KR20200052463A - System and method for learning foreign languages based on artificial intelligence - Google Patents

Abstract

The present invention relates to an artificial intelligence based learning technique. According to an embodiment of the present invention, an artificial intelligence based learning system capable of providing user-customized content can comprise: an interface part providing learning content to a user terminal and receiving a user voice according to the use of the learning content from the user terminal; a voice analysis part generating user analysis data by analyzing the user voice according to the use of the learning content; and a learning evaluation part that performs machine learning with the user analysis data, determines the rating and vulnerability information of the user based on a machine learning performance result, and extracts customized learning content corresponding to the determined rating and the vulnerability information.

Description

Artificial intelligence based learning system and its method {SYSTEM AND METHOD FOR LEARNING FOREIGN LANGUAGES BASED ON ARTIFICIAL INTELLIGENCE}

It relates to an artificial intelligence-based learning system and a method thereof, and more particularly, to a technical idea of performing language learning based on artificial intelligence.

Recently, as interest in artificial intelligence technology increases, attempts to incorporate artificial intelligence technology into English learning are increasing. Specifically, for effective English learning, it is necessary to design English classes centering on core competencies.

For example, for efficient English learning, English lessons can be designed considering core competencies such as self-management competency, knowledge information competency, creative competency, aesthetic competency, communication competency, and community competency.

For a more specific example, for effective English learning, the English education curriculum centered on communication competency can be reconstructed through the process of Table 1 below.

Soju Theme: 'What is justice?' Discuss and solve in a given problem situation Applicable unit Reconstruction-oriented topics Expressions to use while working Growth Target Core Competencies 8.How was your
vacatμon? Example) Kang-sung, who wants to be careful because he can be upset about buying food for a poor friend, and Tae-won, what's the problem with buying me because I have money. Who is right? The verb's past tense: -ed, including irregular variations
-I played soccer.
Communication competency 13.Would
like to come? Express what you want using Would like to, short form.
-I would like to come.
-I'd love to. Core project Guided English-Korean Discussion Project: As a highlight of the topic-based class, English-Korean discussions are conducted through active guidance from native and Korean teachers. Students stand on the side of one of the thoughts of “What is Justice for Children” to organize their thoughts in advance, engage in discussions with sincere attitude, and expand their communication skills through a series of activities to organize their thoughts I can do it.

In addition, for efficient English learning, the English education curriculum centered on community competency can be reconstructed through the process in Table 2 below.

Shochu: 'If you want to go fast, go alone. If you want to go far, go together '
(Go alone to go fast, go together to go far-African proverb) Applicable unit Reconstruction-oriented topics Expressions to use while working Growth Target Core Competencies 1. 1'm from Korea. Think about the racism problem in America through Rosa Parks' Yagi.
Listening to Nick Vujicic and thinking about the problems of appearance in our society Asking who came from using From
-I'm from Korea.
-Where are you from? Community competency 2 She has short hair. Describing the appearance using words about the new topic
-She has big eyes.
-He is wearing a black shirt. Core project Through the talks of Rosa Parks and Nick Vujicic, we recognize the problems of race, nationality and disability discrimination and appearance ideology that exist in our society, and focus on 'our attitude against discrimination'. 1) Lego doll roleplay, 2) UCC video production ， 3) During the campaign poster selection process by group, we have different but equal relationships with each other, and we have time to think to create a better society to live together.
It aims to increase the capacity of the community in order.

In addition, for efficient English learning, the English education curriculum centered on self-management competency can be reconstructed through the process in Table 3 below.

Subtopics: Bad news is time files, the good news is you're the pilot
(The bad news is that time goes as fast as it flies. The good news is that you are the pilot of time.) Applicable unit Reconstruction-oriented topics Expressions to use while working Growth Target Core Competencies 11.I'll clean the park Record Breakers:
-Restructuring the film The incredib1es to set interesting goals for the students themselves, to break records by themselves, and to achieve a sense of accomplishment at the same time as oil. Expressing your will to do something in the future using Will
-I'll play computer games. Self-management competency 13.Would you like to come? Expressing your will using Would
-I would do my homework. Core project My Super Power Project: Each one thinks of super powers that are fun Assuming that he or she climbs the Guinness Book of Records himself, and encourages them to develop self-management skills along with a sense of achievement through planning and breaking records.

