KR102355960B1 - System for providing qualification verification based korean language training service - Google Patents

Abstract

The present invention relates to a system for providing a qualification verification-based Korean language education service. The system includes: a user terminal for outputting at least one instructor profile, selecting one instructor, and entering a class in real time and then carrying out a lesson; an instructor terminal for registering as an instructor based on at least one qualification verification and carrying out a real-time lecture based on selection from the user terminal; and an education service providing server including a registration unit setting at least one qualification and registering at least one instructor terminal with at least one qualification verification to build an instructor pool, an upload unit uploading profile information input from at least one instructor terminal, and a lecture management unit enabling a real-time lecture between the instructor and user terminals in a case where one instructor is selected on the user terminal.

Description

SYSTEM FOR PROVIDING QUALIFICATION VERIFICATION BASED KOREAN LANGUAGE TRAINING SERVICE}

The present invention relates to a system for providing Korean language education services based on qualification condition verification, and provides a platform for educating foreigners by connecting a foreigner with a verified instructor who can pronounce accurate Korean like an announcer.

As Korea recently implemented a policy of internationalization of higher education and the ratio of foreign Korean language learners enrolled in domestic universities has increased, research on academic performance, relationships between enrolled Korean students, and class delivery ability for foreign Korean language learners continues. are doing Foreigners' acquisition of Korean is similar to how Koreans acquire a second foreign language, and their mother tongue influences their acquisition of a foreign language. can be Looking at the Korean phonetic system, phonemes are located at the beginning, middle, and final consonants, and when going to the syllable level, they are composed of the beginning, the middle, and the end. While a language such as English is described horizontally, it may be difficult for a foreigner to calculate the pronunciation of a vertical sound like Korean.

At this time, a platform that connects instructors and learners through online for foreigners learning Korean as a second language was researched and developed. Published) and Korean Patent Publication No. 2021-0003326 (published on January 12, 2021) for foreigners who want to learn Korean, a Korean native speaker living in Korea provides an educational service through an optimized solution through one-on-one video. , a configuration that builds a content database for learning specialized in Korean language education and educates through it, and receives user information including the first language of the user terminal, registers a user, and at least the user information of the user terminal and at least Instructor information of one instructor terminal is compared and matched, user information is transmitted to the matched instructor terminal to assign a user, and a channel is formed between the user terminal and the instructor terminal at the speaking time in the preset curriculum to transmit and receive data. , a configuration for outputting at least one content included in a preset curriculum in a user terminal in synchronization with time is disclosed.

However, since most languages comprise short vowels, which are the standard vowel for vowel squareness, the acoustic characteristics of vowels are different for each language producing country. Even though the same English is used, the pronunciation of each country is different. Since vowels convey pronunciation accompanied by consonants and distinguish speech sounds by the difference in resonant frequencies of speech sounds, it is difficult to even perceive resonant frequencies for vowels that do not exist in foreigners' native languages, and they are converted into similar vowels based on their native language pronunciation. will yield Therefore, the calculation of Korean pronunciation by foreigners is based on the phonological characteristics of the native language, which interferes with the perception and understanding of the Korean phonological characteristics. Therefore, research and development of a platform with expertise is required to connect natives who are qualified to use accurate Korean pronunciation and foreigners who want to learn Korean as a second language.

In one embodiment of the present invention, only broadcasters including an announcer who is qualified to use accurate Korean pronunciation are qualified as teachers to teach Korean, and the profile of each instructor is disclosed so that foreign students can select a teacher, Teachers must be limited to those who have received announcement training or those who are broadcasting, providing the opportunity to receive education to those who can best convey Korean. A Korean language education service based on qualification verification that allows you to identify the vowels and differences produced by Koreans in sentences, and that can be used as basic information in the pronunciation guidance of foreigners based on the patterns calculated by acoustically analyzing the pronunciation of foreigners A method of providing may be provided. However, the technical task to be achieved by the present embodiment is not limited to the technical task as described above, and other technical tasks may exist.

As a technical means for achieving the above-described technical task, an embodiment of the present invention provides a user terminal that outputs at least one instructor profile, selects any one instructor, enters the class in real time, and then proceeds with the class, at least Instructor is registered as an instructor with one qualification condition verification, sets a teacher terminal that conducts a real-time lecture by selecting a user terminal, and at least one qualification condition, and registers at least one instructor terminal with at least one qualification condition verification A registration unit for building a pool, an upload unit for receiving and uploading profile information from at least one teacher terminal, and a lecture management unit for real-time lectures between the instructor terminal and the user terminal when any one instructor is selected from the user terminal It includes an education service providing server comprising a.

According to any one of the above-described problem solving means of the present invention, only broadcasters including announcers who are qualified to use accurate Korean pronunciation are qualified as instructors to teach Korean, and the profile of each instructor is disclosed so that foreign students can learn. Instructors must be selected, and the instructors must be limited to those who have received announcement training or those who are broadcasting, so that those who can best communicate the Korean language can receive an opportunity to receive education, and learn the theory that the announcers have been trained in for announcements. By applying it to foreigners as it is, it is possible to understand the vowels and differences produced by Koreans in natural sentences. After passing the test by dividing the level, you can issue a speech certificate issued by the Speech Association.

1 is a view for explaining a system for providing a Korean language education service based on qualification condition verification according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating an education service providing server included in the system of FIG. 1 .
3 and 4 are diagrams for explaining an embodiment in which a Korean language education service based on qualification condition verification according to an embodiment of the present invention is implemented.
5 is an operation flowchart illustrating a method of providing a Korean language education service based on qualification condition verification according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated, and one or more other features However, it is to be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded in advance.

