WO2022149661A1

WO2022149661A1 - Method and apparatus for providing language-learning content using avatar generated from portrait

Info

Publication number: WO2022149661A1
Application number: PCT/KR2021/005121
Authority: WO
Inventors: 송진주
Original assignee: 주식회사 헤이스타즈
Priority date: 2021-01-06
Filing date: 2021-04-22
Publication date: 2022-07-14
Also published as: KR20220099344A

Abstract

The method for providing language-learning content, according to one embodiment of the present invention, can provide both display entities corresponding to user input messages and response messages therefor, and an image window displaying an image of the response message being read audibly.

Description

Method and apparatus for providing language content using avatars created from portraits

The present invention relates to a method and apparatus for providing language content providing a display object corresponding to each of a user input message and a response message thereto, and an image window in which a single sound image of the response message is displayed together.

In general, foreign language education has been achieved by selecting content suitable for one from among pre-generated language content.

For example, the user accesses the language education system and selects and makes a reservation for the language content deemed suitable for him in consideration of the name of the language content, lecture level, instructor, etc. I had to go through a consultation visit.

However, such an existing method has a problem in that the interests of individual users or the level of individual users are not taken into consideration because the operating entity of the language education system is based on previously generating and uploading contents by grade.

In particular, in language education, although the user's interest has a great influence on the improvement of language achievement, the prior art provides only educational content with a universal theme and uniform content so that the user loses interest in learning the language. There was a problem.

The present invention is to solve the above-mentioned problems, and by generating a monophonic image for messages using an avatar model generated based on a user's selection, arouse the user's interest in language learning and improve the continuity of learning want to do

A method for providing language content according to an embodiment of the present invention includes: obtaining a user input message; receiving a response message to the input message from a server; generating one or more display objects corresponding to each of the input message and the response message; receiving, from the server, a first image window in which an image of a monologue of the response message by an avatar model is displayed; and displaying the one or more display objects and the first image window.

According to an embodiment of the present invention, a method for providing language content includes: before acquiring the input message, acquiring at least one avatar image for generating the avatar model from the user; and transmitting the at least one avatar image to the server, and transmitting a request for generating the avatar model to the server.

The displaying may include dividing the first image window into a first area including the face of the avatar model and a second area excluding the first area; and displaying the one or more display objects on the second area.

Displaying the one or more display objects on the second area includes displaying the one or more display objects on the second area in chronological order so that the most recent display object is displayed at a predetermined position. can do.

The displaying may further include displaying the one or more display objects in chronological order on the first image window.

The displaying may include: identifying a display object selected by a user from among one or more display objects displayed on the first image window; checking a selection message corresponding to the identified display object; transmitting, to the server, a request for generating a second image window in which identification information of the selection message and a reading image of the selection message by the avatar model are displayed; receiving the second image window from the server; and displaying the second image window in place of the first image window.

The method for providing language content includes: obtaining a response message from the user to a query received from the server; transmitting the response message to the server, and receiving an effect selection menu corresponding to the score of the response message from the server; transmitting a user's selection input for the menu to the server; receiving a third image window to which an effect according to the selection input is applied from the server; and displaying the third image window.

In this case, the effect may include an effect of adding a first image including the user's face to the first image window.

Also, the effect may include an effect of applying the item selected by the user to the avatar on the first image window.

A language content providing apparatus according to an embodiment of the present invention includes a control unit, wherein the control unit obtains a user input message, receives a response message to the input message from a server, and each of the input message and the response message generates one or more display objects corresponding to , and receives a first image window in which a reading image of the response message by an avatar model is displayed from the server, and displays the one or more display objects and the first image window. can be displayed

The controller may obtain at least one avatar image for generating the avatar model from the user, transmit the at least one avatar image to the server, and transmit a request for generating the avatar model to the server.

The control unit may divide the first image window into a first area, which is an area including the face of the avatar model, and a second area, excluding the first area, and display the one or more display objects in the second area. have.

The control unit may display the one or more display objects on the second area in chronological order, and display the most recent display object at a predetermined position.

The controller may display the one or more display objects on the first image window in chronological order.

