WO2019221001A1 - Processing system and program - Google Patents

Processing system and program Download PDF

Info

Publication number
WO2019221001A1
WO2019221001A1 PCT/JP2019/018539 JP2019018539W WO2019221001A1 WO 2019221001 A1 WO2019221001 A1 WO 2019221001A1 JP 2019018539 W JP2019018539 W JP 2019018539W WO 2019221001 A1 WO2019221001 A1 WO 2019221001A1
Authority
WO
WIPO (PCT)
Prior art keywords
keyword
voice
devices
unit
state
Prior art date
Application number
PCT/JP2019/018539
Other languages
French (fr)
Japanese (ja)
Inventor
池部　早人
藤井　寿隆
康司 笠嶋
雅章 東城
Original Assignee
パナソニックＩｐマネジメント株式会社
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 パナソニックＩｐマネジメント株式会社 filed Critical パナソニックＩｐマネジメント株式会社
Publication of WO2019221001A1 publication Critical patent/WO2019221001A1/en

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
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • 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
    • G10L15/08—Speech classification or search
    • G10L15/10—Speech classification or search using distance or distortion measures between unknown speech and reference templates
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom

Definitions

  • This disclosure relates to a processing system and a program for executing processing based on sound.
  • voice recognition is used in the remote control device.
  • one device can be operated based on one voice.
  • data indicating a life scene and data indicating the contents of an operation command output to each device are stored in association with the recognized sound. For example, “Wake up” is stored as a life scene in association with the voice “Good morning”, “On” is output as an operation command to be output to an air conditioner, “On” is output as an operation command to be output to a television, and output to a lighting device “On” is stored as the operation command (see, for example, Patent Document 1).
  • the present disclosure has been made in view of such a situation, and an object thereof is to provide a technique for simplifying the setting.
  • a processing system receives a message generated by recognizing a voice including an instruction to store the state of one or more devices and a keyword.
  • the processing system includes a reception unit that receives voice information corresponding to the voice from an operation device that receives a voice including an instruction to store the state of one or more devices and a keyword, and one or more devices An acquisition unit that acquires the state of the information, and a control unit that recognizes the voice information received in the reception unit and stores the state acquired in the acquisition unit while associating the state with a keyword.
  • the setting can be simplified.
  • FIG. 1 is a diagram illustrating a configuration of a remote control system according to a first embodiment. It is a figure which shows the structure of the control system of FIG. It is a figure which shows the data structure of the table memorize
  • the embodiment relates to a remote operation system for remotely operating a device installed in a consumer such as a house.
  • the device can perform communication using ECHONET Lite (registered trademark), which is one of communication protocols in an energy management system (EMS).
  • EMS energy management system
  • Such equipment includes housing equipment, home appliances, building / store equipment, ie, lighting, air conditioning, refrigeration, power equipment, general white goods, sensors, actuators, and the like.
  • the devices here include, for example, air conditioners, televisions, and lighting devices.
  • An operation device such as a smart speaker is used to operate such a device.
  • the operating device includes a microphone and is disposed in a house.
  • a terminal device such as a smartphone may be used instead of the operation device.
  • the user utters an instruction for controlling the device to the operation device as a voice.
  • the controller device converts the sound into an electric signal, and transmits the sound converted into the electric signal (hereinafter referred to as “voice information”) to the voice recognition server device.
  • voice recognition server device generates a message indicating an instruction to control the device by executing voice recognition on the voice information received from the operation device.
  • the message generated in the voice recognition server device is transmitted to the control system via the router in the house.
  • the control system is connected to the device by ECHONET Lite (registered trademark), and controls the device according to an instruction indicated in the message. At this time, the control system also receives identification information for identifying the terminal device together with the message from the terminal device, and controls the device when the authentication for the identification information is successful.
  • ECHONET Lite registered trademark
  • the remote control system executes the following process.
  • the user utters “Remember as a good morning scene” to the terminal device.
  • the voice recognition server device generates and transmits a message including the keyword “good morning” and an instruction to store the status of one or more devices from the corresponding voice information.
  • the control system receives a message from the terminal device, the control system recognizes the keyword “good morning” and an instruction to store the state of one or more devices.
  • the control system acquires the status of one or more devices according to the recognized instruction.
  • the control system stores the keyword and the acquired state of one or more devices in association with each other.
  • FIG. 1 shows the configuration of the remote operation system 1000.
  • the remote operation system 1000 includes an operation device 100, a router 110, a voice recognition server device 120, a conversion server device 130, a control system 200, a first device 300a, a second device 300b, and an Nth device 300n, which are collectively referred to as a device 300.
  • the operation device 100, the router 110, the control system 200, and the device 300 are arranged in a consumer such as a house.
  • the voice recognition server device 120 and the conversion server device 130 are arranged outside a consumer such as a house.
  • FIG. 1 the inside of the consumer is indicated as being in the space, and the outside of the consumer is indicated as being outside the space.
  • (1) normal control, (2) scene storage, and (3) scene control will be described in this order.
  • Normal control is a process of controlling one device 300 with one voice uttered by a user.
  • the operating device 100 corresponds to the above-described smart speaker and is arranged in a space.
  • the operation device 100 is a device including at least a microphone, a processing unit, and a communication unit (not shown).
  • the microphone of the operation device 100 receives the voice uttered by the user who is the speaker.
  • An example of the voice is an instruction to control the device 300.
  • the instruction to control the device 300 includes the name of the device 300 to be controlled and the content of control for the device 300, such as “turn on the air conditioner”.
  • the processing unit of the controller device 100 generates sound information by converting sound received by the microphone into an electric signal.
  • the communication unit of the controller device 100 transmits voice information to the voice recognition server device 120 via the router 110. At that time, the communication unit also transmits identification information for identifying the controller device 100 to the voice recognition server device 120 via the router 110.
  • the router 110 is installed in a space, and separates a local area network including the space and a network outside the space.
  • the router 110 transmits the voice information and identification information received from the operation device 100 to the voice recognition server device 120.
  • the voice recognition server device 120 is installed outside the space and receives voice information and identification information.
  • the voice recognition server device 120 performs voice recognition on the voice information. Since a known technique may be used for the speech recognition, the description is omitted here.
  • the voice recognition server device 120 acquires the name of the device 300 to be controlled and the control content for the device 300.
  • the control content for the device 300 corresponds to an instruction to control the device 300.
  • the voice recognition server device 120 generates a message including the name of the device 300 and the control content.
  • the voice recognition server device 120 recognizes the correspondence between the identification information and the control system 200 that is the message destination, and identifies the message destination from the received identification information.
  • the voice recognition server device 120 transmits a message and identification information to the specified destination. At least a part of the functions provided in the speech recognition server device 120 may be provided in a device in the space, for example, the operation device 100 or another device connected to the operation device 100.
  • the conversion server device 130 is installed outside the space and is connected to the voice recognition server device 120. As described above, the voice recognition server device 120 generates a message, but the content of the message is different for each manufacturer that manufactures the control system 200, for example. The conversion server device 130 recognizes the manufacturer that manufactures the control system 200 that is the destination of the message, and converts the message generated in the voice recognition server device 120 according to the manufacturer. If the messages in each manufacturer are common, the conversion server device 130 may not be included in the remote operation system 1000. The conversion server device 130 transmits a message and identification information to the control system 200 as a destination via the router 110.
  • the control system 200 is installed in a space, connected to the router 110, and connected to a plurality of devices 300. It can be said that the control system 200 is a gateway in the space.
  • the control system 200 may be composed of a single device or a plurality of devices connected to each other. In the former case, it can be said that the control system 200 is a control device. Below, it demonstrates as the control system 200 irrespective of the number of apparatuses.
  • the control system 200 receives a message and identification information from the conversion server device 130 via the router 110.
  • the control system 200 executes an authentication process for the identification information. Since a known technique may be used for the authentication process, the description thereof is omitted here. When the authentication fails, the control system 200 ends the process. On the other hand, when the authentication is successful, the control system 200 extracts the name of the device 300 and the control content from the message.
  • the control system 200 communicates with each device 300 according to a predetermined communication protocol.
  • a predetermined communication protocol is ECHONET Lite (registered trademark) as described above.
  • the control system 200 transmits a control signal in order to control the device 300 according to the extracted control content.
  • a known technique may be used for transmission of such a control signal.
  • Scene storage The remote operation system 1000 defines scene control in addition to normal control.
  • Scene control is processing for controlling a plurality of devices 300 when a user utters a keyword associated with a scene. For example, when the scene is “getting up”, the keyword is “good morning”. This corresponds to a process of controlling the plurality of devices 300 with one voice uttered by the user.
  • the scene storage is a process to be executed in advance before executing the scene control, and is a process for storing the keyword and the control contents of the plurality of devices 300 in association with each other.
  • the microphone of the operation device 100 receives the voice uttered by the user who is the speaker.
  • An example of voice is an instruction to store the state of one or more devices 300.
  • the instruction to store the state of one or more devices 300 includes a keyword corresponding to the scene and an instruction to store the state of one or more devices 300, such as “remember as a good morning scene”. .
  • “good morning” corresponds to a keyword
  • “remember as a scene” corresponds to “an instruction to store the state of one or more devices 300”.
  • the processing unit of the controller device 100 generates sound information by converting sound received by the microphone into an electric signal.
  • the communication unit of the controller device 100 transmits voice information and identification information to the voice recognition server device 120 via the router 110.
  • the voice recognition server device 120 receives voice information and identification information.
  • the voice recognition server device 120 performs voice recognition on the voice information as before. Since a known technique may be used for the speech recognition, the description is omitted here.
  • the voice recognition server device 120 acquires a keyword “good morning” and an instruction to store the state of one or more devices 300.
  • the voice recognition server device 120 generates a message including a keyword and an instruction for storing the state of one or more devices 300.
  • the voice recognition server device 120 transmits a message and identification information as before.
  • FIG. 2 shows the configuration of the control system 200.
  • the control system 200 includes a network side communication unit 210, a processing system 400, and a device side communication unit 240.
  • the processing system 400 includes a reception unit 214, a control unit 220, a storage unit 230, and an acquisition unit 244.
  • the network side communication unit 210 receives a message and identification information from the conversion server device 130 via the router 110.
  • the network side communication unit 210 outputs a message and identification information to the control unit 220.
  • the reception unit 214 receives a message and identification information from the network side communication unit 210. This is equivalent to receiving a message generated by recognizing a voice including an instruction for storing the state of one or more devices 300 and a keyword.
  • the accepting unit 214 outputs the message and the identification information to the control unit 220.
  • the control unit 220 receives a message and identification information from the reception unit 214. As described above, the control unit 220 executes an authentication process for the identification information. When the authentication process is successful, the control unit 220 extracts an instruction for storing the state of one or more devices 300 and a keyword from the message.
  • the control unit 220 determines acquisition of the current state of each device 300 according to an instruction to store the state of one or more devices 300.
  • the device-side communication unit 240 performs communication with each device 300 according to a predetermined communication protocol, for example, ECHONET Lite (registered trademark).
