Learning pipeline for maximizing efficiency and engraving of korean vocabulary learning

Abstract

A method for providing a Korean vocabulary learning system by a processor of a device according to some embodiments of the present disclosure may include: a step of analyzing a predetermined number of sentences input by a learner to determine the learner's proficiency level and to identify the learner's weaknesses; a step of deriving items suitable for the learner's ability by applying Item Response Theory based on the proficiency level and the weaknesses, and adjusting the difficulty of the items by reflecting the learner's existing learning information and achievement; a step of providing the items to the learner and collecting the learner's response data to evaluate the learner's comprehension and learning progress; a step of creating a review schedule by setting a review cycle by applying a modified Forgetting Spaced Repetition System (FSRS) algorithm based on the comprehension and the learning progress; and a step of providing review items to the learner according to the review schedule.

Description

Technology Field

[0001] The present disclosure relates to a learning pipeline for maximizing the efficiency and imprinting of Korean vocabulary learning, and more specifically, to a method for analyzing a learner's proficiency, providing learner-customized questions, and setting an optimized review cycle. Background Technology

[0002] The global market for learning the Korean language is growing rapidly, and the demand for learning Korean among diverse learners, including international students, marriage immigrants, and foreign workers, continues to rise. As of 2024, the number of annual test-takers for the Test of Proficiency in Korean (TOPIK) reached approximately 493,000, serving as an indicator reflecting the importance of learning the Korean language and the expansion of the market. However, despite this growth, existing Korean language learning methods are currently making it difficult for learners to acquire the level of language proficiency they expect due to low achievement rates and inefficient learning techniques.

[0003] Existing Korean language education methods primarily consist of offline and online lectures provided by public and private institutions, as well as textbook-based learning. However, the standard curriculum provided by public institutions has remained largely unchanged since its establishment eight years ago, and many learning programs focus on offline education, leading to a problem of low accessibility. Furthermore, online learning content provided by the private sector often fails to adequately reflect the individual levels and characteristics of learners and is frequently delivered in a uniform manner, resulting in a lack of personalized education. Consequently, learners are forced to rely primarily on repetitive learning methods such as solving multiple-choice questions and filling in blanks; this approach fails to effectively reflect the actual semantic characteristics of the Korean language, causing difficulties in improving practical language proficiency.

[0004] In particular, foreign learners struggle to connect the knowledge acquired during the process of learning Korean vocabulary and grammar to actual conversation. Because Korean possesses linguistic characteristics where the meaning of vocabulary changes depending on context and specific expressions are used naturally only in specific situations, effective communication may be difficult relying solely on rote memorization of words or rote grammar learning. However, existing learning systems fail to adequately reflect these factors, and there is a lack of systematic systems that automatically provide optimal learning content tailored to the learner's level. Consequently, beginner learners find it difficult to move beyond studying basic sentences, while advanced learners face the challenge of finding content of an appropriate difficulty level.

[0005] Recently, the emergence of various online learning platforms has brought about changes in the Korean language education market; however, it still faces limitations such as a lack of content quality, insufficient verification of learning effectiveness, and the absence of personalized learning systems. In particular, scientific learning methodologies necessary for learners to effectively imprint learned material and convert it into long-term memory are often not applied. Furthermore, review systems rely on simple repetitive learning, failing to adequately consider individual learners' learning patterns and forgetting curves.

[0006] To address these limitations, there is an urgent need to develop a new learning system that accurately identifies learners' levels, provides items suitable for individual abilities, and effectively forms long-term memory through optimized review cycles. Prior art literature

[0007] Republic of Korea Patent Registration No. 10-2374101 (Registered on March 8, 2022) The problem to be solved

[0008] The present disclosure aims to solve the aforementioned problems and other problems. The technical problem that some embodiments of the present disclosure aim to achieve is to provide more effective learning by reflecting the individual level and learning patterns of the learner.

[0009] The technical problems to be solved in this disclosure are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0010] A method for providing a Korean vocabulary learning system by a processor of a device according to some embodiments of the present disclosure may include: a step of analyzing a predetermined number of sentences input by a learner to determine the learner's proficiency level and to identify the learner's weaknesses; a step of deriving items suitable for the learner's ability by applying Item Response Theory based on the proficiency level and the weaknesses, and adjusting the difficulty of the items by reflecting the learner's existing learning information and achievement; a step of providing the items to the learner and collecting the learner's response data to evaluate the learner's comprehension and learning progress; a step of creating a review schedule by setting a review cycle by applying a modified Forgetting Spaced Repetition System (FSRS) algorithm based on the comprehension and the learning progress; and a step of providing review items to the learner according to the review schedule.

