Method for providing learner-personalized language learning service

Abstract

The present invention relates to a method for providing a learner-personalized language learning service and, more specifically, to a method for providing a learner-personalized language learning service, which is performed by a server and provides a Korean learning service to a foreign learner. The method comprises the steps of: preparing, by the server, an evaluation corpus including a learning corpus for allowing a learner to learn Korean and an error corpus in which an error made by the learner is expressed; receiving learner information input using a learner terminal; setting a Korean language ability level of the learner on the basis of the learner information; and allowing the learner to learn by using the evaluation corpus according to the set Korean language ability level of the learner. The present invention provides language learning data according to an individual language learning ability level of a learner and a subject desired by the learner, and enables personalized language learning to be performed for each learner, thereby improving learning efficiency and satisfaction.

Description

How to provide learner-customized language learning services

[0001] The present invention relates to a method for providing a learner-customized language learning service, and more specifically, to a method for providing a learner-customized language learning service that can provide a language learning service tailored to the learner's language level.

[0002] The Korean entertainment industry, including K-pop idols, dramas, and movies, enjoys immense popularity across Asia. Recently, it has been expanding its overall influence beyond Asia to the global stage, elevating South Korea's status through the fervent global popularity of K-pop and the Korean Wave. Furthermore, as the entertainment industry has also grown significantly in influence, it is showing strength in sectors such as online games and webtoons. Additionally, modern reinterpretations of traditional culture, such as Hanbok and Pansori, have begun to attract the attention of foreigners. Consequently, the number of foreigners residing in Korea for reasons such as studying abroad, employment, travel, and migration is increasing, and the number of people seeking to learn the Korean language is also on the rise.

[0003] Meanwhile, with the recent popularization of user terminals such as smartphones, tablet PCs, and PDAs (Personal Digital Assistants) and the advancement of information processing technology, dialogue processing systems that recognize user text or voice to facilitate interaction between the user and the terminal are being commercialized. A dialogue processing system is a technology that analyzes user utterances using a corpus upon detection and provides appropriate responses to the user. As the demand for language proficiency learning increases in the increasingly globalized modern society, research on applying dialogue processing systems to language learning systems is actively underway. Consequently, language learning systems support language learning by detecting grammatical errors in user utterances through text or speech recognition units that constitute the system, and by generating and providing corrective feedback regarding the detected errors. In this context, given that the performance and reliability of language learning can be determined by the accuracy of the feedback provided to the user, technology for providing grammatical error feedback is essential to enhance the performance of language learning systems.

[0004] (Prior Art) KR10-2277362 B

[0005] The present invention provides a method for providing a learner-customized language learning service that can provide language learning services tailored to the learner's language level.

[0006] The present invention provides a method for providing a learner-customized language learning service that can quickly correct errors made by the learner.

[0007] The problems that the present invention aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below.

[0008] A method for providing a learner-customized language learning service according to an embodiment of the present invention is performed by a server and is a method for providing a learner-customized language learning service to a foreign learner, and may include: a step of the server preparing an evaluation corpus including a learning corpus for teaching Korean to a learner and an error corpus expressing errors committed by the learner; a step of receiving learner information input by a learner terminal; a step of setting the learner's Korean proficiency level based on the learner information; and a step of teaching the learner using the evaluation corpus in accordance with the set learner's Korean proficiency level.

[0009] The process of preparing the above evaluation corpus may include a process of training the above learning corpus and the above error corpus using artificial intelligence.

[0010] The process of preparing the above-mentioned evaluation corpus may include at least one of the following: a process of classifying the above-mentioned learning corpus according to the learner's Korean language proficiency level; and a process of classifying the above-mentioned learning corpus according to learning topics.

[0011] The process of preparing the above-mentioned evaluation corpus may include: a process of collecting error sentences containing the above-mentioned errors; and a process of generating the above-mentioned error corpus by correcting the errors in the above-mentioned error sentences to generate correct sentences to be fed back to the learner terminal.

