KR102248701B1 - Automatic Interpreting of Multilingual Voice Interpretations To control the timing, end, and provision of certain information in chatting with a given voice - Google Patents

Abstract

The present invention relates to a method for controlling the start and end points of interpretation and provision of predetermined information with a predetermined voice during an automatic interpretation chatting of multilingual voice. More particularly, each of a plurality of chatting participants using different native languages can control the starting point and ending point of a conversation which needs to be interpreted to the other party during a conversation in their native language with predetermined voice information, and allows specific information to be provided with a predetermined voice, as well. The present invention relates to a method for controlling the start and end points of interpretation and provision of predetermined information with a predetermined voice during an automatic interpretation chatting of multilingual voice, comprising the steps of: inputting the first voice information indicating the start of the conversation, the conversation content composed of voice, and the second voice information indicating the end of the conversation content to the first terminal; transmitting the conversation contents from the first terminal to the server; converting the conversation content into a first text at the server and then converting the conversation content into N foreign language texts corresponding to the first text (N is a natural number equal to or greater than 1); converting the N foreign language texts into N foreign language voices respectively; and transmitting the N foreign language voices to a second terminal using a foreign language corresponding to the N foreign language voices, respectively, and outputting the N foreign language voices to a speaker of the second terminal.

Description

Automatic Interpreting of Multilingual Voice Interpretations To control the timing, end, and provision of certain information in chatting with a given voice}

The present invention relates to a method of controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat with a predetermined voice. More specifically, each of a plurality of chat participants using different native languages communicates in their native language. The present invention relates to a method of enabling control of the start and end points of a conversation to be interpreted to the other parties with predetermined voice information, as well as allowing specific information to be provided with a predetermined voice.

With the development of internet technology and mobile technology, chatting service between a number of smart terminals is active.

However, the existing chat system is a system developed for users who use the same language, and chat with each other is possible only when the same language is used.

In other words, real-time chat is difficult for users who speak different languages.

Therefore, there is an inconvenience of having to chat in either language of the parties, or to chat in English, which can be recognized as an international language.

Alternatively, a method was provided for users to write a message in their native language in a chat window, and to use a separate translation program to translate the message into the language of the other user and then chat. Therefore, according to the conventional chat system, there is a problem in that it is difficult to provide a smooth chat service between users using different languages.

On the other hand, in order to improve this problem, a chat service is provided even for multi-party using different languages.

During such multi-party chat, translation is performed in real time by relaying from a translation server. The multi-party chat service provides real-time translation between different kinds of languages, for example, when a person who speaks Korean, a person who speaks Japanese, and a person who speaks English has a three-way chat.

However, the existing multi-party chat service is inefficient and inconvenient as the process goes through redundant processes when using the service. For example, when a chat message is input in Korean on a Korean user terminal, the terminal requests and receives a Japanese translation from the translation server, and then transmits it to the Japanese user. In addition, since a Korean user inputs Korean into the terminal again, and the terminal requests and receives an English translation from the translation server, it must be transmitted to the English user, and thus the same Korean language must be repeatedly input.

As a prior patent technology proposed to solve this problem, the name of the invention filed by HelloChat Co., Ltd. is "an apparatus and method for providing a translation chat service" (Patent Application No. 10-2015-0029838).

This prior patent document proposes a method for providing a translation chat service in which chat texts of different languages input to each of a plurality of user terminals are translated in real time and the original text and the translated text are provided to a chat counterpart user terminal.

The technical idea disclosed in the preceding patent document relates to a method of providing a translation chat service in a first user terminal,

Receiving a first voice input of a first language;

Transmitting the first voice input to a translation chat service providing server;

Receiving a first text in the first language corresponding to the first voice input and a second text in a second language in which the first text is translated from the translation chat service providing server; And

Displaying the first text and the second text,

It can be seen that a method of providing a translation chat service including a is proposed.

However, the technology of the preceding patent document relates to a method of receiving, for example, Korean voice, converting it into Korean and English text, and then displaying it. A number of different native languages are converted to text through the same chat app. It has a problem that it is difficult to apply if you want to share communication.