[0011] The technical solutions obtainable in this disclosure are not limited to the solutions mentioned above, and other solutions not mentioned will be clearly understood by those skilled in the art to which this disclosure belongs from the description below. Effects of the invention

[0012] The effects of the Korean vocabulary learning system according to the present disclosure are described as follows.

[0013] According to some embodiments of the present disclosure, by precisely analyzing the learner's level, providing customized questions, and setting an optimized review cycle, the limitations of existing Korean language learning systems can be overcome and a more effective learning environment can be provided.

[0014] According to some embodiments of the present disclosure, by analyzing a sentence entered by a learner to determine the level of proficiency and identify weaknesses, learning content suitable for the individual learner's ability can be provided, and through this, the learner can learn questions of a difficulty level appropriate to their level, thereby acquiring vocabulary and grammar more efficiently.

[0015] In addition, according to some embodiments of the present disclosure, by applying Item Response Theory (IRT) to enable difficulty adjustment that reflects the learner's existing learning information and achievement level, it is possible to support the learner in learning continuously at an appropriate level, and by providing items optimized according to the learner's understanding and skill changes rather than a simple fixed difficulty level, the learner can engage in balanced learning without feeling overwhelmed or bored.

[0016] According to some embodiments of the present disclosure, by applying a modified Forgetting Spaced Repetition System (FSRS) algorithm to set a customized review cycle that takes into account the individual learner's learning pattern and forgetting curve, the learner can review at an appropriate time and convert learned content into long-term memory more effectively than existing forgetting curve-based review systems.

[0017] According to some embodiments of the present disclosure, by collecting and analyzing learner response data to evaluate learning progress and comprehension, learners can clearly grasp their learning situation and proceed with more systematic learning, thereby maximizing the efficiency of the learning process and providing a more sustainable and effective Korean language learning environment by reflecting the individual needs of learners.

[0018] The effects obtainable through the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs from the description below. Brief explanation of the drawing

[0019] Various embodiments of the present disclosure are described with reference to the drawings, wherein similar reference numbers are used to refer to collectively similar components. In the following embodiments, for illustrative purposes, a number of specific details are presented to provide a comprehensive understanding of one or more embodiments. However, it will be apparent that such embodiment(s) may be practiced without these specific details. FIG. 1 is a block diagram for illustrating an apparatus according to some embodiments of the present disclosure. FIG. 2 is a flowchart illustrating an example of a method for providing a Korean vocabulary learning system according to some embodiments of the present disclosure. Specific details for implementing the invention

[0020] Hereinafter, various embodiment(s) of the device and the method for controlling the device according to the present disclosure will be described in detail with reference to the drawings. Identical or similar components are given the same reference numeral regardless of the drawing symbols, and redundant descriptions thereof will be omitted.

[0021] The purpose and effects of the present disclosure, and the technical configurations for achieving them, will become clear by referring to the embodiments described in detail below in conjunction with the accompanying drawings. In describing one or more embodiments of the present disclosure, if it is determined that a detailed description of related prior art may obscure the essence of at least one embodiment of the present disclosure, such detailed description is omitted.

[0022] The terms of this disclosure are defined with consideration of their functions in this disclosure, and these may vary depending on the intentions or practices of the user or operator. Furthermore, the attached drawings are intended only to facilitate understanding of one or more embodiments of this disclosure, and the technical scope of this disclosure is not limited by the attached drawings; it should be understood that the technical scope of this disclosure includes all modifications, equivalents, and substitutions that fall within the spirit and technical scope of the invention.

[0023] The suffixes "module" and "part" for components used in the following description are assigned or used interchangeably solely for the ease of drafting this disclosure and do not have distinct meanings or roles in themselves.

[0024] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another. Accordingly, the first component mentioned below may be the second component within the technical scope of the present disclosure.

[0025] Singular expressions include plural expressions unless the context clearly indicates otherwise. That is, unless otherwise specified or the context does not make it clear that the singular form is indicated, the singular in this disclosure and claims should generally be interpreted to mean "one or more."

