KR102338217B1 - control method for language learning system - Google Patents

Abstract

A control method of a language learning system comprises the following steps of: allowing a server to obtain an access time point of a first terminal; allowing the server to obtain learning information generated by the first terminal and share learning information with a second terminal corresponding to the first terminal in real time; allowing the server to obtain an end time point of the first terminal; and allowing the server to generate achievement information based on the learning information to share it with the first terminal and the second terminal.

Description

Control method for language learning system {control method for language learning system}

The present invention provides a language learning system including infants and children, students and adults, in particular, free learning without the eyes of others observing around for subjects that require parental or teacher learning guidance and learning observation, such as infants and students. It relates to a control method of a language learning system that creates an atmosphere, but enables a guardian or a teacher to observe learning through a terminal (second terminal).

The conventional learning system is simply made in a passive type based on an educational image or a study sheet. In the case of an educational video, an educational method is used in which the user watches the video and repeats the sentence or word, or writes an answer corresponding to the silenced section.

However, in this conventional learning system, when infants and young children are the subject, there are temporal/spatial restrictions on the learning being carried out in a situation accompanied by a guardian or teacher during learning in order for the guardian or teacher to observe the learning status, and in the case of a student , there is a problem that learning cannot proceed smoothly because it is burdened by others' observation of learning.

In addition, there has been a problem in that the conventional learning system does not provide a method for preventing a situation in which students including infants and young children are neglected in learning in a situation where there is no observation of a guardian or a teacher.

Registered Patent Publication No. 10-1060285, 2011.08.23.

The problem to be solved by the present invention is to prevent a student conducting learning through a learning system from losing concentration on learning by direct supervision of a guardian or teacher, but enabling the guardian or teacher to indirectly observe the learning process To provide a method for controlling a language learning system including a server, a first terminal, and a second terminal.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

In the control method of a language learning system according to an aspect of the present invention for solving the above-mentioned problems, the server acquires the access point of the first terminal, the server acquires the learning information generated by the first terminal and sharing the learning information in real time with the second terminal corresponding to the first terminal, the server, obtaining the end time of the first terminal, and the server, generating achievement information based on the learning information, The step of sharing to the first terminal and the second terminal, and the step of sharing the learning information in real time may further include, by the server, matching the first terminal and the second terminal.

In this case, the step of obtaining the access point includes, by the server, notifying the second terminal of the access of the first terminal, the server obtaining age information and gender information corresponding to the first terminal, the server, artificial intelligence Extracting a first keyword corresponding to the age information and gender information through the model, and sharing at least one first image information corresponding to the first keyword to the first terminal, and the server, at least one from the first terminal The method may further include obtaining a keyword of interest and sharing at least one piece of second image information corresponding to the keyword of interest to the first terminal, and the step of obtaining an end time may include: the server, the first to the second terminal It may further include the step of notifying the termination of the terminal.

In addition, the step of obtaining the learning information, the server, the step of obtaining the selected image information from the first terminal, the server, from the first terminal to generate learning information including shooting information and recording information for a student The step and the server further comprising the step of evaluating the learning information based on the selected image information and sharing the evaluation information to the second terminal, the step of matching the first terminal and the second terminal, the server, the second terminal The step of sharing the shooting information and the recording information in real time and the server may further include the step of generating a chatting screen shared by the first terminal and the second terminal.

In addition, the step of evaluating the learning information and sharing the evaluation information to the second terminal includes, by the server, acquiring at least one of pronunciation error information, erroneous word information, and a verbal action map based on the learning information, and pronunciation error information and Matching oral motion map corresponding to each of the erroneous word information, the server acquiring pronunciation information corresponding to at least one of the pronunciation error information and the erroneous word information, the server providing an example oral motion action image corresponding to the pronunciation information matching the pronunciation information and the example oral motion image, the server determining the similarity between the example oral motion image and the oral motion map according to a preset criterion to obtain a oral motion score, the server, artificial intelligence Using the model, obtaining a re-learning necessary score based on preset weights corresponding to each of the pronunciation error information and the erroneous word information, and generating, by the server, evaluation information based on the oral action score and the re-learning required score may further include, and the step of obtaining at least one of pronunciation error information, erroneous word information, and oral action map based on the learning information includes, by the server, through an artificial intelligence model, pronunciation error information and erroneous word information. obtaining a phonetic symbol correlation value with Obtaining the third image information including, and sharing it with the first terminal as a first review image, the step of generating the achievement information includes, by the server, the first evaluation information and the second evaluation information The step of comparing with the third evaluation information and the server further comprising the step of obtaining, by the server, achievement information including an achievement rate graph generated based on the comparison result of the first to third evaluation information, the first evaluation information , the first evaluation information, the second evaluation information is the evaluation information generated immediately before, the third evaluation information is the evaluation information generated in the rearmost row, it is characterized in that it is generated based on the review video.

In addition, in the step of generating the learning information including the shooting information and the recording information, when a section in which the recording information is blank is obtained over a preset time, the server receives the shooting information corresponding to the section in which the recording information is blank acquiring, by the server, acquiring whether the student object corresponding to the first terminal can be acquired from the shooting information corresponding to the blank section, the server, based on whether the object is acquired, the first non-learning event and the second Acquiring at least one non-learning event among non-learning events, when the first non-learning event is obtained, increasing, by the server, a volume value corresponding to the selected image information to a preset volume, a second non-learning event is obtained, the server shares the second non-learning event occurrence time with the second terminal, the server calculates the total learning time based on the access time and the end time, but calculates the time corresponding to the blank section The step of excluding from the total learning time and the server may further include the step of calculating a recommended learning time based on the total learning time and transmitting it to the first terminal, and the step of obtaining the second non-learning event includes: , obtaining a background image from the first terminal, the server obtaining a plurality of symbols included on the background image, and the server, among the plurality of symbols, when more than a preset number of symbols are detected, the second non-learning acquiring the event.

In addition, the step of acquiring at least one of pronunciation error information, erroneous word information, and oral action map based on the learning information includes: acquiring, by the server, a first sound pattern that is a sound pattern for each sentence based on the selected image information; obtaining, by the server, a second sound pattern corresponding to the first sound pattern from the recording information; matching, by the server, the first sound pattern and the second sound pattern determined to be similar to or greater than a preset standard, and matching other sound patterns Acquiring, by the server, a second sound pattern that has not been obtained as error information, based on the occurrence time of the second sound pattern obtained as error information, a first sound pattern having the same occurrence time as error information A step of matching a sound pattern, the server defining, as pronunciation error information, error information that is similar to a sound more than a preset standard among the first and second sound patterns matched in the error information as pronunciation error information, and the server The method further includes the step of defining similar error information as erroneous word information that is less than a preset standard, wherein the pronunciation information includes a first sound pattern.