[0012] The above learner information further includes at least one of the learner's gender information, age information, occupation information, desired career path information, residential area information, period of residence in Korea information, and period of Korean language study information, and the process of setting the learner's Korean language proficiency level may include a process of testing the learner's Korean language proficiency level using the evaluation corpus based on at least one of the period of residence in Korea information and the period of Korean language study information.

[0013] The above training process includes: a process of transmitting a question to the learner terminal using the above training corpus; a process of receiving a response input to the learner terminal; and a process of determining whether there is an error in the response based on the above training corpus; and if there is no error in the response, the level of the response is evaluated using the above training corpus, and if there is an error in the response, feedback regarding the error can be transmitted to the learner terminal using the above error corpus.

[0014] The process of transmitting the above feedback may include transmitting the above error as a Korean correct answer sentence and a foreign language correct answer sentence translated into the language of the learner's country of origin.

[0015] The process of preparing the evaluation corpus further includes the process of collecting Korean corpora that have already been constructed or are being constructed, and the training process may transmit feedback regarding the error using the Korean corpora if there is an error in the response and the error cannot be determined by the error corpus.

[0016] The method further includes a process of determining the learner's Korean language proficiency level by analyzing the learner's learning content; and a process of updating the learner's information using the learner's learning content and the determined Korean language proficiency level; wherein the process of setting the learner's Korean language proficiency level may include a process of testing the learning content in which the learner made errors based on the updated learner information.

[0017] A method for providing a learner-customized language learning service according to an embodiment of the present invention may be performed by a computer program stored on a recording medium readable by a computer, combined with a computer which is hardware.

[0018] Other specific details of the present invention are included in the detailed description and drawings.

[0019] According to the present invention, by providing language learning data tailored to each learner's individual language learning ability level and desired topics, customized language learning can be conducted for each learner, thereby improving learning efficiency and satisfaction.

[0020] Furthermore, by identifying errors that foreigners commit while using the target language and preparing an error corpus containing correct answers in advance, model answers can be provided as feedback using this corpus when learners make errors during language learning. Consequently, learners can quickly identify and correct their errors.

[0021] In addition, since the learner's learning content is managed cumulatively, the content where the learner made errors in previous learning can be provided again to the learner's device, thereby preventing the learner from making the same errors again with the same learning content.

[0022] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0023] FIG. 1 is a block diagram of a learner-customized language learning service providing device according to an embodiment of the present invention.

[0024] FIG. 2 is a block diagram of a learning server constituting a learner-customized language learning service providing device according to an embodiment of the present invention.

[0025] FIG. 3 is a diagram exemplarily showing the structure of an evaluation corpus applied to a method for providing a learner-customized language learning service according to an embodiment of the present invention.

[0026] FIG. 4 is a flowchart illustrating a method for providing a learner-customized language learning service according to an embodiment of the present invention.

[0027] FIG. 5 is a flowchart illustrating the process in a method for providing a learner-customized language learning service according to an embodiment of the present invention.

[0028] 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 present invention, and the present invention is defined only by the scope of the claims.

[0029] The terms used in this specification are for describing 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. The terms "comprises" and / or "comprising" used in this specification do not exclude the presence or addition of one or more other components in addition to the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and "and / or" includes each of the mentioned components and all combinations of one or more. Although terms such as "first," "second," etc., are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another. Therefore, the first component mentioned below may be the second component within the technical scope of the invention.

[0030] Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0031] Some of the operations or functions described herein as being performed by a terminal, device, or device may instead be performed by a server connected to said terminal, device, or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal, device, or device connected to said server.

[0032] In this specification, some of the operations or functions described as mapping or matching with a terminal may be interpreted as meaning mapping or matching the terminal's unique number or personal identification information, which is the terminal's identifying data.