The control unit identifies a display object selected by a user from among one or more display objects displayed on the first image window, checks a selection message corresponding to the identified display object, and provides identification information of the selection message to the server and Transmitting a request for generating a second image window in which an image of the selected message by the avatar model is displayed, receiving the second image window from the server, and replacing the first image window with the second image window A video window can be displayed.

The control unit obtains the user's response message to the query received from the server, transmits the response message to the server, receives an effect selection menu corresponding to the score of the response message from the server, and the menu may transmit a user's selection input to the server, receive a third image window to which an effect according to the selection input is applied from the server, and display the third image window.

In this case, the effect may include an effect of adding a first image including the user's face to the first image window. Also, the effect may include an effect of applying the item selected by the user to the avatar on the first image window.

According to the present invention, it is possible to arouse a user's interest in language learning and to improve the continuity of learning by generating a monologue image for messages using an avatar model generated based on a user's selection.

In addition, according to the present invention, not only a single sound for a message but also a mouth shape is provided through an avatar model so that a user can easily pronounce a foreign language.

In addition, according to the present invention, the user's learning effect can be improved by differentially providing the number of effects that the user can apply to the avatar model according to the user's response score.

1 is a diagram schematically illustrating the configuration of a language content providing system according to an embodiment of the present invention.

2 is a diagram schematically illustrating a configuration of a user terminal 100 according to an embodiment of the present invention.

3 is a flowchart illustrating a process in which the user terminal 100 provides one or more display objects and a first image window according to an embodiment of the present invention.

4 is a flowchart illustrating a process in which the user terminal 100 provides a second image window according to an embodiment of the present invention.

5 is a flowchart illustrating a process in which the user terminal 100 provides a third image window according to an embodiment of the present invention.

6 is an example of a screen 600 on which an interface 610 for selecting an avatar model is displayed on the user terminal 100 according to an embodiment of the present invention.

FIG. 7 is a diagram for explaining a process of generating the display object 730 and the first image window 740 from the response message 710 .

8 is an example of a screen 800 on which one or more display objects and a first image window are displayed on the user terminal 100 according to an embodiment of the present invention.

[Explanation of code]

100: user terminal

110: communication department

120: control unit

130: memory

140: display unit

200: content providing server

300: chatbot server

Since the present invention can apply various transformations and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. Effects and features of the present invention, and a method for achieving them, will become apparent with reference to the embodiments described below in detail in conjunction with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and when described with reference to the drawings, the same or corresponding components are given the same reference numerals, and the overlapping description thereof will be omitted. .

In the following embodiments, terms such as first, second, etc. are used for the purpose of distinguishing one component from another, not in a limiting sense. In the following examples, the singular expression includes the plural expression unless the context clearly dictates otherwise. In the following embodiments, terms such as include or have means that the features or components described in the specification are present, and the possibility that one or more other features or components may be added is not excluded in advance. In the drawings, the size of the components may be exaggerated or reduced for convenience of description. For example, since the size and shape of each component shown in the drawings are arbitrarily indicated for convenience of description, the present invention is not necessarily limited to the illustrated bar.

The system for providing language content according to an embodiment of the present invention provides a response message to a user's input message, but also provides a monologue image by the avatar model selected by the user to arouse interest in language learning and achieve user achievement can improve

In addition, the present invention can provide a more realistic language content by allowing the avatar to make a mouth shape, facial expression, and action corresponding to a response message in providing a monologue video using the avatar model.

As shown in FIG. 1 , the language content providing system according to an embodiment of the present invention may include a user terminal 100 , a content providing server 200 , and a chatbot server 300 . However, such a system configuration is exemplary, and the spirit of the present invention is not limited thereto.

In an optional embodiment of the present invention, the content providing server 200 and the chatbot server 300 may be implemented integrally. In this case, the content providing server 200 may be implemented to drive a chatbot model or a chatbot agent.

In another optional embodiment of the present invention, there may be a plurality of user terminals 100 .

The content providing server 200 according to an embodiment of the present invention may provide a response message to a user's input message, and may also provide a monologue image based on an avatar model selected by the user.

Although not shown in the drawings, such a content providing server 200 may include a communication unit (not shown), a control unit (not shown), and a memory (not shown).

