WO2021109839A1 - 指令控制装置、控制方法及非易失性存储介质 - Google Patents

指令控制装置、控制方法及非易失性存储介质 Download PDF

Info

Publication number
WO2021109839A1
WO2021109839A1 PCT/CN2020/128811 CN2020128811W WO2021109839A1 WO 2021109839 A1 WO2021109839 A1 WO 2021109839A1 CN 2020128811 W CN2020128811 W CN 2020128811W WO 2021109839 A1 WO2021109839 A1 WO 2021109839A1
Authority
WO
WIPO (PCT)
Prior art keywords
command
unit
control
recognition
voice
Prior art date
Application number
PCT/CN2020/128811
Other languages
English (en)
French (fr)
Inventor
浜田知
高橋大
Original Assignee
海信视像科技股份有限公司
东芝视频解决方案株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 海信视像科技股份有限公司, 东芝视频解决方案株式会社 filed Critical 海信视像科技股份有限公司
Priority to CN202080005756.9A priority Critical patent/CN113228166B/zh
Publication of WO2021109839A1 publication Critical patent/WO2021109839A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems

Definitions

  • the embodiments of the present application relate to a command control device, a control method, and a non-volatile storage medium.
  • the sound control technology can be used to replace the remote control of the TV.
  • the sound superimposed with the instruction hereinafter referred to as the voice command
  • receives sound waves from a microphone attached to the TV And take out the instruction as data through voice recognition.
  • the fetched command data becomes the command executed in the TV.
  • the voice commands issued by the user may be recognized as erroneous commands through voice recognition, and the performance of voice recognition is being studied.
  • Patent Document 1 Japanese Patent Application Publication No. 2017-167247
  • voice recognition may not work well, and the range in which voice control technology can be applied is limited.
  • voice control technology that operates in normal times may operate abnormally due to increased noise in an emergency such as an earthquake.
  • the problem to be solved by this application is to provide a command control device, a control method, and a non-volatile storage medium that assist voice recognition of voice commands.
  • a command control device generates an execution command including a control command for a control target device based on an input sound, wherein the command control device generates an execution command including a first control command and the first control An execution command including any one of second control commands with different commands, and the first control command is a first control command included in a recognition command obtained by performing voice recognition on the voice.
  • FIG. 1 is a diagram showing a configuration example of the entire system of the first embodiment
  • FIG. 2 is a block diagram showing an example of the functional structure of the receiving device of this embodiment
  • FIG. 3 is a block diagram showing an example of the functional structure of the command control unit of the embodiment.
  • FIG. 4 is a diagram showing an example of a control target part that can be controlled by a voice command and a state of the control target part in this embodiment
  • FIG. 5 is a diagram showing an example of auxiliary information that can be used in this embodiment.
  • 6 is a flowchart showing an example of processing operations for the command control unit to receive voice commands and send execution commands in this embodiment
  • FIG. 7 is a diagram showing an example of execution command generation conditions set in the command control unit in order to control the main power supply in this embodiment
  • FIG. 8 is a diagram showing an example of execution command generation conditions set in the command control unit in order to control the volume in the second embodiment
  • FIG. 9 is a diagram showing an example of execution command generation conditions set in the command control unit in order to control the reception of digital content in the third embodiment
  • Fig. 10 is a diagram showing a configuration example of the entire system of the fourth embodiment.
  • auxiliary information output unit 80...main power supply unit, 82...state switching unit, 90...control unit, 91...auxiliary information management unit, 92...status information management unit, 93...time management unit, 100...remote control unit, 101...antenna, 102...communication unit , 103...display unit, 104...speaker unit, 105...interface unit, 111...storage unit, 121...sound analysis unit, 200...content server device, 300...viewing analysis device, 400...sound recognition device, 500...network.
  • FIG. 1 is a diagram showing a configuration example of the entire system of the embodiment.
  • the receiving device 10 is a device for watching digital content.
  • it is a television receiving device (also called a television device, a television receiver, a broadcaster) that can receive and watch digital broadcasts such as 2K or 4K/8K terrestrial broadcasts and satellite broadcasts.
  • Signal receiving device includes, for example, 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 (may be a cloud server) connected to the network 500.
  • the receiving device 10 may also have a recording and playing function, and the digital content recorded in the receiving device 10 can be watched by using the recording and playing function.
  • the receiving device 10 by connecting a recording and playback device not shown to the receiving device 10, it is possible to view the digital content recorded by the recording and playback device not shown.
  • one receiving device 10 is shown, but a plurality of receiving devices 10 may be further connected.
  • the receiving device 10 is a device capable of receiving digital content, all of them need not have the same function.
  • it may be a recorder capable of recording only (Recorder) that does not have a monitor capable of viewing, a set top box (Set Top Box: STB) capable of receiving broadcast signals, and the like.
  • the television device, video recorder, STB, etc. are collectively referred to as the receiving device 10.
  • the television device may be replaced with a receiver 10 such as a video recorder or an STB.
  • the receiving device 10 may also be a mobile device such as a personal computer and a smart phone.
  • the receiving device 10 of this embodiment is capable of voice-based control using voice recognition.
  • the command control unit 1 performs voice recognition on, for example, a voice command uttered by a user, and uses commands obtained by voice recognition (hereinafter referred to as recognition commands) to control various functions in the receiving device 10.
  • the remote controller 100 is a remote controller for remotely controlling the receiving device 10.
  • the receiving device 10 can collect and store the viewing history of the digital content viewed by the receiving device 10 (hereinafter referred to as viewing data). In addition, it is possible to store unique data (hereinafter referred to as device individual data) in the receiving device 10. Including viewing data and device individual data is called viewing device data.
  • the receiving device 10 can output saved data such as viewing device data to the viewing analysis device 300 connected to the network 500, and can receive the analysis result of the viewing device data performed by the viewing analysis device 300.
  • the “viewing” in the present embodiment includes a state in which digital content is received in a state where the user is not actually watching, or a state in which it has been received, or a state in which it has been recorded. Therefore, the “viewing history” in this embodiment includes, for example, the “reception history” that the receiving device such as STB only receives but whether or not viewing; when the receiving device is a video recorder, it is received by the receiving device and reserved for recording, or The recorded “recording history", etc.
  • the “viewing time” in this embodiment includes, for example, the time when a receiving device such as an STB receives the digital content; when the receiving device is a video recorder, the time when the digital content is recorded, and the like.
  • the viewing device data also includes the reception log data, download history data, and recording data generated by the receiving device such as the recorder and STB.
  • the device individual 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 like the fixed number of the receiving device 10 in some cases.
  • the device-specific data includes, for example, the IP address of the receiving device 10, an identification number, and demographic data (hereinafter, referred to as demographic data) registered in advance by the owner or the like.
  • the so-called demographics are data that categorize users who watch the receiving device 10, such as information such as the age, gender, family composition, and residential area of the user.
  • the identification number is a number, character string, etc., for identifying different receiving devices 10, and is composed of, for example, a combination of numbers and letters.
  • 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 communication operator, and other service operators of digital content called Over The Top (OTT).
  • CSP content service provider
  • OTT Over The Top
  • the content server device 200 also includes a server that provides services such as Video On Demand (Video On Demand).
  • the viewing analysis device 300 is a device that exists on the network or on the cloud, collects and stores the viewing device data stored by the receiving device 10, and then analyzes the stored data for various viewing analysis, and requests for example The analyzed receiving device 10 outputs the analysis result.
  • the viewing analysis device 300 is built in, for example, a computer having a CPU, a memory, and the like.
  • the viewing and analyzing device 300 may be a personal computer, or a cloud service performed by a server, a database, or the like.
  • the viewing analysis device 300 may be able to identify each receiving device 10 based on an identification number individually possessed by the receiving device 10 to perform viewing analysis of the individual receiving device 10.
  • the voice recognition device 400 is installed on the network 500.
  • the voice recognition device 400 is built in, for example, a computer having a CPU, a memory, and the like.
  • the voice recognition device 400 may be a personal computer or a cloud server.
  • the voice recognition device 400 receives digital data (hereinafter referred to as voice data) of voice waveforms corresponding to the user’s voice received by a microphone or the like via the network 500, estimates or recognizes the user’s command, and then combines the recognized command (recognition Command) is output as text data.
  • the commands issued by the user to the control target may also be tabulated as text data in advance, and the text data obtained from the received voice data may be compared with the text data in the list, and the highest in the list may be selected.
  • the close command outputs the text data of the selected command.
  • the method of voice recognition in the voice recognition device 400 is not limited to this method.
  • the voice recognition device 400 may also be composed of a speech to text (Speech To Text) server (hereinafter referred to as STT server) and a remote control recognition server, where the language converted to a text server generates text (textualization) of voice data. , Verbalization, etc.), the remote control recognition server generates the command closest to the generated voice text from the list of commands as the recognition command.
  • the remote control recognition server may refer to a command table registered in a storage unit (not shown) in advance, and output a command that matches the sound text generated by the STT server or the closest command in the table as the recognition command.
  • the network 500 is a network to which the receiving device 10, the content server device 200, the viewing analysis device 300, and the voice recognition device 400 are connected so that the respective devices can communicate, for example, the Internet.
  • the network 500 is not limited to the Internet, and if each device can communicate, it may also be a network including a plurality of different networks.
  • 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 that performs receiving processing on a signal superimposed with digital content to obtain and watch the digital content.
  • the broadcast signal reception processing unit 20 processes the digital broadcast and other broadcast signals received from the antenna 101 in accordance with the digital broadcast specifications, and acquires and outputs content data such as video, sound, and text.
  • the specifications of digital broadcasting can be, for example, the MPEG2TS method used in 2K digital broadcasting, the MPEG Media Tranport method (MMT method) used in 4K/8K digital broadcasting, etc., or multiple tuners can be used to correspond to both parties. .
  • MMT method MPEG Media Tranport method
  • multiple tuners can be used to correspond to both parties.
  • processing in accordance with the specifications of digital broadcasting it includes demultiplexing processing that separates the digital data stream into content data such as video, sound, text, etc., error correction code decoding processing, and encryption to decode encrypted data.
  • the auxiliary information output unit 21 extracts the information requested by the control unit 90 from the broadcast signal, and outputs it to the control unit 90.
  • the auxiliary information output unit 21 extracts the requested information from the control information, program-related information, etc. included in the broadcast signal, and outputs it to the control unit 90.
  • the information output to the control unit 90 is processed as needed, and is used in the command control unit 1 as auxiliary information.
  • the content processing unit 30 performs decoding processing on the digital data input from the communication unit 102 to the encoding processing performed by the content server device 200, and outputs content data such as video, sound, and text. Specifically, as the decoding process, the content processing unit 30 performs, for example, demultiplexing processing (separation processing), error correction code decoding processing, and decoding processing for encoded content data (video, text, sound, etc.).
  • the auxiliary information output unit 31 extracts the information requested by the control unit 90 from the data output by the content server device 200 and outputs it to the control unit 90.
  • the auxiliary information output unit 31 extracts related attribute information such as the distribution company of the content program from the control information output by the content server device 200 and the like, and outputs it to the control unit 90.
  • the information output to the control unit 90 is processed as necessary, and is used in the command control unit 1 as auxiliary information.
  • the recording and playback unit 40 is, for example, a disc player (Disc player), HDD recorder, etc., and stores content data output from the broadcast signal reception processing unit 20 and the content processing unit 30, and sends the stored content data to the output control according to the playback request.
  • the output from the unit 60 is output from the display unit 103 and the speaker unit 104 as video, text, and sound.
  • the user watches the video, text, and sound output from the display unit 103 and the speaker unit 104 to watch the digital content stored in the recording and playback unit 40 and the like.
  • the recording and playback unit 40 is provided as one function of the receiving device 10, but it may be an external device via the interface unit 105, for example.
  • the recording and playback unit 40 may also be provided so as to be able to watch the broadcast signal that has been received by the broadcast signal reception processing unit 20.
  • the content A is recorded by the recording and playback unit 40 while the content B that has been received by the other broadcast signal reception processing unit 20 is recorded.
  • the device data generating unit 50 collects data from each functional unit of the receiving device 10 (especially the broadcast signal receiving processing unit 20, the content processing unit 30, and the recording and playing unit 40), and generates viewing device data.
  • Viewing device data includes device individual data and viewing data.
  • the device-individual data is data unique to the receiving device 10, and for example, when the receiving device 10 is installed, it may be set in the receiving device 10 from the remote controller 100 or the like by the user.
  • the identification number used in the viewing analysis may be assigned in advance at the time of purchase of the receiving device 10, for example, and set in the device individual data or the like.
  • the viewing data is, for example, a viewing history, and it can also be successively generated by the receiving device 10 when certain viewings have been performed. Specifically, for example, in accordance with the time when the broadcast signal reception processing unit 20, the content processing unit 30, and the recording and playback unit 40 are activated, in each functional unit, the channel and the program name (or the The standard program id), the date when the program was watched, and the like are stored, and each function unit outputs the stored data to the device data generating unit 50 as viewing data in accordance with the time when each functional unit is stopped.
  • the device data generating unit 50 processes the viewing data as needed, and stores it in a storage unit (not shown) of the receiving device 10.
  • each functional unit especially the broadcast signal reception processing unit 20, the content processing unit 30, and the recording and playback unit 40
  • each functional unit separately stores the viewing data, and when there is a request to send the viewing data from an external device, each functional unit The viewing data is output to the device data generating unit 50, and the device data generating unit 50 processes the viewing data as necessary, and outputs it to an external device as the viewing device data.
  • the device data generation unit 50 outputs the generated viewing device data to the communication unit 102 in response to a request from an external device (especially the viewing analysis device 300).
  • the viewing device data is transmitted from the communication unit 102 via the network 500 to the viewing analysis device 300 that has made the request.
  • the viewing device data may be transmitted to the viewing analysis device 300 at any time.
  • the auxiliary information output unit 51 receives the viewing device data generated by the device data generating unit 50, the viewing data collected from the functional units of the receiving device 10, and the various analysis result data output by the viewing analysis device 300, and outputs to the control unit 90.
  • the information output to the control unit 90 is processed as necessary, and is used in 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 and playback unit 40, and outputs it to the display unit 103 and the speaker unit 104.
  • the state switching section 62 switches the current display state of the display section 103 (on state or off state, displaying state or undisplayed state, etc.) and the current output state of the speaker section 104 (on state or off state, etc.) in accordance with the control from the control section 90. State or off state, sound output state or sound is being set to mute state, etc.).
  • 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 in accordance with control commands from the remote controller 100 and the command control unit 1.
  • the sensor unit 70 is, for example, a camera installed on the front of the television.
  • the camera can photograph the front of the television device, and use image recognition or the like to estimate, for example, a user in front of the television device from the captured image.
  • 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 is used in the command control unit 1 as auxiliary information.
  • the main power supply unit 80 is the power supply for the main function of the receiving device 10. For example, it outputs digital content to the display unit 103 and the speaker unit 104 of the television device, or stops the output (this operation is referred to as the on-off of the television device). Power supply used during 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 device, in accordance with the control from the control unit 90.
  • the control unit 90 manages the current state of the main power supply unit 80, and the control unit 90 controls the state switching unit 82 in accordance with control commands from the remote controller 100 and the command control unit 1.
  • the control unit 90 controls various functions of the receiving device 10. Specifically, the control unit 90 receives various control signals from the interface unit 105 and controls various functions of the receiving device 10. For example, when the user specifies from the remote control 100 whether to watch the content based on the broadcast signal or the content from the content server device 200, the control unit 90 receives the control signal from the remote control via the interface unit 105 and controls the receiving device 10. The function enables it to perform user-specified actions. In addition, it is also possible that in FIG. 2, functional modules that are not specifically connected to the control unit 90 also exchange data.
  • control unit 90 in this embodiment receives an execution command from the command control unit 1 via the interface unit 105, and implements control of each function in the receiving device 10 in accordance with the execution command.
  • the auxiliary information management unit 91 receives auxiliary information output by the 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 functional unit , And store it in a storage unit not shown.
  • the auxiliary information management unit 91 transmits the stored auxiliary information of each functional unit from the interface 105 to the command control unit 1.
  • auxiliary information management unit 91 can also be configured that, for the information stored in the auxiliary information management unit 91, predetermined items are set in the auxiliary information output unit in each functional unit, and the auxiliary information is output when the auxiliary information is updated in each functional unit.
  • the section is automatically output to the auxiliary information management section 91.
  • the auxiliary information management unit 91 requests the auxiliary information output unit of each function for auxiliary information as necessary.
  • the status information management unit 92 stores the status information of the status switching units (the status switching unit 62, the status switching unit 82, etc.) in each functional unit in a storage unit not shown.
  • the status information management unit 92 transmits the stored status information of each function to the command control unit 1 via the interface 105.
  • the control unit 90 always keeps the state information of the state information management unit 92 in the latest state in order to control the state of each functional unit.
  • the information stored in the status information management unit 92 can also be set as the time when a predetermined item is set in the status information output unit (not shown) in each function unit, and the status information is updated in each function unit.
  • the status information output unit automatically outputs to the status information management unit 92.
  • the status information management unit 92 requests status information from the status information output units of each functional unit as needed.
