KR20230126971A - Method for providing multi-translation and server for providing multi-translation - Google Patents

Abstract

A method for providing multiple translations and a server for providing multiple translations are disclosed. According to an embodiment of the present invention, a multi-translation providing method performed by a multi-translation providing server includes a determination step of determining languages used by a plurality of users participating in a chat room, and receiving a message from one or more users among the plurality of users. A receiving step, a translation step of translating the contents of the received message into the language used by the plurality of users using an external translation server, and providing each of the translated messages to each of the plurality of users, It includes a provision step of providing individually according to.

Description

Multiple translation providing method and multiple translation providing server

The present invention relates to a method for providing multiple translations and a server for providing multiple translations. More specifically, the present invention relates to a multi-translation providing method and a multi-translation providing server that translates a message in a chat room into a language used by each user participating in the chat room and provides the translated message to each user individually according to the language used.

Instant messaging services are essential services in modern life and business. A plurality of users say hello to each other through messages in each chat room, or conduct discussions or meetings. However, since conventional instant messaging apps transmit the text entered by the user as it is, in a chat room in which multinational users participate, it is inconvenient to input translations one by one.

Korean Patent Registration No. 10-1271285 is a conventional technology. When a user selects a message to be translated in a chat room and requests translation of the selected message, the translation is performed. However, in the conventional technology, since the process of selecting and requesting a message to be translated by the user is necessarily performed, there is inconvenience in use.

KR 10-1271285 B1 (2013.06.04.)

The present invention has been made to solve the above-mentioned problems, and provides a multiple translation providing method and a multiple translation providing server that automatically detects the language used by users participating in a chat room and automatically translates a message input by the user into the detected language. want to provide

In addition, it is intended to provide a multi-translation providing method and a multi-translation providing server capable of providing usability as if users are conversing in the same language by individually providing messages translated into different languages according to the user's language.

In addition, a multi-translation providing method capable of providing the usability of communicating in different languages but making calls in the same language by translating voices in multi-voice calls or multi-video calls and outputting individually translated contents as voices to each user, and We want to provide a multi-translation providing server.

Solving problems of the present invention are not limited to the above-mentioned contents, and other technical problems not mentioned above will be clearly understood by those skilled in the art from the following description.

According to an embodiment of the present invention, a multi-translation providing method performed by a multi-translation providing server includes a determination step of determining languages used by a plurality of users participating in a chat room; a receiving step of receiving a message from one or more users among the plurality of users; a translation step of translating the contents of the received message into languages used by the plurality of users by using an external translation server; and a providing step of providing each of the translated messages to each of the plurality of users, individually according to the language used.

In addition, the message is a voice, and the conversion step of recognizing the voice of the received message and converting it into text using an external voice recognition server; further comprising the translation step, using the external translation server , the converted text may be translated into the languages used by the plurality of users.

In addition, the message may be generated from the audio of the video of one or more users among the plurality of users.

In addition, the external voice recognition server learns the language style of each user based on the voice of the received message, and generates a voice recognition model for each user that converts the voice into standard text in each language. And, each user's voice can be converted into text using the voice recognition model corresponding to each user.

Also, in the providing step, the content of each translated message may be provided as voice, and may be individually provided to each of the plurality of users according to the language used.

The method further includes a distinguishing step of distinguishing an active user whose last access to the chat room is within a pre-specified time from among the plurality of users, wherein the providing step preferentially identifies the active user among the plurality of users. Each translated message can be provided individually.

In addition, in the providing step, each of the translated messages may be individually provided in the order of the most recent access time among the active users.

In the determining step, the language used by each user may be determined using information on the language used by the terminal of each of the plurality of users.

In addition, in the providing step, the original text of the message before translation is also provided to the plurality of users, the translated message is exposed to the chat room with priority, and when the user's swipe gesture input is received, the translated message is provided. It can be removed from the chat room and the text of the message can be exposed to the chat room.

Also, a computer-readable recording medium storing a program for implementing the above-described multiple translation providing method may be provided.

On the other hand, a multi-translation providing server according to an embodiment of the present invention includes a determination unit for determining languages used by a plurality of users participating in a chat room; a receiving unit receiving a message from one or more users among the plurality of users; a translation unit for translating the contents of the received message into languages used by the plurality of users, respectively, using an external translation server; and a providing unit that provides each of the translated messages to each of the plurality of users, individually according to the language used.

