KR20140042637A - Image processing apparatus and control method thereof, image processing system - Google Patents

Abstract

An image processing apparatus according to an embodiment of the present invention includes an image processing unit for processing a broadcast signal received from the outside to be displayed as an image; A communication unit communicatively connected to the server; A voice input unit to which a user's utterance is input; A voice processing unit for processing a predetermined corresponding action according to a voice command corresponding to the utterance; And a controller for controlling a voice command corresponding to a utterance by any one of the voice processor and the server when a utterance is input through the voice input unit, wherein the controller includes a keyword related to a call sign of a broadcast channel. In the case of including the control unit to control the recommended call sign corresponding to the keyword selected by any one of the voice processing unit and the server according to the preset selection conditions, and performs a corresponding operation according to the voice command for the broadcast channel of the recommended call sign It is done.

Description

TECHNICAL FIELD [0001] The present invention relates to an image processing apparatus, a control method thereof, and an image processing system,

The present invention relates to an image processing apparatus for processing a video signal such as a broadcast signal received from the outside to be displayed as an image, a control method thereof, and an image processing system. More particularly, And a control method thereof, and an image processing system.

The image processing apparatus processes image signal / image data received from the outside according to various image processing processes. The image processing apparatus can display the processed video signal on the display panel on its own display panel or output the processed video signal to the corresponding display device so as to be displayed as an image on the other display device having the panel. That is, the image processing apparatus can include both a case including a panel capable of displaying an image and a case not including a panel, as long as the apparatus can process a video signal. An example of the former case is a TV, An example of a set-top box is a set-top box.

As image processing apparatuses continue to reflect the addition and expansion of various functions in accordance with the development of the technology, a configuration in which a command reflecting the intention of the user in the image processing apparatus is input to the image processing apparatus in accordance with this trend may be variously structured A method has been proposed. For example, conventionally, when the user presses a key / button on a remote controller, the remote controller transmits a control signal to the image processing apparatus to allow the user to perform an operation desired by the user. In recent years, however, There have been proposed various configurations in which the image processing apparatus is controlled to reflect the user's intention, such as detecting motion or ignition by the user, analyzing the detected content, and executing a corresponding operation.

An image processing apparatus according to an embodiment of the present invention includes an image processing unit for processing a broadcast signal received from the outside to be displayed as an image; A communication unit communicatively connected to the server; A voice input unit to which a user's utterance is input; A voice processing unit for performing a predetermined corresponding operation according to a voice command corresponding to the utterance; And a controller configured to control the voice command corresponding to the utterance by any one of the voice processor and the server when the utterance is input through the voice input unit. In the case of including a keyword related to a call sign, one of the voice processor and the server controls the recommended call sign corresponding to the keyword to be selected according to a preset selection condition, and to the broadcast channel of the recommended call sign. It is characterized in that for performing the corresponding operation according to the voice command.

Here, a database of at least one call sign candidate corresponding to the keyword is stored in the image processing apparatus and the server, and the recommendation call sign may be selected according to the selection condition from the plurality of call sign candidates searched from the database.

The selection condition may include selecting a call sign candidate having a selection frequency equal to or greater than a predetermined rank from among the plurality of call sign candidates based on usage history information of the image processing apparatus as the recommended call sign.

Alternatively, the selection condition may include selecting a call sign candidate having a predetermined frequency or more from a plurality of other image processing apparatuses communicating with the server from among the plurality of call sign candidates as the recommended call sign.

The recommendation callsign may select one or more of the plurality of callsign candidates, and the controller may provide an image for the infant to select one of the plurality of selected callsign candidates when a plurality of callsign candidates are selected. I can display it.

The controller may select one of the recommended call signs based on the preset selection condition when the input for selecting one of the call sign candidates is not performed for a preset time after the image is displayed. have.

The communication unit may communicate with a speech-to-text (STT) server that converts the speech into a voice command of text, and the controller may transmit the speech signal of the speech to the STT server when the speech is input to the voice input unit. The voice command corresponding to the utterance may be received from the STT server.

Here, the controller may control the voice command to be processed by the voice processing unit when the voice command is a short text, and to process the voice command by the server when the voice command is a conversation text.

The display apparatus may further include a display unit configured to display a broadcast signal processed by the image processor as an image.

In addition, the control method of the image processing apparatus communicating with the server according to an embodiment of the present invention, the step of inputting the user's speech; Controlling the voice command corresponding to the speech to be processed by any one of the image processing apparatus and the server, and performing a preset corresponding operation according to the voice command, wherein the preset response according to the voice command In the performing of the operation, when the voice command includes a keyword related to a call sign of a broadcast channel, the recommendation call sign corresponding to the keyword is set by one of the image processing apparatus and the server according to a preset condition. Controlling to be selected; And performing a corresponding operation according to the voice command on the broadcast channel of the recommended call sign.

Here, a database of at least one call sign candidate corresponding to the keyword is stored in the image processing apparatus and the server, and the recommendation call sign may be selected according to the selection condition from the plurality of call sign candidates searched from the database.

The selection condition may include selecting a call sign candidate having a selection frequency equal to or greater than a predetermined rank from among the plurality of call sign candidates based on usage history information of the image processing apparatus as the recommended call sign.