The communication unit (not shown) is a device including hardware and software necessary for the content providing server 200 to transmit and receive signals such as control signals or data signals through wired/wireless connection with other network devices such as the user terminal 100 to be described later. can be

The controller (not shown) may include all kinds of devices capable of processing data, such as a processor. Here, the 'processor' may refer to a data processing device embedded in hardware having a physically structured circuit to perform a function expressed by, for example, a code or a command included in a program. As an example of the data processing device embedded in the hardware as described above, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an ASIC (Application-Specific Integrated) Circuit) and a processing device such as an FPGA (Field Programmable Gate Array) may be included, but the scope of the present invention is not limited thereto.

The memory (not shown) performs a function of temporarily or permanently storing data processed by the content providing server 200 . The memory may include a magnetic storage medium or a flash storage medium, but the scope of the present invention is not limited thereto. For example, the memory (memory) may temporarily and/or permanently store an input message received from the user terminal 100 .

A detailed description of the operation of the content providing server 200 will be described later with reference to FIGS. 3 to 5 .

The chatbot server 300 according to an embodiment of the present invention may generate a response message to the received message according to the request of the above-described content providing server 200 . For example, the chatbot server 300 may include an artificial neural network learned for each scenario, and may generate a response message to a message received from the content providing server 200 using the artificial neural network. In this case, the generated response message may be provided to the content providing server 200 and finally delivered to the user terminal 100 . A detailed description thereof will be given later.

Although not shown in the drawings, this chatbot server may also include a communication unit (not shown), a control unit (not shown), and a memory (not shown). A detailed description of each configuration is replaced with a description of each configuration of the content providing server 200 .

The user terminal 100 according to an embodiment of the present invention may receive a response message and/or an image window from the content providing server 200 and provide it to the user. Also, the user terminal 100 may obtain the user's input and provide it to the content providing server 200 .

Referring to FIG. 2 , the user terminal 100 according to an embodiment of the present invention may include a communication unit 110 , a control unit 120 , a memory 130 , and a display unit 140 . Also, although not shown in the drawings, the user terminal 100 according to an embodiment of the present invention may further include an input/output unit, a program storage unit, and the like.

The communication unit 110 is a device including hardware and software necessary for the user terminal 100 to transmit and receive signals such as control signals or data signals through wired/wireless connection with other network devices such as the aforementioned content providing server 200 . can

The controller 120 may include all kinds of devices capable of processing data, such as a processor. Here, the 'processor' may refer to a data processing device embedded in hardware having a physically structured circuit to perform a function expressed by, for example, a code or a command included in a program. As an example of the data processing device embedded in the hardware as described above, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an ASIC (Application-Specific Integrated) Circuit) and a processing device such as an FPGA (Field Programmable Gate Array) may be included, but the scope of the present invention is not limited thereto.

The memory 130 performs a function of temporarily or permanently storing data processed by the user terminal 100 . The memory may include a magnetic storage medium or a flash storage medium, but the scope of the present invention is not limited thereto. For example, the memory 130 may temporarily and/or permanently store image windows received from the content providing server 200 .

The display unit 140 may perform a function of displaying a display object and image windows corresponding to the message to the user. For example, the display unit 140 may display one or more display objects corresponding to the input message and the response message, respectively, and an image window including an avatar model.

Such a user terminal 100 may mean an electronic device implemented in various forms. For example, the user terminal 100 may refer to the portable terminals 101 to 103 or the fixed terminal (or the computer 104 ).

Hereinafter, a method for providing language content according to an embodiment of the present invention will be described with a focus on the operation of the user terminal 100 .

The user terminal 100 according to an embodiment of the present invention may obtain or receive at least one item for generating an avatar model from the user.

For example, the user terminal 100 may acquire at least one image for generating an avatar model. The image obtained at this time may be, for example, an image of a celebrity. The user may obtain an image by using the image acquisition unit provided in the user terminal 100 and use it as at least one image for generating an avatar model, or download an image on a web page to generate an avatar model by downloading an image. can also be used as However, such a method is exemplary and the spirit of the present invention is not limited thereto.