[0033]

[0034] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0035] FIG. 1 is a block diagram of a learner-customized language learning service providing device according to an embodiment of the present invention, FIG. 2 is a block diagram of a learning server constituting a learner-customized language learning service providing device according to an embodiment of the present invention, and FIG. 3 is a diagram exemplarily showing the structure of an evaluation corpus applied to a learner-customized language learning service providing method according to an embodiment of the present invention.

[0036] Referring to FIG. 1, a learner-customized language learning service provider according to an embodiment of the present invention may include a learner terminal (10) and a learning server (20). Additionally, although not illustrated, the learner-customized language learning service provider may further include an administrator terminal (not illustrated). Here, the learner may be a foreigner learning Korean, such as an overseas Korean. Although the learner-customized language learning service provider according to an embodiment of the present invention is described as being used to teach Korean to foreigners, it may also be used to teach various languages, such as English and Japanese, to foreigners. Furthermore, although the learner-customized language learning service provider according to an embodiment of the present invention is described as teaching the learner based on speech data spoken by the learner, such as voice data, it may also teach the learner based on text data. For example, the learner-customized language learning service provider may teach Korean by having the learner listen to and speak or write (text input) learning data provided as voice to the learner terminal. Alternatively, the learner-customized language learning service provider may teach Korean by reading and speaking learning data provided as text to the learner terminal.

[0037] The learner terminal (10) and the learning server (20), or the learner terminal (10), the learning server (20), and the administrator terminal can synchronize in real time and transmit and receive data using a wireless communication network. Wireless communication networks can support various long-distance communication methods, for example, Wireless LAN (WLAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX (World Interoperability for Microwave Access), GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), IEEE 802.16, Long Term Evolution (LTE), LTEA (Long Term Evolution-Advanced), Wireless Mobile Broadband Service (WMBS), BLE (Bluetooth Low Energy), Zigbee, RF (Radio Frequency), Various communication methods such as LoRa (Long Range) may be applied, but are not limited thereto; various widely known wireless or mobile communication methods may also be applied.

[0038] The learner terminal (10) can receive voice data spoken by the learner and can transmit the received voice data to the server (20) using a communication network. Alternatively, the learner terminal (10) can transmit text data entered by the learner to the learning server (20) via a communication network. The learner terminal (10) may include an input component (not shown), such as a microphone or a keypad, to input voice data, text data, etc. Additionally, the learner terminal (10) may include an output component (not shown), such as a display or a speaker, to output learning data provided by the learning server (20) as voice, text, video, etc.

[0039] The learner terminal (10) is connected to the server (20) in the form of an app or web, such as a smartphone or computer, and can receive user information such as the learner's gender, age, place of residence, occupation, period of residence in Korea, and period of Korean language learning entered by the user and transmit it to the server (20).

[0040] The learner terminal (10) is a terminal possessed by a learner who intends to use the learning service, and can operate using an application program (or application) in the present disclosure, and such application program can be downloaded from an external server or management server (20) via wireless communication. For example, the learner terminal (10) may include various terminals such as a smartphone, PDA (Personal Digital Assistant), tablet, wearable device (e.g., smartwatch, smartglass, HMD (Head Mounted Display), etc.), desktop, and various IoT (Internet of Things) terminals, but is not limited thereto.

[0041] The server (20) receives user information transmitted from the learner terminal (10) and can provide a Korean language learning service to the learner terminal (10) based on the user information.

[0042] Referring to FIG. 2, the server (20) may include a data transmission / reception unit (21), a data collection unit (22), a processor (23), and a database unit (24). Such a management server (20) may be implemented by a hardware circuit (e.g., a CMOS-based logic circuit), firmware, software, or a combination thereof. For example, it may be implemented using transistors, logic gates, and electronic circuits in the form of various electrical structures. Although FIG. 2 shows the database unit (24) mounted on or provided in the learning server (20), the database unit (24) may be provided independently of the learning server (20), such as in a cloud.