  • the device side communication unit 240 may be configured integrally with the network side communication unit 210.
  • the control unit 220 determines to acquire the current state of each device 300
  • the device-side communication unit 240 accesses each device 300 and acquires the current state of each device 300.
  • the device-side communication unit 240 transmits a command indicating an instruction to transmit the current state to each device 300, and each device 300 transmits the current state according to the command.
  • the device-side communication unit 240 outputs the acquired current state of each device 300 to the acquisition unit 244.
  • the acquisition unit 244 acquires the current state of one or more devices 300 from the device-side communication unit 240.
  • the device-side communication unit 240 accesses each device 300, so that the device-side communication unit 240 has one or more devices 300. Get the current state of. However, before the control unit 220 determines acquisition of the current state of each device 300, the device-side communication unit 240 periodically accesses each device 300, so that the acquisition unit 244 has one or more devices 300. You may get the current state of. The acquisition unit 244 outputs the current state of the one or more devices 300 to the control unit 220.
  • the control unit 220 causes the storage unit 230 to store the current state of the one or more devices 300 received from the acquisition unit 244 and the extracted keyword in association with each other. That is, the control unit 220 stores the state acquired by the acquisition unit 244 in association with the keyword based on the message received by the reception unit 214.
  • FIG. 3 shows the data structure of the table stored in the storage unit 230.
  • the state “ON” of the first device 300a, the state “ON” of the second device 300b, the state “ON” of the third device 300c, and the like are stored in association with “good morning” which is an example of a keyword.
  • As the state of the device 300 a set temperature or the like may be indicated in addition to “ON” and “OFF”.
  • the microphone of the operation device 100 in FIG. 1 receives the voice uttered by the user who is the speaker.
  • An example of the voice includes a keyword such as “Good morning”.
  • the processing unit of the controller device 100 generates sound information by converting sound received by the microphone into an electric signal.
  • the communication unit of the controller device 100 transmits voice information and identification information to the voice recognition server device 120 via the router 110.
  • the voice recognition server device 120 receives voice information and identification information.
  • the voice recognition server device 120 performs voice recognition on the voice information as before. Since a known technique may be used for the speech recognition, the description is omitted here.
  • the voice recognition server device 120 acquires the keyword “good morning”.
  • the voice recognition server device 120 generates a message including the keyword.
  • the voice recognition server device 120 transmits a message and identification information as before.
  • the network side communication unit 210 receives a message and identification information from the conversion server device 130 via the router 110.
  • the network side communication unit 210 outputs the message and the identification information to the reception unit 214.
  • the receiving unit 214 receives a message and identification information from the network side communication unit 210. This is equivalent to accepting another message generated by recognizing the voice including the keyword.
  • the accepting unit 214 outputs the message and the identification information to the control unit 220.
  • the control unit 220 receives a message and identification information from the reception unit 214.
  • the control unit 220 executes an authentication process for the identification information. When the authentication process is successful, the control unit 220 extracts a keyword from the message.
  • the control unit 220 refers to the table stored in the storage unit 230 and acquires the state of each device 300 stored in association with the extracted keyword. For example, when the extracted keyword is “good morning”, the control unit 220 refers to the table of FIG. 3 to determine the state “on” of the first device 300a, the state “on” of the second device 300b, the third The state “ON” or the like of the device 300c is acquired.
  • the control unit 220 controls each device 300 so as to be in the state of each device 300 via the device-side communication unit 240. That is, the device-side communication unit 240 transmits a control signal that causes the state of each device 300 to each device 300.
  • the subject of the apparatus, system, or method in the present disclosure includes a computer.
  • the computer executes the program, the main function of the apparatus, system, or method according to the present disclosure is realized.
  • the computer includes a processor that operates according to a program as a main hardware configuration.
  • the processor may be of any type as long as the function can be realized by executing the program.
  • the processor includes one or a plurality of electronic circuits including a semiconductor integrated circuit (IC) or an LSI (Large Scale Integration).
  • the plurality of electronic circuits may be integrated on one chip or provided on a plurality of chips.
  • the plurality of chips may be integrated into one device, or may be provided in a plurality of devices.
  • the program is recorded on a non-transitory recording medium such as a ROM, an optical disk, or a hard disk drive that can be read by a computer.
  • the program may be stored in advance in a recording medium, or may be supplied to the recording medium via a wide area communication network including the Internet.
  • FIG. 4 is a flowchart showing a storing procedure by the control system 200.
  • the receiving unit 214 receives a storage instruction and a keyword (S10).
  • the acquisition unit 244 acquires the state of each device 300 (S12).
  • the control unit 220 stores the keyword and state in the storage unit 230 in association with each other (S14).
  • FIG. 5 is a flowchart showing a control procedure by the control system 200.
  • the reception unit 214 receives a keyword (S50).
  • the control unit 220 acquires the state associated with the keyword from the storage unit 230 (S52).
  • the storage unit 230 controls the device 300 to be in the acquired state via the device side communication unit 240 (S54).
  • the state of the one or more devices 300 is received. Since these are acquired and stored in association with each other, the setting can be simplified. Moreover, since the setting is simplified, the setting according to the user's preference can be executed. In addition, since one or more devices 300 are controlled so as to be stored in association with a keyword when another message generated by recognizing the voice including the keyword is received, the one or more devices 300 are controlled. A plurality of devices 300 can be controlled with one voice.
  • the outline of one aspect of the present disclosure is as follows.
  • the processing system 400 includes a reception unit 214 that receives a message generated by recognizing a voice including an instruction to store the state of one or more devices 300 and a keyword, and 1
  • An acquisition unit 244 that acquires the states of two or more devices 300
  • a control unit 220 that stores the states acquired by the acquisition unit 244 in association with keywords based on the messages received by the reception unit 214.
  • the reception unit 214 receives another message generated by recognizing the voice including the keyword, and the control unit 220 extracts the keyword from the other message received by the reception unit 214 and extracts the extracted keyword.
  • One or more devices 300 are controlled so as to be stored in association with each other.
  • Example 2 relates to a remote operation system that controls a plurality of devices by speaking a keyword.
  • the control system 200 stores the keyword and the state of each device 300 in association with each other.
  • the voice recognition server device 120 stores the keyword and the state of each device 300 in association with each other.
  • the remote operation system 1000 according to the second embodiment is the same type as that shown in FIG. Here, it demonstrates centering on the difference with Example 1.
  • FIG. 1 shows that shows that shown in FIG. Here, it demonstrates centering on the difference with Example 1.
  • FIG. 6 shows the configuration of the voice recognition server device 120.
  • the speech recognition server device 120 includes a communication unit 10, a recognition unit 30, and a processing system 400.
  • the processing system 400 includes a reception unit 20, an acquisition unit 40, a control unit 50, and a storage unit 60.
  • the communication unit 10 is connected to the router 110 and the conversion server device 130 in FIG. 1 and performs communication with them.
  • the communication unit 10 receives voice information and identification information from the operation device 100 via the router 110.
  • the receiving unit 20 receives voice information from the communication unit 10. This corresponds to receiving voice information corresponding to a voice including an instruction to store the state of one or more devices 300 and a keyword.
  • the recognition unit 30 performs voice recognition on the voice information received by the reception unit 20. Through the voice recognition, the voice recognition server device 120 acquires a keyword “good morning” and an instruction to store the state of one or more devices 300. The recognizing unit 30 outputs a keyword “Good morning” and an instruction to store the state of one or more devices 300 to the control unit 50.
  • the control unit 50 performs the same processing as the control unit 220, and determines acquisition of the current state of each device 300 according to an instruction to store the state of one or more devices 300.
  • the control unit 50 accesses each device 300 via the communication unit 10, the router 110, and the control system 200, and determines acquisition of the current state of each device 300.
  • the communication unit 10 accesses each device 300 and acquires the current state of each device 300.
  • the communication unit 10 transmits a command indicating an instruction to transmit the current state to each device 300 via the control system 200, and each device 300 transmits the current state according to the command.
  • the communication unit 10 outputs the acquired current state of each device 300 to the acquisition unit 40.
  • the acquisition unit 40 performs the same processing as the acquisition unit 244 and acquires the current state of one or more devices 300 from the communication unit 10.
  • the communication unit 10 accesses each device 300 so that the communication unit 10 has the current state of one or more devices 300. Is getting.
  • the acquisition unit 40 periodically accesses each device 300 so that the acquisition unit 40 acquires the current status of one or more devices 300. You may acquire the state of.
  • the acquisition unit 40 outputs the current state of the one or more devices 300 to the control unit 50.
  • the control unit 50 stores the current state of the one or more devices 300 received from the acquisition unit 40 and the keyword in the storage unit 60 in association with each other.
  • the table stored in the storage unit 60 is the same as the table stored in the storage unit 230.
  • the operation device 100 in FIG. 1 is the same as that in the first embodiment, and transmits voice information and identification information to the voice recognition server device 120 via the router 110.
  • FIG. 6 is used to describe the processing of the speech recognition server device 120.
  • the communication unit 10 receives voice information and identification information from the controller device 100 via the router 110.
  • the receiving unit 20 receives voice information from the communication unit 10. This corresponds to receiving another voice information corresponding to the voice from the operation device 100 that has received the voice including the keyword.
  • the recognition unit 30 performs voice recognition on the voice information received by the reception unit 20.
  • the recognition unit 30 acquires the keyword “good morning” through the speech recognition.
  • the recognizing unit 30 outputs a keyword “Good morning” and an instruction to store the state of one or more devices 300 to the control unit 50.
  • the control unit 50 refers to the table stored in the storage unit 60 and acquires the state of each device 300 stored in association with the extracted keyword.
  • the control part 50 produces
  • the control unit 50 transmits a message and identification information to the control system 200 via the communication unit 10 and the router 110. This corresponds to controlling one or more devices 300 so as to be stored in association with the acquired keyword.
  • the conversion server device 130 executes the same processing as before, and the control system 200 receives a message and identification information from the conversion server device 130 via the router 110.
  • the control system 200 executes an authentication process for the identification information.
  • the control system 200 extracts information on the state of each device 300 to be controlled from the message.
  • the control system 200 transmits a control signal for controlling each device 300 so that each device 300 is in a state.
  • the status of the one or more devices 300 is acquired. Since these are stored in association with each other, the setting can be simplified. Moreover, since the setting is simplified, the setting according to the user's preference can be executed. In addition, when another voice information corresponding to the voice including the keyword is recognized, one or more devices 300 are controlled so as to be stored in association with the keyword. The device 300 can be controlled.
  • the outline of one aspect of the present disclosure is as follows.
  • Another aspect of the present disclosure is also a processing system 400.
  • the processing system 400 includes a receiving unit 20 that receives voice information corresponding to the voice from the operation device 100 that receives a voice including an instruction to store the state of one or more devices 300 and a keyword.
  • An acquisition unit 40 that acquires the states of two or more devices 300, and a control unit 50 that stores the states acquired in the acquisition unit 40 while associating them with keywords by recognizing the voice information received in the reception unit 20.
  • the receiving unit 20 receives another voice information corresponding to the voice from the operation device 100 that has received the voice including the keyword, and the control unit 50 recognizes the other voice information received by the receiving unit 20 as a voice.
  • the keyword is acquired, and the one or more devices 300 are controlled so as to be stored in association with the acquired keyword.
  • the setting can be simplified.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Telephonic Communication Services (AREA)
  • Selective Calling Equipment (AREA)

