KR102568143B1 - Method and device for providing customized service mode - Google Patents

Abstract

A method for providing a customized service mode performed by a voice recognition terminal includes the steps of receiving a voice command for an application installed in a voice recognition terminal, providing a voice service through a first service mode among a plurality of service modes of an application, a first Recognizing a user's reaction while providing a voice service through a service mode, changing a first service mode into a second service mode, recognizing a user's reaction while providing a voice service through the second service mode Analyzing a preference for each service mode based on a history of using each service mode and one or more of the reactions for each service mode, and determining a preferred service mode among a plurality of service modes based on the analyzed preference. can include

Description

Method and terminal for providing customized service mode {METHOD AND DEVICE FOR PROVIDING CUSTOMIZED SERVICE MODE}

The present invention relates to a method and terminal for providing a customized service mode.

A service executed in a smart terminal (eg, smart phone, IPTV, etc.) includes a plurality of service modes (eg, themes). Conventionally, when a user wants to be provided with a service through a specific service mode in a specific application, it is inconvenient to manually change the basic service mode to the specific service mode.

Korean Patent Publication No. 2013-0005656, which is a prior art, identifies a user's gaze from a face detected from an image captured by a camera of a mobile terminal, and determines a viewing mode of the mobile terminal according to the posture of the mobile terminal and the user's gaze. A configuration for displaying screen data in a mode is disclosed.

When a voice command for an application installed in the voice recognition terminal is received, the voice service is provided through the default service mode, and the user's reaction to the voice service in the default service mode is recognized to change the default service mode to another service mode. do. In addition, while a voice service is provided through another service mode, a user's reaction is recognized to change to another service mode excluding the corresponding other service mode among a plurality of service modes of the application. In addition, the user's reaction to the voice service through each of the plurality of service modes of the application and the use history of each service mode are intended to be stored. In addition, when a voice command for an application is received, a preferred service mode is determined among a plurality of service modes of the application by analyzing the preference of the service mode based on the use history of each service mode and the reaction of each service mode, and the preferred service We want to provide voice service through the mode. However, the technical problem to be achieved by the present embodiment is not limited to the technical problems described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, a method for providing a customized service mode performed by a voice recognition terminal according to a first aspect of the present invention includes receiving a voice command for an application installed in the voice recognition terminal; providing a voice service through a first service mode among a plurality of service modes of the application; Recognizing a user's reaction while providing a voice service through the first service mode; changing the first service mode to a second service mode; Recognizing the user's reaction while providing the voice service through the second service mode; Analyzing a preference for each service mode based on at least one of the use history of each service mode and the reaction for each service mode; and determining a preferred service mode among the plurality of service modes based on the analyzed preference. The reaction may be at least one of the user's voice, facial expression, and gesture.

In one example, after the step of determining the preferred service mode, receiving a voice command for the application; and providing a voice service through the determined preferred service mode.

In one example, the providing of the voice service through the first service mode may include performing at least one of voice recognition for the voice command and image recognition for the user to determine at least one of age, gender, and number of users of the user. identifying; and determining the first service mode based on the age, gender, and number of the identified users.

In one example, the recognizing the user's reaction includes recognizing the user's voice and obtaining a reaction voice, and the analyzing the preference of each service mode includes the vocabulary included in the reaction voice. A step of determining whether a word corresponds to a positive evaluation or a negative evaluation for each service mode may be included. The step of recognizing the user's reaction includes the step of recognizing the user's image and obtaining a reaction expression or reaction gesture, and the step of analyzing the preference of each service mode is such that the reaction expression or reaction gesture is used for each service. A step of determining whether the facial expression corresponds to a positive evaluation or a negative evaluation of the mode may be further included.

In one example, accumulating scores for the positive evaluation and the negative evaluation for each service mode based on the determination; and analyzing the preference of each service mode based on the accumulated score.

In one example, receiving installation data of the application and information about the plurality of service modes from the server; and installing the application.

In one example, the information on the plurality of service modes may include preferred age information and preferred gender information of each service mode.

In one example, recognizing the user's reaction may include: storing a recognized facial expression of the user as a facial expression corresponding to a positive evaluation when the reaction voice includes a vocabulary corresponding to a positive evaluation; and storing a recognized facial expression of the user as a facial expression corresponding to a negative evaluation when the reaction voice includes a vocabulary corresponding to a negative evaluation.

In one example, the changing of the first service mode to the second service mode includes determining whether a preset condition for changing to the second service mode is met, and the preset condition is a preset condition. It may be the passage of time or the number of inputs of the reaction.

