KR20190066116A - Dialogue processing apparatus, vehicle having the same - Google Patents

Abstract

According to one embodiment of the present invention, a dialogue system may comprise: an output unit outputting voice; a sensing unit sensing a state of a user; and a control unit providing second utterance generated based on information for the user to the user through the output unit when a response of the user corresponding to first utterance provided to the user is included in a predetermined first reference. According to one embodiment of the present invention, the dialogue system more suitable for taste of the user may be provided by classifying the response of the user corresponding to the utterance provided to the user into various criteria and providing various subsequent utterances according to the situation based on the information for the user and classified information.

Description

{DIALOGUE PROCESSING APPARATUS, VEHICLE HAVING THE SAME}

The present invention relates to an interactive system and a method for a vehicle including the same, and more particularly to a method for providing a variety of subsequent utterances based on a user's response corresponding to a utterance provided to a user in a utterance system with a user of the vehicle Technology invention.

In modern society, automobiles are the most common means of transportation and the number of people using them is increasing. Due to the development of automobile technology, there are many changes in life such as easy movement of long distance and ease of life.

Many electronic devices such as a hands-free device, a GPS receiver, a Bluetooth device, and a high-pass device have been developed for the convenience of the user, and the electric and electronic fields are becoming more and more important in creating new value .

In addition, due to the spread of vehicles and the development of roads, driving a vehicle has become a part of everyday life, and driving long-distance driving at night or driving at night is also becoming a daily operation. Due to these changes, as the time spent by the user increases in the vehicle, various functions are being developed to enable the user to operate in a better environment.

As a representative technique, there is a dialogue system that recognizes the user's voice and talks with the user. Vehicle speech recognition technology is a technology in which the processor automatically determines the linguistic meaning of speech by comparing the characteristics of voice oscillations such as strength of sound and voices with digital signals, Recently, with the development of telematics system (Telematics System), it is applied to vehicles and gradually used in various fields.

Therefore, in order to maintain continuous conversation with the user in the case of the ignition system, it is necessary to judge the user's response to the state of the current user and the utterance provided by the vehicle, and then provide an appropriate utterance based on the user's response.

However, in the case of the existing technology, there is a problem in that there is no persistence of conversation because it is analyzed based on the user's response and the subsequent utterance is not appropriately provided to the user according to the situation.

Therefore, the present invention is an invention devised to solve the problems of the prior art as described above, and it is an object of the present invention to provide various kinds of subsequent utterances based on the response of the user corresponding to the utterance provided to the user, This is to provide a proper dialog system.

In one embodiment, the interactive system includes an output unit for outputting a voice, a sensing unit for sensing a state of the user, and a controller for, when a response of the user corresponding to the first utterance provided to the user is included in a predetermined first reference, And a control unit for providing the user with a second utterance generated based on the first utterance and the information about the user through the output unit.

The controller may determine whether the user's response is included in the first criterion based on at least one of the words used by the user, the context of the response, the face information of the user, and the gesture information of the user.

The control unit may generate the second utterance based on the past utterance record with the user when the response of the user is included in the first criterion.

In addition, the control unit may provide the user with a second utterance including information related to the first utterance when the response of the user is included in the first criterion.

In addition, the control unit may determine the priority of the second utterance, and sequentially provide the second utterance to the user according to the determined priority.

The control unit may not provide the second speech to the user if the response of the user is included in a preset second criterion, or may provide the user with a speech of a different kind from the first speech.

In addition, the control unit may provide a follow-up speech to the user based on the response of the user corresponding to the second speech.

In addition, The user may be provided with a speech based on at least one of weather information, road environment information, and traffic situation information.

In addition, the dialog system may further include a display that displays content related to the utterance.

The interactive system may further include a storage unit for storing information about the user and information about the user.

According to another embodiment of the present invention, there is provided a vehicle comprising: an output unit for outputting a voice; a sensing unit for sensing a state of a user; and a controller for determining whether a response of the user corresponding to the first utterance provided to the user is included in a predetermined first reference And an interactive system for providing the user with the second utterance generated based on the first utterance and the information about the user to the user through the output unit.

The control unit may include an interactive system for determining whether the user's response is included in the first criterion based on at least one of a word used by the user, a context of the response, face information of the user, and gesture information of the user can do.

