KR20160012233A - Interactive server, control method thereof and interactive system - Google Patents

Abstract

Disclosed are an interactive server, a method for controlling the same, and an interactive system. According to the present invention, the interactive server includes: a communications unit for receiving an articulation voice signal by communicating with a display device; a storage unit for storing articulation history information with respect to the articulation voice signal received from the display device; an extraction unit for extracting an articulation element from the received articulation voice signal; and a control unit for generating response information based on the articulation history information, stored in the storage unit, and the extracted articulation element and transmitting the generated response information to the display device. Therefore, the interactive server can understand the intentions of various users with respect to articulation voices, generate response information corresponding to the intention, and provide the response information to the display device.

Description

[0001] Interactive server, control method thereof and interactive system [0002]

The present invention relates to an interactive server, a control method thereof, and an interactive system, and more particularly, to an interactive server, a control method thereof, and an interactive system for providing response information corresponding to various utterances of a user .

Generally, a display device capable of voice recognition in an interactive system collects a user's uttered voice and transmits the collected voice to an external server connected through a network. The external server receiving the uttered voice analyzes the uttered voice to grasp the intention of the user, generates response information corresponding to the user's intention, and transmits the generated response information to the display device. Thereby, the display device can execute the function corresponding to the user's uttered voice or provide the information based on the response information received from the external server.

However, such a conventional interactive system has a limitation in analyzing a user's utterance voice and grasping the user's intention based on the analysis result. For example, in the case of a speech uttered with a clear object such as "show first content ", the external server analyzes the utterance voice to correctly understand the intention of the user, generates response information corresponding to the uttered voice, Lt; / RTI > Thus, the display device can display the first content requested by the user based on the response information.

However, when the user's utterance is ambiguous such as "Show me ", the external server can not clearly grasp the intention of the user from the uttered voice. In other words, the conventional interactive system grasps the intention of the user only for the predetermined utterance voice, performs the operation according to the user's intention, or provides the information, which has a problem that the utterance of the user is restricted.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-mentioned needs, and it is an object of the present invention to carry out an operation corresponding to the utterance of various users in an interactive system.

According to an aspect of the present invention, there is provided an interactive server comprising a communication unit for communicating with a display device and receiving a speech sound signal, a communication unit for communicating speech history information on the speech signal received from the display device, An extraction unit for extracting a speech element from the received speech speech signal; response information generation unit for generating response information based on the speech history information stored in the storage unit and the extracted speech element, To the device.

The control unit may generate the response information by combining an executable word and an instruction word corresponding to the uttered element if the executable word and the command word corresponding to the extracted uttered element exist in the storage unit, Estimating an executable word and a command corresponding to the extracted utterance element based on the utterance history information stored in the storage unit when the executable word and the command corresponding to the extracted utterance element are not present, And generate the response information in combination.

If the executable word and the command word corresponding to the extracted utterance element are not present in the storage unit, the control unit may select one of the utterance history information from among the utterance history information, Acquiring the speech history information within a predetermined time range on the basis of a time point at which the speech speech signal is received and generating an execution word corresponding to the first speech element and a second speech element corresponding to the second speech element in the obtained speech history information Command can be estimated by an executable word and a command corresponding to the utterance voice signal.

The control unit may not generate the response information if the ignition history information within a predetermined time range is not stored based on a time point at which the speech voice signal is received from the speech history information stored in the storage unit .

The control unit may be configured to determine whether or not at least one of the first speech element and the second speech element is included in the speech speech signal within a predetermined time range based on a time point at which the speech signal is received from the speech history information The response information corresponding to the speech voice signal can be generated based on the speech history information of the speech signal.

The voice processing unit may further include a voice processing unit for converting the received voice signal into text information.

According to an embodiment of the present invention, there is provided a method for controlling an interactive server, the method comprising: receiving a speech voice signal from a display device; extracting a speech element from the received speech voice signal; Generating response information based on the previously stored speech history information and the extracted speech element in association with the speech speech signal received from the apparatus, and transmitting the generated response information to the display device.

The method may further include determining whether an executable word and a command corresponding to the extracted utterance element are present, and in the event that an executable word and a command corresponding to the uttered element exist, When the execution word and the instruction word corresponding to the utterance element are absent, an executor corresponding to the extracted utterance element and an executor corresponding to the extracted utterance element based on the previously stored utterance history information, Estimate the command, and combine the estimated executable word and the command word to generate the response information.

In addition, the speech voice signal may include a first speech element and a second speech element, and in the step of generating, if an executable word and a command corresponding to the speech element are not present, Acquiring the speech history information within a predetermined time range based on the received time point, and executing a command corresponding to the execution word corresponding to the first speech element and the second speech element in the obtained speech history information, It can be estimated by an executable word and a command corresponding to the voice signal.

The generating step may not generate the response information if the ignition history information within the predetermined time range is not stored based on the time point at which the speech voice signal is received.

The generation step may include a step of generating a speech signal based on a time point at which the speech signal is received from the speech history information when the speech signal includes at least one of the first speech element and the second speech element, Response information corresponding to the spoken voice signal can be generated based on the spoken history information within the range.

The method may further include converting the received speech signal into text information.

According to another aspect of the present invention, there is provided an interactive system comprising: a display device that performs a function corresponding to a speech uttered when a user's speech is input; And an interactive server for extracting a speech element from the speech signal and generating response information based on the previously stored speech history information and the extracted speech element and transmitting the generated response information to the display device, And can perform a function corresponding to the user's intention based on the response information received from the server.

The interactive server may generate the response information based on an executable word and a command word corresponding to the uttered element when the executable word and the command word corresponding to the extracted uttered element exist, If the corresponding executable word and command do not exist, it is possible to estimate the executable word and command word corresponding to the extracted utterance element based on the previously stored utterance history information, and generate the response information by combining the estimated executable word and the command word have.

As described above, according to the various embodiments of the present invention, in the interactive system, the interactive server can grasp the intention of the user with respect to the speech utterances of various users, and generate response information according to the user's intention and provide the generated response information to the display device.

1 is a first example of an interactive system for providing response information suitable for a user uttered voice according to an embodiment of the present invention,
2 is a second example of an interactive system for providing response information suitable for a user uttered voice according to another embodiment of the present invention,
3 is a block diagram of an interactive server in accordance with an embodiment of the present invention.
FIG. 4 is a diagram illustrating an example of generating ignition information based on a display state of an object displayed on a screen in a display device according to an exemplary embodiment of the present invention; FIG.
5 is a block diagram of a display device according to an embodiment of the present invention;
FIG. 6 is a flowchart illustrating a method of controlling an interactive server according to an exemplary embodiment of the present invention;
7 is a flowchart of a method for generating response information in an interactive server according to one embodiment of the present invention.

Hereinafter, a temporal example of the present invention will be described in detail with reference to the accompanying drawings.

1 is a first exemplary view of an interactive system for providing response information suitable for a user uttered voice according to an embodiment of the present invention.