In this case, the step of matching the first sound pattern and the second sound pattern having the same generation time point to each other may include comparing the matched first sound pattern and the second sound pattern in the error information so that the second sound pattern is the first sound pattern. When the section in which the difference occurs has a goodness of a sound that is repeated at least once, the server calculates, by the server, an average mapness for at least two repeated maps, the server, a plurality of repeated maps located in the section where the difference occurs obtaining a third sound pattern by replacing the In a similar case, the server acquires the second sound pattern corresponding to the third sound pattern as stuttered section information, and the server shares the image information corresponding to the stuttered section information as a second review image to the first terminal and, in the control method of the present invention, when the server shares at least one of the first to second review images with the first terminal, the server responds to the first to second review images. The method may further include outputting, by the server, the oral motion map and the example oral motion image to the first terminal, acquiring the real-time oral motion map from the first terminal, and simultaneously outputting the real-time oral motion map to the first terminal have.

Finally, the step of obtaining the plurality of symbols included on the background image includes, by the server, generating reference coordinates on the background image, the server obtaining, by the server, the plurality of first symbols included on the background image; The server may further include obtaining, by the server, a plurality of second symbols having a density of less than or equal to a preset interval at the reference coordinates among the first symbols, and when more than a preset number of symbols are detected, acquiring a second non-learning event The step of: obtaining, by the server, the number of detected second symbols; if the obtained number is equal to or greater than a preset criterion, determining whether or not to obtain the oral motion map, by the server; when the oral motion map is obtained , the server acquiring an oral motion score corresponding to the oral motion map, the server acquiring an average oral motion score corresponding to the first evaluation information and the second evaluation information, and the server acquiring an average oral motion score When it is determined that the oral motion score is lower than the oral motion score by more than a preset range, the method may further include the step of acquiring a first non-learning event, and the step of determining whether to acquire the oral motion map may include: when the oral motion map is not acquired , the server determines whether the student object is obtained, if the student object is obtained, the server obtains the first non-learning event and when the student object is not obtained, the server receives the second non-learning event The method may further include acquiring, wherein the reference coordinates are central coordinates on the background image or central coordinates for a region in which the oral motion score is calculated the highest among regions in which the oral motion map is obtained.

Other specific details of the invention are included in the detailed description and drawings.

Effects generated by the control method of the language learning system of the present invention include,

First, there is no spatial/temporal restriction on learning because learning is performed through the first terminal (student terminal).

Second, since the parent or teacher's observation of the learning of the student (including infants, adolescents, and adults) is indirectly made, the burden that may be felt in the learning situation is relieved by direct observation of the learning.

Third, indirect learning observation is made of a second terminal (guardian or teacher terminal), so there is no spatial/temporal constraint on learning observation.

Fourth, automatic detection of sentences/words in which an error occurred (wrong or incorrect answer) is not required.

Fifth, pronunciation information corresponding to a sentence/word in which an error has occurred (wrong or incorrect answer) is obtained, and a plurality of words including the obtained pronunciation information are provided for review, and an error corresponding to the obtained pronunciation information occurs frequency can be reduced.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a diagram of a student's learning state through a first terminal according to an embodiment of the present invention.
2 is a state diagram in which learning information is shared in real time with a second terminal matched with a first terminal according to an embodiment of the present invention.
3 is an achievement rate graph according to an embodiment of the present invention.
4 is a system configuration diagram according to an embodiment of the present invention.
5 is a basic flowchart according to an embodiment of the present invention.
6 is a configuration diagram of a server according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully understand the scope of the present invention to those skilled in the art, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

As used herein, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and “unit” or “module” performs certain roles. However, “part” or “module” is not meant to be limited to software or hardware. A “unit” or “module” may be configured to reside on an addressable storage medium or to reproduce one or more processors. Thus, as an example, “part” or “module” refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Components and functionality provided within “parts” or “modules” may be combined into a smaller number of components and “parts” or “modules” or as additional components and “parts” or “modules”. can be further separated.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms including different directions of components during use or operation in addition to the directions shown in the drawings. For example, when a component shown in the drawing is turned over, a component described as “beneath” or “beneath” of another component may be placed “above” of the other component. can Accordingly, the exemplary term “below” may include both directions below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In this specification, a computer refers to all types of hardware devices including at least one processor, and may be understood as encompassing software configurations operating in the corresponding hardware device according to embodiments. For example, a computer may be understood to include, but is not limited to, smart phones, tablet PCs, desktops, notebooks, and user clients and applications running on each device.

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

1 is a diagram of a student's learning state through a first terminal according to an embodiment of the present invention. 2 is a state diagram in which learning information is shared in real time with a second terminal matched with a first terminal according to an embodiment of the present invention. 3 is an achievement rate graph according to an embodiment of the present invention. 4 is a system configuration diagram according to an embodiment of the present invention. 5 is a basic flowchart according to an embodiment of the present invention. 6 is a configuration diagram of a server according to an embodiment of the present invention.

According to FIG. 4 , the present invention includes a server 100 , a first terminal 200 , and a second terminal 300 , and in this case, the first terminal 200 and the second terminal 300 may be electronic devices. have.

In one embodiment, the electronic device is a smartphone, a tablet personal computer (PC), a mobile phone, a video phone, an e-book reader, a desktop PC (desktop PC), a laptop PC (laptop PC), netbook computer (netbook computer), workstation (workstation), server, PDA (personal digital assistant), PMP (portable multimedia player), MP3 player, mobile medical device, camera, or wearable device (wearable device) ), and may include at least one of an AI speaker.

In addition, the first terminal 200 may be a terminal of a student who performs learning using the language learning system according to the present invention, and the second terminal 300 may be a terminal of a student's guardian or a terminal of a student's teacher .

As shown in FIG. 6 , the server 100 may include a memory 110 , a communication unit 120 , and a processor 130 .

The memory 110 may store various programs and data necessary for the operation of the server 100 . The memory 110 may be implemented as a non-volatile memory 110 , a volatile memory 110 , a flash-memory 110 , a hard disk drive (HDD), or a solid state drive (SSD).

The communication unit 120 may communicate with an external device. In particular, the communication unit 120 may include various communication chips such as a Wi-Fi chip, a Bluetooth chip, a wireless communication chip, an NFC chip, and a Bluetooth low power chip (BLE chip). At this time, the Wi-Fi chip, the Bluetooth chip, and the NFC chip perform communication in a LAN method, a WiFi method, a Bluetooth method, and an NFC method, respectively. In the case of using a Wi-Fi chip or a Bluetooth chip, various types of connection information such as an SSID and a session key are first transmitted and received, and then various types of information can be transmitted and received after a communication connection using this. The wireless communication chip refers to a chip that performs communication according to various communication standards, such as IEEE, ZigBee, 3rd Generation (3G), 3rd Generation Partnership Project (3GPP), and Long Term Evolution (LTE).