The control unit may include an interactive system for generating the second utterance based on the past utterance record with the user when the response of the user is included in the first criterion.

The control unit may further include an interactive system for providing the user with a second utterance including information related to the first utterance when the response of the user is included in the first criterion.

In addition, the control unit may include an interactive system that can prioritize the second utterances and sequentially provide the second utterances to the user in accordance with a priority order.

In addition, the control unit may not provide the second utterance to the user if the response of the user is included in a preset second criterion, or may not provide the utterance of the utterance different from the first utterance to the user. . ≪ / RTI >

In addition, the control unit may include an interactive system capable of determining whether to provide a follow-up to the user based on the response of the user corresponding to the second utterance.

In addition, the control unit may include an interactive system capable of providing a speech to the user based on at least one of weather information, road environment information, driving information of the vehicle, and traffic situation information.

The vehicle may also include an interactive system that further includes a display that displays content related to the utterance.

The vehicle may further include an interactive system that further includes a storage unit in which information about the user and information about the user are stored.

The conversation system according to an embodiment classifies the user's response corresponding to the utterance provided to the user into various criteria and then provides various subsequent utterances according to the situation based on the information about the user and the classified information, It is possible to provide a conversation system suitable for the user's taste.

1 is a block diagram illustrating some components of an interactive system according to one embodiment.
2 is a flowchart showing an operation sequence of the interactive system according to one embodiment.
3 is a diagram illustrating a process of providing a follow-up speech based on a user's response, according to an embodiment.
Fig. 4 is a diagram showing an appearance of a vehicle including an interactive system, according to another embodiment. Fig.
5 is a diagram showing an internal view of a vehicle including an interactive system, according to another embodiment.
6 is a diagram illustrating a process of providing a subsequent utterance based on a user's response, according to another embodiment.
7 to 9 are diagrams illustrating a process of providing a subsequent utterance based on a user's response, according to another embodiment.

The embodiments described in the present specification and the configurations shown in the drawings are preferred examples of the disclosed invention, and various modifications may be made at the time of filing of the present application to replace the embodiments and drawings of the present specification.

Also, the terms used herein are used to illustrate the embodiments and are not intended to limit and / or limit the disclosed invention. The singular expressions include plural expressions unless the context clearly dictates otherwise.

In this specification, terms such as " comprise ", " comprise ", or "have ", when used in this specification, designate the presence of stated features, integers, Steps, operations, components, parts, or combinations thereof, whether or not explicitly described herein, whether in the art,

In addition, the terms including the ordinal numbers such as " first ", "second ", and the like used herein can be used to describe various components, but the components are not limited by the terms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. In order to clearly explain the present invention in the drawings, parts not related to the description will be omitted.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of an interactive system, a vehicle including the interactive system, and a method for processing a conversation will be described in detail with reference to the accompanying drawings.

An interactive system according to an exemplary embodiment of the present invention is an apparatus for identifying a user's intention using a user's voice and voice input and providing a service suitable for a user's intention or a service required for a user, The user can perform conversation with the user by outputting the system utterance as a means for clearly grasping the user.

In this embodiment, the service provided to the user includes all operations performed to meet the needs of the user, such as providing information, controlling the vehicle, executing audio / video / navigation functions, . ≪ / RTI >

In addition, the conversation system according to an embodiment can provide a conversation processing technique specific to the vehicle environment, thereby accurately grasping the intention of the user in a special environment of a vehicle.

The gateway connecting these dialog systems to the user may be a vehicle or a mobile device connected to the vehicle. As will be described later, the conversation system may be provided in a vehicle, or may be provided in a remote server outside the vehicle, and may exchange data through communication with a vehicle or a mobile device connected to the vehicle.

It is also possible that some of the components of the conversation system are provided in the vehicle and some are provided in the remote server so that the operation of the conversation system is partially performed in the vehicle and the remote server.

1 is a block diagram illustrating some components of an interactive system in accordance with one embodiment.

1, an interactive system 100 according to one embodiment includes an input 110 for processing input including user input, vehicle-related information, or information related to a user, including user's voice and voice input, A control unit 140 for determining an intention of the user by using the processing result of the input unit 110 and determining an action corresponding to the intention of the user or the state of the vehicle, An output unit 130 for outputting a system utterance for continuing the conversation, and a storage unit 120 for storing various information necessary for the interactive system 100 to perform an operation to be described later.