1, an interactive system according to an embodiment of the present invention includes a display device 100 and an interactive server 200. [

The display device 100 is an Internet-enabled device and can be implemented by various electronic devices such as a smart TV, a mobile phone such as a smart phone, a desktop PC, a notebook, and a navigation device. When the user's voice is input, the display device 100 performs an operation corresponding to the input voice of the user. Specifically, the display apparatus 100 may output a response message corresponding to a user's uttered voice or may perform a function corresponding to the uttered voice of the user. That is, the display apparatus 100 analyzes the input uttered voice to determine whether it can be performed internally, performs a function corresponding to the input uttered voice according to the determination result, or receives And can perform an operation based on one response information.

For example, when a speech sound called "volume up" is input, the display device 100 can adjust the volume based on control information corresponding to the input speech sound among the previously stored control information.

In another example, when a speech voice "What is today's weather?" Is input, the display device 100 transmits a speech voice signal for the inputted speech voice to the interactive server 200. Here, the speech voice may be an analog signal. Accordingly, the display apparatus 100 converts the speech sound, which is an analog signal, into a digital signal (hereinafter, referred to as a speech sound) and transmits the speech signal to the interactive server 200. Thereafter, the display apparatus 100 can output the result of today's weather as a video in the form of voice or text based on the response information received from the interactive server 200.

For example, when a voice uttered "ooooo (content name)" is input, the display device 100 transmits the input utterance voice to the interactive server 200. [ Thereafter, when the response information is received from the interactive server 200, the display device 100 can display a search list for (XXX) (content name) based on the received response information. Here, the search list may include content-specific content information for (xxx) (content name). Accordingly, the user can check the content information for each content displayed on the search list, and make a speech for selecting the content of the content of the content of the content to be viewed by the user. For example, the user can utter "show first" in order to view the XXX (content name) corresponding to the first content information among the content information classified by the content displayed on the search list. Accordingly, the display device 100 receives the speech voice "show first" and transmits it to the interactive server 200. Then, when the response information corresponding to the uttered voice received from the interactive server 200 is received, the display device 100 displays the content ID of the first content information on the basis of the received response information, From the providing server 300 and display it.

The interactive server 200 provides response information suitable for the user's intention based on the speech voice of the user received from the display device 100. [ Specifically, when the user's uttered voice is received by the display device 100, the interactive server 200 extracts the uttered element from the received uttered voice, and based on the extracted uttered element, Information can be generated and transmitted. As described above, the speech voice of the user received from the display device 100 may be a digital signal. Accordingly, when the speech server 200 receives the speech signal converted into the digital signal, it generates text information, extracts the speech element by analyzing the generated text information, The response information corresponding to the speech voice can be generated. Since it is a known technique to generate text information from a speech sound converted into a digital signal, a detailed description thereof will be omitted in the present invention.

On the other hand, as a key keyword for performing an action requested by a user in a speech voice of a user, a speech element can classify a speech element extracted by a target domain, a user action, and a main feature have. As described above, when the text information about the user's utterance voice is generated, the interactive server 200 extracts the utterance elements "today "," . Then, the interactive server 200 classifies the extracted " today "and" weather "into a utterance element (hereinafter referred to as a first utterance element) ? "May be classified into a utterance element (hereinafter referred to as a second utterance element) for a target function (hereinafter referred to as an execution command). Further, the interactive server 200 can classify the utterance element (hereinafter referred to as the third utterance element) for the target area as belonging to the domain of web search, based on the extracted utterance element. As described above, when the first to third utterance elements are classified from the text information of the uttered voice of the user, the interactive server 200 receives weather information from the external server 400 that provides various contents, And transmits the generated response information to the display device 100. [ Accordingly, the display apparatus 100 can display today's weather information through at least one of voice and text based on the response information received from the interactive server 200. [

On the other hand, when the textual information about the utterance voice "Create First" is generated, the interactive server 200 generates a first utterance element "first" and a second utterance element "select" from the generated text information Can be extracted. When such first and second speech components are extracted, the interactive server 200 determines whether or not it is possible to generate response information suitable for the user's intention based on the extracted first and second speech components. According to an embodiment, the interactive server 200 can determine whether to generate response information suitable for the user's intention according to whether the information corresponding to the extracted first and second speech elements exists in the database. Here, the information corresponding to the first and second utterance elements may be a command corresponding to the execution word and the second utterance element corresponding to the first utterance element. Thus, the interactive server 200 determines whether the executable word and the instruction corresponding to the extracted first and second utterance elements are present in the database. As a result of the determination, if the information corresponding to the extracted first and second utterance elements is not present in the database, the interactive server 200 determines whether or not the utterance voice " The response information may be generated based on the ignition history information and the extracted first and second speech components, and the response information may be transmitted to the display device 100. For example, immediately before a speech voice of "select first" is received, a speech voice of "find (name of content)" may be received, and the speech history information of such speech voice is stored . Therefore, the interactive server 200 can generate the content execution related response information for "XXX (content name) " based on the previous spoken history information, and transmit the generated content execution response information to the display device 100. [ Accordingly, the display apparatus 100 can display the first content for "XXX (content name) " based on the response information received from the interactive server 200. [

Meanwhile, the interactive server 200 includes a first server 10 for generating a speech sound of a user converted into a digital signal into text information, and a second server 10 for generating response information corresponding to the speech sound generated by the text information. Server 20 as shown in FIG. Hereinafter, an interactive system for providing response information suitable for a user's utterance voice through the display device 100, the first and second servers 10 and 20 will be described in detail.

2 is a second exemplary diagram of an interactive system for providing response information suitable for a user utterance voice according to another embodiment of the present invention.

As shown in FIG. 2, the display apparatus 100 converts the input utterance voice into a digital signal and transmits the voice signal to the first server 10 when a voice uttered by the user is input. When the speech signal is converted into a digital signal, the first server 10 generates text information on the speech uttered by the user according to a specific pattern of various stored speech utterances, and transmits the text information to the display device 100.

The display device 100 receiving the text information of the user's uttered voice from the first server 10 transmits the text information of the user's uttered voice to the second server 20. [ The second server 20 receiving the text information of the user's uttered voice analyzes the received text information to extract the uttered element and performs an operation corresponding to the uttered voice of the user based on the extracted uttered element And transmits the generated response information to the display device 100. [

Up to now, an operation of providing response information corresponding to a user's uttered voice in an interactive system including the display device 100 and the interactive server 200 according to the present invention has been described. Hereinafter, each configuration of the display device 100 and the interactive server 200 will be described in detail.

3 is a block diagram of an interactive server in accordance with an embodiment of the present invention.

3, the interactive server 200 includes a communication unit 210, a voice processing unit 220, a storage unit 230, an extraction unit 240, and a control unit 250.

The communication unit 210 performs communication with the display device 100 that provides the user's uttered voice. In particular, the communication unit 210 may receive a digital signal (hereinafter referred to as a speech voice) for a speech utterance including a first speech element indicating an execution target and a second speech element indicating an execution command. Here, the first utterance element indicating the execution command is a utterance element classified as a main feature in the utterance voice of the user, and the second utterance element indicating the utterance command is a user action ). ≪ / RTI > For example, in the case of an utterance voice called "find an action movie "," action "may be the first utterance element classified as the main feature, and" find "may be the second utterance element classified as the objective function.