In one example, the changing of the first service mode to the second service mode may include determining whether a request to change to the second service mode is input.

In one example, recognizing the user's reaction while providing the voice service through the preferred service mode; and changing the preferred service mode when the reaction corresponds to a negative evaluation.

In one example, receiving data on a new service mode from the server; and changing the preferred service mode to the new service mode.

A voice recognition terminal according to a second aspect of the present invention includes a voice input unit for receiving a voice command for an application installed in the voice recognition terminal; a controller that sets the service mode of the application to a first service mode during a preset condition and changes the service mode of the application to a second service mode after the preset condition; A reaction recognition unit for recognizing a user's reaction while providing voice service through each of the service modes; a preference analyzer configured to analyze a preference of each service mode based on at least one of a use history of each service mode and the reaction for each service mode; and a preferred service mode determination unit configured to determine a preferred service mode among the plurality of service modes based on the analyzed preference. The reaction may be at least one of the user's voice, facial expression, and gesture.

In one example, the voice input unit may receive a voice command for the application after the preferred service mode is determined, and the control unit may change the service mode of the application to the determined preferred service mode.

In one example, the reaction recognition unit may include a voice recognition unit for acquiring a reaction voice by recognizing the user's voice; and an image recognition unit that recognizes the user's image and obtains a reaction expression or reaction gesture.

In one example, the preference analysis unit may determine whether a vocabulary included in the reaction voice corresponds to a positive evaluation or a negative evaluation for each service mode. The preference analysis unit may determine whether the reaction expression or reaction gesture corresponds to a positive evaluation or a negative evaluation for each service mode. The preference analysis unit may accumulate scores for the positive evaluation and the negative evaluation for each service mode based on the determination, and analyze the preference for each service mode based on the accumulated score.

In one example, the method further includes a receiver configured to receive installation data of the application and information about the plurality of service modes from a server, wherein the information about the plurality of service modes includes preferred age information and preferred gender information of each service mode. can include

In one example, the reaction recognition unit determines a recognized user's facial expression as a facial expression corresponding to a positive evaluation when the reaction voice includes a vocabulary corresponding to a positive evaluation, and the reaction voice includes a vocabulary corresponding to a negative evaluation. When performing the task, the recognized user's facial expression may be determined as a facial expression corresponding to negative evaluation.

The above-described means for solving the problems is only illustrative and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and detailed description.

According to any one of the above-described problem solving means of the present invention, when a voice command for an application installed in a voice recognition terminal is input, a voice service is provided through a default service mode, and a user's response to the voice service in the default service mode is provided. By recognizing the reaction, you can change from the default service mode to another service mode. In addition, a user's reaction may be recognized while a voice service is provided through another service mode, and the service mode may be changed to another service mode excluding the corresponding other service mode among a plurality of service modes of the application. In addition, the user's reaction to the voice service through each of the plurality of service modes of the application and the use history of each service mode may be stored. In addition, when a voice command for an application is received, a preferred service mode is determined among a plurality of service modes of the application by analyzing the preference of the service mode based on the use history of each service mode and the reaction of each service mode, and the preferred service A voice service may be provided through a mode.

1 is a configuration diagram of a customized service mode providing system according to an embodiment of the present invention.
2 is a block diagram of a voice recognition terminal shown in FIG. 1 according to an embodiment of the present invention.
3 is an operational flowchart illustrating a method for providing a customized service mode according to an embodiment of the present invention.
4 is an operational flowchart illustrating a method of providing a voice service through a default service mode according to an embodiment of the present invention.
5 is an operational flowchart illustrating a method of recognizing a user's reaction according to an embodiment of the present invention.
6 is an operational flowchart illustrating a method of analyzing a preference of a service mode according to an embodiment of the present invention.
7 is an operational flowchart illustrating a method of analyzing service mode preference according to another embodiment of the present invention.
8 is an operational flowchart illustrating a method for providing a customized service mode according to another embodiment of the present invention.
9 is an operational flowchart illustrating a method for providing a customized service mode according to another embodiment of the present invention.
10 is a diagram for explaining a method of registering and managing an application according to an embodiment of the present invention.
11 is a diagram for explaining a method of determining a preferred service mode of an application preferred by a user according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail so that those skilled in the art can easily practice the present invention with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected" but also the case where it is "electrically connected" with another element interposed therebetween. . In addition, when a certain component is said to "include", this means that it may further include other components without excluding other components unless otherwise stated.

In this specification, a "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware.

In this specification, some of the operations or functions described as being performed by a terminal or device may be performed instead by a server connected to the terminal or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal or device connected to the corresponding server.