The input unit 110 can receive two types of input: a user voice and a voice input. The non-voice input includes a user's gesture recognition, a non-voice input of the user input through the operation of the input device, vehicle status information indicating the status of the vehicle, driving environment information related to the driving environment of the vehicle, And the like.

In addition to the above information, the information related to the vehicle and the user may be input to the input unit 110 if the information can be used to grasp the user's intention or provide the service to the user. The user may include both the driver and the passenger.

The input unit 110 recognizes the inputted user voice and converts the input user voice into a textual utterance, and grasps the intention of the user by applying a Natural Language Understanding technique to the utterance of the user.

In addition, the input unit 110 may collect information related to the state of the vehicle or the driving environment in addition to the user's voice, and may use the collected information to understand the situation.

The input unit 110 may transmit information related to a user's intention and situation, etc., which are understood through natural language understanding, to the control unit 140.

The control unit 140 determines an action corresponding to the user's intention and the current situation based on the user's intention and information related to the situation transmitted from the input unit 110 and manages factors necessary for performing the action .

In this embodiment, an action may mean all actions performed to provide a particular service, and the type of action may be predefined. In some cases, provision of a service and performance of an action may have the same meaning.

There is no limitation on the type of action, and the conversation system 100 can be performed through the vehicle 200 and can be an action if it is defined in advance and the inference rules, relationships with other actions / events, have.

The control unit 140 may transmit the determined action information to the output unit 130.

The output unit 130 generates and outputs an interactive response and a command necessary to perform the delivered action. The conversation response may be output as text, image, or audio, and when the command is output, services such as vehicle control and external content provision corresponding to the output command may be performed.

The storage unit 120 stores various kinds of information necessary for dialog processing and service provision. For example, information related to a domain, an action, an action, and an object name used for natural language understanding can be stored in advance, a situation understanding table used for understanding the situation can be stored from input information, One data, information related to the user, and information necessary for performing an action may be stored in advance. A more detailed description of the information stored in the storage unit 120 will be described later.

As described above, the conversation system 100 provides a conversation processing technique specific to the vehicle environment. All of the components of the conversation system 100 may be included in the vehicle, or only a part thereof may be included. The conversation system 100 may be provided at a remote server and the vehicle may serve only as a gateway between the conversation system 100 and the user. In either case, the conversation system 100 may be connected to a user via a vehicle or a mobile device associated with the vehicle.

FIG. 2 is a flowchart showing an operation sequence of the interactive system 100 according to an embodiment.

2, the interactive system 100 may provide a first utterance to the user (S100)

Specifically, the output 130 of the dialog system 100 may provide the user with a first utterance. And the first utterance may mean a utterance first provided to a user, but any particular utterance that occurs during a conversation to determine a subsequent utterance may be referred to as a first utterance.

The first utterance may be provided based on information of the user and information of the vehicle environment. Specifically, a first utterance may be generated based on information of a user, for example, age, sex, occupation, driving propensity, hobby, etc. of a user, and weather information, road environment information, The first utterance may be generated based on at least one of the first utterance.

After the first utterance is provided to the user, the conversation system 100 may analyze the user's response to the first utterance provided to the user and determine whether the analyzed result is included in the first criterion. (S110, S120)

In steps S100 and S110, the dialogue system 100 and the user search for an appropriate utterance for maintaining a conversation, and specifically determine whether to provide a second utterance to the user based on whether the user's response is included in the first criterion .

The first criterion is the answer that the user's response corresponding to the first utterance can continue the conversation. Specifically, the user responds to the first utterance with the consent of the user, or the user responds to the utterance in the first utterance so as to maintain the conversation with the user even if the utterance is continued.

 For example, when the user responds to the first utterance in a positive sense, it can be determined that the user is interested in the first utterance. Thus, in this case, the second utterance generated based on the first utterance can be provided to the user.

It may be determined whether the user's response is included in the first criterion based on at least one of the words used by the user, the context of the response, the face information of the user, and the gesture information of the user.