Abstract

A processing system 400 includes a reception unit 214, an acquisition unit 244, and a control unit 220. The reception unit 214 receives a message generated by recognizing a speech which includes a keyword and an instruction for storing the states of one or more devices. The acquisition unit 244 acquires the states of one or more devices. The control unit 220 causes the states acquired by the acquisition unit 244 to be stored in association with the keyword on the basis of the message received by the reception unit 214.

Description

処理システム、プログラムProcessing system, program
　本開示は、音声をもとに処理を実行する処理システム、プログラムに関する。 This disclosure relates to a processing system and a program for executing processing based on sound.
　遠隔操作装置との間の通信によって運転が操作される機器の操作性を容易にするために、遠隔操作装置において音声認識が利用される。このような技術では、１つの音声に基づいて１つの機器が操作可能である。１つの音声に基づいて複数の機器を操作するために、認識される音声に対応づけて、生活シーンを示すデータと各機器に出力する動作指令の内容を示すデータが格納される。例えば「おはよう」という音声に対応づけて、生活シーンとして「起床」が格納され、さらに、エアコンに出力する動作指令として「オン」、テレビに出力する動作指令として「オン」、照明機器に出力する動作指令として「オン」が格納される（例えば、特許文献１参照）。 In order to facilitate the operability of equipment that is operated by communication with the remote control device, voice recognition is used in the remote control device. In such a technique, one device can be operated based on one voice. In order to operate a plurality of devices based on one sound, data indicating a life scene and data indicating the contents of an operation command output to each device are stored in association with the recognized sound. For example, “Wake up” is stored as a life scene in association with the voice “Good morning”, “On” is output as an operation command to be output to an air conditioner, “On” is output as an operation command to be output to a television, and output to a lighting device “On” is stored as the operation command (see, for example, Patent Document 1).
国際公開第１４／０３０５４０号International Publication No. 14/030540
　１つの音声に基づいて複数の機器の動作を制御する場合、各機器の設定はユーザによって異なる。そのため、１つの音声に対する各機器の設定はユーザによってなされるべきである。そのような状況下において、設定は簡易である方が望ましい。 ∙ When controlling the operation of multiple devices based on a single voice, the settings of each device differ from user to user. Therefore, the setting of each device for one voice should be made by the user. Under such circumstances, it is desirable that the setting is simple.
　本開示はこうした状況に鑑みなされたものであり、その目的は、設定を簡易にする技術を提供することにある。 The present disclosure has been made in view of such a situation, and an object thereof is to provide a technique for simplifying the setting.
　上記課題を解決するために、本開示のある態様の処理システムは、１つ以上の機器の状態を記憶させる指示と、キーワードとが含まれた音声を音声認識することによって生成されたメッセージを受けつける受付部と、１つ以上の機器の状態を取得する取得部と、受付部において受けつけたメッセージをもとに、取得部において取得した状態をキーワードに関連づけながら記憶させる制御部と、を備える。 In order to solve the above problems, a processing system according to an aspect of the present disclosure receives a message generated by recognizing a voice including an instruction to store the state of one or more devices and a keyword. A reception unit; an acquisition unit that acquires a state of one or more devices; and a control unit that stores the state acquired in the acquisition unit in association with a keyword based on a message received in the reception unit.
　本開示の別の態様もまた、処理システムである。この処理システムは、１つ以上の機器の状態を記憶させる指示と、キーワードとが含まれた音声を受けつけた操作装置から、当該音声に応じた音声情報を受けつける受付部と、１つ以上の機器の状態を取得する取得部と、受付部において受けつけた音声情報を音声認識することによって、取得部において取得した状態をキーワードに関連づけながら記憶させる制御部と、を備える。 Another aspect of the present disclosure is also a processing system. The processing system includes a reception unit that receives voice information corresponding to the voice from an operation device that receives a voice including an instruction to store the state of one or more devices and a keyword, and one or more devices An acquisition unit that acquires the state of the information, and a control unit that recognizes the voice information received in the reception unit and stores the state acquired in the acquisition unit while associating the state with a keyword.
　なお、以上の構成要素の任意の組合せ、本開示の表現を方法、装置、システム、コンピュータプログラム、またはコンピュータプログラムを記録した記録媒体などの間で変換したものもまた、本開示の態様として有効である。 It should be noted that any combination of the above-described constituent elements, the expression of the present disclosure converted between methods, apparatuses, systems, computer programs, or recording media on which the computer programs are recorded are also effective as an aspect of the present disclosure. is there.
　本開示によれば、設定を簡易にできる。 設定 According to the present disclosure, the setting can be simplified.
実施例１に係る遠隔操作システムの構成を示す図である。1 is a diagram illustrating a configuration of a remote control system according to a first embodiment. 図１の制御システムの構成を示す図である。It is a figure which shows the structure of the control system of FIG. 図２の記憶部に記憶されるテーブルのデータ構造を示す図である。It is a figure which shows the data structure of the table memorize | stored in the memory | storage part of FIG. 図２の制御システムによる記憶手順を示すフローチャートである。It is a flowchart which shows the memory | storage procedure by the control system of FIG. 図２の制御システムによる制御手順を示すフローチャートである。It is a flowchart which shows the control procedure by the control system of FIG. 実施例２に係る音声認識サーバ装置の構成を示す図である。It is a figure which shows the structure of the speech recognition server apparatus which concerns on Example 2. FIG.
（実施例１）
　本開示の実施例を具体的に説明する前に、本実施例の概要を説明する。実施例は、住宅等の需要家内に設置される機器を遠隔から操作する遠隔操作システムに関する。機器は、例えば、電力制御システム（ＥＭＳ：Ｅｎｅｒｇｙ　Ｍａｎａｇｅｍｅｎｔ　Ｓｙｓｔｅｍ）における通信プロトコルの１つであるＥＣＨＯＮＥＴ　Ｌｉｔｅ（登録商標）による通信を実行可能である。このような機器は、住宅設備機器、家電製品、ビル・店舗設備機器、すなわち照明、空調、冷蔵、電力設備、一般白物家電製品、センサ、アクチュエータなどを含む。ここでの機器には、例えば、エアコン、テレビ、照明機器が含まれる。 Example 1
Before specifically describing the embodiment of the present disclosure, an outline of the present embodiment will be described. The embodiment relates to a remote operation system for remotely operating a device installed in a consumer such as a house. For example, the device can perform communication using ECHONET Lite (registered trademark), which is one of communication protocols in an energy management system (EMS). Such equipment includes housing equipment, home appliances, building / store equipment, ie, lighting, air conditioning, refrigeration, power equipment, general white goods, sensors, actuators, and the like. The devices here include, for example, air conditioners, televisions, and lighting devices.
　このような機器の操作には、スマートスピーカのような操作装置が使用される。操作装置は、マイクロフォンを備えており、住宅内に配置される。操作装置の代わりに、スマートフォン等の端末装置が使用されてもよい。ユーザは、機器の制御の指示を音声として操作装置に発話する。操作装置は、音声を電気信号に変換して、電気信号に変換された音声（以下、「音声情報」という）を音声認識サーバ装置に送信する。音声認識サーバ装置は、操作装置から受信した音声情報に対して音声認識を実行することによって、機器の制御の指示が示されたメッセージを生成する。音声認識サーバ装置において生成されたメッセージは、住宅内のルータを経由して制御システムに送信される。制御システムは、ＥＣＨＯＮＥＴ　Ｌｉｔｅ（登録商標）によって機器を接続しており、メッセージにおいて示された指示に応じて機器を制御する。その際、制御システムは、メッセージとともに、端末装置を識別するための識別情報も端末装置から受信し、識別情報に対する認証が成功した場合に、機器を制御する。 An operation device such as a smart speaker is used to operate such a device. The operating device includes a microphone and is disposed in a house. A terminal device such as a smartphone may be used instead of the operation device. The user utters an instruction for controlling the device to the operation device as a voice. The controller device converts the sound into an electric signal, and transmits the sound converted into the electric signal (hereinafter referred to as “voice information”) to the voice recognition server device. The voice recognition server device generates a message indicating an instruction to control the device by executing voice recognition on the voice information received from the operation device. The message generated in the voice recognition server device is transmitted to the control system via the router in the house. The control system is connected to the device by ECHONET Lite (registered trademark), and controls the device according to an instruction indicated in the message. At this time, the control system also receives identification information for identifying the terminal device together with the message from the terminal device, and controls the device when the authentication for the identification information is successful.
　このような処理によれば、ユーザが操作装置に対して「エアコンをオンにする」と発話すれば、エアコンの電源がオンにされる。つまり、１つの音声によって１つの機器が制御される。前述のごとく、１つの音声によって複数の機器を制御するために、例えば、「おはよう」という１つの音声に対して複数の機器の制御が関連づけられる。このような制御を実行するためには、１つの音声のキーワードに対する各機器の制御内容が関連づけて設定されている。このような設定は、ユーザの好みに応じてユーザによってなされるべきであるので、設定が簡易である方が好ましい。そのために、本実施例に係る遠隔操作システムは、次の処理を実行する。 According to such processing, when the user speaks “turn on the air conditioner” to the operation device, the power of the air conditioner is turned on. That is, one device is controlled by one voice. As described above, in order to control a plurality of devices with one voice, for example, control of a plurality of devices is associated with one voice “Good morning”. In order to execute such control, the control contents of each device are set in association with one voice keyword. Since such a setting should be made by the user according to the user's preference, it is preferable that the setting is simple. Therefore, the remote control system according to the present embodiment executes the following process.
　ユーザは、端末装置に対して「おはようのシーンとして覚えて」と発話する。音声認識サーバ装置は、これに対応した音声情報から、「おはよう」というキーワードと、１つ以上の機器の状態を記憶させる指示が含まれたメッセージを生成して送信する。制御システムは、端末装置からのメッセージを受信すると、「おはよう」というキーワードと、１つ以上の機器の状態を記憶させる指示とを認識する。制御システムは、認識した指示に応じて、１つ以上の機器の状態を取得する。制御システムは、キーワードと、取得した１つ以上の機器の状態とを関連づけながら記憶する。 The user utters “Remember as a good morning scene” to the terminal device. The voice recognition server device generates and transmits a message including the keyword “good morning” and an instruction to store the status of one or more devices from the corresponding voice information. When the control system receives a message from the terminal device, the control system recognizes the keyword “good morning” and an instruction to store the state of one or more devices. The control system acquires the status of one or more devices according to the recognized instruction. The control system stores the keyword and the acquired state of one or more devices in association with each other.
　図１は、遠隔操作システム１０００の構成を示す。遠隔操作システム１０００は、操作装置１００、ルータ１１０、音声認識サーバ装置１２０、変換サーバ装置１３０、制御システム２００、機器３００と総称される第１機器３００ａ、第２機器３００ｂ、第Ｎ機器３００ｎを含む。ここで、操作装置１００、ルータ１１０、制御システム２００、機器３００は、住宅等の需要家内に配置される。一方、音声認識サーバ装置１２０、変換サーバ装置１３０は、住宅等の需要家外に配置される。図１では、需要家内がスペース内と示され、需要家外がスペース外と示される。以下では、（１）通常制御、（２）シーン記憶、（３）シーン制御の順に説明する。 FIG. 1 shows the configuration of the remote operation system 1000. The remote operation system 1000 includes an operation device 100, a router 110, a voice recognition server device 120, a conversion server device 130, a control system 200, a first device 300a, a second device 300b, and an Nth device 300n, which are collectively referred to as a device 300. . Here, the operation device 100, the router 110, the control system 200, and the device 300 are arranged in a consumer such as a house. On the other hand, the voice recognition server device 120 and the conversion server device 130 are arranged outside a consumer such as a house. In FIG. 1, the inside of the consumer is indicated as being in the space, and the outside of the consumer is indicated as being outside the space. Hereinafter, (1) normal control, (2) scene storage, and (3) scene control will be described in this order.
（１）通常制御
　通常制御とは、ユーザによって発声された１つの音声によって１つの機器３００を制御する処理である。操作装置１００は、前述のスマートスピーカに相当し、スペース内に配置される。操作装置１００は、図示しないマイクロフォンと処理部と通信部を少なくとも含む装置である。操作装置１００のマイクロフォンは、発話者であるユーザが発話した音声を受けつける。音声の一例は、機器３００の制御の指示である。機器３００の制御の指示では、「エアコンをオンにする」のように、制御対象となる機器３００の名称と、当該機器３００に対する制御内容が含まれる。操作装置１００の処理部は、マイクロフォンで受けつけた音声を電気信号に変換することによって音声情報を生成する。操作装置１００の通信部は、ルータ１１０を介して音声認識サーバ装置１２０に音声情報を送信する。その際、通信部は、操作装置１００を識別するための識別情報も、ルータ１１０を介して音声認識サーバ装置１２０に送信する。 (1) Normal control Normal control is a process of controlling one device 300 with one voice uttered by a user. The operating device 100 corresponds to the above-described smart speaker and is arranged in a space. The operation device 100 is a device including at least a microphone, a processing unit, and a communication unit (not shown). The microphone of the operation device 100 receives the voice uttered by the user who is the speaker. An example of the voice is an instruction to control the device 300. The instruction to control the device 300 includes the name of the device 300 to be controlled and the content of control for the device 300, such as “turn on the air conditioner”. The processing unit of the controller device 100 generates sound information by converting sound received by the microphone into an electric signal. The communication unit of the controller device 100 transmits voice information to the voice recognition server device 120 via the router 110. At that time, the communication unit also transmits identification information for identifying the controller device 100 to the voice recognition server device 120 via the router 110.
