JP7229906B2 - Command controller, control method and control program - Google Patents

Description

Embodiments relate to a command control device, a control method, and a control program.

2. Description of the Related Art In recent years, voice control technology for controlling devices by voice using voice recognition has been studied. For example, voice control technology can be used in place of a remote control for a television. When a user utters a command, which is a control instruction, a voice overlaid with the command (hereinafter referred to as a voice command) is received by a microphone attached to the television. and the command is extracted as data by voice recognition. The extracted command data becomes a command to be executed on the television. In this technology, a voice command uttered by the user may be recognized as an incorrect command by voice recognition due to the influence of ambient noise, etc., and improvement of voice recognition performance is being studied.

JP 2017-167247 A

However, the volume of ambient noise can interfere with voice recognition and limit the range of applicability of voice control technology. In addition, there is a possibility that the control by the voice control technology, which operates in normal times, may not operate normally due to increased noise in an emergency such as an earthquake.

A problem to be solved by the present invention is to provide a command control device, a control method, and a control program that support voice recognition for voice commands.

A command control device according to one embodiment is a command control device that generates an execution command including a control command for a device to be controlled based on an input voice, wherein a first command included in a recognition command obtained by voice recognition of the voice is execution command generating means for generating an execution command including one of one control instruction and a second control instruction different from the first control instruction; and speech recognition for obtaining the recognition command by recognizing the speech. additional information obtaining means for obtaining additional information; and storage means for storing correspondence relationships among the recognition commands, the additional information, and the execution commands, wherein the execution command generation means is configured to generate the recognition commands and the execution commands. and generating the execution command based on the additional information and the correspondence relationship .

FIG. 1 is a diagram showing a configuration example of the entire system according to the first embodiment. FIG. 2 is a block diagram showing an example of the functional configuration of the receiving device according to the embodiment; FIG. 3 is a block diagram showing an example of a functional configuration of a command control unit according to the embodiment; FIG. 4 is a diagram showing an example of a control target part that can be controlled by a voice command and the state of the control target part in the same embodiment. FIG. 5 is a diagram showing an example of auxiliary information that can be used in the same embodiment. FIG. 6 is a flowchart showing a processing operation example for the command control unit to receive a voice command and transmit an execution command in the same embodiment. FIG. 7 is a diagram showing an example of execution command generation conditions set in the command control unit for controlling the main power supply in the embodiment. FIG. 8 is a diagram showing an example of execution command generation conditions set in the command control unit for volume control in the second embodiment. FIG. 9 is a diagram showing an example of execution command generation conditions set in the command control unit for controlling reception of digital content in the third embodiment. FIG. 10 is a diagram showing a configuration example of the entire system according to the fourth embodiment.

Embodiments will be described below with reference to the drawings.

FIG. 1 is a diagram showing a configuration example of the entire system according to the embodiment.

The receiving device 10 is a device for viewing digital content, for example, a television receiving device (television device, television receiver, Also called a broadcast signal receiver). The receiving device 10 also has an external interface for connecting to a network 500 such as the Internet, and can view digital content provided by a content server device 200 (which may be a cloud server) connected to the network 500. is. Further, the receiving device 10 may have a recording/playback function, and the digital content recorded by the receiving device 10 can be viewed by the recording/playback function. Also, by connecting a recording/reproducing device (not shown) to the receiving device 10, digital content recorded by the recording/reproducing device (not shown) may be viewed. Although one receiver 10 is shown in FIG. 1, more receivers 10 may be connected. However, the receiving devices 10 do not need to have the same functions as long as they are capable of receiving digital content. Specifically, a recorder capable of only recording without a viewable monitor or a Set Top Box (STB) capable of receiving broadcast signals may be used. A television set, a recorder, an STB, and the like are collectively referred to as a receiving device 10 .

In this embodiment, an example of a television device is particularly shown, but the television device may be replaced with a receiver 10 such as a recorder or STB. Further, the receiving device 10 may be a mobile device such as a personal computer or a smart phone as a device having a similar receiving function.

The receiving device 10 of this embodiment can be controlled by voice using voice recognition. The command control unit 1, for example, recognizes a voice command uttered by a user, and controls each function in the receiving device 10 using the command obtained by the voice recognition (hereinafter referred to as a recognition command). A remote controller 100 is a remote controller for remotely controlling the receiving device 10 .

The receiving device 10 can also collect and store a viewing history of digital content viewed by the receiving device 10 (hereinafter referred to as viewing data). In addition, data unique to the receiving device 10 (hereinafter referred to as device-specific data) can be stored. Viewing data and device-specific data are collectively referred to as viewing device data. The receiving apparatus 10 can output stored data such as audio-visual equipment data to the viewing analysis apparatus 300 connected to the network 500, and receive analysis results of the audio-visual equipment data performed by the viewing analysis apparatus 300. FIG.

"Viewing" in this embodiment includes receiving, receiving, or recording digital content in a viewable state even if the user does not actually view it. Therefore, the "viewing history" in the present embodiment is, for example, a "receiving history" that is simply received by a receiving device such as an STB, but does not matter whether or not it is viewed, or if the receiving device is a recorder, , "recording history" received by the receiving device, recording reservation or recording, etc. are included. Similarly, the "viewing time" in the present embodiment includes, for example, the time when the receiving device such as STB receives the digital content, or when the receiving device is a recorder, the time when the digital content is recorded. .

Therefore, when the receiving device 10 is replaced with a receiving device such as a recorder or STB, reception log data generated by the receiving device such as the recorder or STB, download history data, recorded data, etc. are included in the audio-visual equipment data.

For example, the device-specific data may be registered in the receiving device 10 by the user using the remote control 100 of the receiving device 10 , or may be set by the manufacturer, such as the individual number of the receiving device 10 . The device-specific data includes, for example, the IP address and identification number of the receiving device 10, and demographic data (hereinafter referred to as demographic data) registered in advance by the owner or the like. Demographics are data for classifying users who view the receiving apparatus 10, and are information such as age, sex, family structure, and area of residence of the users, for example. The identification number is a number, character string, or the like that identifies a different receiver 10, and is composed of, for example, a combination of numbers and alphabets.

The content server device 200 is a network or cloud server that provides digital content. The content server device 200 is provided by, for example, a content service provider (CSP), a telecommunications carrier, or a digital content service provider called Over The Top (OTT). The content server device 200 also includes a server that provides services such as Video On Demand.

The viewing analysis device 300 exists on a network or in the cloud, collects and stores viewing equipment data stored by the receiving device 10, analyzes the stored data, performs various viewing analyses, and, for example, requests analysis. It is a device that outputs the analysis result to the receiving device 10 that has received the data. The viewing analysis device 300 may be constructed in a computer having a CPU, a memory, and the like, for example. The viewing analysis device 300 may be a personal computer, or may be a cloud service using a server, database, or the like.

Also, the viewing analysis device 300 may be able to identify each receiving device 10 by an identification number that the receiving device 10 has individually, and perform viewing analysis for each receiving device 10 .

Speech recognition device 400 is installed on network 500 . The speech recognition device 400 is built in a computer having a CPU, memory, and the like, for example. The speech recognition device 400 may be a personal computer or a cloud server. The speech recognition device 400 receives, via the network 500, digital data of a speech waveform of the user's speech received by a microphone or the like (hereinafter referred to as speech data), estimates or recognizes a command issued by the user, The recognized command (recognized command) is output as text data. In the speech recognition device 400, the commands issued by the user to the controlled object are listed in advance as text data, and the text data obtained from the received speech data is compared with the text data in the list to find the closest command in the list. to output the text data of the selected command. However, the speech recognition method in the speech recognition device 400 is not limited to this method.

The speech recognition apparatus 400 also includes a Speech To Text server (hereinafter referred to as an STT server) that generates speech text by converting speech data into text (characterization, verbalization, etc.), and a list of generated speech texts. It may also comprise a remote recognition server that generates the closest command from among the commands received as the recognition command. Specifically, the remote recognition server refers to a command list registered in advance in a storage unit (not shown) or the like, and selects a command that matches the voice text generated by the STT server or the closest command in the list. You may make it output as a recognition command.

The network 500 is a network in which the receiving device 10, the content server device 200, the viewing analysis device 300, and the viewing analysis device 300 are connected so that each device can communicate with each other, such as the Internet. Also, the network 500 is not limited to the Internet, and may be a network including a plurality of different networks as long as each device can communicate.