The word used by the user can be judged based on whether the word used in the first utterance has a positive meaning or the word used in a negative meaning, and judged in order of adjectives, adverbs, verbs, and nouns for accurate judgment can do.

It is possible to determine that the user's response is included in the first criterion based on the context, and can determine whether the user's response is included in the first criterion based on at least one of the position, posture, and biometric information of the user.

According to step S120, if the user's response is included in the first criterion, the conversation system 100 may provide the user with a second utterance (S130)

Specifically, when the user's response is included in the first criterion, the second utterance is provided to the user based on the past utterance record with the user, or the second utterance containing information related to the first utterance is provided to the user can do.

That is, the conversation system 100 may provide a second utterance to the user based on historical information about how the user responded to utterances that are the same as or similar to the first utterance or the second utterance.

According to the past record, if there is a second utterance that has a negative response, the second utterance which has a negative response is not provided to the user, so that it is possible to maintain the conversation with the user more efficiently.

On the other hand, according to the past record, if there is a second utterance which shows a positive response, it is possible to maintain a conversation with the user more efficiently by providing the user with a second utterance showing a positive response.

In addition, the conversation system 100 can provide the user with a more appropriate utterance by providing the user with a second utterance containing information related to the first utterance.

Also, although not shown in the drawing, the interactive system 100 may provide a user with a video or an image related to the utterance.

Accordingly, the conversation system 100 not only provides the speech only to the user in an auditory manner, but also provides the user with a more accurate presentation of the contents of the speech by providing the image or image associated with the speech, .

Further, in providing the second utterance to the user, the second utterance generated based on at least one of the weather information, the road environment information, the time zone information, and the traffic situation information may be provided to the user, Or to provide utterance to use a particular function. Through this process, it is possible to induce the user to participate more actively in utterance.

In addition, in providing the second utterance to the user, the conversation system 100 may prioritize the utterances available for the second utterance if the user's response falls within the first criterion, To the user.

However, if the user's response is not included in the first criterion, i.e., if the user's response is included in the second criterion in step 120, the conversation system 100 does not provide the user with a second speech, A kind of utterance can be provided to the user.

The second criterion is a criterion opposite to the first criterion and refers to a case where the user responds to the first utterance in a negative meaning such as not agreeing or not interested in the first utterance.

The first and second criteria are not absolute criteria, and may be set to various criteria based on the propensity and information of the user.

According to the process of S140, if the user has provided a second utterance, the conversation system 100 may determine whether to provide a subsequent utterance based on the user's response to the second utterance. (S140)

If the user's response does not agree or has a negative response to the second utterance, it may no longer provide the second utterance to the user.

However, if the user's response has a positive response, such as agreeing on the second utterance, it may continue to provide subsequent utterances such as the third utterance, the fourth utterance associated with the second utterance.

3 is a diagram illustrating a process of providing a follow-up speech based on a user's response, according to an embodiment.

Referring to FIG. 3, the interactive system 100 can provide a user with a first utterance 'augmented reality touch feeling capable of feeling a material and a VR image S1' synthesized in the interior of a house. In this case, although not shown in the drawing, the interactive system 100 can display an augmented reality image using an image device.

If the user has a positive response to this first utterance, the conversation system 100 may provide a second utterance to the user. That is, as shown in the drawing, (S2) ', the conversation system 100 searches for a list of follow-up actions of the user, and if the search candidate is found, The contents of the list corresponding to the first rank can be provided to the user by the second utterance.

For example, the user may be provided with a second utterance of "Yes, touch the first curtain" (S2) to the user, as shown in the figure.

In this case, the user has a positive response to the second utterance. Therefore, the conversation system 100 continues to provide the user with a follow-up utterance (" U2 " That is, the user may be provided with a speech called 'this time the second curtain' (S3), which is an utterance associated with the second utterance, as shown in the figure.

Figure 3 is an exterior view illustrating an exterior view of a vehicle 200 including an interactive system 100 in accordance with one embodiment of the present invention, Figure 4 includes an interactive system 100 in accordance with one embodiment Fig. 2 is an internal view showing an inner appearance of a vehicle 200 having a vehicle. Hereinafter, the description of the same contents will be described together to prevent duplication.