Alternatively, the selection condition may include selecting a call sign candidate having a predetermined frequency or more from a plurality of other image processing apparatuses communicating with the server from among the plurality of call sign candidates as the recommended call sign.

The recommendation callsign may select one or more of the plurality of callsign candidates, and the performing of a preset corresponding operation according to the voice command may include selecting among the selected callsign candidates when a plurality of callsign candidates are selected. The infant may be configured to display an image.

The displaying of the image by the infant may include performing any one of the ones based on the predetermined selection condition when an input for selecting one of the call sign candidates is not performed for a preset time after the image is displayed. The method may include selecting a recommended call sign.

In addition, the image processing apparatus communicates with the STT server for converting the speech into a voice command of the text, the step of inputting the user's speech, the step of transmitting the speech signal of the speech to the STT server; And receiving the voice command corresponding to the utterance from the STT server.

The performing of the preset corresponding operation according to the voice command may include processing the voice command by the image processing apparatus when the voice command is a short message, and executing the voice command when the voice command is a conversation text. And controlling to be processed by the server.

In addition, the image processing system according to an embodiment of the present invention, the image processing apparatus for processing a broadcast signal received from the outside to be displayed as an image; And a server for communicating with the image processing apparatus, wherein the image processing apparatus comprises: a voice input unit to which a user's utterance is input; A voice processing unit for performing a predetermined corresponding operation according to a voice command corresponding to the utterance; And a controller configured to control the voice command corresponding to the utterance by any one of the voice processor and the server when the utterance is input through the voice input unit. In the case of including a keyword related to a call sign, either the voice processor or the server controls the recommended call sign corresponding to the keyword to be selected according to a preset selection condition, and the voice command is directed to a broadcast channel of the recommended call sign. It characterized in that to perform a corresponding operation according to.

The STT server may further include converting the utterance into a voice command of text, wherein the controller transmits the voice signal of the utterance to the STT server when the utterance is input to the voice input unit. The voice command corresponding to the utterance may be received.

1 is a block diagram of a display device according to a first embodiment of the present invention;
2 is an exemplary diagram schematically showing the structure of a database relating to keyword and callsign candidates;
3 is a block diagram illustrating an interaction structure between the display apparatus and the server of FIG. 1;
4 is an exemplary diagram illustrating an interaction process between a display apparatus and a server of FIG. 3;
5 and 6 are views illustrating an example of an infant image to selectably provide any one of a plurality of recommended call signs in the display device of FIG. 1;
7 is an exemplary view illustrating an interaction process between a display apparatus and a server according to a second embodiment of the present invention;
8 is a block diagram illustrating an interaction structure between a display apparatus and a server according to a third exemplary embodiment of the present invention;
9 is an exemplary diagram illustrating an interaction process between a display apparatus and a server of FIG. 8;
10 is a block diagram illustrating a signal transmission structure of a voice processing unit of a display device according to a fourth embodiment of the present invention.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. In the following embodiments, only configurations directly related to the concept of the present invention will be described, and description of other configurations will be omitted. However, it is to be understood that, in the implementation of the apparatus or system to which the spirit of the present invention is applied, it is not meant that the configuration omitted from the description is unnecessary.

1 is a block diagram of a configuration of an image processing apparatus 100 according to a first embodiment of the present invention.

Although the embodiment will be described with reference to the case where the image processing apparatus 100 is a display apparatus having a structure capable of displaying images on its own, the idea of the present invention is that the image processing apparatus 100 does not display images But the present invention is not limited to the embodiments described below as long as it is a device capable of outputting a video signal / control signal to a display device. The present embodiment describes a case where the image processing apparatus 100 is a TV, but the implementation method may be variously modified and applied according to the reasons.

As shown in FIG. 1, the image processing apparatus 100 or the display apparatus 100 according to the present embodiment receives a video signal from a video source (not shown). For example, the display device 100 receives a broadcasting signal transmitted from a transmission device (not shown) of a broadcasting station, and transmits the broadcasting signal to the display device 100 The broadcast image can be displayed by tuning.

The display apparatus 100 includes an image receiving unit 110 for receiving a video signal from a video source (not shown), an image processing unit 120 for processing a video signal received by the image receiving unit 110 according to a predetermined image processing process, A display unit 130 for displaying an image based on the image signal processed by the image processing unit 120, a communication unit 140 for communicating with an external device such as the server 10, A sound processing unit 170 for analyzing and processing the sound / sound input to the sound input unit 160, and a sound processing unit 170 for storing the data / A storage unit 180, and a control unit 190 for controlling various operations of the display device 100. [

The image receiving unit 110 receives the image signal / image data by wire or wireless and transmits the image signal / image data to the image processing unit 120. The image receiving unit 110 may be provided in various ways corresponding to the standard of the image signal to be received and the implementation form of the display device 100. [ For example, the image receiving unit 110 may receive a radio frequency (RF) signal, or may be a composite video, a component video, a super video, a SCART, a high definition multimedia interface (HDMI) A display port, a unified display interface (UDI), or a wireless HD standard. The image receiving unit 110 includes a tuner for tuning the broadcast signal for each channel when the image signal is a broadcast signal.