On the other hand, in another prior patent whose application number is 10-2013-0096771 and the name of the invention is "a system and method for providing a messaging interpretation service based on voice recognition," The first message is generated by using the method, and a second message translated from the first message into a different language is generated, and then transmitted to the other terminal, thereby enabling smooth message conversation even between users of different languages. Technology is being proposed

Looking at the technical idea of this prior patent document: (a) searching for a text corresponding to a voice input received from a user terminal by a service providing server; (b) generating, by the service providing server, a first message in a first language by combining the text searched in step (a); (c) generating, by the service providing server, a second message by translating the first message into a second language different from the first language; (d) the service providing server transmitting the second message to one or more user terminals including the user terminal; it can be seen that the method of providing a voice recognition-based messaging interpretation service of the service providing server including

By the way, in the case of such a prior patent document, it can be seen that it relates only to text chat with a state room using a different language.

1. Patent application number; 10-2015-0029838, title of invention; "Device and method for providing translation chat service" 2. Patent application number; 10-2013-0096771, the name of the invention; "Voice recognition-based messaging interpretation service provision system and method"

An object of the present invention is to enable a plurality of chat participants using different native languages to chat in real time in their own language.

The present invention enables voice chat as well as text chat, and it is an object of the present invention to provide real-time interpretation and voice for speakers in different native languages during voice chat.

In addition, an object of the present invention is to be able to control the starting point and the end point of the interpretation by using a predetermined voice when chatting through voice.

In addition, an object of the present invention is to provide a method for searching and listening for predetermined information through predetermined voice information.

The present invention is a method for controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat with a predetermined voice,

Inputting, to a first terminal, first voice information indicating the start of a conversation, conversation content composed of voice, and second voice information indicating the end of the conversation content;

Transmitting the conversation content from the first terminal to the server;

Converting the conversation content into a first text in the server and then converting it into N foreign language texts (N is a natural number of 1 or more) corresponding to the first text;

Converting the N foreign language texts into corresponding N foreign language voices

And transmitting each of the N foreign language voices to a second terminal using a foreign language corresponding to each of the N foreign language voices, and outputting the N foreign language voices to a speaker of the second terminal.

In addition, the present invention is a method for controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat with a predetermined voice,

Inputting first voice information indicating the start of a conversation, search information composed of voice, and third voice information indicating a search request to a first terminal;

Transmitting the search information from the first terminal to the server;

Converting the search information into first text at the server and searching for data corresponding to the first text;

And converting the search data extracted by the search into text or voice and transmitting it to the first terminal.

In addition, the present invention is a method for controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat with a predetermined voice,
(a) after activating the chat app installed in the terminal, setting and storing arbitrary first voice information and second voice information indicating the start and end of a voice conversation in the chat app;
(b) inputting the first voice information indicating the start of a conversation through the terminal, a conversation content in a first language, and an end of the conversation content with the second voice information;
(c) transmitting the conversation content in the first language from the terminal to an app server;
(d) converting the conversation content composed of the first language into a first text in the app server
(e) inputting the first text to a first server that is an analysis and storage server;
(f) When there is a first foreign language text expressed in at least one or more other languages corresponding to the conversation content composed of the first language corresponding to the first text stored in the first server, the first Transmitting a foreign language text to the app server, converting the first foreign language text into a voice in a first foreign language in the app server, selectively transmitting the first foreign language to a terminal selected as a native language, and outputting the voice as voice;
(g) When there is no second foreign language text expressed in at least one or more other languages corresponding to the conversation content composed of the first language corresponding to the first text stored in the first server, the second foreign language text 1 server transmits the first text to a gateway server that is linked with at least one or more translation sites that provide a foreign language translation function, and the gateway server accesses a first translation site, which is one of the at least one or more translation sites, The first text is transmitted to the first translation site, and the first translation site translates the second foreign language text expressed in at least one different language corresponding to the first text, and the gateway server And the gateway server transmits the second foreign language text to the first server, and the first server stores the second foreign language text and simultaneously transmits the second foreign language text to the app server, and the In the app server, converting the second foreign language text into a second foreign language voice, selectively transmitting the second foreign language to a terminal selected as a native language, and outputting the voice as voice; and
A function of translating and transmitting a foreign language corresponding to the first text by voice from the first server directly to the chat app while reducing support of at least one translation site while repeating steps (a) to (g). It is characterized by increasing

delete

delete

delete

delete

delete

delete

delete

Another embodiment of the present invention is a method of controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat with a predetermined voice,