[0026] In this disclosure, terms such as “comprising,” “comprising,” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in this disclosure, and should not be understood as precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0027] In this disclosure, the term “or” should be understood as “or” in an implied sense, not in an exclusive sense. That is, unless otherwise specified or evident from the context, “X uses A or B” is intended to mean one of the natural implied substitutions. That is, where X uses A; where X uses B; or where X uses both A and B, “X uses A or B” may apply to any of these cases. Furthermore, the term “and / or” as used in this disclosure should be understood to refer to and include all possible combinations of one or more of the listed related items.

[0028] The expression 'at least one of A, B, and C' means one or more of the elements of the group consisting of A, B, and C, and should not be interpreted as requiring at least one of each of the listed A, B, and C, regardless of whether A, B, and C are related as categories.

[0029] The terms "information" and "data" as used in this disclosure may be used interchangeably.

[0030] Unless otherwise defined, all terms used in this disclosure (including technical and scientific terms) may be used in a meaning that is commonly understood by those skilled in the art of this disclosure. Additionally, terms defined in commonly used dictionaries are not to be over-interpreted unless specifically defined otherwise.

[0031] However, the present disclosure is not limited to the embodiments disclosed below but may be implemented in various different forms. Some embodiments of the present disclosure are provided merely to fully inform those skilled in the art of the scope of the present disclosure, and the present disclosure is defined only by the scope of the claims. Therefore, such definition must be based on the content throughout the present disclosure.

[0032] FIG. 1 is a block diagram for illustrating an apparatus according to some embodiments of the present disclosure.

[0033] The device (100) described in the present disclosure may include all devices that perform at least one of transmitting, receiving, and outputting data, content, service, and application, etc.

[0034] The device (100) of the present disclosure can be paired or connected with other devices, external servers, etc., through a wired / wireless network, and can transmit / receive certain data therefrom. In this case, the data transmitted / received through the device (100) can be converted before transmission / reception.

[0035] The device (100) of the present disclosure may include, for example, a standing device such as a PC (Personal Computer), a microprocessor, a mainframe computer, a digital processor, a device controller, etc., a mobile device or handheld device such as a smartphone, a tablet PC, a notebook, etc., and a server such as an application server, a computing server, a database server, a file server, a web server, etc. However, it is not limited thereto.

[0036] In the present disclosure, when a device (100) is referred to, its meaning may mean a computer system or computer device, a fixed device, a mobile device or a server depending on the context, and unless specifically stated otherwise, it may be used to include all of them.

[0037] The device (100) of the present disclosure can be paired or connected with a user terminal (200) through a wire / wireless network (300), and can transmit or receive certain data therefrom. In this case, the data transmitted or received through the wire / wireless network (300) may be converted before transmission or reception. Here, the term “wire / wireless network” (300) collectively refers to a communication network that supports various communication standards or protocols for pairing or / and data transmission and reception between the device (100) and the user terminal (200). Such a wire / wireless network (300) includes all communication networks currently or to be supported in the future by standards, and can support all one or more communication protocols for that purpose.

[0038] Referring to FIG. 1, the device (100) may include a processor (110), a storage unit (120), and a storage unit. Since the components illustrated in FIG. 1 are not essential for implementing the device (100), the device (100) described in this disclosure may have more or fewer components than those listed above.

[0039] Each component of the device (100) of the present disclosure may be integrated, added, or omitted according to the specifications of the device (100) actually implemented. That is, as needed, two or more components may be combined into one component, or one component may be subdivided into two or more components. Furthermore, the function performed in each block is intended to explain the embodiments of the present disclosure, and the specific operation or device thereof does not limit the scope of the present invention.

[0040] The processor (110) can control the overall operation of the device (100) in addition to operations related to the application. The processor (110) can provide or process appropriate information or functions by processing signals, data, information, etc. that are input or output through the components of the device (100) or by running an application stored in the storage unit (120).

[0041] The processor (110) can control at least some of the components of the device (100) to run an application stored in the storage unit (120). Furthermore, the processor (110) can operate at least two or more of the components included in the device (100) in combination with each other to run the application.

[0042] The processor (110) may be composed of one or more cores and may be any of the various commercial processors. For example, the processor (110) may include the device's central processing unit (CPU), general purpose graphics processing unit (GPGPU), tensor processing unit (TPU), etc. However, it is not limited thereto.

[0043] The processor (110) of the present disclosure may be configured as a dual processor or other multiprocessor architecture. However, it is not limited thereto.