In addition, the message is a voice, and a conversion unit for recognizing the voice of the received message and converting it into text using an external voice recognition server; further comprising the translation unit, using the external translation server, The converted text may be translated into languages used by the plurality of users.

In addition, the message may be generated from the audio of the video of one or more users among the plurality of users.

In addition, the external voice recognition server learns the language style of each user based on the voice of the received message, and generates a voice recognition model for each user that converts the voice into standard text in each language. And, each user's voice can be converted into text using the voice recognition model corresponding to each user.

Also, the provision unit may provide the contents of each of the translated messages in voice, and individually provide the contents of each of the translated messages to each of the plurality of users according to the language used.

In addition, a distinguishing unit for distinguishing an active user whose last access to the chat room is within a pre-specified time from among the plurality of users, wherein the providing unit preferentially performs the translation to the active user among the plurality of users. Each message can be provided individually.

Also, the provision unit may individually provide each of the translated messages in the order of the most recent of the active users at the time of the last access.

In addition, the determination unit may determine the language used by each of the plurality of users by using information on the language used by the terminal of each of the plurality of users.

In addition, the providing unit further includes the original text of the message before translation and provides it to the plurality of users, preferentially exposing the translated message to the chat room, and when the user's swipe gesture input is received, the translated message It can be removed from the chat room and the text of the message can be exposed to the chat room.

The method for providing multiple translations and the server for providing multiple translations according to an embodiment of the present invention can automatically detect the language used by users participating in a chat room and automatically translate a message input by the user into the detected language. .

In addition, messages translated into different languages are individually provided according to the user's language, so that users can provide usability as if they are talking to each other in the same language.

In addition, by translating voices in multi-voice calls or multi-video calls and outputting the individually translated contents as voices to each user, it is possible to provide usability of talking in different languages but making calls in the same language.

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

1 is a conceptual diagram for explaining the concept of a multi-translation providing method performed by a multi-translation providing server according to an embodiment of the present invention.
2 is a diagram illustrating a network environment of a multi-translation providing server according to an embodiment of the present invention.
3 is a block diagram showing the configuration of a multi-translation providing server according to an embodiment of the present invention.
4 is a flowchart of a multi-translation providing method performed by a multi-translation providing server according to an embodiment of the present invention.
5 is a flowchart of a multi-translation providing method further including a conversion step according to an embodiment of the present invention.
FIG. 6 is a diagram illustrating a state in which audio of a video streamed in a chat room is recognized, translated, and provided to a user.
7 is a flowchart of a method for providing multiple translations further including a distinguishing step according to an embodiment of the present invention.
FIG. 8 is a diagram showing how a translated message and an original message according to a swipe gesture input are exposed in a chat room according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail so that those skilled in the art can easily practice with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the embodiment of the present invention in the drawings, parts irrelevant to the description are omitted.

Terms used in this specification are only used to describe specific embodiments and are not intended to limit the present invention. Singular expressions may include plural expressions unless the context clearly dictates otherwise.

In this specification, terms such as "include", "have" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, and one Or it may be understood that it does not exclude in advance the possibility of the existence or addition of other features, numbers, steps, operations, components, parts, or combinations thereof.

In addition, the components appearing in the embodiments of the present invention are shown independently to represent different characteristic functions, and it does not mean that each component is made of separate hardware or a single software component unit. That is, each component is listed and described as each component for convenience of description, and at least two components of each component may be combined to form one component, or one component may be divided into a plurality of components to perform a function. An integrated embodiment and a separate embodiment of each of these components are also included in the scope of the present invention unless departing from the essence of the present invention.

In addition, the following embodiments are provided to more clearly explain to those with average knowledge in the art, and the shapes and sizes of elements in the drawings may be exaggerated for clearer explanation.

Hereinafter, preferred embodiments according to the present invention will be described with reference to the accompanying drawings.

1 is a conceptual diagram for explaining the concept of a multi-translation providing method performed by a multi-translation providing server according to an embodiment of the present invention.

Referring to FIG. 1, a method for providing multiple translation according to an embodiment of the present invention translates messages of a plurality of users 120 participating in a chat room 110 into languages used by each user 120, respectively. This is to provide a message to each user 120 individually. In one embodiment, when user A 121 inputs a message 131 in Korean in the chat room 110, a message 131 in Korean appears on the screen 101 of the chat room 110 viewed by user A 121. messages 132, 133, and 134 translated into the language used by each user may be displayed on the screens 102, 103, and 104 of the chat room 110 viewed by other users 122, 123, and 124. . For example, for user B 122 whose language is English, a message 131 input in Korean is output as a translated message 132 in English, and for user C 123 whose language is Japanese, a message 131 input in Korean is translated into Japanese. (133) can be. Also, for the user D 124 whose language is Arabic, the message 134 translated into Arabic may be output.

