Information processing device and information processing method

Abstract

An information processing device (1) includes: a voice data input device (microphone (11)) to which voice data is input; a user data input device (input device (10)) to which user data is input; and a controller (20). The controller (20) recognizes first voice data input to the voice data input device (microphone (11)), outputs second voice data indicating control of a predetermined device based on the result of recognizing the first voice data, controls the predetermined device based on the result of recognizing after notification of the second voice data is completed, and, on the other hand, when user data indicating suspension of control of the predetermined device is input during the period of notifying the second voice data, suspends control of the predetermined device.

Description

Technical Field

[0001] The present invention relates to an information processing device and an information processing method. Background Art

[0002] Conventionally, there are known inventions for controlling devices such as remote controls using a user's voice (Patent Document 1). The invention described in Patent Document 1 recognizes the user's voice and displays control details corresponding to the user's instructions on the remote control. The user confirms the control details displayed on the remote control, and the control is executed after the user approves the control details.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 2007-286174 Summary of the Invention

[0006] Problems to be solved by the invention

[0007] However, the invention described in Patent Document 1 requires the user to confirm the control content and to approve it, and therefore has a problem in that it takes time to actually execute the control.

[0008] The present invention has been made in view of the above-mentioned problems, and an object of the present invention is to provide an information processing device and an information processing method that suspend control only when necessary and execute control quickly and automatically unless there is an instruction to suspend.

[0009] Solutions for solving problems

[0010] An information processing device involved in one embodiment of the present invention recognizes first voice data input into a voice data input device, outputs second voice data indicating control of a specified device based on the result of recognizing the first voice data, controls the specified device based on the result of recognition after notification of the second voice data is completed, and on the other hand, when user data indicating termination of control of the specified device is input during the period of notifying the second voice data, the control of the specified device is terminated.

[0011] Effects of the Invention

[0012] According to the present invention, control is suspended only when necessary and is executed quickly and automatically as long as there is no suspension instruction. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a block diagram of an information processing device 1 according to an embodiment of the present invention.

[0014] Figure 2This is a sequence diagram for explaining an operation example of the information processing device 1 according to the embodiment of the present invention.

[0015] Figure 3 This is a diagram for explaining a display example of the display 12 .

[0016] Figure 4 FIG. 1 is a diagram showing that the voice recognition function has been activated.

[0017] Figure 5 This is a display example during the period when the speaker 31 is notifying the audio data for feedback.

[0018] Figure 6 This is a diagram for explaining an example of an operation performed by a user to stop the control by the controller 20 .

[0019] Figure 7 This is a diagram for explaining another example of the operation performed by the user to stop the control by the controller 20 .

[0020] Figure 8 This is a diagram for explaining another example of the operation performed by the user to stop the control by the controller 20 .

[0021] Figure 9 This is a diagram for explaining another example of the operation performed by the user to stop the control by the controller 20 .

[0022] Figure 10 It is a configuration diagram of an information processing device 2 according to a modified example of the present invention.

[0023] Figure 11 This is a sequence diagram for explaining an operation example of the information processing device 2 according to the modification of the present invention.

[0024] Figure 12 This is a sequence diagram for explaining an operation example of the information processing device 2 according to the modification of the present invention. DETAILED DESCRIPTION

[0025] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the description of the drawings, the same reference numerals are given to the same parts and the description thereof will be omitted.

[0026] Reference Figure 1 The following describes a configuration example of the information processing device 1 according to this embodiment. As an example, the information processing device 1 is mounted on a vehicle. Figure 1 As shown, the information processing device 1 includes an input device 10 , a controller 20 , a database 30 , and a speaker 31 .

[0027] The input device 10 is a general term for a device that receives data from a user riding in a vehicle. Figure 1 As shown, the input device 10 includes a microphone 11, a touch panel 12, a switch 13, and a camera 14. The microphone 11 is input with the user's voice data. The microphone 11 is set, for example, near the driver's seat. The touch panel 12 receives inputs made by the user's touch operation. The touch panel 12 is mainly used as a display of the navigation device. The switch 13 is set on the steering wheel and receives the user's input (the switch is turned on). The camera 14 is set, for example, near the driver's seat and captures the user's posture, gestures, etc. The data input to the input device 10 is sent to the controller 20.