When the utterance voice including the first and second utterance elements is received, the voice processor 220 converts the received utterance voice into text information. According to an embodiment, the voice processing unit 220 can convert the voice of the user, which has been received, to text using a speech to text (STT) algorithm. However, the present invention is not limited to this, and the communication unit 210 may receive text information on the user's utterance voice from the display device 100. [ In this case, the display apparatus 100 receives text information on the input speech of the user from a speech recognition apparatus (not shown) such as the first server 10 and transmits the text information to the interactive server 200. Therefore, the communication unit 210 can receive text information on the uttered voice of the user from the display device 100. [ As described above, when the text information on the uttered voice of the user is received from the display device 100, the configuration of the voice processing unit 220 described above may be omitted.

On the other hand, when the user's utterance voice is converted into text information or when the text information of the user's utterance voice is received from the display device 100, the extractor 240 extracts the utterance component from the utterance voice converted into the text information . As described above, the extracting unit 240 can extract a first speech element representing a main feature and a second speech element representing an execution command from a speech speech converted into text information.

As in the above example, in the case of a utterance voice called "find an action movie ", the extractor 240 can extract a first utterance element called" action " have. As another example, in the case of a utterance voice "Let's do it", the extracting unit 240 can extract a first utterance element called "this" and a second utterance element called "execute".

When the utterance element is extracted, the control unit 250 generates response information based on the utterance history information stored in the storage unit 230 and the extracted utterance element, and transmits the generated response information to the display apparatus 100 . Here, the storage unit 230 is a storage medium that stores various programs necessary for operating the interactive server 200, and may be implemented as a memory, a hard disk drive (HDD), or the like. For example, the storage unit 230 may include a ROM that stores a program for performing an operation of the controller 250, a RAM that temporarily stores data according to an operation of the controller 250, and the like. In addition, the storage unit 230 may further include an EEROM (Electrically Erasable and Programmable ROM) for storing various reference data. In particular, the storage unit 230 may store the ignition history information of the utterance voice received from the display device 100. [ Here, the speech history information is information generated based on the speech utterance received before the speech utterance is received from the display device 100. Specifically, the storage unit 230 stores text information generated from speech utterances received from the display device 100, time information at which the uttered speech was received, response information generated based on the uttered speech, and corresponding response information And time information indicating the occurrence of the failure.

Therefore, the control unit 250 generates response information based on at least one of the speech history information before the current speech speech is received and the speech element extracted from the received speech speech among the previous speech history information stored in the storage unit 230 And transmit it to the display device 100. Specifically, the control unit 250 determines whether information corresponding to the uttered element extracted from the extracting unit 240 exists in the storage unit 230. If the information corresponding to the extracted uttered element exists, And generates response information based on the information corresponding to the element. Here, the information corresponding to the extracted utterance element may include at least one of an executable corresponding to a first utterance element representing an execution object and a command corresponding to a second utterance element representing an execution command. Such an executable word and an instruction may be stored in the storage unit 230. That is, the storage unit 230 may further store an instruction defined for each of the execution words and the second utterance elements defined for the first utterance element. For example, a first utterance element indirectly representing an execution object called " this "may be defined as an executable word" $ this $ ", and a first utterance element indirectly representing an execution object called " $ ", And the first utterance element that indirectly represents the execution object" third "can be defined as the executable word" $ 3rd $ ". In addition, the first utterance element such as "XXX (content name) ", which directly indicates the execution object, can be defined as an executable word" $ xxx (content name) $ ". On the other hand, the second utterance element indicating the execution command includes a first utterance element that directly indicates the utterance object, and a content search, content recommendation, device function execution, device UI control And web search, and the instruction can be defined corresponding to each classified type. Accordingly, when the speech element is extracted from the speech uttered by the user, the controller 250 determines whether the execution word and the command corresponding to the extracted speech element are stored in the storage unit 230. [ As a result of the determination, if the executable word and the command corresponding to the extracted utterance element are stored, the control unit 250 acquires the executable word and the command word corresponding to the extracted utterance element, combines the obtained executable word and the command word, Lt; / RTI >

For example, in the case of a utterance voice of "find a (name of) content", the extracting unit 240 extracts a first utterance element for "ooooo (content name)" and a second utterance element for " It is possible to extract the ignition element. As described above, when the first and second utterance elements are extracted from the utterance uttered as "Find " oo (content name) ", the control unit 250 determines that the execution region is content based on the extracted first utterance element do. Also, the control unit 250 refers to the executable word defined by the first utterance element stored in the storage unit 230 and generates an executable word corresponding to the first utterance element for "XXX (content name)" (Content name) $ ". Further, the control unit 250 determines that the type of the second utterance element for "find" is related to the content search based on the execution region determined as the content The control unit 250 can obtain the command "content_search" corresponding to the content search among the commands defined for the second utterance element stored in the storage unit 230. [ An execution command script called "content_search ($ (content name) $)" can be generated by combining the executable word "$ 0 (content name) $" and the command "content_search" . When such an execution command script is generated, the control unit 250 stores the generated execution command script The display device 100 receives response information from the content providing server 300 on the basis of the execution command script included in the response information received from the interactive server 200, (Content name) ", and display the content list of the received content information on the screen on the screen.

However, the present invention is not limited to this, and the control unit 250 may extract the EPG information stored in the storage unit 230 based on an execution command script called "content_search ($ (Content name) ", or may receive the content information from the external server 400 and transmit the content information to the display device 100. [

For another example, in the case of a utterance voice of "make a sleep reservation ", the extracting unit 240 may extract a first utterance element for" sleep reservation " Thus, when the first and second utterance elements are extracted from the utterance utterance "make a sleep reservation", the controller 250 determines that the execution region is the device control based on the extracted first utterance element. Further, the control unit 250 obtains the executable word "$ sleep reservation $" corresponding to the first utterance element for "sleep reservation " with reference to the executable word defined by the first utterance element stored in the storage unit 230 . In addition, the control unit 250 determines that the type of the second utterance element for "let me" corresponds to the execution of the device function, based on the execution region determined by the device control. Accordingly, the control unit 250 can obtain the command "device_execute " corresponding to the execution of the device function among the commands defined for the second utterance element stored in the storage unit 230. [ Then, the control unit 250 can generate an execution command script called "device_execute ($ sleep reservation $) " by combining the executable word" $ sleep reservation $ "and the command" device_execute "corresponding to the first and second utterance elements have. When such an execution command script is generated, the control unit 250 transmits the response information including the generated execution command script to the display device 100. Accordingly, the display apparatus 100 sets the sleep schedule based on the execution command script included in the response information received from the interactive server 200, and transmits a notification message indicating that the sleep schedule is set to at least one of voice and text It can be output through one.