The terms "about", "substantially", etc. to the extent used throughout the specification are used in or close to the numerical value when manufacturing and material tolerances inherent in the stated meaning are presented, and are intended to enhance the understanding of the present invention. To help, precise or absolute figures are used to prevent unfair use by unconscionable infringers of the stated disclosure. As used throughout the specification of the present invention, the term "step of (to)" or "step of" does not mean "step for".

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware. Meanwhile, '~ unit' is not limited to software or hardware, and '~ unit' may be configured to be in an addressable storage medium or to reproduce one or more processors. Thus, as an example, '~' denotes components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functions provided in the components and '~ units' may be combined into a smaller number of components and '~ units' or further separated into additional components and '~ units'. In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

Some of the operations or functions described as being performed by the terminal, apparatus, or device in the present specification may be performed instead of by a server connected to the terminal, apparatus, or device. Similarly, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the terminal's unique number or personal identification information, which is the identification data of the terminal. can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining a system for providing a Korean language education service based on qualification condition verification according to an embodiment of the present invention. Referring to FIG. 1 , the system 1 for providing Korean language education services based on qualification condition verification includes at least one user terminal 100 , an education service providing server 300 , at least one instructor terminal 400 , and at least one administrator. The terminal 500 may be included. However, since the system 1 for providing Korean language education service based on qualification condition verification of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1 .

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1 , at least one user terminal 100 may be connected to the education service providing server 300 through the network 200 . In addition, the education service providing server 300 may be connected to at least one user terminal 100 , at least one instructor terminal 400 , and at least one administrator terminal 500 through the network 200 . In addition, the at least one instructor terminal 400 may be connected to the education service providing server 300 through the network 200 . In addition, the at least one manager terminal 500 may be connected to the at least one user terminal 100 , the education service providing server 300 , and the at least one instructor terminal 400 through the network 200 .

Here, the network refers to a connection structure in which information exchange is possible between each node, such as a plurality of terminals and servers, and an example of such a network includes a local area network (LAN), a wide area network (WAN: Wide Area Network), the Internet (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television networks, and the like. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi (Wi-Fi) , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC ( Near-Field Communication) networks, satellite broadcast networks, analog broadcast networks, Digital Multimedia Broadcasting (DMB) networks, and the like are included, but are not limited thereto.

In the following, the term at least one is defined as a term including the singular and the plural, and even if the at least one term does not exist, each element may exist in the singular or plural, and may mean the singular or plural. it will be self-evident In addition, that each component is provided in singular or plural may be changed according to embodiments.

The at least one user terminal 100 may be a terminal of a user who wants to learn Korean by using a web page, an app page, a program, or an application related to a Korean language education service based on qualification condition verification. In this case, the user may be a foreigner who wants to learn Korean as a second foreign language, but may be a Korean who wants to correct pronunciation or learn Korean. In this case, the user terminal 100 may be a terminal that accesses the education service providing server 300 , outputs the instructor's profile, selects the instructor, and then participates in the class. Here, the user terminal 100 may be connected one-to-one with the instructor, but may be a terminal capable of participating in various class types such as one-to-many, many-to-many, and many-to-one according to embodiments.

Here, the at least one user terminal 100 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100 is, for example, as a wireless communication device that guarantees portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smart phone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

The education service providing server 300 may be a server that provides a Korean language education service web page, an app page, a program or an application based on qualification condition verification. And, the education service providing server 300, when receiving a profile registration from the instructor terminal 400 in order to verify the qualification of the at least one instructor terminal 400, whether it is a person who has actually received an announcement training, a broadcaster, or an announcer It may be a server that verifies and receives registration. In addition, the education service providing server 300 may be a server that allows the user terminal 100 to participate in a real-time class when a verified instructor's profile is uploaded and the instructor is selected by the user terminal 100 . In addition, the education service providing server 300 collects the ratings and reviews of each instructor from the user terminal 100 and accumulates them as a log, divides the speech, which is the speech of the user terminal 100 by level, and performs the test It may be a server that issues a certificate issued by the association.

Here, the education service providing server 300 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop.

The at least one instructor terminal 400 may be a terminal of an instructor using a web page, an app page, a program, or an application related to the Korean language education service based on qualification condition verification. In this case, the instructor terminal 400 may be a terminal that transmits a profile to the education service providing server 300 in order to prove his/her career or qualifications and allows viewing of qualifications of each institution in a block chain to be described later. have. When registration is completed after the qualification verification of the instructor terminal 400 is completed, it may be a terminal connected to the user terminal 100 and a real-time lecture. Also, the instructor terminal 400 may be a terminal that receives reviews and ratings of each user terminal 100 as feedback.

Here, the at least one instructor terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one instructor terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one instructor terminal 400, for example, as a wireless communication device that guarantees portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smart phone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

The at least one manager terminal 500 may be a terminal that determines whether to register by verifying each instructor using a web page, an app page, a program, or an application related to the Korean language education service based on qualification condition verification.

Here, the at least one manager terminal 500 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, navigation, a laptop equipped with a web browser, a desktop, and a laptop. In this case, the at least one manager terminal 500 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one manager terminal 500, for example, as a wireless communication device that guarantees portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) terminal, a smart phone, a smart pad, a tablet PC, etc. may include all kinds of handheld-based wireless communication devices.