FIG. 2 is a block diagram showing an example of the functional configuration of the receiving device 10 according to the embodiment.

The receiving device 10 is a device for receiving and processing a signal on which digital content is superimposed to acquire and view the digital content.

The broadcast signal reception processing unit 20 processes a broadcast signal such as a digital broadcast received from the antenna 101 according to the digital broadcast standard, acquires and outputs content data such as video, audio, and text. The digital broadcasting standard may be, for example, the MPEG2 TS system used in 2K digital broadcasting or the MPEG Media Transport system (MMT system) used in 4K/8K digital broadcasting. may correspond to Processing that conforms to digital broadcasting standards includes demultiplexing processing that separates a digital data stream into digital data streams of content data such as video, audio, and text, error correction code decoding processing, and decoding of encrypted data. and decoding processing for encoding (video encoding, audio encoding, character encoding, etc.) applied to each content data.

The auxiliary information output section 21 extracts the information requested by the control section 90 from the broadcast signal and outputs it to the control section 90 . The auxiliary information output unit 21 extracts requested information from control information, program-related information, etc. included in the broadcast signal, and outputs the extracted information to the control unit 90 . The information output to the control unit 90 is processed as necessary and used by the command control unit 1 as auxiliary information.

The content processing unit 30 performs decoding processing for the encoding processing performed by the content server device 200 on the digital data input from the communication unit 102, and outputs content data such as video, audio, and characters. . Specifically, the content processing unit 30 performs decoding processing such as demultiplexing processing (separation processing), error correction code decoding processing, and decoding of encoded content data (video, text, audio, etc.). processing, etc.

The auxiliary information output unit 31 extracts information requested by the control unit 90 from data output by the content server device 200 and outputs the information to the control unit 90 . The auxiliary information output unit 31 extracts related attribute information such as the content program distributor from the control information output by the content server device 200 , and outputs the information to the control unit 90 . The information output to the control unit 90 is processed as necessary and used by the command control unit 1 as auxiliary information.

The recording/playback unit 40 is, for example, a disc player or an HDD recorder, stores content data output from the broadcast signal reception processing unit 20 and the content processing unit 30, and outputs the stored content data to the output control unit 60 in accordance with a playback request. , and output from the display unit 103 and the speaker unit 104 as video, text, and audio. The user views digital content stored in the recording/playback unit 40 by viewing video, text, and audio output from the display unit 103 and the speaker unit 104 . In this embodiment, the recording/playback unit 40 is one function of the receiving device 10, but may be an external device via the interface unit 105, for example. Further, when the receiving device 10 includes a plurality of tuners (corresponding to the broadcast signal reception processing unit 20), the recording/playback unit 40 allows the user to view the content A received and processed by the broadcast signal reception processing unit 20. However, the recording/playback unit 40 may record the content B received and processed by another broadcast signal reception processing unit 20 .

The equipment data generation unit 50 collects data from each functional unit (particularly, the broadcast signal reception processing unit 20, the content processing unit, and the recording/playback unit 40) of the receiving device 10 and generates audio-visual equipment data. The viewing device data includes device-specific data and viewing data. The device-specific data is data unique to the receiving device 10 , and may be set in the receiving device 10 by the user from the remote control 100 or the like, for example, when the receiving device 10 is installed. Also, the identification number used in the viewing analysis may be assigned in advance, for example, at the time of purchase of the receiving apparatus 10, and set in the device-specific data or the like.

The viewing data is, for example, a viewing history, and may be sequentially generated when some viewing is performed by the receiving device 10 . Specifically, for example, according to the timing at which the broadcast signal reception processing unit 20, the content processing unit 30, and the recording/reproducing unit 40 are started, each function unit provides the channel and program name (or equivalent) that provides the digital content. program id), the date and time when the program was viewed, and the like, and each functional unit outputs the stored data as viewing data to the device data generating unit 50 according to the timing at which each functional unit is stopped. The equipment data generation unit 50 processes the viewing data as necessary, and stores it in a storage unit (not shown) of the receiving device 10 . Further, each functional unit (particularly, the broadcast signal reception processing unit 20, the content processing unit 30, and the recording/playback unit 40) stores viewing data, and each functional unit receives a transmission request for viewing data from an external device. may output the viewing data to the equipment data generating section 50, and the equipment data generating section 50 may process the viewing data as necessary and output it as the viewing equipment data to the external device.

The equipment data generation unit 50 outputs the generated audio-visual equipment data to the communication unit 102 in response to a request from an external device (in particular, the viewing analysis device 300). The audio-visual equipment data is transmitted from the communication unit 102 via the network 500 to the requested audio-visual analysis device 300 . Further, when the reception device 10 detects a change in the viewing device data, the viewing device data may be transmitted to the viewing analysis device 300 at an arbitrary timing.

The auxiliary information output unit 51 receives audio-visual equipment data generated by the equipment data generation unit 50, audio-visual data collected from each function of the receiving device 10, and various analysis result data output by the audio-visual analysis device 300, and controls them. Output to unit 90 . The information output to the control unit 90 is processed as necessary and used by the command control unit 1 as auxiliary information.

The output control unit 60 adjusts the output timing, display method, etc. of the content data output by the broadcast signal reception processing unit 20 , the content processing unit 30 , and the recording/playback unit 40 , and outputs the content data to the display unit 103 and the speaker unit 104 .

The state switching unit 62 changes the current display state of the display unit 103 (ON state or OFF state, displayed state or non-display state, etc.) and the current output state of the speaker unit 104 (ON state or OFF state, audio output state, audio mute state, etc.) is switched according to the control from the control unit 90 . The control unit 90 manages the display state of the display unit 103 and the output state of the speaker 104 , and the control unit 90 controls the state switching unit 62 according to control commands from the remote controller 100 and the command control unit 1 .

The sensor unit 70 is, for example, a camera installed in front of the television, and may take a picture of the front of the television with the camera and use image recognition from the photographed image, for example, to guess the user in front of the television. .

The auxiliary information output unit 71 outputs the user information estimated by the sensor unit 70 to the control unit 90 . The information output to the control unit 90 is processed as necessary and used by the command control unit 1 as auxiliary information.

The main power supply unit 80 is a power supply for the main function of the receiving device 10, and for example, outputs digital content to the display unit 103 and the speaker unit 104 of the television device, and stops the output (this operation turns on the television device). This is the power supply used during the -OFF operation.

The state switching unit 82 switches the current state of the main power supply unit 80 , that is, the ON/OFF state of the television apparatus, under the control of the control unit 90 . Control unit 90 manages the current state of main power supply unit 80 , and control unit 90 controls state switching unit 82 according to control commands from remote controller 100 and command control unit 1 .

The control unit 90 controls each function of the receiving device 10 . Specifically, the control unit 90 receives various control signals from the interface unit 105 and controls each function of the receiving device 10 . For example, when the user designates from the remote control 100 whether to view content by a broadcast signal or view content from the content server device 200, the control unit 90 receives a control signal from the remote control via the interface unit 105. It receives and controls the function of the receiving device 10 to perform the operation specified by the user. In FIG. 2, data may also be exchanged with functional blocks that are not particularly connected to the control unit 90 .

Also, the control unit 90 in this embodiment receives an execution command from the command control unit 1 via the interface unit 105, and controls each function in the receiving device 10 according to the execution command.

Auxiliary information management unit 91 is output by auxiliary information output units (auxiliary information output unit 21, auxiliary information output unit 31, auxiliary information output unit 41, auxiliary information output unit 51, auxiliary information output unit 71, etc.) in each function. Auxiliary information is received and stored in a storage unit (not shown). The auxiliary information management unit 91 transmits the stored auxiliary information of each function to the command control unit 1 from the interface 105 .

For the information stored in the auxiliary information management unit 91, predetermined items are set in the auxiliary information output unit in each function, and when the auxiliary information is updated in each function, the auxiliary information output unit spontaneously You may make it output to the auxiliary information management part 91. FIG. Also, the auxiliary information management section 91 may request auxiliary information from the auxiliary information output section of each function as necessary.