Also, the user terminal 100 may obtain user selection information to generate an avatar model. In this case, the user terminal 100 may receive a plurality of selectable avatar models from the content providing server 200 . In addition, the user terminal 100 may display a plurality of received avatar models on the interface 610 for generating an avatar model, such as the screen 600 shown in FIG. 6 , so that the user can select a desired avatar model. .

Also, the user terminal 100 may acquire a video for generating an avatar model.

However, the above-described methods are exemplary and the spirit of the present invention is not limited thereto.

The user terminal 100 according to an embodiment of the present invention may transmit avatar information for generating an avatar to the content providing server 200 (S511). At this time, the user terminal 100 transmits the avatar model creation request with the avatar information. It may be transmitted together with the content providing server 200 . In this case, the 'avatar information' transmitted to the content providing server 200 may include at least one image for generating an avatar model, at least one video for generating an avatar model, and/or avatar model selection information.

The content providing server 200 according to an embodiment of the present invention may generate an avatar model with reference to the avatar information received from the user terminal 100 (S512).

In the present invention, an 'avatar model' is a three-dimensional (or two-dimensional) model of a specific person, and may refer to a model configured to perform (or act) an expression, an action, a mouth shape, etc. according to a provided message.

In the present invention, such an avatar model may be generated by the content providing server 200 based on the avatar information provided by the user. The user can create an avatar depicting a person he or she wants by including an image of a celebrity he or she prefers, or an image of his or her family, his or her lover, etc. in the avatar information.

Of course, the already created avatar model is stored in the content providing server 200 , and the user may create (or select) an avatar depicting a desired person by selecting the already created avatar model.

The content providing server 200 according to an embodiment of the present invention may generate an avatar model from avatar information by using various well-known technologies.

For example, the content providing server 200 may generate an avatar model by extracting landmark information from the image of a celebrity received from the user terminal 100 and modifying the appearance of the sample model by referring to the extracted landmark information. have. However, such a method is exemplary and the spirit of the present invention is not limited thereto.

The user terminal 100 according to an embodiment of the present invention may obtain a user input message (S521) and transmit it to the content providing server 200 (S522).

For example, the user terminal 100 may obtain an input message in the form of a text according to the user's manipulation of the keypad, and transmit it to the content providing server 200 .

In an optional embodiment of the present invention, the user terminal 100 may obtain the user's voice, generate text from the voice, and transmit the text and the voice to the content providing server 200 .

The content providing server 200 according to an embodiment of the present invention transmits the input message received from the user terminal 100 to the chatbot server 300 (S523), and receives the response message generated by the chatbot server 300 (S525), it can be provided to the user terminal 100 again. (S526) In this case, the chatbot server 300 may generate a response message to the input message received from the content providing server 200. (S524) )

In other words, the user terminal 100 according to an embodiment of the present invention may receive a response message to the input message from the content providing server 200 (S526).

The content providing server 200 according to an embodiment of the present invention may generate a first image window using the response message received from the chatbot server 300 in step S525 (S531).

In the present invention, the 'image window' such as the first image window, the second image window, and the third image window may mean a window (or window) in which a predetermined operation process and/or operation sound of the avatar model is displayed.

For example, the first image window may mean a window in which a single sound image of the response message of the avatar model is displayed. Similarly, the second image window may mean a window in which a single sound image of the avatar model for the message selected by the user is displayed. Also, the third image window may refer to a window in which an image of an avatar model to which a predetermined effect is applied is displayed.

The content providing server 200 according to an embodiment of the present invention displays a response message by the avatar model 720 (in this case, the response message is received from the chatbot server 300 in step S525, 710). A first image window 740 may be generated.

In parallel with the above-described step S531, the user terminal 100 according to an embodiment of the present invention has one or more display objects corresponding to each of the input message (obtained in step S521) and the response message (received in step S526). (S541) For example, the user terminal 100 may generate a display object 730 in the form of a speech bubble from the response message 710 as shown in FIG. 7 . In this case, the text inside the display object 730 may be generated based on the response message 710 .

However, the shape of the display object 730 shown in FIG. 7 is illustrative and the spirit of the present invention is not limited thereto, and the user terminal 100 may generate a display object for each of a plurality of messages.

The user terminal 100 according to an embodiment of the present invention may receive the first image window from the content providing server 200 (S532).