The processor 130 may control the overall operation of the server 100 using various programs stored in the memory 110 . The processor 130 may include a RAM, a ROM, a graphic processing unit, a main CPU, first to n interfaces, and a bus. In this case, the RAM, ROM, graphic processing unit, main CPU, first to n interfaces, etc. may be connected to each other through a bus.

RAM stores O/S and application programs. Specifically, when the server 100 is booted, O/S may be stored in the RAM, and various application data selected by the user may be stored in the RAM.

The ROM stores an instruction set for booting the system, and the like. When a turn-on command is input and power is supplied, the main CPU copies the O/S stored in the memory 110 to the RAM according to the command stored in the ROM, and executes the O/S to boot the system. Upon completion of booting, the main CPU copies various application programs stored in the memory 110 to the RAM, and executes the application programs copied to the RAM to perform various operations.

The graphic processing unit generates a screen including various objects such as items, images, and texts by using a calculation unit (not shown) and a rendering unit (not shown). Here, the calculation unit may be configured to calculate attribute values such as coordinate values, shape, size, color, etc. of each object to be displayed according to the layout of the screen by using the control command received from the input unit. In addition, the rendering unit may be configured to generate screens of various layouts including objects based on the attribute values calculated by the operation unit. The screen generated by the rendering unit may be displayed in the display area of the display.

The main CPU accesses the memory 110 and performs booting using the OS stored in the memory 110 . In addition, the main CPU performs various operations using various programs, contents, data, etc. stored in the memory 110 .

The first to n interfaces are connected to the various components described above. One of the first to n interfaces may be a network interface connected to an external device through a network.

Meanwhile, further, the processor 130 may control the artificial intelligence model. In this case, of course, the processor 130 may include a graphics-only processor (eg, GPU) for controlling the artificial intelligence model.

Meanwhile, the artificial intelligence model according to the present invention may be a model based on supervised learning or unsupervised learning by a teacher. Furthermore, the artificial intelligence model according to the present invention may include a support vector machine (SVM), a decision tree, a neural network, and the like, and methodologies to which these are applied.

In one embodiment, the artificial intelligence model according to the present invention may be an artificial intelligence model based on a convolutional deep neural network (CNN) learned by inputting learning data. However, the present invention is not limited thereto, and it goes without saying that various artificial intelligence models may be applied to the present invention. For example, a model such as a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), or a Bidirectional Recurrent Deep Neural Network (BRDNN) may be used as the AI model, but is not limited thereto.

In this case, convolutional deep neural networks (CNNs) are a type of multilayer perceptrons designed to use minimal preprocessing. A convolutional neural network consists of one or several convolutional layers and general artificial neural network layers on top of it, and additionally utilizes weights and pooling layers. Thanks to this structure, the convolutional neural network can fully utilize the input data of the two-dimensional structure. In addition, convolutional neural networks can be trained via standard backpropagation. Convolutional neural networks are easier to train than other feed-forward neural network techniques and have the advantage of using fewer parameters.

In addition, deep neural networks (DNNs) are artificial neural networks (ANNs) composed of a plurality of hidden layers between an input layer and an output layer.

In this case, the structure of the deep neural network may be composed of a perceptron. A perceptron consists of several inputs, one processor, and one output value. The processor multiplies each input value by a weight, and then sums the input values multiplied by the weight. Then, the processor outputs one output value by substituting the summed value into the activation function. If a specific value is desired as the output value of the activation function, the weight multiplied by each input value may be corrected, and the output value may be recalculated using the modified weight. In this case, each perceptron may use a different activation function. In addition, each perceptron receives the outputs from the previous layer as input, and then uses the activation function to obtain the output. The obtained output is transferred to the input of the next layer. Through the process as described above, some output values can be finally obtained.

A recursive neural network (RNN) refers to a neural network in which connections between units constituting an artificial neural network constitute a directed cycle. Unlike forward neural networks, recurrent neural networks can utilize the memory inside the neural network to process arbitrary inputs.

Deep Belief Networks (DBN) is a generative graphical model used in machine learning, and in deep learning, it means a deep neural network composed of multiple layers of latent variables. There is a connection between layers, but there is no connection between units within a layer.

The deep trust neural network can be used for prior learning due to the nature of the generative model, and after learning the initial weights through prior learning, the weights can be fine-tuned through backpropagation or other discrimination algorithms. This characteristic is very useful when the training data is small, because the smaller the training data, the stronger the effect of the initial value of the weight on the resulting model. The pre-learned initial weight value is closer to the optimal weight compared to the arbitrarily set initial weight value, which enables performance and speed improvement in the fine-tuning stage.

The above-described artificial intelligence and its learning method have been described for illustrative purposes, and the artificial intelligence and its learning method used in the embodiments described below are not limited. For example, all kinds of artificial intelligence technology and a learning method thereof that a person skilled in the art can apply to solve the same problem may be utilized to implement the system according to the disclosed embodiment.

According to FIG. 5, in the method of controlling a language learning system according to an aspect of the present invention, the server 100 acquires the access point of the first terminal 200, which is a student terminal, the server 100 includes the second A step of acquiring the learning information generated by the first terminal 200 and sharing the learning information in real time with the second terminal 300 that is the parent terminal corresponding to the first terminal 200, the server 100, the first The step of obtaining the end time of the terminal 200 and the server 100, generating achievement information based on the learning information, and sharing it with the first terminal 200 and the second terminal 300 .

In the step of the server 100 acquiring the access point of the first terminal 200, which is a student terminal, as shown in FIG. 2, the access point of the second terminal 300 matched with the first terminal 200 (learning start time) can be shared.

In the step of the server 100, acquiring the learning information generated by the first terminal 200, and sharing the learning information in real time with the second terminal 300, which is a parent terminal corresponding to the first terminal 200, As shown in FIG. 1 , the first terminal 200 collects learning information about the student performing learning corresponding to the first terminal 200 in real time, and as shown in FIG. 2 , the second It can be shared with the terminal 300 .

Here, the learning information includes image information (first to third image information, selected image information, first and second review images, etc.) collected or generated by the first terminal 200 for the student, error information (pronunciation error information, etc.) . etc.) may be

In this case, the step of sharing the learning information in real time may further include, by the server 100 , matching the first terminal 200 and the second terminal 300 .

In addition, the step of obtaining the access point includes the server 100 notifying the second terminal 300 of the access of the first terminal 200 , the server 100 corresponding to the first terminal 200 . obtaining age information and gender information, the server 100 extracts a first keyword corresponding to the age information and gender information through an artificial intelligence model, and at least one first image information corresponding to the first keyword to the first terminal 200, and the server 100 obtains at least one interest keyword from the first terminal 200, and transmits at least one second image information corresponding to the interest keyword to the first terminal (200) may further include the step of sharing.

