KR20190115517A - Character display device based the artificial intelligent and the display method thereof - Google Patents

Abstract

A character display device based on artificial intelligence and a display method thereof are disclosed. The character display device based on artificial intelligence according to the present invention includes a smart toy, generates text data and a command code corresponding to a sound output from the speaker of an artificial intelligence device, transmits the same to the smart toy, The smart toy displays the received text data as one or more of an emoticon, a symbol, and a character on a display part, and drives an operation execution part to perform an operation corresponding to the command code. This not only expands the way of communication and expression of a fragmentary AI device, but also adds fun. So, the combination of visual elements makes the hearing impaired as well as the general public AI speakers available to expand the consumer base.

Description

Character display device based on artificial intelligence and its display method {CHARACTER DISPLAY DEVICE BASED THE ARTIFICIAL INTELLIGENT AND THE DISPLAY METHOD THEREOF}

The present invention relates to an artificial intelligence speaker, and more particularly, an artificial intelligence speaker capable of visually displaying a recognized content using a display unit by recognizing voice input and output to an artificial intelligence speaker or by driving an operation execution unit. A display device using the same and a display method thereof.

Artificial intelligence speakers (hereinafter referred to as "AI Speakers") communicate with the user by voice using artificial intelligence algorithms.

Using AI speaker, you can easily build a smart home environment by simply controlling voice in your home with voice recognition.

Also, unlike touch-based, voice-based operation is easy to learn and use. It's not uncommon for us to control devices using Siri or S-Voice on smartphones, but voice recognition-based UI platforms are hiding near our lives. It's a UI that can be learned naturally without forcibly learning.

AI speakers are called smart speakers or AI assistants, and are voice command devices with a built-in virtual assistant that provides interactive action and hands-free activation with the help of one or more hot words. It is different from general speakers in that it performs functions such as searching and information.

The main input / output devices of voice recognition-based devices are microphones and speakers. Since AI speaker is composed of only these main devices, there is an advantage in that it can record voice data at all times and accumulate it in a cloud server except using a mute function.

In addition, AI speakers were able to understand what users were saying because “deep learning” allowed machines to learn hundreds of thousands of human everyday languages quickly.

Nevertheless, there are still differences in voice recognition commands, and gaps still occur between input commands and natural language recognition functions.

In addition, you have to ask yourself how you can recognize the sound when you are listening to music or watching TV, when there are other noises and noises, or when the user is far away.

To solve these problems, I tried to improve remote speech recognition rate or use 7 microphones like Amazon, but the same problem still exists.

Such an AI speaker is shown in FIG.

Meanwhile, smart toys have recently been transformed into new forms by combining with various IT technologies.

It is evolving into a new form that responds to people's words or actions or combines with tablets and mobile apps.

Various types of smart toys are being released to the overseas market. First of all, Mattel, famous for Barbie dolls, introduced 'Hello Barbie', a smart toy that enables users to talk to users.

Press the button on the doll and the child speaks, records it, encrypts it, and sends it to the cloud server over the Internet.

On the server, the voice recognition SW analyzed it, selected the appropriate answer, and sent it back to Hello Barbie, so that the child and Barbie could talk to each other.

Smart Toy will continue to develop by combining with various IT technologies such as big data and wearables, and it is expected to be used in various fields in daily life beyond simply play and education.

In addition, if Smart Toy is released as a complex product combined with ICT technologies such as cloud, big data, and artificial intelligence, it can deliver synesthesia information and visual fun, and can be used not only for the general public but also for the hearing impaired. You will be able to expand your scope even further.

In addition, the limitation of recognition and the limitation of expression that AI speakers have may be an area that needs improvement. The vast majority of AI speakers on the market today focus on user communication with servers via microphones and speakers. This situation causes confusion in the process of communicating with the server because the AI speaker does not give accurate feedback as to whether or not the AI speaker is properly receiving the voice of the user's content. In addition, since the voice of the result output from the server according to the delivered content is only staying in the voice through the speaker, it does not draw an active rapport with the user. This limitation of recognition and expression that occurs when a user delivers content and receives a result is a big problem with the current AI speaker.

