JP6316214B2 - SYSTEM, SERVER, ELECTRONIC DEVICE, SERVER CONTROL METHOD, AND PROGRAM - Google Patents

Description

  The present disclosure relates to device operation control based on voice recognition, and more specifically, to a technique for controlling device operation by interaction.

  Robots with interactive functions are known. For example, Japanese Patent Laid-Open No. 2003-69732 (Patent Document 1) states that “a robot that is portable, has an interactive function, can take in network information, gives a specific message to a user's emotion, and has a schedule function” (See [Problem] in [Summary]). This robot includes “a voice input unit 4 that recognizes and inputs a user's voice, a voice output unit 5 that outputs a synthesized voice, a storage unit 22, and a control unit 2. The storage unit stores the schedule data input by the user's voice and responds to the user's inquiry according to the schedule data. The content is output by voice "([Solution] in [Summary]).

  Japanese Patent Laid-Open No. 2002-344573 (Patent Document 2) states that “when a preset time is reached, the voice of a talent or a celebrity informs that the time has arrived, and that voice can be freely selected. A possible voice playback timer and a mobile phone having a voice playback timer ”are disclosed ([Summary] [Problem]).

JP 2003-69732 A JP 2002-344573 A

  There is a need for a technique for easily setting a schedule voice output, notification of arrival of time, and the like for a robot having an interactive function. Further, there is a need for a technique for providing a dialogue that can bring interest to the user, not just a dialogue. Furthermore, there is a need for a technology that can change the spoken voice.

  The present disclosure has been made to solve the above-described problems, and an object in one aspect is to easily perform voice output of a schedule, notification of arrival of time, and the like by a robot having an interactive function. It is to provide a system that can. An object in another aspect is to provide a system capable of providing a dialog that can bring interest to the user, not just a dialog. The objective in another situation is to provide the system which can change the audio | voice spoken.

  An object in another aspect is to realize a server, an electronic device, a server control method, or the method capable of easily setting a voice output of a schedule or a notification of arrival of time by a robot having an interactive function. Is to provide a program. An object in another aspect is to provide a server, an electronic device, a server control method, or a program for realizing the method, which can provide a dialogue that can bring interest to the user, not just a dialogue. Still another object of the present invention is to provide a server, an electronic device, a server control method, or a program for realizing the method that can change a voice to be spoken.

  According to one embodiment, a system for operating an electronic device by speech is provided. This system includes a plurality of electronic devices that accept utterances and a server that can communicate with the plurality of electronic devices. The electronic device includes a voice input unit for receiving an utterance and a transmission unit for transmitting the identification information of the electronic device and the content of the received utterance to a server. The server includes storage means for holding the identification information and the content of the utterance, generation means for generating an instruction according to the utterance content, and transmission means for transmitting the identification information and the instruction to the electronic device. Prepare. The electronic device includes receiving means for receiving a command from the server, and operating means for executing an operation based on the command.

  According to another embodiment, a server for controlling an electronic device is provided. The server includes an input unit for receiving utterance contents via a plurality of electronic devices, a storage unit for storing identification information and utterance contents in association with each other, and a command corresponding to the utterance contents. And generating means for transmitting the command to the electronic device specified by the identification information associated with the content of the utterance for generating the command.

  According to another embodiment, an electronic device is provided. The electronic device includes a communication unit for communicating with the server, a voice input unit for receiving an utterance, and an operation unit for executing the operation of the electronic device. The communication means transmits the utterance content of the utterance accepted by the voice input means to the server, and receives a command corresponding to the utterance content from the server. The operation means performs an operation based on the received command.

  According to another embodiment, a method for controlling a server is provided. The control method includes a step of accepting an utterance including an instruction of a future operation by at least one electronic device, a step of retaining identification information of at least one electronic device and the content of the instruction, and a command according to the content of the instruction And generating and transmitting identification information and instructions to the one or more electronic devices based on the arrival of a time when a future operation is performed.

  According to still another aspect, a program for causing a computer to execute the above method is provided.

  The above and other objects, features, aspects and advantages of the present invention will become apparent from the following detailed description of the present invention taken in conjunction with the accompanying drawings.

It is a figure showing one mode in which a user uses system 100 concerning this embodiment. 2 is a block diagram illustrating an example of a configuration of a system 100. FIG. 2 is a block diagram illustrating a configuration of a computer system that implements a server 120. FIG. It is a figure showing one mode of storage of data in hard disk 5 of server 120. 2 is a diagram showing a message output by system 100. FIG. This data defines the time output to the system 100. 2 is a block diagram illustrating a hardware configuration of a robot 110. FIG. It is a flowchart showing a part of process performed when the system 100 registers a wake-up setting. It is a flowchart showing the process for changing an alarm setting. It is a flowchart showing the confirmation process of an alarm clock setting. It is a flowchart showing the process which cancels an alarm clock setting. It is a figure which represents notionally one aspect | mode of the data which the hard disk 5 with which the server 120 is provided stores. 4 is a flowchart showing a part of processing executed by system 100.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, the same parts are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed description thereof will not be repeated.

<First Embodiment>
With reference to FIG. 1, the technical idea which concerns on this Embodiment is demonstrated. FIG. 1 is a diagram illustrating an aspect in which a user uses a system 100 according to the present embodiment. The system 100 includes a plurality of electronic devices (for example, robots 110A, 110B,... 110N) and a server 120. The robots 110A, 110B, and 110N are collectively referred to as the robot 110. The server 120 and the robot 110 are connected to each other via the Internet 130 and other networks. For example, the robot 110 is realized as a vacuum cleaner having a self-propelled function. The electronic device is not limited to a robot, and may be a microwave oven, an air conditioner, or other devices. The electronic device only needs to have at least a voice input function, a communication function with the server 120, and an operation function.

(Alarm setting)
In one aspect, the time for alarm setting can be set in units of 24 hours, for example, and can be specified in units of 10 minutes. When the user wants to use the alarm function, the user 150 can set the time by calling out each time. Once the user 150 sets the time, it can be easily set to the same time after the second time.