[0028] The controller 20 is a general-purpose computer equipped with a CPU (Central Processing Unit), memory, storage device, input / output units, and the like. The controller 20 processes data received from the input device 10. Specifically, the CPU reads various programs stored in the storage device into the memory and executes the various commands contained in the programs. Thus, the controller 20 functions as one of the multiple information processing circuits included in the information processing device 1. The controller 20 includes a speech recognition unit 21, a speech output unit 22, a notification end determination unit 23, and a control signal transmission unit 24 as multiple information processing circuits.

[0029] The speech recognition unit 21 recognizes the user's speech data input to the microphone 11 . The speech recognition uses a well-known technique such as frequency analysis. The speech recognition unit 21 outputs the recognition result to the speech output unit 22 .

[0030] The voice output unit 22 refers to the database 30 to obtain voice data for feedback corresponding to the recognition result of the voice recognition unit 21. The voice data for feedback is related to the control of the specified equipment to be implemented later, and is used to urge the user to confirm. For example, when the user's voice data is recognized as "open the driver's window", the corresponding voice data for feedback is "open the driver's window". A plurality of voice data for feedback are prepared and stored in the database 30. In addition, in this embodiment, it is assumed that the database 30 is stored in a storage device different from the storage device of the controller 20, but it is not limited to this. The database 30 can also be stored in the storage device of the controller 20.

[0031] The voice output unit 22 notifies the user of the voice data for feedback via the speaker 31. Alternatively, the voice output unit 22 may generate voice data for feedback each time based on the recognition result of the voice recognition unit 21. The generation method may be to program the unit 22 so as to generate voice data that repeats the user's voice data.

[0032] When the output of the voice data for feedback begins, the voice output unit 22 transmits a signal indicating the start of the output to the notification end determination unit 23. Furthermore, when the output of the voice data for feedback ends, the voice output unit 22 transmits a signal indicating the end of the output to the notification end determination unit 23. Hereinafter, the signal indicating the start of the output may be simply referred to as the start signal. Similarly, the signal indicating the end of the output may be simply referred to as the end signal.

[0033] The notification end determination unit 23 determines whether the notification by the voice output unit 22 has ended. Specifically, if the voice output unit 22 receives an end signal after receiving a start signal, the notification end determination unit 23 determines that the notification by the voice output unit 22 has ended. On the other hand, if the voice output unit 22 receives a start signal but does not subsequently receive an end signal, the notification end determination unit 23 determines that the notification by the voice output unit 22 has not ended. If the notification end determination unit 23 determines that the notification by the voice output unit 22 has ended, it transmits a signal indicating that the notification has ended to the control signal transmission unit 24.

[0034] When receiving a signal indicating that the notification has ended from the notification end determination unit 23, the control signal transmission unit 24 controls a predetermined device based on the user's instruction (voice data) obtained from the recognition result of the voice recognition unit 21. The predetermined device is a device mounted on the vehicle, such as Figure 1 As shown, the vehicle includes power windows 32, an air conditioner 33, a sunroof 34, a sun visor 35, a power tailgate 36, a power trunk 37, a navigation system 38, and an audio system 39. For example, if the user instructs "Open the driver's window," the control signal transmitter 24 transmits a signal to the driver's power window 32 to open the window. The power window 32 automatically opens based on the received signal. Furthermore, the specified equipment may also include equipment for driving control, such as automated driving.

[0035] Next, refer to Figures 2 to 9 An operation example of the information processing device 1 will be described.

[0036] exist Figure 2 In step S101 shown, the user in the vehicle activates the voice recognition function. In this embodiment, the voice recognition function is not always activated. The voice recognition function is activated according to the user's instruction. Figure 3 An example of how to start the voice recognition function is described below. Figure 3As shown, during driving, route guidance provided by the navigation device 38 is displayed on the touch panel 12. An icon 50 representing a speech is displayed on the touch panel 12. The voice recognition function is activated by the user touching the icon 50. As another activation method, a switch 13 provided on the steering wheel may have an activation trigger function, or the recognition of a user's speech using a predetermined keyword may be used as a trigger to activate the voice recognition function.

[0037] When the voice recognition function is activated, the display of the touch panel 12 switches to Figure 4 As shown in the content. Figure 4 As shown in FIG, after the voice recognition function is activated, icons 51, 52, and devices capable of being instructed by voice are displayed on the touch panel 12. Figure 4 In FIG, an air conditioner, a power window, a navigation device, and an audio device are displayed as devices that can be instructed by voice, but this is only an example.