In the step of the server 100 notifying the second terminal 300 of the connection of the first terminal 200, the second terminal 300 is in a state in which the application has been downloaded to receive the service provided by the system of the present invention. , the server 100 transmits a specific signal (vibration, sound, screen output, etc.) to the second terminal 300 through the application installed in the second terminal 300, so that the student corresponding to the first terminal 200 learns You can notify in real time that you have started.

In the step of the server 100 acquiring age information and gender information corresponding to the first terminal 200 , the server 100 collects personal information based on the student's member information corresponding to the first terminal 200 . The above steps can be implemented by obtaining.

At this time, the first terminal 200 pre-downloads the language learning program provided by the system of the present invention for logging into the server 100, or accesses a site linked with the server 100 of the present invention to use the service. can

The server 100 extracts a first keyword corresponding to age information and gender information through an artificial intelligence model, and shares at least one first image information corresponding to the first keyword to the first terminal 200 In , when age information and gender information are input information, the first keyword may be provided as output information based on the age information and gender information in the artificial intelligence model.

In addition, the server 100 may acquire an image including the first keyword as a hashtag (#) as the first image information from the server 100 or another server 100, and a plurality of images included in the first keyword The number of detections of the keywords is matched, and the greater the number of detections, the higher in the list of first keywords.

Accordingly, when the plurality of first image information is provided to the first terminal 200 , the first image information including the keyword positioned higher in the list of first keywords is to be recommended at the top of the screen of the first terminal 200 . Also, among the keywords included in the first keyword, the first image information having the most keywords included as hashtags may be located at the top of the screen of the first terminal 200 .

For example, the student corresponding to the first terminal 200 is a female at the age of 8, and the first keyword output for the 8-year-old and female includes magical girl, cat, puppy, dress, etc., and the number of detections is high. When the keywords are listed first, the server 100 places the first image information including the magical girl as a hashtag at the top of the screen of the first terminal 200, but the first image including the magical girl and the cat as the hashtag The information can be output so that it is located above the first image information including only the magical girl as a hashtag.

The server 100, obtaining at least one keyword of interest from the first terminal 200, and sharing at least one second image information corresponding to the keyword of interest to the first terminal 200 includes, The step of the server 100 obtaining a search term from the first terminal 200, the server 100 obtaining at least one interest keyword from the search word, the server 100, at least one corresponding to the interest keyword It may further include the step of acquiring the second image information of the sharing to the first terminal (200).

For example, when login information corresponding to the first terminal 200 is generated, the server 100 automatically recommends the first image information based on personal information corresponding to the login information.

At this time, when the student corresponding to the first terminal 200 searches within the first image information or wants to acquire the second image information that is new image information, the search provided on the screen of the first terminal 200 A search word is input into the window, and the server 100 may acquire at least one second image information searched based on the keyword of interest extracted based on the search word and share it on the screen of the first terminal 200 .

In this case, the server 100 may train the artificial intelligence model so that the keyword of interest becomes output information corresponding to age information and gender information.

For example, in the control method of the present invention, the server 100 obtains an interest keyword, the server 100 obtains age information and gender information corresponding to the interest keyword, and the server 100 obtains an interest The method may further include training an artificial intelligence model for evaluating the association between the age information and the gender information and the first keyword by using the learning data including the keyword, the age information, and the gender information.

In this case, the keyword of interest may be finally obtained as the first keyword.

In addition, the step of obtaining the end point further includes, by the server 100, notifying the second terminal 300 of the end of the first terminal 200, the guardian ( Or, the teacher) can confirm the fact that the class of the student corresponding to the first terminal 200 has ended.

The step of acquiring the learning information includes, by the server 100, acquiring the selected image information from the first terminal 200, the server 100, shooting information targeting the student from the first terminal 200 and The step of generating learning information including recording information and the server 100 may further include the step of evaluating the learning information based on the selected image information and sharing the evaluation information with the second terminal 300 .

In the step of the server 100 acquiring the selected image information from the first terminal 200 , the selected image information may be either the first image information or the second image information.

In the step of the server 100, generating learning information including shooting information and recording information for a student from the first terminal 200, as shown in FIG. 1, it is built into the first terminal 200 Alternatively, photographing information and recording information may be acquired through a connected camera, speaker, and microphone and transmitted from the first terminal 200 to the server 100 .

In the step of the server 100 evaluating the learning information based on the selected image information and sharing the evaluation information to the second terminal 300 , as shown in FIG. 2 , the amount of learning is displayed on the screen of the second terminal 300 . , real-time scores, etc. are shared so that guardians (or teachers) can check the current learning progress and achievement of their children (or students).

The step of matching the first terminal 200 and the second terminal 300 includes the server 100 sharing the shooting information and the recording information with the second terminal 300 in real time, and the server 100 is the second The method may further include generating a chatting screen shared by the first terminal 200 and the second terminal 300 .

In the step of the server 100 sharing the shooting information and the recording information to the second terminal 300 in real time, as shown in FIG. 2 , the server 100 sends the second terminal 300 to the first terminal 200 ), by sharing the audio and video acquired in real time, it is possible to provide a service so that the guardian (or teacher) can check the current learning status of the child (or student).

In this case, as shown, image information reproduced in the first terminal 200 in the second terminal 300 may be checked.

In the step of the server 100 generating a chatting screen shared by the first terminal 200 and the second terminal 300 , as shown in FIG. 2 , the server 100 includes the first terminal 200 and the second terminal 300 . A message inputted to the second terminal 300 may be transmitted to a matched terminal, but a chatting screen may be generated and provided to check the details of messages transmitted by each other.

In the step of evaluating the learning information and sharing the evaluation information to the second terminal 300, the server 100 acquires at least one of pronunciation error information, error word information, and oral action map based on the learning information, and pronunciation Matching the oral action map corresponding to the error information and the error word information, respectively, the server 100 acquiring pronunciation information corresponding to at least one of the pronunciation error information and the error word information, the server 100, obtaining an example oral motion image corresponding to the pronunciation information and matching the pronunciation information with the example oral motion image; the server 100 determines the similarity between the example oral motion image and the oral motion map according to a preset criterion to determine the oral order Acquiring the operation score, the server 100, through the artificial intelligence model, the step of acquiring a score necessary for re-learning based on preset weights corresponding to each of the pronunciation error information and the erroneous word information, and the server 100 , may further include the step of generating evaluation information based on the oral motion score and the re-learning required score.