In another example, when the utterance information including the utterance voice "Select first" and the execution information is received, the extracting unit 240 extracts a first utterance "first" from the utterance utterance " Element and "select" can be extracted. In this way, when the first and second uttered speech elements are extracted from the uttered speech uttered "Select first", the control unit 250 refers to the defined utterance word stored in the storage unit 230 for each first utterance element, &Quot; corresponding to the first utterance element "$ 1st $ " for" In addition, the control unit 250 determines that the execution region is the device UI control based on the execution information included in the received utterance information, and determines the type of the second utterance element for "select" based on the determined execution region Is determined to correspond to the device UI control. Accordingly, the control unit 250 can obtain the command "device_select " corresponding to the device UI control among the commands defined for the second utterance element stored in the storage unit 230. [ On the other hand, when the executable word "$ 1st $" corresponding to the first utterance element corresponding to "first" is obtained, the control unit 250 determines, based on execution information included in the utterance information received from the display apparatus 100 Into executable corresponding to executable word "$ 1st $ ". Thereafter, the control unit 250 can generate an execution command script by combining the converted execution word and the command word from the executable word "$ 1st $ ".

Hereinafter, the operation of transmitting the speech information including the utterance voice and the execution information from the display device 100 to the interactive server 200 and the operation of receiving from the interactive device 200 from the display device 100 The operation of generating response information based on the generated speech information will be described in detail.

FIG. 4 is a diagram illustrating an example of generating spoken information based on a display state of an object displayed on a screen in a display device according to an embodiment of the present invention. FIG.

As shown in FIG. 4, the display device 100 can receive and display the first content 30 through a channel requested by the user. Also, the display device 100 may display a content list 40 for the second content requested by the user on the screen based on a user command. As shown in the figure, the content-specific content information 41 to 45 for the second content broadcasted so far can be displayed on the content list 40. On the other hand, the display apparatus 100 may provide identification information on each of the content-specific content information 41 to 45 displayed on the content list 40 on the basis of the predetermined priority. In this state, when the first content 30 and the content list 40 for the second content are displayed on the screen, the user refers to the content information 41 to 45 displayed on the content list 40, It is possible to make a speech for viewing the corresponding second contents. For example, the user can utter the phrase " select the third time "in order to view the second content corresponding to the third-time content information 43. [ When the utterance voice is input, the display device 100 determines whether or not the currently input utterance voice is input within a predetermined time based on the input time of the previous utterance voice. As a result of the determination, if it is determined that the input is made within a predetermined time, the display device 100 transmits a speech voice of "Choose the third choice" to the interactive server 200. On the other hand, if it is determined that the currently input uttered voice has not been input within a predetermined time, the display apparatus 100 displays the utterance voice of "select the third choice" To the interactive server 200, the identification information (the above-described execution information) given to the interactive server 200. [

When such utterance information is received, the extracting unit 240 can extract a first utterance element of "third" and a second utterance element of "select" from the utterance utterance included in the received utterance information. When the first and second uttered elements are extracted, the controller 250 determines whether the executer and the command corresponding to the extracted first and second uttered elements are stored in the storage unit 230. As described above, the storage unit 230 may store executables and commands defined for the first and second utterance elements. Accordingly, the control unit 250 can obtain the executable word "$ 3rd $" corresponding to the first utterance element for the "third" by referring to the executable word defined by the first utterance element stored in the storage unit 230 . The control unit 250 determines that the execution region is the device UI control based on the identification information included in the received spoken information, and determines the type of the second spoken element for "select" based on the determined execution region Is determined to correspond to the device UI control. Accordingly, the control unit 250 can obtain the command "device_select " corresponding to the device UI control among the commands defined for the second utterance element stored in the storage unit 230. [ On the other hand, when the executable word "$ 3rd $" corresponding to the first utterance element corresponding to "first" is acquired, the control unit 250 determines, based on the identification information included in the utterance information received from the display apparatus 100, Into executable corresponding to executable word "$ 3rd $ ". For example, if the identification information of the content information 43 corresponding to "$ 3rd $ " among the content-specific content information 41 to 45 is" # 3 ", the control unit 250 determines that the opportunity word &Quot; to "# 3" Thereafter, the control unit 250 generates an execution command script called " device_select (# 3) " by combining the converted execution word "# 3" and the command "device_select ", and sends the response information including the execution command script to the display device 100 Lt; / RTI > Accordingly, the display apparatus 100 receives the second content of the content corresponding to the content information 43 from the content providing server 300 based on the execution command script included in the response information received from the interactive server 200 And receive and display it.

As described above, when there is an executable word and a command word corresponding to the uttered speech element extracted from the speech uttered by the user, the control unit 250 determines whether or not the word corresponding to the user's intention based on the executable word and the command word corresponding to the uttered element Response information can be generated.

On the other hand, when an executable word and an instruction corresponding to the uttered element extracted from the uttered speech of the user are absent, the control unit 250 determines whether or not the executable word corresponding to the uttered element extracted based on the utterance history information previously stored in the storage unit 230 And instructions. Then, the control unit 250 may combine the estimated directive and the command word to generate response information suitable for the user's intention.

According to the embodiment, when the extracted speech element, that is, the executable word corresponding to the first and second speech elements, and the instruction word are not present, the control unit 250 determines that the speech utterance And obtains the ignition history information within a predetermined time range based on the received time point. Thereafter, the controller 250 may estimate a command corresponding to the first utterance element and the second utterance element corresponding to the first utterance element in the obtained utterance history information with an executable word and a command corresponding to the uttered voice. On the other hand, the controller 250 does not generate the response information if the ignition history information stored in the storage unit 230 does not store the ignition history information within the predetermined time range based on the time when the current speech is received.

As described above, the storage unit 230 stores text information generated from speech utterances received from the display device 100, time information when the utterance speech is received, response information generated based on the utterance speech, May store the ignition history information including at least one of the generated time information. Accordingly, if at least one of the executable word and the command corresponding to the first and second uttered speech elements extracted from the currently received uttered speech is not stored in the storage unit 230, It is possible to estimate executables and commands corresponding to the first and second utterance elements based on the previously stored utterance history information.

For example, in the case of a utterance voice "select first", the extractor 230 may extract a first utterance element of "first" and a second utterance element of "select". When the first and second uttered elements are extracted, the controller 250 determines whether the executer and the command corresponding to the first and second uttered elements are stored in the storage unit 230. Specifically, the control unit 250 can obtain the executable word "$ 1st $" corresponding to the first utterance element "first" by referring to the executable word defined by the first utterance element stored in the storage unit 230 . On the other hand, the control unit 250 determines whether the execution region can be determined based on the first spoken element among the extracted spoken elements. As a result of the determination, if it is determined that the execution region is impossible from the first utterance element for the " first ", the control section 250 selects the second utterance element The command corresponding to the utterance element can not be obtained. Accordingly, the control unit 250 determines that the execution region and the execution command for providing the service for the uttered voice from the utterance voice "select first" are unclear. According to the determination result, the controller 250 determines whether or not there is the speech history information stored within the predetermined time range based on the time point at which the utterance voice of "select first" among the speech history information stored in the storage unit 230 is received . That is, the control unit 250 determines whether the time difference between the time when the utterance voice of "select the first time ", which is stored in the storage unit 230, and the most recently stored previous speech history information is within the predetermined time range Or not. As a result of the determination, if it is determined that the previous speech history information does not fall within the preset time range, the control unit 250 does not generate the response information for the speech word "Select the first time ". On the other hand, if it is determined that the previous speech history information is within the predetermined time range, the extraction unit 240 extracts the first and second speech elements from the text information of the speech speech included in the previous speech history information.