[0044] A processor (110) can read and execute a computer program stored in a storage unit (120) to provide a Korean vocabulary learning system according to some embodiments of the present disclosure. Specifically, the processor (110) can analyze a sentence entered by a learner to determine the learner's proficiency level and perform operations to identify weaknesses. Based on these analysis results, the processor (110) can apply Item Response Theory (IRT) to select or generate items suitable for the learner's ability and adjust the difficulty of the items by reflecting the learner's previous learning data and achievement level.

[0045] The storage unit (120) can store data that supports various functions of the device (100). The storage unit (120) can store a number of application programs (or applications) running on the device (100), data for the operation of the device (100), instructions, and at least one program instruction. At least some of these application programs may be downloaded from an external server via wireless communication. Additionally, at least some of these application programs may exist on the device (100) from the time of shipment for the basic functions of the device (100). Meanwhile, the application programs may be stored in the storage unit (120), installed on the device (100), and driven by the processor (110) to perform the operation (or function) of the device (100).

[0046] Additionally, the storage unit (120) can store information of any form generated or determined by the processor (110), data received through the communication unit (130), and data such as the learner's learning history, achievement level, learning pattern, and review cycle. In particular, in the Korean vocabulary learning system according to the present disclosure, the storage unit (120) can record sentence data entered by the learner, proficiency information for each learner, results of vulnerability analysis, questions answered by the learner, and whether the questions are correct or incorrect. Based on this data, it can be used to track the learner's progress and provide customized learning content.

[0047] The storage unit (120) can store information of any form generated or determined by the processor (110) and information of any form received through the communication unit (130).

[0048] The storage unit (120) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. The device (100) may also be operated in connection with web storage that performs the storage function of the storage unit (120) on the internet.

[0049] Through this storage function, learners can manage their learning history in a cloud-based manner and save and synchronize their learning progress in real time. Through this, the device (100) can contribute to providing data analysis and an optimized learning environment tailored to individual learners.

[0050] The communication unit (130) may include one or more modules that enable wired / wireless communication between the device (100) and a wired / wireless communication system, another device, or an external server. Additionally, the communication unit (130) performs the role of connecting the device (100) to one or more networks and may be embedded in or externally mounted on the device (100) as a module for wired / wireless internet access. Through this, the device (100) can transmit and receive data using wired and wireless networks, and enables cloud-based data processing and remote learning support.

[0051] The communication unit (130) can transmit and receive wireless signals with a base station, an external terminal, or a server through a mobile communication network built according to technical standards or communication methods for mobile communication (e.g., GSM, CDMA, WCDMA, LTE, LTE-A, etc.). In addition, it can support various wireless internet technologies such as WLAN (Wireless LAN), Wi-Fi, Wi-Fi Direct, DLNA, WiBro, WiMAX, HSDPA, HSUPA, LTE, LTE-A, etc., and may also include other next-generation network technologies not included therein. Through this, the device (100) can transmit and receive data in real time while maintaining a stable network connection.

[0052] In particular, the Korean vocabulary learning system of the present disclosure can synchronize the learner's learning data by connecting to an external server or cloud through a communication unit (130). For example, sentences entered by the learner and learning progress can be stored on a cloud server and retrieved for analysis when necessary. Additionally, learning content updated in real time can be downloaded or the latest vocabulary information can be retrieved from an external database, thereby providing a more effective learning experience.

[0053] In addition, the communication unit (130) can transmit and receive data between the device (100) and surrounding devices by utilizing short-range communication technologies such as Bluetooth, RFID, infrared communication (IrDA), UWB, ZigBee, NFC, Wi-Fi Direct, and Wireless USB. For example, when a learner conducts learning using a smartphone or tablet, learning data can be automatically shared through pairing with the device (100), and continuous learning between multiple devices can be supported.

[0054] Additionally, the communication unit (130) can be connected to a test device via a wired / wireless network, thereby allowing for the evaluation of the learner's learning status or integration with a remote feedback system. For example, if a learner repeatedly records incorrect answers to a specific question, the device (100) can transmit the information to a server to provide customized additional learning content, or utilize an AI-based feedback system to analyze the learner's weaknesses and suggest improvement measures.

[0055] Through these communication functions, the Korean vocabulary learning system of the present disclosure can establish an intelligent learning environment capable of real-time data synchronization and the provision of customized learning content, rather than simple offline learning. Through this, learners can continuously manage their learning data in the cloud and effectively proceed with learning anytime and anywhere.