2 is a block diagram for explaining an education service providing server included in the system of FIG. 1, and FIGS. 3 and 4 are an embodiment in which a qualification condition verification-based Korean language education service according to an embodiment of the present invention is implemented. It is a drawing for explaining.

Referring to FIG. 2 , the education service providing server 300 includes a registration unit 310 , an upload unit 320 , a lecture management unit 330 , a speech unit 340 , a storage unit 350 , a comparison unit 360 , It may include a vowel analysis unit 370 , an image unit 380 , an evaluation unit 390 , and a block chain unit 391 .

At least one user terminal 100 , at least one instructor terminal 400 , and at least one administrator terminal may include the education service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with each other. When transmitting a qualification condition verification-based Korean education service application, program, app page, web page, etc. to 500, at least one user terminal 100, at least one instructor terminal 400, and at least one administrator terminal ( 500) may install or open a Korean language education service application, program, app page, web page, etc. based on qualification condition verification. In addition, the service program may be driven in at least one user terminal 100 , at least one instructor terminal 400 , and at least one administrator terminal 500 by using a script executed in a web browser. Here, the web browser is a program that enables the use of a web (WWW: World Wide Web) service, and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, and the like. In addition, the application means an application on the terminal, for example, includes an app (App) executed in a mobile terminal (smartphone).

Before describing Figure 2, in an embodiment of the present invention, the basic concept of whether each instructor is limited to a person who has received an announcement education, an announcer, or a broadcaster will be described. The concepts described below do not overlap in describing FIG. 2 .

Even if the physical vocal structure is innate, a good voice cannot be produced if the relevant organs are not properly controlled. The physical mechanism of speech starts from air pressure in the lungs, passes through the vocal cords and the trachea, and is discharged from the soft palate into the oral cavity and nasal cavity. Due to this series of physical processes, the voice reflects the innate body characteristics, but the brain controls the movement of muscles and the content of speech to control all these organs.

Announcer is the most textbook job related to speaking. This is because a news announcer is a professional profession specialized in information delivery, which is the most basic role of speaking. Jobs in which the voice plays a very important role are typically singers, voice actors, or announcers. Although there are various occupations in which the voice is important, the required voice characteristics are markedly different depending on each occupation or the corresponding position. As a singer is a profession that expresses music through songs, the vocal characteristics of the general speaking state are outside the area of interest, and the key to expressing the song is the tone and method of singing. Therefore, it is important to develop one's own singing method or tone according to the genre of music, the voice corresponding to oneself, and one's own voice characteristics, and to learn vocal skills when singing. For singers, it is a part where they have to learn the basics of how to sing a song and constantly hone it. However, since artistry is important to music, the final key lies in expressing one's own unique personality. It is also a job where factors other than singing have a lot of influence depending on the situation.

The most professional job purely related to voice is voice acting. A voice actor is a job that expresses everything through voice, so basic vocalization and pronunciation skills must be very good. You need to be able to control your vocalization more freely than anyone else, so you can develop your own voice, change your voice according to each situation, and digest various roles. Likewise, it is important for voice actors to have their own unique voice characteristics as well as the basic required vocal ability.

Finally, the announcer can be selected as a job where voice is important. The basic purpose of an announcer is to deliver information, and there are some differences in the basic vocal characteristics required depending on which program the announcer is. . The advantage is that it is relatively easy to compare objectively compared to other voice occupation groups. News anchors are stricter than any other occupational group on the most basic elements of speaking due to the nature of their job, and they pursue the intellectual and ideal form of speech that the people want. Therefore, if a foreigner learns the voice characteristics of the main announcer for each dispatcher as it is, the most accurate and clear speech technique can be learned. In one embodiment of the present invention, only those who have received the announcement education verify and secure the instructor.

Referring to FIG. 2 , the registration unit 310 sets at least one qualification condition and registers the at least one instructor terminal 400 with at least one qualification condition verification to build a pool of instructors. . At least one qualification condition may be any one of a person who has received an announcement education, a broadcaster, and an announcer.

The upload unit 320 may receive and upload profile information from at least one instructor terminal 400 . If a lecture is being held in real time, the available lecture schedule can be updated in real time. This is because, for example, in a real-time class with n students, if n students are full, you cannot participate in the lecture even if you select the corresponding instructor.

The lecture management unit 330 may enable a real-time lecture between the instructor terminal 400 and the user terminal 100 when any one instructor is selected from the user terminal 100 . The user terminal 100 may output at least one instructor profile, select any one instructor, enter the class in real time, and then proceed with the class. The instructor terminal 400 may be registered as an instructor by verifying at least one qualification condition, and may conduct a real-time lecture by selecting the user terminal 100 . In this case, the class may include textbook classes and pre-talking.

The speech unit 340 may issue a speech certificate issued by a preset institution or association after performing a Korean speech test by dividing the user's level of the user terminal 100 . At this time, the user may be not only foreigners residing in Korea, but also foreigners who want to learn Korean thanks to the revival of Hallyu culture, and it is of course possible to educate them. In particular, in Southeast Asia, such as Vietnam, Korean language is designated as the first foreign language and there is a high demand for Korean language education. Here, announcers and broadcasters are those whose qualifications to best convey the Korean language have been verified through tests such as public recruitment and through viewers, those who have received announcement training receive certificates of completion, and broadcasters and announcers receive employment certificates and career certificates. can be verified through At this time, the judges who judge the test may be limited to broadcasters, announcers, and those who have received announcement training. Of course, it is also possible not to limit to these.