Inputting a conversation content through a chat app activated in the first terminal by voice;

Step of transmitting and storing the conversation contents to the server

When predetermined fourth voice information is input from the first terminal, the server converts the previously stored conversation content into first text and then converts the previously stored conversation content into N foreign language texts (N is a natural number greater than or equal to 1) corresponding to the first text. Letting go;

Converting the N foreign language texts into corresponding N foreign language voices

And transmitting each of the N foreign language voices to a second terminal using a foreign language corresponding to each of the N foreign language voices, and outputting the N foreign language voices to a speaker of the second terminal.

Another embodiment of the present invention is a method of controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat with a predetermined voice,

Inputting fifth voice information during a voice conversation through a chat app activated in the first terminal and then inputting first information to be searched by voice;

Transmitting the first information to a server

The server converts the first information into text, searches for data corresponding to the first information, and transmits the data to the first terminal,

The data transmitted to the first terminal may be displayed as text on a chat app of the first terminal or output as a voice through a speaker of the first terminal.

The following effects can be expected when a method of controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat proposed by the present invention is performed with a predetermined voice.

The chat app of the present invention is capable of real-time interpretation.

Therefore, many who speak different languages can speak and listen in their native language while talking through the chat app.

In addition, by using voice information indicating the start and end of the conversation, only the content of the conversation to be transmitted can be interpreted.

FIG. 1 is an example of a system for implementing a method of controlling a time point and an end point of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat proposed by the present invention with a predetermined voice.
2 is a flowchart illustrating the function of the analysis and storage service proposed in the present invention.
3 is another example of a method for correcting a translation error proposed by the present invention.

Hereinafter, with reference to the drawings, a description will be given of a method of controlling the time and end points of interpretation and provision of predetermined information in a multilingual voice automatic interpretation chat proposed by the present invention with a predetermined voice.

As a premise of the description of the present invention, first, a server-side system for implementing the method of the present invention will be described first.

FIG. 1 is an example of a system for implementing a method of controlling a time point and an end point of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat proposed by the present invention with a predetermined voice.

2 is a flowchart illustrating the function of the analysis and storage service proposed in the present invention.

The technical idea of the present invention is that terminal users using different native languages (Korean users, Chinese users, English users, French users, Japanese users, etc.) input text languages used by each of them through a chat app installed in their respective terminals. It can be done, and the chat app installed on the other person's terminal should be displayed in real time in the language that each person uses.

Therefore, there is an advantage that a number of chat app participants who speak different languages can chat naturally with a large number who speak different languages regardless of the language barrier.

That is, when Korean text is input through the chat app, the chat app of the terminal using English, French, Japanese, Chinese, etc. is translated into English, French, Japanese, Chinese, etc. corresponding to Korean, and is displayed on the chat app installed on each terminal. This has the advantage that many people who speak different native languages can chat freely.

Hereinafter, it will be described in more detail with reference to the drawings.

First, each of the multiple users who speak different native languages installs a chat app on their terminal (smart phone, tablet, computer, etc.), and then opens a chat window where they can chat with multiple users through friend settings. can do.

It is assumed that a Korean user inputs, for example, the text "Hello" through a chat window of a chat app installed in his terminal.

The text "Hello" is transmitted to the analysis and storage server provided by the present invention.

The configuration of the analysis and storage server of the present invention can implement the process shown in FIG. 2. 2 is a flowchart illustrating the function of the analysis and storage service proposed in the present invention.

1. Determining the language of the transmitted text

The analysis and storage server determines the language type of the text received through the chat app.

For example, it is determined whether the received text is Korean, English, or Japanese.

2. Next, it searches for other languages that have the same meaning as the text.

For example, English, Japanese, Chinese, etc. corresponding to Korean "hello" are searched through the database.

3. If there is a foreign language corresponding to the text, the foreign language is directly transmitted to the chat app of the terminal using the foreign language.

For example, when Japanese and English corresponding to "Goodbye" exist in the database, the analysis and storage server transmits them directly to the chat app of the terminal using Japanese and English to chat.

Therefore, Japanese and English corresponding to "Goodbye" will be displayed in the chat window of a chat app user who uses Japanese or English.