[0056] FIG. 2 is a flowchart illustrating an example of a method for providing a Korean vocabulary learning system according to some embodiments of the present disclosure.

[0057] Referring to FIG. 2, the processor (110) can determine the learner's proficiency level and identify the learner's weaknesses by analyzing a preset number of sentences (e.g., 10 or fewer) entered by the learner (S110). To do this, the processor (110) can evaluate the structure, vocabulary usage, grammatical accuracy, and semantic consistency of the sentences entered by the learner by executing a learning model and a natural language processing algorithm stored in a storage unit (120).

[0058] Specifically, the processor (110) can tokenize a sentence entered by a learner to extract individual words and phrases, and analyze the learner's overall language level by comparing them with predefined vocabulary and grammar rules. For example, to evaluate the difficulty of vocabulary used within a sentence, the processor (110) can refer to the usage frequency and CEFR (Common European Framework of Reference for Languages) level of each word by comparing them with a vocabulary difficulty database stored in the storage unit (120).

[0059] Additionally, the processor (110) can evaluate the grammatical accuracy and semantic appropriateness of a sentence written by a learner by performing syntactic analysis and semantic analysis. For example, the processor (110) can apply dependency parsing and part-of-speech tagging to examine subject-verb agreement, word order, and the correct use of particles and conjunctions in the sentence.

[0060] Subsequently, the processor (110) can determine the learner's proficiency by comparing the analysis results of the input sentence with the sentence data the learner has written in the past and identify the types of errors the learner consistently makes. For example, if the learner repeatedly makes errors in specific grammatical elements (e.g., honorifics, use of tenses, sentence ending expressions, etc.), the processor (110) can identify this as a weakness and record the areas requiring improvement of the learner in the storage unit (120).

[0061] Additionally, the processor (110) can analyze the learner's language patterns using a machine learning or deep learning model and automatically evaluate the learner's overall level based on this. For example, after comprehensively analyzing the learner's sentence writing style, vocabulary selection, error frequency, etc., the learner's level can be classified into beginner, intermediate, advanced, etc.

[0062] In this way, the processor (110) can determine the learner's ability by analyzing various elements of the input sentence and precisely identify the deficient areas, and based on this, can provide customized learning content so that the learner can acquire vocabulary and grammar more effectively.

[0063] Meanwhile, if the processor (110) determines the learner's proficiency level and identifies the learner's weaknesses in step (S110), it can derive items suitable for the learner's ability by applying Item Response Theory (IRT) based on the proficiency level and weaknesses, and adjust the difficulty of the items by reflecting the learner's existing learning information and achievement (S120).

[0064] In this disclosure, Item Response Theory (IRT) is a statistical model utilized in the fields of education and psychometrics. It is a technique that enables personalized assessment and question generation by mathematically modeling the relationship between a learner's ability and the difficulty of items. Unlike traditional total score-based assessment methods, IRT evaluates a learner's proficiency based on the probability of answering a specific item correctly and operates to maximize learning effectiveness by continuously providing items of the most appropriate difficulty level. IRT typically defines item characteristics based on three factors—difficulty, discrimination, and guessing—and can select appropriate items by comparing them with the learner's current ability level.

[0065] According to some embodiments of the present disclosure, in order to derive items suitable for the learner's ability, the processor (110) may identify proficiency levels and weaknesses by utilizing the analysis results of sentences input by the learner. The proficiency level may be determined by evaluating the complexity, vocabulary usage, grammatical accuracy, contextual consistency, etc., of the sentences input by the learner. For example, beginner learners may use simple sentence structures and basic vocabulary, whereas advanced learners may construct complex sentences and use various grammatical elements. Weaknesses refer to grammatical elements or the misuse of specific vocabulary that the learner repeatedly makes mistakes on, and the processor (110) may identify these patterns by analyzing the learner's past learning data.

[0066] In the present disclosure, existing learning information includes learning records and problem-solving history previously performed by a learner and can be utilized to analyze the learner's learning patterns. For example, if a learner consistently records incorrect answers on a specific type of grammar problem, that type can be identified as a weakness and prioritized for improvement in the future learning process. Additionally, existing learning information may include data such as the difficulty level, solution time, correctness, and achievement of specific learning goals of items previously encountered by the learner.

