KR20200079928A - Apparatus and Method for Substitute Call Service - Google Patents

Abstract

The present invention is to provide a device for providing a proxy call service using a response algorithm when one does not want to answer a call, a call comes from an unknown number, or one does not want to talk directly to a sender and a method thereof. The device includes: a voice recognition unit analyzing a received sender voice signal, extracting a feature from the signal, and selecting the closest voice signal from pre-stored words or sentences based on the extracted feature; a text conversion unit converting the voice signal selected by the voice recognition unit into a text; a display unit displaying the text converted by the text conversion unit on a user terminal screen; a response text generation unit generating a response text for communication with the text converted by the text conversion unit based on a keyword of the text displayed on the display unit and using a response algorithm or an artificial intelligence platform; a text list providing unit providing the display unit with a text list of the response text generated by the response text generation unit; a voice conversion unit converting into a voice signal the response text automatically generated by the response text generation unit and using the artificial platform or the response text selected from the response list provided by the text list providing unit; and a key input unit for key signal input by user terminal key pad or touch screen touching.

Description

Apparatus and Method for Substitute Call Service

The present invention relates to an apparatus and method for proxy call service, in particular, an apparatus for providing a proxy call service using a response algorithm when a user does not want to answer a call or receives a call at an unknown number, or when not directly making a phone call with the sender. It's about how.

These days, people often communicate using text messages or mobile messengers. That is why there are many users who have difficulty making phone calls. Even the term phobia, called phobia, is emerging.

Even if you insist on using text or mobile messenger instead of phone in the relationship between individuals, even if you don't want to do it in social life, you still have to make phone calls.

With the recent development of digital technology and Internet technology, the mobile communication terminal has not only a simple voice communication function, but also a wireless Internet transmission/reception function, a video and audio file generation and storage function, and the like.

Through this, in the case of an important matter in the middle of a voice call, the user directly memorized and stored the content, but the recent mobile communication terminal records and saves the call as an audio file and saves the audio file after the call. It is also possible to play and save.

There is a need for a service capable of providing a surrogate call service to users who have difficulty in making phone calls by applying the mobile terminal having developed such technology.

Publication Patent Publication No. 10-2002-0091920 (published on 2002.12.11.) Publication Patent Publication No. 10-2004-0043866 (published on 2004.05.27.)

Therefore, the present invention has been devised to solve the above problems, and provides a proxy call service using a response algorithm when a user does not want to answer a call or receives an unknown number, or does not want to make a phone call directly with the sender. The purpose is to provide an apparatus and method.

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

The feature of the proxy call service apparatus according to the present invention for achieving the above object is to analyze the voice signal of the received sender, extract the feature, and based on the extracted feature, the voice signal closest to the word or sentence stored in advance. A speech recognition unit for selecting, a text conversion unit for converting the voice signal selected by the speech recognition unit into text, a display unit for displaying the text converted by the text conversion unit on a screen of a user terminal, and displayed on the display unit A response text generation unit that generates a response text for communication with the text converted by the text conversion unit using a response algorithm or an AI platform based on the keyword of the text, and the response text generated by the response text generation unit A voice that converts the selected text from the text list providing unit providing the text list of the display unit to the display unit, and the response text automatically generated by the AI platform or the response list provided by the text list providing unit from the interaction text generation unit into a voice signal And a key input unit for inputting a key signal by touching a keypad or a touch screen of a user terminal.

Preferably, the text list providing unit is characterized in that, after storing an answer message for each category in advance, a category is selected by keyword of the text, and a list of at least one response text is provided.

Preferably, the voice signal converted by the voice converter is a voice directly recorded by a user or a machine sound.

Preferably, the response text generation unit is characterized in that for generating a response message generated instantaneously during a call as a response text, and the voice conversion unit converts the generated response text into a voice signal.

Preferably, the key input unit is characterized in that it selects a key for the proxy call when receiving or transmitting according to a telephone call.

A feature of the proxy call service method according to the present invention for achieving the above object is (A) when a call is received by the user terminal, selecting a proxy call by selecting the proxy call key displayed on the display unit, (B ) Analyzing the voice signal received from the telephone-connected sender through the voice recognition unit to extract its characteristics (-> Patent application is my right, regardless of whether it is actually implemented or not.) Or selecting a voice signal closest to the sentence, (C) converting the voice signal selected through the text conversion unit into text, and displaying the converted text on the screen of the user terminal, and (D) generating the response text Generating an interaction text for communication with the converted text using an interaction algorithm or an AI platform through the unit; and (E) through an interaction text or interaction algorithm automatically generated in the AI platform through the speech conversion unit. And converting the selected response text from the provided response list into a voice signal.