  For example, if the desired time cannot be determined within about 30 seconds after the robot 110 asks for the desired time, a timeout occurs and the setting of the alarm function is not completed. Note that the time until the timeout is not limited to the exemplified time, and other time may be used. Further, the time until timeout may be set by the user of the system 100. The user in this case may be either an operator of the server 120 or a user of the robot 110.

  Note that in another aspect, the robot 110 may sing the “wake-up song” at the set time. In this case, when the user of the robot 110 wants to stop the song on the way, by pressing and holding a start / stop button (not shown) of the main body of the robot 110 for a predetermined time (for example, 2 seconds) or longer, Singing by the robot 110 can be stopped.

  More specifically, in a certain situation, the user 150 utters “set to wake up” (message 151). When the robot 110A or the server 120 recognizes the content of the voice of the message 151, the robot 110A outputs a response (message 152) “I understand. Say the time you want to set.” When the user recognizes the message 152, the user speaks “7:20” (message 153). When the robot 110A or the server 110 recognizes the content of the voice of the message 153, the robot 110A utters “You have set your alarm and will wake you up at 7:20” (message 154).

  In this way, when the user desires to wake up comfortably by the utterance of the robot 110, the user can set the wake-up by designating the time by voice conversation.

  Thereafter, when the set time arrives, the robot 110 outputs a message or a song by voice based on the data from the server 120. This voice may be the voice of the voice actor used when setting the alarm, or in another aspect, a singing voice of a person different from the voice actor may be output.

(Second and subsequent settings)
If the user has set the alarm once, the alarm function can be easily set again at the same time by voice conversation. For example, when the user utters “set to wake up”, the robot 110 utters “I set wake up. I wake up at 7: 20 ♪”. In this case, the utterance of the robot 110 is performed based on the already set time. The alarm time is stored in the robot 110 or the server 120.

(Change of alarm time)
The user can change the alarm time by the robot 110 by voice conversation. For example, the user utters “set to wake up”. When the content of the user's utterance is recognized by the robot 110 or the server 120, the robot 110 utters “I understand ♪ Please say the time you want to set.” The user utters “6:20”. When the content of the user's utterance is recognized by the robot 110 or the server 120, the robot 110 utters “You have set your alarm and will wake you up at 6: 20 ♪”. In this way, the setting of the alarm time is changed.

  The setting of the wake-up time is not limited to the above mode. For example, instead of speaking with the time after the change (for example, 6:20), the user may speak “wake up one hour earlier than usual”. When the robot 110 stores 7:20 as the standard wake-up time of the user, the robot 110 calculates 6:20 as the new time when recognizing the content of the utterance, and sets the wake-up time. You can register as

(Confirmation of alarm setting time)
The user can confirm the alarm setting time of the robot 110 by voice conversation. For example, the user utters “Check to wake up”. When the utterance is recognized by the robot 110 or the server 120, the robot 110 utters, “I wake up at 7 o'clock based on the data stored in the robot 110 or the server 120.

  In another aspect, there may be a meeting where no alarm is set. In this case, even if the user utters “set to wake up” and the utterance is recognized, the robot 110 detects that the alarm of the user is not stored in the robot 110 or the server 120. Based on the result of the detection, the robot 110 utters “No alarm setting”.

(Cancellation of alarm settings)
The user can cancel the alarm function of the robot 110 by voice conversation. For example, the user utters “Cancel the alarm”. When the utterance is recognized by the robot 110 or the server 120, the robot 110 utters “Okay, can I wake up?”. When the user utters a message (for example, “OK”) that conveys the result of the confirmation, the robot 110 utters “The alarm setting has been canceled”.

  In another aspect, the user can cancel the instruction to cancel the alarm setting. For example, the user utters “Cancel the alarm”. When the utterance is recognized by the robot 110 or the server 120, the robot 110 utters “Okay, can I wake up?”. A user who has changed utters "Stop". When the utterance is recognized by the robot 110 or the server 120, the robot 110 utters “The alarm is still set.

  With reference to FIG. 2, the configuration of system 100 according to the present embodiment will be described. FIG. 2 is a block diagram illustrating an example of the configuration of the system 100. The system 100 includes a voice input unit 210, a voice recognition processing unit 220, an extraction unit 230, a storage unit 240, an operation unit 250, a command generation unit 260, and a timing unit 270.

  The voice input unit 210 receives an input of an utterance (for example, an instruction to set an alarm or an instruction to change) to the system 100. The voice input unit 210 outputs a signal corresponding to the utterance to the voice recognition processing unit 220. The signal includes, for example, utterance identification information and the instruction included in the utterance. The instruction may be either voice data or character data.

  The voice recognition processing unit 220 performs voice recognition processing on the identification information and the instruction included in the utterance based on the signal sent from the voice input unit 210, and outputs the processing result to the extraction unit 230.

  The extraction unit 230 extracts the identification information of the utterance and the content of the instruction included in the utterance from the recognition processing result sent from the speech recognition processing unit 220, and stores the extracted data in the storage unit 240.

  The storage unit 240 holds data given to the system 100, data generated in the system 100, and the like.

  The operation unit 250 includes an audio output unit 251. The operation unit 250 executes the operation specified by the command generated by the command generation unit 260 based on the output result from the voice recognition processing unit 220. The operation performed by the operation unit 250 may include, for example, an alarm sound output, other sound output, and operation of a mechanism for cleaning when the system 100 includes a cleaning function.

  The voice output unit 251 outputs a response by voice based on the signal given from the voice recognition processing unit 220 based on the reception of the command from the command generation unit 260.

  The instruction generation unit 260 generates an instruction for causing the operation unit 250 to execute an operation. For example, the command generation unit 260 generates the command using data held in the storage unit 240 and time data measured by the time measuring unit 270. The instruction generation unit 260 sends the generated instruction to the operation unit 250. The instruction includes device identification information and specific instruction contents of the operation.

  The timer unit 270 measures the time in the system 100. The timer 270 can measure time based on a clock that is held in advance, or can receive accurate time information from other information communication devices connected to the system 100. The accurate time information may include, for example, time information acquired by a GPS (Global Positioning System) signal or other positioning signals.