The storage unit 350, using the speech data collected from the at least one instructor terminal 400, the pitch (Pitch), the first formant (Formant, F1) and pitch ratio, the pitch bandwidth, the average within the pitch bandwidth A database can be built by collecting acoustic tone analysis data including pitch position and speech velocity. At this time, the pitch is expressed as a frequency (Frequency) as the height of the sound.

<F1 and pitch ratio>

The formant is one of the important factors determining the fundamental characteristics of an individual's voice. In the case of pitch, it is possible to sufficiently change through the adjustment of the vocal cords and it is possible to produce a natural voice within an appropriate level, but there is a limit to artificial adjustment because the first formant F1 is related to the fundamental length of the vocal cords. When F1 is determined, the second formant F2 is proportionally calculated according to which vowel is calculated, and thus follows the frequency characteristic of F1. For example, when representing the ratio relationship between F1 and pitch, the average female average pitch used for the ratio comparison of F1/F0 may be used. F1 basically reflects the size of the body, so it is lowered in the order of children, women, and men. Listening A low F1 in the natural normal range affects the weight and stability of the voice. On the other hand, if the F1 is high, it will affect the relatively light and youthful feeling. This reflects the overall voice characteristics of men, women, and children. Also, depending on F1, both F2 and F3 frequencies are affected, and this affects the overall frequency resonance shape. On the other hand, the higher the ratio of pitch to F1, the more subdued the voice. This is different from the absolute pitch of the pitch.

<pitch bandwidth>

Since the vocal structure and characteristics of a person, including the vocal cords, are innate factors, the pitch suitable for one is determined to some extent. On the other hand, the pitch bandwidth in a speaking situation is not related to the innate vocal structure, and can be interpreted as a measure to determine how fluidly the speaker is speaking from the basic pitch. The pitch bandwidth reflects how dynamically the pitch change moves. In rigid situations or depressed emotions, the vocal cords are less active, and the most representative example is the vocalization of a robot.

A typical robot vocalization has a constant pitch, so the pitch bandwidth is very narrow, and this is a typical example of a hypothetical expression of blunt emotion. Conversely, in order to elicit feelings for the other party or to increase the ability to deliver targeted content, it is inevitably necessary to increase the activity of the vocal cords. An artificial excessive pitch bandwidth may be unnatural to listen to, but a narrow pitch bandwidth inevitably lowers concentration and inevitably gives boredom. After all, it is advantageous to have a wide pitch bandwidth if it is within the level at which the listener can hear it naturally.

Accordingly, when the overall pitch height and frequency characteristics and the pitch bandwidth and bandwidth ratio of each instructor are represented as the average spectrum around the pitch, it can be a reference value to compare with the user's vocalization. The human sense of frequency is close to log scale, as can be seen in scales that increase in multiples per octave. Therefore, the bandwidth ratio according to the position of the pitch, not the linear pitch bandwidth, is meaningful. Here, the pitch bandwidth is the range from the center frequency with the greatest energy in the pitch range of the entire average spectrum of the speaker's speech until the energy drops by 3dB, and the bandwidth ratio is the value obtained by dividing the average pitch again.

<Average pitch position within the pitch bandwidth>

Humans have a tendency to go down to a low tone when ending a sentence. That is, the position of the average pitch within the pitch bandwidth is determined according to the time invested in finishing the sentence or the slope of the curve that lowers the pitch. For example, based on the position occupied by the average pitch in the pitch bandwidth, the ratio of the low-pitched tone to the high-pitched tone in the pitch bandwidth in consideration of the auditory characteristics may be considered in relation to intonation. The average pitch mainly indicates only the used pitch, but the ratio of the low and high frequencies can be divided through the location of the average pitch within the pitch bandwidth. If the ratio of the low frequency band of the corresponding figure is high, the speaker tends to finish the sentence calmly at the end of the sentence or at the middle comma. Conversely, if the low-pitched tone ratio is low, it reflects the tendency to finish sentences relatively quickly.

The F0 descending slope of the sentence ending also affects the impression. This figure does not represent the entire sentence ending vocal characteristics, and it is not possible to distinguish between good and bad vocal characteristics of the instructor. F _LP in Equation 1 below is the position ratio of the low-pitched band occupied by the average pitch in the pitch bandwidth, and the position ratio of the high-pitched band is F _HP . Here, F _L and F _H represent the minimum and maximum frequencies of the pitch bandwidth, respectively, and F _C is the average pitch.

<Firing rate>

Speech rate is a measure of how many words a speaker utters per second and indicates how fast he or she speaks. Since the appropriate speed differs depending on which sentence is spoken and in which situation, it is not known whether the speed is well controlled only with the average speech speed, but it is possible to grasp the speed tendency to a certain extent through the average. In this case, the criterion for measuring the speed may be the number of syllables per second (SPS).

When the user terminal 100 recognizes the speech utterance, the comparator 360 extracts a factor in which a difference occurs after comparison based on the acoustic tone analysis data and transmits it to the user terminal 100 . have. For example, even in countries where the same English is spoken, the pronunciation of English is different in each region. In India, England, North America, Australia, etc., pronunciations are so different that it is thought that they speak different languages, and each region and country is different even if they speak the same language. Also, just as Korean pronunciation of English, Japanese pronunciation of English, and Chinese pronunciation of English are different, the influence of mother tongue on Korean pronunciation is large for each country. There may be Korean pronunciations that are impossible for each country, and there is a difference that occurs because consonants or vowels that are not in the country have to be pronounced even when the same Korean pronunciation is used.