The state information management unit 92 stores the state information of the state switching units (state switching unit 62, state switching unit 82, etc.) in each function in a storage unit (not shown). The state information management unit 92 transmits the stored state information of each function to the command control unit 1 via the interface 105 . In this embodiment, the control unit 90 controls the state of each function, so the state information of the state information management unit 92 is always kept up-to-date. For the information stored by the state information management unit 92, predetermined items are set in a state information output unit (not shown) within each function, and when the state information is updated in each function, the state information The output section may voluntarily output to the state information management section 91 . Also, the state information management section 92 may request state information from the state information output section of each function as necessary.

The time management unit 93 manages the time of the receiving device 10 . The receiver 10 may have a clock inside, or the time may be obtained by extracting it from a broadcast signal or the like.

The communication unit 102 performs data transmission/reception processing with various devices connected to the network 500 according to a predetermined communication protocol such as TCP/IP or UDP/IP.

The display unit 103 is, for example, a monitor that displays images and characters. The speaker unit 104 is, for example, a speaker that outputs sound. The display unit 103 and the speaker unit 104 output the content data output by the output control unit 60 as video, text, and audio. The user views digital content provided by broadcast signals, content server device 200 and other recording/playback unit 40 by viewing video, text, and audio output from display unit 103 and speaker unit 104 .

The interface unit 105 is an interface for controlling the receiving device 10 from the outside such as the remote controller 100 . Output to unit 90 . Instead of the remote control 100, it may have an interface for receiving a control signal from a terminal such as a smart phone (not shown). Also, the interface unit 105 may have an interface for connecting with an external device. For example, it may be an interface for connecting the receiving device 10 and an external HDD recorder (not shown). In this case, the user can view digital content output from an external HDD recorder (not shown) on the display unit 103 and speaker unit 104 .

Further, the interface 105 in this embodiment has an interface capable of communicating with the interface section 15 of the command control section 1, and the interface may be various serial buses, for example. The interface 105 also receives an execution command output by the command control unit 1 and outputs the execution command to the control unit 90 .

FIG. 3 is a block diagram showing an example of a functional configuration of a command control unit according to the embodiment;

In the command control unit 1, the command generation unit 11 generates a recognition command based on the recognition command generated by the command recognition unit 13 through voice recognition, and the additional information (auxiliary information and state information) acquired by the auxiliary information acquisition unit 16 and the state acquisition unit 17. , an execution command is generated and output from the command transmission unit 18 to the outside of the command control unit 1 . Each functional block will be described below.

The command generation unit 11 stores combinations of recognition commands, additional information, and execution commands (hereinafter referred to as a condition combination list) in the storage unit 111 . The condition combination list can be set in advance by the user. The condition combination list may be incorporated in the computer program of the command generator 11, or may be downloaded from an external server via the network 500, for example. When the recognition command and the additional information are input, the command generator 11 refers to the condition combination list to generate and output an execution command.

The voice detection unit 12 is, for example, a microphone, receives voice uttered by the user, obtains voice data of the received voice waveform by sampling or the like, and outputs the voice data.

The command recognition unit 13 performs voice recognition from voice data output by the voice detection unit 12, estimates or recognizes a command issued by the user, and outputs the recognized command as text data. The command recognition unit 13 may include a voice data processing unit (speech recognition engine) for executing voice recognition within the command recognition unit 13 itself. Voice data can also be sent to obtain recognition commands. By using the speech recognition device 400, the manufacturing cost of the command recognition section 13 can be reduced. In addition, since the speech recognition device 400 obtains speech data from a large number of receiving devices 10 and performs speech recognition, the speech recognition device 400 can obtain a learning effect and improve the performance of speech recognition. . However, in order to use the speech recognition device 400, it is necessary to use the network 500, so there is a disadvantage that the processing delay of speech recognition is large. There is an advantage that the processing delay of is small. In addition, although FIG. 3 shows an example in which the voice detection unit 12 (speaker) is incorporated, a smart speaker or the like may be used. For example, a smart speaker is used by connecting to the interface 105 . Specifically, a smart speaker equipped with a voice recognition engine generates a recognition command, and the command control unit 1 (or the command generation unit 11) acquires the recognition command generated by the smart speaker via, for example, the interface 105. It's okay. The acquired recognition command may be used by the command generation unit 11 to generate an execution command.

The user interface unit 14 is an interface, such as a keyboard of a personal computer, through which characters can be input. Specifically, the user sets the condition combination list in the storage unit 111 from the user interface unit 14 . Note that the condition combination list may be set in the storage unit 111 using the remote control 100, smartphone, or the like. Alternatively, the command generation unit 11 may download the condition combination list to the storage unit 111 from a server (not shown) provided outside the receiving device 10 that provides the condition combination list.

The interface unit 15 performs various data communications with the interface unit 105 . Specifically, the interface unit 15 receives auxiliary information and status information from the interface unit 105 . Also, the interface unit 15 transmits the execution command generated by the command generation unit 11 to the interface unit 105 .

The auxiliary information acquisition unit 16 acquires auxiliary information from the auxiliary information management unit 91 via the interface unit 15 . For example, the auxiliary information acquisition unit 16 outputs an acquisition request for auxiliary information to the auxiliary information management unit 91 in accordance with the timing at which the recognition command is output from the command recognition unit 13, and receives the auxiliary information from the auxiliary information management unit 91. may be obtained.

The state acquisition unit 17 acquires state information from the state information management unit 92 via the interface unit 15 . For example, the state information acquisition unit 16 outputs a state information acquisition request to the state information management unit 92 in accordance with the timing at which the command recognition unit 13 outputs the recognition command or the timing at which the command generation unit 11 receives the recognition command. , the state information may be acquired from the state information management unit 92 .

The command transmission unit 18 transmits the execution command generated and output by the command generation unit 11 from the interface unit 15 to the control unit 90 . Also, it can be transmitted to a device or device on the network 500 via the communication unit 102 .

The control section 19 controls each functional block within the command control section 1 . In FIG. 3, data exchange (control) may also be performed between functional blocks that are not particularly connected to the control unit 19 .

The voice analysis unit 121 performs, for example, frequency analysis (voiceprint analysis) on the voice data output from the voice detection unit 12, estimates the attributes of the voice source such as adult/child, age, and gender, and outputs the result of voice source estimation. get The speech analysis unit 121 performs necessary processing on the speech source estimation result and outputs the result as auxiliary information to the auxiliary information acquisition unit 16 . The speech source estimation result obtained by the speech analysis unit 121 can also be used to determine whether the command generation unit 11, the command recognition unit 13, the command transmission unit 18, etc. can be activated. When the voice analysis unit 121 outputs the voice source estimation result to the control unit 19 so as not to output an execution command when, for example, the user who uttered the voice is a child, the control unit 19 may enable or disable the functions of the command generation unit 11, the command recognition unit 13, and the command transmission unit 18.

FIG. 4 is a diagram showing an example of a control target part that can be controlled by a voice command and the state of the control target part in the same embodiment.

From the left column, "NO", "control target part", "possible state value", and "voice command" are shown. A “control target part” is a part of the receiving device 10 that can be controlled by a voice command. The "possible state value" is a state that the "controlled part" can take. "Voice command" is a control command uttered by the user when switching the state value of the "control target part".

"NO"=1 indicates that the "possible state values" of the main power supply unit 80, which is the "control target part" of the receiving device 10, are two states of ON and OFF. In this case, the "voice command" for switching the state value is "power ON" to turn the state value ON, and "power OFF" to turn the state value OFF. That is, the user utters "power ON" to turn on the power of the television device, and the user utters "power OFF" to turn off the power of the television device.

“NO”=2 indicates that the “possible state values” of the state switching unit 62 of the output control unit 60, which is the “part to be controlled” of the receiving device 10, are ON and OFF. That is, in order to output sound from the speaker unit 104 by turning on the volume of the television device, the user utters "volume on" and turns off the volume of the television device so that the sound is not output from the speaker unit 104. To (mute), the user says "volume off".

“NO”=3 is a content output device that is outputting digital content to the display unit 103 and the speaker unit 104 . A content output device is a general term for the broadcast signal reception processing unit 20, the content processing unit 30, and the recording/playback unit 40. FIG. Specifically, "tuner" in the "possible state value" column corresponds to the broadcast signal reception processing unit 20, "net" corresponds to the content processing unit 30, and "recorder" corresponds to the recording/playback unit 40, respectively. For example, in order to set the broadcast signal reception processing unit 20 to the receiving state and cause the display unit 103 and the speaker unit 104 to output content based on the broadcast signal, the user utters "tuner". In order to set the content processing unit 30 to the reception state and cause the display unit 103 and the speaker unit 104 to output the content from the content server device 200, the user utters "net". In order to set the recording/reproducing unit 40 to the reproducing state and output to the display unit 103 and the speaker unit 104, the user utters "recorder".