[Server configuration]
With reference to FIG. 3, the configuration of server 120 according to the present embodiment will be described. FIG. 3 is a block diagram showing the configuration of a computer system that implements server 120.

  The server 120 includes, as main components, a CPU (Central Processing Unit) 1 that executes a program, a mouse 2 and a keyboard 3 that receive input of instructions from a user of the server 120, data generated by execution of the program by the CPU 1, Alternatively, a RAM (Random Access Memory) 4 that stores data input via the mouse 2 or the keyboard 3 in a volatile manner, a hard disk 5 that stores data in a nonvolatile manner, an optical disk drive device 6, and a communication IF (Interface) 7 and a monitor 8. Each component is connected to each other by a bus. A CD-ROM 9 and other optical disks are mounted on the optical disk drive 6. The communication IF 7 includes, but is not limited to, a USB (Universal Serial Bus) interface, a wired LAN (Local Area Network), a wireless LAN, and a Bluetooth (registered trademark) interface.

  The processing in the server 120 is realized by each hardware and software executed by the CPU 1. Such software may be stored in the hard disk 5 in advance. The software may be stored in a CD-ROM 9 or other non-volatile computer-readable data recording medium and distributed as a program product. Alternatively, the software may be provided as a program product that can be downloaded by an information provider connected to the Internet or other networks. Such software is read from the data recording medium by the optical disk drive 6 or other data reading device, or downloaded via the communication IF 7 and then temporarily stored in the hard disk 5. The software is read from the hard disk 5 by the CPU 1 and stored in the RAM 4 in the form of an executable program. The CPU 1 executes the program.

  Each module constituting the server 120 shown in FIG. 3 is a general one. Therefore, it can be said that one of the essential parts according to the present embodiment is a program stored in the server 120. Since the hardware operation of server 120 is well known, detailed description will not be repeated.

  Data recording media are not limited to CD-ROMs, FDs (Flexible Disks), and hard disks, but include magnetic tapes, cassette tapes, optical disks (MO (Magnetic Optical Discs) / MDs (Mini Discs) / DVDs (Digital Versatile Discs)), IC (Integrated Circuit) card (including memory card), optical card, mask ROM, EPROM (Electronically Programmable Read-Only Memory), EEPROM (Electronically Erasable Programmable Read-Only Memory), fixed semiconductor memory such as flash ROM A non-volatile data recording medium carrying a program may be used.

  The program here may include not only a program directly executable by the CPU but also a program in a source program format, a compressed program, an encrypted program, and the like.

[data structure]
A data structure of server 120 according to the present embodiment will be described with reference to FIGS. FIG. 4 is a diagram illustrating an aspect of data storage in hard disk 5 of server 120. FIG. 5 is a diagram showing a message output by system 100. FIG. 6 is data defining the time output to the system 100.

  As shown in FIG. 4, in one aspect, the hard disk 5 holds a type 410 and a template 420. Type 410 represents the type of template 420. For example, type 410 may include information representing a preset “standard” and information representing a type of “derivation” representing a variation of the standard. Type 410 may include other classifications.

  Template 420 represents a message defined as output by system 100. The content of the template is defined by the provider of system 100 according to the present embodiment, for example. Derived type templates are defined as utterance content that is considered similar or related to the content of a standard template.

  Referring to FIG. 5, in one aspect, hard disk 5 of server 120 holds message ID (Identification) 510 and template 520. Message ID 510 identifies each template held as template 520. The template 520 is created using, for example, data obtained from a voice actor or other actual speech of one or more humans. The template 520 can be changed regularly or irregularly. In yet another aspect, the utterance of the user of system 100 may be registered as template 520.

  Note that the example shown in FIG. 5 is the content of the utterance relating to the alarm, but the example for realizing the technical idea according to the present embodiment is not limited to the utterance relating to the alarm. For example, air conditioner operation settings (ON, OFF, temperature settings, timer settings, etc.), rice cooker operation settings (start time timer settings, rice cooking mode, etc.), microwave oven operation settings (output, cooking time, etc.) In addition, an utterance for setting the operation of the device may be used.

  With reference to FIG. 6, in one aspect, hard disk 5 holds data ID 610 and time data 620. The data ID 610 identifies each time data defined in the time data 620. The time data 620 is input to the server 120 as an utterance by a voice actor or other actual person, like the message template 520 shown in FIG. In other aspects, the time data 620 may be realized by synthesized sound or by utterance by a user of the system 100.

  With reference to FIG. 7, a configuration of robot 110 according to the present embodiment will be described. FIG. 7 is a block diagram illustrating a hardware configuration of the robot 110. In one aspect, the robot 110 includes an operation panel 710, a microphone 720, a speaker 730, a monitor 740, a controller 750, a memory 760, a motor 770, wheels 780, and a communication I / F 790. The controller 750 includes a voice recognition processor 755.

  The operation panel 710 receives an instruction input to the robot 110. The operation panel 710 is realized as, for example, a touch panel, toggle switch, or other physical switch.

  The microphone 720 receives an input of sound to the robot 110 and outputs a signal corresponding to the sound to the controller 750.

The speaker 730 outputs sound based on a signal sent from the controller 750.
The monitor 740 displays the operation status and other information of the robot 110 based on the signal sent from the controller 750. The monitor 740 is practiced as, for example, a liquid crystal monitor or an organic EL (Electro Luminescence) monitor.

  The controller 750 controls the operation of the robot 110 based on a command sent from the operation panel 710. In another aspect, the controller 750 may control the operation of the robot 110 based on a command included in a signal sent from the microphone 720. In yet another aspect, the controller 750 may control the operation of the robot 110 based on data held in the memory 760 and data received from the outside of the robot 110 via the communication I / F 790.

  The speech recognition processing processor 755 performs speech recognition processing on the signal sent from the microphone 720 and stores the processing result in the memory 760. The voice recognition processor 755 is realized as a CPU or other processor. Further, the voice recognition processor 755 converts a signal given to the controller 750 into a voice signal, and sends the voice signal to the speaker 730. The speaker 730 outputs sound based on the sound signal.