2 is a diagram illustrating a network environment of a multi-translation providing server according to an embodiment of the present invention.

1 and 2, the multi-translation providing server 210 according to an embodiment of the present invention is for performing the multi-translation providing method, and creates a chat room 110 to which a plurality of users 120 access. In addition, the messages 131 input by the plurality of users 120 in the chat room 110 may be translated and provided to the users 120 individually. The multi-translation providing server 210 may be connected to the external translation server 220 and the plurality of user terminals 240 through the network 250 .

The external translation server 220 is a server that translates text in a specific language into multiple languages, and the multi-translation providing server 210 transfers the text of the message 131 input to the chat room 110 to the external translation server 220. If transmitted to, the external translation server 220 can translate the text into multiple languages. At this time, the multi-language to be translated may be a language used by a plurality of users 122, 123, and 124 other than the user 121 who inputs the message.

The plurality of user terminals 240 are terminals used by the plurality of users 120 to access the chat room 110, and include smart phones, tablet computers, desktop computers, and laptops. ) Computer, workstation, server computer, PDA (Personal Digital Assistants), portable computer, portable game machine, navigation device, digital camera, smart TV, wearable device , may be one of the vehicle's computers, but is not limited thereto. The plurality of user terminals 240 may communicate with other terminals or the multi-translation providing server 210 through the network 250 using a wireless or wired communication method.

In one embodiment, the multi-translation providing server 210 may be connected to an external voice recognition server 230 through a network 250 . The external voice recognition server 230 may be a server that receives voice for which voice recognition is requested and converts a phrase included in the received voice into text. When voice recognition is requested for an image, the external voice recognition server 230 may perform voice recognition by separating the voice included in the image. The multi-translation providing server 210 may receive the text converted by the external voice recognition server 230 and transmit it to the external translation server 220 to request translation of the text.

3 is a block diagram showing the configuration of a multi-translation providing server according to an embodiment of the present invention, and FIG. 4 is a flowchart of a multi-translation providing method performed by the multi-translation providing server according to an embodiment of the present invention.

1 to 4, a multi-translation providing server 210 according to an embodiment of the present invention includes a memory 310, a communication unit 320, and a processor 330 to provide multi-translation in a chat room 110. ) may be included. The processor 330 may include a determination unit 331 , a reception unit 332 , a translation unit 333 and a provision unit 334 . The memory 310 may store message transmission/reception and message translation related information of the chat room 110, such as information about a plurality of users participating in the chat room 110, message information of each user, and translation message information. The communication unit 320 is connected to the network 250 to perform communication between other external servers and each user's terminal. The processor 330 may perform each step of the multiple translation providing method using each component of the processor 330 . The processor 330 and each component of the processor 330 may be implemented to execute an instruction according to an operating system code and at least one program code included in the memory 310 . Here, each component of the processor 330 may represent different functions performed by the processor 330 according to a control command provided by a program code stored in the multi-translation providing server 210. .

The multi-translation providing method performed by the multi-translation providing server 210 according to an embodiment of the present invention may include a determination step (S410), a receiving step (S420), a translation step (S430), and a providing step (S440). there is.

The determination step ( S410 ) may be a step in which the determination unit 331 determines the languages used by the plurality of users 120 participating in the chat room 110 . In the determination step (S410) of an embodiment, the determination unit 331 may determine using language information of the user terminal 240 of each user 120 participating in the chat room 110. For example, if the language used by the operating system of the terminal used by user A 121 is Korean, the determination unit 331 may determine Korean as the language used by user A 121 . Also, if the language used by the operating system of the terminal used by user B 122 is English, the determination unit 331 may determine English as the language used by user B 122 . In the determination step S410, since the determination unit 331 automatically determines the language used by each user, the users 120 do not need to set or register their own language separately, so that they can use the chat room more comfortably.

The receiving step ( S420 ) may be a step in which the receiving unit 332 receives the message 131 from one or more users 120 among the plurality of users 120 .