In addition, for efficient English learning, the English education curriculum centered on knowledge and information competency can be reconstructed through the process of Table 4 below.

Shochu: 'It is wiser to find out than to suppose'
(It's wiser to look it up yourself than to assume it in your head.-Mark Twain) Applicable unit Reconstruction-oriented topics Expressions to use while working Growth Target Core Competencies 12.There are bees on the flower. 1. Walk around the school and find out and search for the names of the flowers around you by searching for the next flower.
2. Find Willie-Explore the world through activities around the world.
3. Reconstruct the story through elementary level Dictogloss activities Using there is / there are
-There is an eraser on the desk. Knowledge information competency Core project 1.Experience self-directed learning through learning to walk around the school, discover flowers or plants, research what they are on the Internet, and present what you have surveyed in front of friends in English, learn from your friends, and develop knowledge and information skills To stretch.
2 Find the place you want to go through Google Earth, select a place for each group, cultivate a sense of cooperation through the 'Find Wally' production activity, introduce your friends to the place, and learn new knowledge while playing games together. Induce them to.

Currently, artificial intelligence technology is getting deeper into our daily lives than we think. Specifically, it can be said that artificial intelligence technology is applied to all devices having intelligent elements, including robot cleaners, artificial intelligence speakers, and ARS services.

If you look at AI technologies that can be used in English education, first of all, there are artificial neural network translation technologies such as Papago and Google Translator.

Specifically, before deep learning was applied, if statistical machine translation was performed by selecting vocabularies with a high frequency of use before deep learning was applied, after deep learning was applied, considering the connectivity of sentences and words The next word will be predicted through deep learning, and it will be changed to neural machine translation, which will improve its accuracy gradually.

It can be said that the introduction of artificial neural networks in machine translation is indeed a great inflection point. It is a tremendous achievement that machine translation, which had so far been less reliable, has advanced to 70% of human translation. By using the artificial neural network translation technology with improved accuracy, we can make a leap forward in English education in Korea.

More specifically, applying the artificial neural network translation technology to English classes, students with excellent skills can find and read English texts and partially understand (translate English-Korean translations) sentences they don't know. After you have found all the necessary information, you can prepare your own presentation by turning the translator to compose the part you want to present.

You may think that you will not study because you wrote a translator, but through the process of writing, memorizing, and preparing a presentation for yourself, students learn new words and learn the sentence structure yourself while studying sentences. It becomes possible.

Most importantly, you will gain the experience of voluntarily studying something using English, and at the elementary level, this experience can be a seed that can grow into a self-directed adult as you grow forward.

Next, as an artificial intelligence technology that can be used in English education, there is an interactive artificial intelligence technology such as a chatbot.

Specifically, since the introduction of deep learning in interactive AI technology since 2010, its functionality has improved dramatically. Typical examples are closed-domain conversations and Generative-based responsive chatbots.

The principle that the above-mentioned chatbot works is that a large amount of conversation data is first trained in advance, and then, when a question is entered, the most appropriate conversation for the question is generated and answered through 'conversation creation artificial intelligence'. In other words, depending on what the trained data is, the person who talks may feel differently about the nature of the chatbot.

More specifically, applying interactive AI technology to English classes can support the process of searching for information itself in English.

As a more specific example, Google Home and Google Assistant are examples of the application of interactive artificial intelligence technology.

Google Home, the world's largest search engine, is an AI speaker created by Google, and it analyzes behavioral patterns through dialogue with people, and through the result, Google Assistant, an artificial intelligence voice assistant that assists people in their daily lives. Can work.