  The memory 760 holds a program for causing the robot 110 to execute a predetermined operation and data necessary for executing the program. The memory 760 is realized by a flash memory, a hard disk, or other storage device. For example, the memory 760 holds a device ID 761 and a user ID 762. The device ID 761 represents a unique identification number given to the robot 110. User ID 762 identifies a user registered as a user of robot 110. The user is, for example, a purchaser or user of the robot 110. The user ID 762 is arbitrarily input by the user, for example.

  The motor 770 is driven based on a signal sent from the controller 750. The motor 770 gives the rotational force to the wheel 780. The wheel 780 is configured to be able to move the operation of the robot 110 by 360 degrees. As the wheel 780 rotates, the robot 110 moves in that direction.

  The communication I / F 790 is connected to a network and mediates communication between another apparatus and the robot 110 via the network. Communication I / F 790 is realized by, for example, a wireless local area network (LAN). The type of communication is not particularly limited.

[Control structure]
With reference to FIGS. 8 to 11, a control structure of system 100 according to the present embodiment will be described. FIG. 8 is a flowchart showing a part of processing executed when system 100 registers the alarm setting. FIG. 9 is a flowchart showing a process for changing the alarm setting. FIG. 10 is a flowchart showing the confirmation process of the alarm setting. FIG. 11 is a flowchart showing a process for canceling the alarm setting. The following processing may be realized by one or more processors included in the system 100, for example. The one or more processors are included in the robot 110 or the server 120, for example.

(Register alarm settings)
Referring to FIG. 8, in step S810, system 100 accepts an input of an utterance requesting alarm setting. For example, the controller 750 of the robot 110 receives an input of an utterance (for example, a message 151) requesting an alarm setting by the user of the robot 110 via the microphone 720.

  In step S820, system 100 performs speech recognition processing on the content of the utterance. For example, in one aspect, the CPU 1 of the server 120 performs speech recognition processing on the content of the utterance as the speech recognition processing unit 220. In another aspect, the speech recognition processing processor 755 of the robot 110 may perform speech recognition processing on the content of the utterance as the speech recognition processing unit 220.

  In step S830, system 100 outputs a voice (for example, message 152) that prompts the user to input a set time based on the content of the utterance. The voice data is realized, for example, as data obtained by recording voice actor voices registered in advance in the system 100 or other data obtained by recording human voices. In another aspect, the voice data may be realized as data obtained by recording the voice of the user of the system 100 or as synthesized sound data. The same applies to data for the system 100 to output sound in the following processing.

  In one aspect, the CPU 1 of the server 120 outputs the sound via the speaker 730 of the robot 110. When the user of the robot 110 is in the vicinity of the robot 110, the user can listen to the sound.

  In step S840, system 100 determines whether the set time has been recognized based on the result of the voice recognition process. More specifically, for example, the controller 750 or the CPU 1 determines whether or not the input set time has been recognized. When system 100 determines that the set time has been recognized (YES in step S840), control is switched to step S870. Otherwise (NO in step S840), system 100 switches control to step S850.

  In step S850, system 100 determines whether the recognition processing for the set time has timed out based on the result of measurement using the internal clock. When system 100 determines that the set time recognition process has timed out (YES in step S850), it ends the process. Otherwise (NO in step S850), system 100 switches control to step S860.

  In step S860, system 100 outputs a message (for example, message 152) prompting the user to speak again by voice. Thereafter, control is returned to step S840.

  In step S870, system 100 associates and stores identification information (for example, device ID 761) of the device (for example, robot 110) and the alarm setting time. For example, in one aspect, the CPU 1 stores the identification information and the alarm setting time in the hard disk 5. In another aspect, the controller 750 of the robot 110 may store the device identification information and the alarm setting time in the memory 760.

  In step S880, system 100 outputs a message (information for confirming the content of the command) that the alarm has been set at the time of utterance by voice (for example, message 154). In one aspect, the speaker 730 of the robot 110 outputs the message by voice based on a signal sent from the server 120. Thereafter, the system 100 ends the registration process.

(Change settings)
Referring to FIG. 9, in step S <b> 910, system 100 detects an input of a message that prompts the user to change the alarm setting based on the result of speech recognition processing for the utterance by the user.

  In step S920, system 100 outputs, by voice, an utterance message at a desired time based on data stored in advance. The voice data is realized, for example, as data obtained by recording voice actor voices registered in advance in the system 100 or other data obtained by recording human voices. In another aspect, the voice data may be realized as data obtained by recording the voice of the user of the system 100 or as synthesized sound data.

  In step S930, system 100 determines whether or not the set time has been recognized based on the result of the voice recognition process for the message. When system 100 determines that the set time has been recognized (YES in step S930), control is switched to step S960. Otherwise (NO in step S930), system 100 switches control to step S940.

  In step S940, system 100 determines whether the set time recognition process has timed out. When system 100 determines that the set time recognition process has timed out (YES in step S940), system 100 outputs a message indicating that the change cannot be made, and ends the change process. Otherwise (NO in step S940), system 100 switches control to step S950.

  In step S950, system 100 again outputs a message that prompts the user to input the time. Thereafter, control is returned to step S930.

  In step S960, system 100 determines whether an input for stopping the setting or the like has been detected based on the result of the speech recognition process. This determination is made based on, for example, whether an instruction to stop the setting is given to the system 100. When system 100 determines that the input has been detected (YES in step S960), control is switched to step S980. Otherwise (NO in step S960), system 100 switches control to step S970.

  In step S970, system 100 determines whether the time is being set. More specifically, the system 100 determines whether or not the time for setting the alarm is stored in the storage unit 240. When system 100 determines that the time is being set (YES in step S970), system 100 switches control to step S990. Otherwise (NO in step S970), system 100 switches control to step S980.

  In step S980, system 100 outputs a voice message indicating that alarm setting has been canceled based on voice data prepared in advance.

