KR20160044859A

KR20160044859A - Speech recognition apparatus, vehicle having the same and speech recongition method

Info

Publication number: KR20160044859A
Application number: KR1020140139864A
Authority: KR
Inventors: 허성욱
Original assignee: 현대자동차주식회사
Priority date: 2014-10-16
Filing date: 2014-10-16
Publication date: 2016-04-26

Abstract

Disclosed are a voice recognition apparatus, a vehicle including the same, and a voice recognition method. The voice recognition apparatus may include: a receiving unit which receives a voice command of a user; an extracting unit which extracts a keyword from the received voice command of the user by using a voice command database generated based on the frequency of use of a voice recognition service of the user; and a providing unit which provides a service related to the keyword, thereby increasing a voice recognition rate and a voice recognition speed.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a voice recognition apparatus, a vehicle including the same,

The following embodiments are directed to a technique for recognizing a voice command of a user and providing a service desired by the user.

Since the introduction of digital devices, the interface for manipulating digital devices has evolved a great deal. In recent years, flat panel displays and capacitive touch sensors have been widely used as representative sensors for operating various smart devices such as smart phones and tablets.

The advantage of touch sensors is that they are intuitive and can receive immediate command feedback. However, in situations where complicated interaction is required, such as when two hands are not free, when complicated commands are required, when instructions must be executed at various levels of interaction, or when long texts are required, There is a disadvantage that the usability of the sensor is degraded.

On the other hand, the speech recognition sensor is a natural and intuitive interface that can compensate for the disadvantages of the inefficient use of the touch sensor. As a result, the voice recognition sensor is increasingly used mainly in the control of vehicle devices and voice secretaries for smart devices.

However, the recognition rate of the user's voice command through the voice recognition sensor is not high yet, so the usage rate is low. Therefore, research is needed to increase the usage rate of speech recognition sensors.

There is provided a method of recognizing a voice command of a user using a voice command database created based on a frequency of use of a voice recognition service of a user and a method of performing a method of recognizing a voice command of a user.

A speech recognition apparatus according to one aspect includes: a receiving unit for receiving a voice command of a user; An extraction unit for extracting a keyword from the voice command of the user using the voice command database generated based on the frequency of use of the voice recognition service of the user; And a providing unit for providing a service related to the keyword.

The providing unit may provide a service list in which a plurality of services related to the keyword are listed based on the frequency of use of the user's voice recognition service when a plurality of services related to the keyword are used.

In addition, when the touch input of the user is detected during the processing of the voice command of the received user, the providing unit may stop the voice command processing of the user and may be related to the category corresponding to the detected touch input of the user Service can be provided.

The providing unit may provide a service list listing a plurality of services related to the category based on the frequency of use of the voice recognition service of the user when the plurality of services related to the category are used.

A speech recognition apparatus according to one aspect includes: a storage unit for storing a use history of a user's speech recognition service; A determining unit for determining a frequency of use of the voice recognition service of the user based on a usage history of the stored voice recognition service; And a display unit for displaying a plurality of categories according to a priority order based on the usage frequency of the determined user's voice recognition service.

In addition, the display unit can arrange the plurality of categories in the vicinity of the user according to the priority order based on the frequency of use of the determined user's voice recognition service.

The display unit may provide a service related to a category selected by the user from a plurality of categories displayed on the screen of the voice recognition apparatus.

The display unit may provide a service related to the selected category from the user using the voice command database generated based on the frequency of use of the voice recognition service of the user.

A speech recognition method according to one aspect includes: receiving a voice command of a user; Extracting a keyword from the voice command of the user using the voice command database generated based on the frequency of use of the voice recognition service of the user; And providing a service associated with the keyword.

The providing of the service related to the keyword may include providing a service list in which a plurality of services related to the keyword are listed based on the frequency of use of the user's voice recognition service when the service related to the keyword is a plurality As shown in FIG.

The step of providing the service related to the keyword may include stopping the voice command processing of the user when the touch input of the user is sensed while the voice command of the user is being processed. And providing a service related to the category corresponding to the sensed user's touch input.

