KR102181583B1 - System for voice recognition of interactive robot and the method therof - Google Patents

Abstract

The present invention discloses a voice recognition sympathetic robot, a sympathetic robot voice recognition system, and a method thereof. The voice recognition system of a sympathetic robot according to an embodiment of the present invention includes a voice data receiving unit receiving voice data transmitted from an external terminal, a text conversion unit converting the voice data into text, and a keyword from the converted text. A keyword extraction unit for extracting, a response text generation unit for extracting a response text corresponding to the extracted keyword from pre-stored metadata, a voice conversion unit for converting the response text into speech data, and the converted speech data to the external It may include a transmitter for transmitting to the terminal.
The sympathetic robot according to an embodiment of the present invention includes a voice recognition button part receiving a command for starting a voice input through button manipulation, a voice input part receiving a voice uttered from a user, and recording data of the input voice. And a voice transmission unit for transmitting the PCM data to an external system and a voice output unit for receiving and outputting response data from the external system.

Description

Voice recognition sympathetic robot, sympathetic robot voice recognition system and its method {SYSTEM FOR VOICE RECOGNITION OF INTERACTIVE ROBOT AND THE METHOD THEROF}

The present invention relates to a voice recognition sympathetic robot, a voice recognition system and a method for the sympathetic robot, and more particularly, to a system and method for recognizing a user's voice through a sympathetic robot and generating a corresponding event. About.

Robots, dolls, etc. that can communicate with users play an important role in education, such as development of physical movements and functions, and development of intelligence through the development of imagination or creativity. Technology development is receiving great attention.

However, since the existing robot or doll outputs a limited sound or does not have a motion, it is difficult to continuously draw new interest and interest from the user.

Accordingly, there is a need for a study on a robot and a speech recognition system capable of recognizing and responding to the user's voice, but identifying the user's intention from the user's voice input and expressing a corresponding response.

Prior art literature: Korean Patent Registration No. 10-1791942

The present invention minimizes the processing power of the voice recognition sympathetic robot by receiving the user's voice through the voice recognition sympathetic robot and transmitting it to the server to analyze the user's voice and output the corresponding response voice, It provides a voice recognition sympathetic robot, a sympathetic robot voice recognition system, and a method that can reduce cost.

The present invention transmits and processes the voice input to the voice recognition sympathetic robot to the server, but by adjusting the MTU (Maximum Transmission Unit) unit to divide and transmit data, high-speed voice recognition is possible while using relatively low-spec hardware. It provides a voice recognition sympathetic robot, a sympathetic robot voice recognition system, and a method thereof.

The present invention is connected to a server through wireless communication, analyzes a voice specific to each user, and outputs a corresponding voice, so that a voice recognition sympathetic robot capable of more accurate voice recognition according to characteristics such as language habits of individual users, Provides a robotic voice recognition system and method thereof.

The present invention converts the input voice into text and extracts a keyword from the text, but by extracting the similar word and category attribute of the extracted keyword, speech recognition capable of more effectively generating a response text corresponding to the similar word and category attribute A sympathetic robot, a sympathetic robot voice recognition system, and a method thereof are provided.

The voice recognition system of a sympathetic robot according to an embodiment of the present invention includes a voice data receiving unit receiving voice data transmitted from an external terminal, a text conversion unit converting the voice data into text, and a keyword from the converted text. A keyword extraction unit for extracting, a response text generation unit for extracting a response text corresponding to the extracted keyword from pre-stored metadata, a voice conversion unit for converting the response text into speech data, and the converted speech data to the external It may include a transmitter for transmitting to the terminal.

According to an aspect of the present invention, it may further include a user management unit for receiving a primary key identifying a user of the external terminal and reading a setting value corresponding to the unique key.

According to an aspect of the present invention, the keyword extraction unit extracts a plurality of nouns present in the converted text, generates a set of similar words of the noun, and matches the extracted noun category to a preset category. Thus, a similar word set and category attribute may be assigned to each extracted keyword.

According to an aspect of the present invention, the response text generation unit extracts a set of related question lists corresponding to a set of similar words and a category attribute of each of the extracted keywords, and extracts a common question between the question lists, Response text can be generated.