For example, if the utterance voice included in the previous utterance history information is "OOo (content name) found ", the extracting unit 240 extracts a first utterance element for" Find "the second utterance element. Thereafter, the control unit 250 determines whether or not the " first "value is " first " based on the first utterance element for" It is assumed that the first utterance element is the first utterance element for "OOO (content name) ". Then, the control unit 250 determines that the execution region is the device UI control based on the estimated first utterance element, and outputs the instruction corresponding to the device UI control among the commands defined for the second utterance element stored in the storage unit 230 "device_select" can be obtained. Then, the control unit 250 combines the executable word "$ 1st $" corresponding to the first uttered element and the command "device_select" Lt; / RTI > Then, the control unit 250 transmits the response information including the generated execution command script to the display device 100. Accordingly, the display apparatus 100 can output at least one of voice and text as a response message "Select the first content" on the basis of the response information received from the interactive server 200. [ In addition, the display device can receive and display the first content from the content providing server 300 based on the execution command script included in the response information.

According to a further aspect of the present invention, if at least one of the first and second utterance elements is not included in the received utterance speech, The response information can be generated based on the ignition history information within a predetermined time range based on the received time point.

For example, in the case of a speech utterance such as "yes ", the extraction section 240 fails to extract the first and second utterance elements from the utterance utterance" yes ". In this case, the control unit 250 determines that the utterance voice of "Yes" is unclear, and when the utterance voice of "Yes" in the utterance history information stored in the storage unit 230 is received, And obtains the stored previous speech history information. For example, if the utterance voice included in the acquired previous utterance history information is "TV off ", the control unit 250 extracts a first utterance element for" TV " Thereafter, the control unit 250 estimates that the uttered voice "yes" currently received based on the extracted first and second utterance elements is confirmed. Accordingly, the control unit 250 determines that the execution region is device control based on the first utterance element for "TV" extracted from the previous utterance history information. Further, the control unit 250 can obtain an executable word "$ TV $" corresponding to the first utterance element for "TV " by referring to the executable word defined by the first utterance element stored in the storage unit 230 . Further, the control unit 250 determines that the type of the second speech element for "turn off" is related to the execution of the device function based on the execution region determined as the device control. Accordingly, the control unit 250 acquires a command corresponding to the execution of the device function among the commands defined for the second utterance element in the storage unit 230. [ Thereafter, the control unit 250 may acquire the command "device_exectue_turn off " corresponding to the power control among the acquired commands corresponding to the execution of the device function. Thereafter, the control unit 250 combines the execution word "$ TV $" corresponding to the first utterance element and the command "device_exectue_turn off" corresponding to the second utterance element to generate an execution command script "device_exectue_turn off ($ TV $) . When such an execution command script is generated, the control unit 250 transmits the response information including the generated execution command script to the display device 100. Accordingly, the display apparatus 100 can turn off the TV power supply based on the execution command script included in the response information received from the interactive server 200. [

Up to now, each configuration has been described in detail in the interactive server 200 according to the present invention. Hereinafter, each configuration of the display apparatus 100 receiving the user's uttered voice will be described in detail.

5 is a block diagram of a display device according to an embodiment of the present invention.

5, the display device 100 includes an input unit 110, a communication unit 120, a display unit 130, a control unit 140, and a storage unit 150.

The input unit 110 receives a speech uttered by the user. Specifically, the input unit 110 samples the input speech uttered by the user and converts the speech into a digital signal. At this time, if there is a noise (for example, air conditioner sound, cleaner sound, etc.) in the input speech of the user, the input unit 110 converts the speech sound of the user whose noise has been removed to a digital signal . In addition, the input unit 110 may receive various user operations and transmit the received various user operations to the control unit 130. In this case, the input unit 110 inputs a user operation command through a key pad or a touch screen having a touch pad, various function keys, numeric keys, special keys, and character keys Can receive.

The communication unit 120 transmits the user's utterance voice input through the input unit 110 to a server device (hereinafter referred to as an interactive server) and receives response information corresponding to the voice uttered. Here, the communication unit 120 may include various communication modules such as a short-range wireless communication module (not shown), a wireless communication module (not shown), and the like. Here, the short-range wireless communication module (not shown) is a communication module that performs wireless communication with an interactive server 200 located at a short distance and an external server (not shown) that provides contents. For example, Bluetooth, ZigBee, . A wireless communication module (not shown) is a module that is connected to an external network and performs communication according to a wireless communication protocol such as WiFi, IEEE, or the like. In addition, the wireless communication module further includes a mobile communication module for performing communication by accessing a mobile communication network according to various mobile communication standards such as 3G (3rd Generation), 3rd Generation Partnership Project (3GPP), Long Term Evolution You may.

The display unit 130 is implemented by a liquid crystal display (LCD), an organic light emitting diode (OLED) or a plasma display panel (PDP) It is possible to provide a variety of display screens that can be provided through the Internet. In particular, the display unit 161 displays content or content information corresponding to the user's utterance voice based on the response information received from the interactive server 200. [

The control unit 140 controls the overall configuration of the display device 100. FIG. In particular, when response information including an execution command script generated by a combination of an executable word and an instruction word is received from the interactive server 200, the control unit 140 performs an operation based on the execution command script included in the received response information .

As described in the above example, when the response information of the user "Find XXXX (content name)" is spoken from the interactive server 200, the control unit 140 executes the execution (Content name) "from the content providing server 300 via the communication unit 120 based on the command script, and displays the content list of the received content information for each content on a display unit (130) on the screen. Concretely, the response information received from the interactive server 200 may include an execution command script called "content_search ($ OO (content name) $) ". Accordingly, the control unit 140 interprets an execution command script called "content_search ($ (content name) $) ", and the execution word is" $ . As described above, if the directive and the command are distinguished from the execution command script, the control unit 140 receives the content-by-content information for the content "○○○ (content name)" from the content providing server 300 based on the divided indicator , And control the display unit 130 to display the content list of the received content information for each content on the screen. However, the present invention is not limited to this, and the communication unit 120 may receive response information including content-based content information for the " xxx (content name) " from the interactive server 200. In this case, the control unit 140 displays, on the display unit 130, the content-by-content-for-each-content information for the content "OOO (content name)" included in the response information received from the interactive server 200 .

As described in another example described above, when the response information for the user's utterance voice is received from the interactive server 200, the control unit 140 determines whether or not the user So that the sleep timer can be automatically set to a preset time. Specifically, the response information received from the interactive server 200 may include an execution command script called "device_execute ($ sleep reservation $) ". Therefore, the control unit 140 interprets an execution command script called " device_execute ($ sleep reservation $) ", so that the execution word is "$$ sleep reservation $$ ", and the command is" device_execute ". In this way, if the instruction and the instruction are distinguished from the execution command script, the control unit 140 can automatically set the sleeping reservation at a predetermined time based on the divided indicator. If such a sleep schedule is automatically set, the control unit 140 can output a notification message in the form of a text "sleep setting is completed" on the screen through the display unit 130 based on the received response information have.