Hereinafter, specific details for the implementation of the present invention will be described with reference to the accompanying configuration diagram or process flow chart.

1 is a configuration diagram of a customized service mode providing system according to an embodiment of the present invention.

Referring to FIG. 1 , a system for providing a customized service mode may include a voice recognition terminal 100 and a server 110 . However, since the customized service mode providing system of FIG. 1 is only one embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1, and may be configured differently from FIG. 1 according to various embodiments of the present invention. there is.

In general, each component of the customized service mode providing system of FIG. 1 is connected through a network 120 . A network refers to a connection structure capable of exchanging information between nodes such as terminals and servers, and examples of such networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, etc. are included, but are not limited thereto.

The voice recognition terminal 100 may be a terminal capable of interworking with an Internet of Things (IoT) device and controlling the IoT device according to a user's voice command. In addition, a plurality of applications corresponding to each of a plurality of voice services are installed in the voice recognition terminal 100 .

The voice recognition terminal 100 includes a voice recognition device for recognizing a user's voice and an image recognition device for photographing a user and recognizing a user's image.

The voice recognition terminal 100 receives a voice command for an application installed in the voice recognition terminal 100, determines a user's preferred service mode among a plurality of service modes of the corresponding application, and provides a voice service in the determined preferred service mode. can do.

Specifically, the voice recognition terminal 100 recognizes a user's reaction through a voice recognition device or an image recognition device while providing a voice service through each service mode of an application, and provides information on the use history of each service mode and each service mode. Preference of each service mode may be analyzed based on at least one of the reactions. The voice recognition terminal 100 may determine a preferred service mode among a plurality of service modes based on the analyzed preference and provide a voice service in the determined preferred service mode. Here, the reaction may include at least one of a user's voice, facial expression, and gesture.

The server 110 transmits application installation data and information on a plurality of service modes requested from the voice recognition terminal 100 to the voice recognition terminal 100, and transmits data on a new service mode to the voice recognition terminal 100. can be provided to Here, information on a plurality of service modes may include preferred age information and preferred gender information of each service mode.

Hereinafter, the operation of each component of the customized service mode providing system of FIG. 1 will be described in more detail.

FIG. 2 is a block diagram of the voice recognition terminal 100 shown in FIG. 1 according to an embodiment of the present invention.

Referring to FIG. 2 , the voice recognition terminal 100 includes a voice input unit 200, a controller 210, a reaction recognizer 220, a preference analyzer 230, a preference service mode determiner 240, and a receiver 250. ) and a memory 260 . Here, the reaction recognizer 220 may include a voice recognizer 222 and an image recognizer 224 . However, the voice recognition terminal 100 shown in FIG. 2 is only one implementation example of the present invention, and various modifications are possible based on the components shown in FIG. 2 .

The receiving unit 250 may receive installation data of the application and information about a plurality of service modes provided by the application from the server 110 . Here, information on a plurality of service modes may include preferred age information and preferred gender information of each service mode. For example, when the application is an audio application, the receiving unit 250 receives information about a plurality of sound modes (eg, jazz version mode, rock version mode, classical version mode, ballad version mode, etc.) from the server 110. can do. When the application is a TV application, the receiving unit 250 may receive information about a service mode related to a plurality of launcher screens from the server 110 . When the application is an information providing service application through voice, the receiver 250 may receive information on a service mode for each voice gender, voice tone, and speech speed from the server 110 .

A method of registering and managing applications will be described with reference to FIG. 10 for a moment.

10 is a diagram for explaining a method of registering and managing an application according to an embodiment of the present invention.

Referring to FIG. 10 , the voice recognition terminal 100 may receive an xml file 1000 for an application and a plurality of service modes provided by the application from the server 110 . The service provisioning module 1010 of the voice recognition terminal 100 may install a corresponding application and analyze information about a plurality of service modes of the installed application. In addition, the service provisioning module 1010 may register and store information on each analyzed service mode in the service app mode setting table 1020 and the interface specification table 1030 for each mode.

Here, the service app mode setting table 1020 may include preferred age information and preferred gender information for each service mode. When an application is added or when information on the service mode selected for each application is changed, the interface specification table 1030 for each mode is uploaded to the memory of the service controller and managed, and through this, the database access time of the voice recognition terminal 100 can reduce

When the voice recognition terminal 100 initially drives an application, it may drive the application based on an interface standard related to information on a default service mode. Here, the default service mode may be the first service mode.

Referring back to FIG. 2 , the voice input unit 200 may receive a voice command for an application installed in the voice recognition terminal 100 . Here, the application may include a plurality of service modes, and a default service mode may be set as a basic mode.