Accordingly, by accumulating the acoustic tone analysis data of foreigners, the comparator 360 can prepare a data base for studying the characteristics of each foreigner's region, country, and race, and It may have value as characterization and research data.

The vowel analysis unit 370, when a voice utterance is recognized from the user terminal 100, collects a voice sample and analyzes the vowel ah, yi, and right from the voice sample using the Praat program, After calculating the frequency difference of each sound band, a Vowels Triangle between the user and the Korean may be generated and transmitted to the instructor terminal 400 to guide the opening of the mouth and movement of the lips for the vowel in which the difference occurs. In Korean, vowels act as carriers to produce consonants, and in the case of foreigners learning Korean, Korean vowels are calculated based on their native language. Therefore, in the case of analyzing the vowels and differences produced by Koreans in natural sentences and the patterns produced by acoustically analyzing the pronunciation of foreigners, it can be used as basic information for the pronunciation guidance of foreigners.

<Collection of voice samples>

To collect the voices of foreign Korean learners, individual voice samples are recorded as wav files using Roland (R-09HR), and the sampling rate can be set to 44 kHz. In this case, meaningful words can be constructed for the natural reading of texts by foreign Korean learners, and only the part where there is no consonant transition of the trailing vowel after the open rupture of the plosive can be analyzed. In order to avoid getting nervous when reading Hangul sentences or reading syllable-by-syllable, you can have them read the practice sentences first and then read the target sentences.

<Analysis of voice samples>

The vowel /ah, yi, woo/ can be analyzed from the collected voice samples using the Praat program. In order to analyze the shape bands of the vowels included in the target word, the three sound bands are analyzed by analyzing the flat range from the start of the vowel shape band to the transition to other phonemes after the burst of the burst burst. can In this case, an independent sample t-test can be performed to examine the frequency difference between the vocal bands (F1, F2, F3) of the representative vowel of the foreign Korean learner and the control group, the instructor.

<vowel triangle>

According to the size of the vowel square, it is related to speech intelligibility, and the narrower the area of the vowel square, the lower the speech intelligibility. Similarly, the vowel triangle is the same concept, but in the context vowel in the same environment, foreign Korean learners have a smaller area of the vowel triangle than Koreans, and thus the intelligibility of pronunciation is reduced. This reduction was due to the reduction of the vocal cords as the tension for articulation production and the movement of the lips decreased. Accordingly, if the vowel triangle size of foreign Korean learners is smaller than that of Koreans and the vowels /ah, uh, and woo/ are placed further back, the mouth opening and movement of the lip cavity are expanded to increase their pronunciation clarity. Language and pronunciation education or guidance is needed to do this. If these characteristics are understood, the instructor can give the user a mouthpiece such as a cochlear implant, or guide the direction of the instruction by continuously instructing systematic pronunciation training.

The image unit 380 converts the sound data of the instructor of the instructor terminal 400 and the sound data of the user of the user terminal 100 into a spectrogram image using Short-Time Fourier Trasnform (STFT), After extracting the feature data from the transformed spectrogram image using CNN (Convolutional Neural Network), and restructuring the instructor's vibration data and the user's vibration data on the XYZ axis in the time domain, CNN can be used to extract feature data.

When the image unit 380 converts sound data into a spectrogram image, there is a problem that an error occurs in the frequency analysis technique for an abnormal signal of the Fourier transform, and even at the moment when such an error occurs, the frequency analysis You need a way to do that. Accordingly, STFT is a method of dividing a target signal into frame units in consideration of signal stability and performing Fourier transform while moving a window of a certain size. The formula for STFT in the time domain is STFT(t,w)=∫x(τ-t)e- ^jwτ dτ, and the integral range is from -infinity to +infinity.

Here, x(τ) is a signal to be analyzed, and w(τ-t) is a window function. In addition, a spectrogram is a tool for visualizing and grasping a sound or a wave, and the characteristics of a waveform and a spectrum are combined. In the waveform, you can see the change in the time axis, that is, the change in the amplitude axis in the time domain. In the spectrum, you can see the change in the amplitude axis according to the change in the frequency axis. In the spectrogram, the difference in amplitude according to the change in the time and frequency axes is printed It is expressed as a difference in density or display color.

The image unit 380 may extract feature data from the transformed spectrogram image using a Convolutional Neural Network (CNN). Since the spectrogram is output as an image, as a result, when comparing sound data recorded by the user through image analysis with pre-stored sound data, the image should be used for comparison. At this time, when trying to calculate the similarity between different images, it is difficult to determine the degree of similarity between images through pixel-by-pixel comparison. There is a method of extracting and comparing images, which is deep learning technology, CNN.

CNN learns the characteristics of images by itself, can classify images and recognize patterns of images based on the learned characteristics, and is suitable for image processing with a network structure using a convolutional layer. Since an image can be classified based on the features in it, it is used in an embodiment of the present invention. However, it is not limited to CNN, and any method that can distinguish an image and extract its features is possible. CNN extracts the features of the spectrogram in the form of vectors and can measure the similarity between images by using the extracted features.

In one embodiment of the present invention in order to extract the features of the spectrogram, a model using the basic structure of a convolutional neural network consisting of a convolution layer, an activation function layer, and a max pooling layer is used. It can be used, and before measuring the similarity, it is possible to extract and use the feature vector of the spectrogram from the layer before the Softmax layer used to classify the image. Basically, it can be used to measure similarity by extracting features from a model having a CNN having a fully-connected layer and a global average layer (GAP) that brings average values on a feature map. .