The providing of the service related to the category may include providing a service list listing a plurality of services related to the category based on the frequency of use of the voice recognition service of the user when the service related to the category is a plurality As shown in FIG.

A speech recognition method according to one aspect includes storing a use history of a user's speech recognition service; Determining a frequency of use of the voice recognition service of the user based on a usage history of the stored voice recognition service; And displaying the plurality of categories according to the priority based on the frequency of use of the determined user's voice recognition service.

Further, in the displaying step, a plurality of categories can be displayed in a near area from the user according to the priority order based on the frequency of use of the determined user's voice recognition service.

The displaying step may further include providing a service related to a category selected from a user among a plurality of categories displayed on the screen of the voice recognition apparatus.

The providing of the service related to the selected category may include providing a service related to the selected category from the user using the voice command database generated based on the usage frequency of the user's voice recognition service can do.

The vehicle according to one side includes: a receiver for receiving a voice command of a user; An extraction unit for extracting a keyword from the voice command of the user using the voice command database generated based on the frequency of use of the voice recognition service of the user; And a providing unit for providing a service related to the keyword.

There is provided a voice recognition method and a voice recognition method for performing a voice recognition method capable of enhancing a voice recognition rate and a voice recognition speed by recognizing a voice command of a user by using a voice command database created based on a frequency of use of a voice recognition service of a user, Device.

1 and 2 illustrate a speech recognition apparatus for performing a method of recognizing a voice command of a user using a voice command interface generated based on a frequency of use of a voice recognition service of a user according to an exemplary embodiment .
FIG. 3 and FIG. 4 are diagrams showing a speech recognition apparatus performing a method of arranging a plurality of categories on the screen of the speech recognition apparatus based on the frequency of use of the speech recognition service of the user according to an embodiment.
5 and 6 are views showing a control block diagram of a vehicle in which a speech recognition apparatus according to an embodiment is incorporated
7 is a diagram illustrating an internal configuration of a vehicle having a voice recognition apparatus according to an embodiment of the present invention.
FIG. 8 is a diagram illustrating a case where a voice recognition service is provided to a user through a vehicle having a voice recognition apparatus and a portable terminal according to an embodiment.
9 is a flowchart illustrating a method of recognizing a voice command of a user using a voice command database generated based on a frequency of use of a voice recognition service of a user according to an exemplary embodiment.
10 and 11 are diagrams illustrating a method of providing a service related to a keyword extracted from a voice command of a user according to an embodiment.
12 is a flowchart showing a method of arranging a plurality of categories on the screen of the speech recognition apparatus based on the frequency of use of the speech recognition service of the user according to an embodiment.
13 is a view for explaining a method of providing a voice recognition service based on at least one of a voice command of a user and a touch input of a user according to an embodiment.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 and 2 illustrate a speech recognition apparatus for performing a method of recognizing a voice command of a user using a voice command interface generated based on a frequency of use of a voice recognition service of a user according to an exemplary embodiment .

The speech recognition apparatus 100 described below means a system for providing a speech recognition service through a speech recognition engine. The speech recognition apparatus 100 can be embedded in a smart phone, a portable terminal such as a PDA, a wearable device detachable to a user's body, a smart TV including a voice command system, and a vehicle. The voice recognition service described below is a service that helps a user to execute a service desired to be provided by using a voice command of a user received through a voice recognition sensor.

1, the voice recognition apparatus 100 may include a receiving unit 110, an extracting unit 120, a voice command database 130, and a providing unit 140. The receiving unit 110, the extracting unit 120, the voice command database 130 and the providing unit 140 may be integrated into a system on chip incorporated in the voice recognition apparatus 100.

The receiving unit 110 may receive voice commands of the user through the voice recognition sensor. The speech recognition sensor described below means a sensor capable of receiving a voice command of a user. The voice recognition sensor means a microphone or the like.

Also, the receiving unit 110 can receive a touch input of a user, which is sensed on the screen, through the touch sensor. The touch sensor described below means a sensor capable of sensing the touch input of a user occurring in the screen of the voice recognition device. That is, the receiving unit 110 may receive at least one of a user's voice command and a touch input.