The Google Assistant is a voice recognition artificial intelligence assistant built into the Google Home. It utilizes big data held by the Google search engine to process all information such as tastes, behavior patterns, and schedules through dialogue with users.

The aforementioned Google home is equipped with various functions, and the user can perform various activities related to learning through the Google home.

For example, Google Home's Up and Down (command: "Okay. Google. Guess my number.") Program is an activity that Google Home guesses after students think of one of the numbers 1-100. This activity is approaching the correct answer by saying 'Down' when the number spoken by Google Home is greater than the correct answer and 'Up' when it is less than the correct answer. Through this activity, students can feel free to learn the numbers from 1 to 100.

Next, Google Home's Argument Room (command: "Okay. Google. Ask to Argument Room") program is an activity that allows you to argue with Google Home. This is a program suitable for students who can do basic conversation or have simple communication.

Next, in Google Home's Beat Box (command: "Okay. Google. Drop the beat") program, Google Home runs the beat box with random beats. It can be used in class to boost students' excitement just before class or to motivate them. By using the subject expression of the class or the key expressions of the chant to create a simple rhythm of a specific beat, students can learn English expressions with fun.

Next, the Google Home's My Adventure Book (command: "Okay. Google. Ask to My Adventure Book") program provides a mystery story for students to make a decision and catch a criminal who kidnapped a boy named 'One'. .

Here, the Google Home acts as a Storyteller, and students can develop a new story by answering the desired A or B question at the end of each section.

Finally, Google Home's Twisted Tales (command: "Okay, Google. Ask to Twisted Tales") program develops the world-renowned 'Red Hat and Wolf' and 'Hansel and Gretel' from the standpoint of each character. It is a storytelling program. In this program, students can answer A or B questions in each section, and the story is developed differently to help students learn.

Hereinafter, other useful programs for learning will be described.

First of all, Storybird (www.storybird.com) is a useful program for learning. Specifically, Storybird is a program that allows students to create their own stories in three genres: poetry, then books, and novels, using the topics they want. There are several themed pictures created by various artists within the program, and students can select and compose one of them to fit the story they want to write. The teacher account and the student account are separated. The teacher composes a classroom called studio, and the students belong to the teacher's classroom and perform story-making tasks.

Next, the Pixton (www.pixton.com) program is a useful program for learning. This program is similar in character to Storybird, but Storybird is a story-making program, while Pixton is a cartoon-making program. Various backgrounds, characters, and props are embedded for each theme, and the facial expressions and behaviors of the characters can be fine-tuned to create high-quality cartoons.

 Next, Mobizen Mirroring (www.mobizen.com) is a useful program for learning. This program is a mirroring program that connects a mobile phone and a PC so that the screen displayed on the mobile phone can be viewed directly on the PC. By using this program, students can direct using English expressions learned, and they can motivate them to appear on the screen to improve learning effect.

Next, Akinator, a twenty-game game application with artificial intelligence based on a wide range of data, is a useful program for learning. This application is limited to the person imagined by the user and guesses the person imagined by the user through a question of 207H or more.

At this time, the user can answer 'Yes', 'No', 'Maybe Yes', 'Maybe No', 'I don't know', and based on the user's response, Akinator will search for data inherent in the Google search engine. do. In other words, it is a thorough big data-based artificial intelligence program by the Google search engine.

By applying the above-described Akinator to learning, students can compete with Akinator as a person. This activity is a pair activity with two students. Through this activity, students must listen to expressions related to various tenses such as the present and the past because they need to check the person's current status, past behavior, and the continuation of certain facts in order to guess the person. In other words, through this activity, you can improve the listening ability of questioning and tense expressions.

In addition, students can use the Akinator's list of questions to play twenty heads. This activity uses Akinator's question pattern to induce continuous use of basic collocation, allowing students to develop their ability to express in complete sentences. Here, Akinator's questioning method is not simply asking a question randomly, but because it is patterned to find the answer in the shortest time by using the data of the Google search engine, it will be able to proceed more efficiently.