The image processing unit 120 performs a variety of image processing processes on the image signal received by the image receiving unit 110. The image processor 120 outputs a video signal that has undergone such a process to the display unit 130 so that an image based on the video signal is displayed on the display unit 130. For example, when the broadcast signal is tuned to a specific channel in the image receiving unit 110, the image processing unit 120 extracts video, audio, and additional data corresponding to the channel from the broadcast signal, adjusts the video, (130).

The type of the image processing process performed by the image processing unit 120 is not limited. For example, the decoding and interlace image data corresponding to the image format of the image data are converted into a progressive method. De-interlacing, scaling to adjust image data to a preset resolution, noise reduction to improve image quality, detail enhancement, and frame refresh rate conversion And the like.

The image processor 120 may be a system-on-a-chip (SOC) that integrates various functions, or an individual configuration capable of independently performing each of the processes, And is embedded in the display device 100.

The display unit 130 displays an image based on the image signal output from the image processing unit 120. [ The display unit 130 may be implemented in various forms including, but not limited to, a liquid crystal, a plasma, a light-emitting diode, an organic light-emitting diode, electron conduction electron-emitter, carbon nano-tube, nano-crystal, and the like.

The display unit 130 may further include an additional configuration depending on the implementation method. For example, when the display unit 130 is a liquid crystal type, the display unit 130 includes a liquid crystal display panel (not shown), a backlight unit (not shown) for supplying light thereto, and a panel (Not shown).

The communication unit 140 performs transmission and reception of data so that the display device 100 performs bidirectional communication with the server 10. The communication unit 140 connects to the server 10 via a wired / wireless wide area / local area network or a local connection method according to a communication protocol of the server 10.

The user input unit 150 transmits various preset control commands or information to the controller 190 according to a user's operation and input. The user input unit 150 is realized by a menu-key or an input panel installed outside the display device 100 or a remote controller separated from the display device 100. Alternatively, the user input unit 150 may be integrated with the display unit 130, and when the display unit 130 is a touch-screen, the user may select the input menu 130 displayed on the display unit 130 (Not shown) to the controller 190. The controller 190 may be configured to receive the command.

The voice input unit 160 is micro-implemented and detects various sounds generated in the external environment of the display device 100. [ The sound sensed by the voice input unit 160 includes voice uttered by the user and sound generated by various factors other than the user.

The voice processing unit 170 performs processes for voice / sound input to the voice input unit 160 among various preset processes performed in the display device 100. [ Here, the "voice" processed by the voice processing unit 170 means a voice input to the voice input unit 160. [ When the video processing unit 120 processes the video signal, the video signal may include audio data, and the audio data included in the video signal is processed by the video processing unit 120.

When the voice / sound is input to the voice input unit 160, the voice processing unit 170 determines whether the voice / sound is a voice generated by a user or other factors. This determination method can not be specified because various structures can be applied. For example, it can be determined whether the inputted voice / sound corresponds to the wavelength / frequency band corresponding to the voice of the person, or the voice / It is possible to determine whether it is applicable or not.

If the voice processing unit 170 determines that the user's utterance has been input, the voice processing unit 170 processes the predetermined corresponding operation according to the voice command corresponding to the utterance. Here, the voice command means the contents of the utterance of the user. Details of this will be described later.

The storage unit 180 stores unlimited data under the control of the controller 190. The storage unit 180 is implemented as a non-volatile memory such as a flash memory, a hard-disc drive, or the like. The storage unit 180 is accessed by the control unit 190, the image processing unit 120 or the voice processing unit 170 and reads / writes / corrects / deletes / updates data.

The control unit 190 controls the voice processing unit 170 to process the input utterance when the utterance of the user is input through the voice input unit 160. [ When the broadcast image is displayed on the display 130 by processing the broadcast signal received by the image receiver 110 by the image processor 120, the controller 190 commands a user to switch channels through the voice input unit 160. When an utterance is received, the channel is changed according to the content of the utterance.

The method of voice command related to "channel switching" may be a method of speaking a channel number of a broadcast channel desired by a user or uttering a call sign of a desired broadcast channel. Channel numbers and callsigns are pre-defined expressions that distinguish one channel from another. The channel number is expressed by an integer such as 6, 7, 11, or the like.

The call sign is an identification name of a provider providing a specific channel, and is generally an identification name of a broadcasting station broadcasting the channel. Here, there may be a plurality of callsigns of one channel, and when one broadcasting station provides a plurality of channels, each channel has a different callsign for mutual distinction.

An example of the former is as follows. When the call sign of a predetermined first channel is "KBS", the call sign of "Korean broadcast" may also refer to the first channel in the same way as "KBS". Alternatively, the call sign of the second channel may be different from the call sign of the second channel in another region, whereas the call sign of the second channel may be different from that of the second channel. That is, there may be a plurality of call signs of a specific channel instead of one.