“NO”=4 indicates a tuner that is outputting digital content to the display unit 103 and the speaker unit 104 . BS, CS, and terrestrial digital in "possible state values" indicate tuners for BS digital broadcasting, CS digital broadcasting, and digital terrestrial television broadcasting (digital terrestrial broadcasting), respectively. For example, in order to cause the display unit 103 and the speaker unit 104 to output the contents of the BS digital broadcast in the reception state of the BS digital broadcast, the user utters "BS". In order to cause the display unit 103 and the speaker unit 104 to output the contents of the CS digital broadcast in the state of receiving the CS digital broadcast, the user utters "CS". In order to set the terrestrial digital broadcasting to the reception state and cause the display unit 103 and the speaker unit 104 to output the content of the terrestrial digital broadcasting, the user utters "terrestrial digital broadcasting".

“NO”=5 is the channel (program) output to the display unit 103 and the speaker unit 104 by the content output device. 1ch, 2ch, and 3ch of "possible state values" indicate channel numbers. For example, when the display unit 103 and the speaker unit 104 are to output a program on the 1ch while the 1ch is in the receiving state, the user utters "1ch". The same is true for other channels. It should be noted that a channel may normally be defined for each content output device and for each tuner. For example, when the broadcast signal reception processing unit 20 is used as the content output device, channel numbers may be assigned to tuners "BS", "CS", and "terrestrial digital". Also, a unique channel number may be uniformly assigned to all channels of the content output device. In that case, the type of content output device and the type of tuner can be specified by the channel number.

It is also possible to have a state of "home (place to return)" as a "possible state value". "Home" is a state value that can be set by the user.

For example, in the example of No. 3, a case where "tuner" is set as the "home" state value of the content output device, which is the part to be controlled, will be described. For example, while the user is watching a program on the content output device "NET", that is, when the current state of the content output device is "NET", the user utters "NET" as a voice command, and the command recognition unit 13, "net" is recognized and generated as a recognition command. When the recognition command is input, the command generation unit 11 generates and transmits an execution command "tuner" for switching the state to "home" or "tuner", and switches the content output device to the "tuner".

For example, in the example of NO4, a case will be described where "terrestrial digital broadcasting" is set as the "home" state value of the tuner, which is the part to be controlled. For example, while the user is listening to the tuner of "BS", that is, when the current state of the tuner is "BS", the user utters "BS" as a voice command, and the command recognizer 13 recognizes Assume that "BS" is recognized and generated. When the recognition command is input, the command generation unit 11 generates and transmits an execution command "digital terrestrial" for switching the state to "digital terrestrial" which is "home", and switches the tuner to "digital terrestrial".

In the example of NO5, the case where "1ch" is set as the "home" state value of the channel which is the controlled part will be described. For example, while the user is viewing the channel "2ch", that is, when the current state of the channel is "2ch", the user utters "2ch" as a voice command, and the command recognizer 13 recognizes Assume that "2ch" is recognized and generated. When the recognition command is input, the command generator 11 generates and transmits an execution command "1ch" for switching the state to "home" or "1ch", and switches the channel to "1ch".

The "home" state value may be set by the user, or may be automatically set to the state value immediately before the power of the television set was turned off last time. Also, there may be "home" as a voice command. For example, when the user utters the voice command "home" and "home" is generated as a recognized command, the state may transition to the state value set as "home".

FIG. 5 is a diagram showing an example of auxiliary information that can be used in the same embodiment.

From the left column, "NO", "information source", "auxiliary information", and "information value" are shown. The "information source" is the source of the "auxiliary information" or the extraction source (extracted part) of the "auxiliary information". "Auxiliary information" is information used when the command control unit 1 creates an execution command in this embodiment. "Information value" is the value of "auxiliary information".

"NO"=1 indicates that the time management unit 93 of the receiving device 10, which is the "information source", includes the time in the auxiliary information.

"NO" = 2 determines the attribute of the voice transmission source from the voiceprint obtained by the voice analysis performed by the voice analysis unit 121 of the receiving device 10, which is the "information source", and assists the attribute of the voice transmission source. Indicates inclusion in the information. The attributes of the source of voice are, for example, the age of the source, the classification of adults and children defined by age, and the classification of infants, kindergarten children, elementary school students, junior high school students, high school students, university students, working people, etc. defined by age. User identification information.

"NO" = 3 determines the user identification information from the speech recognition result obtained by the speech recognition performed by the command recognition unit 13 of the receiving device 10, which is the "information source", and converts the attribute of the user identification information into the auxiliary information. indicates inclusion.

"NO" = 4, 5, 6 are obtained from voice strength, voice pitch, and voice speed obtained by voice analysis performed by the voice analysis unit 121 of the receiving device 10, which is the "information source", respectively. Each indicates that the strength of the voice, the pitch of the voice, and the speed of the voice are provided as auxiliary information.

"NO" = 7 means that the sensor unit 70 (for example, a camera) of the receiving device 10, which is the "information source", determines the user identification information from the image recognition result obtained by the camera, and converts the attribute of the user identification information into the auxiliary information. indicates that it should be included in

"NO" = 8 to 11 are "broadcaster", "program broadcasting time period", "program type", This indicates that the "program name" is included in the auxiliary information. In the case of "broadcaster", the name of the vendor such as vendor A, vendor B, and vendor C is set as the value of the auxiliary information. In the case of "program broadcasting time zone", the broadcasting time zone is set as the value of the auxiliary information. In the case of "type of program", the value of auxiliary information is the type of program such as drama, sports, music, news, education, and emergency information. In the case of "program name", for example, program names such as program A, program B, and program C are set as auxiliary information values.

"NO"=12 includes the demogram obtained from the analysis result provided by the viewing analysis device 300, which is the "information source", in the information assistance.

"NO" = 13 to 16 are "broadcasting business This indicates that the auxiliary information includes "person", "program broadcasting time period", "program type", and "program name".

"NO" = 17 to 20 are "distributor", "program broadcast time zone", and "program This indicates that "type" and "program name" are included in the auxiliary information. Also, the auxiliary information may include the user who recorded the digital content (especially referred to as the recording manager).

(First embodiment)
In this embodiment, an operation example in which ON/OFF of the main power supply of the receiving apparatus is controlled based on a voice command issued by the user and additional information will be described.

FIG. 6 is a flowchart showing a processing operation example for the command control unit to receive a voice command and transmit an execution command in the same embodiment.

Assume that the user issues a voice command “power ON” or “power OFF” in order to control ON/OFF of the main power of the receiving device 10 . The voice detection unit detects voice (YES in step S11). If the voice detection unit does not detect the voice, it waits until it detects the voice (NO in step S11). Judgment whether the sound detection unit detects or does not detect sound is, for example, by setting a threshold for the intensity of the input sound, determining that the sound is detected if the intensity is equal to or greater than the threshold, and determining that the sound is detected if the intensity is less than the threshold. It may be determined that no sound is detected.

The voice detection unit 12 outputs voice data of the received voice to the voice analysis unit 121, and the voice analysis unit 121 performs voice analysis processing on the received voice data (step S12). Specifically, the voice analysis unit 121 performs frequency analysis (voiceprint analysis) on voice data to estimate the attribute of the source of the voice.

When the speech analysis unit 121 outputs the estimation result to the control unit 19, the control unit 19 determines whether or not to generate a recognition command from the estimation result (step S13). The rules for determining whether or not to generate the recognition command may be set by the user, for example, in the storage unit 111 from the user interface unit 14 . The control unit 19 accesses the storage unit 111 and refers to the determination rule for recognition command generation. When determining to generate a recognition command, the control unit 19 causes the command recognition unit 13 to perform voice recognition on the voice data (YES in step S13). When the control unit 19 determines not to generate a recognition command, it controls the command recognition unit 13 so as not to perform voice recognition on the voice data, and puts the command recognition unit 13 into a waiting state until the next voice is detected. (NO in step S13, S11). When the control unit 19 determines not to generate the recognition command, for example, the display unit 103 or the speaker unit 104 outputs a message such as "Recognition command was not generated" to notify the user. It's okay.

