. However, the learning standard information is not limited to this and may additionally include information set by the user.

[0081] In some embodiments, the learning standard providing unit (133) may visually display the user's current learning status and the standards of successful candidates. For example, it may provide a graph comparing the user's score by detailed area with the average of successful candidates, a chart comparing the user's total learning time with the average learning time of successful candidates, etc., so that the user can objectively understand their learning progress.

[0082] The learning standard providing unit (133) can also suggest improvement measures by comparing the user's learning pattern with the learning pattern of successful candidates. For example, if successful candidates spend an average of 2 hours per study session, but the user spends an average of only 30 minutes studying, the unit can provide a notification recommending an extension of the study time.

[0083] The learning standard provision unit (133) can also separately provide information on successful candidates with substantially the same conditions as the user. For example, it can provide more personalized learning standard information by separately classifying the learning patterns of successful candidates who have scores substantially the same as the user's mock test score at the start of learning, and the learning patterns of successful candidates who have study times substantially the same as the user's study time.

[0084] The motivation module (130) of the electronic system (100) can provide transparent and fair rewards to both the user and the subject matter expert through points, and can provide continuous learning motivation and content creation motivation by diversifying the exchange of physical goods and uses in the form of blockchain tokens. In addition, it provides various learning criteria information of successful candidates so that the user can set objective learning goals and continue motivated learning.

[0085] FIG. 4 is a block diagram schematically illustrating a learning support method according to an embodiment of the present invention. Specifically, the learning support method can be performed by the electronic system described above.

[0086] Referring to FIG. 4, the learning support method may include the steps of providing a user with a mock test containing problems classified into at least one of a plurality of detailed areas for each subject, obtaining answers to the mock test from the user and determining whether the user has achieved a learning goal for each detailed area, determining a supplementary area based on the result of determining whether the learning goal has been achieved, and providing supplementary content corresponding to the supplementary area.

[0087] In the step of providing a mock test, the electronic system (100) may provide a mock test produced by the mock test production unit (121) to the user terminal device (200). The step of providing a mock test to the user may be performed repeatedly. For example, if there is a request for a mock test from the user terminal device (200), the electronic system (100) may provide a mock test to the user terminal device (200).

[0088] The user can participate in and take a mock test through a user terminal device (200) and transmit the answers to the mock test to an electronic system (100). The electronic system (100) can obtain the answers to the mock test from the user and grade the mock test by detailed area.

[0089] In the step of determining whether the learning goal has been achieved, the electronic system (100) inputs the scores of the user's mock test obtained from the user into the learned machine learning model to determine whether the user has achieved the learning goal for each detailed area.

[0090] Machine learning models can be trained using metadata of the problems and training data of successful candidates. For example, a machine learning model can be constructed by training from various angles on the training data of successful candidates, including their learning pattern data, trends in mock exam scores, and score distributions by detailed subject area.

[0091] For example, a machine learning model can be constructed to learn metadata of questions, including question frequency and correct / incorrect answer rates, along with the learning data of successful candidates, so as to enable the determination of whether learning objectives have been achieved by considering the characteristics of the questions rather than simply comparing scores.

[0092] In some embodiments, the machine learning model may learn additional user learning data. As user learning data accumulates, the machine learning model can improve the accuracy of determining whether learning objectives have been achieved in each specific area. For example, it may be configured to enable self-correction by continuously analyzing the correlation between the results of determining whether a new user has achieved their learning objectives and whether they have actually passed a certification exam.

[0093] The electronic system (100) can determine whether the user has achieved their learning goals by inputting the user's scores for each detailed area of ​​the mock test into a trained machine learning model. For example, the machine learning model can analyze the input user's latest mock test scores and the score change patterns of previous mock tests, and determine the status of achievement of the learning goals for each detailed area based on the learning patterns and question metadata of previously trained successful candidates.