The sympathetic robot according to an embodiment of the present invention includes a voice recognition button part receiving a command for starting a voice input through button manipulation, a voice input part receiving a voice uttered from a user, and recording data of the input voice. And a voice transmission unit for transmitting the PCM data to an external system and a voice output unit for receiving and outputting response data from the external system.

According to one aspect of the present invention, the output unit checks whether the delay value of each register of the voice codec is 0, and if it is not 0, it corresponds to the delay value of each register by calling a delay function for waiting for the setting operation of the voice codec. You can give it a waiting time.

The voice recognition method of a sympathetic robot according to an embodiment of the present invention includes the steps of receiving voice data transmitted from an external terminal, converting the voice data into text, extracting keywords from the converted text, And extracting a response text corresponding to the extracted keyword from pre-stored metadata, converting the response text into voice data, and transmitting the converted voice data to the external terminal.

According to an embodiment of the present invention, by receiving a user's voice through a voice recognition sympathetic robot and transmitting it to a server, the server analyzes the user's voice and outputs a corresponding response voice. A voice recognition sympathetic robot, a sympathetic robot voice recognition system, and a method thereof that can minimize processing power and reduce costs are provided.

According to an embodiment of the present invention, the voice input to the voice recognition sympathetic robot is transmitted to a server and processed, but data is divided and transmitted by adjusting the MTU (Maximum Transmission Unit) unit, so that relatively low-spec hardware is used. A voice recognition sympathetic robot, a sympathetic robot voice recognition system, and a method thereof that enable high-speed voice recognition are provided.

According to an embodiment of the present invention, by connecting to a server through wireless communication, analyzing a voice specific to each user and outputting a corresponding voice, more accurate voice recognition is possible in accordance with characteristics such as language habits of individual users. A sympathetic robot, a sympathetic robot voice recognition system, and a method thereof are provided.

According to an embodiment of the present invention, by converting the input voice into text and extracting a keyword from the text, and extracting the similar word and category attribute of the extracted keyword, the response text corresponding to the similar word and the category attribute is more effectively A voice recognition sympathetic robot, a sympathetic robot voice recognition system, and a method thereof that can be generated are provided.

1 is a diagram showing a system for generating an event for voice recognition by receiving a voice through a voice recognition sympathetic robot according to an embodiment of the present invention and transmitting the voice to the sympathetic robot voice recognition system and the overall configuration of the robot .
2 is a block diagram showing a detailed configuration of a sympathetic robot voice recognition system according to an embodiment of the present invention.
3 is a block diagram showing a detailed configuration of a voice recognition sympathetic robot according to an embodiment of the present invention.
4 is an operation flow diagram showing the flow of a sympathetic robot voice recognition method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the contents described in the accompanying drawings. However, the present invention is not limited or limited by the embodiments. The same reference numerals in each drawing indicate the same member.

Conventionally, the technology of recognizing a user's voice through a robot or a doll and outputting a response message to it has not been able to accurately grasp the intention of a user's question through the user's voice. There was a problem.

The present invention is an invention devised to solve the problems of the prior art, and the configuration of the present invention will be described in detail below.

1 is a diagram showing a system for generating an event for voice recognition by receiving a voice through a voice recognition sympathetic robot according to an embodiment of the present invention and transmitting the voice to the sympathetic robot voice recognition system and the overall configuration of the robot .

Referring to FIG. 1, after preparing a procedure for the voice recognition sympathetic robot 200 to communicate with the agent server with the connected smart device 300, the user greets, questions, and emotions through the voice recognition sympathetic robot 200. When an expression message or the like is input through voice, the input voice data may be transmitted to the robot voice recognition system 100.

Thereafter, the robot voice recognition system 100 converts the voice data into text, extracts the keyword, generates a response text corresponding to the extracted keyword, and transmits it to the voice recognition sympathetic robot 200, The recognition sympathetic robot 200 may communicate with the user by outputting it through a speaker or the like.

At this time, the user may input a voice through the voice recognition sympathetic robot 200, and the response voice may be confirmed through the voice recognition sympathetic robot 200.