KR Publication No. 10-2000-0062975 (2002. 05. 03)

Accordingly, the present invention for solving this problem is to display the content data of the artificial intelligence speaker sound as a visual character or the movement of the execution unit through a toy device installed outside the speaker to extend the way of user communication and expression. An object of the present invention is to provide a display device using the artificial intelligence speaker and a display method thereof.

In addition, the present invention provides an artificial intelligence speaker that can enhance and expand the interaction between the user and the artificial intelligence speaker by expressing various expressions of contents that are difficult to be transmitted only by sound, such as emoticons, symbols, characters, actions, gestures, and speed. It is another object of the present invention to provide a display device and a display method thereof.

Characteristic apparatus based on the artificial intelligence according to an embodiment of the present invention for solving the above problems, and has a smart toy that can be displayed on the display window or represented by the operation corresponding to the sound or code output from the artificial intelligence device The artificial intelligence device generates text data and command codes corresponding to sound output from a speaker and transmits the text data to the smart toy, and the text data received by the smart toy is any one of an emoticon, a symbol, and a character on a display unit. It can be achieved by controlling to perform the operation of the operation execution unit, which is displayed as above and represents any one of the body parts as a character with a continuous operation code corresponding to the received command code.

The artificial intelligence device may further include a communication interface for communicating with a server, a content storage unit for storing command code to execute the operation execution unit and text data to be displayed on the display unit, and transmitting the command code and text data to the smart toy. Connections. It may include a device control unit for reading the command code and text data corresponding to the voice data transmitted or received to the server through the communication interface unit in the content storage unit to transmit to the smart toy through the connection unit.

In addition, the display unit is composed of LED, and displays the text data received through the text displayed in the LED color, the motion execution unit that represents any one of the body parts as a character of any of the movement, gesture, or speed of the body part motion One or more augmented content can be displayed.

In addition, the artificial intelligence device determines the command code considering the length of the body part and the angle that can be transformed into three axes by the motion execution unit expressing any one of the body parts as a character, and stores the command code in the content storage unit. Before determining the command code according to the operation code can be configured to continuously extract a continuous code indicating a continuous operation according to the operation type, and to configure the operation code from the extracted continuous code to store in the content storage.

Therefore, according to the display device using the artificial intelligence speaker of the present invention, the communication device and the manner of expression of the fragmentary artificial intelligence speaker by combining an accessory device that adds visual and physical effects to the existing artificial intelligence speaker to the artificial intelligence speaker body It is possible to extend it.

In addition, according to the display device using the artificial intelligence speaker of the present invention, the user can add synesthesia information and visual fun, and can use not only the general public but also the hearing impaired person to expand the area of the consumer group. There is.

In addition, according to the display device using the artificial intelligence speaker of the present invention, it is possible to define the characteristics of the speaker by applying and using the characteristics of the various characters, thereby creating an accessory-oriented business structure, accordingly various character-related companies Can be extended to business items.

In addition, according to the display device using the artificial intelligence speaker of the present invention, the service by connecting to a variety of devices (cleaners, air conditioners, etc.) including artificial intelligence speakers, smart phone accessories, helpers for the hearing impaired, all-sounding AI Can be extended.

In addition, according to the display device using the artificial intelligence speaker of the present invention, there is an effect that can be applied to the digital device accessories, such as smart phones, laptops, devices for the hearing impaired.

In addition, according to the display device using the artificial intelligence speaker of the present invention, the smart functions that the smart toy can have and the part that can be empathized as a toy actively complement and improve the limitation of the recognition and expression of the AI speaker. It can be effective.

1 is a view showing a conventional AI speakers,
2 is a system for driving a display device using the artificial intelligence speaker of the present invention;
3 is a structural diagram of an AI voice interactive interaction,
And
4 is a flowchart illustrating a method of operating a smart toy of the present invention.

The terms or words used in this specification and claims are not to be construed as limiting in their usual or dictionary meanings, and the inventors may properly define the concept of terms in order to best explain their invention in the best way possible. It should be interpreted as meaning and concept corresponding to the technical idea of the present invention.