In addition, multimedia tools (E-tools) can be applied to English writing education. For example, a genre-based approach (Gene Based Approach) or Youtube and Storybird can be linked to perform learning activities.

More specifically, the Gene Based Approach is not a method of improving students' writing skills by focusing on the writing process, but rather a writing learning method based on various genres already made, such as stories and poetry.

Newspaper articles, cartoons, novels, stories, and essays we encounter in our daily lives have a certain frame for each genre. When students simply teach the grammatical aspects and vocabulary of English and do free writing, they concentrate on using what they have learned so that the meaning is not awkward in Korean. The writing method according to the genre-specific is ignored. This is one of the blind spots of EFL students.

Table 5 below shows how to apply the genre-based approach in the field.

Steps to lollow (www.slideshare.net) One Learners are given a model text. 2 Text is read and analyzed with the teacher. 3 Patterns and linguistic features are identified. 4 Teachers and Learners collaboratively construct the genre. 5 Learners in groups use writing frames. 6 Learners write individual genres.

On the other hand, Youtube's PinkFong shows students familiar and diverse stories with fun adaptations or songs, and shows them in 3-5 minutes. Also, specific expressions are repeated so that students can recognize the expression and analyze and learn the expressions together with the teacher.

In addition, through the Storybird program, if students create their own story group, they can easily increase the immersion of students and realize a genre-oriented approach.

As described above, AI technology is currently applied to learning systems in various forms to improve the efficiency of learning, and research on related technologies and application methods for more efficient learning continues.

Korean Registered Patent No. 10-2017-0119179, "Foreign language learning system and foreign language learning method using the same"

The present invention is to provide an artificial intelligence-based learning system and a method capable of providing user-customized content by analyzing user rating and vulnerability information through artificial intelligence-based machine learning.

In addition, the present invention is to provide an artificial intelligence-based learning system and method for improving learning efficiency through customized learning.

The artificial intelligence-based learning system according to an embodiment of the present invention provides learning content to a user terminal, an interface unit for receiving a user voice according to the use of the learning content from the user terminal, and a user voice according to the use of the learning content The machine analyzes the voice analysis unit and user analysis data to generate user analysis data by analyzing the machine, and determines the user's rating and vulnerability information based on the machine-learned user analysis data. It may include a learning evaluation unit for extracting customized learning content corresponding to.

According to one side, the artificial intelligence-based learning system may further include a learning control unit receiving and storing learning content from the content providing server, providing machine learning results to the content providing server, and providing customized learning content to the user terminal. have.

According to one side, the user terminal may include at least one terminal of a computer, a laptop, a tablet PC, a smart phone, and an artificial intelligence speaker capable of collecting a user's voice.

According to one side, the voice analysis unit may be connected to the artificial intelligence engine, and may generate user analysis data by analyzing a user's voice through the artificial intelligence engine.

According to one side, the interface unit receives the authentication information from the user terminal, passes it to the learning control unit, the learning control unit performs authentication based on the authentication information, and loads (Loading) the learning information of the user corresponding to the authentication information. have.

According to one side, the learning information of the user corresponding to the authentication information may include at least one of content-related information used by the user corresponding to the authentication information, information regarding the content usage progress, and user rating and vulnerability information corresponding to the authentication information. Can be.

According to one side, the learning control unit may provide content corresponding to the learning information of the user corresponding to the authentication information to the user terminal.

Artificial intelligence-based learning method according to an embodiment of the present invention provides a learning content to the user terminal in the interface unit, receiving a user voice according to the use of the learning content from the user terminal, and the learning content in the speech analysis unit Step of generating user analysis data by analyzing the user's voice according to the use of the machine and machine learning of the user analysis data in the learning evaluation unit, and judge the user's rating and vulnerability information based on the machine-learned user analysis data And, it may include the step of extracting customized learning content corresponding to the determined rating and vulnerability information.