3, the external appearance of the vehicle 200 according to the embodiment includes wheels 12 and 13 for moving the vehicle 200, a door 15L for shielding the inside of the vehicle 200 from the outside, A front glass 16 that provides the user inside the vehicle 200 with a view of the front of the vehicle 200 and side mirrors 14L and 14R that provide the user with a view of the rear of the vehicle 200. [

The wheels 12 and 13 include a front wheel 12 provided at the front of the vehicle and a rear wheel 13 provided at the rear of the vehicle and a driving device (not shown) provided inside the vehicle 200 includes a vehicle 200 To the front wheel 12 or the rear wheel 13 to move forward or backward. Such a drive system may employ an engine that generates a rotational force by burning fossil fuel, or a motor that generates power by receiving power from a capacitor.

The doors 15L and 15R are rotatably provided on the left and right sides of the vehicle 200 so that a user or a passenger can ride inside the vehicle 200 when the vehicle is opened, Shielding from the outside.

It is also possible to provide grips 17L and 17R capable of opening and closing the doors 15L and 15R (see Fig. 2) on the outside of the vehicle 200 and to transmit a Bluetooth (Low Frequency) signal to the knob 17L And a touch sensing unit (not shown) capable of recognizing the user's touch input.

When the touch sensing unit of the doors 15L and 15R senses the touch input of the user while the user is holding the remote control device (not shown), the vehicle 200 is operated by the remote control device (not shown) And when the authentication is completed, the door lock of the vehicle 200 is released and the door 15L can be opened by the pulling operation of the user's handles 17L, 17R. Here, the user may include not only the user but also the passenger on board the vehicle 200.

The front glass 16 is provided on the front upper side of the main body so that a user inside the vehicle 200 can obtain time information in front of the vehicle 200. The windshield glass is also called a windshield glass.

The side mirrors 14L and 14R include a left side mirror 14L provided on the left side of the vehicle 200 and a right side mirror 14R provided on the right side. 200 can be obtained.

In addition, the vehicle 200 may include a proximity sensor for detecting rear or side obstacles or other vehicles, a rain sensor for detecting rainfall and precipitation, and the like.

The proximity sensor can send a detection signal to the side or rear of the vehicle and receive a reflection signal reflected from an obstacle such as another vehicle. The presence or absence of an obstacle on the side or rear of the vehicle 200 can be detected based on the waveform of the received reflected signal and the position of the obstacle can be detected. As an example of such a proximity sensor, a method of transmitting an ultrasonic wave or an infrared ray and detecting a distance to an obstacle by using ultrasonic waves or infrared rays reflected by the obstacle may be employed.

Referring to FIG. 5, a display 220 for displaying an image or an image provided from an AVN (Audio Video Navigation) terminal may be provided in a central area of the dashboard 20. The display 220 can selectively display at least one of an audio screen, a video screen, and a navigation screen, as well as a screen related to various control screens or additional functions related to the vehicle 200.

The display 220 may be implemented as a liquid crystal display (LCD), a light emitting diode (LED), a plasma display panel (PDP), an organic light emitting diode (OLED), or a cathode ray tube (CRT).

A center input unit 25 of a jog shuttle type may be provided between the driver's seat 18L and the passenger's seat 18R. The user can input the control command by turning the center input unit 25, pressing it, or pushing it in the upward, downward, leftward or rightward direction.

The vehicle 200 may include a speaker 19 capable of outputting sound. The speaker 19 can output sounds necessary for performing an audio function, a video function, a navigation function, and other additional functions.

In FIG. 5, speakers 19 are provided in the seat 18L and the passenger seat 18R, respectively. However, the present invention is not limited thereto and may be provided at various positions within the vehicle 200 .

A dashboard 29 on the driver's seat 18L is provided with a steering wheel 23 and a remote control device (not shown, for example, a FOB key) When the external terminal is inserted into the key groove 22 or the authentication between the external terminal and the vehicle 200 is completed through the wireless communication network, the external terminal and the vehicle 200 can be connected to each other have.

On the other hand, the vehicle 200 is provided with an air conditioner to perform both heating and cooling, and it is possible to control the temperature inside the vehicle 200 by discharging the heated or cooled air through the air vents 21.

The outer and inner configurations of the vehicle 200 according to one embodiment have been described so far. Hereinafter, components and control methods of the vehicle 200 according to one embodiment will be described.