Throughout the specification, when a part is said to "include" a certain component, it means that it can further include other components, without excluding other components unless specifically stated otherwise. In addition, the terms “… unit”, “… unit”, “module”, “device”, and the like described in the specification mean a unit that processes at least one function or operation, which is implemented by a combination of hardware and / or software. Can be.

The term "and / or" throughout the specification should be understood to include all combinations that can be presented from one or more related items. For example, the meaning of "first item, second item and / or third item" may be given from two or more of the first, second or third items as well as the first, second or third items. Any combination of the possible items.

For each step throughout the specification, an identification code (eg, a, b, c, ...) is used for convenience of description, and the identification code does not limit the order of the steps. Unless the context clearly dictates a particular order, it may occur differently from the stated order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

2 is shown as a system for driving a display device using an artificial intelligence speaker of the present invention, the present invention configures a character display device based on artificial intelligence to the sound or code output from the artificial intelligence device 100 By including a smart toy 200 that can be displayed on the display window or expressed in motion, the contents data of the AI speaker sound is displayed as a character or a movement on a toy device installed outside the speaker, thereby communicating and expressing. It works to extend.

In addition, the artificial intelligence device 100 generates text data and command codes corresponding to the sound output from the speaker or the sound input into the microphone and transmits the generated command data to the smart toy 200. The smart toy 200 receives the received text data. One or more of an emoticon, a symbol, and a character are displayed on the display unit 230, and the command code operates to drive the operation execution unit 240 to perform a corresponding operation.

To this end, the artificial intelligence device 100 includes a communication interface 110 communicating with a cloud server 300, a microphone 130 for receiving a user's voice and transmitting it to the server 300, and a voice transmitted from the server 300. Speaker 140 for outputting data, an output unit 150 for outputting control data for controlling the electronic device, a command code to execute the operation execution unit 240 of the smart toy and the text to be displayed on the display 230 Content storage unit 160 for storing data, and the connection unit 170 for transmitting the command code and text data to the smart toy 200, and transmits or receives to the server 300 through the communication interface 110 And a device controller 120 for reading command codes and text data corresponding to the voice data from the content storage unit 160 and transmitting the command codes and text data to the smart toy 200 through the connection unit 170.

The communication interface 110 may transmit and receive data through various communication methods (web communication, wireless communication, Bluetooth, Zigbee, etc.), but in the present invention, the internet communication communicating with the cloud server 300 through the web is performed. It will be described as communicating with the server 300 through.

The connection unit 170 may communicate with the smart toy 200 using short-range wireless communication such as NFC or Bluetooth, but is configured as a connector to connect the USB.

Accordingly, the device controller 120 may transmit the command code and the text data through the connection unit 170, but may also transmit data only when the USB connector is automatically detected and connected.

The device controller 120 estimates a string that best matches the output voice signal using a sound model estimation technique, extracts text data and command code for the string from the content storage unit 160, and extracts the smart toy ( 200).

In addition, based on the Text to Speech (TTS) technology, it converts the user's voice into text to recognize and execute a command.

Artificial intelligence device 100, such as AI speaker is a person's language is the interface between the device, the microphone 130 is installed in one or more, if possible to be mounted in all directions to enable speech recognition in any direction It is necessary.

The artificial intelligence device is a structure that analyzes and analyzes the voice and then services the final result according thereto. The AI device recognizes the voice, and the recognized voice is transmitted to the server 300 and interpreted and analyzed by the language processor 330. The end result is service through affiliated devices and content.

That is, a typical artificial intelligence device operates by activating a device by a user calling a speaker by voice, recording a user's voice, transmitting a recording file to a server, and responding to a user request.

In this case, the device controller 120 encrypts and transmits the data to the server 300, and receives the encrypted data from the server 300.

Preferably it is encrypted while transmitting the voice file, and once again encrypted while storing this file on the server to be stored securely.

(The blue text below appears as a patent for the AI speaker. Is it necessary to explain the present invention?)-> The basic functions between the server and the AI device are explained. This part makes clear the implementation of the invention, and it does not need to worry as it provides a basis for how the AI device can be operated with the smart toy.)

These artificial intelligence devices can get hands-free information or perform functions by voice only without physical contact, resulting in hands-free and convenient to perform many tasks at the same time. It is possible.