Preferably, in step (C), the received voice is characterized in that the user directly listens to at least one of a speaker and an earphone.

Preferably, in the step (C), when it is difficult to display a text in a foreign language or an incomprehensible voice signal, it is characterized in that it is converted into voice recording and stored.

Preferably, in step (D), the response algorithm provides a text list of the preset response text based on the keyword of the converted text through the text list provision unit, and the text list pre-stores an answer message for each category, It is characterized in that a category is selected by keyword of the text, and a list of at least one interaction text is provided as a list.

Preferably, in the step (D) above, it is preferable that the response algorithm does not list the text list (-> "for example" as the part describing the correct embodiment here. .) When you touch once, the selected voice signal is transmitted to the sender at the moment when the other party is disconnected. If you touch the text list twice or long touch, the conversation is terminated regardless of the other party's conversation. Includes steps to be delivered.

Preferably, the voice signal converted in step (E) is a voice recorded by the user or a machine sound.

Preferably, the speech signal converted in step (E) is characterized in that the speech in which the response text is converted through the speech signal modulation algorithm is modulated into a preset speech modulation menu.

The feature of the proxy call service method according to the present invention for achieving the above object is (a) inputting the sender's phone number to the user terminal and selecting the proxy call key displayed on the display unit to select the proxy call, ( b) providing a text list of preset text or instant text generated during a call through a text list providing unit, and (c) a voice signal of a selected text from a list of responses provided through a response algorithm through a voice conversion unit Converting to, (d) when a voice signal received from a sender is input, analyzing the voice signal through a voice recognition unit to extract its characteristics, and selecting a voice signal closest to a previously stored word or sentence; (e) converting the voice signal selected through the text conversion unit into text, and displaying the converted text on the screen of the user terminal; and (f) the conversion using the interaction algorithm or artificial intelligence platform through the interaction text generation unit. Generating a response text for communication with the text, and (g) converting the response text selected from the response text automatically generated by the AI platform through the voice conversion unit or the response list provided through the response algorithm into a voice signal Steps.

Preferably, when the "currency" key is selected among the proxy calls, it is characterized in that it is changed from a proxy call to a direct call.

Preferably, the content of the proxy call is stored and stored in text or voice, and the stored content of the proxy call is sorted and stored in at least one of a person's name order and a date order.

The apparatus and method for proxy call service according to the present invention as described above has the following effects.

First, when you do not want to answer a call or when you receive an unknown number, or when you do not want to make a phone call directly to the sender, you can solve the inconvenience of a call to users who have difficulty in making a phone call through a proxy call service using the response algorithm have.

Second, when a caller makes a call, when the recipient displays a text on the display unit or selects a pre-stored answer message and voice, it can be delivered to the other party by voice through voice synthesis, requiring quietness such as a meeting or a meeting. It has the effect of making it convenient for use to make a call by selecting it from a place.

Third, by allowing the receiver to hear a voice different from the sender's original voice, it can be used a lot among lovers or friends, and can be used when you do not want to reveal the original voice of the sender.

Fourth, a telecommunications operator can expect to earn a call fee if the present invention is used as one additional business, and the user has the effect of being able to make a proxy call and feel interesting.

1 is a block diagram showing the configuration of a proxy call service device according to an embodiment of the present invention
2 and 3 is a flow chart for explaining the proxy call service method of the present invention

Other objects, features and advantages of the present invention will become apparent through the detailed description of the embodiments with reference to the accompanying drawings.

A preferred embodiment of the apparatus and method for proxy call service according to the present invention will be described with reference to the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete and the scope of the invention to those skilled in the art. It is provided to inform you. Therefore, the configuration shown in the embodiments and the drawings described in this specification are only the most preferred embodiments of the present invention and do not represent all of the technical spirit of the present invention. It should be understood that there may be equivalents and variations.

1 is a block diagram showing the configuration of a proxy call service device according to an embodiment of the present invention.