As another model for measuring the similarity of images, a CNN-based autoencoder model can be used. The encoder consists of a convolutional neural network structure, and a decoder ( Decoder) may be included. Spectrogram features are extracted from a specific layer of the learned autoencoder model, and the feature vector generated through the GAP layer can be used to measure image similarity. Euclidean distance and cosine similarity can be measured from the image feature vectors extracted through the above three models, and using these, the degree of similarity for each spectrogram, i.e., can be sorted according to the degree of similarity. .

After the feature data for the sound data has been extracted, it is necessary to extract the feature data for the vibration data. The image unit 380 restructures the collected vibration data on the XYZ axis in the time domain. After performing, the feature data can be extracted using CNN. The basic concept for this returns to the principle of pendulum movement with respect to the time axis (time domain). The weight on the spring moves up and down over time, leaving a graph while moving back and forth between the upper and lower limits based on the central point. Similarly, for example, when a user breathes, a breathing sound is input into the microphone of the user terminal 100, when breathing occurs, how strong it is, and how the pattern is generated and graphed visualization becomes possible. Since the generated graph is also an image, the image unit 380 may extract feature data for the vibration data using the CNN described above.

Artificial intelligence algorithms are modeled through data collection, preprocessing, feature data extraction, learning, and testing. Most of the things used after modeling are the same, except that they do not go through a learning process. Of course, it is possible to relearn the part where an error occurs or an error occurs due to human intervention. Therefore, if the process of actually using after modeling has been described in the above process, the process of modeling while going through the learning and testing process will be described below.

The image unit 380, when extracting feature data from the collected expert sound data and vibration data, and user type sound data and vibration data, based on the extracted feature data LSTM (Long Short-Term Memory) The feature data can be re-extracted. The difference in the modeling process is that the image unit 380 calculates an error rate between the label and feature data, which are preset reference data, and maps and stores a weight having the lowest calculated error rate with the feature data. In the process of learning an artificial intelligence algorithm, learning is carried out using data for which features have already been determined. Also called a training set.

In addition, LSTM is a type of RNN (Recurrent Neural Network), which is a deep learning network that uses past learning results for current learning. -Term Dependency) is an algorithm that solves the problem. The LSTM is configured in the form of a chain that repeats the neural network module, and the LSTM process is executed after the CNN process in the image unit 380 to re-extract features.

The structure of the LSTM replaces the normal neurons of the recurrent neural network with an LSTM cell with a small memory inside. These LSTM cells are connected like a general recurrent neural network, so the state inside the cell helps memorize errors over several stages, and gates are used to maintain the state. The output value can be adjusted using the input gate, the forget gate, and the output gate. The input gate determines how much the input value is accepted, the forget gate determines how much the previous state inside the cell is forgotten, and the output gate determines how much to output. Here, the forget gate, in the same form as the input gate, simply changes the multiplied weight to the weight leading to the forget gate, and determines whether or not to reflect the influence of the input data at the previous time. The input gate calculates the output value of the input gate by adding the value obtained by multiplying the input data of the current time by the weight leading to the input gate, and the value obtained by multiplying the output value of the memory block and the cell output value of the previous time by the weight leading to the input gate. , decides whether to reflect the influence of the input data received at the current time.

LSTM is a structure that adds by determining how many cell state values are forgotten and how many new input values are accepted. Even if this process is repeated, the gradient does not disappear and the learning becomes impossible. LSTM calculates the final output value through the hidden variable in the same way as the standard recurrent neural network, but it controls the flow of information by appropriately using gates in the variable calculation process of the hidden layer. As a result, the cyclic neural network using LSTM cells has a structure that can process time series data that changes along the time axis without the problem of gradient loss. Due to the above-described structure, features are extracted from the image (spectrogram) through CNN and LSTM, and the extracted feature (feature data) is compared with the reference label, which is the reference value, by calculating the error to determine whether the learning result is correct. By storing the weight (used in LSTM) that is the minimum value, when a query, which is a query, is input later, the weight corresponding to the query is applied and the user's pronunciation, breathing, or ligation, etc. What condition can be diagnosed.

The evaluation unit 390 selects an instructor from the user terminal 100, conducts a real-time lecture with the instructor terminal 400, requests to input a rating and review for the instructor, and accumulates the rating and review for each instructor. can be saved

The block chain unit 391 may perform qualification verification for at least one instructor terminal 400 using a block chain, but the block chain may be based on a pseudocode of the chain code. At this time, the at least one instructor terminal 400 and the manager terminal 500 verifying the qualification conditions of each instructor are in a state with a limited function as a light weighted node, and the block chain unit is a full node. You can join the network with all rights on the network.

<Block creation procedure>

Block generation is performed when the instructor terminal 400 participates in a blockchain network or changes the academic background and career of the instructor. ① The instructor terminal 400 participates in the block chain network with the block chain unit 391 and requests block generation when registering his/her information in the block chain and changing existing information. ② When the block chain unit 391 receives a registration request, it starts a block generation procedure based on the information provided by the instructor terminal 400 . At this time, in order to check whether the instructor of the corresponding instructor terminal 400 has already existed, whether the corresponding instructor is registered in the block chain is searched. ③ The block chain unit 391 checks whether the instructor is registered in the block chain according to the request of the manager terminal 500, and delivers it to the manager. ④ The manager requests information about the academic background and career of the professor from the government or institution to check whether the information of the professor is forged. ⑤ The government or institution checks whether it is acceptable to provide academic background and career information to professors. ⑥ The instructor's terminal 400 transmits whether or not to agree to the provision of personal information so that his/her information can be stored in the block chain. ⑦ The government or institution notifies whether or not the instructor information is verified. ⑧ In the block chain, information about the instructor is created and stored as a block.