　ルータ１１０は、スペース内に設置され、スペースを含むローカルエリアのネットワークと、スペース外のネットワークとを分離する。ルータ１１０は、操作装置１００から受信した音声情報と識別情報とを音声認識サーバ装置１２０に送信する。 The router 110 is installed in a space, and separates a local area network including the space and a network outside the space. The router 110 transmits the voice information and identification information received from the operation device 100 to the voice recognition server device 120.
　音声認識サーバ装置１２０は、スペース外に設置され、音声情報と識別情報とを受信する。音声認識サーバ装置１２０は、音声情報に対して音声認識を実行する。音声認識には公知の技術が使用されればよいので、ここでは説明を省略する。音声認識によって、音声認識サーバ装置１２０は、制御対象となる機器３００の名称と、当該機器３００に対する制御内容を取得する。機器３００に対する制御内容は、機器３００の制御の指示に相当する。音声認識サーバ装置１２０は、機器３００の名称と、制御内容とが含まれたメッセージを生成する。また、音声認識サーバ装置１２０は、識別情報と、メッセージの宛先となる制御システム２００との対応関係を認識しており、受信した識別情報からメッセージの宛先を特定する。音声認識サーバ装置１２０は、特定した宛先に、メッセージと識別情報とを送信する。音声認識サーバ装置１２０が備える機能の少なくとも一部は、スペース内の装置、例えば、操作装置１００や、操作装置１００に接続される他の装置が備えていてもよい。 The voice recognition server device 120 is installed outside the space and receives voice information and identification information. The voice recognition server device 120 performs voice recognition on the voice information. Since a known technique may be used for the speech recognition, the description is omitted here. Through the voice recognition, the voice recognition server device 120 acquires the name of the device 300 to be controlled and the control content for the device 300. The control content for the device 300 corresponds to an instruction to control the device 300. The voice recognition server device 120 generates a message including the name of the device 300 and the control content. The voice recognition server device 120 recognizes the correspondence between the identification information and the control system 200 that is the message destination, and identifies the message destination from the received identification information. The voice recognition server device 120 transmits a message and identification information to the specified destination. At least a part of the functions provided in the speech recognition server device 120 may be provided in a device in the space, for example, the operation device 100 or another device connected to the operation device 100.
　変換サーバ装置１３０は、スペース外に設置され、音声認識サーバ装置１２０に接続される。前述のごとく、音声認識サーバ装置１２０はメッセージを生成するが、メッセージの内容は、例えば、制御システム２００を製造するメーカ毎に異なる。変換サーバ装置１３０は、メッセージの宛先となる制御システム２００を製造するメーカを認識しており、当該メーカに応じて、音声認識サーバ装置１２０において生成されたメッセージを変換する。各メーカにおけるメッセージが共通である場合、変換サーバ装置１３０は遠隔操作システム１０００に含まれなくてもよい。変換サーバ装置１３０は、ルータ１１０を介して宛先となる制御システム２００に、メッセージと識別情報とを送信する。 The conversion server device 130 is installed outside the space and is connected to the voice recognition server device 120. As described above, the voice recognition server device 120 generates a message, but the content of the message is different for each manufacturer that manufactures the control system 200, for example. The conversion server device 130 recognizes the manufacturer that manufactures the control system 200 that is the destination of the message, and converts the message generated in the voice recognition server device 120 according to the manufacturer. If the messages in each manufacturer are common, the conversion server device 130 may not be included in the remote operation system 1000. The conversion server device 130 transmits a message and identification information to the control system 200 as a destination via the router 110.
　制御システム２００は、スペース内に設置され、ルータ１１０に接続されるとともに、複数の機器３００に接続される。制御システム２００は、スペース内のゲートウエイであるといえる。制御システム２００は、１つの装置で構成されてもよく、互いに接続された複数の装置で構成されてもよい。前者の場合、制御システム２００は制御装置であるといえる。以下では、装置の数に関係なく、制御システム２００として説明する。制御システム２００は、ルータ１１０経由で変換サーバ装置１３０からのメッセージと識別情報とを受信する。制御システム２００は、識別情報に対する認証処理を実行する。認証処理には公知の技術が使用されればよいので、ここでは説明を省略する。認証が失敗した場合、制御システム２００は、処理を終了する。一方、認証が成功した場合、制御システム２００は、メッセージから機器３００の名称と、制御内容とを抽出する。 The control system 200 is installed in a space, connected to the router 110, and connected to a plurality of devices 300. It can be said that the control system 200 is a gateway in the space. The control system 200 may be composed of a single device or a plurality of devices connected to each other. In the former case, it can be said that the control system 200 is a control device. Below, it demonstrates as the control system 200 irrespective of the number of apparatuses. The control system 200 receives a message and identification information from the conversion server device 130 via the router 110. The control system 200 executes an authentication process for the identification information. Since a known technique may be used for the authentication process, the description thereof is omitted here. When the authentication fails, the control system 200 ends the process. On the other hand, when the authentication is successful, the control system 200 extracts the name of the device 300 and the control content from the message.
　制御システム２００は、所定の通信プロトコルにしたがって各機器３００との通信を行う。所定の通信プロトコルの一例は、前述のごとく、ＥＣＨＯＮＥＴ　Ｌｉｔｅ（登録商標）である。制御システム２００は、抽出した制御内容に応じて機器３００を制御するために、制御信号を送信する。このような制御信号の送信には公知の技術が使用されればよい。 The control system 200 communicates with each device 300 according to a predetermined communication protocol. An example of the predetermined communication protocol is ECHONET Lite (registered trademark) as described above. The control system 200 transmits a control signal in order to control the device 300 according to the extracted control content. A known technique may be used for transmission of such a control signal.
（２）シーン記憶
　遠隔操作システム１０００は、通常制御に加えて、シーン制御を規定する。シーン制御とは、シーンに対応づけられたキーワードをユーザが発声した場合に、複数の機器３００を制御する処理である。例えば、シーンが「起床」である場合にキーワードは「おはよう」である。これは、ユーザによって発声された１つの音声によって複数の機器３００を制御する処理に相当する。また、シーン記憶は、シーン制御を実行させる前に予め実行すべき処理であり、キーワードと、複数の機器３００の制御内容を関連づけて記憶させる処理である。 (2) Scene storage The remote operation system 1000 defines scene control in addition to normal control. Scene control is processing for controlling a plurality of devices 300 when a user utters a keyword associated with a scene. For example, when the scene is “getting up”, the keyword is “good morning”. This corresponds to a process of controlling the plurality of devices 300 with one voice uttered by the user. The scene storage is a process to be executed in advance before executing the scene control, and is a process for storing the keyword and the control contents of the plurality of devices 300 in association with each other.
　シーン記憶においても操作装置１００のマイクロフォンは、発話者であるユーザが発話した音声を受けつける。音声の一例は、１つ以上の機器３００の状態を記憶させる指示である。１つ以上の機器３００の状態を記憶させる指示では、「おはようのシーンとして覚えておいて」のように、シーンに対応したキーワードと、１つ以上の機器３００の状態を記憶させる指示が含まれる。ここで、「おはよう」がキーワードに相当し、「シーンとして覚えておいて」が「１つ以上の機器３００の状態を記憶させる指示」に相当する。操作装置１００の処理部は、マイクロフォンで受けつけた音声を電気信号に変換することによって音声情報を生成する。操作装置１００の通信部は、ルータ１１０を介して音声認識サーバ装置１２０に音声情報と識別情報とを送信する。 Also in the scene memory, the microphone of the operation device 100 receives the voice uttered by the user who is the speaker. An example of voice is an instruction to store the state of one or more devices 300. The instruction to store the state of one or more devices 300 includes a keyword corresponding to the scene and an instruction to store the state of one or more devices 300, such as “remember as a good morning scene”. . Here, “good morning” corresponds to a keyword, and “remember as a scene” corresponds to “an instruction to store the state of one or more devices 300”. The processing unit of the controller device 100 generates sound information by converting sound received by the microphone into an electric signal. The communication unit of the controller device 100 transmits voice information and identification information to the voice recognition server device 120 via the router 110.
　音声認識サーバ装置１２０は、音声情報と識別情報とを受信する。音声認識サーバ装置１２０は、これまでと同様に、音声情報に対して音声認識を実行する。音声認識には公知の技術が使用されればよいので、ここでは説明を省略する。音声認識によって、音声認識サーバ装置１２０は、「おはよう」というキーワードと、１つ以上の機器３００の状態を記憶させる指示とを取得する。音声認識サーバ装置１２０は、キーワードと、１つ以上の機器３００の状態を記憶させる指示とが含まれたメッセージを生成する。音声認識サーバ装置１２０は、これまでと同様に、メッセージと識別情報とを送信する。 The voice recognition server device 120 receives voice information and identification information. The voice recognition server device 120 performs voice recognition on the voice information as before. Since a known technique may be used for the speech recognition, the description is omitted here. Through the voice recognition, the voice recognition server device 120 acquires a keyword “good morning” and an instruction to store the state of one or more devices 300. The voice recognition server device 120 generates a message including a keyword and an instruction for storing the state of one or more devices 300. The voice recognition server device 120 transmits a message and identification information as before.
　変換サーバ装置１３０の説明は省略し、制御システム２００の処理を説明するために、ここでは図２を使用する。図２は、制御システム２００の構成を示す。制御システム２００は、ネットワーク側通信部２１０、処理システム４００、機器側通信部２４０を含む。処理システム４００は、受付部２１４、制御部２２０、記憶部２３０、取得部２４４を含む。ネットワーク側通信部２１０は、ルータ１１０経由で変換サーバ装置１３０からのメッセージと識別情報とを受信する。ネットワーク側通信部２１０は、メッセージと識別情報とを制御部２２０に出力する。 Description of the conversion server device 130 is omitted, and FIG. 2 is used here to explain the processing of the control system 200. FIG. 2 shows the configuration of the control system 200. The control system 200 includes a network side communication unit 210, a processing system 400, and a device side communication unit 240. The processing system 400 includes a reception unit 214, a control unit 220, a storage unit 230, and an acquisition unit 244. The network side communication unit 210 receives a message and identification information from the conversion server device 130 via the router 110. The network side communication unit 210 outputs a message and identification information to the control unit 220.
　受付部２１４は、ネットワーク側通信部２１０からメッセージと識別情報とを受けつける。これは、１つ以上の機器３００の状態を記憶させる指示と、キーワードとが含まれた音声を音声認識することによって生成されたメッセージを受けつけることに相当する。受付部２１４は、メッセージと識別情報とを制御部２２０に出力する。制御部２２０は、受付部２１４からメッセージと識別情報とを受けつける。前述のごとく、制御部２２０は、識別情報に対する認証処理を実行する。認証処理が成功した場合、制御部２２０は、メッセージから、１つ以上の機器３００の状態を記憶させる指示と、キーワードとを抽出する。制御部２２０は、１つ以上の機器３００の状態を記憶させる指示にしたがって、各機器３００の現在の状態の取得を決定する。 The reception unit 214 receives a message and identification information from the network side communication unit 210. This is equivalent to receiving a message generated by recognizing a voice including an instruction for storing the state of one or more devices 300 and a keyword. The accepting unit 214 outputs the message and the identification information to the control unit 220. The control unit 220 receives a message and identification information from the reception unit 214. As described above, the control unit 220 executes an authentication process for the identification information. When the authentication process is successful, the control unit 220 extracts an instruction for storing the state of one or more devices 300 and a keyword from the message. The control unit 220 determines acquisition of the current state of each device 300 according to an instruction to store the state of one or more devices 300.