Also, the user terminal 100 according to an embodiment of the present invention may display the one or more display objects generated in step S541 and the first image window received in step S532 together (S551).

The user terminal 100 according to an embodiment of the present invention may display one or more display objects 802 on the first image window 801 as shown in FIG. 8 .

In this case, the user terminal 100 according to an embodiment of the present invention sets the first image window 801 to a first area 810 that is an area including the face of the avatar model, and a second area excluding the first area 810 . (820).

Also, the user terminal 100 may display one or more display objects 802 only in the second area 820 .

The user terminal 100 according to an embodiment of the present invention displays one or more display objects 802 in the second area 820 in chronological order, and the most recent display object is located at a predetermined position (eg, the lowermost ) can be displayed. Of course, the user terminal 100 may move the position of the existing display object according to the addition of the latest display object, and according to the addition of the new display object, it leaves the second area 820 and enters the first area 810. Objects can be made invisible.

As described above, the present invention provides the first image window and a display object corresponding to each message, but prevents the display object from being displayed in the region where the mouth of the avatar model is displayed in the image window, thereby improving the learning efficiency of the user. have.

In addition, the present invention provides learning content in the form of chatting that the user is familiar with, but provides an image related to a message in the background, in particular, an image in which an avatar model pronounces a message, so that the user can engage in learning without a psychological burden.

4 is a flowchart illustrating a process in which the user terminal 100 provides a second image window according to an embodiment of the present invention. Hereinafter, it will be described with reference to FIG. 8 .

The user terminal 100 according to an embodiment of the present invention may display one or more display objects and a first image window. (S551) Since step S551 has been described in detail with reference to FIG. 3, a detailed description thereof will be omitted. do.

The user terminal 100 according to an embodiment of the present invention may obtain a user's selection input for selecting any one of the one or more display objects 802 displayed on the first image window 801 ( S561)

For example, the user may select a second display object 821 among one or more display objects 802 . In this case, the user may select the second object 821 itself, or may select the second object 821 by selecting a separate object 822 related to the object.

The user terminal 100 according to an embodiment of the present invention may check a selection message corresponding to the identified display object (or the selected display object). (S562) For example, in FIG. is selected, the user terminal 100 may confirm "Korean teacher, this is Ham Eun-jung" as a selection message.

The user terminal 100 according to an embodiment of the present invention may transmit the checked selection message or identification information of the message to the content providing server 200 (S563). The content providing server 0200 uses the selection message to A second image window may be generated ( S564 ). In this case, the second image window may be a window in which a single sound image of a selection message by the avatar model is displayed.

The user terminal 100 according to an embodiment of the present invention may receive the second image window from the content providing server 200 (S565), and display it together with one or more display objects 802 (S566).

Accordingly, the present invention enables effective repetitive learning of the message selected by the user. That is, according to the present invention, not only messages according to the current conversation, but also video windows for past messages can be repeatedly provided in the same interface, so that effective repetitive learning is achieved.

The content providing server 200 according to an embodiment of the present invention may determine the question and answer content (S571). For example, the content providing server 200 refers to the question and answer field selection information received from the user terminal 100. , the question and answer content may be determined. In this case, the content providing server 200 may pre-store a plurality of question and answer content for each field.

The content providing server 200 according to an embodiment of the present invention may transmit a query included in the question answering content to the chatbot server 300 (S572) and receive a corresponding query message (S574). In other words, The content providing server 200 may use the chatbot server 300 to generate a modified query message in a form suitable for providing a query to a user. In this case, the chatbot server 300 may generate a query message using the query received from the content providing server 200 (S573).

The content providing server 200 according to an embodiment of the present invention may transmit a query message to the user terminal 100 . In other words, the user terminal 100 according to an embodiment of the present invention may receive a query message from the content providing server 200 (S575).

The user terminal 100 may obtain a response message including the user's response to the query message (S581), and transmit the response message to the content providing server 200 (S582).

The content providing server 200 according to an embodiment of the present invention may calculate a score by comparing the response included in the question and answer content determined in step S571 with the response according to the response message received in step S582 (S583). For example, the content providing server 200 may calculate a score based on a similarity between a response included in the question and answer content and a received response.