According to one embodiment, by analyzing the user's rating and vulnerability information through artificial intelligence-based machine learning, it is possible to provide customized content.

According to one embodiment, learning efficiency may be improved through customized learning.

1 is a diagram illustrating an artificial intelligence-based learning system according to an embodiment.
2 is a diagram illustrating an embodiment of an artificial intelligence-based learning system according to an embodiment.
3 is a diagram illustrating another embodiment of an artificial intelligence based learning system according to an embodiment.
4 is a diagram illustrating an artificial intelligence-based learning method according to an embodiment.

Hereinafter, various embodiments of this document are described with reference to the accompanying drawings.

It should be understood that the embodiments and terms used therein are not intended to limit the technology described in this document to specific embodiments, and include various modifications, equivalents, and / or substitutes of the embodiments.

In the following description, when it is determined that detailed descriptions of related well-known functions or configurations in the description of various embodiments may unnecessarily obscure the subject matter of the present invention, detailed descriptions thereof will be omitted.

In addition, terms to be described later are terms defined in consideration of functions in various embodiments, which may vary according to a user's or operator's intention or practice. Therefore, the definition should be made based on the contents throughout this specification.

In connection with the description of the drawings, similar reference numerals may be used for similar elements.

Singular expressions may include plural expressions unless the context clearly indicates otherwise.

In this document, expressions such as “A or B” or “at least one of A and / or B” may include all possible combinations of items listed together.

Expressions such as "first," "second," "first," or "second," can modify the components, regardless of order or importance, to distinguish one component from another component It is used but does not limit the components.

When it is stated that one (eg, first) component is “connected (functionally or communicatively)” to another (eg, second) component or is “connected,” a component is referred to as the other component It may be directly connected to the element, or may be connected through another component (eg, third component).

In the present specification, "configured to (or configured) (configured to)", depending on the situation, for example, in hardware or software, "suitable for," "with the ability to", "has been modified to" It can be used interchangeably with "made to do," "can do," or "designed to do."

In some situations, the expression "a device configured to" may mean that the device "can" with other devices or parts.

For example, the phrase “processors configured (or set) to perform A, B, and C” means by executing a dedicated processor (eg, an embedded processor) to perform the operation, or one or more software programs stored in the memory device. , It may mean a general-purpose processor (for example, a CPU or an application processor) capable of performing the corresponding operations.

Also, the term 'or' refers to the inclusive 'inclusive or' rather than the exclusive 'exclusive or'.

That is, unless stated otherwise or unclear from the context, the expression 'x uses a or b' refers to any of the natural inclusive permutations.

In the above-described specific embodiments, components included in the present invention are expressed in singular or plural according to the specific embodiments presented.

However, the singular or plural expressions are appropriately selected for the situation presented for convenience of explanation, and the above-described embodiments are not limited to the singular or plural components, and even the components expressed in plural are composed of the singular or , Even a component represented by a singular number may be composed of a plurality.

On the other hand, the description of the invention has been described with respect to specific embodiments, various modifications are possible within the limits that do not depart from the scope of the technical spirit implied by various embodiments.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined not only by the claims described below, but also by the claims and equivalents.

1 is a diagram illustrating an artificial intelligence-based learning system according to an embodiment.

Referring to FIG. 1, the learning system 100 according to an embodiment may provide user-customized content by analyzing user's rating and vulnerability information through artificial intelligence-based machine learning, and through learning customized through learning. Efficiency can be improved.

To this end, the learning system 100 may include an interface unit 110, a voice analysis unit 120, and a learning evaluation unit 130. In addition, the learning system 100 may further include a learning control unit 140.

In addition, the learning system 100 may be implemented as a server, the server may be designed based on Node.js, and voice file recording and processing may utilize Socket.io. Meanwhile, MySQL can be used as the database.

First, the interface unit 110 according to an embodiment may provide learning content to a user terminal and receive a user voice according to the use of the learning content from the user terminal.