The controller 210 may set the service mode of the application as the default service mode during a preset condition and change the service mode of the application to another service mode after the preset condition. The default service mode may be the first service mode, and another service mode may be the second service mode.

When receiving a voice command for an application from a user for the first time, the controller 210 may provide a voice service through a default service mode during a preset condition. For example, when the voice recognition terminal 100 receives a VOD content search command for an IPTV (not shown) interlocked with the voice recognition terminal 100, the controller 210 uses the default mode, the female voice mode, for VOD Content search results may be guided.

The controller 210 may provide a voice service through a default service mode until recognizing the user's reaction (at least one of the user's voice, facial expression, and gesture). The controller 210 may provide a voice service through a default service mode for a preset time.

The control unit 210 identifies at least one of the user's age, gender, and number of people from the voice recognition of the user's voice command by the voice recognition unit 222 and the image recognition of the user by the image recognition unit 224, A default service mode may be determined based on the age, gender, and number of identified users, and a voice service may be provided through the default service mode.

The reaction recognition unit 220 may recognize a user's reaction while providing a voice service through each service mode of an application.

The voice recognition unit 222 may recognize the user's voice and obtain a reaction voice from the voice. The image recognition unit 224 may recognize a user's image and obtain a reaction expression or reaction gesture from the image.

When a user's reaction voice is acquired while providing a voice service through a default service mode, the reaction recognition unit 220 may classify the obtained reaction voice into a positive evaluation or a negative evaluation and store it in the memory 260 . For example, when the reaction voice includes a vocabulary corresponding to a positive evaluation, the reaction recognition unit 220 may determine and store the recognized user's facial expression as a facial expression corresponding to the positive evaluation. When the reaction voice includes a vocabulary corresponding to a negative evaluation, the reaction recognition unit 220 may determine and store the recognized user's facial expression as a facial expression corresponding to a negative evaluation. The reaction recognition unit 220 may use facial expressions stored as positive evaluations and facial expressions stored as negative evaluations to classify whether a reaction expression or a reaction gesture input next corresponds to a positive evaluation or a negative evaluation.

When the reaction recognition unit 220 acquires a user's reaction expression or reaction gesture while providing a voice service through the default service mode, the reaction recognition unit 220 classifies whether the acquired reaction expression or reaction gesture corresponds to a positive evaluation or a negative evaluation, and stores the memory. (260).

The controller 210 may change the default service mode to the first service mode when a preset condition is satisfied.

For example, the controller 210 may change the default service mode to another service mode when a predetermined time elapses. For example, the controller 210 may change the service mode whenever 20 minutes of service use time elapse.

For another example, the controller 210 may change the default service mode to the first service mode based on the number of times the user inputs a reaction. For example, the controller 210 may change the service mode every time the user's reaction is input 5 times.

The controller 210 may change the default service mode to the first service mode when expressions corresponding to negative evaluations are input more than a preset number of times. Alternatively, the controller 210 may change the default service mode to another service mode when the user utters a vocabulary corresponding to negative evaluation. For example, when a search result for a VOD content search in IPTV is provided in a female voice mode, and a facial expression corresponding to a negative evaluation is made, the female voice mode may be changed to a male voice mode.

The controller 210 may change the default service mode to the first service mode when a request to change to the first service mode is input from the user.

The reaction recognition unit 220 may recognize a user's reaction while providing a voice service through the first service mode. The voice recognition unit 222 may acquire a reaction voice by recognizing the user's voice while providing the voice service through the first service mode. When a user's reaction voice is obtained while providing a voice service through the first service mode, the reaction recognition unit 220 may classify the obtained reaction voice into a positive evaluation or a negative evaluation and store it in the memory 260 .

When the reaction recognition unit 220 acquires a user's reaction expression or reaction gesture while providing a voice service through the first service mode, the reaction recognition unit 220 classifies whether the obtained reaction expression or reaction gesture corresponds to a positive evaluation or a negative evaluation, may be stored in the memory 260 .

The preference analysis unit 230 determines whether the vocabulary included in the reaction voice corresponds to a positive evaluation or negative evaluation for each service mode, and the reaction expression or reaction gesture corresponds to a positive evaluation or negative evaluation for each service mode. After determining whether it is a facial expression or gesture, it is possible to accumulate scores for positive and negative evaluations for each service mode.

The preference analyzer 230 accumulates scores for positive evaluations when the vocabulary included in the reaction voice acquired while providing the voice service through the first service mode is positively evaluated for the first service mode, and If it is a negative evaluation for , scores for negative evaluations can be accumulated.