Hereinafter, detailed procedures and configurations for inputting voice and generating a response text corresponding thereto will be described in more detail.

2 is a block diagram showing a detailed configuration of a sympathetic robot voice recognition system according to an embodiment of the present invention.

Referring to FIG. 2, the sympathetic robot speech recognition system 100 includes a voice data receiving unit 110, a text conversion unit 120, a keyword extraction unit 130, a response text generation unit 140, and a voice conversion unit 150. ) And a transmitter 160.

The voice data receiver 110 may receive voice data transmitted from an external terminal. That is, when the user's voice is recognized through the sympathetic robot 200 or the smart device 300 connected thereto, the voice data receiving unit 110 may receive and receive the received voice.

At this time, the received voice data may be various types of data including PCM data.

As an example, the sympathetic robot 200 may use Artik053. When the Artik053 recognizes the user's voice, it is transmitted to the voice data receiver 110, and the voice data transmitted in this process is equal to or greater than the set MTU value. In this case, a high-speed voice recognition can be supported even through the sympathetic robot 200 using relatively low-spec hardware (ex. Artik053) as described above by being divided into several packets and transmitted.

In addition, since the SDK for using the API service cannot be installed on low-end hardware such as Artik053, if the voice data is divided into small packets as described above and transmitted, the part processed as microphone input in the existing STT API is communicated as above. The received voice data can be converted into a received format and used, and through this, a streaming service for quickly converting voice into text can be provided even in low-end hardware such as an embodiment of the present invention.

After receiving the voice data, the text conversion unit 120 may convert the voice data into text. At this time, since the sympathetic robot voice recognition system 100 has different language habits for each individual use, it receives a primary key that identifies the user of the external terminal to suit the characteristics of the individual user, and the unique key A user management unit may be further included to read a setting value corresponding to.

That is, by varying set values for voice recognition and text conversion for each user and performing a process of voice recognition and text conversion optimized for individual users, user-customized voice recognition can be achieved.

Meanwhile, in the STT (Speech to Text) process for converting speech to text, you can use APIs supported through the cloud, recognize more than 120 languages and dialects, and use machine learning technology to real-time streaming or pre-recording. Audio can be processed.

When the voice data is converted into text in the above, the keyword extracting unit 130 may extract a key keyword from the converted text.

To this end, a plurality of nouns present in the converted text are extracted, a similar word set of the noun is generated, and the extracted noun category is matched with a preset category, Category attribute can be assigned.

As an example, if the sentence entered by the user is "I'm going on a picnic tomorrow", the nouns'tomorrow' and'excursion' included in the sentence are extracted, and'tomorrow','next day', which are similar words for'tomorrow' , And'the next day', etc., a set of similar words is extracted, and'tomorrow' is a word representing time, so'time word' can be assigned as a category attribute.

Also, in the case of'excursion', a set of similar words such as'picnic','outing', and'outing party', which are similar words, is extracted, and'excursion' is a word representing outdoor behavior, so'outdoor behavior' as a category attribute. You can give it a word.

Accordingly, by using the similar word set and category attribute for the keyword, the response text generator 140, which will be described below, can more accurately identify the user's intention and derive a response text corresponding thereto.

Accordingly, in connection with this, the response text generator 140 may extract a response text corresponding to the extracted keyword from pre-stored metadata.

To this end, the response text generation unit 140 extracts a set of related question lists in correspondence with a set of similar words and a category attribute of each of the extracted keywords, and extracts a common question between the question lists to obtain the response text. Can be created.

As an example, if 5 questions are included in a question list set related to the extracted keyword'tomorrow' and 7 questions are included in a question list set related to'excursion', the contents overlap as much as possible in the two question list sets. You can extract a question and decide it as a text to answer to the user.

Accordingly, the voice conversion unit 150 may convert the determined response text into voice data.

Here, in the TTS (Text to Speech) process for converting text to speech, a deep learning technology is used to synthesize sounds like a real human voice, and various languages and voices can be set, and the user's Voices can be generated in a form similar to language habits, and can be generated by reflecting pronunciation of specific words according to user-specified words or stored terms (company name, acronyms, foreign words, new words, etc.).