[0038] Figure 4 The icon 52 shown is an icon indicating that voice recognition is possible. After confirming that the icon 52 is displayed on the touch panel 12, the user inputs an instruction for causing the specified device to operate by voice. Figure 2 As shown in step S103, the user inputs voice data toward the microphone 11. Figure 2 In the example, the user's instruction is "open the driver's window".

[0039] The processing proceeds to step S105, and the voice recognition unit 21 that has obtained the user's voice data recognizes the voice data. The processing proceeds to step S107, and the voice output unit 22 refers to the database 30 to obtain voice data for feedback corresponding to the recognition result of the voice recognition unit 21. The user's instruction is recognized as "open the driver's window", so "open the driver's window" is selected as the voice data for feedback. The voice output unit 22 notifies the user of the voice data for feedback through the speaker 31. When the notification of the voice data for feedback is started, that is, when the output of the voice data for feedback from the speaker 31 is started, the display of the touch panel 12 is switched to Figure 5 The content shown.

[0040] The process proceeds to step S109, where the notification end determination unit 23 determines whether the notification by the voice output unit 22 has ended. If the notification end determination unit 23 receives an end signal after receiving a start signal from the voice output unit 22, the notification end determination unit 23 determines that the notification by the voice output unit 22 has ended. Figure 2 In the example, the completion of the notification by the voice output unit 22 means that the output of the voice data "Open the driver's window" has been completed.

[0041] When a start signal is received from the voice output unit 22 but no end signal is received thereafter, the notification end determination unit 23 determines that the notification by the voice output unit 22 has not ended. In other words, when a start signal is received from the voice output unit 22 but no end signal is received thereafter, the notification end determination unit 23 determines that the voice data for feedback is being notified from the speaker 31.

[0042] If the notification by the voice output unit 22 is determined to have ended (step S109: No), the process proceeds to step S111. In step S111, the notification completion determination unit 23 transmits a signal indicating the completion of the notification to the control signal transmission unit 24. Upon receiving this signal, the control signal transmission unit 24 transmits a control signal to the driver's power window 32 to open the window. The process proceeds to step S113, and the power window 32, having received the control signal, automatically opens (step S115).

[0043] On the other hand, when it is determined that the notification by the audio output unit 22 has not ended (step S109 : YES), the process proceeds to step S119 .

[0044] In step S119, when a signal indicating the termination of control is received from the user during the period of notifying the voice data for feedback from the speaker 31 (step S119: "Yes"), the controller 20 terminates the control of the specified device (step S121). Here, the signal indicating the termination of control (hereinafter sometimes referred to as the termination signal) is explained. The termination signal is a signal sent to the controller 20 when the user performs a specified operation. When the user instructs "open the driver's window" through voice, the user receives the feedback of "open the driver's window" through the speaker 31. At this time, assuming that there is an error in the voice recognition, it can be imagined that the control is terminated as the user's expectation. Figure 2 In the example shown, the user's voice instruction is correctly recognized, but there may be cases where the user's voice instruction is not correctly recognized, such as "open the passenger window." In this case, it is conceivable that the control is suspended as the user's desire.

[0045] In this embodiment, as long as the voice data for feedback is being notified from the speaker 31, the user can send a stop signal to the controller 20 through a plurality of methods, thereby being able to stop the control by the controller 20. On the other hand, when the notification by the voice output unit 22 has ended, the user can no longer send a stop signal to the controller 20, or even if the user can send the stop signal, the controller 20 will not accept the stop signal. Therefore, in order to stop the control by the controller 20, the user needs to perform a prescribed operation during the period during which the voice data for feedback is being notified from the speaker 31. In addition, the period during which the voice data for feedback is being notified from the speaker 31 is defined as the period from when the notification end determination unit 23 receives a start signal from the voice output unit 22 to when it receives an end signal.

[0046] Reference Figures 6 to 9 A predetermined operation performed by the user to stop the control by the controller 20 will be described.

[0047] like Figure 6 As shown, the user can terminate the control performed by the controller 20 by touching icon 51 displayed on the touch panel 12. Specifically, when the user touches icon 51 while the speaker 31 is transmitting voice data for feedback, a termination signal is transmitted to the controller 20. Upon receiving the termination signal, the controller 20 does not transmit a control signal for opening the power window 32. As a result, the control performed by the controller 20 is terminated. Icon 51 is a so-called return icon.

[0048] In addition, if Figure 7 As shown, the user can stop the control by the controller 20 by touching the icon 54 displayed on the touch panel 12. Specifically, when the user touches the icon 54 while the voice data for feedback is being notified from the speaker 31, a stop signal is sent to the controller 20. In addition, the text "Stop" is displayed on the icon 54.