The preference analyzer 230 accumulates scores for the positive evaluation when the reaction expression or reaction gesture obtained during the provision of the voice service through the first service mode is a positive evaluation for the first service mode, and In the case of a negative evaluation for , scores for the negative evaluation may be accumulated.

The preference analysis unit 230 may analyze the preference of each service mode based on at least one of a use history of each service mode and a reaction to each service mode. The preference analyzer 230 may analyze the preference of each service mode based on the accumulated scores for each service mode.

The preferred service mode determination unit 240 may determine a preferred service mode among a plurality of service modes based on the analyzed preference.

A method of determining the preferred service mode of an application will be described with reference to FIG. 11 for a moment. 11 is a diagram for explaining a method of determining a preferred service mode of an application preferred by a user according to an embodiment of the present invention.

Referring to FIG. 11 , when the voice recognition terminal 100 receives a request for execution of a specific service mode of an application from a user through a voice command, the voice recognition terminal 100 checks information on the default service mode of the application and operates in the default service mode. A specific service mode may be called based on interface standard information for When the default service mode is running, the voice recognition terminal 100 analyzes the user's reaction (one of voice, facial expression, and gesture), stores the analyzed reaction in the reaction table 1100, and displays the reaction state 1102 and the number of hits ( Scores 1106 may be accumulated according to 1104).

The voice recognition terminal 100 includes a watch dog module 1110 that monitors the reaction table 1100, and when the score of a specific service mode is changed by the watch dog module 1110, the service app mode setting table The decision state 1108 of 1020 may be changed so that the service mode is driven in the determined service mode at the next service driving request.

Referring back to FIG. 2 , after the preferred service mode is determined, the voice input unit 200 may receive a voice command for the application from the user in a state in which the application is deactivated. In this case, the controller 210 may provide a voice service through the preferred service mode determined as the service mode of the application.

The reaction recognition unit 220 may recognize a user's reaction while providing a voice service through the determined preferred service mode.

When the recognized user's reaction corresponds to a negative evaluation, the controller 210 may change the preferred service mode to another service mode.

When data on the new service mode received from the server 110 exists, the controller 210 may change the preferred service mode to the new service mode for a certain period of time.

The memory 260 stores data input and output between components inside the voice recognition terminal 100, and is input and output between the voice recognition terminal 100 and components outside the voice recognition terminal 100. save the data

On the other hand, those skilled in the art, voice input unit 200, control unit 210, reaction recognition unit 220, voice recognition unit 222, image recognition unit 224, preference analysis unit 230, preference service mode determination unit ( 240), the receiver 250, and the memory 260 may be separately implemented, or one or more of them may be integrated and implemented.

3 is an operational flowchart illustrating a method for providing a customized service mode according to an embodiment of the present invention.

The method for providing a customized service mode according to the embodiment shown in FIG. 3 includes steps sequentially processed by the voice recognition terminal 100 and the server 110 in the embodiment shown in FIGS. 1 and 2 . Therefore, even if omitted below, the description of the voice recognition terminal 100 and server 110 of FIGS. 1 and 2 can be applied to the method for providing a customized service mode according to the embodiment shown in FIG. 3 .

Referring to FIG. 3 , in step S301, the voice recognition terminal 100 may receive a voice command for an application installed in the voice recognition terminal 100 from the user.

In step S303, the voice recognition terminal 100 may provide a voice service through a default service mode among a plurality of service modes of an application.

In step S305, the voice recognition terminal 100 may recognize a user's reaction while providing a voice service through a default service mode. Here, the reaction may be at least one of a user's voice, facial expression, and gesture.

In step S307, the voice recognition terminal 100 may change the default service mode to another service mode.

In step S309, the voice recognition terminal 100 may recognize a user's reaction while providing a voice service through another service mode. Here, the reaction may be at least one of a user's voice, facial expression, and gesture.

In step S311, the voice recognition terminal 100 may analyze the preference of each service mode based on at least one of a use history of each service mode and a reaction to each service mode.

In step S313, the voice recognition terminal 100 may determine a preferred service mode among a plurality of service modes based on the analyzed preference.

Although not shown in FIG. 3 , in step S307 , the voice recognition terminal 100 may determine whether or not a preset condition for changing to another service mode is met. Here, the preset condition may be the lapse of a preset time or the number of inputs of a reaction. The voice recognition terminal 100 may change the default service mode to another service mode when a preset condition for changing to another service mode is met.

Although not shown in FIG. 3 , in step S307 , the voice recognition terminal 100 may determine whether a request to change to another service mode is input. The voice recognition terminal 100 may change the default service mode to another service mode when a request to change to another service mode is received from the user.