The translation step (S430) may be a step in which the translation unit 333 uses the external translation server 220 to translate the contents of the message received in the reception step (S420) into the languages used by the plurality of users 120, respectively. there is. In the translation step (S430), the translation unit 333 may transmit the text of the received message 131 to the external translation server 220, and the external translation server 220 may receive a translation obtained by translating the text. At this time, the translation unit 333 may also transmit language information of the users 120 participating in the chat room 110, and the external translation server 220 converts the text to each user based on the transmitted language information. can be translated into languages.

In the providing step (S440), each of the messages translated by the providing unit 334 in the translation step (S430) is provided to each of the plurality of users 120, but provided individually according to the language used by each user 120. It may be a step to In the providing step (S440), the providing unit 334 may transmit the translated text received by the translation unit 333 to each user terminal 240 used by each user 120 according to the language used, and each The user terminal 240 outputs the message 132 , 133 , 134 containing the contents of the received translation on the chat room screen 102 , 103 , 104 so that the user 122 , 123 , 124 can read the translated message. In the providing step (S440), since the provision unit 334 provides each user with individually translated messages, a situation in which one message is translated into different languages and repeatedly appears in the chat room 110 is prevented to keep the message record clean. can In addition, users can use the chat room as if they are conversing using the same language.

In addition, in the providing step (S440), the providing unit 334 may provide the contents of the translated message in voice. For example, when the translation unit 334 transmits the translation received by the translation unit 333 to each user terminal 240, the providing unit 334 further includes voice information for reading the translation aloud and transmits the translation to each user terminal 240. By doing so, when the translated message 132, 133, 134 is output on the chat room screen 102, 103, 104 in each user terminal 240, the audio of the translated message 132, 133, 134 is also displayed. can be output. At this time, voice information for reading the translation aloud may also be provided individually according to the language used by each user 120 .

5 is a flowchart of a multi-translation providing method further including a conversion step according to an embodiment of the present invention, and FIG. 6 is a diagram showing how to recognize, translate, and provide a voice for a video streamed in a chat room to a user. .

3 to 6, in one embodiment of the present invention, the multi-translation providing server 210 may further include a conversion unit 335, and the multi-translation providing server 210 performs multiple translations. The method may further include a conversion step S510.

The conversion step (S510) may be a step in which the conversion unit 335 converts the received voice into text using the external voice recognition server 230 when the message received from the user 120 is voice. In the conversion step (S510), the conversion unit 335 transmits the voice received from the user 120 to the external voice recognition server 230, and the external voice recognition server 230 receives the text converted from the voice to convert the voice. can be converted to text. The text converted from voice may be translated by the translation unit 333 into the language used by each user.

In one embodiment, the receiving unit 332 may receive an image. As shown in FIG. 6, when the user 121 outputs the video 610 in the chat room 110, the conversion unit 335 converts the video 610 streamed in the chat room 110 to the external voice recognition server 230. ) can be transmitted. The external voice recognition server 230 may separate the voice 611 from the received image 610, recognize the voice 611, and convert it into text. Alternatively, the conversion unit 335 may pre-separate audio from the video streamed in the chat room 110 and transmit only the separated audio to the external voice recognition server 230 .

The audio 611 of the video 610 converted to text by the conversion unit 335 is translated into the language used by each user by the translation unit 333, and then converted into the language used by each user by the providing unit 334. ) may be provided as a text message 621. Depending on the embodiment, the text message 621 translated by the providing unit 334 may be output as a voice 622 . The user can easily understand the video 610 streamed in a foreign language by reading the text message 621 translated into the chat room 110 or listening to the translated voice 622 . For example, when multiple calls or multiple video calls are made in the chat room 110, each user's voice is translated in real time and displayed as text or output as a translated voice, so that each user can have a natural conversation without a language barrier.

In one embodiment, the external voice recognition server 230 learns the language style of each user 120 based on the voice 611 of the received message, and converts the voice 611 into text in a standard form for each language. A speech recognition model that converts to can be generated for each user. The external voice recognition server 230 may convert the voice 611 of each user 120 into text using the voice recognition model corresponding to each user 120 .

Here, the voice recognition model may be implemented in various structures such as a neural network, for example, a Gaussian Mixture Model (GMM), a Deep Neural Network (DNN), or a Bidirectional Long Short Term Memory (BLSTM). The machine learning structure in which the speech recognition model can be implemented is not limited to the above-described structure, and may be implemented in a form in which one or more structures are combined. A neural network may represent a recognition model implemented by hardware performing complex calculations using a large number of artificial nodes or a combination of hardware and software. A neural network may perform a recognition operation or a learning process through artificial nodes.