As shown in FIG. 1, the proxy call service device includes a voice recognition unit 10, a text conversion unit 20, a display unit 30, a response text generation unit 40, a text list providing unit 50, and voice It includes a conversion unit 60, a key input unit 70. At this time, the proxy call service device may be included in the user terminal.

The voice recognition unit 10 analyzes the voice signal of the received sender, extracts the characteristic, and selects the closest voice signal from a previously stored word or sentence based on the extracted characteristic.

The text conversion unit 20 converts the voice signal selected by the speech recognition unit 10 into text. The method for converting a voice signal to text follows a known technique, and detailed description thereof is omitted here.

The display unit 30 displays the text converted by the text conversion unit 20 on the screen of the user terminal.

The response text generation unit 40 is based on the keyword of the text displayed on the display unit 30, and the text converted by the text conversion unit 20 using a response algorithm and artificial intelligence platform (Google Assistant, Amazon Alexa, etc.) Generates a response text for communication. In addition, the response text generation unit 40 may generate a response message generated on the fly during a call as a response text.

The text list providing unit 50 provides a text list of the interaction text generated by the interaction text generation unit 40 to the display unit 30. At this time, the provided text list is generated by listing at least one or more interaction texts for communication with the text. Accordingly, the text list providing unit 50 pre-stores an answer message for each category, selects a category with a keyword of the text, and provides a list of at least one response text.

The voice conversion unit 60 may select the response text selected from the response text generated from the AI platform or the basic response list provided by the text list providing unit 50 or the response text created directly during a call in the interaction text generation unit 40. Convert to audio signal. At this time, the voice signal converted to the response text may be a voice recorded by the user or a machine sound. In addition, the voice conversion unit 60 may modulate the voice in which the response text is converted through the voice signal modulation algorithm into a preset voice modulation menu. The voice modulation menu allows the user to select a voice different from the user's voice, such as a thin voice, a bass voice, a slightly slow voice, and a fast voice.

The voice signal modulation algorithm extracts only the voice signal by removing the noise signal collected together with the voice signal, and extracts the extracted voice signal as a digital signal, and then inserts the modulation feature data for each frame section or deletes some data for each frame section. Or, increase the width of voice modulation, decrease the width of voice modulation, speed up the voice frequency, or slow down the voice frequency so that it is modulated into a voice signal that is significantly different from the original sender voice signal.

The key input unit 70 inputs a key signal by touching a keypad or a touch screen of a user terminal. The key input unit 70 may select a key for proxy call when receiving or transmitting according to a telephone call. In addition, the key input unit 70 may select one text for the corresponding text from the text list provided by the text list providing unit 50 or make and use it manually.

The operation of the proxy call service device according to the present invention configured as described above will be described in detail with reference to the accompanying drawings. The same reference numerals as in Fig. 1 refer to the same members performing the same functions.

2 and 3 are flowcharts for explaining the proxy call service method of the present invention. At this time, Figure 2 is a flow chart for explaining a proxy call service for proxy calls when receiving in response to a telephone call, Figure 3 is a flow chart for explaining a proxy call service for proxy calls at the time of transmission according to the phone call.

First, referring to FIG. 2, a proxy call service for proxy calls upon reception according to a telephone call will be described. This can be used when you do not want to answer an incoming call, or when you receive an unknown number, you can use a proxy call service.

Referring to FIG. 2, first, when a call is received by the user terminal (S10 ), the proxy call key displayed on the display unit 30 is touched to select the proxy call (S20 ). To this end, in addition to the "answer call" icon next to the phone number contact, an icon of "representative call or similar term" is additionally displayed.

Subsequently, the voice signal received from the caller connected to the phone through the voice recognition unit 10 is analyzed to extract its characteristics, and the closest voice signal from the previously stored word or sentence is selected (S30).

Then, the voice signal selected through the text conversion unit 20 is converted into text, and the converted text is displayed on the screen of the user terminal (S40). At this time, the received voice may be directly heard by the user through a speaker, earphones, or the like. In addition, voice signals that are difficult to express in text such as foreign languages may be stored as voice recording.

The interactive text generation unit 40 generates an interactive text for communication with the converted text using an interactive algorithm and an artificial intelligence platform (Google Assistant, Amazon Alexa, etc.) (S50).

