WO2019132092A1

WO2019132092A1 - Plush doll robot with voice recognition function

Info

Publication number: WO2019132092A1
Application number: PCT/KR2018/000173
Authority: WO
Inventors: 이성종
Original assignee: 수상에스티주식회사
Priority date: 2017-12-29
Filing date: 2018-01-04
Publication date: 2019-07-04
Also published as: KR20200119821A

Abstract

Disclosed is a plush doll robot with a voice recognition function. A plush doll robot with a voice recognition function, according to one embodiment of the present invention, comprises: a control unit for performing an action corresponding to a command input by a user; a voice recognition unit for storing a user's voice as an input voice file, transmitting the input voice file to the control unit when a predetermined command is included in the input voice, and transmitting the input voice file to a voice recognition server when a predetermined command is not included in the input voice; a voice providing unit for receiving a voice response file corresponding to the input voice file from the voice recognition server and outputting the voice response file as a voice; a sensor unit, provided with at least one sensor of a touch sensor and a pulse sensor, for sensing a body input; a wireless communication unit for wirelessly communicating with an external terminal by using at least one of Wi-Fi, Bluetooth, and NFC; a motor unit for driving a plurality of motors to control movement of the body of the plush doll robot; and an LED for, when an LED lighting signal is included in signals received from the sensor unit and the voice recognition server, illuminating light in response to the received lighting signal.

Description

Plush doll robot with speech recognition function

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a sewing robot having a voice recognition function, and more particularly to a plush toy having a voice recognition function for outputting a voice corresponding to a user's voice by connecting to a voice recognition server through an external terminal using wireless communication Robot.

Conventionally, a system for controlling an envoy by combining the Internet with a doll has been developed. Dolls are very interested in the development of smart doll technology because they play an important role in infant and child playing and develop the physical exercise and function, and play an educational role by developing imagination and creativity through intelligence development. However, since the doll has a limited sound output or no action, it is difficult for the user to continuously attract new interest and interest. Therefore, the doll recognizes the user's voice and answers, or connects the doll motor It is necessary to study a sewing doll robot having a voice recognition function which enables a user to operate in a preset situation and to provide a variety of contents by being connected to an external terminal so that the user does not lose interest.

The present invention provides a plush dolphin robot having a voice recognition function that is connected to a server through wireless communication to analyze a voice of a user and output a voice corresponding thereto.

When the user's body input is sensed, the operation of the robot and the LED (LED) blink due to the motor, so that the user can recognize the voice recognition

To provide a plush doll robot with a function.

The present invention provides a plush dolphin robot having a speech recognition function capable of providing a variety of contents to a user by converting a file including a text into a voice file and correcting an error occurring during the conversion.

The present invention provides a stuffed toy robot having a voice recognition function that can be of interest to a child user by providing mobile contents composed of a stuffed toy character connected to an external terminal.

A robot for performing a sewing robot having a voice recognition function according to an embodiment of the present invention includes a controller for performing an action corresponding to a command input of a user, a controller for storing a user's voice as an input voice file, A voice recognition unit for transmitting the input voice file to the control unit and transmitting the input voice file to the voice recognition server if the voice of the user is not included, A touch sensor, and a pulse sensor for receiving the answer voice file from the speech recognition server and outputting the answer voice file as a sound; a sensor unit for detecting a body input by providing at least one sensor, A wireless communication unit for wirelessly communicating with an external terminal using at least one of Wi-Fi, Bluetooth, and NFC; A motor unit for controlling the movement of the body by driving a number of motors and an LED lighting signal among signals received from the sensor unit and the voice recognition server, And an LED (light emitting diode).

According to an aspect of the present invention, the voice providing unit may allow a user to synthesize a voice to select a base voice or a base voice with a predetermined voice.

According to an aspect of the present invention, the speech recognition server may include a TTS conversion unit that receives a scan file including text and converts the text included in the scan file into a speech file.

According to an aspect of the present invention, the TTS conversion unit provides basic information of the scan file to a user registered in a predetermined space on a network, and first requests an operation of correcting an error of the voice file in accordance with the basic information The original of the scan file and the voice file is transmitted to the correction applicant, the correction applicant receives the corrected voice file to verify the corrected voice file, and when the verification of the corrected voice file is completed, A predetermined portion of the sales revenue of one voice file can be provided to the correction applicant.

According to one aspect of the present invention, the TTS conversion unit provides the correction applicant with a (100-X)% (here, X denotes the contribution of the correction applicant) of the net profit to the predetermined sales quantity of the voice file ((100-X) - (sales quantity - predetermined sales quantity))% of the net profit when the sales quantity exceeds the preset sales quantity.

According to an embodiment of the present invention, there is provided a sewing robot having a voice recognition function connected to a server through wireless communication to analyze a voice of a user and output a voice corresponding thereto.