　機器側通信部２４０は、所定の通信プロトコル、例えばＥＣＨＯＮＥＴ　Ｌｉｔｅ（登録商標）にしたがって各機器３００との通信を行う。機器側通信部２４０は、ネットワーク側通信部２１０と一体的に構成されてもよい。機器側通信部２４０は、制御部２２０が各機器３００の現在の状態の取得を決定した場合に、各機器３００にアクセスして、各機器３００の現在の状態を取得する。その際、機器側通信部２４０は、現在の状態を送信させる指示が示されたコマンドを各機器３００に送信し、各機器３００は、コマンドにしたがって現在の状態を送信する。機器側通信部２４０は、取得した各機器３００の現在の状態を取得部２４４に出力する。取得部２４４は、１つ以上の機器３００の現在の状態を機器側通信部２４０から取得する。 The device-side communication unit 240 performs communication with each device 300 according to a predetermined communication protocol, for example, ECHONET Lite (registered trademark). The device side communication unit 240 may be configured integrally with the network side communication unit 210. When the control unit 220 determines to acquire the current state of each device 300, the device-side communication unit 240 accesses each device 300 and acquires the current state of each device 300. At that time, the device-side communication unit 240 transmits a command indicating an instruction to transmit the current state to each device 300, and each device 300 transmits the current state according to the command. The device-side communication unit 240 outputs the acquired current state of each device 300 to the acquisition unit 244. The acquisition unit 244 acquires the current state of one or more devices 300 from the device-side communication unit 240.
　ここでは、各機器３００の現在の状態の取得を制御部２２０が決定してから、機器側通信部２４０が各機器３００にアクセスすることによって、機器側通信部２４０は、１つ以上の機器３００の現在の状態を取得している。しかしながら、各機器３００の現在の状態の取得を制御部２２０が決定する前に、機器側通信部２４０が各機器３００に定期的にアクセスすることによって、取得部２４４は、１つ以上の機器３００の現在の状態を取得してもよい。取得部２４４は、１つ以上の機器３００の現在の状態を制御部２２０に出力する。 Here, after the control unit 220 determines acquisition of the current state of each device 300, the device-side communication unit 240 accesses each device 300, so that the device-side communication unit 240 has one or more devices 300. Get the current state of. However, before the control unit 220 determines acquisition of the current state of each device 300, the device-side communication unit 240 periodically accesses each device 300, so that the acquisition unit 244 has one or more devices 300. You may get the current state of. The acquisition unit 244 outputs the current state of the one or more devices 300 to the control unit 220.
　制御部２２０は、取得部２４４から受けつけた１つ以上の機器３００の現在の状態と、抽出したキーワードとを関連づけて記憶部２３０に記憶させる。つまり、制御部２２０は、受付部２１４において受けつけたメッセージをもとに、取得部２４４において取得した状態をキーワードに関連づけながら記憶させる。図３は、記憶部２３０に記憶されるテーブルのデータ構造を示す。キーワードの一例である「おはよう」に関連づけられて第１機器３００ａの状態「オン」、第２機器３００ｂの状態「オン」、第３機器３００ｃの状態「オン」等が記憶される。他のキーワードに対しても同様である。機器３００の状態として、「オン」、「オフ」以外に設定温度等が示されてもよい。 The control unit 220 causes the storage unit 230 to store the current state of the one or more devices 300 received from the acquisition unit 244 and the extracted keyword in association with each other. That is, the control unit 220 stores the state acquired by the acquisition unit 244 in association with the keyword based on the message received by the reception unit 214. FIG. 3 shows the data structure of the table stored in the storage unit 230. The state “ON” of the first device 300a, the state “ON” of the second device 300b, the state “ON” of the third device 300c, and the like are stored in association with “good morning” which is an example of a keyword. The same applies to other keywords. As the state of the device 300, a set temperature or the like may be indicated in addition to “ON” and “OFF”.
（３）シーン制御
　シーン制御においても図１の操作装置１００のマイクロフォンは、発話者であるユーザが発話した音声を受けつける。音声の一例は、「おはよう」のようにキーワードを含む。操作装置１００の処理部は、マイクロフォンで受けつけた音声を電気信号に変換することによって音声情報を生成する。操作装置１００の通信部は、ルータ１１０を介して音声認識サーバ装置１２０に音声情報と識別情報とを送信する。 (3) Scene control Also in the scene control, the microphone of the operation device 100 in FIG. 1 receives the voice uttered by the user who is the speaker. An example of the voice includes a keyword such as “Good morning”. The processing unit of the controller device 100 generates sound information by converting sound received by the microphone into an electric signal. The communication unit of the controller device 100 transmits voice information and identification information to the voice recognition server device 120 via the router 110.
　音声認識サーバ装置１２０は、音声情報と識別情報とを受信する。音声認識サーバ装置１２０は、これまでと同様に、音声情報に対して音声認識を実行する。音声認識には公知の技術が使用されればよいので、ここでは説明を省略する。音声認識によって、音声認識サーバ装置１２０は、「おはよう」というキーワードを取得する。音声認識サーバ装置１２０は、キーワードが含まれたメッセージを生成する。音声認識サーバ装置１２０は、これまでと同様に、メッセージと識別情報とを送信する。 The voice recognition server device 120 receives voice information and identification information. The voice recognition server device 120 performs voice recognition on the voice information as before. Since a known technique may be used for the speech recognition, the description is omitted here. Through the voice recognition, the voice recognition server device 120 acquires the keyword “good morning”. The voice recognition server device 120 generates a message including the keyword. The voice recognition server device 120 transmits a message and identification information as before.
　変換サーバ装置１３０の説明は省略し、制御システム２００の処理を説明するために、ここでも図２を使用する。ネットワーク側通信部２１０は、ルータ１１０経由で変換サーバ装置１３０からのメッセージと識別情報とを受信する。ネットワーク側通信部２１０は、メッセージと識別情報とを受付部２１４に出力する。受付部２１４は、ネットワーク側通信部２１０からメッセージと識別情報とを受けつける。これは、キーワードが含まれた音声を音声認識することによって生成された別のメッセージを受けつけることに相当する。受付部２１４は、メッセージと識別情報とを制御部２２０に出力する。制御部２２０は、受付部２１４からメッセージと識別情報とを受けつける。前述のごとく、制御部２２０は、識別情報に対する認証処理を実行する。認証処理が成功した場合、制御部２２０は、メッセージから、キーワードとを抽出する。 Description of the conversion server device 130 is omitted, and FIG. 2 is again used to explain the processing of the control system 200. The network side communication unit 210 receives a message and identification information from the conversion server device 130 via the router 110. The network side communication unit 210 outputs the message and the identification information to the reception unit 214. The receiving unit 214 receives a message and identification information from the network side communication unit 210. This is equivalent to accepting another message generated by recognizing the voice including the keyword. The accepting unit 214 outputs the message and the identification information to the control unit 220. The control unit 220 receives a message and identification information from the reception unit 214. As described above, the control unit 220 executes an authentication process for the identification information. When the authentication process is successful, the control unit 220 extracts a keyword from the message.
　制御部２２０は、記憶部２３０に記憶されたテーブルを参照し、抽出したキーワードに関連づけられて記憶された各機器３００の状態を取得する。例えば、抽出したキーワードが「おはよう」である場合、制御部２２０は、図３のテーブルを参照することによって、第１機器３００ａの状態「オン」、第２機器３００ｂの状態「オン」、第３機器３００ｃの状態「オン」等を取得する。制御部２２０は、機器側通信部２４０を介して各機器３００の状態となるように、各機器３００を制御する。つまり、機器側通信部２４０は、各機器３００の状態となるような制御信号を各機器３００に送信する。 The control unit 220 refers to the table stored in the storage unit 230 and acquires the state of each device 300 stored in association with the extracted keyword. For example, when the extracted keyword is “good morning”, the control unit 220 refers to the table of FIG. 3 to determine the state “on” of the first device 300a, the state “on” of the second device 300b, the third The state “ON” or the like of the device 300c is acquired. The control unit 220 controls each device 300 so as to be in the state of each device 300 via the device-side communication unit 240. That is, the device-side communication unit 240 transmits a control signal that causes the state of each device 300 to each device 300.
　本開示における装置、システム、または方法の主体は、コンピュータを備えている。このコンピュータがプログラムを実行することによって、本開示における装置、システム、または方法の主体の機能が実現される。コンピュータは、プログラムにしたがって動作するプロセッサを主なハードウェア構成として備える。プロセッサは、プログラムを実行することによって機能を実現することができれば、その種類は問わない。プロセッサは、半導体集積回路（ＩＣ）、またはＬＳＩ（Ｌａｒｇｅ　Ｓｃａｌｅ　Ｉｎｔｅｇｒａｔｉｏｎ）を含む１つまたは複数の電子回路で構成される。複数の電子回路は、１つのチップに集積されてもよいし、複数のチップに設けられてもよい。複数のチップは１つの装置に集約されていてもよいし、複数の装置に備えられていてもよい。プログラムは、コンピュータが読み取り可能なＲＯＭ、光ディスク、ハードディスクドライブなどの非一時的記録媒体に記録される。プログラムは、記録媒体に予め格納されていてもよいし、インターネット等を含む広域通信網を介して記録媒体に供給されてもよい。 The subject of the apparatus, system, or method in the present disclosure includes a computer. When the computer executes the program, the main function of the apparatus, system, or method according to the present disclosure is realized. The computer includes a processor that operates according to a program as a main hardware configuration. The processor may be of any type as long as the function can be realized by executing the program. The processor includes one or a plurality of electronic circuits including a semiconductor integrated circuit (IC) or an LSI (Large Scale Integration). The plurality of electronic circuits may be integrated on one chip or provided on a plurality of chips. The plurality of chips may be integrated into one device, or may be provided in a plurality of devices. The program is recorded on a non-transitory recording medium such as a ROM, an optical disk, or a hard disk drive that can be read by a computer. The program may be stored in advance in a recording medium, or may be supplied to the recording medium via a wide area communication network including the Internet.
　以上の構成による遠隔操作システム１０００の動作を説明する。図４は、制御システム２００による記憶手順を示すフローチャートである。受付部２１４は、記憶の指示とキーワードとを受けつける（Ｓ１０）。取得部２４４は、各機器３００の状態を取得する（Ｓ１２）。制御部２２０は、キーワードと状態とを関連づけて記憶部２３０に記憶させる（Ｓ１４）。 The operation of the remote operation system 1000 having the above configuration will be described. FIG. 4 is a flowchart showing a storing procedure by the control system 200. The receiving unit 214 receives a storage instruction and a keyword (S10). The acquisition unit 244 acquires the state of each device 300 (S12). The control unit 220 stores the keyword and state in the storage unit 230 in association with each other (S14).
　図５は、制御システム２００による制御手順を示すフローチャートである。受付部２１４は、キーワードを受けつける（Ｓ５０）。制御部２２０は、キーワードに関連づけられた状態を記憶部２３０から取得する（Ｓ５２）。記憶部２３０は、機器側通信部２４０を介して、取得した状態となるように機器３００を制御する（Ｓ５４）。 FIG. 5 is a flowchart showing a control procedure by the control system 200. The reception unit 214 receives a keyword (S50). The control unit 220 acquires the state associated with the keyword from the storage unit 230 (S52). The storage unit 230 controls the device 300 to be in the acquired state via the device side communication unit 240 (S54).
　本実施例によれば、１つ以上の機器３００の状態を記憶させる指示と、キーワードとが含まれた音声を音声認識することによって生成されたメッセージを受けつけると、１つ以上の機器３００の状態を取得して、これらを関連づけて記憶させるので、設定を簡易にできる。また、設定が簡易になるので、ユーザの好みに応じた設定を実行できる。また、キーワードが含まれた音声を音声認識することによって生成された別のメッセージを受けつけると、キーワードに関連づけられて記憶された状態となるように、１つ以上の機器３００を制御するので、１つの音声で複数の機器３００を制御できる。 According to this embodiment, when an instruction for storing the state of one or more devices 300 and a message generated by recognizing a voice including a keyword are received, the state of the one or more devices 300 is received. Since these are acquired and stored in association with each other, the setting can be simplified. Moreover, since the setting is simplified, the setting according to the user's preference can be executed. In addition, since one or more devices 300 are controlled so as to be stored in association with a keyword when another message generated by recognizing the voice including the keyword is received, the one or more devices 300 are controlled. A plurality of devices 300 can be controlled with one voice.
　本開示の一態様の概要は、次の通りである。本開示のある態様の処理システム４００は、１つ以上の機器３００の状態を記憶させる指示と、キーワードとが含まれた音声を音声認識することによって生成されたメッセージを受けつける受付部２１４と、１つ以上の機器３００の状態を取得する取得部２４４と、受付部２１４において受けつけたメッセージをもとに、取得部２４４において取得した状態をキーワードに関連づけながら記憶させる制御部２２０と、を備える。 The outline of one aspect of the present disclosure is as follows. The processing system 400 according to an aspect of the present disclosure includes a reception unit 214 that receives a message generated by recognizing a voice including an instruction to store the state of one or more devices 300 and a keyword, and 1 An acquisition unit 244 that acquires the states of two or more devices 300, and a control unit 220 that stores the states acquired by the acquisition unit 244 in association with keywords based on the messages received by the reception unit 214.
　受付部２１４は、キーワードが含まれた音声を音声認識することによって生成された別のメッセージを受けつけ、制御部２２０は、受付部２１４において受けつけた別のメッセージから、キーワードを抽出し、抽出したキーワードに関連づけられて記憶された状態となるように、１つ以上の機器３００を制御する。 The reception unit 214 receives another message generated by recognizing the voice including the keyword, and the control unit 220 extracts the keyword from the other message received by the reception unit 214 and extracts the extracted keyword. One or more devices 300 are controlled so as to be stored in association with each other.
（実施例２）
　次に、実施例２を説明する。実施例２は、実施例１と同様に、キーワードを発声することによって、複数の機器を制御する遠隔操作システムに関する。実施例１では、制御システム２００が、キーワードと各機器３００の状態とを関連づけて記憶する。一方、実施例２では、音声認識サーバ装置１２０が、キーワードと各機器３００の状態とを関連づけて記憶する。実施例２に係る遠隔操作システム１０００は、図１と同様のタイプである。ここでは、実施例１との差異を中心に説明する。 (Example 2)