6 is a block diagram illustrating some components of vehicle 200, in accordance with one embodiment.

6, a vehicle 200 according to an exemplary embodiment includes a sensing unit 210 for sensing a state of a user, a display 220 for outputting images or images received from the control unit 250, a controller 250, An output unit 230 for outputting the voice received from the user, a storage unit 240 for storing information on the user, a response of the user sensed by the sensing unit 210, and a user's utterance And may include a control unit 250 for providing the user with the information through the output unit 230 or the display 220.

The sensing unit 210 may sense the user's condition in real time and transmit the sensed result to the control unit 250.

Specifically, the sensing unit 210 may sense the current state of the user even before the controller 250 provides the user with a speech. After the control unit 250 provides the user with the utterance, the user may sense in real time what state the user responded to the provided utterance, and then transmit the sensed result to the controller 250. As will be described later, the control unit 250 may determine whether the user belongs to the first criterion or the second criterion based on the detection result transmitted from the sensing unit 210. [

In addition, the sensing unit 210 can sense states of a plurality of users when a plurality of passengers are present in the vehicle 200, as well as a state of the user. For example, it is possible to detect a change in position of a plurality of users, a change in posture, or biometric information (facial expression, heartbeat, body temperature) for a specific user, and transmit the sensed result to the control unit 250.

In addition, the sensing unit 210 can sense various states related to the vehicle 200 as well as states related to the user. For example, it is possible to detect information about the current position, speed, and travel route of the vehicle 200, furthermore, it can detect weather information, road environment information, driving time zone information and traffic situation information, Are transmitted to the control unit 250, and the control unit 250 can provide appropriate speech to the user according to the user's environment based on the received information.

Accordingly, the sensing unit 210 may include various devices including a sensor for sensing the state of the user. For example, a facial sensing device and an ocular sensing device may be provided to acquire facial information of a user, and may include sensors capable of sensing a change in a heartbeat in order to determine the state of the user. In addition, gesture recognition devices capable of determining a user's gesture may also be included.

The display 220 may output the image or image received from the control unit 250 to the outside.

Specifically, the display 220 outputs a video or an image related to a speech provided to the user by the control unit 250, so that the contents of the speech can be more effectively communicated to the user.

Accordingly, the display 220 may include a display panel (not shown) for expressing the display. The display panel may include a cathode ray tube (CRT) display panel, a liquid crystal display (LCD) A light emitting diode (LED) panel, an organic light emitting diode (OLED) panel, a plasma display panel (PDP), a field emission display (FED) have.

In addition, the display 220 may include a touch screen display for receiving a user's input by touching. In this case, the display may include a display panel 220 for displaying an image or an image, and a touch panel ).

The output unit 230 can output a voice. Specifically, the output unit 230 can output the speech contents received from the control unit 250 so that the user can recognize the contents of the speech.

Accordingly, the output unit 230 may include a speaker 19 for outputting sound, and the speaker 19 may be provided at various positions inside the vehicle 200 as described above.

The storage unit 240 may store various kinds of information about the user and the past utterance record with the user.

In detail, the storage unit 240 may store various kinds of information about the user, age, sex, occupation, driving habits, hobbies, etc. of the user, and may further store conversation records with the past vehicle 200 . The control unit 250 can provide the user with the most appropriate speech according to the situation based on the information stored in the storage unit 240.

Accordingly, the storage unit 240 may include a nonvolatile memory device such as a cache, a read only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), and a flash memory Or a storage medium such as a CD-ROM, a hard disk drive (HDD), or a volatile memory device such as a random access memory (RAM). The storage unit 240 may be a memory implemented as a separate chip from the processor described below in connection with the controller 250, and may be implemented as a single chip with the processor.

At least one component may be added or deleted corresponding to the performance of the components of the vehicle 200 shown in Fig. It will be readily understood by those skilled in the art that the mutual position of the components can be changed corresponding to the performance or structure of the system.

6 may be software and / or hardware components such as Field Programmable Gate Arrays (FPGAs) and Application Specific Integrated Circuits (ASICs).