An example of the latter is as follows. Broadcasting stations having a call sign of "KBS" may provide broadcast signals to predetermined third and fourth channels, respectively. In this case, the call sign of the third channel is "KBS-1", and the call sign of the fourth channel is different from "KBS-2". "KBS" may be regarded as a representative call sign of the broadcasting station, and "KBS-1" and "KBS-2" are sub-call signs related to "KBS". That is, a call sign of "KBS" is associated with both the third channel and the fourth channel.

Therefore, if the user's speech input through the voice input unit 160 is a voice command of "KBS turn on", it means any channel among the third channel of "KBS-1" and the fourth channel of "KBS-2". It may be unclear.

Accordingly, according to the present exemplary embodiment, the controller 190 determines whether a voice command corresponding to a user's speech includes a keyword (key-word) related to a call sign of a broadcast channel.

If it is determined that the voice command includes a call sign related keyword, the controller 190 controls the voice processing unit 170 to search for a call sign corresponding to the keyword in a database including a plurality of call signs. Here, the database is stored in the storage unit 180 and the retrieved call sign is referred to as a call sign candidate. At this time, when a plurality of call sign candidates corresponding to the corresponding keyword are found, the controller 190 selects a recommended call sign from among the plurality of call sign candidates based on a preset selection condition.

Alternatively, the controller 190 may transmit a keyword and a voice command to the server 10 in which the database is stored. In this case, the server 10 selects the recommended call sign on the principle similar to the above-described configuration, analyzes the corresponding operation according to the voice command, and transmits a control signal according to the selection and analysis result to the display apparatus 100.

The controller 190 performs a corresponding operation according to a voice command on the broadcast channel of the selected recommended call sign.

Hereinafter, a configuration of the database 200 and a method of searching the database 200 to search the call sign candidate 230 will be described with reference to FIG. 2.

2 is an exemplary view schematically showing the structure of the database 200.

As illustrated in FIG. 2, the controller 190 determines whether a call sign-related keyword is included in the " KBS " The storage unit 180 stores the relational database 200 in which keywords and callsigns are mapped corresponding to each other, and the controller 190 searches the database 200 with a predetermined keyword so that the corresponding keyword is a callsign related keyword. It can be determined whether or not.

The database 200 is used to search for one or more callsign candidates 230 with either keyword 220 by mapping a plurality of keywords 220 and a plurality of callsigns 230 to each other. In this figure, only the relation of items related to two representative call signs 210 of "KBS" and "FTV" in the database 200 is shown.

The representative callsign 210 serves as a link for correlating the keyword 220 and the callsign candidate 230. Specifically, when a predetermined keyword 220 is input, first, the representative call sign 210 related to the keyword 220 is first searched on the database 200. When the representative callsign 210 is searched, the lower callsign 230 or related callsign candidate 230 of the found representative callsign 210 is searched secondarily.

The keyword 220 is grouped / categorized for the representative callsign 210 with various terms, including synonyms, synonyms, and the like associated with the representative callsign 210. In addition, callsign candidate 230 includes callsigns of one or more channels associated with representative callsign 210, which are grouped / categorized relative to representative callsign 210.

For example, when the keyword 220 "fishing channel" is input, the representative call sign 210 associated with the "fishing channel" is "FTV" and the call sign candidate 230 related to the representative call sign 210 "FTV". Is one "FTV". That is, as long as the database 200 searches, the call sign of the channel corresponding to the keyword 220 of "fishing channel" is one "FTV".

Meanwhile, when the keyword 220 of "KBS" is input, the representative callsign 210 associated with "KBS" is "KBS", and the callsign candidate 230 related to the representative callsign "KBS" is "KBS-1", There are four types, "KBS-2", "KBS-sports" and "KBS-movie".

By searching the database 200 in this manner, at least one callsign candidate 230 associated with the keyword 220 may be obtained. However, the above-described method is only one example of implementing the database 200, and the implementation manner of the database 200 may be variously applied and is not limited to the above-described example.

3 is a block diagram illustrating an interaction structure between the display apparatus 100 and the servers 20 and 30.

As shown in FIG. 3, the display apparatus 100 includes a communication unit 140, a voice input unit 160, a voice processing unit 170, and a controller 190. This configuration is as described in FIG. Here, the communication unit 140 includes a speech-to-text (STT) server 20 for converting a user's utterance into a voice command, an interactive server 30 for determining a corresponding operation corresponding to the voice command by analyzing the voice command .

When the voice signal is received, the STT server 20 generates the text of the voice signal by analyzing the waveform of the voice signal. The STT server 20 receives a voice signal of a user's utterance from the display device 100 and converts it into a voice command.

The interactive server 30 includes a database to which operations of various display apparatuses 100 corresponding to voice commands are mapped. The interactive server 30 analyzes the voice command received from the display device 100 and transmits a control signal for performing an operation corresponding to the voice command to the display device 100 according to the analysis result.

The control unit 190 transmits the voice signal of the utterance to the STT server 20 and receives the voice command corresponding to the utterance from the STT server 20. [

The control unit 190 determines whether the voice command received from the STT server 20 corresponds to the short message or the dialogue. The control unit 190 causes the voice processing unit 170 to process the voice command if the voice command is a short message and allows the voice command to be processed by the interactive server 30 if the voice command is a conversation.