Although not shown in FIG. 3 , after S313 , the voice recognition terminal 100 may receive application installation data and information about a plurality of service modes from the server 100 and install the application. Here, information on a plurality of service modes may include preferred age information and preferred gender information of each service mode.

In the above description, steps S301 to S313 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

4 is an operational flowchart illustrating a method of providing a voice service through a default service mode according to an embodiment of the present invention.

The method for providing a voice service through the default service mode according to the embodiment shown in FIG. 4 includes steps processed time-sequentially by the voice recognition terminal 100 in the embodiment shown in FIGS. 1 to 3 . Therefore, even if the content is omitted below, the description of the voice recognition terminal 100 and the server 110 of FIGS. 1 to 3 is also applied to the method of providing a voice service through the default service mode according to the embodiment shown in FIG. 4. can be applied

Referring to FIG. 4 , in step S401, the voice recognition terminal 100 may perform at least one of voice recognition of a user's voice command and image recognition of the user to identify at least one of the user's age, gender, and number of people. there is.

In step S403, the voice recognition terminal 100 may determine a default service mode based on the age, gender, and number of identified users.

In the above description, steps S401 to S403 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

5 is an operational flowchart illustrating a method of recognizing a user's reaction according to an embodiment of the present invention.

The method for recognizing a user's reaction according to the embodiment shown in FIG. 5 includes steps processed time-sequentially by the voice recognition terminal 100 in the embodiment shown in FIGS. 1 to 4 . Therefore, even if the content is omitted below, the description of the voice recognition terminal 100 and the server 110 of FIGS. 1 to 4 can be applied to the method for recognizing a user's reaction according to the embodiment shown in FIG. 5. there is.

Referring to FIG. 5 , in step S501 , the voice recognition terminal 100 may acquire a reaction voice by recognizing a user's voice while providing a voice service through a default service mode or another service mode.

In step S503, the voice recognition terminal 100 may store the recognized facial expression of the user as a facial expression corresponding to the positive evaluation when the acquired reaction voice includes a vocabulary corresponding to the positive evaluation.

In step S505, the voice recognition terminal 100 may store the recognized facial expression of the user as a facial expression corresponding to the negative evaluation when the reaction voice includes a vocabulary corresponding to the negative evaluation.

In the above description, steps S501 to S505 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

6 is an operational flowchart illustrating a method of analyzing a preference of a service mode according to an embodiment of the present invention.

The service mode preference analysis method according to the embodiment shown in FIG. 6 includes steps processed time-sequentially in the voice recognition terminal 100 in the embodiment shown in FIGS. 1 to 5 . Therefore, even if the content is omitted below, the description of the voice recognition terminal 100 and the server 110 of FIGS. 1 to 5 can be applied to the service mode preference analysis method according to the embodiment shown in FIG. 6. .

Referring to FIG. 6 , in step S601, the voice recognition terminal 100 may acquire a reaction voice by recognizing the user's voice.

In step S603, the voice recognition terminal 100 may determine whether a vocabulary included in the obtained reaction voice corresponds to a positive evaluation or a negative evaluation for each service mode.

In step S605, the voice recognition terminal 100 may accumulate scores for positive evaluation and negative evaluation for each service mode based on the determination in step S603.

In step S607, the voice recognition terminal 100 may analyze the preference of each service mode based on the accumulated scores.

In the foregoing description, steps S601 to S607 may be further divided into additional steps or combined into fewer steps, depending on an embodiment of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

7 is an operational flowchart illustrating a method of analyzing service mode preference according to another embodiment of the present invention.

The service mode preference analysis method according to the embodiment shown in FIG. 7 includes steps processed time-sequentially in the voice recognition terminal 100 in the embodiment shown in FIGS. 1 to 6 . Therefore, even if omitted below, the description of the voice recognition terminal 100 and the server 110 of FIGS. 1 to 6 can be applied to the service mode preference analysis method according to the embodiment shown in FIG. 7 . .

Referring to FIG. 7 , in step S701, the voice recognition terminal 100 may acquire a reaction expression or a reaction gesture by recognizing a user's image.

In step S703, the voice recognition terminal 100 may determine whether the acquired reaction expression or reaction gesture corresponds to a positive evaluation or a negative evaluation for each service mode.

In step S705, the voice recognition terminal 100 may accumulate scores for positive evaluation and negative evaluation for each service mode based on the determination in step S703.

In step S707, the voice recognition terminal 100 may analyze the preference of each service mode based on the accumulated scores.