The server 100 acquires at least one of pronunciation error information, erroneous word information, and oral action map based on the learning information, and matches the oral oral action map corresponding to the pronunciation error information and the erroneous word information, respectively, in the pronunciation The error information is a section in which the mismatched language is detected when a language that does not match the read sentence provided by the server 100 to the first terminal 200 is detected in the recorded information.

Error word information means that, when the server 100 transmits dictation information for listening and writing to the first terminal 200 , the word entered into the first terminal 200 is misspelled or not written, and the server 100 ), when a language that does not match with the read-along word provided to the first terminal 200 is detected in the recorded information, it is characterized in that it is a section in which the language does not match.

The oral motion map is characterized as information obtained by mapping the movement of the characteristic points by acquiring a plurality of characteristic points to the mouth shape of the student obtained based on the photographing information.

Specifically, when incorrect answer information of at least one of the pronunciation error information and the error word information occurs, the server 100 acquires a verbal motion map corresponding to the section between the time when the incorrect answer information is generated and the time when the incorrect answer information is terminated. and matching, by the server 100, the oral order motion map to the incorrect answer information.

When the server 100 acquires pronunciation information corresponding to at least one of the pronunciation error information and the erroneous word information, the server 100 generates incorrect answer information on at least one of the pronunciation error information and the erroneous word information and obtaining, by the server 100, a sentence or word corresponding to a section between the time points where the incorrect answer information is terminated, and extracting, by the server 100, pronunciation information about the sentence or word.

Here, the pronunciation information may be a data obtained by correctly pronouncing a sentence or word or a sound corresponding to a section between a time point at which incorrect answer information is terminated in the selected image information.

In the step where the server 100 acquires an example oral motion image corresponding to the pronunciation information and matches the pronunciation information and the example oral motion image, the example oral motion image is a native speaker or a video producer or a 3D character pronounces the pronunciation information It is characterized in that it is image information about the shape of the lips.

In the step in which the server 100 determines the similarity between the example oral motion image and the oral motion map according to a preset criterion to obtain a oral motion score, the server 100 extracts the example oral motion map from the example oral motion image step, the server 100 extracting a first vector amount that is a vector value of the oral motion map, and extracting a second vector amount that is a vector value of an exemplary oral motion map, the server 100, the first to The method may further include determining similarity based on the second vector amount and obtaining, by the server 100, an oral motion score proportional to the similarity.

That is, by comparing the mouth shape of the student with the example mouth shape for the same pronunciation information, a score can be set according to whether the mouth shape is similar.

In the step of the server 100, through the artificial intelligence model, acquiring a re-learning necessary score based on a preset weight corresponding to each of the pronunciation error information and the erroneous word information, the preset weight is specifically, pronunciation error information And, for the incorrect answer information including error word information, the difficulty is high and similar incorrect answer information or the same incorrect answer information is generated based on the difficulty by problem, the difficulty by video information, the difficulty by pronunciation information, the number of times of generation of similar incorrect information, the number of times of generation of the same incorrect information, etc. The higher the number, the higher the weight.

Therefore, the higher the weight, the higher the re-learning required score is obtained proportionally, and accordingly, the server 100, in the step of generating evaluation information based on the oral operation score and the re-learning required score, corresponding to the evaluation information The number of times required for re-learning may increase.

Here, the artificial intelligence model serves to calculate the number of times of generating similar incorrect answer information and the number of generating the same incorrect answer information, that is, using a plurality of pronunciation error information and a plurality of incorrect word information as input variables, the number of similar incorrect answer information generated , it is possible to output the number of times of generating the same incorrect answer information.

Acquiring at least one of pronunciation error information, error word information, and oral action map based on the learning information includes, by the server 100, through an artificial intelligence model, pronunciation error information and pronunciation symbol association based on the error word information. obtaining, by the server 100, a plurality of words including phonetic symbol information corresponding to the phonetic symbol association value when the phonetic symbol association value is equal to or greater than a preset value, and the server 100, The method may further include acquiring the third image information including the words and sharing it with the first terminal 200 as a first review image.

In the step of the server 100, through the artificial intelligence model, acquiring the pronunciation symbol association value based on the pronunciation error information and the erroneous word information, the pronunciation error information and the correct answer information corresponding to the erroneous word information are compared and similar or identical It is determined whether a phonetic symbol with a sound exists, and if it exists, how similar it is can be obtained as a correlation value.

In this case, the correlation values may be obtained as 0 when they are not similar, and may be obtained as 1 when they are the same.

When the phonetic symbol correlation value is equal to or greater than a preset value, in the step of the server 100 acquiring a plurality of words including phonetic symbol information corresponding to the phonetic symbol correlation value, in one embodiment, the set value is 0.5, which is 50% , obtaining, by the server 100, at least one phonetic symbol having a correlation value of 0.5 or more and 1 or less as phonetic symbol information, and the server 100, a plurality of words including phonetic symbol information or having similar phonetic symbols It may further include the step of obtaining

In the step of the server 100 acquiring third image information including a plurality of words and sharing it with the first terminal 200 as a first review image, the server 100, through an artificial intelligence model, The method may further include obtaining, by the server 100, at least one second keyword corresponding to the words, and obtaining, by the server 100, at least one piece of recommended image information corresponding to the second keyword as third image information.

In the step of the server 100 acquiring at least one second keyword corresponding to the plurality of words through the artificial intelligence model, the second keyword may relate to a story topic that can be extracted due to the plurality of words .

Specifically, when receiving a plurality of words, the artificial intelligence model may obtain a plurality of topics that can be extracted from the plurality of words, and output a second keyword indicating which can be a hashtag corresponding to the plurality of topics. .

In the step of the server 100 acquiring at least one piece of recommended image information corresponding to the second keyword as the third image information, the recommended image information including the second keyword as a hashtag, that is, the subject indicated by the second keyword It is possible to obtain the recommended image information in which the story proceeds as the third image information.

Therefore, the present invention acquires image information with a high probability of appearing a sentence or word having a pronunciation similar or identical to the pronunciation frequently mistaken by a student, and transmits it to the first terminal 200 as third image information, which is image information for review. can provide

In the step of generating the achievement information, the server 100 compares the first evaluation information and the second evaluation information with the third evaluation information, and the server 100 compares the first to third evaluation information. Further comprising the step of obtaining achievement information including a graph of the achievement rate generated based on the first evaluation information, the first evaluation information, the second evaluation information, the evaluation information that occurred immediately before, the third evaluation information , is the evaluation information generated in the most rear row, and is characterized in that it is generated based on the review image.

As shown in FIG. 3 , the first to third evaluation information may be numericalized and expressed as a score, and the comparison achievement information may be expressed as a graph as shown.