[0049] Or, as Figure 8 As shown, the user can suspend the control by the controller 20 by sliding the touch panel 12. Sliding refers to the operation of sliding the finger while touching the touch panel 12. When the user swipes the touch panel 12 during the notification of voice data for feedback from the speaker 31, a suspension signal is sent to the controller 20. Figure 8 In the example shown, the screen is swiped from left to right, but this is not limiting. The user can also swipe from top to bottom or from right to left. Regardless of the swipe direction, if the screen is swiped while the feedback voice data is being transmitted from the speaker 31, a stop signal is sent to the controller 20.

[0050] Or, as Figure 9 As shown, the user can press a specific switch ( Figure 9 The control by the controller 20 is terminated by pressing the switch 61 in the control panel. Specifically, when the user presses the switch 61 during the notification of the voice data for feedback from the speaker 31, a termination signal is sent to the controller 20. The switch 61 is a so-called return switch.

[0051] Alternatively, the user can terminate the control performed by the controller 20 using voice. Specifically, when the user indicates "terminate" by voice to the microphone 11 while the voice data for feedback is being notified from the speaker 31, the control performed by the controller 20 is terminated. When voice data is input while the voice data for feedback is being notified from the speaker 31, the voice recognition unit 21 recognizes the input voice data. If the recognized voice data indicates termination of control, the controller 20 terminates the control. In this case, the voice data input while the voice data for feedback is being notified from the speaker 31 serves as a termination signal.

[0052] As another example, the user can use a gesture to terminate control by controller 20. Specifically, if the user makes a gesture indicating termination in front of camera 14 while voice data for feedback is being transmitted from speaker 31, a termination signal is transmitted to controller 20. As an example, the termination gesture is a gesture of covering the area in front of camera 14 with one's hand. If image data is input from camera 14 while voice data for feedback is being transmitted from speaker 31, controller 20 analyzes the image data. If a termination gesture is detected in the image data, controller 20 terminates control. In this case, the image data input while voice data for feedback is being transmitted from speaker 31 serves as the termination signal.

[0053] Furthermore, factors that may cause control to be suspended are not limited to misrecognition of voice data. For example, the user may wish to cancel an instruction. In other words, there may be cases where the user has given a voice instruction to "open the driver's window" but simply wishes to cancel the instruction. In this case, as described above, the user can simply perform the specified operation while the voice data for feedback is being transmitted from speaker 31.

[0054] Back to Figure 2 In step S117, if the user performs an operation for transmitting a stop signal while the voice data for feedback is being notified from the speaker 31, the stop signal is transmitted to the controller 20. Steps S119 and S121 have already been described. Figure 2The example shown is a case where a stop signal is sent, but of course there are cases where a stop signal is not sent. If the user does nothing while the voice data for feedback is being notified from the speaker 31, then a stop signal is not sent. In this case, the window is opened quickly after the notification is completed.

[0055] exist Figure 2 In step S109, the completion of the notification by the audio output unit 22 means that the notification is completed without a stop signal being sent from the user during the period of notification of the audio data for feedback from the speaker 31.

[0056] In addition, the description assumes that the user can no longer send a stop signal to the controller 20 when the notification by the voice output unit 22 has ended, and this is supplemented. When the notification by the voice output unit 22 has ended, the display of the touch panel 12 changes from Figure 5 The displayed content switches to Figure 3 Therefore, when the notification by the voice output unit 22 has ended, the user can no longer use the touch panel 12 to send a stop signal.

[0057] (Effect)

[0058] As described above, according to the information processing device 1 according to this embodiment, the following operational effects can be obtained.

[0059] The information processing device 1 includes: a voice data input device (microphone 11), to which voice data of a user riding in a vehicle is input; a user data input device (microphone 11, touch panel 12, switch 13, camera 14), to which user data is input by the user; and a controller 20. The controller 20 recognizes first voice data input to the voice data input device. The first voice data is voice data representing an instruction for causing a specified device to operate, and an example is the above-mentioned "open the driver's window". Based on the recognition result of the first voice data, the controller 20 outputs second voice data indicating control of the specified device from the speaker 31. An example of the second voice data is the above-mentioned "open the driver's window".