[0043] The data transmission and reception unit (21) can be connected to the learner terminal (10) via a communication network and can receive user information transmitted from the learner terminal (10). Additionally, the data transmission and reception unit (21) can transmit and receive various data for Korean language learning with the learner terminal (10). The various data for Korean language learning may include learning data, feedback data, learning analysis results, etc. transmitted from the learning server (20) to the learner terminal (10), and questions, answers, etc. input into the learner terminal (10) during the learning process.

[0044] The data collection unit (22) can collect corpora used for language learning, such as corpora prepared in advance to generate learning corpora and error corpora, through the data transmission and reception unit (21), and store them in the database unit (24). Here, the corpora prepared in advance refer to corpora that are publicly available in dictionaries, news APIs, blogs, websites, etc., and Korean corpora that have already been constructed or are being constructed.

[0045] Additionally, the data collection unit (22) can collect words, sentences, etc., containing errors committed by foreigners through the internet. At this time, the data collection unit (22) can extract utterances containing errors from the foreigner's speech as error sentences from blogs, documents, or videos that are directly posted by the foreigner or contain content of conversations by the foreigner, and store them in the database unit (24). Here, the errors may include particles, word choices, honorifics, informal speech, dialects, etc.

[0046] Additionally, the data collection unit (22) can automatically collect new words from the collected corpus or identify new words from keywords collected through crawling on the internet and store them in the database unit (24). The data collection unit (22) verifies the meaning, usage examples, and sources of the collected words, and can increase the reliability of the language learning service by performing automatic verification using sources from credible institutions such as AI or the National Institute of Korean Language Standard Korean Dictionary Open API. Additionally, the data collection unit (22) can collect Korean corpora that are currently built or are being built, identify the flow of Korean usage, and identify neologisms, coined words, slang, colloquialisms, etc., to generate a learning corpus and an error corpus.

[0047] The processor (23) can generate learning data for training a learner using data collected by the data collection unit (22), such as corpora, error sentences, new words, etc. At this time, the learning data may include a learning corpus to be provided to the learner according to the learner's language learning ability or learning topic, as shown in FIG. 3, and an error corpus to provide feedback for correcting errors made by the learner during language learning.

[0048] The processor (23) can retrieve corpora collected by the data collection unit (22) and stored in the database unit (24), and eliminate duplicates by comparing the similarity between the corpora. The processor (23) can generate learning corpora by level of Korean language proficiency by comparing them with internationally accepted standard Korean language curriculums or Korean language level standards tables disclosed by the National Institute of Korean Language, etc. For example, the processor (23) can generate learning corpora by classifying them into Level 1 learning corpora, Level 2 learning corpora, etc., according to the learner's level of Korean language proficiency. In addition, the processor (23) can generate learning corpora by subject of study, such as occupation, school (major), hobbies, and language proficiency tests (e.g., Korean Language Proficiency Test). For example, if the subject of study is occupation, the processor (23) can generate learning corpora by subject of study using words and sentences mainly used for each occupation. In this case, the learning corpora generated by subject of study can be classified into occupation learning corpora, school (major) learning corpora, hobby learning corpora, etc.

[0049] Additionally, the processor (23) can generate an error corpus using error sentences stored in the database unit (24). The processor (23) can generate a correct sentence by correcting or rectifying the error sentence, and can generate an error corpus by matching the error sentence with the correct sentence. For example, the error sentence may be a sentence with an incorrect particle or word choice, a sentence in which honorifics or informal speech are not used appropriately, or a sentence containing a dialect. The correct sentence may be a sentence in which particles or words are appropriately corrected, a sentence modified to use honorifics or informal speech depending on the situation, or a sentence in which a dialect is modified into standard language (e.g., Seoul dialect). Additionally, the processor (23) can generate a translation of the correct sentence into the language of the learner's country of origin, and can generate an error corpus by matching the error sentence, the correct sentence, and the translation. The error corpus generated in this way can be used to provide feedback of model answers to the learner terminal (10) so that the learner can identify and correct errors when the learner makes errors during language learning.