The server 300 of the present invention operates as a cloud server, and operates to process the voice input through the microphone 130 of the artificial intelligence device 100 and output it to the speaker 140 and the output unit 150 again.

That is, the processed voice controls the associated device through the output unit 150, and the content is serviced through the speaker 140.

The cloud server 300 and the artificial intelligence device 100 perform interactive interaction. Interactive interaction is an interaction through interactive operation such as voice or chatbot. The system is called variously by name of interactive agent, artificial intelligence assistant, etc. according to the function and the range of role. Give and take.

The implementation of artificial intelligence requires a server with high specifications. So it costs a lot. But delivering it to the cloud eliminates the need for high-end servers. This is because the processing for the AI implementation takes place in the cloud server. This greatly reduces the cost of building AI, making it easier for anyone to use AI services.

In addition to these benefits, there are two more benefits to applying the cloud. You can get AI services anywhere and at any time, with no hardware constraints.

Cloud server 300 shows the possibility of a new web-based operating system as a web service platform. Cloud servers typically build complex business logic in the form of key service APIs related to simple search, storage, and data management. Because they can get them to use it.

Therefore, the server 300 of the present invention is a cloud computing platform that operates as an AI platform based on artificial intelligence technologies such as 'speech recognition', 'natural language processing', and 'recommendation'. It is responsible for handling user requests through various devices and services such as speakers.

The AI platform is distinguished from AI speakers or AI assistants that operate as an interface between the user and the AI platform.

The actual user's needs are handled on a platform based on cloud computing, and the main technologies that make up the platform have been improved in performance such as 'speech recognition', 'visual recognition', 'natural language processing' and 'recommendation'. AI 'technology. For this reason, these forms are commonly referred to as "artificial intelligence platforms."

For example, the user calls the secretary through the microphone 130 with the call name 'Alexa'. Alexa is ready to listen to the 'tell me the weather today' voice of the user through the microphone 130, the device controller 120 transmits the request to the cloud server 300 through the communication interface 110.

That is, the cloud server 300 operating as an artificial intelligence platform, the DB processor 350 or real-time search for a suitable result according to the understanding and understanding of the user's command in the gesture processor 330, and transmits the weather today to the transmitter 340. When transmitted to the AI device 100 which is an AI speaker, the user hears the weather today through the voice of Alexa to the speaker 140.

As such, the AI platform is the backbone of providing a better understanding of the requests coming from the point of contact with various users such as devices and mobile applications (apps).

The formal feature of the AI platform is a "voice-based user interface." Until now, users have usually interacted with machines using input devices such as mice or keyboards based on displays. After some more time, I talked with the machine by touching it with my fingers. The dialogue between humans and machines is evolving towards the convenience of humans as the level of machines increases. The level of machines is improving dramatically and human efforts to understand them are diminishing.

The devices that symbolize the AI platform are home AI speakers such as Amazon Echo and Google Home. The devices and places where the AI platform can be used aren't limited to speakers or homes. The AI assistant, the interface to the AI platform, is coming into smartphones and is expanding into cars.

The first of the functions of the AI platform of the present invention is music management.

Hands-free, the biggest advantage of AI speakers. Recognize your voice and play music right away.

Second, with AI speakers, not only shopping but also delivery orders, O2O (Online To Offline) will expand even further, and it is expected to enjoy a more convenient life.

Third, running specific apps and services.

SNS as well as messenger. With the ability to manipulate all the features of apps and services by voice, convenience will be even greater.

Fourth, weather information is provided. Know the weather instantly. In addition to the weather, the ability to see the temperature and dust concentration in the room has been added.

Fifth, it is a feature to tell questions & chat.

AI speakers can continue to talk, and if you have any questions, they will answer you immediately.

Sixth, Internet of Things control.

In other words, it is convenient to turn on / off IOT device by connecting with home appliances.

Seventh, smart toy control using visual auditory display.

Connected to the smart toy to display a character or emoticon using the display unit and the corresponding operation is performed through the operation execution unit.

In the present invention, in order for the AI platform to perform these features, the server 300 and the AI device 100 operate to perform a voice interactive interaction.