The extraction unit 120 may extract the keyword from the voice command of the user using the voice command database 130. [ The extraction unit 120 may extract keywords from the voice command of the user by searching the data stored in the voice command database 130 using the voice recognition engine.

The keyword means a part or all of the words included in the voice command of the user. According to one embodiment, the keyword includes words related to a service that the user desires to receive, among the words included in the voice command of the user. The keyword is not limited to one embodiment, and some or all of the words included in the voice command of the user through various methods may be selected as keywords. In addition, the service described below refers to all application services such as an application that can be executed through the processor of the speech recognition apparatus.

According to one embodiment, if the user's voice command is 'dial up', the keyword may be 'phone'. Accordingly, the extraction unit 120 can extract 'telephone' as a keyword among the words included in the voice command of the user by using the voice command database 130.

The voice command database 130 may store a usage history of the voice recognition service. The use history of the voice recognition service means information related to the service executed by the user through the voice recognition service. That is, the usage history of the voice recognition service includes information related to which service is executed according to the voice command of the user.

The voice command database 130 may store a word or an instruction word, that is, a keyword having a high frequency of use of the voice recognition service of the user based on the use history. For each of the keywords, the voice command database 130 may store information mapped to the service related to the keyword. According to one embodiment, the voice command database 130 may be stored with the keyword 'phone' mapped with information about the phone connection application providing the service associated with 'phone'. In addition, the voice command database 130 may store information about a plurality of services related to the keyword mapped to each keyword. At this time, the voice command database 130 may store information added with a point of addition to a plurality of services according to the frequency of use.

The providing unit 140 may provide a service related to the keyword. The providing unit 140 may search for a service related to the keyword from the voice command database and provide a service related to the keyword based on the search result.

According to one embodiment, the provider 140 may execute application services, such as applications associated with keywords. If the keyword is " phone, " the offerer 140 may execute the phone connection application mapped to the keyword " phone. &Quot;

As another example, when there are a plurality of services related to the keyword, the service providing unit 140 may provide a service list in which the services related to the keyword are listed according to the frequency of use. When there are a plurality of services related to the keyword, the speech recognition device analyzes a plurality of services related to the keyword based on the data stored in the voice command database and searches for the service in a high use frequency order, May be provided.

When the user's touch input is detected while searching for a service related to the keyword extracted from the voice command of the user, the provider 140 may stop providing the service related to the keyword extracted from the voice command of the user.

For example, when a plurality of categories are individually displayed on the screen of the voice recognition apparatus 100, the providing unit 140 may associate the category displayed in the vicinity of the area where the user's touch input occurred among the plurality of displayed categories Service can be provided. The category described below means to include a plurality of services. Accordingly, a plurality of services can be classified into one or more categories.

The providing unit 140 may transmit the category related services to the user in the order of the highest frequency of use by using the information stored in the voice command database 130. [ According to one embodiment, the service provider 140 can display the services related to the category in a descending order of the frequency of use, through a display or via a speaker. Accordingly, the providing unit 140 can provide the desired service by executing the service selected by the user.

1, the voice command database 130 may be stored in the voice recognition apparatus 100 and may be implemented as one module with the receiving unit 110, the extracting unit 110, and the providing unit 140 .

As another example, referring to FIG. 2, the voice command database 130 may be stored in an external device separate from the voice recognition device 100. At this time, the voice recognition apparatus 100 can provide a voice recognition service in cooperation with an external apparatus in which the voice command database 130 is stored through a communication network.

According to one embodiment, the speech recognition apparatus 100 may transmit a voice command of a user received through the receiving unit 110 or may transmit a keyword extracted by the extraction unit 120. [ Corresponding to this, the external device can derive the service information related to the keyword using the voice command database 130, and deliver it to the providing unit 140. The information about the service includes information related to the service that the user is expected to execute through the voice command database. Then, the providing unit 140 can execute the service related to the keyword by using the information about the service.

FIG. 3 and FIG. 4 are diagrams showing a speech recognition apparatus performing a method of arranging a plurality of categories on the screen of the speech recognition apparatus based on the frequency of use of the speech recognition service of the user according to an embodiment.