4. Next, if there is no foreign language corresponding to the text, the analysis and storage server transmits the text (eg, Korean Hello) to the gateway server, but other languages (eg, Chinese, Vietnamese, French, Russian) except English and Japanese. Etc.).

5. The gateway server of the present invention is linked with at least one translation site that provides a foreign language translation function.

As shown, the gateway server of the present invention is a Google API that provides a translation service, a Papago API, a Tencent API, a SKT API, a Naver API, an Israel API, and an API (that is, a translation site) that provides a number of other translation services. Is linked with.

The gateway may designate at least one or more specific translation sites. This is because the quality of translation varies from site to site. Accordingly, the gateway is capable of designating at least one or more translation sites that provide optimum translation quality among various translation sites.

6. The foreign language test translated at the translation site is transmitted to the gateway server, and the gateway server transmits it to the analysis and storage server.

7. The analysis and storage server stores the foreign language text (eg, English, Japanese, Chinese, etc.) and transmits it to the app server.

8. The app server transmits the foreign language text to multiple users chatting through the same chat room.

In this case, when the language used by the chat participant is English, the English text is transmitted, and when the Chinese is the language, the Chinese text is transmitted.

Accordingly, the chat participant can view text translated into the language that the chat participant uses as well as the text written by the chat participant who speaks another language, as well as the ability to input text in the language they use.

Accordingly, it can be seen that chat participants using different native languages can input and receive text in their own language.

The general summary of the present invention described above is as follows.

A user (participant) who uses the chat app according to the present invention using a terminal may open a predetermined chat room or participate to chat with a plurality of participants after selecting a language to be used in the chat app setting step.

First, one chat participant who selects language A creates and inputs a context in the language A in the chat window.

The context is transmitted to the app server, and the app server transmits the context to the analysis and storage server.

After determining the language of the context, the analysis and storage server determines whether other foreign languages corresponding to the context (B text in B language, C text in C language, D text in D language, etc.) exist in the database. Confirm.

For example, if the text B corresponding to the text A exists in the database, the analysis and storage server transmits the text B to the app server, and the app server transmits the text B to the chat app of the participant using the text B.

Therefore, there is an advantage that high speed processing is possible.

On the other hand, if the foreign language corresponding to the context is not in the database, the context is transmitted to the gateway server.

The gateway server provides the context to at least one translation site, receives the translation result, and transmits it to the analysis and storage server.

The analysis and storage server stores the translation result (e.g., another foreign language corresponding to the A text (B text in B language, C text in C language, D text in D language, etc.) and transmits it to the app server.

The app server transmits the result of treason corresponding to the language of the chat participant to the chat app of each chat participant.

Thus, there is an advantage that many who speak different native languages can chat in real time in their own language.

On the other hand, in the case of the analysis and storage server according to the present invention, it is possible to store translated texts of various qualities corresponding to a predetermined text in a database when a certain time elapses, and in this case, it is not necessary to go through a gateway server, so not only quick response but also gradual As the number of translations through the API is reduced, there is an advantage in that economic efficiency increases.

Meanwhile, the analysis and storage server of the present invention may provide a function for deriving an optimal result for the original text and translations of various languages corresponding thereto by providing its own deep learning learning tool.

On the other hand, the chat participant can select and retransmit it to the app server when the sentence of the translated text received by the chat participant is strange, and the app server retransmits it to the analysis and storage server.

In this case, if there is another translation corresponding thereto in the analysis and storage server, another translation may be transmitted to the chat app of the chat participant through the app server.

If there is no other translation, it is transmitted through the gateway server, and the gateway receives the result of another translation site and transmits it to the analysis and storage server, which can be sent back to the chat participant's chat app through the app server. This can be done repeatedly, and if the user no longer requests to retransmit the translated text to the app server, the analysis and storage server determines that the translation has been successfully translated, learns, and through these results, the analysis and storage server The priority for the best translated text can be determined internally and the results are stored for later use as major translations.

Next, FIG. 3 is another example of a method for correcting a translation error proposed by the present invention.

If there is an error in the translated text received by a participant of the chat app using Korean, selecting the retranslation function key provided by the chat app allows you to receive the desired translated text by repeating the operation as described above.