When commanded by the control unit 19 to generate a recognition command, the command recognition unit 13 obtains the recognition command as text data by voice recognition. The command recognition unit 13 outputs the recognition command to the command generation unit 11 (step S14). In step S14, the command recognition unit 13 first attempts to acquire a recognition command with the voice recognition engine provided in the command recognition unit 13, and if the voice recognition fails and is not acquired, the recognition rate of voice recognition is higher. An external speech recognition device 400 may be used to obtain recognition commands.

Upon receiving the recognition command from the command recognition unit 13 , the command generation unit 11 refers to the condition combination list in the storage unit 111 .

FIG. 7 is a diagram showing an example of execution command generation conditions (combination condition list) set in the command control unit for controlling the main power supply in the embodiment.

An example of the combination condition list indicates "NO", "execution command", "recognition command", "status information", and "auxiliary information" from the left column. The "execution command" described in the same line is determined based on the "recognition command", "status information", and "auxiliary information" described in each line. A “recognition command” is a recognition command generated and output by the command recognition unit 13 . The combination condition list may be set in the storage unit 111 from the user interface unit 14 by the user, for example. The combination condition list shown in FIG. 7 is an example, and the number of pieces of auxiliary information (the number of columns) can be added.

Returning to FIG. 6, the processing operation of the command control section 1 will be described. When the command recognizing unit 13 inputs, for example, "power ON" as the "recognition command", the command generating unit 11 refers to the combination condition list and determines the column items of the list, ie, "auxiliary information" and "state information". The auxiliary information acquisition unit 16 and the state information acquisition unit 17 are instructed to acquire the information. The auxiliary information acquisition unit 16 requests the auxiliary information management unit 91 to acquire the auxiliary information items of the combination condition list, namely, “time”, “voice strength”, and “user identification information”. (step S15). The state information acquisition unit 17 recognizes that the control target is the main power supply 80 because the “recognition command” is “power ON”, and acquires the state information of the main power supply 80 to the state information management unit 92 . , to the command generator 11 (step S16).

The command generation unit 11 refers to the combination condition list to search for a line in which the acquired auxiliary information, status information, and recognition command match the combination of conditions in the combination condition list. If there is a command in the "execution command" item in the line where the combination of conditions matches, the command described in the "execution command" item is generated as an execution command and output to the command transmission unit 18 (step S17). , YES in S18, S19). On the other hand, for example, like NO7 in FIG. 7, when the item of "execution command" that matches the combination of conditions is "no transmission", no execution command is generated, and the command control unit 1 proceeds to the next step. is detected (NO in steps S17 and S18). If the execution command is “not sent”, the command control unit 1 may send a message to the control unit 90 that means “the execution command was not sent or was not generated”. Upon receiving the message, the control unit 90 may display the message on the display unit 103 or output a voice including the content of the message from the speaker unit 104 to notify the user.

Further, when the item of "execution command" matching the combination of conditions is "no transmission", the command control unit 1 may generate and transmit an "execution command for maintaining the current state". For example, as a result of the voiceprint analysis of the voice command by the voice analysis unit 121, when auxiliary information indicating that the source of the voice is “child” is input to the command generation unit 11 as the user identification information, the auxiliary information is input to the command generation unit 11 without using the recognition command. An "execution command for maintaining the current state" may be generated and transmitted using only information. In this case, the command generation unit 11 may send a message to the control unit 90 with a meaning such as "that operation cannot be performed." At this time, the control unit 90 that has received the message may display the message on the display unit 103 or output a voice including the content of the message from the speaker unit 104 to notify the user.

When the execution command is input, the command transmission section 18 transmits the execution command to the control section 90 via the interface section 15 (step S101). The control unit 90 controls the functions to be controlled according to the received execution commands.

When the command control unit 1 generates or transmits the execution command, the command control unit 1 may transmit to the control unit 90 a message containing the content of "the execution command has been transmitted." Further, when the recognition command and the generated execution command are different, the command control section 1 may transmit a message including the content "the execution command is different from the recognition command" to the control section 90 . The command control unit 1 may notify the user by displaying a message on the display unit 103 or by outputting a voice including the content of the message from the speaker unit 104 . By doing so, the user can confirm whether the voice command issued by the user is correctly executed.

Details of the combination condition list will be described again with reference to FIG.

When "NO" = 1, the auxiliary information is all "-", which indicates that the auxiliary information is not used. is. In the example of "NO"=1, when the "recognition command" is "power ON" and the "state information" is "ON", the execution command is "power OFF". Since "NO"=2 to 4 are the same, the explanation is omitted.

When "NO"=5, the "recognition command" is "power ON", the "state information" is "ON", and the "time" which is the first "auxiliary information" is "noon". , and when the second "auxiliary information" "vocal strength" is "strong", the execution command is "no transmission (or no generation)". Here, the value of "time" which is "auxiliary information" is set to "daytime". A corresponding time classification value may be determined from the “time” acquired by the auxiliary information acquisition unit 16 , and the time classification value (daytime when NO=5) may be output to the command generation unit 11 . The same is true for the second "auxiliary information", ie, "strength of voice". For example, the auxiliary information acquisition unit 16 has a correspondence relationship between the “speech intensity” input from the speech analysis unit 121 and the intensity classification (strong, weak), and the “speech intensity , and output the strength classification value (strong if NO=5) to the command generating unit 11 . Since "NO"=6 to 12 are the same, the explanation is omitted. By using the "time" and "voice strength" as auxiliary information such as "NO" = 5 to 12, the surrounding noise becomes louder during the "daytime" time zone, so the voice recognition Executable commands can be generated taking into account situations where the accuracy of the engine is degraded and the recognized commands differ from the user's spoken commands.

When "NO"=13, the "recognition command" is "power ON", the "status information" is "ON", and the "time" which is the first "auxiliary information" is "night". , the execution command is "power off" when the "user identification information", which is the second "auxiliary information", is "adult". As with "NO"=5, for example, when the voice analysis unit 121 inputs the age of the source of the voice command by voiceprint analysis to the auxiliary information acquisition unit 16, the correspondence relationship between the age and the age classification value (adult, child) , the corresponding age classification value may be determined from the “age” received by the auxiliary information acquisition unit 16 , and the age classification value (adult if NO=13) may be output to the command generation unit 11 . Since "NO"=14 to 20 are the same, the explanation is omitted. By using "time" and "user identification information" as auxiliary information such as "NO" = 13 to 20, the voice recognition engine can Although the accuracy is not degraded, "Night" can be used when the user wants to restrict the generation and transmission of execution commands.

As described above, according to the procedure of the flowchart of FIG. 6, it is possible to generate an execution command using the condition combination list of FIG.

When the condition of "NO"=1 in the condition combination list shown in FIG. 7 is applied, the current state of the main power supply (corresponding to "state information") is "ON". Normally, in such a situation, the user is less likely to issue the voice command "power ON", and is more likely to issue the voice command "power OFF", which is the opposite of the current state "ON". Conceivable. However, when the voice command "power off" is recognized as "power on" by the voice recognition engine of the command recognition unit 13 due to ambient noise, etc., the user utters "power off". , a situation occurs in which the main power supply of the receiving apparatus 10 cannot be turned off, and the stress on the user becomes great. However, according to this embodiment, the command control unit 1 interprets the recognition command based on the state information of the receiving apparatus 10 using the condition of "NO"=1 in the condition combination list. It is possible to prevent the situation. Similarly, when "NO" in the condition combination list = 2 to 4 is applied to the command control unit 1, if the recognition command is a control instruction for switching the current state ("state information") of the main power supply, the recognition Match the control instructions of the command and the execution command. Conversely, if the recognition command is a control instruction to the same state as the "state information", the control instruction of the execution command will be a control instruction opposite to or different from the recognition command. The reason for this behavior is that the speech recognition engine is particularly likely to misinterpret ON and OFF speech. In this embodiment, considering that the user rarely issues a voice command so that the current state of the controlled object and the state after control are the same, interpretation of the voice command by voice recognition is supported. make it possible.

In the condition combination list of FIG. 7 in this embodiment, NO1 to NO20 indicate condition combinations for determining execution commands. It is also possible to refer to the condition combination list in consideration of Priority may be given in the order of rows from NO1 to NO20, as shown in FIG. In this case, even if the command generation unit 11 acquires the auxiliary information, it does not use the auxiliary information because NO1 to NO4 have priority. Also, a column item indicating the order of priority may be added to the list in FIG. 7 so that the user can set the priority for the combination of conditions in each row.