  In step S990, system 100 outputs, for example, a message “For example, the alarm clock is still set. I will wake up at XX hour.” Based on the voice data prepared in advance.

(Alarm setting confirmation process)
Referring to FIG. 10, in step S <b> 1010, system 100 detects a user utterance that represents a command to confirm wake-up based on the result of the speech recognition process.

  In step S1020, system 100 refers to storage unit 240 based on the detected user utterance and confirms the contents of the alarm setting. For example, the CPU 1 refers to the hard disk 5 and confirms whether there is an alarm setting associated with the user.

  In step S1030, system 100 determines whether there is a wake-up setting based on the content stored in storage unit 240. When system 100 determines that the alarm setting exists (YES in step S1030), control is switched to step S1040. Otherwise (NO in step S1030), system 100 switches control to step S1050.

  In step S1040, system 100 outputs a message indicating that the alarm is set based on the voice data stored in advance.

  In step S1050, system 100 outputs a message indicating that the alarm is not set based on voice data stored in advance.

(Cancellation of alarm settings)
Referring to FIG. 11, in step S <b> 1110, system 100 detects an input of a user utterance indicating that the alarm setting is canceled based on the result of the voice recognition process.

  In step S1120, system 100 determines whether or not an alarm is set based on detection of the user utterance. For example, the CPU 1 refers to the hard disk 5 and checks whether there is an alarm setting associated with the user. If system 100 determines that the alarm is set (YES in step S1120), control is switched to step S1130. Otherwise (NO in step S1120), system 100 switches control to step S1125.

  In step S1125, system 100 outputs a message indicating that the alarm is not set based on the voice data stored in advance.

  In step S1130, system 100 outputs a message for confirming cancellation of the alarm setting based on the voice data stored in advance.

  In step S1140, system 100 determines whether or not an instruction to execute cancellation has been input. This determination is made based on the content of the signal for system 100. When system 100 determines that the instruction has been input (YES in step S1140), system 100 switches control to step S1160. Otherwise (NO in step S1140), system 100 switches control to step S1150.

  In step S1150, system 100 determines whether or not the current time has timed out. If system 100 determines that the current time has timed out (YES in step S1150), system 100 switches control to step S1180. Otherwise (NO in step S1150), system 100 switches control to step S1155.

  In step S1155, system 100 outputs a message prompting input of an instruction by voice based on voice data stored in advance. Thereafter, control is returned to step S1140.

  In step S1160, system 100 deletes the alarm setting data. For example, the CPU 1 deletes data related to the user stored in the hard disk 5.

  In step S1170, system 100 outputs a message indicating that the alarm setting has been canceled based on the voice data stored in advance.

  In step S1180, system 100 outputs a message indicating that the alarm setting remains, based on the voice data stored in advance.

[data structure]
With reference to FIG. 12, the data structure of server 120 that implements system 100 according to the present embodiment will be described. FIG. 12 is a diagram conceptually showing one mode of data stored in hard disk 5 included in server 120. In one aspect, the hard disk 5 holds a user ID 210, a device ID 1220, a wake-up setting time 1230, and an audio version 1240.

  The user ID 1210 identifies the user of the robot 110. The device ID 1220 identifies the robot.

  Alarm setting time 1230 represents a time at which a device (for example, robot 110A) specified by device ID 1220 should sound an alarm. The voice version 1240 represents an utterance method when uttering the voice output when the alarm is sounded. For example, for the device (robot0010) identified by the user ID 1210 “user001”, the voice by the voice actor A is output.

[Control structure]
The control structure of the system 100 will be further described with reference to FIG. FIG. 13 is a flowchart showing a part of processing executed in the system 100.

  In step S1310, server 120 detects the arrival of the set alarm time based on the output from the built-in clock.

  In step S1320, server 120 reads content data for audio reproduction from storage unit 240. The content data can include, for example, music.

  In step S1330, server 120 generates a sound to be reproduced by robot 110 using the content data and the alarm setting.

  In step S1340, server 120 generates a signal including the generated voice and device ID.

  In step S1350, server 120 transmits the generated signal to robot 110 identified by the device ID.

  In step S1360, robot 110 reproduces the content as an alarm sound based on the received signal. More specifically, for example, the speaker 730 of the robot 110 outputs a message by a certain voice actor as a wake-up sound based on a signal sent from the server 120.

  Note that the sound output from the system 100 is not limited to the sound of a specific voice actor. Further, the output sound is not limited to the sound of the same person, and the sound of each of a plurality of persons may be used. For example, the system 100 may output different sounds at the time of setting the alarm, at the time of changing, at the time of confirmation, and at the time when the set time arrives.

  In another aspect, when the set time arrives, the robot 110 may execute another operation instead of the utterance. For example, when the robot 110 has a cleaning function, the robot 110 may start the cleaning operation.

<Second Embodiment>
Hereinafter, a second embodiment will be described. The system according to the second embodiment is realized by the same configuration as the configuration of the system 100 according to the first embodiment, except as described below. Therefore, the description of the system configuration according to the present embodiment will not be repeated.

  The system according to the second embodiment is realized using an air conditioner, a microwave oven, and other devices. The device includes at least a voice recognition function, a communication function with the server 120, and a voice output function in addition to functions unique to the device (for example, an air conditioning function, a heating function, and the like).

  For example, when the device is an air conditioner, in one aspect, the user can interactively set the operation of the air conditioner (setting, confirmation, change, deletion, etc. of operation start time). In this case, instead of the robot 110, an air conditioner having a communication function and a voice recognition function, a remote controller of the air conditioner, or a communication terminal having a communication function and a voice recognition function with the air conditioner can interact with the user of the air conditioner. .

  In another aspect, the microwave oven may include a voice recognition function. For example, after the user puts the ingredients into the microwave, the name, output and cooking time of the ingredients are spoken to the microwave. For example, first, the user speaks “Hey the gratin.” When the utterance is recognized by the microwave oven or the server 120, the microwave utters, for example, “Okay. I'll heat the gratin. When the user utters “OK”, the microwave speaks “OK. I will heat the gratin for 3 minutes at 1000 w.”, And the microwave starts to operate. After that, when the specified time has passed, the microwave speaks, “I have a gratin. Be careful because it ’s hot.” In this way, for example, a user living alone can enjoy a meal. Note that confirmation, change, cancellation, etc. of the driving time can be realized in the same manner as the confirmation, change, cancellation of the wake-up setting time in the first embodiment.