The control unit 250 controls each component included in the vehicle 200 and simultaneously generates a speech based on the user's response sensed by the sensing unit 210 and information about the user stored in the storage unit 250 The generated and generated speech may be provided to the user via at least one of the output unit 230 and the display 220.

Specifically, when the user's response corresponding to the first utterance provided to the user is included in the preset first reference, the controller 250 instructs the user to perform the second utterance based on the first utterance and the user's information .

Here, the first utterance refers to a sequence of utterances provided to the user, but not necessarily the utterance uttered by the user is referred to as a first utterance, and a specific utterance during a conversation with the user is referred to as a first utterance Lt; / RTI >

In addition, when the user's response is included in the first criterion, the control unit 250 may provide the second utterance to the user based on the past utterance record with the user, or may provide the second utterance including the information related to the first utterance To the user.

In addition, the controller 250 may display on the display 130 an image or an image associated with the utterance as well as the output 230 to more efficiently provide utterances to the user.

In addition, the control unit 250 includes a memory (not shown) for storing data for a program reproducing an algorithm or algorithm for controlling the operation of the components in the vehicle 200, and a memory (Not shown) for performing the above-described operations. At this time, the memory and the processor may be implemented as separate chips. Alternatively, the memory and the processor may be implemented in a single chip.

7 to 9 are diagrams illustrating a process of providing a follow-up speech based on a user's response, according to another embodiment.

Referring to FIG. 7, the vehicle 200 can provide the user 2 with a first utterance "augmented reality touch feeling that can feel a material and a VR image synthesized in the interior of the house" S1 have. In this case, though not shown in the drawing, an image can be displayed through the display 130.

With respect to this first utterance, as shown in the figure, the user 2 is 'good' (U1), the user (2) responds positively to the first utterance.

 Therefore, in such a case, the vehicle 200 may search the list of subsequent actions of the user 2, and may provide the second search word user 2 with contents corresponding to the first search candidate. For example, the user 2 may be provided with a second utterance "Touch Yes Yes First Curtain" (S2) to the user 2, as shown in the figure.

8 is a diagram illustrating a process of providing a subsequent utterance based on a user's response, according to another embodiment.

Referring to FIG. 8, the vehicle 200 may provide the user 2 with a first utterance called " Writing was very good yesterday " (U1).

Where the first utterance is a utterance generated based on information that the user 2 has written in the past. That is, the vehicle 200 can provide the user 2 with various utterances based on the current and past information of the user 2. [

With respect to this first utterance, as shown in the figure, the user 2 is informed that '! (U1), it corresponds to the case where the user 2 has a positive response to the first utterance. Therefore, in this case, the vehicle 200 searches the list of subsequent actions of the user 2, and provides the user 2 with an utterance corresponding to one of the candidates searched for, or the second utterance associated with the first utterance Can be provided.

For example, as shown in the figure, as the utterance associated with the first utterance to the user 2, (S2) "to the user 2. That is, the vehicle 200 may instruct the user to perform a specific action associated with the first utterance It can provide the second utterance that it requires.

In this case, since the user 200 responded positively to the second utterance in response to the message " U2, " the user 200 added a famous sentence, (2). ≪ / RTI >

9 is a diagram illustrating a process of providing a subsequent utterance based on a user's response, according to another embodiment.

Referring to Fig. 9, the vehicle 200 is provided to the user 2 as a first utterance 'Master! Can you hear the birds? '(S1). Accordingly, the first utterance may be the utterance generated based on the current environment of the vehicle 200.

That is, the vehicle 200 can provide the user with various utterances generated based on the driving and environment information of the current vehicle 200. For example, it can track the face information of the user 2 and provide the user 2 with a first utterance generated based on information about the object at a location that the user 2 is watching.

In response to the first utterance, as shown in the figure, when the user 2 answers 'Yes, it is good' (U1), if the user 2 has a positive response to the first utterance . Thus, the vehicle 200 searches for a list of subsequent actions of the user 2, provides the user 2 with an utterance corresponding to the first of the candidates searched for, or provides a second utterance associated with the first utterance can do.

For example, as shown in the figure, it may be said to be a bell, as an utterance related to the first utterance to the user (2). (S2) "to the user 2. The user may be asked to confirm whether the recording is to be recorded.

If the user responds "Yes, thank you" (U2), the vehicle 200 continues to provide a follow-up call to the user 2 since the user has uttered a positive response to the second utterance .