  • the time management unit 93 manages the time of the receiving device 10.
  • the receiving device 10 may have a clock inside, or it may be obtained by extracting the time from a broadcast signal or the like.
  • the communication unit 102 performs data transmission and reception processing with various devices connected to the network 500 in accordance with predetermined communication protocols such as TCP/IP and UDP/IP.
  • the display unit 103 is, for example, a monitor that displays videos 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 sound.
  • the user watches the video, text, and sound output by the display unit 103 and the speaker unit 104 to view the digital content provided by the broadcast signal, the content server device 200, and other recording and playback units 40.
  • the interface unit 105 is an interface for controlling the receiving device 10 from the outside such as the remote control 100. For example, it receives a control signal from the remote control 100, a switch (not shown) attached to the receiving device 10, and the like, and sends the control signal to the receiving device 10.
  • the control unit 90 outputs.
  • the remote controller 100 it may have an interface which receives a control signal from a terminal, such as a smart phone which is not shown in figure.
  • the interface unit 105 may have an interface for connecting with an external device.
  • it may be an interface for connecting the receiving device 10 to an external HDD recorder (not shown).
  • the user can use the display unit 103 and the speaker unit 104 to view digital content output from an external HDD video recorder (not shown).
  • the interface 105 in this embodiment has an interface capable of communicating with the interface unit 15 of the command control unit 1.
  • the interface may be various serial buses.
  • the interface 105 receives the 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 the functional configuration of the command control unit of the embodiment.
  • the command generation unit 11 generates and executes the command based on the recognition command generated by the command recognition unit 13 through voice recognition, and the additional information (auxiliary information and status information) obtained by the auxiliary information acquisition unit 16 and the status acquisition unit 17
  • the command is output from the command transmission unit 18 to the outside of the command control unit 1.
  • the command generation unit 11 stores a combination of identification commands, additional information, and execution commands (hereinafter referred to as a condition combination table) in the storage unit 111.
  • the condition combination list (list) can be preset by the user.
  • the condition combination table may be incorporated in the computer program of the command generation unit 11, or it may be downloaded from an external server via the network 500, for example.
  • the command generation unit 11 refers to the condition combination table to generate and output an execution command.
  • the sound detection unit 12 is, for example, a microphone, and receives the sound uttered by the user, acquires sound data of the received sound waveform through sampling or the like, and outputs it.
  • the command recognition unit 13 performs voice recognition based on the voice data output by the voice detection unit 12, estimates or recognizes the command issued by the user, and outputs the recognition command as text data.
  • the command recognition unit 13 may include a voice data processing unit (voice recognition engine) that performs voice recognition inside, but it may also send the voice data to the voice recognition device 400 on the network 500 equipped with a voice recognition engine (engine) to obtain Identify instructions.
  • voice recognition engine voice recognition engine
  • the voice recognition device 400 obtains voice data from a plurality of receiving devices 10 and performs voice recognition, so that the voice recognition device 400 also has the advantage of achieving a learning effect and being able to improve the performance of voice recognition.
  • the voice recognition device 400 is used via the network 500, it has the disadvantage that the processing delay of voice recognition is large.
  • the voice recognition engine in the command recognition unit 13 when used, it has a voice
  • the processing delay of recognition has the advantage of being small.
  • FIG. 3 an example in which the sound detection unit 12 (speaker) is built-in is shown, but a smart speaker or the like may also be used.
  • a smart speaker equipped with a voice recognition engine may generate a recognition command
  • the command control unit 1 or command generation unit 11
  • the acquired recognition instruction may also be used in the instruction generation unit 11 to generate an execution instruction.
  • the user interface unit 14 is, for example, an interface capable of character input such as a keyboard of a personal computer. Specifically, the user sets the condition combination table in the storage unit 111 from the user interface unit 14. In addition, the condition combination table may be set in the storage unit 111 using the remote controller 100, a smart phone, or the like. In addition, the command generation unit 11 may download the condition combination table to the storage unit 111 from a server that provides a condition combination table (not shown) provided outside the receiving device 10.
  • the interface unit 15 and the interface unit 105 perform various data communications. Specifically, the interface unit 15 receives auxiliary information and status information from the interface unit 105. In addition, 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.
  • the auxiliary information acquisition unit 16 may output an acquisition request for auxiliary information to the auxiliary information management unit 91 and acquire the auxiliary information from the auxiliary information management unit 91, for example, based on the time when the recognition command is output from the command recognition unit 13.
  • the status acquisition unit 17 acquires status information from the status information management unit 92 via the interface unit 15. For example, according to the time when the command recognition unit 13 outputs the recognition command or the time when the command generation unit 11 receives the recognition command, the status information acquisition unit 17 outputs a status information acquisition request to the status information management unit 92, and then obtains the status information from the status information management unit. 92 Get status information.
  • 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. In addition, it can also be transmitted to devices and equipment on the network 500 via the communication unit 102.
  • the control unit 19 controls each functional module in the command control unit 1. In addition, it may also be configured such that in FIG. 3, data interaction (control) is also performed between functional modules that are not specifically connected to the control unit 19.
  • the sound analysis unit 121 performs, for example, frequency analysis (voice ripple analysis) on the sound data output from the sound detection unit 12 to estimate the attributes of the sound source such as adults and children, age, and gender to obtain a sound source estimation result.
  • the sound analysis unit 121 performs necessary processing on the sound source estimation result and outputs it to the auxiliary information acquisition unit 16 as auxiliary information.
  • the sound source estimation result obtained by the sound analysis unit 121 can also be used for whether to activate the command generation unit 11, the command recognition unit 13, the command transmission unit 18, and the like.
  • the sound analysis unit 121 outputs the sound source estimation result to the control unit 19, the control unit 19
  • the control unit 19 The functions of the command generation unit 11, the command recognition unit 13, and the command transmission unit 18 are enabled or disabled.
  • FIG. 4 is a diagram showing an example of the control target part and the state of the control target part that can be controlled by voice commands in this embodiment.
  • control target part is a part of the receiving device 10 that can be controlled by voice commands.
  • the "desirable state value” is the desirable state of the "control target part”.
  • the "voice command” is a control command issued by the user when the state value of the "control target part” is switched.
  • the “voice command” for switching the state value is “power on” when the state value is turned on, and “power off” when the state value is turned off. That is, in order to turn on the power of the television device, the user pronounces "power on", and to turn off the power of the television device, the user pronounces "power off”.
  • the content output device is a general term for the broadcast signal reception processing unit 20, the content processing unit 30, and the recording and playback unit 40.
  • the “tuner” in the “admissible state value” column corresponds to the broadcast signal reception processing unit 20
  • the “network” corresponds to the content processing unit 30
  • the “recorder” corresponds to the recording and playback unit 40.
  • the user pronounces "tuner”.
  • the user pronounces "network”.
  • the recording and playback unit 40 in the playback state so that the display unit 103 and the speaker unit 104 can output, the user pronounces "recorder”.
  • the BS, CS, and terrestrial digital of the "desirable state value" respectively indicate the tuners of BS digital broadcasting, CS digital broadcasting, and terrestrial digital television broadcasting (terrestrial digital broadcasting).
  • the CS digital broadcast into the receiving state so that the display unit 103 and the speaker unit 104 output the content of the CS digital broadcast
  • the terrestrial digital broadcasting into a receiving state so that the display unit 103 and the speaker unit 104 output the content of the terrestrial digital broadcasting
  • 1ch, 2ch, and 3ch of the "admissible status value" indicate channel numbers. For example, in the case where 1ch is set to the receiving state so that the display unit 103 and the speaker unit 104 output a program of 1ch, the user pronounces "1ch". The same is true for other channels.
  • a channel may be defined for each content output device and for each tuner. For example, when the content output device is used as the broadcast signal reception processing unit 20, a channel number may be assigned to each of the tuners "BS", "CS", and "Terrestrial Digital". In addition, a unique channel number may be uniformly assigned to all channels of the content output device. In this case, the type of content output device and the type of tuner can be determined based on the channel number.
  • a state of "home (return to place)” may also be present.
  • “Return” is a state value that can be set by the user.
  • the “tuner” is set as the “return” state value of the content output device as the control target part.
  • the command generation unit 11 When the recognition command is input to the command generation unit 11, the command generation unit 11 generates and transmits the execution command "tuner” for switching the state to "tuner” as “return”, and switches the content output device to " tuner".
  • the above-mentioned setting of the "return” state value may be set by the user, or may be automatically set to the state value before the power of the television device was turned off last time.
  • a voice command there may also be “return”. For example, if the user pronounces the voice command as “return” and generates “return” as the recognition command, the state may transition to the state value set as "return”.
  • FIG. 5 is a diagram showing an example of auxiliary information that can be used in this embodiment.
  • the “information source” is the transmission source of the "ancillary information” or the extraction source of the "ancillary information” (the location where the extraction is performed).
  • the “auxiliary information” is information used when the command control unit 1 creates an execution command in this embodiment.
  • the "information value” is the value of the "ancillary information”.
  • “Number” 2 indicates that the attribute of the sound transmission source is determined based on the sound ripple, and the attribute of the sound transmission source is included in the auxiliary information, wherein the sound is implemented by the sound analysis unit 121 of the receiving device 10 as the "information source”
  • the sound ripple is obtained by analysis.
  • the attributes of the sound transmission source are, for example, the age of the transmission source, the classification of adults and children defined by age, and the classification of infants, kindergarten children, elementary school students, middle school students, high school students, college students, and social people defined by age, that is, user identification information.
  • the sound analysis unit 121 of the receiving device 10 serving as the "information source” performs sound analysis to obtain the above-mentioned sound intensity, sound height, and sound speed, respectively.
  • “Number” 8 to 11 respectively indicate that the "broadcast operator", “program broadcast time slot”, and “program broadcast time zone” extracted from the broadcast signal by the broadcast signal reception processing unit 20 of the receiving device 10 as the "information source” are included in the auxiliary information.
  • the names of operators such as operator A, operator B, and operator C are used as the value of the auxiliary information.
  • the broadcast time period is taken as the value of the auxiliary information.
  • program type for example, the type of program such as drama, sports, music, news, education, and emergency information is used as the value of the auxiliary information.
  • program name for example, the names of programs such as program A, program B, and program C are used as the value of the auxiliary information.
  • the auxiliary information includes demographic statistics obtained from the analysis result provided by the viewing analysis device 300 as the "information source”.
  • “Number” 13 to 16 respectively indicate that the auxiliary information includes the "information source” as the "information source” when the recording and playback unit 40 (which may also include an external video recorder, etc.) of the receiving device 10 is extracted from the broadcast wave when the program is recorded. Broadcast operator”, “program broadcast time period”, “program type”, “program name”.
  • “Number” 17 to 20 respectively indicate that the supplementary information includes the “distribution operator” and "program broadcast time extracted from the information attached to the content transmitted from the content server device 200 of the receiving device 10 as the "information source” Segment", “program type”, “program name”.
  • FIG. 6 is a flowchart showing an example of processing operations for the command control unit to receive a voice command and send an execution command in this embodiment.
  • the user issues a voice command "power on” or "power off”.
  • the sound detection unit detects sound (Yes in step S11). When the sound detection unit does not detect the sound, it waits for detection of the sound (No in step S11).
  • the sound detection unit determines whether the sound is detected or not. For example, it may also be: a threshold value is set for the intensity of the input sound, if it is greater than the threshold value, it is determined that the sound is detected, and if it is less than the threshold value, it is determined that it is not detected. sound.
  • the sound detection unit 12 outputs the sound data of the received sound to the sound analysis unit 121, and the sound analysis unit 121 performs a sound analysis process on the received sound data (step S12). Specifically, the sound analysis unit 121 performs frequency analysis (voice ripple analysis) on the sound data, and estimates the attributes of the sound transmission source.
  • frequency analysis voice ripple analysis
  • the control unit 19 determines whether to generate a recognition command based on the estimation result (step S13).
  • the user may set it in the storage unit 111 from the user interface unit 14, for example.
  • the control unit 19 accesses the storage unit 111 to refer to the judgment rule for the generation of the recognition command.
  • the control unit 19 determines that the generation of the recognition command is to be performed, it causes the command recognition unit 13 to perform voice recognition for the voice data (Yes in step S13).
  • control unit 19 determines that the generation of the recognition command is not performed, it controls so that the command recognition unit 13 does not perform voice recognition for the voice data, and sets the command recognition unit 13 in a waiting state until the next voice is detected So far (No in step S13, S11).
  • the control unit 19 determines that the generation of the recognition command is not performed, for example, the display unit 103 and the speaker unit 104 may output a message such as "The generation of the recognition command has not been performed" to notify the user.
  • step S14 it can also be set as follows: the command recognition unit 13 first tries to use the voice recognition engine provided in the command recognition unit 13 to obtain the recognition command, and if the voice recognition fails and cannot be obtained, the recognition by voice recognition is used.
  • the external voice recognition device 400 with a higher rate obtains the recognition instruction.
  • the command generation unit 11 When the command generation unit 11 receives the recognition command from the command recognition unit 13, it refers to the condition combination table of the storage unit 111.
  • FIG. 7 is a diagram showing an example of execution command generation conditions (combination condition table) set in the command control unit in order to control the main power supply in this embodiment.
  • the combination condition table For the example of the combination condition table, “number”, “execution command”, “recognition command”, “status information”, and “auxiliary information” are shown from the column on the left. It is shown that the "recognition command”, the "status information”, and the “auxiliary information” described in each row are used as conditions to determine the "execution command” described in the same row.
  • the “recognition command” is a recognition command generated and output by the command recognition unit 13.
  • the combination condition table may be set in the storage unit 111 from the user interface unit 14 by the user, for example.
  • the combination condition table shown in FIG. 7 is an example, and the number of auxiliary information (the number of columns) can be further added.
  • the command generation unit 11 refers to the combination condition table, and instructs the auxiliary information acquisition unit 16 and the status information acquisition unit 17 to acquire as “Supplementary Information” and "Status Information” of the column items of the table.
  • the auxiliary information acquisition unit 16 requests and acquires the "time”, “sound intensity”, and “user identification information” of the auxiliary information items as the combination condition table from the auxiliary information management unit 91, and outputs it to the command generation unit 11 (step S15 ).
  • the state information acquisition unit 17 grasps the status of the control target main power supply 80 based on the "recognition command” being "power on”, acquires the status information of the main power supply 80 for the status information management unit 92, and outputs it to the command generation unit 11 ( Step S16).
  • the command generation unit 11 refers to the combination condition table, and searches for rows where the acquired auxiliary information, status information, and the combination of the identification command and the condition of the combination condition table are consistent. 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 (steps S17, S18 The middle one is S19). On the other hand, for example, if the item of "execution command" with the same combination of conditions is "not sent” as shown in number 8 in FIG. 7, the execution command is not generated, and the command control unit 1 waits for the next sound detection (No in steps S17 and S18).
  • the command control unit 1 may send a message including the meaning of “the execution command is not sent or not generated” to the control unit 90.
  • the control unit 90 that has received the message may display the message on the display unit 103 or output a sound including the content of the message from the speaker unit 104 to notify the user.
  • the command control unit 1 may generate and send an “execution command for maintaining the current state”. For example, if the voice analysis unit 121 performs voice moire analysis on the voice command, the auxiliary information that the source of the voice is "child" is input to the command generation unit 11 as the user identification information. Use identification instructions, and only use auxiliary information to generate and send "execution instructions for maintaining the current state”. In this case, the command generation unit 11 may send a message including the meaning "this operation cannot be performed” or the like to the control unit 90. At this time, the control unit 90 that has received the message may display the message on the display unit 103 or output a sound including the content of the message from the speaker unit 104 to notify the user.
  • the command transmission unit 18 transmits the execution command to the control unit 90 via the interface unit 15 (step S101).
  • the control unit 90 controls the functions of the control target in accordance with the received execution command.
  • the command control unit 1 may send a message including the content "the execution command was sent" to the control unit 90.
  • the command control unit 1 may send a message including "the execution command is different from the recognition command” to the control unit 90. It is also possible for the command control unit 1 to cause the display unit 103 to display a message or to output a sound including the content of the message from the speaker unit 104 to notify the user. Through the above setting, the user can confirm whether the voice command issued by him is executed correctly.
  • the auxiliary information is all “-”, which means that the auxiliary information is not used, and is an example in which the command generation unit 11 generates the execution command using only the status information and the recognition command.
  • the description is omitted.
  • the accuracy of the voice recognition engine will not be degraded during the "night” time period because the surrounding noise is small. However, it can be used when the user wants to restrict the generation and transmission of execution commands during the "night”.
  • condition combination table of FIG. 7 can be used to generate an execution command.
  • the current state of the main power supply (corresponding to "state information") is "on". It is generally believed that in such a situation, the user is less likely to issue a voice command of "power on”, on the contrary, it is more likely to issue a voice command of "power off” that is opposite to the current state of "on”. However, if the voice command of "power off” is recognized by the voice recognition engine of the command recognition unit 13 as “power on” due to surrounding noises, etc., it will happen that even though the user pronounces "power off", the receiving device 10 cannot be connected. When the main power supply is turned off, the user's pressure becomes greater.