At this time, the interaction algorithm provides a text list of the preset response text based on the keyword of the converted text through the text list provision unit 50. The provided text list is created by listing at least one or more interaction texts for communication with the text. Accordingly, an answer message for each category is stored in advance, or immediately made during an instant in a call, and then a category is selected by keyword of the text to provide a list of at least one interaction text.

For example, in the case of a number that is not in the contact list of the user terminal, the response algorithm is a basic pattern of response, "Who are you?", "What is it?", "Is it urgent?" You can provide a list of such interactions. And, in the case of a number in the contact list of the user's terminal, the basic pattern of response is "Hello?", "What happened?", "Why?" You can provide a list of such interactions. At this time, the basic pattern is not limited to this, and may have various patterns.

On the other hand, in the response algorithm, when the text list provided from the text list providing unit 50 is touched, for example, the selected voice signal is transmitted to the sender at the moment when the other party is disconnected, for example, double touch or If you touch it for a long time, you can disconnect the other party regardless of the other party's conversation and send the selected voice signal immediately.

Then, through the voice conversion unit 60, the response text selected from the response text automatically generated by the AI platform or the response list provided through the response algorithm is converted into a voice signal (S60). In addition, pressing the "call key" at any time may cause the response algorithm to connect directly to the other party instead of responding.

At this time, the voice signal converted to the response text may be a voice recorded by the user or a machine sound. In addition, the converted speech signal may be modulated into a speech modulation menu preset with the speech in which the response text is converted through a speech signal modulation algorithm. The voice modulation menu allows the user to select a voice different from the user's voice, such as a thin voice, a low-pitched voice, and a quick voice, like a woman.

The voice signal modulation algorithm extracts only the voice signal by removing the noise signal collected together with the voice signal, and extracts the extracted voice signal as a digital signal, and then inserts the modulation feature data for each frame section or deletes some data for each frame section. Or, increase the width of voice modulation, decrease the width of voice modulation, speed up the voice frequency, or slow down the voice frequency so that it is modulated into a voice signal that is significantly different from the original sender voice signal.

Then, until the proxy call ends, the step S30 is repeated to perform the proxy call (S70).

Next, with reference to FIG. 3, a proxy call service for proxy calls during transmission according to a telephone call will be described. This can be used when sending a phone call, such as a delivery service or a delivery request, or when you do not want to make a phone call directly.

Referring to FIG. 3, first, a call number is input to a user terminal and a surrogate call is selected by selecting a surrogate call key displayed on the display unit 30 (S100 ). To do this, in addition to the "dial" icon next to the phone number contact, the "representative call" icon is displayed.

Subsequently, through the text list providing unit 50, a text list of preset text or instant text generated during a call is provided (S200 ).

The provided text list is created by listing at least one or more interaction texts for communication with the text. Accordingly, after storing the response message for each category in advance, a category is selected by keyword of the text, and a list of at least one interaction text is provided. As an example, the response algorithm may provide a response list as a basic response pattern according to delivery food, courier request, errand, and the like.

In addition, in the response algorithm, when the text list provided by the text list providing unit 50 is touched, for example, the selected voice signal is transmitted to the sender at the moment when the other party's speech is interrupted. Regardless of whether or not the conversation is terminated, the selected voice signal can be transmitted immediately.

Subsequently, the response text selected from the response list provided through the response algorithm through the voice conversion unit 60 is converted into a voice signal (S300). At this time, the voice signal is not limited to the text list provided by the text list providing unit 50, and may be a voice uttered by the user.

In addition, the voice signal in which the response text is converted may be a voice directly recorded by the user or a machine sound. In addition, the converted speech signal may be modulated into a speech modulation menu preset with the speech in which the response text is converted through a speech signal modulation algorithm. The voice modulation menu allows the user to select a voice different from the user's voice, such as a thin voice, a bass voice, a slightly slow voice, and a fast voice.

When a voice signal received from a sender is inputted during the proxy call, the voice signal is analyzed through the voice recognition unit 10 to extract its characteristics, and the closest voice signal is selected from previously stored words or sentences (S400).

Then, the voice signal selected through the text conversion unit 20 is converted into text, and the converted text is displayed on the screen of the user terminal (S500). At this time, the received voice may be directly heard by the user through a speaker, earphones, or the like.

The interaction text and the artificial intelligence platform (Google Assistant, Amazon Alexa, etc.) are generated through the interaction text generation unit 40 to generate the interaction text for communication with the converted text (S600).