  In another aspect, a rice cooker may be used. Similar to the robot 110, the rice cooker includes a voice recognition function, a voice output function, and a communication function with the server 120. In this case, the user puts rice in the rice cooker. The user speaks “cook rice”. When the utterance is recognized by the rice cooker or the server 120, the rice cooker utters "I understand. The user speaks, for example, “3 go”. When the utterance is recognized by the rice cooker or server 120, the rice cooker utters "I understand. What time do you eat?" The user speaks, for example, “7 o'clock”. When the utterance is recognized by the rice cooker or the server 120, the rice cooker utters "I understand. I'll cook three times by 7 o'clock." After that, when the rice cooker confirms that the water necessary for cooking is filled, the rice cooker sets a timer and cooks the rice so that the user can eat the rice at 7 o'clock.

  As described above, according to the present embodiment, since the device speaks, the user of the device can use the device while having fun.

<Third Embodiment>
The third embodiment will be described below. The system according to the third embodiment is realized by the same configuration as the configuration of the system 100 according to the first embodiment, except as described below. Therefore, the description of the system configuration according to the present embodiment will not be repeated.

  The system according to the third embodiment is also used in supermarkets, boutiques and other commercial facilities. For example, when the time service before closing is performed, the manager of the commercial facility can set, change, confirm, and cancel (delete) the time for starting the time service for the robot 110. . Alternatively, the robot 110 may be configured to promote promotions for utterances from potential customers.

<Fourth embodiment>
Hereinafter, a fourth embodiment will be described. The system according to the fourth embodiment is realized by the same configuration as the configuration of the system 100 according to the first embodiment, except as described below. Therefore, the description of the system configuration according to the present embodiment will not be repeated.

  The system according to the present embodiment can cause a plurality of robots to utter a notification all at once. That is, the target of realizing the alarm function and other notification functions is not limited to one user. For example, the system 100 may realize the notification function for each of a plurality of robots included in a group created in advance. In this case, the server 120 holds the network address of each robot included in the group, and transmits a wake-up signal to each network address when the designated time arrives. In this way, notification to a plurality of users is realized efficiently.

  In still another aspect, when a certain user makes a response to the notification by utterance, a configuration may be used in which other users included in the group are also notified of this.

<Fifth embodiment>
The fifth embodiment will be described below. The system according to the fifth embodiment is realized by the same configuration as the configuration of the system 100 according to the first embodiment, except as described below. Therefore, the description of the system configuration according to the present embodiment will not be repeated.

  In the system according to the present embodiment, the content spoken by the robot 110 is not limited to a message related to the alarm time setting. The robot 110 can utter a message other than an alarm clock. For example, the robot 110 may utter a message for notification such as a message “There is an electrical equipment inspection today. A power failure will occur from 1 to 2”.

  Such an utterance can be realized by either a push type or a pull type. For example, in the push type, the server 120 reads the user's schedule and notifies the user's robot 110 of the corresponding schedule. In the case of the pull type, when the user makes an utterance asking the schedule such as “What is the schedule for today?” And the utterance is recognized by the server 120 or the robot 110, the server 120 determines the schedule of the user. If the corresponding schedule exists, the contents of the schedule are output by voice. With such a configuration, the user can use the robot 110 as a secretary.

  In another aspect, when a schedule involving other users is retrieved, the robot 110 utters “There is an appointment with Mr. A” to the user. When the user replies “OK”, the reply is sent from the robot 110 to the server 120. When the server 120 recognizes the user's response, the server 120 utters "There is a promise with Mr. X (the user of the robot 110)" through another robot used by the other user. When Mr. A answers “OK”, the response is sent from the robot used by Mr. A to the server 120. The server 120 speaks to the robot 110 “Mr. A confirmed the promise”. This ensures that a schedule shared by a plurality of users is implemented.

<Sixth Embodiment>
Hereinafter, a sixth embodiment will be described. The system according to the sixth embodiment is realized by the same configuration as the configuration of the system 100 according to the first embodiment, except as described below. Therefore, the description of the system configuration according to the present embodiment will not be repeated.

  The system according to the present embodiment has a learning function. For example, the system may store a history of alarm settings for each user. In addition, when the time of the alarm setting by the user is different from the normal time, the system confirms whether the alarm setting time is correct based on the history (for example, “true? ?)). When such an utterance is output, the user confirms again whether or not the utterance time is correct, so that an incorrect time setting can be prevented.

<Seventh embodiment>
The seventh embodiment will be described below. The system according to the seventh embodiment is realized by the same configuration as the configuration of the system 100 according to the first embodiment, except as described below. Therefore, the description of the system configuration according to the present embodiment will not be repeated.

  The system according to the present embodiment differs from the above-described embodiment in that the voice data once transmitted from the server 120 to the robot 110 and used by the robot 110 is stored in the robot 110 and reused by the robot 110. Different.

  That is, the robot 110 stores a message including a voice actor or other person's utterance and an ID for identifying the message. Based on the arrival of a preset alarm time, the robot 110 outputs a message by voice or sings a predetermined song. Thereafter, when the robot 110 receives an instruction including an ID, it is confirmed whether or not the ID included in the received instruction is stored in the robot 110. When the robot 110 confirms that the ID is stored in the robot 110, the robot 110 outputs a message or music associated with the stored ID by voice. In this way, even when communication between the server 120 and the robot 110 is unstable, the robot 110 reliably utters a message at a set time using locally stored data. be able to.

<Eighth Embodiment>
The eighth embodiment will be described below. The system according to the eighth embodiment is realized by the same configuration as the configuration of the system 100 according to the first embodiment, except as described below. Therefore, the description of the system configuration according to the present embodiment will not be repeated.