  • the recognition command is interpreted based on the status information of the receiving device 10, so that such a situation can be prevented.
  • the "number" 2 to 4 of the condition combination table is applied to the command control unit 1
  • the recognition command is a control command such as switching the current state of the main power supply ("status information")
  • the recognition command is consistent with the control command of the execution command.
  • the recognition command is a control command in the same state as the "status information"
  • the control command for the execution command becomes the opposite or different control command from the recognition command.
  • the reason for this action is that the voice recognition engine especially has a higher probability of misrecognizing the sound of on and off.
  • the user issues a voice command in order to make the current state of the control target the same as the state after the control, and this makes it possible to assist the interpretation of the voice command by voice recognition.
  • number 1 to number 20 show the condition combinations used to determine the execution command, but it is also possible to give priority to them so that the command generation unit 11 considers priority Right to refer to the condition combination table. It is also possible to give priority in the order of rows from 1 to 20 as shown in FIG. 7. In this case, even if the instruction generation unit 11 acquires the auxiliary information, the numbers 1 to 4 have priority, so the auxiliary information is not used. In addition, it may also be configured to additionally add a column item showing the priority order to the table of FIG. 7 so that the user can set the priority in the condition combination of each row.
  • auxiliary information when there are multiple "auxiliary information", priority may also be given within the "auxiliary information".
  • the auxiliary information is given higher priority in the order of "time”, "intensity of sound", and "user identification information", for example.
  • the command generation unit 11 refers to, for example, the combination condition table from the combination of conditions in which the auxiliary information with higher priority is placed.
  • the user can also set as follows: the auxiliary information gives the highest priority to the condition combination with only "time”, and then the condition combination with only "time” and “sound intensity” is given priority , Next, give priority to conditional combinations that only have "time” and "user identification information".
  • the user sets points indicating the priority to the "time”, “sound intensity”, and “user identification information”, so that the command generation unit 11 calculates the "time”, “sound intensity”,
  • the sum of the points assigned by the "user identification information” is set to a higher priority from the higher sum of the points to give priority to each combination condition table.
  • the command generation unit 11 can calculate the priority order. Therefore, the user only needs to set points indicating the priority to the “time”, “sound intensity”, and “user identification information”.
  • condition combination shown in the combination condition table it is desirable to set the condition combination shown in the combination condition table to a combination that basically does not become the same condition.
  • a rule such as making the command generation unit 11 select in the order of the table may be determined in advance.
  • the volume output from the speaker unit 104 of the receiving device 10 is controlled on and off by using the voice command issued by the user, the status information, and the program category and user identification information as auxiliary information
  • the main power supply is set to be in an on state.
  • FIG. 8 is a diagram showing an example of execution command generation conditions set in the command control unit in order to control the volume in the second embodiment. 6 is used to describe an example of a processing operation in which the command control unit 1 used in this embodiment receives a voice command and sends an execution command, but the description of the same parts as in the first embodiment will be omitted.
  • the user issues a voice command "volume on” or "volume off”.
  • the sound detection unit detects sound (Yes in step S11).
  • the control unit 19 determines that a recognition command is generated, and causes the command recognition unit 13 to perform voice recognition for the voice data (Yes in step S13).
  • the command recognition unit 13 acquires a recognition command as text data by voice recognition, and outputs the recognition command to the command generation unit 11 (step S14).
  • the command generation unit 11 When the command generation unit 11 receives the recognition command from the command recognition unit 13, it refers to the condition combination table of the storage unit 111. If the "volume on” is input as the “recognition command” from the command recognition unit 13, the command generation unit 11 refers to the combination condition table, and instructs the auxiliary information acquisition unit 16 and the status information acquisition unit 17 to acquire the "auxiliary" as the column items of the table. Information", “Status Information”. The auxiliary information acquisition unit 16 requests and acquires the "program category” and "user identification information” as auxiliary information items in the combination condition table from the auxiliary information management unit 91, and outputs it to the command generation unit 11 (step S15).
  • the state information acquisition unit 17 grasps the status of the control target as the main power source 80 based on the "recognition command” being "volume on”, acquires the status information of the speaker unit 104 from the status information management unit 92, and outputs it to the command generation unit 11 ( Step S16).
  • the command generation unit 11 refers to the combination condition table, and if there is a command in the "execution command” item of the row where the obtained auxiliary information, status information, and identification command match the combination, it writes the "execution command” item
  • the command of is generated as an execution command and output to the command transmission unit 18 (Yes in steps S17 and S18, S19).
  • the command control unit 1 waits for the next sound detection (No in steps S17, S18).
  • the command transmission unit 18 transmits the execution command from the interface unit 15 to the control unit 90 (step S101).
  • Numberer 5 to 12 is an example of using "user identification information" as auxiliary information.
  • “Number” 5 to 12 can be used.
  • the user can conceive various use cases by setting the combination condition table, and can command and control voice commands.
  • the receiving device 10 uses voice commands issued by the user, status information, and user identification information and time as auxiliary information to control the digital content output to the display unit 103 and the speaker unit 104 is shown.
  • a state where the main power supply is on is assumed.
  • an example in which two execution commands are output 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 in order to control the reception of digital content in the third embodiment.
  • step S11 the command recognition unit 13 obtains a recognition command as text data by voice recognition, and outputs the recognition command to the command generation unit 11 (step S14).
  • the command generation unit 11 refers to the condition combination table of the storage unit 111, and instructs the auxiliary information acquisition unit 16 and the status information acquisition unit 17 to acquire "assistance information" as the column items of the table. ,"status information”.
  • the auxiliary information acquisition unit 16 requests and acquires the "user identification information” and “time” as the auxiliary information items of the combination condition table from the auxiliary information management unit 91, and outputs it to the command generation unit 11 (step S15).
  • the state information acquisition unit 17 recognizes that the control target is a content output device based on 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 generation unit 11 generates an execution command through steps 17 to S19 and outputs it to the command transmission unit 18.
  • the execution command is sent from the command sending unit 18 to the control unit 90 (step S101).
  • two execution commands are generated. These are the first execution command for the content output device and the second execution command for the program category.
  • the command generation unit 11 since the “status information” of the content output device is “recorder”, it indicates that the “recorder” is currently being output to the display unit 103 and the speaker unit 104.
  • the recognition command received by the command generation unit 11 is "network”
  • the first auxiliary information that is, the user identification information
  • the second auxiliary information that is, the time is "night”.
  • the command generation unit 11 generates two of "network” and "education” as an execution command for the program type as execution commands.
  • the two generated execution commands are sent from the command transmission unit 18 to the control unit 90, and a program related to "education” that is distributed through the "network” is output to the display unit 103 and the speaker unit 104.
  • the command generation unit 11 When the recognition command is input, the command generation unit 11 generates and transmits the execution command "Terrestrial Digital” for switching to the state value (assumed to be “Terrestrial Digital") set in "Return” of the control target part "Tuner".
  • the control unit 90 receives the execution command "terrestrial digital", and switches the tuner to "terrestrial digital”.
  • the command generation unit 11 responds to a voice command issued by the user for a control target part (or a recognition command obtained by recognizing the voice command), and responds to "tuner” and "channel (program)" "These multiple control target parts generate execution commands.
  • the "return" set for the "channel (program)” may be set to a channel that was being watched before the power of the television device was turned off last time, or may be set to a channel set in advance by the user.
  • the execution commands for different control target parts may not be distinguished, and one execution command may be used.
  • the user can generate a plurality of execution commands from one voice command and send and execute them.
  • Fig. 10 is a diagram showing a configuration example of the entire system of the third embodiment.
  • the command control device 2 and the IoT device 600A and the IoT device 600B are connected to the network 500.
  • the IoT device 600A and the IoT device 600B have the same functions, and the IoT device 600A and the IoT device 600B are referred to as the IoT device 600 unless the two are particularly distinguished. Only two IoT devices 600 are shown in FIG. 10, but multiple IoT devices may be provided.
  • the command control device 2 is built in, for example, a computer having a CPU, a memory, and the like.
  • the instruction control device 2 may be a personal computer or a cloud service including a server, a database, and the like.
  • the command control device 2 includes a command control unit 1 and a communication unit 102A.
  • the command control unit 1 and the communication unit 102A respectively correspond to the functions of the command recognition unit 1 and the communication unit 102 in FIG. 3.
  • the IoT device 600 is all kinds of IoT devices, connected to the network 500, and performs data communication with devices on the network 500.
  • the IoT device 600 may be, for example, sensors such as a temperature detection sensor, a water leakage detection sensor, and a door opening/closing sensor, or a detection device using these sensors.
  • the IoT device 600 may also be home appliances such as air conditioners, television devices, lighting, and cameras.
  • it if it is connected to the network 500, it may be a mobile terminal such as a smartphone.
  • the IoT device 600 in this embodiment provides auxiliary information and status information to the command control device 2, receives execution instructions output by the command control device 2, and controls the functions of the IoT device 600 according to the received execution instructions.
  • 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.
  • the respective functions correspond to the functions of the auxiliary information output unit 21, the status switching unit 82, the control unit 90, the auxiliary information management unit 91, the status information management unit 92, the communication unit 102, and the interface unit 105 in FIG. 2.
  • each function of FIG. 2 is allocated to the command control device 2 and the IoT device 600A.
  • the big difference between the receiving device 10 shown in the first embodiment and the IoT device 600 shown in this embodiment is that the receiving device 10 includes the command control unit 1 internally, but the IoT device 600 does not include Command control unit 1.
  • 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, and may also be other starting and stopping of functional parts. Take control.
  • the order in which the command control device 2 sends execution commands to the IoT device 600 can use the flowchart of FIG. 6. Detailed descriptions of the same procedures as those of the first embodiment and the second embodiment will be omitted.
  • the user remotely controls the IoT device 600A via the network 500 in the vicinity of the command control device 2.
  • the user sets an execution command generation condition (combination condition table) for the IoT device 600A to the command control unit 1 of the command control device 2.
  • the user issues a voice command to the voice detection unit 12 of the command control device 2.
  • the sound detection unit 12 detects the sound, and after the sound analysis process performed by the sound analysis unit 121, the command recognition unit 13 generates a recognition command, and outputs the recognition command to the command generation unit 11 (Yes in step S11, Yes in S12, S13 , S14).
  • the command generation unit 11 When a recognition command is input from the command recognition unit 13, the command generation unit 11 refers to the combination condition table, and instructs the auxiliary information acquisition unit 16 and the status information acquisition unit 17 to acquire "assistance information" and "status information” as column items of the table, respectively.
  • the auxiliary information acquisition unit 16 requests and acquires each item of the auxiliary information of the combination condition table from the auxiliary information management unit 91A, and outputs it to the command generation unit 11 (step S15).
  • the step S15 in this embodiment will be described in detail.
  • the auxiliary information acquisition unit 16 requests the IoT device 600A for auxiliary information via the communication unit 102A.
  • the control unit 90A receives a request for auxiliary information via the communication unit 102A2.
  • the control unit 90A obtains auxiliary information from the auxiliary information management unit 91A, and transmits the obtained auxiliary information to the command control device 2 via the communication unit 102A2.
  • the state information acquisition unit 17 grasps the control object based on the recognition command, and requests the IoT device 600A for the state information of the control object via the communication unit 102A.
  • the control unit 90A receives a request for status information via the communication unit 102A2.
  • the control unit 90A acquires status information from the status information management unit 92A, and transmits the acquired status information to the command control device 2 via the communication unit 102A2.
  • the command generation unit 11 receives the status information via the communication unit 102A (step S16).
  • the command generation unit 11 refers to the combination condition table, and when there is a command in the "execution command” item of the condition that matches the combination of the acquired auxiliary information, status information, and identification command, it is described in the item that generates the "execution command”
  • the command of is used as an execution command, and is output to the command transmission unit 18 (Yes in steps S17 and S18, S19).
  • the item of "execution command” is "not sent"
  • the generation of the execution command is not performed, and the command control unit 1 waits for the next sound detection (No in steps S17 and S18).
  • the command control unit 1 may display the message on a display unit (not shown) of the command control device 2 for a message containing the meaning of "an execution command not sent or not generated” such as "command not sent".
  • the user is notified by displaying on the screen or outputting a sound including the content of the message 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 controlled function is controlled in accordance with the received execution instruction.
  • the command control unit 1 may display the message on a display unit (not shown) of the command control device 2 for a message containing the meaning "an execution command has been sent.”
  • a voice including the content of the message is output from a speaker unit (not shown) of the command control device 2 to notify the user.
  • the command control device 2 may place the message on the command control device 2 not shown in the figure for a message containing the content "the execution command is different from the recognition command"
  • the user is notified by displaying on the display unit of the, or outputting a sound including the content of the message from a speaker unit (not shown) of the command control device 2.
  • the execution command can be used to control the IoT device 600 connected to the network 500.
  • control unit 90 including the auxiliary information management unit 91 and the state information management unit 92
  • the control unit 90 may be provided as an external control device or the like to be controlled.
  • the control device is also connected to the network 500.
  • the command control device and various configurations and combinations are conceivable regarding the functions in the device and the hardware that executes the functions, and they are not limited to the examples of the embodiments shown above.
  • the voice analysis unit 121 performs voice ripple analysis, acquires “child” as user identification information in the auxiliary information acquisition unit 16, and inputs it to the command generation unit 11.
  • the voice command is input to the command recognition unit 13 to generate a recognition command and input to the command generation unit 11.
  • the command generating unit 11 generates “power off” as an execution command based on the recognition command “power off” and the auxiliary information “child”, for example, and outputs it to the control unit 90.
  • the instruction generation unit 11 acquires “child” as user identification information from the auxiliary information acquisition unit 16 and acquires “late night” as the time zone. In this case, the instruction generation unit 11 may generate, for example, "an execution instruction for maintaining the current state" based only on auxiliary information such as "child” and "late night”.
  • the command recognition unit 13 recognizes that the control target part is "channel (program)" based on the voice command given by the child. If the command recognition unit 13 outputs the identification information including the recognized control target part to the auxiliary information acquisition unit 16, the auxiliary information acquisition unit 16 acquires the control target part included in the identification information from the broadcast signal reception processing unit 20 and the like.
  • the auxiliary information of the “channel (program)”, that is, the “program viewing target”, is output to the command generation unit 11.
  • the command generation unit 11 generates an execution command based on the user identification information obtained from the voice analysis unit 121, namely, the two auxiliary information of “child” and “program viewing target”. For example, in the case where a "child” is included in the program viewing object, the recognition instruction is directly generated as an execution instruction. In addition, in a case where the program viewing target does not include “children”, for example, "an execution instruction for maintaining the current state" is generated.
  • parental control for voice commands can be performed.
  • command control unit 1 or command control device 2 which has an action control mechanism (command generation unit 11) that acquires action control information (recognition commands) based on input sounds (voice commands), and Set the operating state of the control target device (receiving device 10) to either the first mode or the second mode different from the first mode,
  • the operation state of the control target device is the first mode and the operation control information is information related to the operation state in the first mode
  • the operation state is set to the second mode.
  • the operation state information (state information) related to the state of the control target part of the control target device is acquired.
  • control condition information (auxiliary information) different from the motion control information and the motion state information is acquired.
  • control condition information is based on at least one of the group of time period, user identification information, user attributes, received content information, broadcast operator, distribution operator, and video content manager Information set by any one.
  • a program for the computer to execute the operation control information (recognition command) obtained from the input sound (voice command), and to set the operation state of the control target device (receiving device 10) to the first mode or different from the first mode
  • the operation of any action state in the second mode
  • the operation state of the control target device is the first mode and the operation control information is information related to the operation state in the first mode
  • the operation state is set to the second mode.
  • drawings may, in some cases, schematically show the width, thickness, shape, etc. of each part compared with the actual form.
  • the direction of the arrow is not shown.
  • data and signals are exchanged.
  • the functions shown in the block diagrams, the flowcharts, and the processes shown in the sequence diagrams can also be implemented by hardware (IC chip, etc.) or software (programs, etc.) or a combination of hardware and software.
  • control logic when it is expressed as a program including instructions to be executed by a computer, and when it is expressed as a computer-readable storage medium in which the above-mentioned instructions are recorded, this also applies The technical solution of the device of this application.
  • the names and terms used are not limited, and even other expressions are included in this application as long as they have substantially the same content and the same subject.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Selective Calling Equipment (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