At this time, the interaction algorithm provides a text list of the preset response text based on the keyword of the converted text through the text list provision unit 50. The provided text list is created by listing at least one or more interaction texts for communication with the text. Accordingly, after storing the response message for each category in advance, a category is selected by keyword of the text, and a list of at least one interaction text is provided.

Then, until the proxy call ends, the step S300 is repeated to perform the proxy call (S700).

On the other hand, if the user selects the "call" key at any time during proxy calls (reception, transmission), the user can change from the proxy call to the direct call.

In addition, the contents of the surrogate call (receiving, sending) provide a function of storing and storing in text or voice, and can be sorted and stored in the order of person's name, date, etc. to easily check the stored surrogate contents.

Although the technical spirit of the present invention described above has been specifically described in a preferred embodiment, it should be noted that the above-described embodiment is for the purpose of description and not for limitation. In addition, those skilled in the art of the present invention will understand that various embodiments are possible within the scope of the technical spirit of the present invention. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

10: speech recognition unit 20: text conversion unit
30: display unit 40: response text generation unit
50: text list providing unit 60: speech conversion unit
70: key input unit

Claims (8)

A voice recognition unit that analyzes a voice signal of a received sender, extracts the characteristic, and selects the closest voice signal from a previously stored word or sentence based on the extracted characteristic;
A text conversion unit for converting the voice signal selected by the speech recognition unit into text;
A display unit that displays the text converted by the text conversion unit on a screen of a user terminal;
A response text generation unit that generates a response text for communication with the text converted by the text conversion unit using a response algorithm or an artificial intelligence platform based on keywords of the text displayed on the display unit;
A text list providing unit providing a text list of the interaction text generated by the interaction text generation unit to the display unit;
A voice conversion unit for converting the response text selected from the response text or the response list provided by the text list providing unit, which is automatically generated by the AI platform, in the response text generation unit;
Surrogate call service device including a key input unit for inputting a key signal by touching the keypad or touch screen of the user terminal.
According to claim 1,
The text list providing unit stores a response message for each category in advance, and then selects a category with a keyword of the text to provide a list of at least one response text.
According to claim 1,
The voice signal converted by the voice conversion unit is a user-recorded voice or a proxy call service device, characterized in that the machine sound.
According to claim 1,
The response text generation unit generates a response message generated on the fly during the call as the response text,
The voice conversion unit is a proxy call service device, characterized in that for converting the generated text to the voice signal.
According to claim 1,
The key input unit for proxy calls when receiving or transmitting according to a telephone call
Surrogate call service device, characterized in that for selecting the key.
(A) when a call is received by the user terminal, selecting a surrogate call by touching the surrogate call key displayed on the display unit;
(B) analyzing a voice signal received from a telephone-connected sender through a voice recognition unit, extracting its characteristics, and selecting a voice signal closest to a previously stored word or sentence;
(C) converting the voice signal selected through the text conversion unit into text, and displaying the converted text on the screen of the user terminal,
(D) generating an interaction text for communication with the converted text using an interaction algorithm or an artificial intelligence platform through the interaction text generation unit;
(E) a surrogate call service method comprising the step of converting a response text selected from a response text automatically generated from the AI platform through a voice conversion unit or a response list provided through a response algorithm into a voice signal. The method of claim 6,
The step (C) is a proxy call service method characterized in that the text is converted into a voice recording when it is difficult to display a text in a foreign language or an incomprehensible voice signal. (a) inputting a caller's telephone number to a user terminal and selecting a surrogate call by selecting a surrogate call key displayed on the display unit;
(b) providing a text list of preset text or instant text generated during a call through a text list providing unit;
(c) converting a selected response text from a response list provided through a response algorithm through a voice conversion unit into a voice signal;
(d) when a voice signal received from a sender is input, analyzing the voice signal through a voice recognition unit to extract characteristics thereof, and selecting a voice signal closest to a previously stored word or sentence;
(e) converting the voice signal selected through the text conversion unit into text, and displaying the converted text on the screen of the user terminal;
(f) generating an interaction text for communication with the converted text using an interaction algorithm or an artificial intelligence platform through the interaction text generation unit;
(g) a proxy call service method comprising the step of converting a response text selected from a response text automatically generated by the AI platform or a response list provided through a response algorithm through a voice conversion unit into a voice signal.

Images