3, the voice recognition apparatus 200 may include a storage unit 210, a determination unit 220, a voice command database 230, and a display unit 240. The storage unit 210, the determination unit 220, the voice command database 230, and the display unit 240 may be integrated into a system on chip incorporated in the voice recognition apparatus 200.

When the user uses the voice recognition service, the storage unit 210 may store the usage history of the voice recognition service of the user. The storage unit 210 may store a usage history of the user's voice recognition service such as whether a service is executed according to a voice command of the user.

According to an exemplary embodiment, the storage unit 210 may store a log file in which a usage history of the user's voice recognition service is recorded in the voice command database 230. [ The use history of the voice recognition service means information related to the service executed by the user through the voice recognition service. That is, the use history of the voice recognition service includes information related to which service has been executed according to the voice command transmitted by the user. The method of storing the use history of the voice recognition service by the storage unit 210 is not limited to this, and may store data in which the use history of the user's voice recognition service is recorded through various methods.

The determination unit 220 can determine the frequency of use based on the usage history of the user's voice recognition service. The frequency of use means the usage tendency of the user's voice recognition service. For example, the frequency of use refers to information related to a usage tendency of the user's voice recognition service, such as which user mainly uses a voice recognition service. Accordingly, the determination unit 220 can analyze the frequency of use and classify the category appropriately according to the analysis result, thereby increasing convenience for the user.

According to one embodiment, the determination unit 220 may analyze the stored log file to determine the frequency of use of the user's voice recognition service. The determining unit 220 may analyze the user's frequently used services according to the voice command using the stored log file. Accordingly, the determination unit 220 can determine the frequency of use of the user's voice recognition service based on the analysis result. The determination unit 220 may store the frequency of use of the voice recognition service in the voice command database 230. [ Accordingly, the determination unit 230 may classify the category based on the frequency of use stored in the voice command database 230. [ The method of classifying categories is not limited to one embodiment, and can be classified by various methods.

According to one embodiment, the determination unit 220 may analyze the use history of the collected user service and give a point of addition. The determination unit 220 can determine a category related to a frequently used service based on the added point.

The frequency of use of the service can be varied by time zone or by month. Accordingly, the determining unit 230 can analyze the usage history by time or by month to determine the frequency of use by time or by month.

According to one embodiment, a user may have different services frequently used depending on the time zone or the month. For example, in the case of commuting time, frequency of use of the route guidance service may be high, and in the evening, radio broadcasting service may be frequently used. As another example, in the evening from April to September, the frequency of TV service usage may be high due to baseball broadcasting. Therefore, the determination unit 230 can determine the frequency of use according to the time zone or the month, thereby grasping the service desired by the user more accurately. The determining unit 230 may analyze the usage history according to the time or the month and may store the usage frequency of the determined voice recognition service in the voice command database 230 as a result of the analysis.

The display unit 240 can display a plurality of categories stepwise in the area close to the user in descending order of frequency of use. The display unit 240 can assign an additive point to each of a plurality of categories based on the frequency of use and can set a priority to a plurality of categories based on the added points. Accordingly, the display unit 240 can display a plurality of categories in order of priority from the user in order of priority.

5 and 6 are views showing a control block diagram of a vehicle in which a speech recognition apparatus according to an embodiment is incorporated

According to one embodiment, the speech recognition apparatus 100 may correspond to an AVN (Audio Video Navigation) terminal built in a vehicle. The AVN terminal described below refers to a device capable of integrally performing audio, video and navigation functions.

5 and 6 may receive not only a voice command of the user through the voice recognition sensor but also a touch input of the user sensed on the display of the AVN terminal through the touch sensor. Also, the receiving unit may receive a command input by a user through a controller of a jog shuttle type or hard key type installed in the vehicle.

The extracting unit and the providing unit shown in FIGS. 5 and 6 are the same as the processes performed by the extracting unit 120 and the providing unit 140 shown in FIG. 1, FIG. 2, and FIG. The speech recognition apparatus 100 may execute a service that the user desires to receive and provide the service through a display installed in the vehicle, or may transmit the user through a speaker.