[0094] For example, a machine learning model can comprehensively analyze whether the weighted scores for each detailed area, reflecting the user's scores and metadata, have reached the average score criteria of successful candidates and whether they align with the trend of change in the average scores of successful candidates. As a result of this judgment, the machine learning model can output the status of whether the learning objective has been achieved or not for each detailed area.

[0095] For example, a machine learning model can determine that a specific area has achieved its learning objectives if it maintains a stable score on question types with high accuracy rates for similar content or high frequency of appearance.

[0096] For example, a machine learning model can determine that a specific subject area has not achieved its learning objectives if the user's score in that area is lower than the average score of successful candidates, if the score in that specific area consistently declines in consecutive mock exams, or if the user repeatedly makes incorrect answers on core question types that appear frequently.

[0097] In the step of determining the supplementary area, the electronic system (100) may determine the area among the multiple detailed areas that has not achieved the learning goal as the supplementary area based on the result of determining whether the user has achieved the learning goal for each detailed area.

[0098] In some embodiments, the electronic system (100) may identify detailed areas determined to be in a state of non-achievement of learning objectives through the supplementary area determination unit (123), and sort them according to priority to determine them as supplementary areas. For example, the supplementary area determination unit (123) may give higher priority to detailed areas with a high proportion of questions in the actual certification exam, detailed areas with a large score gap with successful candidates, or detailed areas where scores are continuously declining.

[0099] In the step of providing supplementary content, the electronic system (100) may provide problems and lectures corresponding to the supplementary area. For example, problems and lectures classified as the supplementary area may be provided to the user.

[0100] The electronic system (100) can select problems and lectures classified into the corresponding supplementary area from the problem database (111) and lecture database (112) through the supplementary content provision unit (124). The supplementary content provision unit (124) can adjust the difficulty of the supplementary content according to the user's learning level and establish a personalized learning roadmap according to the priority of the supplementary area. The electronic system (100) can provide the problems and lectures classified into the selected supplementary area to the user terminal device.

[0101] In some embodiments, the electronic system (100) may provide supplementary content in stages according to the user's score level. Additionally, the electronic system (100) may present a learning plan to the user that provides supplementary content corresponding to a first-priority supplementary area, and then sequentially provides supplementary content corresponding to a second-priority supplementary area.

[0102] In some embodiments, the learning support method may further include a point accumulation step.

[0103] In the point accumulation stage, the electronic system (100) awards points to the user and the content expert based on the user's activities and the content expert's activities, and these points can be exchanged for product purchases and blockchain tokens and traded on an external exchange.

[0104] In some embodiments, the electronic system (100) can accumulate points in a user account according to the user's learning activities and performance through a point accumulation unit (131). For example, points may be accumulated when the user logs in, participates in a mock test, or takes a lecture, and points may be accumulated when the supplementary area is re-evaluated as having achieved the learning goal or when the mock test score increases compared to the previous one.

[0105] Meanwhile, in some embodiments, the electronic system (100) may also accumulate points for the content expert's content creation activities, assignment grading, lecture satisfaction, Q&A, sales performance, etc. For example, points may be accumulated in the content expert account when the content expert provides new problems or lectures, updates existing content, or writes answers to users' questions.

[0106] The accumulated points are automatically managed through a smart contract and can be transferred to an internal payment service or a personal cryptocurrency wallet, as illustrated in FIG. 3, upon the request of a user or content expert.

[0107] In some embodiments, the learning support method may further include a step of storing learning activity information.

[0108] The electronic system (100) can collect and store learning activity information, including the user's total learning time, learning time by detailed area, mock test participation activity, and learning goal achievement activity, through the learning activity storage unit (132). For example, the learning activity information may further include the user's mock test score, lecture completion record, and whether a certificate has been obtained.

[0109] For example, a program for implementing a learning support method according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable recording medium.