The transmitter 160 may transmit the converted voice data to the external terminal. In this case, the transmitted data may be transmitted in various formats including MP3 format.

As described above, by recognizing the voice using the sympathetic robot voice recognition system and generating the corresponding response text, individual user-customized voice recognition and response text can be generated, and the user's intention is more accurately identified and Effects can occur that can provide a response.

Hereinafter, a configuration in which a voice is input through a voice recognition sympathetic robot, transmits it to a sympathetic robot voice recognition system, and a configuration for receiving and outputting a response text (voice converted data) from the sympathetic robot voice recognition system will be described in more detail. do.

3 is a block diagram showing a detailed configuration of a voice recognition sympathetic robot according to an embodiment of the present invention. At this time, the voice recognition sympathetic robot 200 may, for example, incorporate an ARTIK053 board.

Referring to FIG. 3, the voice recognition sympathetic robot 200 may include a voice recognition button unit 210, a voice input unit 220, a voice transmission unit 230, and a voice output unit 240.

The voice recognition button unit 210 may receive a command for starting a voice input through button manipulation. That is, in the conventional case, voice input is initiated by sensing sound through a smart speaker, but in one embodiment of the present invention, voice input is initiated only when the user operates a button. Since the user's voice conversation is not monitored until it is done, the conversation content can be recorded regardless of the user's intention and managed so that it is not leaked to a third party.

The button is located on the hand part of the sympathetic robot, and by providing the sensibility to hold the robot's hand when the button is operated, the user can be set to feel more sympathetic with the robot.

The voice input unit 220 receives a voice uttered from a user, and when voice input is started through the voice recognition button, the user's voice may be input through a microphone input or the like.

The voice transmission unit 230 may transmit the recorded data of the input voice to an external system in the form of PCM data. That is, by transmitting data in the form of PCM data, data can be transmitted more effectively and without loss.

On the other hand, voice transmission is the maximum datagram size value that can be sent without a segment on the network interface, and it can be transmitted by setting the MTU size, which is the maximum size that a packet can send at one time, to 590. Since it can be divided into packets and transmitted, data can be transmitted more effectively.

When receiving response data in the form of voice data from the external system, the voice output unit 240 may output response data so that the user can recognize it through an output device such as a speaker.

Meanwhile, the audio output unit 240 may use the following method in order to minimize a delay that occurs when setting a codec used for audio output.

In the process of setting the codec register before using the codec, the delay function is called to wait for the codec setting operation to have a waiting time as much as script[i].delay. Actually, if the value of script[i].delay is 0, the delay function is called. There are many. Therefore, to prevent the delay according to the time of calling the script[i].delay function itself, check whether the script[i].delay value of each register is 0, and only if it is not 0, the script for waiting for the setting operation of the voice codec By calling the [i].delay function, a waiting time corresponding to the delay value of each register can be given. Here, the member of script[i] is the register address, and script[i].delay corresponds to the delay value of each register.

As described above, through the sympathetic robot according to an embodiment of the present invention, a device capable of minimizing the processing power of the voice recognition sympathetic robot and reducing costs may be provided.

4 is an operation flow diagram showing the flow of a sympathetic robot voice recognition method according to an embodiment of the present invention.

Meanwhile, in the following description, the voice recognition sympathetic robot 200 includes an ARTIK053 board and communicates with the voice recognition system 100 of the sympathetic robot through socket communication as an example.

To this end, in step 410, voice data transmitted from an external terminal may be received.

That is, when the client (ARITK053) connects to the voice recognition system 100 server of the sympathetic robot through socket communication with the ARTIK053 board, User_info_check() is executed for user identification, and the user selects a primary key with a unique value. It can be distinguished through.

If the client information is passed along with the action_thread() call, the user's voice data (PCM data) can be imported to the server using the google_cloud_streaming() operation using the corresponding client socket.

Next, in step 420, the voice data may be converted into text. At this time, it can be converted to text through the Google cloud streaming Speech To Text API.