Voice interactive interaction follows the Voice User Interface (VUI) method, which enables a machine to extract meaning from human voice and enable interaction between human and system based on voice recognition technology.

Referring to the structure diagram of the AI voice interactive interaction of FIG. 3, the voice interactive interaction is a method of processing and responding to a natural language based interaction in real time.

For example, FIG. 3 illustrates a structure of a voice interactive interaction structure in which state changes between a user and a system are used during voice interaction based on a traditional Human Computer Interaction (HCI) structure. Assuming 1: 1 interaction (user: system) structure, it is composed of three stages, 'Wake-up', 'Command', and 'Result'. The 'Wake-up' phase is where the user calls the system through Wake-up Word (WUW). The second 'Command' phase delivers the user's task as a voice command. Finally, the 'Result phase' System response is provided. In the ‘Wake-up’ phase, if the system is connected to power as a stand-by, the user calls the agent through WUW (Call WUW phase).

The WUW is the name of the interactive agent and the persona of the interactive agent that the user feels.

For example, when using Amazon Echo, the system is called through WUW called `` Alexa '' when using Amazon Echo and `` Aria '' when using SK Telecom's NUGU. The user may attempt a voice command for the task after igniting the WUW. The ‘Wake-up’ step is a prerequisite for commanding and is a special step that is not present in other interaction methods. In the system, the dialogue engine recognizes the utterances in real time simultaneously with the user's voice command. The system may also provide feedback that speech is being handled at this stage. The system delivers a variety of answers according to the recognition and processing results. First, the system can deliver a complete answer that can process a task by identifying a user's speech at once. If the complete answer is consistent with the user's intention, the user can end the conversation or try the conversation from the beginning again on another topic. However, if the system misidentifies the user's intentions and provides completion feedback, the user can return to the 'Call WUW' step and attempt to re-ignite, adding to the user's utterance to perform the user's intended task. If there is an element to ask the question, the system can provide additional feedback to identify the elements necessary for task processing. After this feedback, the user can return to the Voice Command step and perform a speech on the question.

Such voice interactive interaction is a human-friendly information input / output method, and most AI interactive services provide natural language-based interactions, so they can be easily used without any knowledge or learning, but the recognition rate for natural language processing is low. It is true.

Therefore, in the present invention, in order to complement the recognition rate of the natural language processing by using smart toys, an accessory device that adds visual and physical effects to the artificial intelligence speaker is combined with the artificial speaker body by a fragmentary method of communication of the artificial speaker It is to expand the way of expression.

To this end, the server 300 analyzes the communication unit 310 for communicating with the artificial intelligence device 100 and the receiver 320 for receiving the request of the artificial intelligence device through the communication unit 310 and the received voice in various ways. A language processing unit 330 for processing the emotions so that the smart toy 200 can express them, a transmitter 340 for transmitting the voice processed by the language processing unit 330 to the smart toy 200 and storing the processed voices DB unit 350 may be included.

The smart toy 200 of the emotional function is preferably configured to have a basic personality (Personality). This property does not change, and the nature of the input accepted is determined by the nature. It is also reflected in the output is expressed in the behavior of the smart toy 200. Input through the microphone 130 is replaced by the emotion (Emotion) is refracted by the interference of the personality and affects the mood (Mood) of the smart toy. The smart toy 200 in which a mood is changed by an input is to output a voice and an action according to the determined mood.

Personality applies the FFM (Five Factor Model). FFM is a personal psychology model that describes human personality with five mutually independent factors. It is composed of openness, sincerity, extroversion, affinity, and nervousness.

The above five factors are numbered from 1 to 5 to define the characteristics of smart toys. In a somewhat inconsistent attitude, they are free-spirited and can provide fun to users through unexpected improvisations, especially when they are excited.

An open and outgoing personality allows people to become friendly with people and responds with tactful and fresh actions to the user's words. On the other hand, the emotions are somewhat unstable, so you can expect various reactions as you frequently travel between the two extremes of personality.