In the foregoing description, steps S701 to S707 may be further divided into additional steps or combined into fewer steps, depending on an embodiment of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

8 is an operational flowchart illustrating a method for providing a customized service mode according to another embodiment of the present invention.

The method for providing a customized service mode according to the embodiment shown in FIG. 8 includes steps sequentially processed by the voice recognition terminal 100 in the embodiment shown in FIGS. 1 to 7 . Therefore, even if the content is omitted below, the description of the voice recognition terminal 100 and the server 110 of FIGS. 1 to 7 can be applied to the method for providing a customized service mode according to the embodiment shown in FIG. 8 .

Referring to FIG. 8 , in step S801, the voice recognition terminal 100 may receive a voice command for an application from a user.

In step S803, the voice recognition terminal 100 may provide a voice service in a preferred service mode predetermined through preference analysis of each service mode.

In step S805, the voice recognition terminal 100 may recognize a user's reaction while providing a voice service through a predetermined preferred service mode. Here, the reaction may be at least one of a user's voice, facial expression, and gesture.

In step S807, the voice recognition terminal 100 may change the preferred service mode when the recognized reaction corresponds to a negative evaluation.

In the above description, steps S801 to S807 may be further divided into additional steps or combined into fewer steps, depending on an embodiment of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

9 is an operational flowchart illustrating a method for providing a customized service mode according to another embodiment of the present invention.

The method for providing a customized service mode according to the embodiment shown in FIG. 9 includes steps sequentially processed by the voice recognition terminal 100 and the server 110 in the embodiment shown in FIGS. 1 to 8 . Therefore, even if omitted below, the description of the voice recognition terminal 100 and server 110 of FIGS. 1 to 8 can be applied to the method for providing a customized service mode according to the embodiment shown in FIG. 9 .

Referring to FIG. 9 , in step S901, the voice recognition terminal 100 may receive a voice command for an application from a user.

In step S903, the voice recognition terminal 100 may provide a voice service in a predetermined preferred service mode through preference analysis of each service mode.

In step S905, the voice recognition terminal 100 may receive data on a new service mode from the server 110.

In step S907, the voice recognition terminal 100 may change the predetermined preferred service mode to a new service mode.

In the above description, steps S901 to S907 may be further divided into additional steps or combined into fewer steps, depending on an embodiment of the present invention. Also, some steps may be omitted if necessary, and the order of steps may be changed.

An embodiment of the present invention may be implemented in the form of a recording medium including instructions executable by a computer, such as program modules executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transport mechanism, and includes any information delivery media.

The above description of the present invention is for illustrative purposes, and those skilled in the art can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present invention. .

100: voice recognition terminal
110: server
200: voice input unit
210: control unit
220: reaction recognition unit
222: voice recognition unit
224: image recognition unit
230: preference analysis unit
240: Preference service mode determining unit
250: receiver
260: memory

Claims (23)