According to an embodiment of the present invention, when a user's body input is sensed, an operation of the robot due to the motor and an LED (LED) blink to provide a sewing robot having a voice recognition function that can be of interest to the user .

According to one embodiment of the present invention, a plush dolls robot having a speech recognition function capable of providing a variety of contents to a user by converting a file including a text into a voice file and correcting an error occurring during the conversion do.

According to an embodiment of the present invention, there is provided a stuffed toy robot having a voice recognition function that can be of interest to a child user by providing mobile contents composed of a stuffed toy character connected to an external terminal.

1 is a block diagram of a stuffed toy robot having a speech recognition function according to an embodiment of the present invention.

2 is a diagram for explaining a process of converting a scan file including text into an audio file according to an embodiment of the present invention.

3 is a diagram showing a voice file sold according to an embodiment of the present invention.

4 is a diagram illustrating a change in expression of an application character according to a user voice according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the present invention is not limited to or limited by the embodiments. Like reference symbols in the drawings denote like elements.

1 is a block diagram of a sewing robot 100 having a speech recognition function according to an embodiment of the present invention.

1, a sewing robot 100 having a voice recognition function includes a control unit 110, a voice recognition unit 120, a voice data providing unit 130, a wireless communication unit 140, a sensor unit 150, An LED 170, a voice recognition server 200, and an external terminal 300. The voice recognition server 200 and the voice recognition server 200 are connected to each other via a network.

The controller 110 may perform an action corresponding to a command input by the user.

The voice recognition unit 120 stores a voice of a user as an input voice file and transmits the input voice file to the control unit 110 when a predetermined command among the input voice is included, If the preset command is not included, the input voice file can be transferred to the voice recognition server 200 through the external terminal 300.

For example, when the user speaks 'LED lit', the user is stored as an input voice file. The voice recognition unit 120 recognizes a predetermined 'LED lighting' command among the input voice file, And the controller 110 turns on the LED 170 provided in the stuffed animal robot 100 or the LED provided in the outside. In addition, the control unit 110 analyzes the input voice file to start the LED lighting. And transmits the answer voice file to the stuffed animal robot 100. Referring again to FIG. 1, the voice data providing server 130 receives the answer voice file corresponding to the input voice file from the voice recognition server 200, and outputs the answer voice file transmitted through the voice.

For example, if the user speaks a voice of 'bear three bears', the voice is stored in the voice recognition unit 120 as an input voice file, and the word has no preset command. Therefore, the input voice file is transmitted to the voice recognition server 200 through the external terminal 300, and the voice recognition server 200 analyzes the input voice file and reads 'three bears will be played' Create three "Bear" songs as answer voice files. The generated answer voice file is transmitted to the voice data providing unit 130, and the voice data providing unit 130 outputs the answer voice file by voice. In addition, the voice data providing unit 130 may select a base voice by a user to synthesize a voice, or may select a base voice with a predetermined voice. For example, the user may input his /

It can be output to the user's own voice, composing multiple voices,

And the voice is transmitted to the sewing doll robot 100 as a base voice

And the voice of the answer voice file can be outputted by the registered base voice.

1, the wireless communication unit 140 may communicate with an external terminal 300 using at least one of Wi-Fi, Bluetooth, and NFC,

Wireless communication can be performed.

When the NFC communication is NFC-communicated with the NFC reader attached to the sewing robot 100 and the NFC reader installed in the external terminal 300, the NFC communication is performed through the application executed in the external terminal 300, (100) can be controlled.

For example, the stuffed animal robot 100 and the external terminal 300 are in a state in which the NFC communication is connected through the NFC reader. When the application of the external terminal 300 is executed and the 'fairy tale' menu is clicked, When the moving picture is clicked, an answer voice file in which the text is changed to speech in advance is selected, and the answer voice file is transmitted to the voice data providing unit 130 of the stuffed animal robot 100, 130) outputs the answer voice file as a sound.

Referring again to FIG. 1, the sensor unit 150 may detect at least one of a touch sensor and a pulse sensor to detect a body input.

The touch sensor is attached to the head portion of the stuffed animal robot 100, and when the user's touch is recognized, the touch sensor transmits a signal to the controller 110.

The sound supplied from the sound providing unit may be output to the signal transmitted to the controller 110, or the arm may be operated by driving the motor.

The pulse sensor is attached to an arm portion of the sewing robot 100 and is executed when a voice command is given to the user's voice by the voice recognition unit 120. [ When the user holds the arm of the stuffed animal robot 100, the pulse is measured, and the measurement signal is transmitted to the controller 110. The controller 110 controls the controller 110 to generate a voice corresponding to the measurement signal, A sound is output from the voice remover 130 and the user can measure the pulse.