According to one side, the user terminal may include at least one terminal among a computer, a laptop, a tablet PC, a smart phone, and an artificial intelligence speaker capable of collecting a user's voice, but the type of the user terminal is limited to the above-described example It does not work.

For example, the user terminal may be connected to the learning system 100 through a dedicated web page or mobile app. Also, it may be connected to the learning system 100 through a dedicated chat robot.

 Next, the voice analysis unit 120 according to an embodiment may generate user analysis data by analyzing the user voice according to the use of the learning content.

According to one side, the voice analysis unit 120 may be connected to the artificial intelligence engine, and may generate user analysis data by analyzing a user's voice through the artificial intelligence engine.

For example, the AI engine may be an AI engine provided by companies such as Google, Amazon, and Baidu.

Next, the learning evaluation unit 130 according to an embodiment performs machine learning on user analysis data, determines user rating and vulnerability information based on the machine learning user analysis data, and determines the determined rating and Customized learning contents corresponding to vulnerability information can be extracted.

In other words, the learning evaluation unit 130 performs machine learning based on pronunciations, expressions, and forgetting curves of a plurality of users, and extracts customized content by determining user ratings and vulnerability information using the results of machine learning. can do.

According to one side, the learning control unit 140 may receive and store learning content from the content providing server, and provide the machine learning result to the content providing server.

That is, the learning control unit 140 may assist the content provider to generate high-quality content based on the machine learning result by feeding the machine learning result to the external content providing server.

In addition, the learning control unit 140 may provide customized learning content to the user terminal. In other words, the learning control unit 140 may provide the customized content extracted from the learning evaluation unit 130 to the user terminal through the interface unit 110.

According to one side, the learning system 100 may further include a data storage unit (not shown) for storing user learning information including machine learning results, user-specific ratings, and vulnerability information.

According to one side, the interface unit 110 may receive authentication information from the user terminal and transmit it to the learning control unit 140.

Next, the learning control unit 140 performs authentication based on the authentication information, and may load (Loading) the user's learning information corresponding to the authentication information.

For example, the learning information of the user corresponding to the authentication information may include at least one of content-related information used by the user corresponding to the authentication information, information on the content usage progress, and user rating and vulnerability information corresponding to the authentication information. Can be.

According to one side, the learning control unit 140 may provide content corresponding to the learning information of the user corresponding to the authentication information to the user terminal.

In other words, the learning system 100 may proceed with learning by maintaining a session, and may provide appropriate feedback to the user terminal according to the learning progress.

Meanwhile, the user terminal may load the corresponding learning content through the user's voice command after user authentication.

2 is a diagram illustrating an embodiment of an artificial intelligence-based learning system according to an embodiment.

In other words, FIG. 2 is a diagram for explaining an embodiment of the learning system of FIG. 1, and descriptions overlapping with those described through FIG. 1 among the contents described with reference to FIG. 2 will be omitted.

2, reference numeral 210 denotes a user terminal, reference numeral 220 denotes a learning system, reference numeral 230 denotes an artificial intelligence server located outside, reference numeral 240 denotes a content providing server. .

For example, the learning system 220 may be a learning server that provides learning content to users.

Specifically, the learning system 220 receives the user voice according to the use of the learning content from the user terminal 210, analyzes the user voice received through the artificial intelligence server 230, generates user analysis data, and generates The user's rating and vulnerability information may be determined through machine learning based on one user analysis data, and customized learning content corresponding to the determined rating and vulnerability information may be provided to the user terminal 210.

In addition, the learning system 220 may feedback the machine learning result to the content providing server 240 located outside.

3 is a diagram illustrating another embodiment of an artificial intelligence based learning system according to an embodiment.

In other words, FIG. 3 is a diagram for explaining another embodiment of the learning system of FIG. 1, and descriptions overlapping with those described through FIG. 1 among the contents described with reference to FIG. 3 will be omitted.