[0067] In the present disclosure, achievement is an indicator that evaluates how effectively a learner has acquired content while progressing with learning, and the processor (110) can measure this based on various factors. The achievement evaluation may generally include the correct answer rate of the learner solving problems, the pattern of incorrect answers, the learning speed, and the degree of improvement in repeated learning. For example, if the correct answer rate gradually improves when a learner solves the same type of problem multiple times, it can be determined that the achievement is increasing. Conversely, if the same mistakes are continuously repeated, it can be analyzed that additional learning is needed in that area.

[0068] In the present disclosure, the difficulty level of the questions may be adjusted to reflect the learner's achievement level so that individualized learning can be achieved. The processor (110) may increase the difficulty level if the learner maintains a certain level of correct answer rate, and conversely, adjust the difficulty level if incorrect answers persist, so that the learner can gradually improve. For example, if the learner correctly answers basic questions regarding a specific type of grammar in succession, the learning level may be raised by presenting questions containing more complex sentence structures. Conversely, for question types that the learner struggles with, questions containing additional explanations or modified questions with reduced difficulty may be provided to gradually improve understanding.

[0069] In this way, the processor (110) can utilize item response theory to provide items optimized for the learner's ability and enable the learner to gradually improve their language ability through continuous learning evaluation and difficulty adjustment. Through this, the learner can receive learning content tailored to their level, effectively compensate for weaknesses, and perform more efficient vocabulary and grammar learning.

[0070] Meanwhile, the processor (110) can adjust the difficulty of the questions in step (S120), provide the questions with adjusted difficulty to the learner, and collect the learner's response data to evaluate the learner's understanding and learning progress (S130).

[0071] Specifically, the processor (110) can adjust the difficulty of the questions based on the learner's existing learning data and achievement evaluation results, and provide the learner with questions with adjusted difficulty. More specifically, if the learner's achievement level increases, the processor (110) can provide questions of higher difficulty to enable the learner to continue challenging themselves, and conversely, if the achievement level is low or repetitive errors are found in specific grammatical elements, it can provide questions with lower difficulty to help the learner understand the concept more easily. For example, if the learner has difficulty with the tense changes of Korean verbs, the processor (110) can provide questions that explain the concept more clearly or provide questions that include example sentences to help the learner understand the concept easily.

[0072] After the questions are provided, the processor (110) can collect the learner's response data to analyze how accurately the learner solved the problem, the time taken to solve the problem, and the pattern of the answer selected by the learner. The response data is used as an important factor in identifying the learner's learning pattern, and through this, the processor (110) can quantitatively evaluate the learner's understanding. For example, if the learner solves a specific type of question quickly while having a high correct answer rate, it can be determined that the learner has sufficiently understood the concept. Conversely, if incorrect answers are repeated or the time taken to solve the problem becomes excessively long, it can be determined that the concept has not been sufficiently acquired and that additional learning is required.

[0073] In addition, the processor (110) can analyze long-term learning data to evaluate the learner's learning progress. Learning progress can be evaluated based on the learner's problem-solving history, changes in the correct answer rate, and whether the learning speed has improved over a certain period. For example, if a learner has answered 8 or more of the last 10 questions correctly and the time taken to solve the questions has been reduced, the learner may be considered to have sufficiently mastered a specific concept. On the other hand, if the learner continues to record incorrect answers on the same type of questions, the processor (110) may determine that the concept has not yet been fully mastered and may provide additional learning materials or gradually lower the difficulty level to enhance the learning effect.

[0074] Additionally, the processor (110) may perform response pattern analysis to more precisely evaluate the learner's understanding. If the learner repeatedly commits a specific type of error when selecting an incorrect answer, the processor (110) may identify this as a weakness of the learner and reflect it in subsequent problems. For example, if the learner confuses Korean particles (e.g., "i / ga" and "eun / neun"), the processor (110) may provide additional problems that emphasize the concept in the subsequent learning process.

[0075] This process supports learners in continuously performing learning at their level and can contribute to maximizing the effectiveness of learning. Ultimately, the processor (110) can provide an optimized learning path for individual learners by evaluating comprehension in real time based on the learner's response data and continuously monitoring learning progress. Through this, learners can systematically improve their skills and acquire Korean vocabulary and grammar more effectively.