In addition, as shown in FIG. 5, the voice command database may be stored in the voice recognition apparatus 100, and the voice command database may be implemented as one module with the receiving unit, the extracting unit, and the providing unit.

As another example, as shown in Fig. 6, the voice command database may be stored in an external device separate from the voice recognition device 100. [ At this time, the voice recognition apparatus 100 can provide a voice recognition service in cooperation with an external apparatus that stores a voice command database through a communication network. The detailed description is the same as described in the description of FIG. 1 and FIG. 2, and will be omitted.

7 is a diagram illustrating an internal configuration of a vehicle having a voice recognition apparatus according to an embodiment of the present invention.

The voice recognition device may correspond to the AVN terminal 170 built in the vehicle. The AVN terminal 170 is a device capable of integrally performing audio, video, and navigation functions. The AVN terminal 170 can selectively display at least one of an audio screen, a video screen, and a navigation screen via the AVN display 171, as well as various control screens related to vehicle control or an AVN terminal 170 It is possible to display a screen related to the additional function.

Referring to FIG. 7, the AVN display 171 may be located in the center fascia 11, which is a central area of the dashboard 10. According to one embodiment, the AVN display 171 may be a liquid crystal display (LCD), a light emitting diode (LED), a plasma display panel (PDP), an organic light emitting diode (OLED), a cathode ray tube Can be implemented.

Also, the AVN input unit 172 may be located in the center fascia 11, which is the central area of the dashboard 10. The driver can input a command for controlling the AVN terminal 170 by operating the AVN input unit 172. [

As shown in FIG. 7, the AVN input unit 172 may be provided in a hard key type in an area adjacent to the AVN display 171. Also, when the AVN display 171 is implemented as a touch screen type, the AVN display 171 can also perform the function of the AVN input unit 172.

Meanwhile, the center console 40 may be provided with a center input unit 43 of a jog shuttle type or a hard key type. The center console 40 refers to the portion where the gear operating lever 41 and the tray 42 are formed between the driver's seat 21 and the front passenger's seat 22. The center input unit 43 may perform all or a part of functions of the AVN input unit 172. [

The voice input unit 180 can receive a voice command uttered by the driver through a microphone and convert the voice command into an electrical signal. The voice input unit 180 may be mounted on the head lining 13 as shown in FIG. 3 for the effective voice input, but the embodiment of the vehicle is not limited thereto. The voice input unit 180 may be mounted on the dashboard 10, (Not shown). In addition, there is no limit to the location that is suitable for receiving the voice of the driving driver.

5 and 6 can receive the voice input through the voice input unit 180 as well as the touch input through the AVN display 171. [ In addition, the receiver can also receive a control command inputted by operating the AVN input unit 172, the center input unit 43, or the like by the driver.

Referring to FIG. 7, a speaker 143, which can output sound, may be provided inside the vehicle. Accordingly, the vehicle can output the sound necessary for performing the audio function, the video function, the navigation function, and other additional functions through the speaker 143. [

When the driver's voice command is received, the AVN terminal 170 can extract the keyword from the driver's voice command using the voice command database. The speech recognition device may execute a service associated with the keyword. According to an embodiment, when the keyword extracted from the driver using the voice command database corresponds to 'destination search', the voice recognition apparatus can execute the navigation application. Accordingly, the speech recognition device can help the driver to go to a desired destination by repeating the information about the destination to the driver. At this time, the AVN terminal 170 can receive information on the destination via the AVN display 171, or receive information on the destination through the audio input unit 180. [

Further, while searching for a service related to the keyword extracted from the voice command of the driver, the AVN terminal 170 can receive the touch input of the driver. At this time, the AVN terminal 170 may stop searching for a keyword related service from the voice command database.

The AVN terminal 170 can search for a service related to the category displayed in the area where the touch input of the driver is sensed by using the voice command database. Accordingly, the AVN terminal 170 can display the service related to the category in the order of the highest frequency of use, on the AVN display 171, or can transmit it to the driver through the speaker 143.

According to one embodiment, the AVN terminal 170 can arrange the categories in descending order of frequency of use from the upper left corner of the AVN display 171. Accordingly, the driver can more easily touch the frequently used category in the driver's seat 21. [

FIG. 8 is a diagram illustrating a case where a voice recognition service is provided to a user through a vehicle having a voice recognition apparatus and a portable terminal according to an embodiment.