[0050] This processor (23) can analyze the learner's learning content to determine the learner's level of Korean language ability, and can update the learner information by combining the learning content and analysis results with the previously stored learner information and store it in the database unit (24). In addition, when the learner requests the provision of a learning service, the processor (23) can test the learner's language learning ability, such as Korean language learning ability, by providing the learning content in which errors were made in previous learning to the learner terminal (10) based on the learner information, that is, the updated learner information.

[0051] The processor (23) can generate an evaluation corpus containing a training corpus and an error corpus by training, verifying, and testing the collected corpora and words using artificial intelligence machine learning. At this time, machine learning may include symbolic inductive learning, a subsymbolic and connectionist approach, and probabilistic learning. Instance-based learning, decision trees, and inductive logic may be used for symbolic inductive learning; neural networks and genetic algorithms may be used for subsymbolic and connectionist approaches; and Bayesian network learning, hidden Markov models, and probabilistic grammar may be used for probabilistic learning. In addition, various machine learning methods such as active learning, boosting, reinforcement learning, and constructive induction may be used.

[0052] The database unit (24) can receive various information input into the learner terminal (10) and store it as learner information. Additionally, the database unit (24) can store various corpora, words, images, etc. collected by the data collection unit (22) as collected data. Furthermore, the database unit (24) can store learning corpora, error corpora, etc. generated by the processor (23) as evaluation corpora, and can store various data generated during the process of generating evaluation corpora. Additionally, the database unit (24) can store Korean corpora that have already been built or are being built as evaluation corpora.

[0053] This database section (24) may be mounted on the learning server (20), but may also be mounted on various storage devices spaced apart from the learning server (20).

[0054]

[0055] Hereinafter, a method for providing a learner-customized language learning service according to an embodiment of the present invention will be described. Content that overlaps with what has been previously explained will be briefly explained or omitted.

[0056] FIG. 4 is a flowchart illustrating a method for providing a learner-customized language learning service according to an embodiment of the present invention, and FIG. 5 is a flowchart illustrating a process in a method for providing a learner-customized language learning service according to an embodiment of the present invention.

[0057] A method for providing a customized language learning service for a learner according to an embodiment of the present invention is performed by a learning server (20) and is a method for providing a customized language learning service for a learner who is a foreigner, and may include: a process (S110) in which the learning server (20) prepares an evaluation corpus including a learning corpus for teaching Korean to a learner and an error corpus in which errors committed by the learner are expressed; a process (S120) of receiving learner information input into a learner terminal (10); a process (S140) of setting the learner's Korean proficiency level based on the learner information; and a process (S150) of teaching the learner using the evaluation corpus in accordance with the set learner's Korean proficiency level.

[0058] The process of preparing an evaluation corpus (S110) involves the data collection unit (22) of the learning server (20) collecting corpora used for language learning, such as corpora prepared in advance to generate learning corpora and error corpora, through the data transmission and reception unit (21), and storing them in the database unit (24). For example, the data collection unit (22) can collect learning corpora by accessing a news API or the National Institute of Korean Language, and can collect error corpora by accessing a blog, etc. Additionally, the process of preparing an evaluation corpus may further include the process of collecting Korean corpora that have already been built or are being built. These Korean corpora may be used when the errors committed by the learner are not found in the error corpora. Furthermore, the Korean corpora may be used to identify the usage flow of the Korean language and to identify neologisms, coined words, slang, colloquialisms, etc., in order to generate learning corpora and error corpora.

[0059] In addition, the process of preparing an evaluation corpus (S110) can automatically collect new words from the collected corpus or identify new words from keywords collected through crawling on the internet and store them in the database unit (24). At this time, the meaning, usage examples, and sources of the collected words are verified, and automatic verification is performed using sources from credible institutions such as AI or the National Institute of Korean Language Standard Korean Dictionary Open API, thereby increasing the reliability of the language learning service.