4, the display unit 130 may receive and display the first content 30 on a channel requested by the user according to a control command of the controller 140. [ Also, the display unit 130 may display a content list 40 for the second content requested by the user on the screen based on the user command. If the content list 40 including the content-specific content information 41 to 45 for the second content is displayed on the screen, the control unit 140 displays the content-based content information 41 To 45) can be given. In this way, in the state where the first content 30 and the content list 40 for the second content are displayed on the screen, a speaking voice for viewing the second content corresponding to the specific turn can be input from the user . For example, the user can utter the phrase " select the third time "in order to view the second content corresponding to the third-time content information 43. [ When the utterance voice is input, the control unit 140 determines whether or not the utterance history information about the utterance voice "Select Third" is stored in the storage unit 150. Here, the ignition history information may include time information in which a speech input from a previous user and a corresponding speech sound are input. As a result of the determination, if the ignition history information is not stored, the control unit 140 sets the ignition information including the "third choice" speech information and the identification information given to the content information 41- To the server (200).

On the other hand, if the ignition history information is stored in the storage unit 150, the control unit 140 acquires the latest ignition history information based on the time information included in the stored ignition history information. Thereafter, the control unit 140 determines whether or not the speech voice "select third" is input within a predetermined time based on the time information included in the estimated speech history information. If it is determined that the input is made within the predetermined time, the control unit 140 transmits a speech voice of "select the third choice" to the interactive server 200 through the communication unit 120. [ On the other hand, if it is determined that the currently input uttered voice has not been input within a predetermined time, the control unit 140 determines whether or not the utterance voice of "third choice" (The above-described execution information) given to the interactive server 200. The interactive server 200 then transmits the generated information to the interactive server 200. [

Thereafter, when the response information for the utterance voice of "Choose the third choice" is received from the interactive server 200, the control unit 140 displays the content information 41 The second content corresponding to the third time content information 43 among the first to fourth content information 43 to 45 may be received from the content providing server 300 and displayed through the display unit 130.

Up to this point, each configuration of the display apparatus 100 for recognizing the user's utterance voice according to the present invention and performing an operation based on the response information corresponding to the recognized utterance voice has been described in detail. Hereinafter, a method of controlling the interactive server 200 that provides response information corresponding to a user's uttered voice and the display device 100 that performs an operation based on the response information will be described in detail.

6 is a flowchart illustrating a method of controlling an interactive server according to an exemplary embodiment of the present invention.

6, the interactive server 200 receives an utterance voice signal (hereinafter referred to as a utterance voice) from the display device 100 (S610). Here, the speech voice of the user is a voice signal converted from a voice signal of analog form into a digital signal. When such a speech sound is received, the interactive server 200 converts the received speech sound into text information (S620). According to an embodiment, the interactive server 200 may convert a user's utterance voice to text using a Speech to Text (STT) algorithm. However, the present invention is not limited to this, and the interactive server 200 may receive the text information of the user's utterance voice from the display device 100. [ In this case, the display apparatus 100 receives text information on the input speech of the user from the ASR server, such as the first server 10, and transmits the text information to the interactive server 200. Thus, the interactive server 200 can receive textual information about the user's utterance voice from the display device 100. [

When the user's uttered voice is converted into text information or the textual information of the user's uttered voice is received from the display device 100, the interactive server 200 extracts the utterance element from the utterance voice converted into text information (S630). In other words, the interactive server 200 extracts a first speech element representing a main feature and a second speech element representing an execution command from a speech speech converted into text information. When at least one of the first and second uttered elements is extracted, the interactive server 200 determines whether to generate response information suitable for the user's intention based on the extracted utterance element (S640). As a result of the determination, if it is determined that response information can not be generated based on the extracted speech element, the interactive server 200 does not generate response information from the speech uttered by the user. On the other hand, if it is determined that response information can be generated based on the extracted speech element, the interactive server 200 generates response information from the speech uttered by the user. Thereafter, the interactive server 200 transmits the generated response information to the display device 100 (S650).

Specifically, when the first and second uttered elements are extracted from the uttered voice of the user, the interactive server 200 judges whether or not the executable word and the instruction corresponding to the extracted first and second uttered elements are stored in advance do. Here, the first utterance element is a utterance element representing a main feature, and the second utterance element is a utterance element representing an execution command. Accordingly, the interactive server 200 determines whether or not an instruction corresponding to the first utterance element representing the main feature and an instruction corresponding to the second utterance element that stores the execution command are stored. As a result of the determination, if the executable word and command word corresponding to the extracted first and second utterance elements are stored, the interactive server 200 combines the executable word and command words corresponding to the extracted first and second utterance elements Create an executable command script. On the other hand, if the executable word and the instruction word corresponding to the extracted first and second utterance elements are not stored, the interactive server 200 corresponds to the extracted first and second utterance elements based on the previously stored utterance history information It is determined whether the executable word and the command estimation are possible. As a result of the determination, if it is possible to estimate the executable word and the command word corresponding to the extracted first and second utterance elements based on the previously stored utterance history information, the interactive server 200 combines the estimated executable word and the command word, Create a script. On the other hand, if it is impossible to estimate the executable word and the command word corresponding to the extracted first and second utterance elements based on the previously stored utterance history information, the interactive server 200 does not generate the response information for the uttered voice of the user . In this way, the interactive server 200 according to the present invention determines whether or not to generate response information for the user's utterance voice based on the uttered element extracted from the uttered voice of the user and the previously stored utterance history information, And transmits the generated response information to the display device 100. [

Hereinafter, a method for generating response information based on the speech element extracted from the speech uttered by the user in the interactive server 200 and the previously stored speech history information will be described in more detail with reference to FIG.

7 is a flowchart of a method for generating response information in an interactive server according to one embodiment of the present invention.

As shown in FIG. 7, the speech voice of the user may be converted into text information or the speech voice converted into text information from the display device 200 may be received through the above-described step S620. As described above, when the user's utterance voice is converted or received as text information, the interactive server 200 extracts the utterance element from the utterance voice converted into text information. When the utterance element is extracted, the interactive server 200 analyzes the extracted utterance element to determine whether there is a first utterance element indicating a main feature and a second utterance element indicating an execution command (S710). As a result of the determination, if it is determined that the extracted utterance element does not include at least one of the first utterance element and the second utterance element, the interactive server 200 determines whether there is previous utterance history information through step S740 .

On the other hand, if the first and second uttered speech elements are extracted from the speech uttered by the user, the interactive server 200 determines whether there are executable words and commands corresponding to the extracted first and second uttered elements (S720 ). As a result of the determination, if there is an executable word and an instruction word corresponding to the extracted first and second uttered elements, the interactive server 200 combines the executable word and the instruction word corresponding to the extracted first and second uttered elements Information is generated (S730). On the other hand, if there is no executable word and command word corresponding to the extracted first and second utterance elements, the interactive server 200 determines whether the utterance history information about the uttered speech received before the utterance voice of the user is received exists (S740). As a result of the determination, if the firing history information does not exist, the interactive server 200 does not generate the response information for the user's spoken voice. On the other hand, if there is the ignition history information, the interactive server 200 obtains the ignition history information within a predetermined time range based on the time when the user's speech is received (S750). Thereafter, the interactive server 200 executes a command corresponding to the first utterance element extracted from the uttered voice of the user and the instruction corresponding to the second utterance element in the acquired utterance history information, And a command (S760). As described above, when an executable word and a command corresponding to a user uttered voice are estimated, the interactive server 200 generates response information by combining the estimated executable word and the command (S770).