A method for providing a customized service mode performed by a voice recognition terminal,
receiving a voice command for an application installed in the voice recognition terminal;
providing a voice service through a first service mode among a plurality of service modes of the application;
Recognizing a user's reaction while providing a voice service through the first service mode;
changing the first service mode to a second service mode;
Recognizing the user's reaction while providing the voice service through the second service mode;
Analyzing a preference for each service mode based on at least one of a use history of each service mode and the reaction for each service mode; and
Determining a preferred service mode among the plurality of service modes based on the analyzed preference
including,
The reaction includes the user's voice and expression,
Recognizing the user's reaction
storing a facial expression of a recognized user as a facial expression corresponding to a positive evaluation when the reaction voice obtained from the user's voice includes a vocabulary corresponding to a positive evaluation; and
When the reaction voice includes a vocabulary corresponding to negative evaluation, storing the recognized user's facial expression as a facial expression corresponding to negative evaluation,
The facial expression stored as the positive evaluation and the facial expression stored as the negative evaluation are used to classify whether a user's reaction expression, which is input next, corresponds to either a positive evaluation or a negative evaluation.
According to claim 1,
receiving a voice command for the application after the step of determining the preferred service mode; and
providing a voice service through the determined preferred service mode;
Further comprising, a method for providing a customized service mode.
According to claim 1,
Providing a voice service through the first service mode
identifying at least one of age, gender, and number of users of the user by performing at least one of voice recognition of the voice command and image recognition of the user; and
determining the first service mode based on the age, gender, and number of the identified users;
To include, a method for providing a customized service mode.
According to claim 1,
Wherein the reaction further comprises a gesture of the user, a method for providing a customized service mode.
According to claim 4,
Recognizing the user's reaction
Acquiring the reaction voice by recognizing the user's voice;
Analyzing the preference of each service mode
Determining whether the vocabulary included in the reaction voice corresponds to a positive evaluation or a negative evaluation for each service mode
To include, a method for providing a customized service mode.
According to claim 4,
Recognizing the user's reaction
Acquiring a reaction expression or a reaction gesture by recognizing the user's image;
Analyzing the preference of each service mode
The method of providing a customized service mode further comprising determining whether the reaction expression or reaction gesture corresponds to a positive evaluation or a negative evaluation for each of the service modes.
According to claim 5 or 6,
accumulating scores for the positive evaluation and the negative evaluation for each service mode based on the determination; and
Analyzing the preference of each service mode based on the accumulated score
To include, a method for providing a customized service mode.
According to claim 1,
receiving installation data of the application and information about the plurality of service modes from a server; and
installing the application;
Further comprising, a method for providing a customized service mode.
According to claim 8,
Wherein the information on the plurality of service modes includes preferred age information and preferred gender information of each service mode.
delete According to claim 1,
Changing the first service mode to the second service mode
Determining whether a predetermined condition for changing to the second service mode is satisfied;
Wherein the predetermined condition is the lapse of a predetermined time or the number of inputs of the reaction, a method for providing a customized service mode.
According to claim 1,
Changing the first service mode to the second service mode
and determining whether a request to change to the second service mode is input.
According to claim 2,
Recognizing the user's reaction while providing the voice service through the preferred service mode; and
The method of providing a customized service mode further comprising the step of changing the preferred service mode when the reaction corresponds to a negative evaluation.
According to claim 2,
Receiving data on a new service mode from a server; and
Changing the preferred service mode to the new service mode
Further comprising, a method for providing a customized service mode.
In the voice recognition terminal,
a voice input unit that receives a voice command for an application installed in the voice recognition terminal;
a controller that sets the service mode of the application to a first service mode during a preset condition and changes the service mode of the application to a second service mode after the preset condition;
a reaction recognition unit for recognizing a user's reaction while providing voice service through each of the service modes;
a preference analyzer configured to analyze a preference of each service mode based on at least one of a use history of each service mode and the reaction for each service mode; and
A preferred service mode determining unit determining a preferred service mode from among the plurality of service modes based on the analyzed preference.
including,
The reaction includes the user's voice and expression,
The reaction recognition unit
When the reaction voice obtained from the user's voice includes a vocabulary corresponding to a positive evaluation, the recognized user's facial expression is stored as a facial expression corresponding to a positive evaluation, and the reaction voice includes a vocabulary corresponding to a negative evaluation. At the same time, the user's facial expression recognized together is stored as a facial expression corresponding to negative evaluation,
The reaction recognition unit
Based on the facial expression stored as the positive evaluation and the facial expression stored as the negative evaluation, a reaction expression of a user input next is classified as a facial expression corresponding to a positive evaluation or a negative evaluation.
According to claim 15,
The voice input unit receives a voice command for the application after the preferred service mode is determined;
Wherein the control unit changes the service mode of the application to the determined preferred service mode.
According to claim 15,
The reaction further comprises a gesture of the user, the voice recognition terminal.
18. The method of claim 17,
The reaction recognition unit
a voice recognition unit that recognizes the user's voice and obtains the reaction voice; and
An image recognition unit that recognizes the user's image and obtains a reaction expression or a reaction gesture.
To include, a voice recognition terminal.
According to claim 18,
The voice recognition terminal, wherein the preference analysis unit is configured to determine whether the vocabulary included in the reaction voice corresponds to a positive evaluation or a negative evaluation for each of the service modes.
According to claim 18,
The voice recognition terminal, wherein the preference analysis unit is configured to determine whether the reaction expression or reaction gesture corresponds to a positive evaluation or a negative evaluation for each service mode.
According to claim 19 or 20,
Wherein the preference analyzer accumulates scores for the positive evaluation and the negative evaluation for each service mode based on the determination, and analyzes the preference for each service mode based on the accumulated score. Terminal.
According to claim 15,
Further comprising a receiving unit for receiving installation data of the application and information on the plurality of service modes from a server,
The information on the plurality of service modes includes preferred age information and preferred gender information of each of the service modes.
According to claim 18,
The reaction recognizing unit judges a recognized user's facial expression as a facial expression corresponding to a positive evaluation when the reaction voice includes a vocabulary corresponding to a positive evaluation, and recognizes a recognized expression when the reaction voice includes a vocabulary corresponding to a negative evaluation. A voice recognition terminal that determines a user's facial expression as a facial expression corresponding to negative evaluation.

Images