[0060] The process of preparing an evaluation corpus (S110) can generate a training corpus and an error corpus for training learners using data collected based on artificial intelligence, such as corpora, error sentences, and new words. The training corpus can be generated in stages according to the learner's language learning ability level, and can be generated by topic according to the learning topic. The error corpus can be generated by creating correct sentences by correcting or rectifying error sentences, and by matching the error sentences with the correct sentences. In this case, the error corpus may include translations of the correct sentences into the learner's country of origin language.

[0061] Such an evaluation corpus can be stored in the database section (24) of the learning server (20).

[0062] Meanwhile, the learning server (20) may receive a request (S120) for the provision of a language learning service through the learner terminal (10). At this time, if the learner is using the language learning service for the first time, learner information may be entered through the learner terminal (10) and transmitted to the learning server (20). The learner information may include the learner's country of origin, gender, age, occupation, hobbies, period of residence in Korea, period of Korean language learning (period of learning Korean through methods other than the relevant language learning service), etc. The learner information received in this way may be stored in the database unit (24).

[0063] And if the learner has previously used a language learning service, when a request for language learning service provision is received through the learner terminal (10), the learning server (20) can call the learner information stored in the database unit (24) and provide the language learning service according to the learner information.

[0064] In this way, when a request for the provision of a language learning service is received, the learning server (20) can test the learner's language ability (S130) by transmitting test data to the learner terminal (10) for a level test based on the learner information. At this time, the learner can perform a language ability or Korean language ability test using the test data transmitted to the learner terminal (10). The learner may input a response to the test data transmitted to the learner terminal (10) in voice, or may input it in text, etc., through an input device such as a keypad.

[0065] In this way, the learner's Korean language proficiency level is set through a test (S140), and the learning server (20) transmits learning data to the learner's terminal (10) according to the learner's Korean language proficiency level to perform language learning, such as Korean language learning (S150).

[0066] Referring to FIG. 5, the learning server (20) can select a learning corpus (S151) based on the set learner's language ability level and transmit learning data, such as questions (S152), to the learner terminal (10). The learner inputs a response to the learner terminal (10) in voice or text according to the learning data, and the learner terminal (10) can transmit the response to the learning server (20) (S153). At this time, the learning server (20) may request the learner terminal (10) to select a learning topic before transmitting the learning data to the learner terminal (10). However, the learning server (20) is not limited to this and may transmit the learning data to the learner terminal (10) according to a predetermined learning progress (curriculum).

[0067] The learning server (20) receives a response from the learner terminal (10) and can evaluate the learner's Korean language ability using a pre-prepared evaluation corpus. At this time, the learning server (20) can determine whether there is an error in the learner's response by using a learning corpus among the evaluation corpora (S154). If there is no error in the learner's response, the learning server (20) can determine the learner's level of Korean language ability by analyzing the learner's learning content (S157). On the other hand, if there is an error in the learner's response, the learning server (20) can select an error corpus (S155) and determine the error committed by the learner using the selected error corpus. Then, the learning server (20) can generate the error sentence and the correct sentence, such as a model answer, for the error committed by the learner and provide feedback (S156) to the learner terminal (10). At this time, the learning server (20) may also provide a translation of the error sentence and the correct sentence into the learner's country of origin language along with the Korean error sentence and the correct sentence. This enables learners to easily and accurately identify errors made during learning, thereby helping them avoid repeating those errors.

[0068] Meanwhile, if the error committed by the learner cannot be determined using the selected error corpus, feedback on the error committed by the learner may be generated using Korean corpora that are already built or are being built and transmitted to the learner terminal (10).

[0069] Korean language learning is performed in this manner, and the learning server (20) can analyze the learner's learning content to determine the learner's language ability level (S157).