1, the motor of the motor unit 160 is attached to the shoulder of the sewing robot 100. When the controller 110 receives a signal, the motor unit 160 drives the motor based on the received signal. The LED 170 is transmitted to the controller 110 when an LED lighting signal is generated in the sensor unit 150 and the voice recognition server 200. The LED lighting signal is transmitted to the LED lighting signal received from the controller 110 And can be turned on in a corresponding manner.

When the wireless communication unit of the stuffed animal robot 100 and the external terminal 300 of the robot 140 are connected to Wi-Fi, Bluetooth and NFC communication, The input voice file stored in the voice recognition server 200 can be analyzed and stored through the voice recognition program 210 included in the voice recognition server 200. [

Also, an answer voice file is generated based on the analyzed information through the speech recognition program 210, and the generated answer voice file is transmitted to the voice data providing unit 130 of the stuffed animal robot 100, The answerer 130 can output a voice response file by voice.

For example, when the wireless communication unit 140 and the external terminal 300 of the stuffed animal robot 100 are connected to Wi-Fi, Bluetooth, and NFC communication,

If the plush doll robot 100 tells the voice 'what is the weather today', the plush doll

The voice recognition unit 120 of the robot 100 stores the voice as an input voice file,

And transmitted to the speech recognition server 200 through the speech 300.

The input speech file transmitted from the speech recognition server 200 is analyzed through the speech recognition program 210, and the 'Today's weather is minus 4 degrees. A voice file is generated and transmitted to the voice data providing unit 130 of the stuffed animal robot 100. The voice data providing unit 130 sounds an answer voice file to output voice data, .

Referring to FIG. 2, the voice recognition server 200 may include a TTS converter 220 for receiving a scan file including text and converting the text included in the scan file to a voice file.

The TTS conversion unit 220 provides the basic information of the scan file to a user registered in a predetermined space on the network and transmits the first correction applicant who applied for the correction of the error of the voice file corresponding to the basic information And a verification unit that verifies the corrected voice file by receiving the voice file whose correction is completed by the correction applicant, and when the verification of the corrected voice file is completed, Of the sales revenue of the applicant.

Referring to FIG. 3, the scan file including the text is converted into a voice file, and the voice file is sold to explain the occurrence of profit. In the following, the distribution of the profit will be described in detail.

Wherein the TTS conversion unit provides the correction applicant with a (100-X)% (where X represents the contribution of the correction applicant) of the net profit to the predetermined sales quantity of the audio file, (100-X) - (Sales Quantity - Pre-established Sales Quantity))% of the net profit.

In this case, if the percentage ((100-X) - (sales quantity - pre-set sales quantity)) becomes 0% or less, no compensation is provided to the applicant for correction.

Thus, by increasing the initial profit, the applicant can increase the participation in the application for correction, and the manager can increase the profit more as the sales quantity increases, thereby effectively distributing the profit of the applicant and the manager.

For example, if a user registered in a predetermined space on the network is notified of a scan file of a book called 'great pussy', basic information (e.g., title of a book, number of pages of a book, etc.) The error% (e.g., 30%, in this case, the error included in the voice file means the contribution when the correction is completed) included in the voice file is provided, and the user registered in the predetermined space provides the voice file 30% of the speech file and send the original of the speech file containing the 'great shit' scan file and 30% error to the first applicant who applied for the correction of the 30% error of the voice file do.

The original is transmitted to the correction applicant, and when the correction applicant completes correcting the error of the voice file including the 30% error, the voice file having corrected the error is transmitted to the voice recognition server 200.

When the verification is completed, the voice recognition server (200) notifies the voice recognition server (200) of the voice file that the voice recognition server (200) corrects the error and informs another user registered in a predetermined space on the network When the user purchases and reproduces an audio file, the sound is output from the sewing robot 100 and the external terminal 300.

And provides the correction applicant with a predetermined portion of the net profit generated in the sales process of the error-corrected voice file.

The correction applicant who corrected the 30% error provides 70 (100-30%) of the net profit up to 10 of the sales quantity of the error-corrected voice file, and ((100 -30) - (sales quantity-10))%.

As another example, if the sales volume of the voice file compensated for the 30% error is 25, the error compensated user provides 55 ((100-30) - (25-10))% of the net profit.

Here, if the sales quantity is more than 125 and becomes 0%, the compensation applicant does not provide profit.

In addition, the speech recognition server 200 may extract the word when a preset word is included in the input speech file received from the speech recognition unit 120, generate information based on the extracted word, And generate an answer voice file by analyzing based on the generated information.

For example, if the user speaks a voice 'promise tomorrow at 12 o'clock', the stuffed animal robot 100 generates an input voice file based on the voice and transmits it to the voice recognition server 200, 'Tomorrow', '12 o'clock', and 'appointment' of the input voice file are extracted and stored in the server 200.