Also, when there are multiple pieces of "auxiliary information", priority may be given within the "auxiliary information". For example, in the combination condition list of FIG. 7, priority is given to auxiliary information in the order of "time", "voice strength", and "user identification information". In this case, the command generation unit 11 refers to, for example, the condition combination including the auxiliary information with the higher priority in the combination condition list. Specifically, the highest priority is given to the combination of conditions in which the auxiliary information is only "time", the next priority is given to the combination of conditions only in "time" and "strength of voice", and then The user may set so that priority is given only to the condition combination of "time" and "user identification information".

In addition, by setting a score indicating priority to "time", "voice strength", and "user identification information" by the user, it is assigned to "time", "voice strength", and "user identification information" The command generator 11 may be caused to calculate the sum of the points obtained, and priority may be given to each combination condition list by, for example, giving higher priority to a list with a higher sum of points. In this case, since the command generator 11 can calculate the priority, the user only needs to set the score indicating the priority for "time", "voice strength", and "user identification information".

Moreover, basically, it is desirable to set the condition combinations shown in the combination condition list so that there are no combinations that have the same conditions. If there is a combination that satisfies the same condition, the command generator 11 may predetermine a rule such as selection in the order of the list.

(Second embodiment)
In the present embodiment, ON/OFF of the volume output from the speaker unit 104 of the receiving apparatus 10 is controlled using the voice command issued by the user, the status information, and the program type and voice strength as auxiliary information. An operation example of the command control unit 1 in the case of doing is shown. In addition, in this embodiment, it is assumed that the main power supply is in an ON state.

FIG. 8 is a diagram showing an example of execution command generation conditions set in the command control unit for volume control in the second embodiment. An example of a processing operation for the command control unit 1 in this embodiment to receive a voice command and transmit an execution command will be described with reference to FIG. Description is omitted.

Assume that the user issues a voice command “volume ON” or “volume OFF” in order to control ON/OFF of the volume output of the speaker unit 104 of the receiving device 10 . The voice detection unit detects voice (YES in step S11). As a result of the voice analysis processing, the control unit 19 determines to generate a recognition command, and causes the command recognition unit 13 to perform voice recognition on the voice data (YES in step S13). The command recognition unit 13 obtains the recognition command as text data through voice recognition, and outputs the recognition command to the command generation unit 11 (step S14).

Upon receiving the recognition command from the command recognition unit 13 , the command generation unit 11 refers to the condition combination list in the storage unit 111 . When "volume ON" is input as the "recognition command" from the command recognition unit 13, the command generation unit 11 refers to the combination condition list and acquires the column items "auxiliary information" and "state information" of the list. to the auxiliary information acquisition unit 16 and the state information acquisition unit 17, respectively. The auxiliary information acquisition unit 16 requests the auxiliary information management unit 91 to acquire the items of the auxiliary information of the combination condition list, namely, “type of program” and “intensity of voice”, and outputs them to the command generation unit 11 (step S15). The state information acquisition unit 17 recognizes that the control target is the main power supply 80 because the “recognition command” is “volume ON”, acquires the state information of the speaker unit 104 from the state information management unit 92, and receives the command Output to the generation unit 11 (step S16).

The command generation unit 11 refers to the combination condition list, and if there is a command in the item of “execution command” of the line in which the combination of the acquired auxiliary information, the status information, and the recognition command matches, ” is generated as an execution command, and output to the command transmission unit 18 (steps S17, YES in S18, S19). On the other hand, if the item of "execution command" is "no transmission", the command control unit 1 does not generate an execution command and waits until the next voice is detected (NO in steps S17 and S18). ). When the execution command is input, the command transmission section 18 transmits the execution command from the interface section 15 to the control section 90 (step S101).

Details of the combination condition list will be described with reference to FIG.

If "NO"=1, the "state information" is "ON", indicating that the "volume" is currently in the output state. The condition combination of "NO"=1 is that the "recognition command" is "volume ON", the first "auxiliary information" "program type" is "emergency information", and the second "auxiliary This is an example in which the command generation unit 11 generates “no transmission (or no generation)” as an execution command when “voice strength”, which is information, is “-” (no condition). Since "NO"=2 to 4 are the same, the explanation is omitted. If the "type of program" is used as auxiliary information, such as "NO"=1 to 4, and the "type of program" is "emergency information", a request to turn on the volume is issued in any situation. can be considered. For example, if an earthquake or the like occurs while the broadcast signal reception processing unit 20 is receiving a broadcast signal, and if the volume is turned off by chance, the user may issue a voice command "volume on" to turn on the volume. to output However, in an emergency such as an earthquake, it is expected that the surrounding noise will increase, and there is a high possibility that the voice command issued by the user will be erroneously recognized. In such a case, when the auxiliary information acquisition unit 16 acquires "emergency information" as the "program type" of the acquired auxiliary information, the command generation unit 11 generates the received "recognition command" and the "status information" of the control target. Always turn on the volume regardless of

“NO”=5 to 12 are examples of using “user identification information” as auxiliary information. For example, when it is desired to prevent children from viewing digital content on the receiving device 10 during daytime hours, a combination of conditions such as "NO"=5 to 12 can be used.

As described above, the user sets the combination condition list as in the present embodiment, so that various use cases can be assumed and command control can be performed for voice commands.

(Third embodiment)
In the present embodiment, the receiving device 10 outputs digital content to the display unit 103 and the speaker unit 104 using voice commands issued by the user, status information, and user identification information and time as auxiliary information. An operation example of the command control unit 1 when controlling is shown. In addition, in this embodiment, it is assumed that the main power supply is in an ON state. Also, in this embodiment, an example of outputting two execution commands for one voice command is shown.

FIG. 9 is a diagram showing an example of execution command generation conditions set in the command control unit for controlling reception of digital content in the third embodiment.

An example of the processing operation for the command control unit 1 in this embodiment to receive a voice command and transmit an execution command will be described using the flowchart of FIG. omit the explanation.

Assume that the user issues any of the voice commands “net”, “tuner”, or “recorder” in order to control the output of digital content to display unit 103 and speaker unit 104 of receiving device 10 . The voice detection unit detects voice (YES in step S11). Through steps S12 and S13, the command recognition unit 13 obtains the recognition command as text data by voice recognition, and outputs the recognition command to the command generation unit 11 (step S14).

When the "recognition command" is input from the command recognition unit 13, the command generation unit 11 refers to the condition combination list in the storage unit 111, and acquires the column items "auxiliary information" and "status information" of the list. to the auxiliary information acquisition unit 16 and the state information acquisition unit 17, respectively. The auxiliary information acquisition unit 16 requests the auxiliary information management unit 91 to obtain the items of the auxiliary information of the combination condition list, namely, “user identification information” and “time”, and outputs them to the command generation unit 11 (step S15). . The state information acquisition unit 17 recognizes that the control target is the content output device from the "recognition command", acquires the state information of the speaker unit 104 from the state information management unit 92, and outputs it to the command generation unit 11 (step S16).

The command generator 11 generates an execution command through steps 17 to S19 and outputs it to the command transmitter 18 . An execution command is transmitted from the command transmission unit 18 to the control unit 90 (step S101). In this embodiment, two execution commands are generated. A first execution command for the content output device and a second execution command for the program type.

Details of the combination condition list will be described with reference to FIG.

If “NO”=1, the “status information” of the content output device is “tuner”, which indicates that the “tuner” is currently outputting to display unit 103 and speaker unit 104 . The condition combination of "NO"=1 is that when the recognition command received by the command generation unit 11 is "net" and the user identification information, which is the first auxiliary information, is "adult", the command generation unit 11 This is an example of generating an execution command for outputting to the display unit 103 and the speaker unit 104 from "net" which is one of the content output devices. Since "NO"=2 and 3 are the same, the explanation is omitted.

If “NO”=4, the “status information” of the content output device is “tuner”, which indicates that the “tuner” is currently outputting to display unit 103 and speaker unit 104 . The condition combination of "NO"=4 is that the recognition command received by the command generator 11 is "net", the user identification information as the first auxiliary information is "child", and the second auxiliary information is In this example, the command generation unit 11 does not generate or transmit an execution command in order not to output to the display unit 103 and the speaker unit 104 from the "net", which is one of the content output devices, when the time is "noon". . The case of “NO”=4 can be used, for example, when children want to avoid viewing digital content from the “net” on the receiving device 10 during daytime hours.