Mood also uses a new mood-type graph that borrows from Russell's “emotional prototype”. The x-axis represents the positive or negative of the emotion. It is a pleasant feeling toward the + direction and an unpleasant feeling toward the-direction. The Y axis represents tension and relaxation. As you go up, you feel nervous or awake, and as you go down, you feel relaxed. It is a graph displaying (-4, -4) to (+ 4, + 4) and shows the range of emotion of smart toy in coordinates. Smart toy coordinates change according to the input emotion (Emotion) and the mood (Mood) is determined according to the position of the coordinates. Mood is a combination of 'excitement', 'brightness', 'happiness', 'satisfaction', 'independence', 'depression', 'misery', 'complaint', and 'moderate', the most common stable state. Nine.

Eight emotions, except ‘normal’, are set as emotions that smart toy accepts, and regardless of any input, smart toy receives it as an input value. By moving the coordinates according to the value, the mood type of the smart toy changes. Each emotion has a unique direction of movement and may have different intensity values, even if different voice and motion inputs are in the same emotion category. Even if the input value is the same, the accepted emotion value may vary according to the current state of the smart toy.

After generating sound wave data corresponding to the control command, the target may be designated to output sound waves so that only the corresponding smart toys may be designated.

In the present invention, the existing server and the artificial intelligence device are used, but the smart toy combined with the artificial intelligence device is capable of displaying a visual or audio expression by supporting the expression.

To this end, the content storage unit 160 of the artificial intelligence device is configured to code the command code and text data by word in Table 1 as shown below, and to correct or add a new by learning.

Command code Text data Command code Text data Command code Text data One Too much 26 So much fun 51 I'm so tired 2 I'm mad 27 Refreshing 52 Too sleepy 3 Honna 28 Cool 53 Not funny 4 Ignore it 29 So funny 54 I'm worried 5 I'm a bad boy. 30 I'm so excited 55 I hate it all 6 Yaibaboya 31 Good good 56 I'm hungry 7 you idiot 32 I am so happy 57 So upset 8 Don't blame 33 I will save you 58 I don't want to eat 9 I hate you 34 Good mood 59 Too bad 10 Miraculous 35 So happy 60 It's bad. 11 Look at this 36 It's okay now 61 Want to cry 12 I wonder 37 I understand you 62 Too sad 13 let's work hard 38 It's easy 63 I do not need 14 Really good 39 I need you 64 Now it's clear 15 Too excited 40 It'll turn out okay 65 Stop it 16 So scary 41 Very good 66 Quiet 17 nervous 42 No problem 67 I'm not playing with you 18 Fighting cheers 43 Thank you so much 68 Hate it 19 Wake 44 I trust you 69 So noisy 20 exciting 45 Let's take a minute 70 Go away 21 What to do 46 Let's calm down 22 shall we start 47 Don't get excited 23 Departure 48 do not be angry 24 Funny 49 do not want to do it 25 Awesome 50 Please forgive

The command code and the text data are transmitted to the smart toy 200 and displayed on the display 230 as a character, a symbol, an icon, and the like, and the operation execution unit 240 may continuously execute the operation on the corresponding code.

For example, the display 230 displays a corresponding command and transmits and displays any one of the emotion icons as shown in FIG. 1 below.

 [Figure 1]

In addition, as shown in Table 2, if the motion execution unit of the smart toy is made up of the hands of the body part, the following emotional expressions may be executed and may be implemented in a continuous operation.

command Gesture command Gesture anger Frustration Passion depressed aggro Cheerfulness tranquility Excitement Crush Happiness

The smart toy 200 according to the command code receiver 220 for receiving text data and command codes and the text data received by the command code receiver 220 in order to supplement the power of the artificial intelligence device visually and visually A display unit 230 for displaying at least one of an emoticon, a symbol, and a character; an operation execution unit 240 driven according to a received command code; a user app unit 250 storing an application related to the present invention; And it comprises a storage unit 260.

The motion execution unit 240 is composed of a character shaped any part of the body part.

For example, it can be composed of a character that embodies hands, head, legs, or body. In the case of hands, changing the shape and speed of the hand as shown in Fig. 2 will allow expression of various emotions along with the expression of a doctor.

The smart toy 200 may be electrically connected to the artificial intelligence device 100 to receive text data and a command code, or may be spaced apart from each other.