On the other hand, as shown in Fig. 3, when an incorrect translation containing a different language in a specific Hangul is generated and received, when a participant requests retranslation, the analysis and storage server uses the result trained by its own deep learning learning method. Thus, an optimal translation text can be provided.

Meanwhile, the chat app of the present invention may be provided with a function key for requesting an original text (an original text input by a chat partner) for a text in a predetermined language displayed on the chat app.

That is, when a chat participant who receives the translated text B text for the context selects a function key for viewing the original text of the text B, the analysis and storage server can selectively transmit the context stored in the database.

In addition, the chat app of the present invention may be provided with a function key for requesting an original text (original text input by a chat partner) for text in a predetermined language displayed on the chat app.

In this case, the analysis and storage server transmits the original text.

As described above, the analysis and storage server used in the real-time multilingual multi-translation chat method using the automatic translation function proposed in the present invention can store various translation results, and the retranslated results are accumulated according to the retranslation request of the chat participant. In addition, the optimal translation text will be stored according to the result of deep learning learning.

That is, B, C, D text, etc. translated into other languages for A text will be stored, as well as many texts having the same meaning as B, C, D text, etc. will be retained.

Therefore, when a retranslation request for any one of the translated texts transmitted to the chat app is repeatedly input to the analysis and storage server through the app server, the frequency of selection among texts having the same same and similar meaning as the translated text sent immediately before It will be possible to select a text with a higher value and send it to the chat app.

Therefore, there is an advantage that high quality translated text can be provided as the period elapses.

That is, when the same and similar texts of various qualities are accumulated and stored in correspondence with each language, and the process according to the present invention is repeatedly performed until the chat participant agrees to the corresponding translation, the analysis and storage server of the present invention It is possible to operate in a scroll without support, so it has the advantage of not only responding quickly to translation but also reducing the economic burden.

On the other hand, the present invention intends to propose another embodiment when used in the above system.

Another embodiment of the present invention is "a method of controlling the time and end points of interpretation and provision of predetermined information in a multilingual voice automatic interpretation chat with a predetermined voice".

It will be described in more detail below.

First, the app server of the present invention shown in FIG. 1 is further provided with a speech to text (STT) function unit for converting speech transmitted through a terminal into text and a text to speech (TTS) function unit for converting text into speech. .

In addition, the app server of the present invention may further include a control unit for recognizing a predetermined command from voice input through a terminal.

That is, the app server of FIG. 1 may further include an STT function unit, a TTS function unit, and a control unit.

In the present invention, the STT function unit, the TTS function unit, and the control unit are used to convert the voice input through the terminal into text, and then at least one or more other foreign language texts that have undergone the above-described translation process are converted into speech, respectively, To be able to transfer.

Therefore, when implementing the method according to the present invention, the voice transmitted through the chat app installed in the terminal is automatically interpreted, and the voice can be output in the language used by the other terminal.

Therefore, in the case of using the chat app according to the present invention, it is possible to expect an effect of receiving a real-time interpretation service even though languages are different from each other.

However, when the automatic voice interpretation function is provided as in the present invention, an unwanted voice may be transmitted to a counterpart terminal for interpretation.

Accordingly, the present invention proposes a method for controlling the starting point and the end point of a voice conversation to be interpreted during a multilingual voice automatic interpretation chat.

First, each user may set first voice information indicating the start of a predetermined conversation and second voice information indicating the end of a predetermined conversation through the chat app of the present invention installed in his or her terminal and store it in the chat app.

After setting the first voice information and the second voice information in this way, the user utters the first voice through the chat app, then inputs the content of the conversation to be spoken by voice, and then utters the second voice.

That is, voice information is input to the terminal in the order of first voice information, conversation content, and second voice information.

Then, in the chat app according to the present invention, after receiving the first voice indicating the start of the voice conversation, the conversation contents are stored, and when the second voice is input, the voice conversation contents are transmitted to the app server according to the present invention.

Next, in the app server according to the present invention, after receiving the voice conversation content through the STT function, it is converted into text,

After converting to text, the process of converting to another foreign language text is performed as described in FIGS. 1 to 3.

Next, the translated text of the foreign language is transmitted to the app server of the present invention and converted into the corresponding foreign language voice through the TTS function unit of the app server.