[0110] Although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above. Various modifications are possible by those skilled in the art without departing from the essence of the invention as claimed in the patent claims, and such modifications should not be understood individually from the technical spirit or perspective of the present invention. Explanation of the symbols

[0111] 100: Electronic system 200: User terminal device 300: Content Expert Terminal Device 101: Memory 102: Processor 110: Learning Content Module 120: Learning Support Module 130: Motivation Module 111: Problem Database 112: Lecture Database 121: Mock Exam Production Department 122: Learning Objective Achievement Judgment Department 123: Supplementary Area Determination Unit 124: Supplementary Content Provision Unit 131: Point Accumulation Section 132: Learning Experience Analysis Module 133: Learning Standards Provider 10: Learning Support System 140: Token Conversion Module 150: Product Payment Module

Claims

Claim 1 A learning support method performed by an electronic system, comprising: a step of providing a user with a mock test composed of questions that are classified into one of a plurality of sub-areas of a subject, wherein the questions within the same sub-area differ in difficulty and type; a step of inputting the scores by sub-area of ​​the mock test obtained from the user into a machine learning model trained with metadata including the frequency of question appearance and correct / incorrect answer rates, and learning data of successful candidates including learning pattern data of successful candidates who have succeeded in obtaining a certification, trends in mock test scores, score distribution by sub-area, and correct / incorrect answer rates, wherein the machine learning model analyzes whether the score change patterns by sub-area calculated from the user's previous mock tests and the latest mock test correspond to the average score change trends of the successful candidates, and compares this with the certification pass status of past learners having patterns similar to the user's learning data to calculate the probability of the user obtaining a certification by sub-area, and determines a sub-area where the calculated probability is above a preset threshold as a state of achieved learning goals, and a sub-area below the threshold as a state of not achieved learning goals; and supplementing the sub-area among the plurality of sub-areas that is in a state of not achieved learning goals based on the result of determining whether the learning goals have been achieved. A learning support method comprising: a step of determining a region; a step of determining a priority among the supplementary regions based on, if there are multiple supplementary regions, the frequency of questions in the detailed regions, the user's score change pattern by detailed region, and the difference between the average score of successful candidates by detailed region and the user's score by detailed region; and a step of providing the user with priority problems classified as supplementary regions and lectures corresponding to the supplementary regions according to the determined priority of the supplementary regions; wherein the machine learning model continuously analyzes the correlation between the user's judgment result on achieving learning goals and whether the user actually passed the certification exam to self-correct. Claim 2 A learning support method according to claim 1, further comprising the step of providing the user with the average score of the successful candidates by detailed area, the average total study time of the successful candidates for the subject, and the average study time per session of the successful candidates for the subject. Claim 3 A learning support method according to claim 1, further comprising the step of accumulating points for the user and the content expert based on the activities of the user participating in the mock test and taking the lecture, and the activities of the content expert participating in the production of the lecture and directly influencing the learning support of the learner, wherein the points are used as a payment method for purchasing at least one of the internal educational materials, learning content, and textbooks of the electronic system, or the token conversion module of the electronic system converts them into blockchain-based tokens through a smart contract and transmits them to an external personal cryptocurrency wallet. Claim 4 A learning support method in which, in paragraph 3, the points are accumulated for the user when the user’s score in each detailed area increases compared to the previous mock test or when the supplementary area is re-evaluated as having achieved the learning goal. Claim 5 A learning support method in which the above points are accumulated for the content expert when the above lecture is updated, when an answer to the above lecture or the above problem is written, or when the above user receives a rating higher than a preset rating. Claim 6 A learning support method according to claim 1, further comprising the step of collecting and accumulating learning data including the user's total learning time, learning time by detailed area, mock test participation records, and whether learning goals have been achieved in a big data repository of the electronic system, and after the machine learning model learns the learning data to analyze the user's weak areas, learning patterns, and changes in achievement, presenting personalized learning directions and supplementary learning strategies to the user. Claim 7 An electronic system comprising a memory in which an instruction is stored and at least one processor that executes said instruction, wherein the processor performs the learning support method of claim 1 by executing said instruction. Claim 8 A computer-readable recording medium, wherein a recording medium having a program for executing the learning support method of claim 1 on a computer.

Images