一种指令控制装置、控制方法及非易失性存储介质。指令控制装置辅助针对声音指令的声音识别。指令控制装置基于输入的声音来生成包含针对控制对象设备的控制命令在内的执行指令，其中，生成包含第1控制命令和与所述第1控制命令不同的第2控制命令中的任一者在内的执行指令，其中，所述第1控制命令是对所述声音进行声音识别而获取的识别指令中包含的控制命令。

Description

指令控制装置、控制方法及非易失性存储介质
本申请要求在2019年12月6日提交日本专利局、申请号为2019-221573、发明名称为“指令控制装置、控制方法及控制程序”的日本专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施方式涉及指令控制装置、控制方法及非易失性存储介质。
背景技术
近年来，研究了使用声音识别以声音来控制设备的声音控制技术。例如，声音控制技术能够用于代替电视机的遥控器，若用户发出了作为控制命令的指令，则叠加有指令的声音(以下，称为声音指令)由附属于电视机的麦克风等接收声波，并通过声音识别将指令作为数据进行取出。取出来的指令数据成为在电视机中执行的指令。在该技术中，在周围的噪音等的影响下，用户所发出的声音指令有时会通过声音识别被识别为错误的指令，正在研究声音识别的性能提高。
在先技术文献
专利文献
专利文献1：日本特开2017－167247号公报
发明内容
然而，根据周围的噪音的大小的不同，有时声音识别无法良好地起作用，能够应用声音控制技术的范围受到限定。另外，在平时动作的基于声音控制技术的控制有可能在地震等紧急时因噪音变大而变得不正常地动作。
本申请要解决的问题是提供对声音指令的声音识别进行辅助的指令控制装置、控制方法及非易失性存储介质。
本申请的一个实施方式的指令控制装置基于输入的声音来生成包含针对控制对象设备的控制命令在内的执行指令，其中，所述指令控制装置生成包含第1控制命令和与所述第1控制命令不同的第2控制命令中的任一者在内的执行指令，所述第1控制命令是对所述声音进行声音识别而获取的识别指令所包含的第1控制命令。
附图说明
图1是示出第1实施方式的系统整体的构成例的图；
图2是示出该实施方式的接收装置的功能结构的一个例子的框图；
图3是示出该实施方式的指令控制部的功能结构的一个例子的框图；
图4是示出在该实施方式中能够利用声音指令进行控制的控制对象部位和控制对象部位的状态的一个例子的图；
图5是示出在该实施方式中能够利用的辅助信息的一个例子的图；
图6是示出在该实施方式中用于指令控制部接收声音指令并发送执行指令的处理动作例的流程图；
图7是示出在该实施方式中为了控制主电源而在指令控制部中设定的执行指令生成条件的一个例子的图；
图8是示出在第2实施方式中为了控制音量而在指令控制部中设定的执行指令生成条件的一个例子的图；
图9是示出在第3实施方式中为了控制数字内容接收而在指令控制部中设定的执行指令生成条件的一个例子的图；
图10是示出第4实施方式的系统整体的构成例的图。
附图标记说明
1…指令控制部、2…指令控制装置、10…接收装置、11…指令生成部、12…声音检测部、13…指令识别部、14…用户接口部、15…接口部、16…辅助信息获取部、17…状态信息获取部、18…指令发送部、19…控制部、20…广播信号接收处理部、21…辅助信息输出部、30…内容处理部、31…辅助信息输出部、40…录像播放部、41…辅助信息输出部、50…设备数据生成部、51…辅助信息输出部、60…输出控制部、62…状态切换部、70…传感器部、71…辅助信息输出部、80…主电源部、82…状态切换部、90…控制部、91…辅助信息管理部、92…状态信息管理部、93…时刻管理部、100…遥控器、101…天线、102…通信部、103…显示部、104…扬声器部、105…接口部、111…存储部、121…声音分析部、200…内容服务器装置、300…收看解析装置、400…声音识别装置、500…网络。
具体实施方式
以下，参照附图说明实施方式。
图1是示出实施方式的系统整体的构成例的图。
接收装置10是收看数字内容的设备，例如是能够接收并收看2K或4K/8K这样的地面波广播、卫星广播等数字广播的电视机接收装置(也称为电视机装置、电视接收机、广播信号接收装置)。另外，接收装置10例如具备用于与互联网等网络500连接的外部接口，能够收看与网络500连接的内容服务器装置200(也可以是云服务器)提供的数字内容。另外，接收装置10也可以具有录像播放功能，能够利用录像播放功能来收看在接收装置10中录像到的数字内容。另外，也可以通过在接收装置10上连接未图示的录像播放装置，从而能够收看未图示的录像播放装置录像到的数字内容。此外，在图1中，示出了1个接收装置10，但是，可也进一步连接多个接收装置10。但是，接收装置10只要是能够接收数字内容的设备，则不需要全部具有相同的功能。具体而言，也可以是不具有能够进行收看的监视器的仅能录像的录像机(Recorder)、能够接收广播信号的机顶盒(Set Top Box：STB)等。将电视机装置、录像机、STB等统称为接收装置10。
在本实施方式中，特别示出电视机装置的例子，但是，也可以将电视机装置替换为录像机、STB等接收装置10。另外，作为具有同样的接收功能的装置，接收装置10也可以是个人计算机、智能手机等移动设备。
本实施方式的接收装置10是能够进行使用声音识别的基于声音的控制。指令控制部1例如对用户所发音的声音指令进行声音识别，使用利用声音识别取得的指令(以下，称为识别指令)来控制接收装置10内的各功能。另外，遥控器100是对接收装置10进行遥控控制的遥控器。
另外，接收装置10能够对由接收装置10收看过的数字内容的收看历史(以下，称为收看数据)进行收集并存储。另外，能够在接收装置10中存储固有的数据(以下，称为设备个别数据)。包含收看数据和设备个别数据在内称为收看设备数据。接收装置10能够将收看设备数据等保存数据向与网络500连接的收看解析装置300输出，并且能够接收收看解析装置300实施的针对收看设备数据的解析结果。
本实施方式中的所谓“收看”，包含即使用户实际上虽未正在收看但以能够收看的状态接收数字内容或已接收到的状态、或者已录像到的状态。因此，本实施方式中的“收看历史”例如包含：STB等接收装置仅进行接收但不论是否收看的“接收历史”；在接收装置为录像机的情况下由接收装置接收并被录像预约的、或被录像到的“录像历史”等。另外，同样地，本实施方式中的“收看时间”例如包含：STB等接收装置接收了数字内容的时间；在接收装置为录像机的情况下，录像了数字内容的时间等。
因此，在将接收装置10替换为录像机、STB等接收装置的情况下，在收看设备数据中也包含录像机、STB等接收装置生成的接收日志数据、下载历史数据、录像数据等。
设备个别数据例如既可以由用户使用接收装置10的遥控器100登记到接收装置10中，有的情况下也如接收装置10的固定编号那样由生产商设定。设备个别数据例如包含接收 装置10的IP地址、识别编号、以及预先由所有者等登记的人口统计数据(以下，称为人口统计)等。所谓人口统计，是将收看接收装置10的用户分类的数据，例如是用户的年龄、性别、家族构成、居住地区等信息。识别编号是识别不同的接收装置10的编号、字符串等，例如由数字、字母的组合构成。
内容服务器装置200是提供数字内容的网络上或者云服务器。内容服务器装置200例如由内容服务提供商(CSP)、通信运营商、以及其他被称为过顶传输(Over The Top：OTT)的数字内容的服务运营商等提供。内容服务器装置200也包含提供视频点播(Video On Demand)这样的服务的服务器。
收看解析装置300是如下装置：存在于网络上或者云上，对由接收装置10存储的收看设备数据进行收集并存储，进而对存储的数据进行解析以进行各种收看解析，并向例如请求了解析的接收装置10输出解析结果。收看解析装置300例如被构筑在具有CPU、存储器等的计算机中。收看解析装置300既可以是个人计算机，也可以是由服务器、数据库等进行的云服务。
另外，收看解析装置300也可以能够根据接收装置10个别地具有的识别编号来识别各个接收装置10，从而进行个别的接收装置10收看解析。
声音识别装置400被设置在网络500上。声音识别装置400例如被构筑在具有CPU、存储器等的计算机中。声音识别装置400既可以是个人计算机，也可以是云服务器。声音识别装置400经由网络500接收与由麦克风等接收到的用户的声音相对应的声音波形的数字数据(以下，称为声音数据)，推定或者识别用户发出的指令，将识别出的指令(识别指令)作为文本数据进行输出。在声音识别装置400中，也可以将用户向控制对象发出的指令预先作为文本数据进行列表化，对根据接收到的声音数据而取得的文本数据与列表的文本数据进行比较，选择列表中的最接近的指令，将选择出的指令的文本数据输出。但是，声音识别装置400中的声音识别的方法不限定于该方法。
另外，声音识别装置400也可以由语言转成文字(Speech To Text)服务器(以下，称为STT服务器)和遥控识别服务器构成，其中，该语言转成文字服务器生成将声音数据文本化(文字化、语言化等)而得到的声音文本，该遥控识别服务器从列表化了的指令之中将与生成了的声音文本最接近的指令作为识别指令来生成。具体而言，遥控识别服务器也可以参照预先登记在未图示的存储部等中的指令表，将与STT服务器生成了的声音文本一致的指令或者表中最接近的指令作为识别指令进行输出。
网络500是连接有接收装置10、内容服务器装置200、收看解析装置300、声音识别装置400从而使各装置能够通信的网络，例如是互联网。另外，网络500不仅限于互联网，如果各装置能够通信，则也可以是包含多个不同网络的网络。
图2是示出实施方式的接收装置10的功能结构的一个例子的框图。
接收装置10是对叠加有数字内容的信号进行接收处理以获取数字内容并收看的设备。
广播信号接收处理部20对从天线101接收到的数字广播等广播信号按照数字广播的规范进行处理，获取视像、声音、文字等内容数据并输出。数字广播的规范例如可以是在2K数字广播中采用的MPEG2TS方式、在4K/8K数字广播中采用的MPEG媒体传输(MPEG Media Tranport)方式(MMT方式)等，也可以利用多个调谐器对应双方。作为与数字广播的规范相应的处理，包含将数字数据流分离成视像、声音、文字等内容数据的数字数据流的解复用处理、错误订正码解码处理、对加密后数据进行解码的加密解码处理、针对已对各内容数据实施了的编码化(视像编码化、声音编码化、文字编码化等)的解码处理等。
辅助信息输出部21从广播信号中提取由控制部90请求的信息，并向控制部90输出。辅助信息输出部21尤其是从广播信号中包含的控制信息、节目关联信息等中提取被请求的信息，并向控制部90输出。对输出到控制部90的信息，根据需要而实施加工，作为辅助信息在指令控制部1中使用。
内容处理部30对于从通信部102输入的数字数据，针对由内容服务器装置200实施了的编码处理实施解码处理等，并输出视像、声音、文字等内容数据。具体而言，作为解 码处理，内容处理部30例如实施解复用处理(分离处理)、错误订正码解码处理、针对编码了的内容数据(视像、文字、声音等)的解码处理等。
辅助信息输出部31从由内容服务器装置200输出的数据中提取由控制部90请求的信息，并输出到控制部90。辅助信息输出部31尤其是从由内容服务器装置200输出的控制信息等中提取内容节目的发布运营商等关联属性信息等，并输出到控制部90。对于被输出到控制部90中的信息，根据需要而实施加工，并作为辅助信息在指令控制部1中使用。
录像播放部40例如是光盘播放器(Disc player)、HDD录像机等，存储广播信号接收处理部20、内容处理部30输出的内容数据等，并按照播放请求，将存储了的内容数据向输出控制部60输出，作为视像、文字、声音从显示部103、扬声器部104输出。用户通过收看显示部103、扬声器部104输出的视像、文字、声音，从而收看在录像播放部40中存储了的数字内容等。此外，在本实施方式中，录像播放部40设置为接收装置10的一个功能，但是，例如也可以是经由了接口部105的外置装置。另外，在接收装置10具备多个调谐器(相当于广播信号接收处理部20)的情况下，录像播放部40也可以设置成，能够一边收看利用广播信号接收处理部20进行了接收处理后的内容A，一边通过录像播放部40对由其它广播信号接收处理部20进行了接收处理后的内容B进行录像。
设备数据生成部50从接收装置10的各功能部(尤其是广播信号接收处理部20、内容处理部30、录像播放部40)收集数据，并生成收看设备数据。收看设备数据包含设备个别数据和收看数据。设备个别数据是接收装置10所固有的数据，例如也可以在设置接收装置10时，由用户从遥控器100等设定到接收装置10中。另外，对于在收看解析中使用的识别编号，例如也可以在接收装置10的购买时等预先分配，并设定在设备个别数据等中。
收看数据例如是收看历史，也可以由接收装置10在进行了某些收看的情况下逐次生成。具体而言，例如，与广播信号接收处理部20、内容处理部30、录像播放部40被起动的时刻相应地，在各功能部中，对提供数字内容的频道、节目名(或以该节目名为基准的节目id)、收看了节目的日期等进行存储，与各功能部被停止的时刻相应地，各功能部将存储了的数据作为收看数据输出到设备数据生成部50。设备数据生成部50根据需要而对收看数据进行加工，并存储到接收装置10的未图示的存储部中。另外，也可以设置成：各功能部(尤其是广播信号接收处理部20、内容处理部30、录像播放部40)分别存储收看数据，在从外部装置存在收看数据的发送请求时，各功能部将收看数据输出到设备数据生成部50，设备数据生成部50根据需要而对收看数据实施加工，作为收看设备数据向外部装置输出。
设备数据生成部50根据来自外部装置(尤其是收看解析装置300)的请求，将生成了的收看设备数据向通信部102输出。将收看设备数据从通信部102经由网络500而向进行了请求的收看解析装置300发送。另外，也可以是，在接收装置10中，在检测到收看设备数据的变化的情况下，在任意的时刻将收看设备数据向收看解析装置300发送。
辅助信息输出部51接收设备数据生成部50生成了的收看设备数据、从接收装置10的各功能部收集到的收看数据、以及收看解析装置300输出的各种解析结果数据，并输出到控制部90。对于输出到控制部90的信息，根据需要而实施加工，并作为辅助信息在指令控制部1中使用。
输出控制部60对于广播信号接收处理部20、内容处理部30、录像播放部40输出了的内容数据，调整输出时刻、显示方法等，并向显示部103、扬声器部104输出。
状态切换部62按照来自控制部90的控制来切换显示部103的当前的显示状态(开状态或者关状态、正在显示的状态或者未显示的状态等)、扬声器部104的当前的输出状态(开状态或者关状态、声音输出状态或者正在将声音设置成静音的状态等)。控制部90管理显示部103的显示状态、扬声器104的输出状态，控制部90按照来自遥控器100、指令控制部1的控制命令来控制状态切换部62。
传感器部70是设置于电视机正面的例如照相机，可以用照相机拍摄电视机装置的正面，并使用图像识别等根据拍摄到的图像来推测例如在电视机装置的前方的用户。
辅助信息输出部71将传感器部70推测出的用户信息输出到控制部90。对于输出到控制部90中的信息，根据需要而实施加工，并作为辅助信息在指令控制部1中使用。
主电源部80是接收装置10的主功能的电源，例如，是在向电视机装置的显示部103、扬声器部104输出数字内容、或停止输出(将该操作称为电视机装置的开－关操作)时使用的电源。