First, a description will be given of a method of generating response information for a user's utterance voice in the interactive server 200 when the utterance element extracted from the utterance voice of the user does not include at least one of the first and second utterance elements .

For example, in the case of utterance utterances such as "yes ", the interactive server 200 fails to extract the first and second utterances from the utterance uttered" yes. &Quot; In this case, the interactive server 200 judges that the utterance voice of "Yes" is unclear, and judges that the utterance utterance stored in the predetermined time range based on the time when the utterance voice " And acquires history information. For example, if the utterance voice included in the acquired previous utterance history information is "TV off ", the interactive server 200 extracts a first utterance element for" TV " . Then, the interactive server 200 estimates that the uttered voice of "Yes" currently received based on the extracted first and second utterance elements is confirm. Accordingly, the interactive server 200 determines that the execution region is device control based on the first speech element for "TV" extracted from the previous speech history information. In addition, the interactive server 200 can obtain an executable word "$ TV $" corresponding to the first utterance element for "TV " by referring to the executable word defined by the first stored utterance element. In addition, the interactive server 200 determines that the type of the second speech element for "turn off" is related to the execution of the device function based on the execution area determined as the device control. Accordingly, the interactive server 200 acquires a command corresponding to the execution of the device function among the predefined commands for each of the previously stored second utterance elements. Thereafter, the interactive server 200 may acquire the command "device_exectue_turn off " corresponding to the power control among the commands obtained in response to the execution of the device function. Thereafter, the interactive server 200 combines the executable word "$ TV $" corresponding to the first utterance element and the command "device_exectue_turn off" corresponding to the second utterance element to execute "device_exectue_turn off ($ TV $) Create a command script. When such an execution command script is generated, the interactive server 200 can generate response information including the generated execution command script.

Hereinafter, a method for generating response information for a user's utterance voice in the interactive server 200 when there is an executable word and an instruction word corresponding to the first and second utterance elements extracted from the uttered voice of the user Explain it.

On the other hand, when the utterance voice of "Show " xxx (content name)" is inputted, the interactive server 200 generates a first utterance element for " Quot; can be extracted. When the first and second utterance elements are extracted, the interactive server 200 determines that the execution region is the content based on the extracted first utterance element. In addition, the interactive server 200 stores an executable word "$ 0 (content name) " corresponding to the first utterance element for" $ ". Further, the interactive server 200 judges that the type of the second utterance element for "find" is related to the content search based on the execution region judged as the content. Therefore, the interactive server 200 can acquire the command "content_search " corresponding to the content search among the commands defined for the previously stored second utterance element.

As described above, when an executable word and a command corresponding to the first and second utterance elements are acquired, the interactive server combines the obtained executable word " $ 0 (content name) $ "and the command" content_search " ($ 0 (content name) $) ". When such an execution command script is generated, the interactive server 200 can generate response information including the generated execution command script.

Hereinafter, a method of generating response information for the user's utterance voice in the interactive server 200 when the executable word and the command corresponding to the first and second uttered elements extracted from the uttered voice of the user are absent Explain it.

For example, in the case of a utterance voice "select first", interactive server 200 may extract a first utterance element of "first" and a second utterance element of "select". When such first and second utterance elements are extracted, the interactive server 200 determines whether or not the executer and the command corresponding to the first and second utterance elements are stored in advance. Specifically, the interactive server 200 can obtain the executable word "$ 1st $" corresponding to the first utterance element of "first" by referring to the executable word defined by the previously stored first utterance element. On the other hand, the interactive server 200 determines whether execution region judgment is possible based on the extracted first speech element. As a result of the determination, if it is determined that the execution region is impossible from the first utterance element for the " first ", the interactive server 200 responds to the second utterance element " It does not acquire the command to be executed. Therefore, the interactive server 200 judges that the execution area and the execution command for providing the service for the uttered voice from the utterance voice "select first" are unclear. Based on the result of the determination, the interactive server 200 determines whether or not there is the speech history information stored within the predetermined time range based on the time point at which the speech sound "select first" among the pre-stored speech history information is received do. That is, the interactive server 200 determines whether or not the time difference between the time at which the utterance voice of "select first" of the previously stored utterance history information is received and the most recently stored previous utterance history information falls within a preset time range . As a result of the determination, if it is determined that the previous speech history information does not fall within the predetermined time range, the interactive server 200 does not generate the response information for the speech word "Select the first time ". On the other hand, if it is determined that the previous speech history information is within the predetermined time range, the interactive server 200 extracts the first and second speech elements from the text information of the speech speech included in the previous speech history information.

For example, if the utterance voice included in the previous utterance history information is "ooooo (content name) found ", the interactive server 200 generates a first utterance element for" And extracts the second utterance element "find ". Thereafter, the interactive server 200 searches the first and second utterances extracted from the utterance utterances included in the previous utterance history information based on the first utterance element for "oo " (content name) It is assumed that the first utterance element for " ooo (content name) "is the first utterance element. Thereafter, the interactive server 200 judges that the execution region is the device UI control based on the estimated first speech element, and judges whether the command "device_select" corresponding to the device UI control among the predefined commands for the second & Can be obtained. Thereafter, the interactive server 200 combines the executable word "$ 1st $ " corresponding to the first uttered element and the command" device_select " Create a command script. When such an execution command script is generated, the interactive server 200 can generate response information including the generated execution command script.

In this way, the interactive server 200 according to the present invention analyzes the user's utterance voice to grasp the user's utterance intention, and determines whether to generate the response information based on the perceived utterance intention. If it is determined that the response information can not be generated based on the user's utterance intention, the interactive server 200 may generate the response information of the current user's utterance voice based on the user's previous utterance speech. Therefore, the user is not restricted to a specific utterance but can speak in a manner to express himself / herself and be provided with a service according to the utterance.

The present invention has been described with reference to the preferred embodiments.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is clearly understood that the same is by way of illustration and example only and is not to be construed as limiting the scope of the invention as defined by the appended claims. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

10: first server 20: second server
100: display device 110: input part
120, 210: communication unit 130:
140, 250: control unit 150, 230:
200: interactive server 220: audio processing unit
240: Extracting unit 300: Content providing server
400: external server

Claims (41)