  The system according to the present embodiment is different from the systems according to the above-described embodiments in that the robot 110 can output a plurality of types of sounds. For example, the server 120 holds in advance voice data for outputting the voices of a plurality of voice actors. The user transmits to the server 120 information indicating which voice actor wants to speak using voice. The information includes the voice actor ID. Upon receiving the information, the server 120 extracts the voice actor ID, generates a message using the voice of the voice actor as a message for the user, and transmits the message to the robot 110. In this way, the user can enjoy alarming with the voice of the desired voice actor.

  In another aspect, the server 120 may output an utterance by any one of a plurality of voice actors to the robot 110 at random. The random output can be realized using a random number generated by a random number generator, for example. In this way, since the user of the robot 110 cannot know in advance which voice actor will wake up from the robot 110, in addition to the normal alarm function, the user of the robot 110 can enjoy a little surprise.

[Configuration summary]
As described above, the technical features according to the present disclosure can be summarized as the system 100, the server 120, and the robot 110, for example, as follows.

  (1) According to an embodiment, a system 100 for operating a robot 110 by speaking is provided. The system 100 includes a plurality of robots (for example, robots 110A, 110B,..., 110N) that accept utterances, and a server 120 that can communicate with the plurality of robots 110. The robot 110 includes a voice input unit (for example, a microphone 720) for receiving an utterance, and a transmission unit (for example, a communication I / F 790) for transmitting the identification information of the robot 110 and the content of the received utterance to a server. Is provided. The server transmits the hard disk 5 for holding the identification information and the content of the utterance, the generation unit (for example, the CPU 1) for generating a command corresponding to the content of the utterance, and the identification information and the command to the robot 110. The transmission part (for example, communication I / F7) is provided. The robot 110 includes a receiving unit (for example, a communication I / F 790) for receiving a command from the server, and an operation unit (for example, a motor 770 and a wheel 780) that executes an operation based on the command.

  (2) According to another embodiment, a server 120 for controlling the robot 110 is provided. This server 120 includes a communication I / F 7 for accepting utterance contents via a plurality of robots 110, a hard disk 5 for associating and holding the identification information of the robot 110 and the utterance contents, and the utterance contents. The CPU 1 for generating a corresponding command and the communication I / F 7 for transmitting the command to the robot 110 specified by the identification information associated with the content of the utterance for generating the command.

  (3) In another aspect, the communication I / F 7 transmits information for confirming the command to the robot 110.

  (4) In another aspect, the communication I / F 7 is based on the content of the utterance from the robot 110, and the robot is specified by the identification information associated with the content of the utterance for generating the command. 110.

  (5) In another aspect, the server 120 is configured to further hold audio data for causing the at least one robot 110 to output audio. The communication I / F 7 further transmits voice data to at least one robot 110.

  (6) In another aspect, the server is configured to hold a plurality of audio data. The communication I / F 7 is configured to accept an utterance input for selecting any one of the plurality of voice data. The CPU 1 generates a command using the selected audio data.

  (7) In another aspect, the robot 110 is configured to determine whether or not the speaker is a user registered in the robot 110 based on the utterance. When the speaker is a user, the communication I / F 7 of the server 120 receives the identification information of the robot 110 and the accepted utterance.

  (8) According to another embodiment, in one aspect, the robot 110 includes a communication I / F 790 for communicating with the server 120, a microphone 720 for receiving an utterance, and an operation unit that executes the operation of the robot 110. (For example, a motor 770 and wheels 780).

  Communication I / F 790 transmits the content of the utterance accepted by microphone 720 to server 120, and receives a command corresponding to the content of the utterance from server 120. The operation unit executes an operation based on the received command. For example, the wheel 780 rotates according to the operation of the motor 770 and moves the robot 110.

  (9) In another aspect, the robot 110 further includes a receiving unit (for example, a communication I / F 790) configured to receive audio data for outputting audio from the server. The operation unit includes an audio output unit (for example, a speaker 730) for outputting audio based on the audio data.

  (10) In another aspect, the robot 110 stores a memory for storing voice data and a voice data for outputting the next utterance when the next utterance is given to the robot 110. A confirmation unit (for example, a controller 750) for confirming whether or not the When audio data to be transmitted is stored in the robot 110, the speaker 730 outputs audio based on the audio data stored in the memory.

  (11) In another aspect, the server 120 is configured to hold a plurality of audio data. The microphone 720 receives an input of an utterance that selects any one of the plurality of audio data. The controller 750 generates a command using the selected audio data as a generation unit. The speaker 730 outputs sound based on the selected sound data.

  (12) In another aspect, the robot 110 transmits a signal for controlling the device to another device (for example, another robot) that can communicate with the server based on the command.

  (13) In another aspect, the robot 110 further includes an authentication unit for determining whether the speaker is a user registered in the robot 110 based on the utterance. The authentication unit is realized, for example, when the controller 750 executes an authentication process. When the speaker is a user, the communication I / F 790 transmits the identification information of the robot 110 and the received utterance to the server 120.

  (14) In another aspect, the robot 110 further includes a human sensor and a moving unit (for example, a wheel 780) for moving to the vicinity of the user based on an output from the human sensor.

  (15) Preferably, the human sensor is configured to be activated in accordance with an instruction from the server.

  (16) According to another embodiment, a server control method for controlling an electronic device is provided. The control method includes a step of accepting the content of the utterance via the plurality of robots 110, a step of holding the identification information of the robot 110 and the content of the utterance in association with each other, a step of generating a command according to the content of the utterance, Transmitting the command to the robot 110 specified by the identification information associated with the content of the utterance for generating the command.

  As described above, according to each of the above-described embodiments, one server 120 transmits a command to each of a plurality of electronic devices (for example, robots 110A, 110B,... 110N), and the utterance content from each electronic device. The operation according to is performed.