For example, the external voice recognition server 230 may learn the dialect used by each user 120 based on the voice 611 and generate a voice recognition model to which parameters of the user's dialect are applied.

In addition, the external voice recognition server 230 may learn the use of a distinctive pronunciation or slang that appears for each user 120 and reflect it to the voice recognition model.

The speech recognition model may be a modified speech recognition model by applying each parameter according to various dialect, pronunciation, stress, and slang usage data in a standardized speech recognition model, and may be generated in various ways according to the type of data to be learned. there is.

In the conversion step (S510), when the conversion unit 335 transmits user information such as user identification information and used language information and the voice to be converted 611 to the external voice recognition server 230, the external voice recognition server 230 By using a speech recognition model trained to be optimized for the user, converting it into text and returning it to the conversion unit 335, speech recognition can be performed accurately and efficiently even when standard pronunciation or stress of each language is not used. .

In addition, the external voice recognition server 230 can shorten the conversion time by directly applying the previously used voice recognition model to subsequent voice recognition based on user information of each user 120 .

7 is a flowchart of a method for providing multiple translations further including a distinguishing step according to an embodiment of the present invention.

Referring to FIGS. 1, 3 and 7, in an embodiment of the present invention, the multi-translation providing server 210 may further include a distinguishing unit 336, and the multi-translation providing method includes a discriminating step (S610). ) may further include.

The discrimination step ( S610 ) may be a step in which the discrimination unit 336 distinguishes an active user whose last access time to the chat room 110 is within a predetermined time from among the plurality of users 120 . For example, a situation where user A 121 and user B 122 last accessed the chat room 110 5 minutes ago, and user C 123 last accessed the chat room 110 10 minutes ago. In , if the predetermined time is 5 minutes, user A 121 and user B 122 may be active users. As such, the distinguishing unit 336 may distinguish an active user from among the users 120 participating in the chat room 110 based on a pre-designated time. Depending on the embodiment, the predetermined time may vary. For example, the pre-specified time may be 0 minutes, which may mean a user currently accessing the chat room 110 .

The translation unit 333 and the provision unit 334 may first provide the translated message to the user determined by the differentiation unit 336 to be an active user in the distinguishing step (S610), and then provide the translated message to users other than the active user. message can be provided. Through this, the processing load of each server can be reduced by postponing the translation process of users not participating in the conversation to a later priority, and it is possible to provide fast translation without delay to users currently participating in the conversation.

In addition, the translation unit 333 and the provision unit 334 may provide the translated message by determining processing priority among the users determined by the discrimination unit 336 to be active users in the discrimination step (S610). For example, if user A 121 of user A 121 and user B 122, who are active users, has the latest access time, the translated message may be provided with priority to user A 121. If the predetermined time is 10 minutes, among active users, there may be users who do not participate in the current conversation. Accordingly, the processing load of each server can be further reduced by prioritizing among active users and providing translation messages.

FIG. 8 is a diagram showing how a translated message and an original message according to a swipe gesture input are exposed in a chat room according to an embodiment of the present invention.

3, 4 and 8, in the providing step (S440) of the multi-translation providing method according to an embodiment of the present invention, the providing unit 334 further includes the original text of the message before translation and provides it to a plurality of users. However, the translated message is exposed to the chat room 800 with priority and when the swipe gesture input 820 of the user 810 is received, the translated message 801 is removed from the chat room 800 and the text of the message 802 can be exposed in the chat room. As shown in FIG. 8 , when the user 810 inputs a swipe gesture 820 in the translated message box 830 of the chat room 800, the translated message 801 is moved along the swipe direction. Along with the removed and translated message 801 , the original text 802 of the message before translation may appear in the chat room 800 . Since the user 800 can check the contents of the original text 802 of the message before translation as needed, he can more accurately understand the nuance and content of the message.

The multi-translation server and the multi-translation method performed by the multi-translation server of the present invention can provide usability such that users actually communicate in different languages, but in the same language. Through this, users who speak different languages can have a conversation without feeling burdened about the language, and can more accurately convey what they mean to the other party.

In addition, in a multi-voice call and a multi-video call, voices are translated according to the language used by each user and output as voices, so that it is possible to have the feeling of talking in the same language in real time.

Various embodiments described in this specification may be implemented by hardware, middleware, microcode, software, and/or combinations thereof. For example, various embodiments may include one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), ), processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions presented herein, or combinations thereof.