In step 430, a keyword may be extracted from the converted text, and in step 440, a response text corresponding to the extracted keyword may be extracted from pre-stored metadata.

In step 450, the response text may be converted into voice data, and in step 460, the converted voice data may be transmitted to the external terminal.

For this, the response text is created as 1-Chenal, Mono, 22050HZ mp3 file using AWS Polly Text To Speech API, and the corresponding mp3 file is converted to 2-Channel Stereo 44000HZ using FFmpeg module and delivered to the ARTIK053 board. Can proceed.

As described above, according to an embodiment of the present invention, by receiving the user's voice through the voice recognition sympathetic robot and sending it to the server, the server analyzes the user's voice and outputs a corresponding response voice, Provided are a voice recognition sympathetic robot, a sympathetic robot voice recognition system, and a method for minimizing the processing power of the robot type and reducing costs.

According to an embodiment of the present invention, by connecting to a server through wireless communication, analyzing a voice specific to each user and outputting a corresponding voice, more accurate voice recognition is possible in accordance with characteristics such as language habits of individual users. A sympathetic robot, a sympathetic robot voice recognition system, and a method thereof are provided.

According to an embodiment of the present invention, by converting the input voice into text and extracting a keyword from the text, and extracting the similar word and category attribute of the extracted keyword, the response text corresponding to the similar word and the category attribute is more effectively A voice recognition sympathetic robot, a sympathetic robot voice recognition system, and a method thereof that can be generated are provided.

In addition, according to an embodiment of the present invention, low power consumption and light weight are used to facilitate portability, significantly lower initial cost, and allow users to receive high-speed voice recognition services while on the move. Can be.

In addition, the sympathetic robot voice recognition method according to an embodiment of the present invention may be recorded in a computer-readable medium including program instructions for performing operations implemented by various computers. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The medium may be a program instruction specially designed and configured for the present invention, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of the program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, although an embodiment of the present invention has been described by a limited embodiment and drawings, an embodiment of the present invention is not limited to the above-described embodiment, which is a common knowledge in the field to which the present invention belongs. Anyone who has it can make various modifications and variations from these substrates. Accordingly, one embodiment of the present invention should be grasped only by the claims set forth below, and all equivalent or equivalent modifications thereof will be said to belong to the scope of the inventive concept.

100: sympathetic robot voice recognition system
110: voice data receiver
120: text conversion unit
130: keyword extraction unit
140: response text generator
150: voice conversion unit
160: transmitter
200: sympathetic robot
210: voice recognition button unit
220: voice input unit
230: voice transmission unit
240: audio output unit

Claims (7)

A voice data receiving unit for receiving voice data transmitted from an external terminal;
A text conversion unit converting the voice data into text;
A keyword extraction unit for extracting a keyword from the converted text;
A response text generator for extracting a response text corresponding to the extracted keyword from pre-stored metadata;
A voice conversion unit converting the response text into voice data;
A transmitter for transmitting the converted voice data to the external terminal; And
User management unit for receiving a primary key identifying a user of the external terminal and reading a set value corresponding to the unique key
Including,
The keyword extraction unit,
Extracting a plurality of nouns present in the converted text,
Generate a set of similar words of the noun, and match the extracted category of the noun with a preset category,
For each extracted keyword, a similar word set and category attribute are assigned,
The response text generation unit,
Each extracted question list set corresponding to the similar word set and category attribute of each of the extracted keywords is extracted, and the response text is generated by extracting a common question between the question lists,
The external terminal,
A voice recognition button unit receiving a command for starting voice input through button manipulation;
A voice input unit receiving a voice spoken by a user;
A voice transmission unit that transmits the recorded data of the input voice to an external system in the form of PCM data, and divides and transmits the data in a predetermined MTU unit; And
An audio output unit for receiving and outputting response data from the external system;
Including,
The output unit,
Check if the delay value of each register of the voice codec included in the response data is 0, and if it is not 0, call a delay function to wait for the setting operation of the voice codec to give a waiting time corresponding to the delay value of each register. Voice recognition system of a sympathetic robot, characterized in that. delete delete delete delete delete delete

Images