This is because, since the dialogue is a natural language, it is relatively easy to mechanically extract the corresponding action desired by the user in the dialogue command. For example, when the user's voice command is a short sentence of "KBS", the voice processing unit 170 may directly perform the operation with a call sign keyword of "KBS" and an operation keyword of "wrong".

However, in the case of a dialogue such as "Please change the channel you are watching to Korean broadcast", which is the same voice command, the call sign keyword of "KBS" corresponding to "Korean broadcast" is derived and "Please change". There is a need for a process of deriving an action keyword corresponding to "twist". Due to various factors such as the load of the system or the amount of information in the database, it may not be easy for the voice processing unit 170 to process such a dialogue.

4 is an exemplary diagram illustrating an interaction process between the display apparatus 100 and the servers 20 and 30 according to the present exemplary embodiment.

As shown in FIG. 4, when a utterance is input from the user (600), the display apparatus 100 transmits a voice signal of the corresponding utterance to the STT server 20 (610).

The STT server 20 converts the voice signal into a voice command (620), and transmits the converted voice command to the display apparatus 100 (630).

The display apparatus 100 analyzes the voice command received from the STT server 30 and extracts a call sign related keyword from the voice command (640). Here, the display apparatus 100 determines whether a voice command is a short / conversation text.

If the voice command is determined to be a conversation, the display apparatus 100 transmits the voice command and the call sign related keyword to the interactive server 30 (650).

The interactive server 30 performs a callsign analysis process based on a voice command and callsign related keywords received from the display apparatus 100 (660). In the call sign analysis process, searching for a call sign candidate corresponding to a call sign related keyword, selecting a recommended call sign from among searched call sign candidates, and determining an operation of the display apparatus 100 corresponding to the recommended call sign in the text are performed. The details thereof will be described later.

When the selection of the recommended call sign and the determination of the corresponding operation of the voice command are completed, the interactive server 30 transmits a control signal according to the selection and the determination result to the display apparatus 100. Accordingly, the display apparatus 100 may perform a corresponding operation for the recommended call sign according to the control signal.

For example, if the recommended call sign is "KBS-1" and the corresponding operation is analyzed to be channel switching, the interactive server 30 transmits a control signal indicating the contents to the display apparatus 100 to display the display apparatus 100. ) Switch to the "KBS-1" channel.

On the other hand, if it is determined in step 640 that the voice command is short, the display apparatus 100 performs a call sign analysis process based on the received voice command and call sign related keywords. This process is performed according to substantially the same principle as the process performed in the foregoing interactive server 30.

Hereinafter, the callsign analysis process using callsign related keywords will be described.

The interactive server 30 searches for a callsign candidate corresponding to a callsign related keyword, and determines whether there are a plurality of searched callsign candidates.

The determination of whether to include the keyword related to the call sign and the search of the call sign candidate corresponding to the keyword may be performed by the method described with reference to FIG. 2. That is, the interactive server 30 searches the word extracted from the voice command on the database 200 (see FIG. 2) to determine whether there is a matched word 220 (see FIG. 2), and if there is a matched word, The callsign candidate 230 (see FIG. 2) of the representative callsign 210 (see FIG. 2) may be obtained.

On the other hand, in the process of extracting a keyword from the voice command, correction or filtering may be performed for misunderstanding of the voice command. For example, if there is a voice command of "broadcasting Anguk Broadcasting", the word "Korean Broadcasting" in the database is judged to be similar to the word "Anguk Broadcasting" even if the word "Anguk Broadcasting" is not in the database. The word "Korean broadcast" can be selected. The method of determining the similarity of words may be variously determined and does not limit the spirit of the present invention.

On the other hand, if there is only one retrieved callsign candidate, the interactive server 30 selects the callsign candidate as the recommended callsign.

On the other hand, if there are a plurality of retrieved call sign candidates, the interactive server 30 selects the recommended call sign according to a preset selection condition.

As the selection condition for selecting the recommended callsign from among the callsign candidates, various conditions may be set in advance. For example, the interactive server 30 selects a plurality of callsigns having a high frequency of selection higher than a predetermined rank from the callsign candidates as recommended callsigns based on the usage history information of the display apparatus 100, or selects a plurality of callsigns. The highest one callsign can be selected as the recommended callsign.

When there are four callsigns of "KBS-1", "KBS-2", "KBS-sports", and "KBS-movie" in the callsign candidate, the control unit 190 determines that these channels remain for a predetermined period based on the usage history information. The frequency selected by the display apparatus 100 is determined. For example, when the frequency of selection is high in the order of "KBS-sports", "KBS-movie", "KBS-2", and "KBS-1", the controller 190 controls the plurality of call signs in the order of selection frequency. You can select or choose one callsign.

Herein, the controller 190 may display a user interface (UI) for providing a user to select one of a plurality of callsign candidates.

5 and 6 are exemplary diagrams of an infant image 310 and 320 to selectably provide any one of a plurality of recommended call signs.