[0050] Now, the vehicle 200 including the interactive system 100 and the interactive system 100 according to one embodiment has been described.

In a conversation system, in order to maintain a continuous conversation with a user, it is necessary to determine the state of the current user and the response of the driver to the utterance provided by the vehicle, and then provide the most appropriate utterance according to the current situation.

However, in the related art, there has been a problem that it is difficult to maintain continuity of the conversation because the user analyzes the response based on the user's response and does not appropriately provide the subsequent utterance to the user depending on the situation.

However, the conversation system 100 and the vehicle 200 according to the embodiment may classify the response of the user corresponding to the utterance provided to the user into various criteria, and then, based on the information about the user and the classified information, There is an advantage that it is possible to provide a subsequent utterance in accordance with the user's preference by providing various subsequent utterances that are appropriate.

Although the embodiments have been described with reference to specific embodiments and drawings, those skilled in the art will appreciate that various modifications and changes may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI > or equivalents, even if it is replaced or replaced. Therefore, other embodiments and equivalents to the claims are within the scope of the following claims.

100: Conversation system
110: input unit
120:
130:
140:
200: vehicle

Claims (20)

An output unit for outputting a voice;
A sensing unit for sensing a state of the user; And
Wherein when the user's response corresponding to the first utterance provided to the user is included in a predetermined first reference, the second utterance generated based on the first utterance and the information about the user is transmitted to the user through the output unit And a control unit for providing the message to the user. The method according to claim 1,
Wherein,
And determining whether the user's response is included in a first criterion based on at least one of a word used by the user, a context of the response, face information of the user, and gesture information of the user. The method according to claim 1,
Wherein,
And generates the second utterance based on the past utterance record with the user when the response of the user is included in the first criterion. The method according to claim 1,
Wherein,
And if the response of the user is included in the first criterion, providing a second utterance comprising information related to the first utterance to the user. The method according to claim 1,
Wherein,
Determining a priority of the second utterance, and sequentially providing the second utterance to the user according to a predetermined priority. The method according to claim 1,
Wherein,
Wherein the second speech is not provided to the user if the response of the user is included in a predetermined second criterion or the speech is provided to the user different from the first speech. The method according to claim 1,
Wherein,
And determine whether to provide a follow-up to the user based on the user's response corresponding to the second utterance. The method according to claim 1,
Wherein,
And provides the user with utterance based on at least one of weather information, road environment information, and traffic situation information. The method according to claim 1,
Further comprising a display that displays content related to the utterance. The method according to claim 1,
And a storage unit for storing ignition information and information about the user. An output unit for outputting a voice;
A sensing unit for sensing a state of the user; And
Wherein when the user's response corresponding to the first utterance provided to the user is included in a predetermined first reference, the second utterance generated based on the first utterance and the information about the user is transmitted to the user through the output unit And a control unit for providing the vehicle with the vehicle. 12. The method of claim 11,
Wherein,
And a dialog system for determining whether the user's response is included in a first criterion based on at least one of a word used by the user, a context of the response, face information of the user, and gesture information of the user. 12. The method of claim 11,
Wherein,
And a dialogue system for generating the second utterance based on a past utterance record with the user if the response of the user is included in the first criterion. 12. The method of claim 11,
Wherein,
And if the user's response is included in the first criterion, providing a second utterance comprising information related to the first utterance to the user. 12. The method of claim 11,
Wherein,
A dialog system for prioritizing the second utterance and sequentially providing the second utterance to the user according to a predetermined priority. 12. The method of claim 11,
Wherein,
And a conversation system that does not provide the second utterance to a user if the response of the user is included in a predetermined second criterion or provides the user with a utterance of a different kind than the first utterance. 12. The method of claim 11,
Wherein,
And a dialog system for determining whether to provide a follow-up to the user based on the user's response corresponding to the second speech. 12. The method of claim 11,
Wherein,
And an interactive system for providing a speech to the user based on at least one of weather information, road environment information, driving information of the vehicle, and traffic situation information. 12. The method of claim 11,
And a display that displays content related to the utterance. 12. The method of claim 11,
And a storage unit for storing ignition information with respect to the user and information about the user.

Images