<Individual academic background and career verification process>

The educational background and career provision procedure is not a situation in which a professor is asked to take a user who is a student for his/her class, but rather a situation in which a user who is a student is actually a customer viewing the platform advertisement of the present invention in the user terminal 100 of the user, and the academic background or academic background of the professor included in this advertisement It may be used as a request of the user terminal 100 to check whether the work experience is correct, that is, to check whether the content is forged. First, ① When advertising the profile of the instructor terminal 400 registered as an instructor on the homepage of the present invention, his/her ID registered in the block chain is submitted together. ② The block chain unit 391 notifies whether the homepage is registered. ③ The user terminal 100 requests the blockchain unit 391 to verify whether the academic background and career included in the homepage are forged. ④ The block chain unit 391 checks whether or not to agree to check the career in the block chain with the instructor terminal 400 . ⑤ The instructor terminal 400 sends a message to the block chain unit 391 to authorize the user to inquire his/her data. ⑥ The block chain unit 391 checks the internal data of the block chain by executing the chain code, and at this time, searches the instructor data using the instructor's unique ID. ⑦ The block chain unit 391 transmits the data registered in the block chain to the user terminal 100 so that forgery can be checked.

<Chain code operation>

At this time, you can use the chain code for whether you agree to provide personal information, search for data inside the block, create and modify blocks, and verify career information. Since the professor's career and academic background information is included in personal information, a procedure to confirm the professor's information consent is necessary. The subject using the chaincode is used by governments or institutions that can help verify instructor information. In this case, the method of obtaining consent to provide information from the instructor allows the confirmation of consent in the form of a message or e-mail. Block creation and verification can be performed only when the instructor agrees to provide information.

The chain code used to search for instructors can be used after confirming consent to provide personal information. This is because it is a chaincode that actually gets the data inside the block chain. Data search chaincode can be searched using two methods: QueryString and txType. The QueryString method is a method of performing a search using only the instructor ID. The txType method is a method of performing a search by assigning an instructor ID and additional conditions. At this time, if the corresponding chain code is not used, it may be configured so that information cannot be verified on the block chain.

The background technology used in the above configuration is blockchain, chaincode, and hyperledger consensus algorithm. First of all, blockchain is used to synchronize data to simplify complex systems or prevent confusion by utilizing blockchain. The difference between the existing security method and blockchain is that by providing the same information to all people involved in the network, even if a specific person forges data, it is not recognized because it is different from the information known to all members. In other words, it is a technology that performs anti-counterfeiting through disclosure, unlike the existing data hiding.

Transactions in the blockchain can only be registered in a block if they are authorized using a hash function. In this process, an electronic signature is used, which is used to provide a non-repudiation function. The method that is mainly used as a method for transaction processing is the method using chaincode. Chaincode is used not only to generate blocks, but also to provide functions that can provide various services using blockchain. Chaincodes can be classified into system chaincodes and user chaincodes.

Hyperledger Fabric uses a different transaction processing method than other blockchain platforms. In the case of other blockchain platforms, the method of linking with the chain is used by verifying the transaction contents. In contrast, Hyperledger Fabric operates with procedures of Execute, Order, Validate, and Update state. In the case of the existing Hyperledger Fabric, the PBFT (Practical Byzantine Fault Tolerance) method was used as a consensus method, but a decrease in transaction per second (tps) performance occurred as a problem. In this case, it may be applied using simple BFT (SBFT). Of course, in addition to the above-described method, since the license, academic background, or career may be verified or shared by various methods, the present invention is not limited thereto.

Hereinafter, an operation process according to the configuration of the education service providing server of FIG. 2 will be described in detail with reference to FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

Referring to FIG. 3 , (a) the education service providing server 300 receives an instructor registration application from at least one instructor terminal 400 and (b) determines whether to register through verification, then builds a manpower pool and You can upload your profile. And, (c) viewing the profile of each instructor on the user terminal 100 and selecting a class, (d) various types of lectures such as one-to-one, one-to-many, many-to-one, and many-to-many between the user and the instructor can be conducted in real time. . In addition, as shown in FIG. 4(a) , a certificate may be issued when a preset condition is satisfied after performing a speech test by dividing each user by level. This certificate is also recorded in the above-mentioned blockchain, so that even if a user works in Korea or returns to their home country, it is possible to prevent forgery or false submission of the fact that they have obtained a speech certificate. In addition, each instructor can upload a rating and review as shown in (b), and negative reviews or scores below the average are notified to each instructor so that each instructor can reflect the corresponding feedback in the class. And, through various pronunciation analysis as in (c), it is possible to identify the characteristics of the native language of foreigners studying Korean as a second foreign language and analyze the differences in Korean pronunciation to inform the instructor, the leader, and the foreigner himself which part to correct. .

The matters not described with respect to the method of providing Korean language education service based on qualification condition verification of FIGS. 2 to 4 are the same as those described for the method of providing Korean language education service based on qualification condition verification through FIG. 1 or from the described content. Since it can be easily inferred, the following description will be omitted.