状态切换部82按照来自控制部90的控制来切换主电源部80的当前的状态，即电视机装置的开－关的状态。控制部90管理主电源部80的当前的状态，控制部90按照来自遥控器100、指令控制部1的控制命令来控制状态切换部82。
控制部90控制接收装置10的各功能。具体而言，控制部90从接口部105接收各种控制信号，并控制接收装置10的各功能。例如，在用户从遥控器100指定了是收看基于广播信号的内容、还是收看来自内容服务器装置200的内容的情况下，控制部90经由接口部105接收来自遥控器的控制信号，控制接收装置10的功能，使其进行用户指定的动作。此外，也可以是，在图2中，与控制部90之间并未特别连线的功能模块之间也进行数据的交互。
另外，本实施方式中的控制部90经由接口部105接收来自指令控制部1的执行指令，并按照执行指令来实施接收装置10内的各功能的控制。
辅助信息管理部91接收各功能部内的辅助信息输出部(辅助信息输出部21、辅助信息输出部31、辅助信息输出部41、辅助信息输出部51、辅助信息输出部71等)输出的辅助信息，并存储到未图示的存储部中。辅助信息管理部91将已存储的各功能部的辅助信息从接口105发送到指令控制部1。
也可以设置为：对于在辅助信息管理部91中存储的信息，将预先确定的项目设定在各功能部内的辅助信息输出部中，在各功能部中更新了辅助信息的时刻由辅助信息输出部自动地输出到辅助信息管理部91。另外，也可以设置为：辅助信息管理部91根据需要而向各功能的辅助信息输出部请求辅助信息。
状态信息管理部92将各功能部内的状态切换部(状态切换部62、状态切换部82等)的状态信息存储到未图示的存储部。状态信息管理部92经由接口105而将存储了的各功能的状态信息发送到指令控制部1。在本实施方式中，控制部90为了控制各功能部的状态，而将状态信息管理部92的状态信息始终保持为最新的状态。此外，关于状态信息管理部92存储的信息，也可以设置为：将预先确定的项目设定在各功能部内的未图示的状态信息输出部中，在各功能部中更新了状态信息的时刻由状态信息输出部自动地输出到状态信息管理部92。另外，也可以设置为，状态信息管理部92根据需要而向各功能部的状态信息输出部请求状态信息。
时刻管理部93管理接收装置10的时刻。既可以在接收装置10的内部具有时钟，也可以从广播信号等提取时刻来得到。
通信部102按照例如TCP/IP、UDP/IP这样的预先确定的通信协议等，与连接于网络500的各种装置之间进行数据的收发处理。
显示部103是显示视像、文字的例如监视器。扬声器部104是输出声音的例如扬声器。显示部103、扬声器部104将输出控制部60输出的内容数据作为视像、文字、声音进行输出。用户通过收看显示部103、扬声器部104输出的视像、文字、声音，从而收看由广播信号、内容服务器装置200、其它录像播放部40提供的数字内容。
接口部105是用于从遥控器100等外部对接收装置10进行控制的接口，例如，从遥控器100、附属于接收装置10的未图示的开关等接收控制信号，并向接收装置10的控制部90输出。也可以具有代替遥控器100而接收来自未图示的智能手机等终端的控制信号的接口。另外，接口部105也可以具有用于与外部装置连接的接口。例如，也可以是用于将接收装置10与未图示的外置的HDD录像机连接的接口。在此情况下，用户能够利用显示部103、扬声器部104来收看未图示的外置的HDD录像机输出的数字内容。
另外，本实施方式中的接口105具有能够与指令控制部1的接口部15进行通信的接口，例如接口也可以是各种串行总线。另外，接口105接收指令控制部1输出的执行指令， 并向控制部90输出执行指令。
图3是示出该实施方式的指令控制部的功能结构的一个例子的框图。
在指令控制部1中，指令生成部11基于指令识别部13通过声音识别而生成的识别指令、以及辅助信息获取部16、状态获取部17获取的追加信息(辅助信息和状态信息)来生成执行指令，并从指令发送部18输出到指令控制部1的外部。以下，说明各功能模块。
指令生成部11在存储部111中存储有识别指令、追加信息、以及执行指令的组合(以下，称为条件组合表)。条件组合表(list)能够由用户预先设定。条件组合表既可以被装入在指令生成部11的计算机程序中，也可以例如经由网络500从外部的服务器下载。若向指令生成部11输入了识别指令和追加信息，则指令生成部11参照条件组合表来生成执行指令并输出。
声音检测部12例如是麦克风，接收用户发出的声音，通过采样(sampling)等来取得接收到的声音波形的声音数据，并输出。
指令识别部13根据声音检测部12输出的声音数据来实施声音识别，推定或者识别用户发出的指令，将识别指令作为文本数据进行输出。指令识别部13可以在其内部具备执行声音识别的声音数据处理部(声音识别引擎)，但也可以将声音数据发送到具备声音识别引擎(engine)的网络500上的声音识别装置400，从而取得识别指令。通过利用声音识别装置400，能够降低指令识别部13的制造成本等。另外，声音识别装置400通过从多个接收装置10取得声音数据并实施声音识别，从而声音识别装置400还具有取得学习效果从而能够实现声音识别的性能提高等好处。但是，因为为了使用声音识别装置400而经由网络500，所以具有声音识别的处理延迟较大这样的缺点，在这一点上，在利用指令识别部13的内部的声音识别引擎的情况下，具有声音识别的处理延迟较小的优点。另外，在图3中，示出了内置声音检测部12(扬声器)的例子，但是，也可以使用智能扬声器等。例如，将智能扬声器连接于接口105来使用。具体而言，也可以是，搭载有声音识别引擎的智能扬声器生成识别指令，指令控制部1(或者指令生成部11)例如经由接口105获取智能扬声器生成的识别指令。获取到的识别指令也可以在指令生成部11中用于生成执行指令。
用户接口部14例如是如个人电脑的键盘等那样能够进行文字输入的接口。具体而言，用户从用户接口部14将条件组合表设定在存储部111中。此外，也可以使用遥控器100、智能手机等将条件组合表设定在存储部111中。另外，也可以是，指令生成部11从设置于接收装置10的外部的未图示的提供条件组合表的服务器将条件组合表下载到存储部111。
接口部15与接口部105进行各种数据通信。具体而言，接口部15从接口部105接收辅助信息、状态信息。另外，接口部15对接口部105发送指令生成部11生成的执行指令。
辅助信息获取部16从辅助信息管理部91经由接口部15获取辅助信息。辅助信息获取部16例如也可以根据从指令识别部13输出识别指令的时刻，对辅助信息管理部91输出辅助信息的获取请求，从辅助信息管理部91获取辅助信息。
状态获取部17从状态信息管理部92经由接口部15获取状态信息。例如也可以是，根据指令识别部13输出识别指令的时刻或者指令生成部11接收识别指令的时刻，状态信息获取部17对状态信息管理部92输出状态信息的获取请求，并从状态信息管理部92获取状态信息。
指令发送部18将指令生成部11生成并输出的执行指令从接口部15向控制部90发送。另外，还能够经由通信部102发送到网络500上的装置、设备。
控制部19对指令控制部1内的各功能模块进行控制。此外，也可以设置为：在图3中，在与控制部19之间没有特别连线的功能模块之间也进行数据的交互(控制)。
声音分析部121对从声音检测部12输出的声音数据，例如实施频率分析(声波纹分析)，推测大人儿童、年龄、性别等声音源的属性从而得到声音源推测结果。声音分析部121对声音源推测结果实施所需的加工并作为辅助信息输出到辅助信息获取部16。另外，由声音分析部121取得的声音源推测结果也能够利用于是否启动指令生成部11、指令识别部13、指令发送部18等。也可以是，根据声音源推测结果，例如在发出了声音的用户是 儿童的情况下，为了使得不输出执行指令，而若声音分析部121将声音源推测结果输出到控制部19，则控制部19将指令生成部11、指令识别部13、指令发送部18的功能设为有效或设为无效。
图4是示出在该实施方式中能够通过声音指令控制的控制对象部位和控制对象部位的状态的一个例子的图。
从左侧的列起示出了“编号”、“控制对象部位”、“可取的状态值”、“声音指令”。“控制对象部位”是能够通过声音指令控制的接收装置10的部位。“可取的状态值”是“控制对象部位”的可取的状态。“声音指令”是在对“控制对象部位”切换状态值时用户发出的控制命令。
“编号”＝1表示作为接收装置10的“控制对象部位”的主电源部80的“可取的状态值”为开和关这2个状态。在此情况下，用于切换状态值的“声音指令”在使状态值成为开的情况下是“开电源”，在使状态值成为关的情况下是“关电源”。即，为了开电视机装置的电源，用户发音“开电源”，为了关电视机装置的电源，用户发音“关电源”。
“编号”＝2表示作为接收装置10的“控制对象部位”的输出控制部60的状态切换部62的“可取的状态值”为开和关这2个状态。即，为了开电视机装置的音量以便从扬声器部104输出声音，用户发音“开音量”，为了关电视机装置的音量以便不从扬声器部104输出声音(静音)，用户发音“关音量”。
“编号”＝3是处于正在将数字内容输出到显示部103、扬声器部104的状态的内容输出装置。内容输出装置是广播信号接收处理部20、内容处理部30、录像播放部40的总称。具体而言，“可取的状态值”的列中的“调谐器”相当于广播信号接收处理部20，“网络”相当于内容处理部30，“录像机”相当于录像播放部40。例如，为了使广播信号接收处理部20成为接收状态以便使显示部103、扬声器部104输出基于广播信号的内容，用户发音“调谐器”。为了使内容处理部30成为接收状态以便使显示部103、扬声器部104输出来自内容服务器装置200的内容，用户发音“网络”。为了使录像播放部40成为播放状态以便使显示部103、扬声器部104输出，用户发音“录像机”。
“编号”＝4是处于正在将数字内容输出到显示部103、扬声器部104的状态的调谐器。“可取的状态值”的BS、CS、地面数字分别表示BS数字广播、CS数字广播、地面数字电视广播(地面数字广播)的调谐器。例如，为了使BS数字广播成为接收状态以便使显示部103、扬声器部104输出BS数字广播的内容，用户发音“BS”。为了使CS数字广播成为接收状态以便使显示部103、扬声器部104输出CS数字广播的内容，用户发音“CS”。为了使地面数字广播成为接收状态以便使显示部103、扬声器部104输出地面数字广播的内容，用户发音“地面数字”。
“编号”＝5是内容输出装置正在向显示部103、扬声器部104输出的频道(节目)。“可取的状态值”的1ch、2ch、3ch表示频道编号。例如，在使1ch成为接收状态以便使显示部103、扬声器部104输出1ch的节目的情况下，用户发音“1ch”。对于其它频道也是同样的。此外，通常，也可以针对每个内容输出装置且针对每个调谐器定义频道。例如，在将内容输出装置设为广播信号接收处理部20的情况下，也可以针对调谐器“BS”、“CS”、“地面数字”的每一个分配频道编号。另外，也可以对内容输出装置的所有频道统一地分配固有的频道编号。在此情况下，能够根据该频道编号来确定内容输出装置的种类、调谐器的种类。
另外，作为“可取的状态值”，也可以具有“回归(home)(返回场所)”这种状态。“回归”是用户能够设定的状态值。
例如，在编号3的例子中，说明将“调谐器”设定为作为控制对象部位的内容输出装置的“回归”状态值的情况。例如，在用户收看内容输出装置“网络”的节目的途中，即内容输出装置的当前状态为“网络”时，用户作为声音指令进行“网络”的发音等，在指令识别部13中识别并生成“网络”作为识别指令。若将识别指令输入到指令生成部11，则指令生成部11生成用于将状态向作为“回归”的“调谐器”进行切换的执行指令“调谐器”并发送，将内容输出装置切换到“调谐器”。
例如，在编号4的例子中，说明将“地面数字”设定为作为控制对象部位的调谐器的“回归”状态值的情况。例如，在用户收看“BS”的调谐器的途中，即调谐器的当前状态为“BS” 时，用户作为声音指令进行“BS”发音等，在指令识别部13中识别并生成“BS”作为识别指令。若将识别指令输入到指令生成部11，则指令生成部11生成用于将状态向作为“回归”的“地面数字”进行切换的执行指令“地面数字”并发送，将调谐器切换到“地面数字”。
在编号5的例子中，说明将“1ch”设定为作为控制对象部位的频道的“回归”状态值的情况。例如，在用户收看“2ch”的频道的途中，即频道的当前状态为“2ch”时，用户作为声音指令进行“2ch”的发音等，在指令识别部13中识别并生成“2ch”作为识别指令。若将识别指令输入到指令生成部11，则指令生成部11生成用于将状态向作为“回归”的“1ch”进行切换的执行指令“1ch”并发送，将频道切换到“1ch”。
此外，上述的对“回归”状态值的设定既可以由用户设定，也可以自动设定为前次使电视机装置的电源成为关之前的状态值。另外，作为声音指令，也可以有“回归”。例如，也可以是，若用户将声音指令发音为“回归”，且作为识别指令生成“回归”，则状态转移到被设定为“回归”的状态值。
图5是示出在该实施方式中能够利用的辅助信息的一个例子的图。
从左侧的列起示出“编号”、“信息源”、“辅助信息”、“信息值”。“信息源”是“辅助信息”的发送源或者“辅助信息”的提取源(进行了提取的部位)。“辅助信息”是在本实施方式中指令控制部1制作执行指令的情况下利用的信息。“信息值”是“辅助信息”的值。
“编号”＝1表示作为“信息源”的接收装置10的时刻管理部93在辅助信息中包含时刻。
“编号”＝2表示根据声波纹来确定声音的发送源的属性，并在辅助信息中包含声音的发送源的属性，其中，通过作为“信息源”的接收装置10的声音分析部121实施声音分析而得到该声波纹。声音的发送源的属性例如是发送源的年龄、按年龄定义的大人儿童的分类、以及按年龄定义的婴儿、幼儿园儿童、小学生、中学生、高中生、大学生、社会人等分类即用户识别信息。
“编号”＝3表示根据声音识别结果来确定用户识别信息，并在辅助信息中包含用户识别信息的属性，其中，通过作为“信息源”的接收装置10的指令识别部13实施声音识别而得到该声音识别结果。
“编号”＝4、5、6分别表示根据声音的强度、声音的高度、声音的速度，来分别提供声音的强度的强弱、声音的高度的高低、声音的速度的快慢作为辅助信息，其中，通过作为“信息源”的接收装置10的声音分析部121实施声音分析而分别得到上述的声音的强度、声音的高度、声音的速度。
“编号”＝7表示作为“信息源”的接收装置10的传感器部70(例如照相机)根据用照相机获取到的图像识别结果来确定用户识别信息，在辅助信息中包含用户识别信息的属性。
“编号”＝8至11分别表示在辅助信息中包含作为“信息源”的接收装置10的广播信号接收处理部20从广播信号中提取出的“广播运营商”、“节目广播时间段”、“节目种类”、“节目名”。在“广播运营商”的情况下，例如将运营商A、运营商B、运营商C等运营商的名称作为辅助信息的值。在“节目广播时间段”的情况下，将广播时间段作为辅助信息的值。在“节目种类”的情况下，例如将戏剧、体育、音乐、新闻、教育、紧急信息等节目的种类作为辅助信息的值。在“节目名”的情况下，例如将节目A、节目B、节目C等节目的名称作为辅助信息的值。
“编号”＝12，在辅助信息中包含从作为“信息源”的收看解析装置300提供的解析结果取得的人口统计。
“编号”＝13至16分别表示在辅助信息中包含作为“信息源”的接收装置10的录像播放部40(可以还包含外置的录像机等)录像了节目时从广播波中提取出的“广播运营商”、“节目广播时间段”、“节目种类”、“节目名”。