As shown in FIG. 5, the controller 190 selects "KBS-sports" and "KBS-movie" having the highest selection frequency as the recommendation call sign on the display apparatus 100 based on the usage history information, and selects the selected recommendation. The infant provides an image 310 to select a desired channel from among the call signs. The user may select one of the call sign and the broadcasting channel from among "KBS-sports" and "KBS-movie" through the image 310.

Alternatively, as shown in FIG. 6, the controller 190 selectably provides any one of all call sign candidates of "KBS-sports", "KBS-movie", "KBS-2", and "KBS-1". An infant may provide an image 320. The infant may display all the call sign candidates found in the image 320, but the controller 190 may determine the display order of each call sign according to the selection frequency. For example, the infant image 320 may be displayed by arranging each callsign candidate in the order of the highest selection frequency.

If the infant is not selected by the user for a preset time at the time when the images 310 and 320 are displayed, the controller 190 may determine the channel of the highest priority among the callsign candidates, for example, the highest selection frequency. Select "KBS-sports" to perform the corresponding action.

As a selection condition for selecting the recommended callsign from among the callsign candidates, an embodiment different from the above example may be applied. Various other display apparatuses other than the display apparatus 100 are connected to the server 10 (see FIG. 1). Here, the server 10 may be the same server as the STT server 20 or the interactive server 30, or may be a different server. Also, although the STT server 20 and the interactive server 30 are expressed as being different servers, they may be implemented with the same server.

These other display apparatuses respectively transmit usage history information to the server 10. The server 10 selects the frequency of selection of each of the "KBS-1", "KBS-2", "KBS-sports", and "KBS-movie" in the callsign candidate based on the usage history information collected from each other display apparatus. To judge.

The controller 190 transmits the callsign candidates of "KBS-1", "KBS-2", "KBS-sports", and "KBS-movie" to the server 10, and selects a recommendation candidate within the callsign candidate. You can request

Accordingly, the server 10 determines the ranking of the selection frequency based on the usage history information from another display device in the call sign candidate. When the selection frequency rank is "KBS-movie", "KBS-2", "KBS-sports", "KBS-1", and the number of recommendation candidates requested from the display apparatus 100 is one, the server 10 Determines that the KBS-movie having the highest selection frequency rank is the recommendation candidate and informs the display apparatus 100. Thus, the controller 190 may display information related to "KBS-movie" as an image.

In this case, when only one recommendation call sign is selected, the controller 190 may automatically display a broadcast channel image of the recommendation call sign. However, channel numbers corresponding to call signs may not be the same for each region.

Therefore, the controller 190 obtains local information where the display apparatus 100 is located and determines the channel number of the call sign corresponding to the imprisonment. The method of determining the region of the display apparatus 100 may be variously applied. For example, the region / country ID included in the header or metadata of the broadcast signal may be extracted, or based on the MAC address of the communicator 140. The server 10 may determine or the user may input local information in advance in the display apparatus 100.

As described above, if the voice command corresponding to the user's utterance includes a call sign related keyword, the display apparatus 100 selects a recommendation call sign corresponding to the keyword and according to the voice command for the broadcast channel of the selected recommendation call sign. The corresponding operation may be performed.

7 is an exemplary diagram illustrating an interaction process between the display apparatus 100 and the servers 20 and 30 according to the second exemplary embodiment of the present invention.

As illustrated in FIG. 7, when an utterance is input from the user (700), the display apparatus 100 transmits a voice signal of the corresponding utterance to the STT server 20 (710).

The STT server 20 converts the received voice signal into a voice command (720). This step is the same as in the case of FIG. 4.

The STT server 20 transmits the voice command to the interactive server 30 (730).

The interactive server 30 performs a series of callsign analysis processes, such as searching for callsign candidates and selecting recommended callsigns (740). Details of this can be applied to the case of the previous embodiment, so a detailed description thereof will be omitted. However, unlike the case of FIG. 4, the call sign analysis process according to the present embodiment proceeds by extracting the call sign keyword from the voice command.

The interactive server 30 transmits a control signal indicating a recommended call sign and a corresponding operation to the display apparatus 100 so that the display apparatus 100 operates according to the control signal (750).

On the other hand, in the above embodiment, the user's utterance input to the display apparatus 100 is converted into a voice command by the STT server 20, and if the voice command is a short message, the display device 100 is processed and if the voice command is a dialogue, the conversation The configuration processed by the type server 30 has been described.

However, the idea of the present invention is not limited to this, and a structure for converting a speech to a voice command and a subject for processing the voice command according to whether a voice command is a short message or a dialogue is different from the previous embodiment .

FIG. 8 is a block diagram illustrating an interaction structure between the display apparatus 100a and the server 40 according to the third embodiment, and FIG. 9 illustrates an interaction process between the display apparatus 100a and the server 40 of FIG. 8. It is an illustration.

8, the display device 100a includes a communication unit 140a, a voice input unit 160a, a voice processing unit 170a, and a control unit 190a.

Here, the voice processing unit 170a includes an STT converting unit 171a for converting the voice transmitted from the voice input unit 160a into a voice command, and a short message processing unit 172a for processing the voice command if the voice command is short .