[0076] After evaluating the learner's understanding and learning progress in step (S130), the processor (110) can set a review cycle and generate an optimized review schedule by applying a modified Forgetting Spaced Repetition System (FSRS) algorithm based on this (S140).

[0077] In the present disclosure, the Capture and Retrieval Spatial Repetition System (FSRS) algorithm may operate by adjusting the review cycle of individual learning items by considering the learner's memory retention rate and forgetting curve. While conventional simple repetitive learning methods involve reviewing the same content at fixed intervals, FSRS is characterized by dynamically adjusting the review timing by reflecting the learner's learning achievement and forgetting speed in real time. In the present disclosure, the FSRS algorithm is modified to reflect the learner's understanding and learning progress as additional variables, thereby enabling more precise optimization of the review cycle.

[0078] Specifically, the processor (110) can evaluate the learner's understanding by analyzing the correct answer rate of the questions answered by the learner, the time taken to solve the problems, and the repeated incorrect answer patterns. Understanding can be measured based on how accurately the learner solved the questions, how long it took to solve the problems, and whether the same mistakes are repeated. Additionally, learning progress is an indicator that evaluates the degree of improvement in the learning level based on the results of problem-solving performed by the learner over a certain period, and can be measured by reflecting changes in the learner's correct answer rate, whether the learning speed has improved, and the level of mastery of specific concepts.

[0079] The processor (110) can set the review cycle by applying the FSRS algorithm based on the evaluated understanding and learning progress. If the learner shows high understanding and a high correct answer rate on a specific question, the processor (110) can adjust the review cycle of that question by increasing it to allow the learner time to convert it into long-term memory. Conversely, if the learner consistently records incorrect answers on a specific concept, the processor (110) can set the review cycle of that question to be shorter so that the learner can review it more frequently. Additionally, if the learner's progress improves beyond a certain level, the processor (110) can gradually improve the learning level by adding questions of higher difficulty.

[0080] For example, when a learner first studies a question about "the difference between honorifics and informal speech," the processor (110) can set the initial review cycle to one day later. Afterwards, if the learner studies the question again and records a high correct answer rate, the processor (110) can induce long-term memory by gradually increasing the review cycle to 3 days, 7 days, 14 days, etc. On the other hand, if the learner consistently records incorrect answers on the same question, the processor (110) can adjust the review cycle to short intervals, such as one hour later, six hours later, 12 hours later, so that the learner can quickly supplement the concept.

[0081] Additionally, the processor (110) can generate a customized review schedule by reflecting the individual learning patterns of the learner. For example, if a particular learner is strong in vocabulary learning but struggles with grammar learning, the processor (110) can optimize the review schedule by shortening the review cycle for grammar-related questions and increasing the review cycle for vocabulary questions.

[0082] In this way, the processor (110) applies a modified FSRS algorithm to set a review cycle that reflects the learner's individual learning pattern, thereby enabling the learner to efficiently transfer learning content into long-term memory. Through this, the learner can reduce unnecessary repetition and receive an optimized review schedule tailored to their individual learning level and progress speed, making more effective Korean language learning possible.

[0083] Meanwhile, if the processor (110) has created a review schedule in step (S140), it can provide review questions to the learner according to the review schedule (S150).

[0084] In the present disclosure, review questions are generated in an optimized manner to enable learners to effectively review previously learned concepts, and may be configured to reflect the learner's understanding, achievement, learning patterns, etc.

[0085] In the process of generating review questions, the processor (110) analyzes the concepts learned by the learner, the correct answer rate, the time taken to solve the problems, and the types of repeated incorrect answers, and prioritizes selecting cases where a specific concept is not sufficiently mastered or is likely to be forgotten. For example, if a learner has learned a problem distinguishing between honorifics and informal speech in Korean, but the correct answer rate is low at 50% or less and the time taken to solve it is long, the processor (110) is likely to include the concept in the review questions.

[0086] Review questions can be generated by either providing previously offered questions exactly as they are, or by modifying existing questions to present them in a new format. Providing existing questions helps learners establish concepts by repeatedly solving the same problems, whereas providing modified questions can encourage learning the same concepts through a different approach. For example, if a learner solved a multiple-choice question asking, "Choose the sentence below that uses the correct honorific expression," the modified review question might be presented as an essay-type question such as, "Convert the following informal sentence into honorific language." Through this, learners can be guided to apply concepts to real-life situations beyond simple problem-solving.