Electrically connected means that two devices are directly connected to each other through a USB connector, and the like is not limited to wires.

In addition, the smart toy 200 may be configured to bind the artificial intelligence device in a band-like shape or be provided in a character shape on one side of the artificial intelligence device in order to be coupled to the artificial intelligence device to operate integrally.

Eventually, the smart toy 200 displays one or more of emoticons, symbols, and characters on the display 230 according to text data and command codes transmitted from an artificial intelligence device such as an artificial intelligence speaker, and an operation execution unit 240. By transmitting the information through the loudspeaker output of the AI device, or by enhancing and extending the interaction with the AI speaker, the emotion can be expressed instead.

To this end, the display unit 230 is composed of LED, and displays the information received by the color of the LED or the displayed text, and the operation execution unit is composed of any one of the body parts of the character of the body part, It is possible to express various emotions included in the contents by displaying information to be expressed by movement, position change, gesture, or speed control.

For example, "^^, ㅋㅋ, ㅎㅎ, ㅍ, haha, hihi, hoho" can be displayed as a joy, and "tsu, black, whit, hing" can be expressed as sadness.

Therefore, when the command code is received from the artificial intelligence device in the storage unit 260, the control unit 210 stores an operation code consisting of a continuous code for continuously moving the command code, and if the command code is received, the command When the operation code corresponding to the code is read from the storage unit 260 to drive the operation execution unit 240, the operation execution unit may perform a continuous operation.

In addition, the storage unit 260 may continuously determine and store an operation code considering the length of the characterized body part and an angle that may be deformed in three axes.

In addition, if the operation execution unit 240 to drive the arm can be configured to be driven as the actual motion of the arm by configuring a small motor and joints, tendons and the like.

In addition, by configuring the user app unit 250 for storing the application for driving the artificial intelligence-based character display device of the present invention can be corrected through the terminal 400.

The application is configured to download and store the related app through an app store or the like or to download and install the application by accessing the web server 300 through a mobile communication network.

Preferably, the application may be installed through the authentication process of the server in the installation process of the app.

That is, the present invention may download and install an app by accessing the server 300 operated as a website, but may use a method of distributing an app suitable for each OS on an app store regardless of whether it is an IOS system or an Android system. .

Since the download and installation process and authentication step of the app (App) is a general thing, a detailed description thereof will be omitted.

In the present invention, the application mounted on the smart toy 200 is a display unit 410 for displaying an application for driving an artificial intelligence-based character display device related to the present invention stored in the user app unit 420 of the portable terminal 400 in the future. It can be configured to upgrade content by adding or changing information about text data and operation code.

For example, by adjusting the scale, the direction, etc. according to the character represented by any one of the body parts to continuously determine and store the operation code considering the length of the body part and the angle that can be transformed into three axes.

In the above description, the smart toy performs the display or operation corresponding to the content to be output to the speaker by the artificial intelligence device, but the present invention is not limited thereto, and the voice data received through the microphone of the artificial intelligence device is not limited thereto. Of course, the same configuration and function can be expressed.

That is, when a voice by an external user is received through the microphone 130 of the artificial intelligence device, the device controller 120 selects text data and command codes related to the voice from the content storage unit 160 stored in Table 1 The display unit 230 and the operation execution unit 240 are operated by transmitting to the smart toy 200.

Of course, the display 230 may not only display the text data transmitted from the server 300 according to the user's selection, but also display the user's voice as a stream.

The smart toy driving method of the present invention will be described using the above configuration.

4 is a flowchart illustrating a method for operating a smart toy of the present invention, as shown, by transmitting the data to the smart toy 200 when an event occurs in the artificial intelligence device 100 that operates as an artificial speaker Be able to express visually and aurally.

In addition, a detailed description of data transmission and reception for operating as a general artificial intelligence speaker between the artificial intelligence device 100 and the server 300 will be omitted.

First, the artificial intelligence device 100 is configured to code the command code and text data for each word in the content storage unit 160 by word through learning and investigation, and to correct or add new words by learning ( S110).