  In another aspect, one function in the server 120 may be operated by a plurality of electronic devices. In that case, various settings of the function may be performed for each electronic device.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

  1 CPU, 2 mouse, 3 keyboard, 4 RAM, 5 hard disk, 6 optical disk drive, 8,740 monitor, 9 ROM, 100 system, 110, 110A, 110B, 110N robot, 120 server, 130 Internet, 210 voice input unit , 220 voice recognition processing unit, 230 extraction unit, 240 storage unit, 250 operation unit, 251 voice output unit, 260 command generation unit, 270 timing unit, 410 type, 420,520 template, 620 time data, 710 operation panel, 720 Microphone, 730 speaker, 750 controller, 755 voice recognition processor, 760 memory, 770 motor, 780 wheel.

Claims (17)

A system for operating an electronic device by speaking,
A plurality of electronic devices that accept the utterance;
A server capable of communicating with the plurality of electronic devices,
The electronic device is
Voice input means for accepting the utterance;
Transmission means for transmitting the identification information of the electronic device and the content of the accepted utterance to the server,
The server
Storage means for associating and holding the content of the utterance including the identification information and time setting;
Generating means for generating an instruction based on the time setting corresponding to the identification information among the time settings held in the storage means for the contents of the utterance not including the time setting;
A transmission means for transmitting the identification information and the command to the electronic device,
The generating means includes
When receiving an utterance of the content to cancel the command based on the time setting from the electronic device, generate an output command of a message confirming cancellation of the command to the electronic device,
When an utterance with the content of canceling the cancellation of the command is received as a response to the message from the electronic device, a message output command including a time setting corresponding to the identification information of the electronic device is sent to the electronic device Is configured to generate
The electronic device is
Receiving means for receiving the command from the server;
An operation means for executing an operation based on the instruction. A server for controlling an electronic device,
Input means for accepting the content of an utterance via a plurality of the electronic devices;
Storage means for associating and holding the content of the utterance including identification information and time setting of the electronic device;
Generating means for generating an instruction based on the time setting corresponding to the identification information among the time settings held in the storage means for the content of the utterance not including the time setting;
Transmission means for transmitting the command to the electronic device specified by the identification information associated with the content of the utterance for generating the command ,
The generating means includes
When receiving an utterance of the content to cancel the command based on the time setting from the electronic device, generate an output command of a message confirming cancellation of the command to the electronic device,
When an utterance with the content of canceling the cancellation of the command is received as a response to the message from the electronic device, a message output command including a time setting corresponding to the identification information of the electronic device is sent to the electronic device Ru is configured to generate a server.   The server according to claim 2, wherein the transmission unit transmits information for confirming the command to the electronic device.   The transmission means transmits the command to the electronic device specified by the identification information associated with the content of the utterance for generating the command based on the content of the utterance from the electronic device. The server according to claim 2. The server is configured to further hold audio data for causing the at least one electronic device to output audio,
The server according to claim 2, wherein the transmission unit is configured to further transmit the audio data to the at least one electronic device. The server is configured to hold a plurality of the audio data;
The input means is configured to accept an input of an utterance for selecting any one of the plurality of voice data.
The server according to claim 5, wherein the generation unit is configured to generate the command using the selected voice data. The electronic device is configured to determine whether the speaker is a user registered in the electronic device based on the utterance,
The voice according to claim 2, wherein when the speaker is the user, the input unit is configured to receive the identification information of the electronic device and the received utterance. Recognition server. Electronic equipment,
A communication means for communicating with the server;
Voice input means for accepting utterances;
Operating means for executing the operation of the electronic device,
The communication means includes
Transmitting the content of the utterance accepted by the voice input means to the server;
Based on the content of the utterance including the time setting transmitted to the server in the past, the command generated by the server according to the content of the utterance not including the time setting is received from the server,
Based on the content of the utterance to cancel the content of the utterance including the time setting transmitted to the server in the past, the output command of the message confirming the cancellation generated by the server is received,
Receiving a message output command including a time setting generated by the server and transmitted to the server in the past, based on the utterance of the content to cancel the cancellation in response to the message;
The operation means is an electronic device that performs an operation based on a received command. Receiving means configured to receive voice data for outputting voice from the server;
The electronic apparatus according to claim 8, wherein the operation unit includes an audio output unit for outputting audio based on the audio data. A memory for storing the audio data;
When the next utterance is given to the electronic device, it further comprises confirmation means for confirming whether audio data for outputting the next utterance is stored in the memory,
The audio output means is configured to output audio based on audio data stored in the memory when the audio data to be transmitted is stored in the electronic device. 9. The electronic device according to 9. The server is configured to hold a plurality of the audio data;
The voice input means is configured to accept an input of an utterance that selects any one of the plurality of voice data.
The server generates the command using the selected voice data,
The electronic device according to claim 9, wherein the sound output unit is configured to output sound based on the selected sound data.   12. The transmitter according to claim 8, further comprising: a transmission unit configured to transmit a signal for controlling the device to another device capable of communicating with the server based on the command. The electronic device described. Further comprising authentication means for determining whether or not the speaker is a user registered in the electronic device based on the utterance;
The communication means is configured to transmit the identification information of the electronic device and the accepted utterance to the server when the utterer is the user. The electronic device described. With human sensor,
The electronic device according to any one of claims 8 to 13, further comprising moving means for moving to a vicinity of a user based on an output from the human sensor.   The electronic device according to claim 14, wherein the human sensor is configured to be activated in accordance with an instruction from the server. A server control method for controlling an electronic device,
Receiving utterance content via a plurality of the electronic devices;
A step of associating and holding the content of the utterance including identification information of the electronic device and time setting;
Generating a command based on a time setting corresponding to the identification information among the held time settings for the content of the utterance not including a time setting;
Transmitting the command to the electronic device specified by the identification information associated with the content of the utterance for generating the command ,
Generating the instructions comprises:
Generating an output command for a message for confirming cancellation of the command to the electronic device when an utterance of the content to cancel the command based on the time setting is received from the electronic device;
When an utterance with the content of canceling the cancellation of the command is received as a response to the message from the electronic device, a message output command including a time setting corresponding to the identification information of the electronic device is sent to the electronic device Generating a server.   A program for causing a computer to execute the method according to claim 16.

Images