Next, the converted foreign language voice is output through the speaker of the counterpart terminal participating in the chat app.

Therefore, in the case of using the chat app according to the present invention, even if voice conversations in different languages are performed, each has the advantage that they can speak in their own language and listen in their own language.

In the present invention, the first voice information and the second voice information indicating the start and end of the voice conversation can be set by each of the chat app.

For example, the first voice information may be set to “sea” and the second voice information may be set to “sky”.

In the case of using the present invention, there is an advantage of being able to block unwanted conversations from being automatically interpreted and provided to the other party.

On the other hand, the present invention also provides a function of requesting a search for specific information by voice and listening to it by voice.

For example, if you say "tohamsan" after uttering the first voice information and then input the voice "search" as the third voice information, the app server recognizes this as a search request and then goes through the process described in FIGS. After acquiring information about "Tohamsan", the TTS function can be provided by voice.

This function is a method in which the terminal user requests specific information by voice.

In other words, after uttering the first voice information, the search target is spoken in voice, and the third voice information, such as “search”, which means a search request, is referred to, and the app server recognizes it as an information search request and has priority among search information corresponding to The highest search information can be provided by voice or text.

For reference, the third voice information can be freely set by the user in the chat app installed in the terminal.

As described above, in the case of implementing the method according to the present invention, multiple chat participants using different foreign languages express their respective languages by voice, while automatically interpreting the language of the other party using the foreign language and use them in real time. Has the advantage of being able to listen in a language

In addition, according to the present invention, there is an advantage that information search can be requested by voice without text input, and the searched information can be provided by text or voice according to the setting of a chat app.

Therefore, the technical idea of the present invention is summarized as follows.

Multilingual voice automatic interpretation As a method of controlling the time and end points of interpretation and provision of predetermined information during a chat with a predetermined voice,

Inputting, to a first terminal, first voice information indicating the start of a conversation, conversation content composed of voice, and second voice information indicating the end of the conversation content;

Transmitting the conversation content from the first terminal to the server;

Converting the conversation content into a first text in the server and then converting it into N foreign language texts (N is a natural number of 1 or more) corresponding to the first text;

Converting the N foreign language texts into corresponding N foreign language voices

And transmitting each of the N foreign language voices to a second terminal using a foreign language corresponding to each of the N foreign language voices, and outputting the N foreign language voices to a speaker of the second terminal.

On the other hand, another technical idea of the present invention

Inputting first voice information indicating the start of a conversation, search information composed of voice, and third voice information indicating a search request to a first terminal;

Transmitting the search information from the first terminal to the server;

Converting the search information into first text at the server and searching for data corresponding to the first text;

The search data extracted by the search may be converted into text or voice and transmitted to the first terminal.

On the other hand, another embodiment of the present invention is a method of controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat with a predetermined voice,

Inputting a conversation content through a chat app activated in the first terminal by voice;

Step of transmitting and storing the conversation contents to the server

When predetermined fourth voice information is input from the first terminal, the server converts the previously stored conversation content into first text and then converts the previously stored conversation content into N foreign language texts (N is a natural number greater than or equal to 1) corresponding to the first text. Letting go;

Converting the N foreign language texts into corresponding N foreign language voices

It is also possible to provide a method comprising: transmitting the N foreign language voices to a second terminal using a foreign language corresponding to the N foreign language voices, respectively, and outputting the N foreign language voices to a speaker of the second terminal;

In this case, the fourth information can be freely set by the user in the chat app of the terminal.

Another embodiment of the present invention is a method of controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat with a predetermined voice,

Inputting fifth voice information during a voice conversation through a chat app activated in the first terminal and then inputting first information to be searched by voice;

Transmitting the first information to a server

The server converts the first information into text, searches for data corresponding to the first information, and transmits the data to the first terminal,

The data transmitted to the first terminal may be displayed as text on a chat app of the first terminal or may be output as a voice through a speaker of the first terminal.

Here, the fifth voice information can be set freely by the user.