Referring to FIG. 8, the speech recognition apparatus may be embedded in the portable terminal 800. The user can touch the display of the portable terminal 800 to transmit the touch input or transmit the voice command through the microphone built in the portable terminal 800. [

The user's touch input, and the voice command, the voice recognition apparatus searches the service desired by the user using the voice command database in which data related to the frequency of use of the voice recognition service of the user is built, .

The voice recognition apparatus can search for a service desired by the user using the voice database stored in the portable terminal 800 and provide the searched service. As another example, the portable terminal 800 may receive a search result related to a desired service by a user in cooperation with a voice database stored in an external device through a communication network, and may provide a service based on the received search result.

According to one embodiment. The speech recognition apparatus can display the frequently used categories from the top left to the bottom of the display of the portable terminal 800 in order. The method of arranging categories is not limited to one embodiment, and a plurality of categories can be displayed on the display according to various criteria.

9 is a flowchart illustrating a method of recognizing a voice command of a user using a voice command database generated based on a frequency of use of a voice recognition service of a user according to an exemplary embodiment.

In step 900, the speech recognition device may receive a voice command of the user using a speech recognition sensor. The speech recognition sensor described below means a sensor capable of receiving a voice command of a user.

In step 910, the speech recognition device may extract the keyword from the user's voice command using the voice command database. The keyword described below refers to a word related to a service that the user wants to receive among the words included in the voice command of the user.

The speech recognition apparatus can generate a speech command database based on the frequency of use of the speech recognition service. According to one embodiment, the speech recognition apparatus can collect usage history of the user's speech recognition service and determine the frequency of use of the speech recognition service. The use history of the voice recognition service means information related to the service executed by the user through the voice recognition service. That is, the use history of the voice recognition service includes information related to which service has been executed according to the voice command transmitted by the user.

The voice command database may store a word or an instruction word, that is, a keyword having a high frequency of use of the voice recognition service of the user based on the use history. For each of the keywords, the speech command database may be stored with information related to the service related to the keyword mapped.

The information on the service mapped to the keyword may include a plurality of services. For example, information on 'DMB service' and 'movie playback service' may be mapped to the word 'viewing'. Accordingly, when the keyword extracted from the user is 'viewing', the voice recognition device can display 'DMB service' and 'movie playback service' on the screen to give the user what service they want to execute.

In step 920, the speech recognition device may provide a service associated with the keyword. When there is one service related to the keyword, the speech recognition apparatus can execute the service related to the keyword. Alternatively, when there are a plurality of services related to the keyword, the speech recognition apparatus may provide the user with a service list in which a plurality of services related to the keyword are arranged in the order of priority.

10 and 11 are diagrams illustrating a method of providing a service related to a keyword extracted from a voice command of a user according to an embodiment.

Referring to FIG. 10, the speech recognition apparatus can extract a keyword from a voice command of a user using a voice command database. The speech recognition device may execute a service associated with the keyword. As shown in FIG. 10, the service may include application services such as 'destination search', 'music search', 'radio', 'DMB', 'dialing', and 'Blue link Assistant'.

According to an embodiment, when the keyword extracted from the user corresponds to 'music', the speech recognition apparatus can execute the music search application service. Accordingly, the speech recognition apparatus can remind the user of what music is found, thereby helping the user to find the desired music.

As another example, when there are a plurality of services related to the keyword, the speech recognition apparatus may display the service list in which a plurality of services are listed according to the priority order based on the frequency of use of the voice service, or may transmit the service list to the user through the speaker.

11, the services associated with the keywords "IU" may include "Call service," "music playing service ', and' navigation service '. That is, the voice command database users' Call Service 'in the word' IU 'based on the frequency of use of voice recognition services, "playing music service', and the mapped data, navigation service, the voice recognition device stores .