In an optional embodiment, the response message received from the user terminal 100 includes the user's voice, and the content providing server 200 calculates a score based on the similarity between the response voice included in the question and answer content and the user's voice. You may. More specifically, the content providing server 200 according to an embodiment of the present invention converts the voice received from the user terminal 100 into text, and based on the similarity between the generated text and the response text included in the question and answer content. so that the score can be calculated. However, this is an example, and the spirit of the present invention is not limited thereto.

The content providing server 200 according to an embodiment of the present invention may check the type of effect that the user can select according to the calculated score, and provide an effect selection menu including the checked effect to the user terminal 100 . (S584) For example, the content providing server 200 may provide an effect selection menu to the user terminal 100 by increasing the number of types of selectable effects as the score increases.

The user terminal 100 according to an embodiment of the present invention may receive an effect selection menu corresponding to the score of the response message from the content providing server 200 (S584). In addition, the user terminal 100 may receive the received menu It is possible to transmit the user's selection input to the content providing server 200 (S585).

Accordingly, the content providing server 200 according to an embodiment of the present invention may generate a third image window to which the selected effect is applied to the first image window (S591).

In this case, the effect may be an effect of adding the first image including the user's face to the first image window. To this end, the user terminal 100 may transmit the first image including the user's face together with the effect selection information to the content providing server 200 in step S585. In an example in which the avatar model is generated based on an image of a celebrity, the third video window may include a video (especially, a video having a conversation) captured by the celebrity and the user.

Meanwhile, the effect may be an effect of applying the item selected by the user to the avatar on the first image window. For example, the effect may be an effect of applying the clothes selected by the user or the accessories selected by the user to the avatar on the first image window.

However, the two effects described above are exemplary and the spirit of the present invention is not limited thereto.

The user terminal 100 according to an embodiment of the present invention may receive the third image window generated in step S591 (S592) and display it together with one or more display objects (S593).

As described above, according to the present invention, the user's learning effect can be improved by differentially providing the number of effects that the user can apply to the avatar model according to the user's response score.

The embodiment according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded in a computer-readable medium. In this case, the medium may be to store a program executable by a computer. Examples of the medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as CD-ROM and DVD, a magneto-optical medium such as a floppy disk, and those configured to store program instructions, including ROM, RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and used by those skilled in the computer software field. Examples of the computer program may include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

The specific implementations described in the present invention are only examples, and do not limit the scope of the present invention in any way. For brevity of the specification, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connections or connecting members of the lines between the components shown in the drawings exemplarily represent functional connections and/or physical or circuit connections, and in an actual device, various functional connections, physical connections that are replaceable or additional may be referred to as connections, or circuit connections. In addition, unless there is a specific reference such as "essential", "importantly", etc., it may not be a necessary component for the application of the present invention.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the spirit of the present invention is not limited to the scope of the scope of the present invention. will be said to belong to

Claims

In the method of providing language content,

obtaining a user's input message;

receiving a response message to the input message from a server;

generating one or more display objects corresponding to each of the input message and the response message;

receiving, from the server, a first image window in which an image of a monologue of the response message by an avatar model is displayed; and

Displaying the one or more display objects and the first image window; Containing, language content providing method.
The method according to claim 1

The step of displaying

dividing the first image window into a first area including the face of the avatar model and a second area excluding the first area; and

Displaying the one or more display objects in the second area; Containing, language content providing method.
The method according to claim 1

The step of displaying

Displaying the one or more display objects in chronological order on the first image window; further comprising, a method for providing language content.
4. The method of claim 3

The step of displaying

identifying a display object selected by a user from among one or more display objects displayed on the first image window;

checking a selection message corresponding to the identified display object;

transmitting, to the server, a request for generating a second image window in which identification information of the selection message and a reading image of the selection message by the avatar model are displayed;

receiving the second image window from the server; and

Displaying the second image window in place of the first image window; Containing, language content providing method.
The method according to claim 1

How to provide the language content

obtaining a response message from the user to the query received from the server;

transmitting the response message to the server, and receiving an effect selection menu corresponding to the score of the response message from the server;

transmitting a user's selection input for the menu to the server;

receiving a third image window to which an effect according to the selection input is applied from the server; and

Displaying the third image window; Containing, language content providing method.