A method of controlling a display device,
Outputting a first response message based on first response information corresponding to the first utterance voice when a first utterance voice is received; And
And outputting a second response message based on the second response information corresponding to the second utterance voice when the second utterance voice is received,
Wherein the second response information is generated based on ignition history information and a display state of an object displayed on the screen, and the ignition history information includes the first response information. The method according to claim 1,
Wherein the ignition history information further includes information on the first utterance voice. The method according to claim 1,
Determining whether the first utterance voice includes control information for controlling the function of the display device; And
And performing a function corresponding to the first utterance voice if the first utterance voice includes the control information. The method according to claim 1,
Determining whether the second utterance voice includes control information for controlling the function of the display device; And
And performing a function corresponding to the second utterance voice if the second utterance voice includes the control information. The method according to claim 3 or 4,
Wherein the control information includes information for controlling a volume of the display device,
Wherein the function is a volume adjustment function. The method according to claim 1,
Wherein the second response information comprises:
Wherein the first and second utterances are generated based on the utterance history information most recently obtained before the second utterance voice and the second utterance voice are received. The method according to claim 1,
Wherein the outputting of the first response message comprises:
And outputting a content search result message based on the content search information when a speech sound requesting a content search is received,
Wherein the outputting of the second response message comprises:
And outputting a response message corresponding to a speech sound related to the content based on the response to the content execution when the speech sound associated with the content is received,
Wherein the content execution related response information is generated based on at least one of a speech sound related to the content and the content search information. The method according to claim 1,
Wherein the first response information comprises:
And an execution word and a command corresponding to the first utterance voice, or information obtained based on the executable word and the command word. 9. The method of claim 8,
Wherein the first utterance voice includes a first utterance element representing an execution object and a second utterance element representing an execution command,
Wherein the execution word corresponds to the first speech element and the instruction word corresponds to the second speech element. The method according to claim 1,
Wherein the second response information comprises:
And an execution word and a command corresponding to the second utterance voice, or information obtained based on the executable word and the command word. 11. The method of claim 10,
Wherein the second utterance voice includes a first utterance element representing an execution object and a second utterance element representing an execution command,
Wherein the execution word corresponds to the first speech element and the instruction word corresponds to the second speech element. The method according to claim 1,
Wherein the ignition history information
And at least one speech sound received before the first speech sound is received and response information corresponding to the at least one speech sound. 10. The method of claim 9,
Wherein the execution word and the command are combined to generate an execution command script. The method according to claim 1,
Wherein the outputting of the second response message comprises:
Performing a function corresponding to the second utterance voice if the second utterance voice includes control information for controlling the function of the display device,
And outputs the second response message if the second speech voice does not include the control information. A method of controlling a display device,
Outputting a first response message based on first response information corresponding to the first utterance voice when a first utterance voice is received; And
And outputting a second response message based on the second response information corresponding to the second utterance voice when the second utterance voice is received,
Wherein the second response information is generated based on ignition history information and a display state of an object displayed on the screen, and the ignition history information includes information on the first speech voice. 16. The method of claim 15,
Wherein the ignition history information further includes the first response information. 16. The method of claim 15,
Determining whether the first utterance voice includes control information for controlling the function of the display device; And
And performing a function corresponding to the first utterance voice if the first utterance voice includes the control information. 16. The method of claim 15,
Determining whether the second utterance voice includes control information for controlling the function of the display device; And
And performing a function corresponding to the second utterance voice if the second utterance voice includes the control information. The method according to claim 17 or 18,
Wherein the control information includes information for controlling a volume of the display device,
Wherein the function is a volume adjustment function. 16. The method of claim 15,
Wherein the outputting of the second response message comprises:
Performing a function corresponding to the second utterance voice if the second utterance voice includes control information for controlling the function of the display device,
And outputs the second response message if the second speech voice does not include the control information. In the display device,
display;
A communication unit for performing communication with the server device; And
Controls the communication unit to receive the first response information corresponding to the first speech voice by transmitting a speech voice signal for the received first speech voice to the server apparatus, To output a response message through the display,
Controls the communication unit to receive the second response information corresponding to the second speech voice by transmitting a speech voice signal for the received second speech voice to the server apparatus, And a control unit for controlling to output a response message through the display,
Wherein the second response information is generated based on ignition history information and a display state of an object displayed on the screen, and the ignition history information includes the first response information. 22. The method of claim 21,
And the ignition history information further includes information on the first utterance voice. 22. The method of claim 21,
Wherein,
Determining whether or not the first utterance voice includes control information for controlling the function of the display device and performing a function corresponding to the first utterance voice if the first utterance voice includes the control information . 22. The method of claim 21,
Wherein,
Determining whether the second utterance voice includes control information for controlling the function of the display device and performing a function corresponding to the second utterance voice if the second utterance voice includes the control information . 25. The method according to claim 23 or 24,
Wherein the control information includes information for controlling a volume of the display device,
Wherein the function is a volume adjustment function. 22. The method of claim 21,
And a storage unit,
Wherein,
And stores the ignition history information in the storage unit. 22. The method of claim 21,
Wherein the second response information comprises:
Is generated based on the speech history information most recently obtained before the second speech speech and the second speech speech are received. 22. The method of claim 21,
Wherein,
A content search result message is output based on the content search information when a spoken voice requesting the content search is received,
A response message corresponding to a speech sound associated with the content is output based on response information related to the execution of the content when the speech sound associated with the content is received,
Wherein the content execution related response information is generated based on at least one of a speech sound associated with the content and the content search information. 22. The method of claim 21,
Wherein the first response information comprises:
An executable word and an instruction corresponding to the first utterance voice, or information obtained based on the executable word and the instruction word. 30. The method of claim 29,
Wherein the first utterance voice includes a first utterance element representing an execution object and a second utterance element representing an execution command,
Wherein the execution word corresponds to the first speech element and the instruction word corresponds to the second speech element. 22. The method of claim 21,
Wherein the second response information comprises:
And an execution word and an instruction corresponding to the second utterance voice, or information obtained based on the executable word and the instruction word. 32. The method of claim 31,
Wherein the second utterance voice includes a first utterance element representing an execution object and a second utterance element representing an execution command,
Wherein the execution word corresponds to the first speech element and the instruction word corresponds to the second speech element. 22. The method of claim 21,
Wherein the ignition history information
And at least one speech sound received before the first speech sound is received and response information corresponding to the at least one speech sound. 31. The method of claim 30,
Wherein the execution word and the command are combined to be generated as an execution command script. 22. The method of claim 21,
Wherein,
Performing a function corresponding to the second utterance voice if the second utterance voice includes control information for controlling the function of the display device,
And outputs the second response message if the second speech voice does not include the control information. In the display device,
display;
A communication unit for performing communication with the server device; And
Controls the communication unit to receive the first response information corresponding to the first speech voice by transmitting a speech voice signal for the received first speech voice to the server apparatus, To output a response message through the display,
Controls the communication unit to receive the second response information corresponding to the second speech voice by transmitting a speech voice signal for the received second speech voice to the server apparatus, And a control unit for controlling to output a response message through the display,
Wherein the second response information is generated on the basis of the speech history information and the display state of the object displayed on the screen, and the speech history information includes information on the first speech speech. 37. The method of claim 36,
Wherein the ignition history information further includes the first response information. 37. The method of claim 36,
Wherein,
Determining whether or not the first utterance voice includes control information for controlling the function of the display device and performing a function corresponding to the first utterance voice if the first utterance voice includes the control information . 37. The method of claim 36,
Wherein,
Determining whether the second utterance voice includes control information for controlling the function of the display device and performing a function corresponding to the second utterance voice if the second utterance voice includes the control information . 40. The method of claim 38 or 39,
Wherein the control information includes information for controlling a volume of the display device,
Wherein the function is a volume adjustment function. 37. The method of claim 36,
Wherein,
Performing a function corresponding to the second utterance voice if the second utterance voice includes control information for controlling the function of the display device,
And outputs the second response message if the second speech voice does not include the control information.

Images