When there are a plurality of services related to the keyword, the speech recognition apparatus may display a service list in which a plurality of services are listed according to the priority order based on the frequency of use of the voice service, or may transmit the service list to the user through a speaker. 11, the speech recognition device to the user 'Call Services, displayed on the screen in order of the' music play service ', and' navigation service 'position, or through a speaker associated with the "IU" .

12 is a flowchart showing a method of arranging a plurality of categories on the screen of the speech recognition apparatus based on the frequency of use of the speech recognition service of the user according to an embodiment.

In step 1200, the speech recognition device may store the frequency of use of the user's speech recognition service. According to one embodiment, the speech recognition apparatus may collect usage history of the user's speech recognition service, such as whether a service has been executed according to the user's voice command.

In step 1210, the speech recognition device may determine the frequency of use of the user's speech recognition service based on the usage history of the collected speech recognition service. Accordingly, the speech recognition apparatus can generate a speech command database composed of words or commands that are frequently used.

The speech recognition apparatus can continuously collect the use history of the user's speech recognition service and update the speech command database. The update period of the voice command database can be manually set by the user or the administrator. Alternatively, the voice command database may be automatically updated according to preset criteria.

In step 1220, the speech recognition device may display a plurality of categories according to a priority based on a voice command database. According to an embodiment, the speech recognition apparatus can display categories in order of priority in a region where the user can touch the screen of the speech recognition apparatus.

The frequency of use means the usage propensity of the user's voice recognition device. For example, the frequency of use includes information related to what service is executed according to a voice command, what service is mainly used at a specific time using the voice recognition service, and the like. Accordingly, the speech recognition apparatus can analyze the frequency of use and classify the categories in accordance with the analysis result, thereby enhancing the user's convenience.

According to one embodiment, the speech recognition apparatus can analyze the use history of the collected user service and give a point of addition. The speech recognition apparatus can display a category related to a frequently used service on the screen based on the added point given.

13 is a view for explaining a method of providing a voice recognition service based on at least one of a voice command of a user and a touch input of a user according to an embodiment.

Hereinafter, the case where the voice recognition apparatus receives the voice command of the user (CASE I) and the case where the voice command of the user and the touch input of the user are received together (CASE II) will be described separately.

First, when the user's voice command is received (CASE I), the voice recognition apparatus can extract the keyword from the voice command of the user using the voice command database. The speech recognition device may execute a service associated with the keyword.

According to an embodiment, when the keyword extracted from the user using the voice command database corresponds to 'music', the voice recognition device can execute the music search application service. Accordingly, the speech recognition apparatus can remind the user of what music is found, thereby helping the user to find the desired music.

While searching for a service related to the keyword extracted from the voice command of the user, the voice recognition device can receive the touch input of the user (CASE II). At this time, the speech recognition apparatus can stop retrieving the service related to the keyword from the speech command database.

The speech recognition apparatus can search for a service related to the category displayed in the area where the user's touch input is sensed by using the voice command database generated based on the frequency of use. Accordingly, the speech recognition apparatus can display the service related to the category in a descending order of the frequency of use, on the screen of the speech recognition apparatus, or can transmit the service to the user through the speaker.

Referring to FIG. 13, the voice recognition apparatus can display categories such as 'road information, oil price information', 'TV, watching movies', 'Web connection', and 'External device connection' on the screen. According to an embodiment of the present invention, while searching for a service related to a keyword extracted from a voice command of a user, The touch input of the user can be detected in the vicinity of the screen where the 'oil price information' is displayed. The speech recognition apparatus can stop searching for a service related to a keyword by using a speech recognition engine and provide a service related to 'road information, oil price information'. Accordingly, the speech recognition apparatus can provide a service list in which a plurality of services related to 'road information, oil price information' are arranged according to priorities.

The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. 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 implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

10: Dashboard
11: Center Fesia
12: Steering wheel
13: Head lining
21: Driver's seat
22: Passenger seat
40: Center console
41: Gear control lever
42: Tray
43: center input unit
143: Speaker
170: AVN terminal
171: AVN display
172: AVN input unit
180:

Claims

A receiving unit for receiving a voice command of a user;
An extraction unit for extracting a keyword from the voice command of the user using the voice command database generated based on the frequency of use of the voice recognition service of the user; And
Providing service related to the keyword
And a voice recognition device.