“编号”＝17至20分别表示在辅助信息中包含从作为“信息源”的接收装置10的内容服务器装置200发送的内容中附带的信息中提取出的“发布运营商”、“节目广播时间段”、“节目种类”、“节目名”。另外，可以在辅助信息中包含录像了数字内容的用户(特别地称为录像管理者)。
(第1实施方式)
在本实施方式中，示出基于用户发出的声音指令和追加信息来控制接收装置的主电源的开-关的情况下的动作例。
图6是示出在该实施方式中用于指令控制部接收声音指令并发送执行指令的处理动作例的流程图。
用户为了控制接收装置10的主电源的开-关，而发出了声音指令“开电源”或者“关电源”。声音检测部检测声音(步骤S11中的是)。在声音检测部未检测到声音的情况下，等待到检测到声音(步骤S11的否)。声音检测部是检测到声音或未检测到的判断例如也可以是：对输入的声音的强度设定阈值，如果为阈值以上，则判断为检测到声音，如果小于阈值，则判断为未检测到声音。
声音检测部12将接收到的声音的声音数据输出到声音分析部121，声音分析部121对接收到的声音数据进行声音分析处理(步骤S12)。具体而言，声音分析部121对声音数据进行频率分析(声波纹分析)，推测声音的发送源的属性。
若声音分析部121将推测结果输出到控制部19，则控制部19根据推测结果来判断是否生成识别指令(步骤S13)。关于识别指令的生成可否的判断规则，也可以是用户从用户接口部14例如设定在存储部111中。控制部19访问存储部111来参照识别指令的生成的判断规则。控制部19在判断为实施识别指令的生成的情况下，使指令识别部13执行针对声音数据的声音识别(步骤S13中的是)。控制部19在判断为不实施识别指令的生成的情况下，进行控制，以使得使指令识别部13不进行针对声音数据的声音识别，将指令识别部13设置为等待状态直至检测下次的声音为止(步骤S13的否、S11)。也可以是，控制部19在判断为不实施识别指令的生成的情况下，例如使显示部103、扬声器部104输出“未进行识别指令的生成”等消息，通知用户。
若从控制部19对指令识别部13命令了识别指令的生成，则指令识别部13通过声音识别来取得作为文本数据的识别指令。指令识别部13将识别指令输出到指令生成部11(步骤S14)。在步骤S14中，也可以设置为：指令识别部13首先尝试用指令识别部13内具备的声音识别引擎来获取识别指令，在声音识别失败而未能获取到的情况下，利用声音识别的识别率更高的外部的声音识别装置400来获取识别指令。
指令生成部11若从指令识别部13接收到识别指令，则参照存储部111的条件组合表。
图7是示出在该实施方式中为了控制主电源而在指令控制部中设定的执行指令生成条件(组合条件表)的一个例子的图。
对于组合条件表的例子，从左侧的列起示出“编号”、“执行指令”、“识别指令”、“状态信息”、“辅助信息”。示出了以按各行中每一个记载的“识别指令”、“状态信息”、以及“辅助信息”作为条件，确定同一行中记载的“执行指令”。“识别指令”是指令识别部13生成并输出的识别指令。组合条件表例如也可以由用户从用户接口部14设定在存储部111中。图7所示的组合条件表是一个例子，还能够进一步追加辅助信息的数量(列的数量)。
返回到图6，说明指令控制部1的处理动作。若从指令识别部13向指令生成部11输入了例如“开电源”作为“识别指令”，则指令生成部11参照组合条件表，分别向辅助信息获取部16和状态信息获取部17命令获取作为表的列项目的“辅助信息”、“状态信息”。辅助信息获取部16向辅助信息管理部91请求并获取作为组合条件表的辅助信息的项目的“时刻”、“声音的强度”、“用户识别信息”，并输出到指令生成部11(步骤S15)。状态信息获取部17根据“识别指令”为“开电源”的情况而掌握控制对象为主电源80的情况，针对状态信息管理部92获取主电源80的状态信息，并输出到指令生成部11(步骤S16)。
指令生成部11参照组合条件表，查找获取到的辅助信息、状态信息、以及识别指令与组合条件表的条件的组合一致的行。在条件的组合一致的行中“执行指令”的项目中存在指令的情况下，将“执行指令”的项目中记载的指令作为执行指令来生成，并向指令发送部18输出(步骤S17、S18中的是，S19)。另一方面，例如，在如图7的编号8那样，条件的组合一致的“执行指令”的项目为“不发送”的情况下，不生成执行指令，指令控制部1等待下次检测到声音(步骤S17、S18的否)。在执行指令为“不发送”的情况下，指令控制部1也可以将包含“执行指令未发送或未生成”这种意思的消息发送到控制部90。接收到消 息的控制部90也可以在显示部103显示消息、或者从扬声器部104输出包含消息内容的声音，以通知用户。
另外，在条件的组合一致的“执行指令”的项目为“不发送”的情况下，指令控制部1也可以生成并发送“用于维持当前状态的执行指令”。例如，也可以是，在由声音分析部121对声音指令进行声波纹分析的结果是，作为用户识别信息将声音的发送源为“儿童”的辅助信息输入到指令生成部11的情况下，不使用识别指令，而仅用辅助信息来生成“用于维持当前状态的执行指令”并发送。在此情况下，指令生成部11也可以将包含“无法进行该操作”等这种意思的消息发送到控制部90。此时，接收到消息的控制部90也可以在显示部103显示消息、或者从扬声器部104输出包含消息内容的声音，以通知用户。
如果输入执行指令，则指令发送部18经由接口部15将执行指令发送到控制部90(步骤S101)。控制部90按照接收到的执行指令来对控制对象的功能进行控制。
也可以是，指令控制部1在生成或者发送了执行指令的情况下，将包含“发送了执行指令”这种内容的消息发送到控制部90。另外，也可以是，指令控制部1在识别指令与生成的执行指令不同的情况下，将包含“执行指令与识别指令不同”这一内容的消息发送到控制部90。也可以是，在指令控制部1中，使显示部103显示消息、或者从扬声器部104输出包含消息内容的声音，以通知用户。通过如上设置，用户能够确认自己发出的声音指令是否被正确地执行。
再次使用图7来说明组合条件表的细节。
在“编号”＝1的情况下，辅助信息均为“－”，这表示不使用辅助信息，是指令生成部11仅用状态信息和识别指令来生成执行指令的例子。在“编号”＝1的例子中，在“识别指令”为“开电源”、“状态信息”为“开”时，执行指令为“关电源”。对于“编号”＝2至4也是同样的，因此省略说明。
在“编号”＝5的情况下，为如下例子：在“识别指令”为“开电源”、“状态信息”为“开”、第1个“辅助信息”即“时刻”为“昼”、第2个“辅助信息”即“声音的强度”为“强”时，执行指令为“不发送(或者不生成)”。在此，作为“辅助信息”的“时刻”的值设为“昼”，但是，例如也可以是，辅助信息获取部16具有时刻与时刻分类值(朝、昼、夜)的对应关系，辅助信息获取部16根据获取到的“时刻”来判定对应的时刻分类值，并将时刻分类值(在编号＝5的情况下，昼)输出到指令生成部11。对于第2个“辅助信息”即“声音的强度”也是同样的。例如也可以是，辅助信息获取部16具有从声音分析部121输入的“声音的强度”与强度分类(强、弱)的对应关系，辅助信息获取部16根据接收到的“声音的强度”来判定对应的强度分类值，并将强度分类值(在编号＝5的情况下，强)输出到指令生成部11。对于“编号”＝6至12也是同样的，因此省略说明。如“编号”＝5至12那样，通过将“时刻”和“声音的强度”利用为辅助信息，从而能够将因在“昼”的时间段中周围的噪音变大导致声音识别引擎的精度会劣化而识别指令与用户的声音指令不同这种状况考虑在内地，生成执行指令。
在“编号”＝13的情况下，是如下的例子：在“识别指令”为“开电源”、“状态信息”为“开”、第1个“辅助信息”即“时刻”为“夜”、第2个“辅助信息”即“用户识别信息”为“大人”时，执行指令为“关电源”。与“编号”＝5同样地，例如也可以是，在声音分析部121将通过声波纹分析取得的声音指令的发送源的年龄输入到辅助信息获取部16的情况下，按照年龄与年龄分类值(大人、儿童)的对应关系，根据辅助信息获取部16接收到的“年龄”来判定对应的年龄分类值，并将年龄分类值(在编号＝13的情况下，大人)输出到指令生成部11。对于“编号”＝14至20也是同样的，因此省略说明。如“编号”＝13至20那样，通过利用“时刻”和“用户识别信息”作为辅助信息，从而在“夜”的时间段中因为周围的噪音较小而声音识别引擎的精度不会劣化，但是，能够在“夜”里用户想要限制执行指令的生成、发送这种场合下利用。
以上，按照图6的流程图的顺序，能够使用图7的条件组合表来生成执行指令。
在适用了图7中的条件组合表的“编号”＝1的条件的情况下，主电源的当前状态(相当于“状态信息”)为“开”。通常认为，在这样的状况下，用户发出“开电源”这种声音指令的可能性较小，反而，发出与当前状态“开”相反的“关电源”的声音指令的可能性更高。但 是，若因周围的噪音等导致“关电源”的声音指令由指令识别部13的声音识别引擎识别为“开电源”，则会发生尽管用户发音了“关电源”却无法将接收装置10的主电源设为关的事态，用户的压力变大。但是，根据本实施方式，在指令控制部1中，通过使用条件组合表的“编号”＝1的条件，基于接收装置10的状态信息来解释识别指令，从而能够防止这样的事态。同样，在指令控制部1中适用了条件组合表的“编号”＝2至4的情况下，在识别指令为切换主电源的当前状态(“状态信息”)这样的控制命令的情况下，使识别指令与执行指令的控制命令一致。相反，在识别指令为与“状态信息”相同状态的控制命令的情况下，执行指令的控制命令成为与识别指令相反的或者不同的控制命令。这样使其动作的原因在于，声音识别引擎尤其有较高可能性弄错开和关的声音的识别。在本实施方式中，考虑到用户为了使控制对象的当前状态与控制后的状态成为相同而发出声音指令的情况几乎不会存在这一点，使得能够辅助通过声音识别进行的对声音指令的解释。
在本实施方式中的图7的条件组合表中，在编号1至编号20中示出了用于确定执行指令的条件组合，但是，还能够对它们赋予优先权，使指令生成部11考虑优先权地参照条件组合表。也可以如图7那样按照编号1至编号20的行顺序来给予优先权。在此情况下，指令生成部11即使获取到了辅助信息，也因为编号1至编号4具有优先权，所以不使用辅助信息。另外，也可以设置为：在图7的表中另行追加示出优先顺序的列项目，使得用户能够在各行的条件组合中设定优先权。
另外，在“辅助信息”存在多个的情况下，也可以在“辅助信息”内给予优先权。例如，在图7的组合条件表中，对于辅助信息，例如按照“时刻”、“声音的强度”、“用户识别信息”的顺序赋予较高的优先权。在此情况下，指令生成部11例如在组合条件表中从放入有优先权较高的辅助信息的条件组合起进行参照。具体而言，用户也可以如下这样设定：辅助信息对仅有“时刻”的条件组合给予最高的优先权，接下来，对仅有“时刻”和“声音的强度”的条件组合给予优先权，接下来，对仅有“时刻”和“用户识别信息”的条件组合给予优先权。
另外，也可以是，通过用户对“时刻”、“声音的强度”、“用户识别信息”设定表示优先度的分数，从而使指令生成部11计算对“时刻”、“声音的强度”、“用户识别信息”赋予的分数的总和，从分数的总和的较高者起另行进行优先顺序设置为高等从而对各组合条件表给予优先权。在此情况下，指令生成部11能够计算优先顺序，因此，用户只要对“时刻”、“声音的强度”、“用户识别信息”设定表示优先度的分数即可。
另外，希望将组合条件表所示的条件组合设定为基本上没有成为相同条件的组合。在存在成为相同条件的组合的情况下，也可以预先确定使指令生成部11按表顺序进行选择等规则。
(第2实施方式)
在本实施方式中，示出利用用户发出的声音指令、状态信息、以及作为辅助信息的节目种类和用户识别信息，对接收装置10的扬声器部104输出的音量的开-关进行控制的情况下的指令控制部1的动作例。此外，在本实施方式中，设置为主电源为开的状态。
图8是示出在第2实施方式中为了控制音量而在指令控制部中设定的执行指令生成条件的一个例子的图。此外，使用图6来说明用于本实施方式中的指令控制部1接收声音指令并发送执行指令的处理动作的例子，但是，对于与第1实施方式同样的部分省略说明。
用户为了控制接收装置10的扬声器部104的音量输出的开-关，而发出了声音指令“开音量”或者“关音量”。声音检测部检测声音(步骤S11中的是)。声音分析处理的结果，控制部19判断为生成识别指令，使指令识别部13执行针对声音数据的声音识别(步骤S13中的是)。指令识别部13通过声音识别取得作为文本数据的识别指令，将识别指令输出到指令生成部11(步骤S14)。
指令生成部11若从指令识别部13接收到识别指令，则参照存储部111的条件组合表。若从指令识别部13输入了“开音量”作为“识别指令”，则指令生成部11参照组合条件表，命令辅助信息获取部16和状态信息获取部17分别获取作为表的列项目的“辅助信息”、“状态信息”。辅助信息获取部16向辅助信息管理部91请求并获取组合条件表中的作为辅助信息的项目的“节目种类”、“用户识别信息”，并输出到指令生成部11(步骤S15)。状态信 息获取部17根据“识别指令”为“开音量”的情况而掌握控制对象为主电源80的情况，从状态信息管理部92获取扬声器部104的状态信息，并输出到指令生成部11(步骤S16)。
指令生成部11参照组合条件表，在获取到的辅助信息、状态信息、以及识别指令的组合一致的行的“执行指令”的项目中存在指令的情况下，将“执行指令”的项目中记载的指令作为执行指令来生成，并向指令发送部18输出(步骤S17、S18中的是，S19)。另一方面，在“执行指令”的项目为“不发送”的情况下，不进行执行指令的生成，指令控制部1等待检测下次的声音(步骤S17、S18的否)。若输入执行指令，则指令发送部18将执行指令从接口部15发送到控制部90(步骤S101)。
使用图8来说明组合条件表的细节。
在“编号”＝1的情况下，由于“状态信息”为“开”，所以表示当前“音量”为输出状态。“编号”＝1的条件组合是如下例子：“识别指令”为“开音量”，第1个“辅助信息”即“节目种类”为“紧急信息”，第2个“辅助信息”即“用户识别信息”为“－”(无条件)时，指令生成部11生成“不发送(或者不生成)”作为执行指令。关于“编号”＝2至4，也是同样的，因此省略说明。如“编号”＝1至4那样，作为辅助信息，利用“节目种类”，在“节目种类”为“紧急信息”的情况下，能够考虑在所有的状况下想要使音量成为开(ON)这种请求。例如，在广播信号接收处理部20接收广播信号中发生了地震等的情况下，在偶尔已将音量设为了关时，用户为了使音量成为开而敏捷地输出“开音量”的声音指令。但是，设想在地震等紧急时周围的噪音变大，用户发出的声音指令被错误地识别的可能性较高。在这样的情况下，作为辅助信息获取部16获取到的辅助信息的“节目种类”，若获取了“紧急信息”，则指令生成部11与接收到的“识别指令”、控制对象的“状态信息”无关地，始终使音量成为开。
“编号”＝5至12是使用“用户识别信息”作为辅助信息的例子。例如，在昼间的时间段等中想要避免儿童用接收装置10收看数字内容这种情况下，能够利用“编号”＝5至12那样的条件组合。
以上，如本实施方式这样，用户通过设定组合条件表，从而设想各种各样的用例，能够对声音指令进行指令控制。
(第3实施方式)
在本实施方式中，示出接收装置10利用用户发出的声音指令、状态信息、以及作为辅助信息的用户识别信息和时刻，对向显示部103、扬声器部104输出的数字内容进行控制的情况下的指令控制部1的动作例。此外，在本实施方式中，设想了主电源为开的状态。另外，在本实施方式中，示出对于1个声音指令，输出2个执行指令的例子。
图9是示出在第3实施方式中为了控制数字内容接收而在指令控制部中设定的执行指令生成条件的一个例子的图。