In the step of generating learning information including shooting information and recording information, when a section in which the recording information is blank is obtained over a preset time, the server 100, shooting information corresponding to the section in which the recording information is blank step of obtaining, the server 100 obtaining whether the student object corresponding to the first terminal 200 can be obtained from the shooting information corresponding to the blank section, the server 100 determining whether the object is obtained Based on the first non-learning event and the second non-learning event, obtaining at least one non-learning event, when the first non-learning event is obtained, the server 100 selects a volume value corresponding to the selected image information The step of increasing the volume to a preset volume, when the second non-learning event is obtained, the server 100 sharing the second non-learning event occurrence time point with the second terminal 300, the server 100 accessing Calculating the total learning time based on the starting point and the ending time, excluding the time corresponding to the blank section from the total learning time, and the server 100 calculates the recommended learning time based on the total learning time to first The method may further include transmitting to the terminal 200 .

The steps additionally included in the step of generating the learning information including the shooting information and the recording information are steps for detecting and coping with situations in which the student does not study or is unable to concentrate on learning, such as leaving a seat.

Specifically, when a section in which the recording information is blank is obtained over a preset time, in the step of the server 100 acquiring shooting information corresponding to the section in which the recording information is blank, the server 100 first By storing the voice information of the pre-registered student in the terminal 200, it is possible to determine whether a corresponding voice is obtained from the recording information based on the voice information.

Accordingly, it is possible to determine a section in which a voice corresponding to the voice information is not obtained as a blank section of the recording information, and determine the shooting information obtained at a time point corresponding to the blank section.

In the step of the server 100 acquiring whether the student object corresponding to the first terminal 200 can be obtained from the shooting information corresponding to the blank section, the student object is the It may be image information corresponding to the face image.

In the step of the server 100 acquiring at least one non-learning event among the first non-learning event and the second non-learning event based on whether the object is acquired, the first non-learning event may occur when the object is acquired An event that exists in response to a student falling asleep while learning or engaging in a behavior other than learning.

Also, the second non-learning event is an event that may occur when an object is not obtained, and may mean that a student leaves the space in which the first terminal 200 is located during learning.

When the first non-learning event is obtained, in the step of the server 100 increasing the volume value corresponding to the selected image information to a preset volume, in order to encourage the concentration of the student corresponding to the first terminal 200 By increasing the volume to a certain volume, an alarm effect can be given.

When the second non-learning event is obtained, in the step of the server 100 sharing the second non-learning event occurrence time point with the second terminal 300 , the server 100 is a terminal of a guardian (or a teacher) By sending an alarm to the second terminal 300, information about the absence of a student can be provided, and the second terminal 300 can share real-time shooting information, as shown in FIG. It is possible to recognize the absence of the student by checking the situation being photographed in the first terminal 200 .

The server 100 calculates the total learning time based on the access point and the end time, but excludes the time corresponding to the blank section from the total learning time, and the server 100 recommends it based on the total learning time In the step of calculating the learning time and transmitting it to the first terminal 200, based on the total learning time of the student, it is recommended compared to the recommended daily, weekly, and monthly learning amount previously registered by the first terminal 200 or the teacher Learning time can be provided.

Acquiring the second non-learning event includes, by the server 100, acquiring a background image from the first terminal 200, and acquiring, by the server 100, a plurality of symbols included in the background image and obtaining, by the server 100, a second non-learning event when more than a preset number of symbols are detected among the plurality of symbols.

In the step of the server 100 acquiring the background image from the first terminal 200 , the background image is an image excluding the object.

In the step of the server 100 acquiring the plurality of symbols included on the background image, the symbols are the vertices of the bookshelf, the vertices of the door frames, the door handles, the corners of the wall, the corners, the vertices of the chair headrest, and the vertex of the chair backrest. It can include coordinates of a vertex, the center point of a wall clock, the center point of a table clock, and the like.

When the server 100 detects more than a preset number of symbols among the plurality of symbols, in the step of acquiring the second non-learning event, when an object is acquired based on shooting information, specific symbols are detected by being obscured by the object However, when the object is not located or is located at the edge of the background image, more than a preset number of symbols may be detected.

That is, it is possible to determine whether an object is obtained according to the number of symbols detected in real time, and through this, it is possible to determine whether the student leaves the seat or is asleep during learning.

Acquiring at least one of pronunciation error information, erroneous word information, and oral action map based on the learning information includes, by the server 100, acquiring a first sound pattern that is a sound pattern for each sentence based on the selected image information , server 100, obtaining a second sound pattern corresponding to the first sound pattern from the recording information, the server 100 matches the first sound pattern and the second sound pattern determined to be similar to or more than a preset standard and obtaining, by the server 100, a second sound pattern that is not matched with other sound patterns as error information; The step of matching the sound pattern with the second sound pattern obtained as error information, the server 100 receives error information similar to the sound shape among the first and second sound patterns matched in the error information above a preset standard The step of defining the pronunciation error information and the server 100 may further include the step of defining, by the server 100, similar error information as the error word information in which the soundness is less than a preset standard, the pronunciation information is the first sound pattern characterized by including.

In this case, the sound pattern including the first and second sound patterns is information on the voice system, and it is characterized in that it includes breathing, vocalization, and articulation.

In the step of the server 100 acquiring a first sound pattern that is a sound pattern for each sentence based on the selected image information, the first sound pattern relates to the audio information output from the selected image information (correct answer).

In the step of the server 100 obtaining a second sound pattern corresponding to the first sound pattern from the recording information, the second sound pattern relates to voice information output from the recording information (student answer).

In the step of the server 100 matching the first sound pattern and the second sound pattern determined to be similar to or more than a preset standard, and acquiring a second sound pattern that does not match other sound patterns as error information, the first sound pattern A second sound pattern determined to be similar to (correct answer) may be classified as a correct answer, and a second sound pattern having no similar first sound pattern may be classified as incorrect answer and error information.

In the step of the server 100 matching the first sound pattern having the same occurrence time with the second sound pattern obtained as the error information, based on the occurrence time of the second sound pattern obtained as the error information, the second sound The correct answer word or sentence corresponding to the second sound pattern may be obtained by specifying the first sound pattern, which is correct answer information for the pattern.

In the step of the server 100 defining, as pronunciation error information, error information similar to a sound more than a preset standard among the first sound pattern and the second sound pattern matched in the error information, the second error information (wrong answer) The similarity of the sound to the first sound pattern, which is correct answer information to which the sound pattern is matched, may be classified as an incorrect pronunciation in the second sound pattern rather than an incorrect answer to a word.

In the step of the server 100, in the step of defining similar error information as erroneous word information whose sound is less than a preset standard, the second sound pattern, which is error information (wrong answer), is matched with a first sound pattern and sound, which is correct information. If the appearance of ' is not similar, the second sound pattern may be classified as an incorrect answer for a word.