Next, Example 2 will be described. As in the first embodiment, the second embodiment relates to a remote operation system that controls a plurality of devices by speaking a keyword. In the first embodiment, the control system 200 stores the keyword and the state of each device 300 in association with each other. On the other hand, in the second embodiment, the voice recognition server device 120 stores the keyword and the state of each device 300 in association with each other. The remote operation system 1000 according to the second embodiment is the same type as that shown in FIG. Here, it demonstrates centering on the difference with Example 1. FIG.
　実施例２における（１）通常制御は、実施例１と同様であるので省略し、ここでは、（２）シーン記憶、（３）シーン制御の順に説明する。
（２）シーン記憶
　操作装置１００は、実施例１と同一であり、ルータ１１０を介して音声認識サーバ装置１２０に音声情報と識別情報とを送信する。音声認識サーバ装置１２０の処理を説明するために、ここでは図６を使用する。図６は、音声認識サーバ装置１２０の構成を示す。音声認識サーバ装置１２０は、通信部１０、認識部３０、処理システム４００を含む。処理システム４００は、受付部２０、取得部４０、制御部５０、記憶部６０を含む。通信部１０は、図１のルータ１１０、変換サーバ装置１３０に接続され、それらとの間で通信を実行する。 Since (1) normal control in the second embodiment is the same as that in the first embodiment, it will be omitted. Here, (2) scene storage and (3) scene control will be described in this order.
(2) Scene storage The operation device 100 is the same as that in the first embodiment, and transmits voice information and identification information to the voice recognition server device 120 via the router 110. In order to explain the processing of the speech recognition server device 120, FIG. 6 is used here. FIG. 6 shows the configuration of the voice recognition server device 120. The speech recognition server device 120 includes a communication unit 10, a recognition unit 30, and a processing system 400. The processing system 400 includes a reception unit 20, an acquisition unit 40, a control unit 50, and a storage unit 60. The communication unit 10 is connected to the router 110 and the conversion server device 130 in FIG. 1 and performs communication with them.
　通信部１０は、ルータ１１０を介して操作装置１００からの音声情報と識別情報とを受信する。受付部２０は、通信部１０から音声情報を受けつける。これは、１つ以上の機器３００の状態を記憶させる指示と、キーワードとが含まれた音声に応じた音声情報を受けつけることに相当する。認識部３０は、受付部２０において受けつけた音声情報に対して音声認識を実行する。音声認識によって、音声認識サーバ装置１２０は、「おはよう」というキーワードと、１つ以上の機器３００の状態を記憶させる指示とを取得する。認識部３０は、「おはよう」というキーワードと、１つ以上の機器３００の状態を記憶させる指示とを制御部５０に出力する。 The communication unit 10 receives voice information and identification information from the operation device 100 via the router 110. The receiving unit 20 receives voice information from the communication unit 10. This corresponds to receiving voice information corresponding to a voice including an instruction to store the state of one or more devices 300 and a keyword. The recognition unit 30 performs voice recognition on the voice information received by the reception unit 20. Through the voice recognition, the voice recognition server device 120 acquires a keyword “good morning” and an instruction to store the state of one or more devices 300. The recognizing unit 30 outputs a keyword “Good morning” and an instruction to store the state of one or more devices 300 to the control unit 50.
　制御部５０は、制御部２２０と同様の処理を実行しており、１つ以上の機器３００の状態を記憶させる指示にしたがって、各機器３００の現在の状態の取得を決定する。制御部５０は、通信部１０、ルータ１１０、制御システム２００を介して、各機器３００にアクセスして、各機器３００の現在の状態の取得を決定する。通信部１０は、制御部５０が各機器３００の現在の状態の取得を決定した場合に、各機器３００にアクセスして、各機器３００の現在の状態を取得する。その際、通信部１０は、現在の状態を送信させる指示が示されたコマンドを制御システム２００経由で各機器３００に送信し、各機器３００は、コマンドにしたがって現在の状態を送信する。通信部１０は、取得した各機器３００の現在の状態を取得部４０に出力する。取得部４０は、取得部２４４と同様の処理を実行しており、１つ以上の機器３００の現在の状態を通信部１０から取得する。 The control unit 50 performs the same processing as the control unit 220, and determines acquisition of the current state of each device 300 according to an instruction to store the state of one or more devices 300. The control unit 50 accesses each device 300 via the communication unit 10, the router 110, and the control system 200, and determines acquisition of the current state of each device 300. When the control unit 50 determines acquisition of the current state of each device 300, the communication unit 10 accesses each device 300 and acquires the current state of each device 300. At that time, the communication unit 10 transmits a command indicating an instruction to transmit the current state to each device 300 via the control system 200, and each device 300 transmits the current state according to the command. The communication unit 10 outputs the acquired current state of each device 300 to the acquisition unit 40. The acquisition unit 40 performs the same processing as the acquisition unit 244 and acquires the current state of one or more devices 300 from the communication unit 10.
　ここでは、各機器３００の現在の状態の取得を制御部５０が決定してから、通信部１０が各機器３００にアクセスすることによって、通信部１０は、１つ以上の機器３００の現在の状態を取得している。しかしながら、各機器３００の現在の状態の取得を制御部５０が決定する前に、通信部１０が各機器３００に定期的にアクセスすることによって、取得部４０は、１つ以上の機器３００の現在の状態を取得してもよい。取得部４０は、１つ以上の機器３００の現在の状態を制御部５０に出力する。 Here, after the control unit 50 determines acquisition of the current state of each device 300, the communication unit 10 accesses each device 300 so that the communication unit 10 has the current state of one or more devices 300. Is getting. However, before the control unit 50 determines the acquisition of the current state of each device 300, the acquisition unit 40 periodically accesses each device 300 so that the acquisition unit 40 acquires the current status of one or more devices 300. You may acquire the state of. The acquisition unit 40 outputs the current state of the one or more devices 300 to the control unit 50.
　制御部５０は、取得部４０から受けつけた１つ以上の機器３００の現在の状態と、キーワードとを関連づけて記憶部６０に記憶させる。記憶部６０に記憶されるテーブルは、記憶部２３０に記憶されるテーブルと同様である。 The control unit 50 stores the current state of the one or more devices 300 received from the acquisition unit 40 and the keyword in the storage unit 60 in association with each other. The table stored in the storage unit 60 is the same as the table stored in the storage unit 230.
（３）シーン制御
　図１の操作装置１００は、実施例１と同一であり、ルータ１１０を介して音声認識サーバ装置１２０に音声情報と識別情報とを送信する。ここでも、音声認識サーバ装置１２０の処理を説明するために図６を使用する。通信部１０は、ルータ１１０を介して操作装置１００からの音声情報と識別情報とを受信する。受付部２０は、通信部１０から音声情報を受けつける。これは、キーワードが含まれた音声を受けつけた操作装置１００から、当該音声に応じた別の音声情報を受けつけることに相当する。認識部３０は、受付部２０において受けつけた音声情報に対して音声認識を実行する。音声認識によって、認識部３０は、「おはよう」というキーワードを取得する。認識部３０は、「おはよう」というキーワードと、１つ以上の機器３００の状態を記憶させる指示とを制御部５０に出力する。 (3) Scene Control The operation device 100 in FIG. 1 is the same as that in the first embodiment, and transmits voice information and identification information to the voice recognition server device 120 via the router 110. Again, FIG. 6 is used to describe the processing of the speech recognition server device 120. The communication unit 10 receives voice information and identification information from the controller device 100 via the router 110. The receiving unit 20 receives voice information from the communication unit 10. This corresponds to receiving another voice information corresponding to the voice from the operation device 100 that has received the voice including the keyword. The recognition unit 30 performs voice recognition on the voice information received by the reception unit 20. The recognition unit 30 acquires the keyword “good morning” through the speech recognition. The recognizing unit 30 outputs a keyword “Good morning” and an instruction to store the state of one or more devices 300 to the control unit 50.
　制御部５０は、記憶部６０に記憶されたテーブルを参照し、抽出したキーワードに関連づけられて記憶された各機器３００の状態を取得する。制御部５０は、取得した各機器３００の状態となるようなメッセージを生成する。制御部５０は、通信部１０、ルータ１１０を介して制御システム２００にメッセージと識別情報とを送信する。これは、取得したキーワードに関連づけられて記憶された状態となるように、１つ以上の機器３００を制御することに相当する。 The control unit 50 refers to the table stored in the storage unit 60 and acquires the state of each device 300 stored in association with the extracted keyword. The control part 50 produces | generates the message which becomes the state of each acquired apparatus 300. FIG. The control unit 50 transmits a message and identification information to the control system 200 via the communication unit 10 and the router 110. This corresponds to controlling one or more devices 300 so as to be stored in association with the acquired keyword.
　変換サーバ装置１３０はこれまでと同様の処理を実行し、制御システム２００は、ルータ１１０経由で変換サーバ装置１３０からのメッセージと識別情報とを受信する。制御システム２００は、識別情報に対する認証処理を実行する。認証が成功した場合、制御システム２００は、制御すべき各機器３００の状態に関する情報をメッセージから抽出する。制御システム２００は、各機器３００の状態になるように、各機器３００を制御するための制御信号を送信する。 The conversion server device 130 executes the same processing as before, and the control system 200 receives a message and identification information from the conversion server device 130 via the router 110. The control system 200 executes an authentication process for the identification information. When the authentication is successful, the control system 200 extracts information on the state of each device 300 to be controlled from the message. The control system 200 transmits a control signal for controlling each device 300 so that each device 300 is in a state.
　本実施例によれば、１つ以上の機器３００の状態を記憶させる指示と、キーワードとが含まれた音声に応じた音声情報を音声認識すると、１つ以上の機器３００の状態を取得して、これらを関連づけて記憶させるので、設定を簡易にできる。また、設定が簡易になるので、ユーザの好みに応じた設定を実行できる。また、キーワードが含まれた音声に応じた別の音声情報を音声認識すると、キーワードに関連づけられて記憶された状態となるように、１つ以上の機器３００を制御するので、１つの音声で複数の機器３００を制御できる。 According to the present embodiment, when voice information corresponding to voice including an instruction for storing the status of one or more devices 300 and a keyword is recognized, the status of the one or more devices 300 is acquired. Since these are stored in association with each other, the setting can be simplified. Moreover, since the setting is simplified, the setting according to the user's preference can be executed. In addition, when another voice information corresponding to the voice including the keyword is recognized, one or more devices 300 are controlled so as to be stored in association with the keyword. The device 300 can be controlled.
　本開示の一態様の概要は、次の通りである。本開示の別の態様もまた、処理システム４００である。この処理システム４００は、１つ以上の機器３００の状態を記憶させる指示と、キーワードとが含まれた音声を受けつけた操作装置１００から、当該音声に応じた音声情報を受けつける受付部２０と、１つ以上の機器３００の状態を取得する取得部４０と、受付部２０において受けつけた音声情報を音声認識することによって、取得部４０において取得した状態をキーワードに関連づけながら記憶させる制御部５０と、を備える。 The outline of one aspect of the present disclosure is as follows. Another aspect of the present disclosure is also a processing system 400. The processing system 400 includes a receiving unit 20 that receives voice information corresponding to the voice from the operation device 100 that receives a voice including an instruction to store the state of one or more devices 300 and a keyword. An acquisition unit 40 that acquires the states of two or more devices 300, and a control unit 50 that stores the states acquired in the acquisition unit 40 while associating them with keywords by recognizing the voice information received in the reception unit 20. Prepare.
　受付部２０は、キーワードが含まれた音声を受けつけた操作装置１００から、当該音声に応じた別の音声情報を受けつけ、制御部５０は、受付部２０において受けつけた別の音声情報を音声認識することによって、キーワードを取得し、取得したキーワードに関連づけられて記憶された状態となるように、１つ以上の機器３００を制御する。 The receiving unit 20 receives another voice information corresponding to the voice from the operation device 100 that has received the voice including the keyword, and the control unit 50 recognizes the other voice information received by the receiving unit 20 as a voice. Thus, the keyword is acquired, and the one or more devices 300 are controlled so as to be stored in association with the acquired keyword.
　以上、本開示を実施例をもとに説明した。この実施例は例示であり、それらの各構成要素あるいは各処理プロセスの組合せにいろいろな変形例が可能なこと、またそうした変形例も本開示の範囲にあることは当業者に理解されるところである。 In the above, this indication was demonstrated based on the Example. This embodiment is an exemplification, and it is understood by those skilled in the art that various modifications can be made to each of those components or combinations of processing processes, and such modifications are also within the scope of the present disclosure. .
　１００　操作装置、　１１０　ルータ、　１２０　音声認識サーバ装置、　１３０　変換サーバ装置、　１５０　端末装置、　２００　制御システム、　２１０　ネットワーク側通信部、　２１４　受付部、　２２０　制御部、　２３０　記憶部、　２４０　機器側通信部、　２４４　取得部、　３００　機器、　４００　処理システム、　１０００　遠隔操作システム。 100 operation device, 110 router, 120 voice recognition server device, 130 conversion server device, 150 terminal device, 200 control system, 210 network side communication unit, 214 reception unit, 220 control unit, 230 storage unit, 240 device side communication unit, 244 acquisition unit, 300 devices, 400 processing system, 1000 remote operation system.
　本開示によれば、設定を簡易にできる。 設定 According to the present disclosure, the setting can be simplified.