此外，使用图6的流程图说明本实施方式中的用于指令控制部1接收声音指令并发送执行指令的处理动作例，但是，对于与第1实施方式同样的部分省略说明。
假设用户为了控制数字内容向接收装置10的显示部103、扬声器部104的输出，而发出了声音指令“网络”、“调谐器”或者“录像机”的任意一个。声音检测部检测声音(步骤S11中的是)。经过步骤S12、S13，指令识别部13通过声音识别而取得作为文本数据的识别指令，并将识别指令输出到指令生成部11(步骤S14)。
若从指令识别部13输入“识别指令”，则指令生成部11参照存储部111的条件组合表，命令辅助信息获取部16和状态信息获取部17分别获取作为表的列项目的“辅助信息”、“状态信息”。辅助信息获取部16向辅助信息管理部91请求并获取作为组合条件表的辅助信息的项目的“用户识别信息”、“时刻”，并输出到指令生成部11(步骤S15)。状态信息获取部17根据“识别指令”来掌握控制对象为内容输出装置的情况，从状态信息管理部92获取扬声器部104的状态信息，并输出到指令生成部11(步骤S16)。
指令生成部11经过步骤17至S19而生成执行指令，并向指令发送部18输出。从指令发送部18将执行指令发送到控制部90(步骤S101)。在本实施方式中，生成2个执行指令。是针对内容输出装置的第1执行指令和针对节目种类的第2执行指令。
使用图9来说明组合条件表的细节。
在“编号”＝1的情况下，由于内容输出装置的“状态信息”为“调谐器”，所以表示当前“调谐器”正在向显示部103、扬声器部104进行输出。“编号”＝1的条件组合是如下例子：在指令生成部11接收到的识别指令为“网络”、第1个辅助信息即用户识别信息为“大人”时，指令生成部11生成用于从作为内容输出装置之一的“网络”向显示部103、扬声器部104进行输出的执行指令。关于“编号”＝2、3也是同样的，因此省略说明。
在“编号”＝4的情况下，由于内容输出装置的“状态信息”为“调谐器”，所以表示当前“调谐器”正在向显示部103、扬声器部104进行输出。“编号”＝4的条件组合是如下例子：在指令生成部11接收到的识别指令为“网络”、第1个辅助信息即用户识别信息为“儿童”、第2个辅助信息即时刻为“昼”时，指令生成部11为了不从作为内容输出装置之一的“网络”向显示部103、扬声器部104进行输出，而不生成或者发送执行指令。“编号”＝4的状况例如能够利用于如下场合：在昼间的时间段等中想要避免儿童用接收装置10收看来自“网络”的数字内容。
另外，在“编号”＝9的情况下，由于内容输出装置的“状态信息”为“录像机”，所以表示当前“录像机”正在向显示部103、扬声器部104进行输出。“编号”＝9的条件组合中，在指令生成部11接收到的识别指令为“网络”、第1个辅助信息即用户识别信息为“儿童”、第2个辅助信息即时刻为“夜”时，指令生成部11生成“网络”和作为针对节目种类的执行指令的“教育”这2个，作为执行指令。将生成的2个执行指令从指令发送部18发送到控制部90，使由“网络”进行发布服务的关于“教育”的节目向显示部103、扬声器部104输出。“编号”＝9的状况例如能够利用于如下场合：在夜间的时间段中儿童想要用接收装置10观看“网络”的情况下，想要设置为收看节目种类为“教育”的数字内容。
另外，例如，假设在用户收看BS中，即，控制对象部位“调谐器”的状态信息为“BS”时，用户进行了“BS”的发音等作为声音指令，指令识别部13生成“BS”作为识别指令，并输出到指令生成部11。若输入识别指令，则指令生成部11生成并发送向控制对象部位“调谐器”的“回归”中设定的状态值(假设是“地面数字”)切换的执行指令“地面数字”。控制部90接收执行指令“地面数字”，并将调谐器切换到“地面数字”。此时，也可以设置为：对于向显示部103、扬声器104输出的频道(节目)，选择作为控制对象部位的“频道(节目)”中设定的“回归”的状态值。即，在该例子的情况下，指令生成部11对于用户发出的1个针对控制对象部位的声音指令(或者识别该声音指令而取得的识别指令)，针对“调谐器”和“频道(节目)”这些多个控制对象部位生成执行指令。对“频道(节目)”设定的“回归”例如既可以设为在前次使电视机装置的电源成为关之前正在收看的频道，也可以设为用户预先设定的频道。另外，也可以不区分针对不同的控制对象部位的执行指令，而设为1个执行指令。
以上，如本实施方式这样，用户通过设定组合条件表，从而能够从1个声音指令生成多个执行指令并发送和执行。
(第4实施方式)
在本实施方式中，示出将指令控制部1作为一个独立的装置来利用的情况下的系统的例子。
图10是示出第3实施方式的系统整体的构成例的图。
在网络500上连接有指令控制装置2、以及IoT设备600A、IoT设备600B。IoT设备600A和IoT设备600B具备同样的功能，在不特别区别两者的情况下，将IoT设备600A和IoT设备600B称为IoT设备600。IoT设备600在图10中仅示出了2个，但可以设置有多个。
指令控制装置2例如被构筑在具有CPU、存储器等的计算机中。指令控制装置2既可以是个人计算机，也可以是包含服务器、数据库等的云服务。指令控制装置2包含指令控制部1和通信部102A。指令控制部1、通信部102A分别相当于图3中的指令识别部1、通信部102的功能。
IoT设备600是所有种类的IoT设备，与网络500连接，与网络500上的装置实施数据通信。IoT设备600例如既可以是温度检测传感器、漏水检测传感器、门开闭传感器等传感器类，也可以是使用了这些传感器的检测装置。另外，IoT设备600也可以是空调、 电视机装置、照明、照相机等家电。另外，如果与网络500连接，则也可以是智能手机那样的移动终端。本实施方式中的IoT设备600对指令控制装置2提供辅助信息和状态信息，接收指令控制装置2输出的执行指令，并根据接收到的执行指令来控制IoT设备600的功能。
具体而言，IoT设备600包含辅助信息输出部21A、状态切换部22A、控制部90A、辅助信息管理部91A、状态信息管理部92A、通信部102A、接口部105A。各自的功能相当于图2中的辅助信息输出部21、状态切换部82、控制部90、辅助信息管理部91、状态信息管理部92、通信部102、接口部105的功能。
即，也可以说将图2的各功能分配给指令控制装置2和IoT设备600A。第1实施方式中示出的接收装置10与本实施方式中示出的IoT设备600的较大差异在于，在接收装置10中在内部具备指令控制部1，但是，在IoT设备600中不具备指令控制部1。在本实施方式中，指令控制部1被配备于指令控制装置2，IoT设备600经由网络500从指令控制装置2接收执行指令。
指令控制装置2能够控制的IoT设备600的控制对象部位例如既可以是第1至第3实施方式中示出的电源(开-关)，此外，还可以是其他的对功能部位的起动和停止进行控制。
指令控制装置2对IoT设备600发送执行指令的顺序能够利用图6的流程图。对于与第1实施方式、第2实施方式同样的顺序省略详细说明。
用户在指令控制装置2的附近，经由网络500对IoT设备600A远程地进行控制。用户对指令控制装置2的指令控制部1设定针对IoT设备600A的执行指令生成条件(组合条件表)。
用户为了控制IoT设备600A的功能，而对指令控制装置2的声音检测部12发出了声音指令。声音检测部12检测声音，经过由声音分析部121进行的声音分析处理，指令识别部13生成识别指令，并将识别指令输出到指令生成部11(步骤S11中的是、S12、S13中的是、S14)。
若从指令识别部13输入识别指令，则指令生成部11参照组合条件表，命令辅助信息获取部16和状态信息获取部17分别获取作为表的列项目的“辅助信息”、“状态信息”。辅助信息获取部16向辅助信息管理部91A请求并获取组合条件表的辅助信息的各个项目，并输出到指令生成部11(步骤S15)。详细说明本实施方式中的步骤S15。
辅助信息获取部16经由通信部102A向IoT设备600A请求辅助信息。在IoT设备600A中，控制部90A经由通信部102A2接收辅助信息的请求。控制部90A从辅助信息管理部91A获取辅助信息，并将获取到的辅助信息经由通信部102A2发送到指令控制装置2。
状态信息获取部17根据识别指令掌握控制对象，经由通信部102A向IoT设备600A请求控制对象的状态信息。在IoT设备600A中，控制部90A经由通信部102A2接收状态信息的请求。控制部90A从状态信息管理部92A获取状态信息，并将获取到的状态信息经由通信部102A2发送到指令控制装置2。在指令控制装置2中，指令生成部11经由通信部102A接收状态信息(步骤S16)。
指令生成部11参照组合条件表，在与获取到的辅助信息、状态信息以及识别指令的组合一致的条件的“执行指令”的项目中存在指令的情况下，生成“执行指令”的项目中记载的指令作为执行指令，并向指令发送部18输出(步骤S17、S18中的是，S19)。另一方面，在“执行指令”的项目为“不发送”的情况下，不进行执行指令的生成，指令控制部1等待下一次的声音的检测(步骤S17、S18中的否)。在此情况下，也可以是，指令控制部1对于包含“不发送指令”等“未发送执行指令或未生成”这种意思的消息，使消息在指令控制装置2的未图示的显示部上显示，或者使包含消息内容的声音从指令控制装置2的未图示的扬声器部输出，从而通知用户。
指令发送部18将输入的执行指令经由通信部102A发送到IoT设备600A(步骤S101)。在IoT设备600A中，按照接收到的执行指令来对控制的功能进行控制。也可以是，指令控制部1在生成或者发送了执行指令的情况下，对于包含“发送了执行指令”这种意思的消息，使消息在指令控制装置2的未图示的显示部上显示，或者使包含消息内容的声音从指 令控制装置2的未图示的扬声器部输出，从而通知用户。另外，也可以是，指令控制装置2在识别指令与生成的执行指令不同的情况下，对于包含“执行指令与识别指令不同”这种内容的消息，使消息在指令控制装置2的未图示的显示部上显示，或者使包含消息内容的声音从指令控制装置2的未图示的扬声器部输出，从而通知用户。通过如上设置，用户能够确认自己发出的声音指令的意图是否被准确地执行。
用户若按照以上的顺序对连接于网络500的指令控制装置2发出了声音指令，则能够利用执行指令来控制连接于网络500的IoT设备600。
根据以上所述的至少1个实施方式，能够提供辅助针对声音指令的声音识别的指令生成装置、生成方法及生成程序。
在以上的实施方式中，示出了在作为控制对象装置的接收装置10、IoT设备600上设置控制部90(包含辅助信息管理部91、状态信息管理部92)的功能的例子，但是，也可以将控制部90的功能的全部或一部分设置为控制对象的外部的控制装置等。在此情况下，控制装置也连接于网络500。对于指令控制装置也同样，关于装置内的功能和执行该功能的硬件可以想到各种构成、组合，并不限定于以上示出的实施方式的例子。
(变形例)
在本变形例中，例如示出如下例子：通过使用图5的“用户识别信息”、“时间段”作为辅助信息，从而使得儿童的收看限制、操作限制等家长控制(Parental Control)成为可能。设置成操作电视机装置的遥控器等由大人管理。
具体而言，在儿童发出了声音指令的情况下，利用声音分析部121进行声波纹分析，在辅助信息获取部16中获取“儿童”作为用户识别信息，并输入到指令生成部11。同时，将该声音指令输入到指令识别部13，生成了识别指令，并输入到指令生成部11。指令生成部11例如基于识别指令“关电源”、辅助信息“儿童”来生成“关电源”作为执行指令，并输出到控制部90。另一方面，指令生成部11从辅助信息获取部16获取了“儿童”作为用户识别信息，并获取了“深夜”作为时间段。在此情况下，也可以是，指令生成部11仅根据“儿童”和“深夜”这种辅助信息，例如生成“用于维持当前状态的执行指令”。
虽然图5中未图示，但是，也可以通过将“节目收看对象”等也一并用作辅助信息，从而能够进行家长控制。例如，指令识别部13根据儿童发出的声音指令来识别出控制对象部位为“频道(节目)”。若指令识别部13将包含识别出的控制对象部位在内的识别信息输出到辅助信息获取部16，则辅助信息获取部16从广播信号接收处理部20等获取识别信息中包含的针对控制对象部位“频道(节目)”的辅助信息即“节目收看对象”，并输出到指令生成部11。指令生成部11基于从声音分析部121取得的用户识别信息即“儿童”和“节目收看对象”这2个辅助信息来生成执行指令。例如，在节目收看对象中包含“儿童”的情况下，将识别指令直接生成为执行指令。另外，在节目收看对象中不包含“儿童”的情况下，例如生成“用于维持当前状态的执行指令”。
以上，根据本变形例，能够进行针对声音指令的家长控制。另外，根据本变形例，在识别指令、状态信息、辅助信息中，能够不使用识别指令而是仅根据基于声音指令获取到的辅助信息来生成执行指令。
根据以上所述的至少1个实施方式、变形例，能够提供辅助针对声音指令的声音识别的指令控制装置、控制方法及控制程序。
上述的本装置还能够如下这样记载。
(A－1)
一种电子装置(指令控制部1或者指令控制装置2)，其具备动作控制机构(指令生成部11)，该动作控制机构根据输入的声音(声音指令)获取动作控制信息(识别指令)，并将控制对象装置(接收装置10)的动作状态设置为第1模式、或与第1模式不同的第2模式中的任一个动作状态，
在所述控制对象装置的动作状态为第1模式、且所述动作控制信息为与所述第1模式下的动作状态相关的信息时，将所述动作状态设置为所述第2模式。
(A－2)
根据(A－1)所述的电子装置，获取与所述控制对象装置的控制对象部位的状态相关的动作状态信息(状态信息)。
(A－3)
根据(A－1)或(A－2)所述的电子装置，获取与所述动作控制信息及所述动作状态信息不同的控制条件信息(辅助信息)。
(A－4)
根据(A－3)所述的电子装置，所述控制条件信息是基于时间段、用户识别信息、用户属性、接收内容信息、广播运营商、发布运营商及录像内容管理者的组中的至少任意一者设定的信息。
(A－5)
一种程序，用于使计算机执行从输入的声音(声音指令)获取动作控制信息(识别指令)、并将控制对象装置(接收装置10)的动作状态设置为第1模式或与第1模式不同的第2模式的任一个动作状态的操作，
在所述控制对象装置的动作状态为第1模式、且所述动作控制信息为与所述第1模式下的动作状态相关的信息时，将所述动作状态设置为所述第2模式。
说明了本申请的几个实施方式，但是，这些实施方式是作为例子而示出的，并不意图限定申请的范围。这些新的实施方式能够以其它的各种各样的形态来实施，在不脱离申请的主旨的范围内，能够进行各种省略、替换、变更。这些实施方式、其变形包含在申请的范围、主旨中，并且包含在权利要求书中记载的发明及与其等同的范围中。进一步，另外，在技术方案的各构成要素中，即使在将构成要素分割而表述的情况、或者将多个合并而表述的情况、或者将它们组合而表述的情况下，也属于本申请的范畴。另外，也可以将多个实施方式组合，通过该组合构成的实施例也属于申请的范畴。
另外，附图为了使得说明更清楚，而有的情况下，与实际的形态相比，对于各部的宽度、厚度、形状等示意性表示。在框图中，对于未连线的模块间或者即使连线而未示出箭头的方向，有的情况下也进行数据、信号的交互。框图中所示的各功能、流程图、序列图所示的处理也可以通过硬件(IC芯片等)或者软件(程序等)或者硬件和软件的组合来实现。另外，在将技术方案表述为控制逻辑的情况、表述为包含使计算机执行的指令在内的程序的情况、以及表述为记载有上述指令的计算机可读取的存储介质的情况下，也是应用了本申请的装置的技术方案。另外，对于使用的名称、用语，没有限定，即使是其它表述，只要实质上是相同内容、相同主旨，则也包含在本申请中。