In the step of matching the first sound pattern and the second sound pattern having the same occurrence time point to each other, the first sound pattern and the second sound pattern matched in the error information are compared, and the second sound pattern is determined with respect to the first sound pattern. When the section in which the difference occurs has a sound quality that is repeated at least once, the server 100 calculates an average mapness for at least two repeated maps, the server 100 includes a plurality of locations in the section where the difference occurs obtaining a third sound pattern by substituting, by the server 100, the third sound pattern by replacing the repeated mapsy with one average mapsy, comparing, by the server 100, the third sound pattern with a corresponding first sound pattern, the first sound pattern and the third When the sound pattern is similar to or more than a preset standard, the server 100 acquires the second sound pattern corresponding to the third sound pattern as stuttered section information, and the server 100 responds to the stuttered section information corresponding to the stuttered section information. The method may further include sharing the image information as a second review image to the first terminal 200 .

The server 100 compares the first sound pattern and the second sound pattern matched in the error information, and when the section in which the second sound pattern differs from the first sound pattern has a sound that is repeated at least once, the server 100 , in the step of calculating the average of the at least two repeated Masipsies, it can be determined that the section having the repeated sounds is stuttered while the student corresponding to the first terminal 200 is vocalizing, Accordingly, by processing the stuttered section into a non-stuttering voice, it is possible to determine whether the second sound pattern having the repeated section is correct or not.

In the step of the server 100 acquiring the third sound pattern by replacing the plurality of repeated mapsi located in the section in which the difference occurs with one average mapsi, the second sound pattern processed into a voice not stuttered in the stuttered section This third sound pattern is stored.

Comparing, by the server 100, the third sound pattern with the corresponding first sound pattern, and when the first sound pattern and the third sound pattern are similar to or more than a preset standard, the server 100 responds to the third sound pattern When it is determined that the third sound pattern is similar to the first sound pattern in the step of acquiring the corresponding second sound pattern as the stuttered section information, information on the section stuttered by the second sound pattern, which is an unprocessed form of the third sound pattern (information that is not an incorrect answer), and in the opposite case, it may be determined that it is error information (information that is an incorrect answer).

In the step of the server 100 sharing the image information corresponding to the stuttered section information to the first terminal 200 as a second review image, image information corresponding to the second sound pattern that is the stuttered section information (selected image) information, first to third image information, etc.) is classified as a second review image and shared with the first terminal 200 , but a viewpoint or a section corresponding to the stuttered section information is reproduced and transmitted to the first terminal 200 . You can have the corresponding student review it.

In the control method, when the server 100 shares at least one of the first and second review images with the first terminal 200 , the server 100 performs an oral motion map corresponding to the first and second review images. and outputting an exemplary oral motion image to the first terminal 200, and the server 100, obtaining a real-time oral motion map from the first terminal 200, and simultaneously displaying the real-time oral motion map to the first terminal 200 It may further include the step of outputting to.

Specifically, on the screen of the first terminal 200, an example oral motion image in the shape of the lips for the correct answer is output together with the oral motion map, which is the shape of the student's lips, for the incorrect answer so that they can be compared, but the student's current pronunciation The shape of the lips can be checked through the screen of the first terminal 200 like a mirror, so that the pronouncing lip motion can be corrected.

The step of obtaining a plurality of symbols included on the background image includes, by the server 100, generating reference coordinates on the background image, and the server 100 obtaining, by the server 100, a plurality of first symbols included on the background image and obtaining, by the server 100, a plurality of second symbols having a density of less than or equal to a predetermined interval at the reference coordinates among the first symbols.

When more than a preset number of symbols are detected, the step of acquiring the second non-learning event includes, by the server 100, acquiring the number of detected second symbols; The step of 100) determining whether to obtain the oral motion map, when the oral motion map is obtained, the server 100 acquiring the oral motion score corresponding to the oral motion map, the server 100, the second Obtaining an average oral motion score corresponding to the first evaluation information and the second evaluation information, and when the server 100 determines that the oral motion score is lower than the average oral motion score by more than a preset range, the first non-learning event It may further include the step of obtaining

The step of determining whether to acquire the oral motion map is, if the oral motion map is not acquired, the server 100 determines whether to acquire the student object, when the student object is acquired, the server 100, the second The step of obtaining 1 non-learning event and if the student object is not obtained, the server 100 may further include the step of obtaining a second non-learning event, the reference coordinates are the center coordinates on the background image, or It is characterized in that it is the central coordinate for the region where the oral motion score is calculated the highest among regions where the oral motion map is obtained.

In addition, the control method of the present invention recognizes a change in tone (vibration) that occurs depending on the language when a foreign language and Korean are pronounced by the same person, acquires tone information corresponding to Korean during learning, and obtains tone information from recording information When is obtained, a first non-learning event may be obtained.

In this case, the change in tone when pronouncing the native language and the foreign language may be an effect of learning by imitating the tone of a teacher who has educated the foreign language.

Specifically, the control method includes, by the server 100, acquiring tone information from the first terminal 200, the server 100 acquiring a fourth sound pattern corresponding to the tone information, the server 100 ) may further include: obtaining voice information corresponding to the fourth sound pattern from the recording information; and obtaining, by the server 100, a first non-learning event.

On the other hand, the steps of the method or algorithm described in relation to the embodiment of the present invention may be implemented as hardware directly, implemented as a software module executed by hardware, or a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any type of computer-readable recording medium well known in the art to which the present invention pertains.

The components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software components, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, including C, C++ , Java, assembler, etc. may be implemented in a programming or scripting language. Functional aspects may be implemented in an algorithm running on one or more processors.

As mentioned above, although embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains know that the present invention may be embodied in other specific forms without changing the technical spirit or essential features thereof. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

100 : server
110: memory
120: communication department
130: processor
200: first terminal
300: second terminal

Claims (8)