Claims (6)

  1. 　１つ以上の機器の状態を記憶させる指示と、キーワードとが含まれた音声を音声認識することによって生成されたメッセージを受けつける受付部と、
    　前記１つ以上の機器の状態を取得する取得部と、
    　前記受付部において受けつけたメッセージをもとに、前記取得部において取得した状態を前記キーワードに関連づけながら記憶させる制御部と、
    　を備える処理システム。     An accepting unit for receiving a message generated by recognizing a voice including an instruction for storing the state of one or more devices and a keyword;
    An acquisition unit for acquiring the state of the one or more devices;
    Based on the message received in the reception unit, a control unit that stores the state acquired in the acquisition unit while associating it with the keyword;
    A processing system comprising:
  2. 　前記受付部は、前記キーワードが含まれた音声を音声認識することによって生成された別のメッセージを受けつけ、
    　前記制御部は、前記受付部において受けつけた別のメッセージから、前記キーワードを抽出し、抽出した前記キーワードに関連づけられて記憶された状態となるように、１つ以上の機器を制御する、
    　請求項１に記載の処理システム。     The reception unit receives another message generated by recognizing a voice including the keyword,
    The control unit extracts one of the keywords from another message received by the reception unit, and controls one or more devices so as to be stored in association with the extracted keyword.
    The processing system according to claim 1.
  3. 　１つ以上の機器の状態を記憶させる指示と、キーワードとが含まれた音声を受けつけた操作装置から、当該音声に応じた音声情報を受けつける受付部と、
    　前記１つ以上の機器の状態を取得する取得部と、
    　前記受付部において受けつけた音声情報を音声認識することによって、前記取得部において取得した状態を前記キーワードに関連づけながら記憶させる制御部と、
    　を備える処理システム。     An accepting unit that receives voice information corresponding to the voice from an operating device that has received a voice including an instruction to store the state of one or more devices and a keyword;
    An acquisition unit for acquiring the status of the one or more devices;
    A controller that stores the state acquired in the acquisition unit in association with the keyword by recognizing the audio information received in the reception unit;
    A processing system comprising:
  4. 　前記受付部は、前記キーワードが含まれた音声を受けつけた操作装置から、当該音声に応じた別の音声情報を受けつけ、
    　前記制御部は、前記受付部において受けつけた別の音声情報を音声認識することによって、前記キーワードを取得し、取得した前記キーワードに関連づけられて記憶された状態となるように、１つ以上の機器を制御する、
    　請求項３に記載の処理システム。     The reception unit receives another voice information corresponding to the voice from the operation device that receives the voice including the keyword,
    The control unit obtains the keyword by recognizing another voice information received by the reception unit, and the one or more devices are in a state of being stored in association with the acquired keyword. To control the
    The processing system according to claim 3.
  5. 　１つ以上の機器の状態を記憶させる指示と、キーワードとが含まれた音声を音声認識することによって生成されたメッセージを受けつけるステップと、
    　前記１つ以上の機器の状態を取得するステップと、
    　受けつけたメッセージをもとに、取得した状態を前記キーワードに関連づけながら記憶させるステップとをコンピュータに実行させるためのプログラム。     Receiving a message generated by recognizing a voice including an instruction to store a state of one or more devices and a keyword;
    Obtaining a status of the one or more devices;
    A program for causing a computer to execute a step of storing an acquired state in association with the keyword based on an accepted message.
  6. 　１つ以上の機器の状態を記憶させる指示と、キーワードとが含まれた音声を受けつけた操作装置から、当該音声に応じた音声情報を受けつけるステップと、
    　前記１つ以上の機器の状態を取得するステップと、
    　受けつけた音声情報を音声認識することによって、取得した状態を前記キーワードに関連づけながら記憶させるステップとをコンピュータに実行させるためのプログラム。     Receiving voice information corresponding to the voice from an operating device that has received a voice including an instruction to store the state of one or more devices and a keyword;
    Obtaining a status of the one or more devices;
    A program for causing a computer to execute a step of recognizing received voice information and storing the acquired state in association with the keyword.
PCT/JP2019/018539 2018-05-14 2019-05-09 Processing system and program WO2019221001A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2018093347A JP2019200492A (en) 2018-05-14 2018-05-14 Processing system and program
JP2018-093347 2018-05-14