[0087] Review questions may include multiple-choice, short-answer, fill-in-the-blank, sentence reconstruction, and context-based questions, and the question types may be adjusted to reflect the learner's level and understanding. For example, if a learner has learned the conjugation forms of verbs, basic review questions may be provided as multiple-choice questions such as "Choose the correct verb conjugation form among the following," but as the difficulty level increases, they may be transformed into short-answer questions such as "Complete the following sentence using the given verb."

[0088] Additionally, the processor (110) can adjust the difficulty of the review questions to reflect the learner's achievement. If the learner consistently answers a specific concept correctly, the difficulty of the review questions can be increased to include more complex sentence structures or modified so that the concept can be used naturally within the context. Conversely, if the learner repeatedly makes mistakes on the same concept, the difficulty of the review questions can be lowered to allow for relearning of the basic concept.

[0089] For example, if a learner has studied the difference between the Korean particles "은 / 는" and "이 / 가" but has a low level of understanding, review questions may be provided as multiple-choice questions, such as "Select the appropriate particle in the following sentence." If it is determined that the learner sufficiently understands the concept, the review questions may be changed to free-form descriptive questions, such as "Write a sentence explaining the given situation." Through this, learners can engage in more in-depth learning and develop the ability to apply concepts to actual communication.

[0090] In this way, the processor (110) generates review questions that reflect the individual learning pattern of the learner and provides them in an optimized manner, thereby supporting the learner to effectively supplement concepts that are lacking and to maximize long-term memory formation.

[0091] According to at least one of the embodiments of the present disclosure described above, there is an advantage in effectively supporting a learner's acquisition of vocabulary and grammar by providing customized learning content that reflects the learner's individual level and learning pattern, and by setting an optimized review cycle. In addition, by analyzing the learner's response data and dynamically adjusting the difficulty of learning, the learner can be provided with problems appropriate to their level and guided to solve problems of a progressively higher level. Through this, the learner can maximize long-term memory formation while minimizing unnecessary repetitive learning.

[0092] In the present disclosure, the device (100) is not limited to the configuration and method of the several embodiments described above, but may be configured by selectively combining all or part of each embodiment so that various modifications can be made to the several embodiments.

[0093] The various embodiments described in this disclosure may be implemented, for example, in a recording medium readable by a computer or similar device using software, hardware, or a combination thereof.

[0094] According to hardware implementation, some of the embodiments described herein may be implemented using at least one of application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, and other electrical units for performing functions. In some cases, some of the embodiments described in this disclosure may be implemented with at least one processor.

[0095] According to a software implementation, some embodiments, such as the procedures and functions described in this disclosure, may be implemented in separate software modules. Each of the software modules may perform one or more functions, tasks, and operations described in this disclosure. Software code may be implemented as a software application written in a suitable programming language. Here, the software code may be stored in a storage unit (120) and executed by at least one processor (110). That is, at least one program instruction may be stored in the storage unit (120) and at least one program instruction may be executed by at least one processor (110).

[0096] A method for at least one processor of an apparatus according to some embodiments of the present disclosure to provide a Korean vocabulary learning system may be implemented as code readable by at least one processor on a recording medium readable by at least one processor equipped in the apparatus. A recording medium readable by at least one processor includes all types of recording devices in which data that can be read by at least one processor is stored. Examples of recording media readable by at least one processor include Read Only Memory (ROM), Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0097] Meanwhile, although the present disclosure has been described with reference to the attached drawings, this is merely an example and is not limited to specific examples. Various modifications that can be made by those skilled in the art to which the invention pertains are also included within the scope of rights according to the claims. Furthermore, such modifications should not be understood individually from the technical spirit of the present invention.

Claims

Claim 1 A method for providing a Korean vocabulary learning system by means of a processor of a device, wherein the method comprises: a step of analyzing a predetermined number of sentences entered by a learner to determine the learner's proficiency level and to identify the learner's weaknesses; a step of deriving items suitable for the learner's ability by applying Item Response Theory based on the proficiency level and the weaknesses, and adjusting the difficulty of the items by reflecting the learner's existing learning information and achievement; a step of providing the items to the learner and collecting the learner's response data to evaluate the learner's comprehension and learning progress; a step of creating a review schedule by setting a review cycle by applying a modified Forgetting Spaced Repetition System (FSRS) algorithm based on the comprehension and the learning progress; and a step of providing review items to the learner according to the review schedule.

Images