If “NO”=9, the “status information” of the content output device is “recorder”, which indicates that “recorder” is currently outputting to display unit 103 and speaker unit 104 . The condition combination of "NO"=9 is that the recognition command received by the command generator 11 is "net", the user identification information as the first auxiliary information is "child", and the second auxiliary information is When the time is "night", the command generator 11 generates two execution commands, "net" and "education", which is an execution command for the program type. The two generated execution commands are transmitted from the command transmission unit 18 to the control unit 90, and output to the display unit 103 and the speaker unit 104 a program related to "education" distributed by "net". The case of "NO" = 9 is, for example, a case where, when a child tries to watch "net" on the receiving device 10 at nighttime, it is desired to view digital content whose program type is "educational". can be used for

Further, for example, while the user is watching BS, that is, when the state information of the control target part "tuner" is "BS", the user utters "BS" as a voice command, and the command recognition unit 13 , “BS” is generated as a recognition command and output to the command generation unit 11 . When the recognition command is input, the command generation unit 11 generates and transmits an execution command "digital terrestrial" to switch to the state value ("digital terrestrial") set to "home" of the part to be controlled "tuner". do. The control unit 90 receives the execution command "digital terrestrial" and switches the tuner to "digital terrestrial". At this time, the channel (program) to be output to the display unit 103 and the speaker 104 may be selected from the "home" state value set for the "channel (program)" which is the control target portion. That is, in the case of this example, the command generation unit 11 generates a plurality of "tuner" and "channel (program)" for a voice command (or a recognition command that recognizes the voice command) issued by the user for one control target part. Generates an execution command for the control target part of The "home" set for the "channel (program)" may be, for example, the channel that was viewed immediately before the power of the television device was turned off last time, or the channel preset by the user. Also, the execution commands for different target control parts may not be divided into one execution command.

As described above, the user can set a combination condition list as in the present embodiment to generate, transmit, and execute a plurality of execution commands from one voice command.

(Fourth embodiment)
This embodiment shows an example of a system in which the command control section 1 is used as an independent device.

FIG. 10 is a diagram showing a configuration example of the entire system according to the third embodiment.
A command control device 2 and IoT devices 600A and 600B are connected to a network 500 . The IoT devices 600A and 600B have similar functions and are referred to as the IoT device 600 unless otherwise distinguished. Although only two IoT devices 600 are shown in FIG. 10, there may be many.

The command control device 2 is constructed in a computer having, for example, a CPU and a memory. The command control device 2 may be a personal computer, or may be a cloud service including a server, database, and the like. The command control device 2 includes a command recognition section 1 and a communication section 102A. Command recognition unit 1 and communication unit 102A correspond to the functions of command recognition unit 1 and communication unit 102 in FIG. 3, respectively.

The IoT device 600 is any kind of IoT equipment that is connected to the network 100 and performs data communication with devices on the network 100 . The IoT device 600 may be, for example, sensors such as a temperature detection sensor, a water leak detection sensor, a door opening/closing sensor, or a detection device using these sensors. Also, the IoT device 600 may be a home appliance such as an air conditioner, a television device, lighting, or a camera. Also, a mobile terminal such as a smartphone may be used as long as it is connected to the network 100 . The IoT device 600 in this embodiment provides auxiliary information and status information to the command control device 2, receives the execution command output by the command control device 2, and functions of the IoT device 600 according to the received execution command. to control.

Specifically, the IoT device 600 includes an auxiliary information output unit 21A, a state switching unit 22A, a control unit 90A, an auxiliary information management unit 91A, a state information management unit 92A, a communication unit 102A, and an interface unit 105A. Each function corresponds to the functions of the auxiliary information output unit 21, the state switching unit 82, the control unit 90, the auxiliary information management unit 91, the state information management unit 92, the communication unit 102, and the interface unit 105 in FIG.

That is, it can be said that each function in FIG. 2 is allocated to the command control device 2 and the IoT device 600A. A major difference between the receiving device 10 shown in the first embodiment and the IoT device 600 shown in the present embodiment is that the receiving device 10 has a command control unit 1 inside, but the IoT device 600 has The reason is that the command control unit 1 is not provided. In this embodiment, the command control unit 1 is provided in the command control device 2 , and the IoT device 600 receives execution commands from the command control device 2 via the network 500 .

The control target part of the IoT device 600 that can be controlled by the command control device 2 may be, for example, the power supply (ON-OFF) shown in the first to third embodiments, or control the start and stop of the functional parts. You can also

The flow chart of FIG. 6 can be used for the procedure for the command control device 2 to send the execution command to the IoT device 600 . A detailed description of procedures similar to those of the first and second embodiments will be omitted.

The user is near the command control device 2 and remotely controls the IoT device 600A via the network 500. FIG. The user sets execution command generation conditions (combination condition list) for the IoT device 600A in the command control unit 1 of the command control device 2 .

Assume that the user issues a voice command to the voice detection unit 12 of the command control device 2 in order to control the function of the IoT device 600A. The voice detection unit 12 detects voice, the voice analysis unit 121 performs voice analysis processing, the command recognition unit 13 generates a recognition command, and outputs the recognition command to the command generation unit 11 (YES in step S11, S12 , YES in S13, S14).

When a recognition command is input from the command recognizing unit 13, the command generating unit 11 refers to the combination condition list, and acquires the column items of the list, ie, “auxiliary information” and “state information”, respectively. And the state information acquisition unit 17 is commanded. The auxiliary information acquisition unit 16 requests various items of auxiliary information in the combination condition list from the auxiliary information management unit 91A, acquires them, and outputs them to the command generation unit 11 (step S15). Step S15 in this embodiment will be described in detail.

The auxiliary information acquisition unit 16 requests auxiliary information from the IoT device 600A via the communication unit 102A. In the IoT device 600A, the control unit 90A receives the request for auxiliary information via the communication unit 102A2. The control unit 90A acquires auxiliary information from the auxiliary information management unit 91A and transmits the acquired auxiliary information to the command control device 2 via the communication unit 102A2.

The state information acquisition unit 17 recognizes the controlled object from the recognition command, and requests the state information of the controlled object from the IoT device 600A via the communication unit 102A. In the IoT device 600A, the control unit 90A receives the state information request via the communication unit 102A2. The control unit 90A acquires the state information from the state information management unit 92A and transmits the acquired state information to the command control device 2 via the communication unit 102A2. In the command control device 2, the command generator 11 receives the status information via the communication section 102A2 (step S16).

The command generation unit 11 refers to the combination condition list, and if there is a command in the item of "execution command" of the condition in which the combination of the acquired auxiliary information, the status information, and the recognition command matches, the "execution command ” is generated as an execution command, and output to the command transmission unit 18 (steps S17, YES in S18, S19).
On the other hand, if the item of "execution command" is "no transmission", the command control unit 1 does not generate an execution command and waits until the next voice is detected (NO in steps S17 and S18). ). In this case, the command control unit 1 displays a message such as "no command sent" on the display unit (not shown) of the command control device 2, which means "an execution command was not sent or was not generated." The user may be notified of the message by displaying it or by outputting a voice including the message content from a speaker unit (not shown) of the command control device 2 .

The command transmission unit 18 transmits the input execution command to the IoT device 600A via the communication unit 102A (step S101). The IoT device 600A controls the control function according to the received execution command. When the command control unit 1 generates or transmits an execution command, the command control unit 1 causes a display unit (not shown) of the command control unit 2 to display a message containing the meaning of "execution command has been transmitted." The message may be notified to the user by, for example, outputting a voice including the content of the message from a speaker unit (not shown) of the device 2 . Further, when the recognition command and the generated execution command are different, the command control device 2 displays a message including the content "the execution command is different from the recognition command" on the display section (not shown) of the command control device 2. The user may be notified of the message by displaying it or by outputting a voice including the message content from a speaker unit (not shown) of the command control device 2 . By doing so, the user can confirm whether or not the intention of the voice command issued by the user is correctly executed.

According to the above procedure, when the user issues a voice command to the command control device 2 connected to the network 500, the IoT device 600 connected to the network 500 can be controlled by the execution command.