5 is a diagram illustrating a process in which data is transmitted/received between components included in the system for providing Korean language education service based on qualification condition verification of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted and received between each component will be described with reference to FIG. 5, but the present application is not limited to such an embodiment, and the example shown in FIG. 5 according to the various embodiments described above will be described. It is apparent to those skilled in the art that the data transmission/reception process may be changed.

Referring to FIG. 5 , the education service providing server sets at least one qualification condition and registers at least one instructor terminal with at least one qualification condition verification to build a pool of instructors (S5100), and at least Profile information is received and uploaded from one instructor terminal (S5200).

In addition, the education service providing server, when any one instructor is selected from the user terminal, allows a real-time lecture between the instructor terminal and the user terminal to proceed (S5300).

The order between the above-described steps (S5100 to S5300) is merely an example, and is not limited thereto. That is, the order between the above-described steps ( S5100 to S5300 ) may be mutually changed, and some of these steps may be simultaneously executed or deleted.

Matters not described with respect to the method of providing Korean language education service based on qualification condition verification of FIG. 5 are the same as or from the contents described for the method of providing Korean language education service based on qualification condition verification through FIGS. 1 to 4 above. Since it can be easily inferred, the following description will be omitted.

The method of providing Korean language education service based on qualification condition verification according to an embodiment described with reference to FIG. 5 may also be implemented in the form of a recording medium including instructions executable by a computer, such as an application or program module executed by a computer. can Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above-described method for providing Korean language education service based on qualification condition verification according to an embodiment of the present invention is provided by an application basically installed in a terminal (which may include a program included in a platform or operating system, etc. basically installed in the terminal). may be executed, and may be executed by an application (ie, a program) directly installed in the master terminal by a user through an application providing server such as an application store server, an application or a web server related to the corresponding service. In this sense, the above-described method for providing Korean language education service based on qualification condition verification according to an embodiment of the present invention is implemented as an application (ie, a program) installed by default in a terminal or directly installed by a user, and is transmitted to a computer such as a terminal. It may be recorded on a readable recording medium.

The description of the present invention described above is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be interpreted as being included in the scope of the present invention. do.

Claims (10)

a user terminal that outputs at least one instructor profile, selects any one instructor, enters the class in real time, and then proceeds with the class;
an instructor terminal registered as an instructor by verifying at least one qualification condition and conducting a real-time lecture by selecting a user terminal; and
A registration unit that sets at least one qualification condition and establishes an instructor pool by registering at least one instructor terminal with the at least one qualification condition verification, receiving and uploading profile information from the at least one instructor terminal An upload unit, an education service providing server including a lecture management unit that allows a real-time lecture between the instructor terminal and the user terminal to be conducted when any one instructor is selected by the user terminal; and
The at least one qualification condition is
It is characterized by being any one of a person who has received an announcement education, a broadcaster and an announcer, a voice actor, and a singer,
The education service providing server,
Sound including pitch, first formant (F1) and pitch ratio, pitch bandwidth, average pitch position within the pitch bandwidth, and speech speed using the speech speech data collected from the at least one instructor terminal It further includes; a storage unit to build a database by collecting red tone analysis data,
The education service providing server,
When the user terminal recognizes the speech utterance, after comparison based on the acoustic tone analysis data, a comparison unit for extracting a factor causing the difference and transmitting it to the user terminal; further comprising,
The education service providing server,
When a voice utterance is recognized from the user terminal, a voice sample is collected and the vowel ah, yi, and right are analyzed from the voice sample using the Praat program, and after calculating the frequency difference between the voice utterance of Koreans and each sound pattern, It further includes; a vowel analysis unit that generates a Vowels Triangle between the user and the Korean and transmits it to the instructor terminal to guide the mouth opening and lip movement for the vowel in which the difference occurs.
The sound data of the instructor of the instructor terminal and the sound data of the user of the user terminal are converted into a spectrogram image using Short-Time Fourier Trasnform (STFT), and the converted spectrogram image is converted into a Convolutional Neural (CNN) image. Network) to extract feature data, and after restructuring the instructor's vibration data and the user's vibration data on the XYZ axis in a time domain, extracting the feature data using the CNN It further includes;
The vowel analysis unit,
After an open burst of a plosive consonant, the three sound bands are analyzed by analyzing the flat range from the beginning of the vowel shape band until the transition to another phoneme occurs. A system for providing Korean language education service based on qualification condition verification that analyzes the frequency difference between F2 and F3).
delete The method of claim 1,
The education service providing server,
a speech unit for issuing a speech certificate issued by a preset institution or association after performing a Korean speech test by dividing the user's level of the user terminal;
Qualification condition verification-based Korean language education service providing system, characterized in that it further comprises.
delete delete delete The method of claim 1,
The class is a system for providing Korean language education services based on qualification condition verification, characterized in that it includes textbook classes and pre-talking.
delete The method of claim 1,
The education service providing server,
an evaluation unit for selecting the instructor from the user terminal, conducting a real-time lecture with the instructor terminal, requesting to input a rating and review for the instructor, and accumulating and storing the rating and review for each instructor;
Qualification condition verification-based Korean language education service providing system, characterized in that it further comprises.
The method of claim 1,
The education service providing server,
a block chain unit for performing qualification verification for the at least one instructor terminal using a block chain, wherein the block chain is based on a pseudocode of the chain code;
further comprising,
The at least one instructor terminal and the administrator terminal verifying the qualification conditions of each instructor are in a state with a limited function as a light weighted node, and the block chain unit is a full node with all authority of the network. A system for providing Korean language education service based on qualification condition verification, characterized in that it participates in the network in the state.

Images