In addition, another embodiment of the present invention
Multilingual voice automatic interpretation As a method of controlling the time and end points of interpretation and provision of predetermined information during a chat with a predetermined voice,
(a) after activating the chat app installed in the terminal, setting and storing arbitrary first voice information and second voice information indicating the start and end of a voice conversation in the chat app;
(b) inputting the first voice information indicating the start of a conversation through the terminal, a conversation content in a first language, and an end of the conversation content with the second voice information;
(c) transmitting the conversation content in the first language from the terminal to an app server;
(d) converting the conversation content composed of the first language into a first text in the app server
(e) inputting the first text to a first server that is an analysis and storage server;
(f) When there is a first foreign language text expressed in at least one or more other languages corresponding to the conversation content composed of the first language corresponding to the first text stored in the first server, the first Transmitting a foreign language text to the app server, converting the first foreign language text into a voice in a first foreign language in the app server, selectively transmitting the first foreign language to a terminal selected as a native language, and outputting the voice as voice;
(g) When there is no second foreign language text expressed in at least one or more other languages corresponding to the conversation content composed of the first language corresponding to the first text stored in the first server, the second foreign language text 1 server transmits the first text to a gateway server that is linked with at least one or more translation sites that provide a foreign language translation function, and the gateway server accesses a first translation site, which is one of the at least one or more translation sites, The first text is transmitted to the first translation site, and the first translation site translates the second foreign language text expressed in at least one different language corresponding to the first text, and the gateway server And the gateway server transmits the second foreign language text to the first server, and the first server stores the second foreign language text and simultaneously transmits the second foreign language text to the app server, and the In the app server, converting the second foreign language text into a second foreign language voice, selectively transmitting the second foreign language to a terminal selected as a native language, and outputting the voice as voice; and
A function of translating and transmitting a foreign language corresponding to the first text by voice from the first server to the chat app while reducing support of at least one translation site while repeating steps (a) to (g). Can increase

Through the various embodiments as described above, chat app participants can naturally communicate in their native language, as well as freely select the time point of the conversation content to be interpreted and transmitted, and request a search for information that they are interested in during the conversation. By providing the voice information of the server to the server, there is an advantage in that you can check the question you are in text or voice

For reference, in describing the technical idea of the present invention, the server should be understood as a generic concept that includes an app server or an app server, an analysis and storage server, or further includes a gateway server.

delete

delete

delete

delete

Claims (5)

Multilingual voice automatic interpretation As a method of controlling the time and end points of interpretation and provision of predetermined information during a chat with a predetermined voice,
(a) after activating the chat app installed in the terminal, setting and storing arbitrary first voice information and second voice information indicating the start and end of a voice conversation in the chat app;
(b) inputting the first voice information indicating the start of a conversation through the terminal, a conversation content in a first language, and an end of the conversation content with the second voice information;
(c) transmitting the conversation content in the first language from the terminal to an app server;
(d) converting the conversation content composed of the first language into a first text in the app server
(e) inputting the first text to a first server that is an analysis and storage server;
(f) When there is a first foreign language text expressed in at least one or more other languages corresponding to the conversation content composed of the first language corresponding to the first text stored in the first server, the first Transmitting a foreign language text to the app server, converting the first foreign language text into a voice in a first foreign language in the app server, selectively transmitting the first foreign language to a terminal selected as a native language, and outputting the voice as voice;
(g) When there is no second foreign language text expressed in at least one or more other languages corresponding to the conversation content composed of the first language corresponding to the first text stored in the first server, the second foreign language text 1 server transmits the first text to a gateway server that is linked with at least one or more translation sites that provide a foreign language translation function, and the gateway server accesses a first translation site, which is one of the at least one or more translation sites, The first text is transmitted to the first translation site, and the first translation site translates the second foreign language text expressed in at least one different language corresponding to the first text, and the gateway server And the gateway server transmits the second foreign language text to the first server, and the first server stores the second foreign language text and simultaneously transmits the second foreign language text to the app server, and the In the app server, converting the second foreign language text into a second foreign language voice, selectively transmitting the second foreign language to a terminal selected as a native language, and outputting the voice as voice; and
A function of translating and transmitting a foreign language corresponding to the first text by voice from the first server to the chat app while reducing support of at least one translation site while repeating steps (a) to (g). A method of controlling the time and end points of interpretation and provision of predetermined information during a multilingual voice automatic interpretation chat, characterized in that to increase, with a predetermined voice. delete delete delete delete

Images