Claims (10)

  1. 一种指令控制装置，基于输入的声音来生成包含针对控制对象的控制命令在内的执行指令，
    所述指令控制装置，生成包含第1控制命令和与所述第1控制命令不同的第2控制命令中的任一者在内的执行指令，其中，所述第1控制命令是对所述声音进行声音识别而获取的识别指令中所包含的控制命令。
  2. 根据权利要求1所述的指令控制装置，其中，
    所述指令控制装置，基于所述识别指令和追加信息来生成所述执行指令。
  3. 根据权利要求2所述的指令控制装置，其中，
    所述指令控制装置，基于所述识别指令和所述追加信息来确定是否生成所述执行指令。
  4. 根据权利要求2所述的指令控制装置，其中，
    所述指令控制装置，基于所述识别指令和所述追加信息来确定是否发送所述执行指令。
  5. 根据权利要求2至4中任一项所述的指令控制装置，其中，
    所述追加信息包含状态信息，所述状态信息是由所述执行指令控制的所述控制对象的控制状态。
  6. 根据权利要求2至4中任一项所述的指令控制装置，其中，
    所述追加信息包含辅助信息，所述辅助信息并非所述控制对象的控制状态。
  7. 根据权利要求2至4中任一项所述的指令控制装置，其中，
    所述追加信息包含状态信息和辅助信息，所述状态信息是由所述执行指令控制的所述控制对象的控制状态，所述辅助信息并非所述控制对象的控制状态。
  8. 根据权利要求2所述的指令控制装置，其中，
    所述指令控制装置具备：
    声音识别部，其识别所述声音，获取所述识别指令；
    追加信息获取机构，其获取所述追加信息；
    存储机构，其存储所述识别指令、所述追加信息、以及所述执行指令的对应关系；以及
    执行指令生成机构，其根据所述对应关系生成所述执行指令。
  9. 一种指令控制方法，基于输入的声音来生成包含针对控制对象设备的控制命令在内的执行指令，
    生成包含第1控制命令和与所述第1控制命令不同的第2控制命令中的任一者在内的执行指令，其中，所述第1控制命令是对所述声音进行识别而获取的识别指令中所包含的控制命令。
  10. 一种非易失性存储介质，其存储有控制程序，所述控制程序使计算机基于输入的声音而生成包含针对控制对象设备的控制命令在内的执行指令，其中，
    生成包含第1控制命令和与所述第1控制命令不同的第2控制命令中的任一者在内的执行指令，其中，所述第1控制命令是对所述声音进行识别而获取的识别指令所包含的控制命令。
PCT/CN2020/128811 2019-12-06 2020-11-13 指令控制装置、控制方法及非易失性存储介质 WO2021109839A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202080005756.9A CN113228166B (zh) 2019-12-06 2020-11-13 指令控制装置、控制方法及非易失性存储介质

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019-221573 2019-12-06
JP2019221573A JP7229906B2 (ja) 2019-12-06 2019-12-06 コマンド制御装置、制御方法および制御プログラム

Publications (1)

Publication Number Publication Date
WO2021109839A1 true WO2021109839A1 (zh) 2021-06-10

Family

ID=76221412

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/128811 WO2021109839A1 (zh) 2019-12-06 2020-11-13 指令控制装置、控制方法及非易失性存储介质

Country Status (3)

Country Link
JP (1) JP7229906B2 (zh)
CN (1) CN113228166B (zh)
WO (1) WO2021109839A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070282611A1 (en) * 2006-05-31 2007-12-06 Funai Electric Co., Ltd. Electronic Equipment and Television Receiver
CN103442138A (zh) * 2013-08-26 2013-12-11 华为终端有限公司 语音控制方法、装置及终端
CN105609103A (zh) * 2015-12-18 2016-05-25 合肥寰景信息技术有限公司 一种语音即时识别系统
CN108882014A (zh) * 2018-06-13 2018-11-23 成都市极米科技有限公司 智能电视儿童桌面的管理方法、管理装置和可读存储介质

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FI973093A (fi) * 1997-07-23 1999-01-24 Nokia Mobile Phones Ltd Menetelmä telepalvelun ohjaamiseksi ja päätelaite
JPH11119792A (ja) * 1997-10-20 1999-04-30 Toyota Motor Corp 音声認識機能付き機器制御装置および音声認識装置
JP4363076B2 (ja) * 2002-06-28 2009-11-11 株式会社デンソー 音声制御装置
JP3724461B2 (ja) * 2002-07-25 2005-12-07 株式会社デンソー 音声制御装置
JP5556529B2 (ja) * 2010-09-16 2014-07-23 株式会社デンソー 車載音声認識装置
JP6779659B2 (ja) * 2015-07-21 2020-11-04 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ 制御方法および制御装置
CN109819297A (zh) * 2017-11-22 2019-05-28 中国移动通信有限公司研究院 一种操作控制方法及机顶盒
CN108766424A (zh) * 2018-05-28 2018-11-06 深圳市天乔科技有限公司 智能家居智能语音学习控制方法
CN109448721A (zh) * 2018-12-20 2019-03-08 西安Tcl软件开发有限公司 语音控制方法、系统、云服务器及语音设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070282611A1 (en) * 2006-05-31 2007-12-06 Funai Electric Co., Ltd. Electronic Equipment and Television Receiver
CN103442138A (zh) * 2013-08-26 2013-12-11 华为终端有限公司 语音控制方法、装置及终端
CN105609103A (zh) * 2015-12-18 2016-05-25 合肥寰景信息技术有限公司 一种语音即时识别系统
CN108882014A (zh) * 2018-06-13 2018-11-23 成都市极米科技有限公司 智能电视儿童桌面的管理方法、管理装置和可读存储介质

Also Published As

Publication number Publication date
CN113228166A (zh) 2021-08-06
CN113228166B (zh) 2023-02-28
JP2021092612A (ja) 2021-06-17
JP7229906B2 (ja) 2023-02-28

Similar Documents

Publication Publication Date Title
US9219949B2 (en) Display apparatus, interactive server, and method for providing response information
US11676595B2 (en) Information processing device, reception device, and information processing method
US8629940B2 (en) Apparatus, systems and methods for media device operation preferences based on remote control identification
US9900663B2 (en) Display apparatus and control method thereof
US11227620B2 (en) Information processing apparatus and information processing method
US8798311B2 (en) Scrolling display of electronic program guide utilizing images of user lip movements
US20070216538A1 (en) Method for Controlling a Media Content Processing Device, and a Media Content Processing Device
US8600732B2 (en) Translating programming content to match received voice command language
US20150341694A1 (en) Method And Apparatus For Using Contextual Content Augmentation To Provide Information On Recent Events In A Media Program
US12035006B2 (en) Electronic apparatus having notification function, and control method for electronic apparatus
US20110154387A1 (en) Television authorizing system for playing media content and authorizing method thereof
US20240171815A1 (en) Systems and methods for facilitating voice interaction with content receivers
KR20160090123A (ko) 선호채널 설정 장치 및 방법
US20130177288A1 (en) Electronic device and audio output method
WO2021109839A1 (zh) 指令控制装置、控制方法及非易失性存储介质
KR102673375B1 (ko) 사용자의 발화를 기반으로 컨텐츠를 제공하는 장치 및 시스템
KR20100030474A (ko) 서비스 정보 제공방법 및 그 장치
US8407742B2 (en) System and method for reserving preference event of broadcasting program
US11343588B2 (en) Information processing apparatus, information processing method, transmission apparatus, and transmission method
KR20150084276A (ko) 인터넷 프로토콜 텔레비전(iptv)을 제어하는 방법 및 디지털 방송 수신기
WO2021155812A1 (zh) 接收装置、服务器以及语音信息处理系统
JP7242423B2 (ja) 映像信号処理装置、映像信号処理方法
KR102156356B1 (ko) 방송 수신 장치
KR101510892B1 (ko) 통합 멀티뷰어 제어 방법 및 장치
TWI244870B (en) Digital television and method of broadcasting broadcast signals

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20895675

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20895675

Country of ref document: EP

Kind code of ref document: A1