According to at least one embodiment described above, it is possible to provide a command generation device, generation method, and generation program that support speech recognition for voice commands.

In the above embodiment, an example is shown in which the functions of the control unit 90 (including the auxiliary information management unit 91 and the state information management unit 92) are installed on the receiving device 10 and the IoT device 600, which are devices to be controlled. , all or part of the functions of the control unit 90 may be provided as an external control device to be controlled. In this case, the control device is also connected to network 500 . Similarly, for the command control device, various configurations and combinations of functions within the device and hardware for executing the functions are conceivable, and are not limited to the examples of the embodiments shown above.
(Modification)
In this modified example, for example, by using the "user identification information" and "time zone" in FIG. Give an example. It is assumed that an adult is in charge of the remote control for operating the television set.

Specifically, when a child issues a voice command, the voice analysis unit 121 performs voiceprint analysis, the auxiliary information acquisition unit 16 acquires “child” as the user identification information, and the input to the command generation unit 11 is “child”. do. Assume that the voice command is input to the command recognition unit 13 at the same time, a recognition command is generated, and the recognition command is input to the command generation unit 11 . The command generation unit 11 generates, for example, “power OFF” as an execution command based on the recognition command “power OFF” and the auxiliary information “child”, and outputs it to the control unit 90 . On the other hand, it is assumed that the command generation unit 11 acquires “children” as the user identification information from the auxiliary information acquisition unit 16 and acquires “midnight” as the time period. In this case, the command generation unit 11 may generate, for example, an "execution command for maintaining the current state" from only the auxiliary information "children" and "midnight".

Although not shown in FIG. 5, parental control is possible by also using "program viewing target" as auxiliary information. For example, it is assumed that the command recognition unit 13 recognizes that the control target part is the "channel (program)" from the voice command uttered by the child. When the command recognition unit 13 outputs the recognition information including the recognized control target part to the auxiliary information acquisition unit 16, the auxiliary information acquisition unit 16 acquires the auxiliary information for the control target part "channel (program)" included in the recognition information. is acquired from the broadcast signal reception processing unit 20 or the like, and is output to the command generation unit 11 . The command generation unit 11 generates an execution command based on the two pieces of auxiliary information “children” and “program viewing target” which are the user identification information obtained from the voice analysis unit 121 . For example, if the program viewing target includes "child", the recognition command is directly generated as the execution command. Also, if the program viewing targets do not include "children", for example, an "execution command for maintaining the current state" is generated.

As described above, according to this modified example, parental control for voice commands is possible. Further, according to this modification, it is possible to generate an execution command from only the auxiliary information acquired based on the voice command without using the recognition command, out of the recognition command, the state information, and the auxiliary information.

According to at least one of the embodiments and modifications described above, it is possible to provide a command control device, a control method, and a control program that support speech recognition for voice commands.

The apparatus described above can also be described as follows.
(A-1)
Operation control information (recognition command) is acquired from an input voice (voice command), and the operation state of the device to be controlled (receiving device 10) is set to either the first mode or the second mode different from the first mode. An electronic device (command control unit 1 or command control device 2) comprising operation control means (command generation unit 11) for setting the operating state,
The operating state of the controlled device is the first mode, and
When the operation control information relates to the operation state in the first mode, the electronic device sets the operation state to the second mode.
(A-2)
The electronic device according to (A-1), which acquires operation state information (state information) regarding a state of a control target portion of the control target device.
(A-3)
The electronic device according to (A-1) or (A-2), which acquires control condition information (auxiliary information) different from the operation control information and the operation state information.
(A-4)
The control condition information is set based on at least one of a group of time zones, user identification information, user attributes, received content information, broadcasters, distributors, and recorded content managers (A- 3) The electronic device described in 3).
(A-5)
Operation control information (recognition command) is acquired from an input voice (voice command), and the operation state of the device to be controlled (receiving device 10) is set to either the first mode or the second mode different from the first mode. A program for causing a computer to enter the operating state,
The operating state of the controlled device is the first mode, and
The above program, wherein when the operation control information relates to the operation state in the first mode, the operation state is set to the second mode.

While several embodiments of the invention have been described, these embodiments have been presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and equivalents thereof. Furthermore, in each constituent element of the claims, even if the constituent element is divided and expressed, a plurality of constituent elements are expressed together, or a combination of these is expressed, it is within the scope of the present invention. Moreover, a plurality of embodiments may be combined, and examples configured by such combinations are also within the scope of the invention.

Also, in order to make the description clearer, the drawings may schematically show the width, thickness, shape, etc. of each part compared to the actual mode. In the block diagram, data and signals may be exchanged between unconnected blocks, or between connected blocks in directions not indicated by arrows. Each function shown in the block diagram and the processing shown in the flowcharts and sequence charts may be realized by hardware (such as an IC chip), software (such as a program), or a combination of hardware and software. In addition, when the claims are expressed as control logic, when expressed as a program including instructions for executing a computer, and when expressed as a computer-readable recording medium in which the instructions are written, the apparatus of the present invention is applied. be. Also, the names and terms used are not limited, and other expressions are included in the present invention as long as they have substantially the same content and the same meaning.

DESCRIPTION OF SYMBOLS 1... Command control part 2... Command control apparatus 10... Receiving apparatus 11... Command generation part 12... Voice detection part 13... Command recognition part 14... User interface part 15... Interface part 16... Auxiliary information Acquisition unit 17 Status information acquisition unit 18 Command transmission unit 19 Control unit 20 Broadcast signal reception processing unit 21 Auxiliary information output unit 30 Contents processing unit 31 Auxiliary information output unit 40 Recording/playback unit 41 Auxiliary information output unit 50 Equipment data generation unit 51 Auxiliary information output unit 60 Output control unit 62 State switching unit 70 Sensor unit 71 Auxiliary information output unit 80 Main power supply unit 82 State switching unit 90 Control unit 91 Auxiliary information management unit 92 State information management unit 93 Time management unit 100 Remote control 101 Antenna 102 Communication unit DESCRIPTION OF SYMBOLS 103... Display part 104... Speaker part 105... Interface part 111... Storage part 121... Voice analysis part 200... Contents server apparatus 300... Viewing analysis apparatus 400... Voice recognition apparatus 500... Network.

Claims (8)

In a command control device that generates an execution command including a control instruction for a controlled object based on an input voice,
execution command generating means for generating an execution command including either a first control command included in a recognition command obtained by recognizing the voice or a second control command different from the first control command; ,
a speech recognition unit for recognizing the speech to obtain the recognition command;
additional information obtaining means for obtaining additional information;
storage means for storing a correspondence relationship between the recognition command, the additional information, and the execution command;
The command control device, wherein the execution command generation means generates the execution command based on the recognition command, the additional information, and the correspondence relationship. 2. The command control device according to claim 1 , wherein whether or not to generate said execution command is determined based on said recognition command and said additional information. 2. The command control device according to claim 1 , wherein whether or not to transmit said execution command is determined based on said recognition command and said additional information. 4. The command control device according to any one of claims 1 to 3 , wherein said additional information includes state information indicating a control state of said controlled object controlled by said execution command. 4. The command control device according to any one of claims 1 to 3 , wherein the additional information includes auxiliary information that is not the control state of the controlled object. 4. The additional information according to any one of claims 1 to 3 , wherein the additional information includes state information that is the control state of the controlled object controlled by the execution command, and auxiliary information that is not the control state of the controlled object. Command controller. In a command control method for generating an execution command including a control command for a device to be controlled based on an input voice,
generating an execution command including either a first control command included in the recognition command obtained by recognizing the voice or a second control command different from the first control command;
recognizing the speech to obtain the recognition command;
get additional information
storing a correspondence relationship between the recognition command, the additional information, and the execution command;
A command control method , wherein the execution command is generated based on the recognition command, the additional information, and the correspondence relationship . In a control program that is executed by a computer and generates an execution command including a control instruction for a device to be controlled based on an input voice,
a step of generating an execution command including either a first control command included in the recognition command obtained by recognizing the voice or a second control command different from the first control command;
recognizing the speech to obtain the recognized command;
a procedure for obtaining additional information; and
a procedure for storing the correspondence between the recognition command, the additional information, and the execution command;
a procedure for generating the execution command based on the recognition command, the additional information, and the correspondence relationship;
A control program comprising

Images