Referring to FIG. 3, at 300, the learning system may provide customized content to a user using means such as a speaking app, artificial intelligence (AI) speaker, and homepage, and user analysis data to provide customized content. Machine learning and user rating and vulnerability information may be determined based on machine-learned user analysis data.

4 is a diagram illustrating an artificial intelligence-based learning method according to an embodiment.

In other words, FIG. 4 is a diagram for explaining an artificial intelligence-based learning method using the learning system of FIG. 1, and descriptions overlapped with those described through FIG. 1 among the contents described through FIG. 4 will be omitted. .

Referring to FIG. 4, in step 410, the learning method according to an embodiment may provide learning content to the user terminal in the interface unit and receive a user voice according to the use of the learning content from the user terminal.

Next, in step 420, the learning method according to an embodiment may generate user analysis data by analyzing the user voice according to the use of the learning content in the speech analysis unit.

Next, in step 430, the learning evaluation unit performs machine learning on the user analysis data, determines the user's rating and vulnerability information based on the machine-learned user analysis data, and corresponds to the determined rating and vulnerability information. Customized learning content can be extracted.

The device described above may be implemented with hardware components, software components, and / or combinations of hardware components and software components. For example, the devices and components described in the embodiments include, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors (micro signal processors), microcomputers, field programmable arrays (FPAs), It may be implemented using one or more general purpose computers or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may run an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

The software may include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and / or data may be interpreted by a processing device, or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodied in the transmitted signal wave.

The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, or the like alone or in combination. The program instructions recorded in the medium may be specially designed and configured for the embodiments or may be known and usable by those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs, DVDs, and magnetic media such as floptical disks. -Hardware devices specifically configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

100: learning system 110: interface unit
120: speech analysis unit 130: learning evaluation unit
140: learning control

Claims (8)

An interface unit that provides learning content to a user terminal and receives a user voice according to the use of the learning content from the user terminal;
Voice analysis unit to generate user analysis data by analyzing the user voice according to the use of the learning content and
Machine learning of the user analysis data, determining the user's rating and vulnerability information based on the machine learned user analysis data, and extracting customized learning content corresponding to the determined rating and vulnerability information Learning evaluation department
Artificial intelligence-based learning system comprising a. According to claim 1,
Further comprising a learning control unit for receiving and storing the learning content from a content providing server, providing the machine learning result to the content providing server, and providing the customized learning content to the user terminal
Artificial intelligence based learning system. According to claim 1,
The user terminal
Comprising at least one terminal of a computer, a laptop, a tablet PC, a smart phone and an artificial intelligence speaker capable of collecting the user's voice
Artificial intelligence based learning system. According to claim 1,
The speech analysis unit
Is connected to the artificial intelligence engine, and analyzes the user's voice through the artificial intelligence engine to generate the user analysis data
Artificial intelligence based learning system. According to claim 2,
The interface unit
Receiving authentication information from the user terminal, transmits it to the learning control unit,
The learning control unit
Perform authentication based on the authentication information, and load learning information of a user corresponding to the authentication information.
Artificial intelligence based learning system. The method of claim 5,
The user's learning information corresponding to the authentication information is
It includes at least one of content-related information used by a user corresponding to the authentication information, information regarding the content usage progress, and user rating and vulnerability information corresponding to the authentication information.
Artificial intelligence based learning system. The method of claim 5,
The learning control unit
Providing content corresponding to the user's learning information corresponding to the authentication information to the user terminal
Artificial intelligence based learning system. Providing learning content to a user terminal in an interface unit and receiving a user voice according to the use of the learning content from the user terminal;
Generating a user analysis data by analyzing a user voice according to the use of the learning content in a voice analysis unit;
Machine learning (Machine learning) the user analysis data in the learning evaluation unit, based on the machine-learned user analysis data to determine the user's rating and vulnerability information, customized learning corresponding to the determined rating and vulnerability information Steps to extract content
Artificial intelligence-based learning method comprising a.

Images