Such hardware and/or software and the like may be implemented within the same device or within separate devices to support the various operations and functions described herein. Additionally, components, units, modules, components, etc., described as "-units" in the present invention may be implemented together or separately as separate but interoperable logic devices. Depiction of different features for modules, units, etc. is intended to highlight different functional embodiments and does not necessarily mean that they must be realized by separate hardware components. Rather, functionality associated with one or more modules or units may be performed by separate hardware components or integrated within common or separate hardware components.

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

Although the present invention has been described with reference to the embodiments shown in the drawings, this is only exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

110: chat room
120: multiple users
210: multi-translation provision server
220: external translation server
230: external voice recognition server
310: memory
320: communication department
331: judgment unit
332: receiver
333: translation department
334: provision unit
335: conversion unit
336: distinguishing part

Claims (19)

A multi-translation providing method performed by a multi-translation providing server,
a determination step of determining languages used by a plurality of users participating in the chat room;
a receiving step of receiving a message from one or more users among the plurality of users;
a translation step of translating the contents of the received message into languages used by the plurality of users by using an external translation server; and
and a providing step of providing each of the translated messages to each of the plurality of users, individually according to the language used.
According to claim 1,
The message is voice,
A conversion step of recognizing the voice of the received message and converting it into text using an external voice recognition server; further comprising,
In the translating step, the converted text is translated into languages used by the plurality of users, respectively, using the external translation server.
According to claim 2,
The message is generated from the audio of the video of at least one user among the plurality of users.
According to claim 2,
The external voice recognition server,
Learning the language style of each user based on the voice of the received message, and generating a voice recognition model for each user that converts the voice into a text in a standard form of each language;
and converting each user's voice into text using the voice recognition model corresponding to each user.
According to claim 1,
In the providing step, the content of each of the translated messages is provided by voice, and individually provided to each of the plurality of users according to the language used.
According to claim 1,
A distinction step of distinguishing an active user whose last access to the chat room is within a pre-specified time from among the plurality of users;
In the providing step, the translated message is individually provided to the active user among the plurality of users with priority.
According to claim 6,
In the providing step, each of the translated messages is individually provided in the order of a recent access time among the active users.
According to claim 1,
In the determining step, the language used by each user is determined using information on the language used by the terminal of each of the plurality of users.
According to claim 1,
In the providing step, the original text of the message before translation is also provided to the plurality of users, the translated message is exposed to the chat room with priority, and when the user's swipe gesture input is received, the translated message is provided to the plurality of users. and removing from the chat room and exposing the original text of the message to the chat room.
A computer-readable recording medium storing a program for implementing the method according to any one of claims 1 to 9.
As a multi-translation providing server,
a determination unit for determining languages used by a plurality of users participating in the chat room;
a receiving unit receiving a message from one or more users among the plurality of users;
a translation unit for translating the contents of the received message into languages used by the plurality of users, respectively, using an external translation server; and
A multi-translation providing server comprising: a providing unit which provides each of the translated messages to each of the plurality of users and individually provides them according to the language used.
According to claim 11,
The message is voice,
A conversion unit for recognizing the voice of the received message and converting it into text using an external voice recognition server;
The translation unit, using the external translation server, translates the converted text into the languages used by the plurality of users, respectively.
According to claim 12,
The message is generated from the audio of the video of one or more users among the plurality of users.
According to claim 12,
The external voice recognition server,
Learning the language style of each user based on the voice of the received message, and generating a voice recognition model for each user that converts the voice into a text in a standard form of each language;
and converting the voice of each user into text using the voice recognition model corresponding to each user.
According to claim 11,
The multi-translation providing server, wherein the providing unit provides the contents of each of the translated messages by voice, and individually provides the contents of each of the translated messages to each of the plurality of users according to the language used.
According to claim 11,
a distinguishing unit for discriminating an active user whose last time accessing the chat room from among the plurality of users is within a pre-specified time;
and wherein the providing unit individually provides each of the translated messages to the active user among the plurality of users preferentially.
According to claim 16,
wherein the providing unit individually provides each of the translated messages in the order of the most recent one of the active users at the time of the last access.
According to claim 11,
wherein the determination unit determines the language used by each user by using information on the language used by the terminal of each of the plurality of users.
According to claim 11,
The provision unit further includes the original text of the message before translation and provides it to the plurality of users, preferentially exposes the translated message to the chat room, and when the user's swipe gesture input is received, transmits the translated message to the chat room. and exposing the original text of the message to the chat room.