The method according to claim 1,
Wherein the providing unit comprises:
And provides a service list in which a plurality of services related to the keyword are listed based on the frequency of use of the voice recognition service of the user when the service related to the keyword is a plurality of services.

The method according to claim 1,
Wherein the providing unit comprises:
The method comprising: stopping the voice command processing of the user when detecting the touch input of the user while processing the voice command of the received user; Device.

The method of claim 3,
Wherein the providing unit comprises:
And provides a service list in which a plurality of services related to the category are listed based on the frequency of use of the voice recognition service of the user when the plurality of services related to the category are included.

A storage unit for storing a usage history of the voice recognition service of the user;
A determining unit for determining a frequency of use of the voice recognition service of the user based on a usage history of the stored voice recognition service; And
And a display unit for displaying a plurality of categories according to the order of priority based on the frequency of use of the determined voice recognition service of the user
And a voice recognition device.

6. The method of claim 5,
The display unit includes:
And arranges the plurality of categories in a region close to the user based on the priority of use based on the frequency of use of the determined voice recognition service of the user.

6. The method of claim 5,
The display unit includes:
And provides a service related to a category selected by the user from among a plurality of categories displayed on the screen of the speech recognition apparatus.

6. The method of claim 5,
The display unit includes:
And provides a service related to the selected category from the user using the voice command database generated based on the frequency of use of the voice recognition service of the user.

Receiving a voice command of the user;
Extracting a keyword from the voice command of the user using the voice command database generated based on the frequency of use of the voice recognition service of the user; And
Providing a service associated with the keyword
And a speech recognition method.

10. The method of claim 9,
Wherein the step of providing a service associated with the keyword comprises:
Providing a service list in which a plurality of services related to the keyword are listed based on the frequency of use of the speech recognition service of the user when the service related to the keyword is a plurality
Further comprising the steps of:

10. The method of claim 9,
Wherein the step of providing a service associated with the keyword comprises:
Stopping the voice command processing of the user when detecting the touch input of the user while processing the voice command of the received user; And
Providing a service related to a category corresponding to the detected touch input of the user
Further comprising the steps of:

12. The method of claim 11,
Wherein the step of providing a service associated with the category comprises:
Providing a service list in which a plurality of services related to the category are listed based on the frequency of use of the voice recognition service of the user when the service related to the category is a plurality
Further comprising the steps of:

Storing a use history of the user's voice recognition service;
Determining a frequency of use of the voice recognition service of the user based on a usage history of the stored voice recognition service; And
Displaying a plurality of categories in accordance with a priority order based on the frequency of use of the determined user's voice recognition service
And a speech recognition method.

14. The method of claim 13,
Wherein the displaying comprises:
And arranging the plurality of categories in a region close to the user according to the priority order based on the frequency of use of the determined speech recognition service of the user.

14. The method of claim 13,
Wherein the displaying comprises:
A step of providing a service related to a category selected from a user among a plurality of categories displayed on a screen of the voice recognition apparatus
Further comprising the steps of:

14. The method of claim 13,
Wherein the step of providing a service related to a selected category from the user comprises:
Providing a service related to the selected category from the user using the voice command database generated based on the frequency of use of the voice recognition service of the user
And a speech recognition method.

A receiving unit for receiving a voice command of a user;
An extraction unit for extracting a keyword from the voice command of the user using the voice command database generated based on the frequency of use of the voice recognition service of the user; And
Providing service related to the keyword
&Lt; / RTI >

18. The method of claim 17,
Wherein the providing unit comprises:
Providing a service list in which a plurality of services related to the keyword are listed based on the frequency of use of the speech recognition service of the user when the service related to the keyword is a plurality of services.

18. The method of claim 17,
Wherein the providing unit comprises:
And stops the voice command processing of the user when the touch input of the user is detected while processing the voice command of the received user and provides a service related to the category corresponding to the detected touch input of the user.

20. The method of claim 19,
Wherein the providing unit comprises:
Providing a service list in which a plurality of services related to the category are listed based on the frequency of use of the voice recognition service of the user when the service related to the category is a plurality of services.