After the text data and the command code are stored in the content storage unit 160 in step S110, the device controller 120 determines whether an event has occurred through the microphone 130 and the speaker 140 (S120).

Here, the event means that the voice is input or output through the microphone 130 and the speaker 140, and may include a message guided by the server 300.

If it is determined in step S120 that the event has occurred, the device controller 120 searches in the content storage unit 160 for text data and command codes associated with words included in the corresponding voice (S130).

During the search, the event is detected, or before and after sending the command code to the smart toy 200 or at the same time the event occurred to the speaker 140 (S140), the searched dex data and command code is a smart toy (200) To be sent through the connection unit 170 (S150).

In operation S150, when the text data and the command code are received from the AI device 100, the smart toy 200 controls the display unit 230 and the operation execution unit 240 to display characters using the text data and the command code. Or to perform a moving operation (S210).

Specifically, in step S210 to display any one or more of emoticons, symbols, and characters on the display 230 using the received text data.

In addition, the control unit 210 extracts an operation code consisting of the associated continuous code stored in the storage unit 260 so that the character can continuously operate using the received command code, the operation execution unit 240 continuously It's moving.

As described above, the artificial intelligence-based character display device and its display method of the present invention can extend the service by connecting to an artificial speaker, a smart phone accessory, a helper for the hearing impaired, and a device that generates all sounds. This can be applied to a variety of devices (cleaners, air conditioners, etc.) included.

While the invention has been described in detail with respect to the described embodiments, it will be apparent to those skilled in the art that various modifications and variations are possible within the spirit of the invention, and such modifications and variations belong to the appended claims.

100: artificial intelligence device 110: communication interface unit
120: device control unit 130: microphone
140: speaker 150: output unit
160: content storage unit 170: connection unit
200: smart toy 210: control unit
220: command code receiving unit 230: display unit
240: operation execution unit 300: server
400: terminal

Claims (7)

An artificial intelligence-based character display device having a smart toy that can be displayed on a display device or represented by an action in response to a sound or a code output from an artificial intelligence device,
The artificial intelligence device generates text data and command codes corresponding to the sound output from the speaker and transmits the same to the smart toy.
The smart toy
Display the received text data on the display as one or more of emoticons, symbols, and characters, and at the same time, the action executing unit expressing any one of the body parts as a character with a continuous action code corresponding to the received command code. AI based character display device to control.
The method of claim 1,
The artificial intelligence device
Communication interface unit for communicating with the server;
A content storage unit for storing command code to execute the operation execution unit and text data to be displayed on the display unit;
A connection unit for transmitting the command code and text data to the smart toy;
A device control unit for reading command codes and text data corresponding to voice data transmitted or received to a server through the communication interface unit from the content storage unit and transmitting the command code and text data to the smart toy through the connection unit;
AI-based character display device further comprising.
The method of claim 2,
The display unit is composed of LEDs, and displays the text data received through the text displayed by the LED color, the motion execution unit representing any one of the body parts as a character any one of the movement, gesture, or speed of the body part motion Artificial intelligence-based character information display device for displaying the above augmented content.
The method of claim 2,
The artificial intelligence device
An artificial intelligence-based character information display device for determining a command code considering a length of the body part and an angle that can be deformed into three axes and storing the command code in the content storage unit.
The method of claim 1,
The smart toy
When receiving the command code from the artificial intelligence device, according to the operation type to extract a code indicating a continuous operation in the storage unit continuously, the artificial code to control the operation execution unit by configuring the operation code from the extracted continuous code Intelligence based character display device.
(a) selecting command data for controlling text data and movement to be visually displayed according to the voice detected from the artificial intelligence speaker;
(b) displaying at least one of an emoticon, a symbol, and a character on the display unit with the text data selected in step (a); and
(c) controlling the operation execution unit which expresses any one of the body parts as a character to perform the operation using the command code selected in the step (a);
Motion display method using an artificial intelligence speaker comprising a.
The method of claim 6,
Step (c) is
Before deciding the command code according to the operation type
An artificial intelligence-based character display method of continuously extracting a code representing a continuous motion according to a corresponding motion type, and configuring the motion code using the extracted continuous code to control the motion execution unit to perform the motion.