The speech input unit 160a transmits the speech signal of the input speech to the STT conversion unit 171a when the speech is inputted from the user. The STT converting unit 171a analyzes the voice signal transmitted from the voice input unit 160a and converts the voice signal into a voice command including the voice. The STT converter 171a transmits the converted voice command controller 190a. That is, the STT conversion unit 171a performs the function of the STT server 20 of the first embodiment.

The controller 190a determines whether the voice command is a short / conversation text. The controller 190a transmits the voice command to the short command processor 172a when the voice command is a short text. The short sentence command processing unit 172a analyzes the voice command under the control of the control unit 190a, and executes the corresponding operation according to the analysis result. Since the above embodiment can be applied to the analysis and execution of the voice command, detailed description will be omitted.

On the other hand, if the voice command is a conversation text, the controller 190a does not transmit the voice command to the short command processor 172a but transmits the voice command to the interactive server 40 through the communication unit 140a. The interactive server 20 performs the same function as the interactive server 30 of the first embodiment described above.

Accordingly, the display apparatus 100a performs an operation corresponding to the control signal received from the interactive server 20.

As shown in FIG. 9, the display apparatus 100a is communicatively connected to the interactive server 40. When the utterance is input from the user (810), the display apparatus 100a determines whether the voice command corresponding to the utterance is short / conversation 820. If the display apparatus 100a determines that the voice command is a conversation text, the display apparatus 100a transmits the voice command to the interactive server 40 in operation 830.

When the interactive server 40 receives a voice command from the display apparatus 100 (910), the interactive server 40 extracts a call sign related keyword from the voice command (920).

Alternatively, the call sign related keyword may not be extracted by the interactive server 40 but may be extracted by the display apparatus 100a. In this case, the display apparatus 100a transmits call sign related keywords and voice commands to the interactive server 40 together.

The interactive server 40 searches for a callsign candidate corresponding to the keyword (930). When a plurality of callsign candidates are found, the interactive server 40 selects a recommended callsign from the plurality of searched callsign candidates according to the selection condition as described above (940). In addition, the interactive server 40 analyzes the voice command to determine a corresponding operation according to the voice command.

The interactive server 40 transmits a control signal indicating a recommended call sign and a corresponding operation to the display apparatus 100a (950).

The display apparatus 100a executes a corresponding operation for the broadcast channel of the recommended call sign according to the control signal received from the interactive server 40 (840).

On the other hand, if it is determined in step 820 that the voice command is short, the display apparatus 100a analyzes the recommended call sign and the corresponding operation by the display apparatus 100a itself.

10 is a block diagram illustrating a signal transmission structure of the voice processor 171b of the display apparatus 100b according to the fourth embodiment of the present invention.

As shown in FIG. 10, the voice processing unit 170b includes an STT converter 171b for converting a user's utterance transmitted from the voice input unit 160b into a voice command, and a voice converted by the STT converter 171b. A short command processing unit 172b for processing the command when the command is a short text, and an interactive command processing unit 173b for processing the voice command converted by the STT conversion unit 171b for the conversation / natural language. The structure of the voice processing unit 170b is not limited to this example, and this example is merely a brief representation of matters directly related to the embodiment of the present invention.

The speech input unit 160b, when a speech is input from the user, transmits the speech signal of the input speech to the STT conversion unit 171b. The STT conversion section 171b converts the speech delivered from the speech input section 160b into a speech command containing the content of the corresponding speech. The STT converter 171b transfers the converted voice command to the controller 190b.

The controller 190b determines whether the voice command is short or conversation. In this case, whether the short sentence or the dialogue sentence is determined may be processed according to various algorithms.

If the voice command is a short message, the controller 190b transmits the voice command to the short command processor 172b. On the other hand, when the voice command is a dialogue, the controller 190b transmits the voice command to the interactive command processor 173b.

The short command processor 172b performs substantially the same function as the short command processor 172a shown in FIG. In addition, the interactive command processing unit 173b performs the functions performed by the interactive servers 30 and 40 of the preceding embodiments.

That is, unlike the previous embodiments, the display apparatus 100b according to the present exemplary embodiment does not perform data / signal transmission with the external servers 20 to 40, and the display apparatus 100b itself generates a voice according to the user's speech. The translation of the command and the operation corresponding to the voice command can be analyzed.

On the other hand, when the display device is connected to a separate server (not shown) that executes a callsign analysis process, the short command processing unit 172a or the interactive command processing unit 173b sends keywords and voice commands to the corresponding server (not shown). In this case, the call sign analysis process may be performed at the server (not shown).

That is, in the above embodiments, although the call sign analysis process is expressed as being performed in the interactive server 30 or 40 or the voice processing units 170, 170a and 170b, a separate server (not shown) that performs the call sign analysis process is performed. The process may be performed by this.

The above-described embodiments are merely illustrative, and various modifications and equivalents may be made by those skilled in the art. Accordingly, the true scope of protection of the present invention should be determined by the technical idea of the invention described in the following claims.