[0070] Additionally, the learning server (20) can provide feedback on the learning results to the learner terminal (10), for example, by notifying the learner of their language proficiency level (S158), and store the learner's learning results in the database unit (24). At this time, the learning server (20) can update user information (S159) by matching and storing the learner's language proficiency level, for example, their Korean language proficiency level, with user information. Additionally, the learning server (20) can perform subsequent language learning based on the updated user information. For example, the learning server (20) can test the learner during subsequent language learning by using errors the learner made in the previous language learning.

[0071]

[0072] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0073] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive.

[0074] The present invention can help foreign learners adapt to social life in another country by providing language learning data tailored to the individual foreign learner's level of language learning ability and the topics desired by the learner.

Claims

1. A method for providing a learner-customized language learning service to a foreign learner, which is performed by a server and provides Korean language learning services to a foreign learner, A process in which a server prepares an evaluation corpus that includes a training corpus for teaching Korean to a learner and an error corpus that expresses errors made by the learner; A process of receiving learner information input via a learner terminal; and A process of setting the learner's Korean language proficiency level based on the above learner information; and A method for providing a learner-customized language learning service, comprising: a process of training the learner using the evaluation corpus according to the set Korean language proficiency level of the learner.

2. In Claim 1, A method for providing a learner-customized language learning service, wherein the process of preparing the above-mentioned evaluation corpus includes the process of training the above-mentioned learning corpus and the above-mentioned error corpus using artificial intelligence.

3. In Claim 2, The process of preparing the above-mentioned evaluation corpus is, A process of classifying the above-mentioned learning corpus according to the learner's Korean language proficiency level; and A method for providing a learner-customized language learning service comprising at least one of the following: a process of classifying the above learning corpus by learning topic.

4. In Claim 3, The process of preparing the above-mentioned evaluation corpus is, The process of collecting error sentences containing the above error; and A method for providing a learner-customized language learning service, comprising the process of generating an error corpus by correcting errors in the above error sentences and generating a correct sentence to be fed back to the learner terminal.

5. In Claim 4, The above learner information further includes at least one of the learner's gender information, age information, occupation information, desired career path information, residential area information, period of residence in Korea information, and period of Korean language learning information, and A method for providing a customized language learning service for learners, comprising the process of setting the Korean language proficiency level of the learner, which includes testing the learner's Korean language proficiency level using the evaluation corpus based on at least one of the information on the period of residence in Korea and the information on the period of learning Korean.

6. In Claim 4, The above-mentioned training process is, A process of transmitting a question to the learner terminal using the above-mentioned learning corpus; A process of receiving a response input via the above-mentioned learner terminal; and A process for determining whether there is an error in the response based on the above-mentioned training corpus; including If there are no errors in the above response, the level of the above response is evaluated using the above training corpus, and A method for providing a learner-customized language learning service that, if there is an error in the above response, transmits feedback on the error to the learner terminal using the above error corpus.

7. In Claim 6, A method for providing a learner-customized language learning service, wherein the process of transmitting the above feedback includes transmitting the above error as a correct Korean sentence and a correct foreign language sentence translated into the language of the learner's country of origin.

8. In Claim 6, The process of preparing the above-mentioned evaluation corpus further includes the process of collecting Korean corpora that have already been constructed or are being constructed, and The above-mentioned training process is a method for providing a learner-customized language learning service that transmits feedback on the error using the above-mentioned Korean corpora when there is an error in the above-mentioned response and the error cannot be determined by the above-mentioned error corpus.

9. In Claim 1, The method further includes: a process of determining the Korean language proficiency level of the learner by analyzing the learner's learning content; and a process of updating the learner information using the learner's learning content and the determined Korean language proficiency level. A method for providing a customized language learning service for learners, wherein the process of setting the Korean language proficiency level of the learner includes a process of testing the learning content in which the learner made errors based on updated learner information.

10. A computer program stored on a computer-readable recording medium that is combined with a computer, which is hardware, to perform the method of any one of claims 1 to 9.

Images