In the control method of a language learning system,
obtaining, by the server, an access point of the first terminal;
obtaining, by the server, the learning information generated by the first terminal, and sharing the learning information with a second terminal corresponding to the first terminal in real time;
obtaining, by the server, an end time of the first terminal; and
Including, by the server, generating achievement information based on the learning information and sharing it with the first terminal and the second terminal;
The step of sharing the learning information in real time,
Further comprising; matching, by the server, the first terminal and the second terminal;
The step of obtaining the access point includes:
notifying, by the server, the connection of the first terminal to the second terminal;
obtaining, by the server, age information and gender information corresponding to the first terminal;
extracting, by the server, a first keyword corresponding to the age information and the gender information through an artificial intelligence model, and sharing at least one first image information corresponding to the first keyword with the first terminal; and
The method further includes, by the server, obtaining at least one keyword of interest from the first terminal and sharing at least one second image information corresponding to the keyword of interest to the first terminal,
The step of obtaining the end time is,
The server notifying the end of the first terminal to the second terminal; further comprising,
The step of obtaining the learning information is,
obtaining, by the server, image information selected from the first terminal;
generating, by the server, learning information including shooting information and recording information for a student from the first terminal; and
The server evaluates the learning information based on the selected image information and shares the evaluation information with the second terminal; further comprising,
The step of matching the first terminal and the second terminal comprises:
sharing, by the server, the shooting information and the recording information in real time with the second terminal; and
The server further comprises; generating a chatting screen shared by the first terminal and the second terminal;
The step of evaluating the learning information and sharing the evaluation information to the second terminal comprises:
obtaining, by the server, at least one of pronunciation error information, erroneous word information, and an oral action map based on the learning information, and matching the pronunciation error information and a verbal action map corresponding to the erroneous word information, respectively;
obtaining, by the server, pronunciation information corresponding to at least one of the pronunciation error information and the error word information;
obtaining, by the server, an example oral motion image corresponding to the pronunciation information, and matching the pronunciation information with the example oral motion image;
obtaining, by the server, a verbal motion score by determining the similarity between the example oral motion image and the oral motion map according to a preset criterion;
obtaining, by the server, a re-learning necessary score based on a preset weight corresponding to each of the pronunciation error information and the error word information, through an artificial intelligence model; and
The server further comprises; generating evaluation information based on the oral motion score and the re-learning required score;
Acquiring at least one of pronunciation error information, erroneous word information, and oral action map based on the learning information comprises:
obtaining, by the server, a pronunciation symbol association value based on the pronunciation error information and the error word information through an artificial intelligence model;
obtaining, by the server, a plurality of words including phonetic symbol information corresponding to the phonetic symbol correlation value when the phonetic symbol correlation value is equal to or greater than a preset value; and
Further comprising; obtaining, by the server, third image information including the plurality of words, and sharing it with the first terminal as a first review image;
The step of generating the achievement information,
comparing, by the server, the first evaluation information and the second evaluation information with the third evaluation information; and
Obtaining, by the server, achievement information including an achievement rate graph generated based on a comparison result of the first to third evaluation information;
The first evaluation information is the first evaluation information,
The second evaluation information is evaluation information that occurred just before,
The third evaluation information is evaluation information generated in the rearmost row, and is generated based on the review image. delete delete delete According to claim 1,
The step of generating learning information including the shooting information and the recording information,
obtaining, by the server, photographing information corresponding to a section in which the recording information is blank, when a section in which the recording information is blank is obtained over a preset time;
obtaining, by the server, whether it is possible to obtain a student object corresponding to the first terminal from the photographing information corresponding to the blank section;
acquiring, by the server, at least one non-learning event of a first non-learning event and a second non-learning event based on whether the object is acquired;
increasing, by the server, a volume value corresponding to the selected image information to a preset volume when the first non-learning event is acquired;
when the second non-learning event is obtained, the server sharing a second non-learning event occurrence time point with the second terminal;
calculating, by the server, a total learning time based on the access time and the end time, excluding a time corresponding to the blank section from the total learning time; and
Further comprising; calculating, by the server, a recommended learning time based on the total learning time and transmitting it to the first terminal;
The step of acquiring the second non-learning event includes:
obtaining, by the server, a background image from the first terminal;
obtaining, by the server, a plurality of symbols included in the background image; and
and obtaining, by the server, a second non-learning event when more than a preset number of symbols are detected among the plurality of symbols. According to claim 1,
Acquiring at least one of pronunciation error information, erroneous word information, and oral action map based on the learning information comprises:
obtaining, by the server, a first sound pattern that is a sound pattern for each sentence based on the selected image information;
obtaining, by the server, a second sound pattern corresponding to the first sound pattern from the recording information;
matching, by the server, a first sound pattern and a second sound pattern determined to be similar to or greater than a preset standard, and obtaining, as error information, a second sound pattern in which other sound patterns do not match;
matching, by the server, a first sound pattern having the same generation time point to a second sound pattern obtained as the error information based on the generation time point of the second sound pattern obtained as the error information;
defining, by the server, error information similar to a sound more than a preset standard among the first sound pattern and the second sound pattern matched in the error information as pronunciation error information; and
Further comprising; defining, by the server, similar error information as erroneous word information whose sound quality is less than a preset standard;
The pronunciation information, the control method characterized in that it includes the first sound pattern. 7. The method of claim 6,
The step of matching the first sound pattern and the second sound pattern having the same generation time point to each other comprises:
Comparing the first sound pattern and the second sound pattern matched in the error information, when the second sound pattern has a goodness of a sound in which a section in which a difference occurs with respect to the first sound pattern is repeated at least once, calculating, by the server, an average mapsy of at least two repeated mapsy;
obtaining, by the server, a third sound pattern by replacing a plurality of repeated mapsi located in the section where the difference occurs with one of the average mapsi;
comparing, by the server, the third sound pattern with the corresponding first sound pattern;
when the first sound pattern and the third sound pattern are similar to or more than a preset standard, obtaining, by the server, information on a section in which the second sound pattern corresponding to the third sound pattern is traced; and
The server further includes; sharing, by the server, image information corresponding to the stuttered section information to the first terminal as a second review image,
The control method is
When the server shares at least one of the first to second review images with the first terminal, the server generates a oral motion map and an example oral motion image corresponding to the first and second review images to the second terminal. 1 outputting to the terminal; and
The method further comprising: obtaining, by the server, a real-time oral motion map from the first terminal, and simultaneously outputting the real-time oral motion map to the first terminal. 6. The method of claim 5,
The step of obtaining a plurality of symbols included on the background image,
generating, by the server, reference coordinates on the background image;
obtaining, by the server, a plurality of first symbols included on the background image; and
The method further includes, by the server, obtaining, by the server, a plurality of second symbols having a density of less than or equal to a predetermined interval in the reference coordinates among the first symbols,
If more than the preset number of symbols are detected, acquiring a second non-learning event comprises:
obtaining, by the server, the number of detected second symbols;
determining, by the server, whether to acquire the oral motion map, when the acquired number is equal to or greater than a preset criterion;
obtaining, by the server, an oral motion score corresponding to the oral motion map when the oral motion map is obtained;
obtaining, by the server, an average oral motion score corresponding to the first evaluation information and the second evaluation information; and
When the server determines that the oral operation score is lower than the average oral operation score by more than a preset range, acquiring a first non-learning event; further comprising,
The step of determining whether to obtain the oral motion map is,
determining, by the server, whether to obtain the student object, when the oral motion map is not obtained;
obtaining, by the server, a first non-learning event when the student object is obtained; and
If the student object is not obtained, the server acquiring a second non-learning event; further comprising,
The reference coordinate is a central coordinate on the background image or a central coordinate for a region in which the oral motion score is calculated the highest among regions in which the oral motion map is obtained.

Images