When the user speaks a voice 'Tell me a schedule tomorrow', the speech recognition server 200 generates an answer voice file, reflects the extracted and stored information, and the 'tomorrow schedule has an appointment at 12 o'clock.' And sends the answer voice file to the voice data providing unit 130 of the stuffed animal robot 100 and outputs the answer voice to the user so that the user can recognize the schedule for tomorrow.

1, the external terminal 300 receives a signal of the stuffed animal robot 100 from the wireless communication unit 140 of the stuffed animal robot 100,

The mobile communication terminal 200 provides the mobile contents using the received signal,

The doll robot 100 can relay the communication.

Referring to FIG. 4, the mobile contents include a function of expressing the representation of the mobile robot 100 in the form of animation through an application, a function of moving the mouth of the robot character to the sewing robot, outputting a voice file, When the doll robot character is touched, the stuffed toy robot 100 can perform at least one of the functions of outputting sound, driving the motor and flashing LEDs, and providing a learning content by executing the application .

For example, when a user speaks a voice, an input voice file based on the voice is analyzed by the voice recognition server 200 to select an emotion, and the selected emotion is transmitted to the application of the external terminal 300 And displays a facial expression matching the emotion on the external terminal 300.

As described above, according to the embodiment of the present invention, the present invention can provide a plush dolphin robot having a speech recognition function, which is connected to a server through wireless communication to analyze a user's voice and output a corresponding voice.

Further, when the user's body input is detected, the operation of the robot due to the motor and the LED blink, thereby providing a sewing doll robot having a voice recognition function that can be of interest to the user.

In addition, it is possible to provide a plush dolphin robot having a speech recognition function that allows a user to provide various contents by converting a file including a text into a voice file and correcting an error occurring during the conversion.

In addition, by providing mobile contents composed of a stuffed toy robot character connected to an external terminal, it is possible to provide a stuffed toy robot having a voice recognition function, which can be of interest to a child user.

The control method of the sewing robot having the speech recognition function according to an embodiment of the present invention may be recorded in a computer-readable medium including program instructions for performing various computer-implemented operations. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The media may be program instructions that are specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is clearly understood that the same is by way of illustration and example only and is not to be construed as limiting the scope of the invention as defined by the appended claims. Various modifications and variations are possible in light of the above teachings. Accordingly, it is to be understood that one embodiment of the present invention should be understood only by the appended claims, and all equivalent or equivalent variations thereof are included in the scope of the present invention.

100: Plush doll robot

110:

120:

130:

140:

150:

160:

170: LED (LED)

200: voice recognition server

210: Speech recognition program

220: TTS conversion section

300: User terminal

Claims

A controller for performing an action corresponding to a command input of a user;

Storing the voice of the user as an input voice file,

The control unit transmits the input voice file to the control unit,

If the preset voice command is not included in the voice of the user,

A speech recognition unit for delivering the speech to a ceremonial server;

The answer voice file corresponding to the input voice file is transmitted from the voice recognition server

And outputting the answer voice file as a sound;

At least one of a touch sensor and a pulse sensor is provided to detect a body input

;

Wi-Fi, Bluetooth, and NFC.

A wireless communication unit for performing wireless communication with an external terminal using the wireless communication unit;

A motor unit for driving a plurality of motors to control movement of the body; And

And an LED (Light Emitting Diode) lighting signal among signals received from the sensor unit and the voice recognition server

If it is determined that the LED is lit,

Di (LED); A robot having a speech recognition function including a robot.
The method according to claim 1,

Wherein the voice providing unit comprises:

Users can combine voices to select a bass voice or a preset voice

A sewing machine having a voice recognition function which can select a base voice

Doll robots.
The method according to claim 1,

The voice recognition server comprises:

A scan file including text is received, and a text included in the scan file is transmitted

And a TTS conversion unit for converting the voice signal into a voice file.

Robot with a stuffed doll.
The method of claim 3,

Wherein the TTS conversion unit comprises:

The basic information of the scan file is transmitted to a user registered in a predetermined space on the network

And an operation of correcting the error of the voice file in accordance with the basic information is defined as Choi

The original of the scan file and the voice file is transmitted to the correction applicant who has applied for the second time,

And a verification unit configured to verify the corrected voice file by receiving the voice file whose correction has been completed by the correction applicant and verify the corrected voice file,

And provides the predetermined portion of the voice to the correction applicant.

Plush dolls robot with function.
5. The method of claim 4,

Wherein the TTS conversion unit comprises:

(100-X)% of the net profit (here,

X represents the contribution of the correction applicant) to the correction applicant,

((100-X) - (sales quantity - the number of sales already set)

) Of the robot is provided with a speech recognition function.