10: Server
100: image processing device / display device
110:
120:
130:
140:
150: User input
160:
170:
180:
190:

Claims (23)

An image processing apparatus comprising:
An image processor which processes a broadcast signal received from the outside to be displayed as an image;
A communication unit communicatively connected to the server;
A voice input unit to which a user's utterance is input;
A voice processing unit for performing a predetermined corresponding operation according to a voice command corresponding to the utterance;
And a control unit for controlling the voice processing unit and the server to process the voice command corresponding to the utterance when the utterance is input through the voice input unit,
The controller may be configured to display at least one call sign corresponding to the keyword stored in either the voice processor or the server when the voice command includes a keyword related to a call sign of a broadcast channel. An image processing apparatus characterized by the above. The method of claim 1,
At least one callsign candidate database corresponding to the keyword is stored in one of the image processing apparatus and the server, and at least one callsign corresponding to the keyword is selected through a search from the database. Processing unit. The method of claim 1,
The preset selection condition may include selecting a call sign having the highest frequency of selection from the at least one call sign based on usage history information of the image processing apparatus. The method of claim 1,
The preset selection condition may include selecting a call sign whose frequency of selection is greater than or equal to a predetermined order in a plurality of other image processing apparatuses communicating with the server. 3. The method of claim 2,
The controller may be configured to display the at least one call sign and to display an image of an infant providing the user to select one of the at least one call sign. The method of claim 5, wherein
And the control unit displays the at least one call sign in the order of the predetermined selection condition. The method of claim 6, wherein
And the controller is configured to display a cursor on a callsign having the highest rank among the at least one callsign displayed in the order of the predetermined selection condition. The method of claim 5, wherein
The controller may be further configured to determine which one of the at least one call sign is selected from the user during a preset time after the image is displayed, based on a selection condition provided to be different from the preset selection condition. The image processing apparatus, characterized in that for selecting one of the call sign. The method of claim 1,
The communication unit communicates with a speech-to-text (STT) server that converts the utterance into a voice command of text,
Wherein the control unit transmits the voice signal of the utterance to the STT server when the utterance is input to the voice input unit and receives the voice command corresponding to the utterance from the STT server. 10. The method of claim 9,
Wherein the control unit controls the voice command to be processed by the voice processing unit when the voice command is a short message and the voice command to be processed by the server when the voice command is a conversation. Device. The method of claim 1,
And a display unit for displaying a broadcast signal processed by the image processor as an image. In the control method of the image processing apparatus to communicate with the server,
Inputting a user's utterance;
Controlling the voice command corresponding to the speech to be processed by any one of the image processing apparatus and the server, and performing a preset corresponding operation according to the voice command;
The performing of the preset corresponding operation according to the voice command may include:
If the voice command includes a keyword related to a call sign of a broadcast channel, displaying at least one call sign corresponding to the keyword stored by either the image processing apparatus or the server. Control method of an image processing apparatus. The method of claim 12,
At least one callsign candidate database corresponding to the keyword is stored in one of the image processing apparatus and the server, and at least one callsign corresponding to the keyword is selected through a search from the database. Control method of processing device. The method of claim 12,
The preset selection condition is a control method of the image processing apparatus, characterized in that the call frequency having the highest selection frequency among the at least one call sign is selected based on the usage history information of the image processing apparatus. The method of claim 12,
The preset selection condition is a control method of an image processing apparatus, characterized in that for selecting a call sign of the frequency of selection in the plurality of other image processing apparatuses communicating with the server or more than a predetermined order. The method of claim 12,
And displaying the image by the infant providing the user to select any one of the at least one call sign when the at least one call sign is displayed. The method of claim 16, wherein
And the infant displays the at least one call sign in the order of the predetermined selection condition in the image. The method of claim 17, wherein
And displaying a cursor on a callsign having the highest rank among the at least one callsign displayed in the order of the predetermined selection condition in the image. The method of claim 16, wherein
The displaying of the image by the infant may include selecting to be different from the preset selection condition when an input for selecting one of the at least one call sign is not performed by the user during a preset time after the image is displayed. And selecting one of the call signs based on a condition. The method of claim 12,
The image processing apparatus communicates with the STT server for converting the speech into a voice command of the text,
Wherein the inputting of the user's utterance comprises:
Transmitting the voice signal of the utterance to the STT server;
And receiving the voice command corresponding to the utterance from the STT server. 21. The method of claim 20,
Controlling the voice command to be processed by the image processing apparatus when the voice command is a short text, and processing the voice command by the server when the voice command is a conversation text. Control method of an image processing apparatus. In an image processing system,
An image processing apparatus for processing a broadcast signal received from the outside to be displayed as an image;
And a server for communicating with the image processing apparatus,
The image processing apparatus comprising:
A voice input unit to which a user's utterance is input;
A voice processing unit for performing a predetermined corresponding operation according to a voice command corresponding to the utterance;
And a control unit for controlling the voice processing unit and the server to process the voice command corresponding to the utterance when the utterance is input through the voice input unit,
The controller may be further configured to display at least one call sign corresponding to the keyword stored in one of the voice processor and the server when the voice command includes a keyword related to a call sign of a broadcast channel. Processing system. The method of claim 22,
Further comprising a STT server for converting the speech into a voice command of the text,
The controller may be configured to transmit a voice signal of the speech to the STT server when the speech is input to the speech input unit, and receive the speech command corresponding to the speech from the STT server.

Images