Publications (1)

Publication Number Publication Date
WO2019221001A1 true WO2019221001A1 (en) 2019-11-21

Family

ID=68539832

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/018539 WO2019221001A1 (en) 2018-05-14 2019-05-09 Processing system and program

Country Status (2)

Country Link
JP (1) JP2019200492A (en)
WO (1) WO2019221001A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001117751A (en) * 1999-10-18 2001-04-27 Fujitsu Ltd Equipment information storing/reproducing device using voice and computer readable recording medium stored with program to be executed by computer for materializing the device
JP2011519128A (en) * 2008-04-23 2011-06-30 コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ Lighting system controller and method for controlling a lighting scene
WO2014030540A1 (en) * 2012-08-24 2014-02-27 株式会社 東芝 Remote control device
JP2017091785A (en) * 2015-11-09 2017-05-25 パナソニックＩｐマネジメント株式会社 Lighting control system and program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001117751A (en) * 1999-10-18 2001-04-27 Fujitsu Ltd Equipment information storing/reproducing device using voice and computer readable recording medium stored with program to be executed by computer for materializing the device
JP2011519128A (en) * 2008-04-23 2011-06-30 コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ Lighting system controller and method for controlling a lighting scene
WO2014030540A1 (en) * 2012-08-24 2014-02-27 株式会社 東芝 Remote control device
JP2017091785A (en) * 2015-11-09 2017-05-25 パナソニックＩｐマネジメント株式会社 Lighting control system and program

Also Published As

Publication number Publication date
JP2019200492A (en) 2019-11-21

Similar Documents

Publication Publication Date Title
US20200294494A1 (en) Device control system, device control method, and terminal device
US20220286317A1 (en) Apparatus, system and method for directing voice input in a controlling device
US10938595B2 (en) Device control system, device control method, and non-transitory computer readable storage medium
JP2005311864A (en) Household appliances, adapter instrument, and household appliance system
JP2019086535A (en) Transmission control device and program
JP3838029B2 (en) Device control method using speech recognition and device control system using speech recognition
US20040073620A1 (en) Home network system for generating random number and method for controlling the same
US11508375B2 (en) Electronic apparatus including control command identification tool generated by using a control command identified by voice recognition identifying a control command corresponding to a user voice and control method thereof
US20190173834A1 (en) Device Control System, Device, and Computer-Readable Non-Transitory Storage Medium
WO2019221001A1 (en) Processing system and program
JP7162169B2 (en) processor, remote control system, program
WO2019216372A1 (en) Control system and program
WO2018158894A1 (en) Air conditioning control device, air conditioning control method, and program
JP7036561B2 (en) Home appliance system
WO2022124389A1 (en) Display control system and program
JP2020153635A (en) Air conditioning system
JP7042439B2 (en) Controls and programs
CN113129578A (en) Matching method, control method, system and storage medium of infrared equipment
JP7026340B2 (en) Setting device, control device, program
CN212750365U (en) Intelligent voice hearing aid and intelligent furniture system
JP2020129183A (en) Control device, control system, and control method
WO2018207483A1 (en) Information processing device, electronic apparatus, control method, and control program
JP7433841B2 (en) Equipment operating system, equipment operating method, information processing device and computer program
US20240235879A1 (en) Apparatus, system and method for directing voice input in a controlling device
WO2022215279A1 (en) Control method, control device, and program

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: 19803555

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: 19803555

Country of ref document: EP

Kind code of ref document: A1