[0060] After the second voice data notification is complete, controller 20 controls the specified device based on the recognition result. On the other hand, if user data indicating the termination of control of the specified device is input during the second voice data notification period, control of the specified device is terminated. The user data indicating the termination of control is the aforementioned termination signal. According to information processing device 1 with such a structure, after feedback is provided to the user, control is executed quickly and automatically unless the user indicates termination. Furthermore, the user can terminate control as needed.

[0061] The predetermined devices are devices installed in the vehicle and include at least one of the power windows 32 , the air conditioner 33 , the sunroof 34 , the sun visor 35 , the power tailgate 36 , the power trunk 37 , the navigation device 38 , and the audio device 39 .

[0062] The notification based on the second voice data is a notification indicating that a predetermined device is to be controlled. As an example, the notification based on the second voice data is a notification indicating that the power window 32 is to be opened.

[0063] If no user data indicating the termination of control of a specified device is input and the notification based on the second voice data ends, the controller 20 continues to control the specified device. Thus, after providing feedback to the user, control is quickly and automatically executed unless there is a user termination instruction. Furthermore, if no user data indicating the termination of control of a specified device is input and the notification based on the second voice data ends, the controller 20 does not accept any further user data input and continues to control the specified device.

[0064] The user data is data indicating that the user has operated the touch panel 12 , image data obtained by capturing the user's posture, data indicating that the user has operated the switch 61 provided on the steering wheel, or voice data input to the voice data input device.

[0065] After the notification of the second voice data is completed is defined as after the output of the second voice data ends, and the period of notifying the second voice data is defined as the period from the start to the end of the output of the second voice data.

[0066] (Variation)

[0067] Next, refer to Figure 10 A modification of this embodiment will be described.

[0068] Compared to information processing device 1, information processing device 2 according to the modification further includes a determination unit 25 and a standby time setting unit 26. Configurations that overlap with those of information processing device 1 are denoted by reference numerals and their descriptions are omitted. The following description focuses on the differences.

[0069] The determination unit 25 determines a device that the user can use from the input device 10. The "usable device" referred to here means a device that can be used to stop the control performed by the controller 20. In other words, the "usable device" means a device that can be used while the speaker 31 is notifying the voice data for feedback.

[0070] exist Figure 10In FIG, a microphone 11, a touch panel 12, a switch 13, and a camera 14 are shown as input devices 10. However, not all of these may be available at all times. They may not be available due to a malfunction or other reasons. Alternatively, they may not be available due to some limitation. Whether they are available can be determined by the presence or absence of a signal indicating normal operation.

[0071] When receiving signals indicating normal operation from microphone 11, touch panel 12, switch 13, and camera 14, determination unit 25 can determine that the device is usable while the feedback voice data is being notified from speaker 31. Determination unit 25 transmits a signal indicating the determination result to standby time setting unit 26.

[0072] The standby time setting unit 26 sets the standby time based on the signal received from the determination unit 25. The standby time is the time during which a cancellation signal from the user is accepted after the notification by the voice output unit 22 has ended. In the above embodiment, the controller 20 is described as not accepting a cancellation signal when the notification by the voice output unit 22 has ended. However, in a modified example, a cancellation signal is accepted within the set standby time even after the notification by the voice output unit 22 has ended. For example, if the notification by the voice output unit 22 lasts for 2 seconds and the standby time set by the standby time setting unit 26 is 3 seconds, in the modified example, the time during which the user can send a cancellation signal is 5 seconds (2 seconds + 3 seconds).

[0073] Next, the method for setting the standby time will be explained. The standby time is set based on the available devices determined by determination unit 25. For example, assume that the only available device determined to be available is camera 14. In this case, the standby time is set longer than if other devices were determined. This is because the user needs to shield camera 14 with their hand in order to send a pause signal, and this ensures the time required for this action. This standby time is referred to as the first standby time.

[0074] Next, assume that the only device identified as usable is microphone 11. In this case, the waiting time is set shorter than when camera 14 is identified. This is because the time required to speak is shorter than when blocking the view of camera 14 with one's hand. This waiting time is referred to as the second waiting time.

[0075] Next, assume that the only device identified as usable is touch panel 12. In this case, the waiting time is set shorter than when camera 14 is identified. This is because operating touch panel 12 takes less time than blocking camera 14 with a hand. This waiting time is referred to as the third waiting time.

[0076] Next, assume that the only device identified as usable is switch 13 (switch 61). In this case, the waiting time is set shorter than when camera 14 is identified. This is because operating switch 61 takes less time than blocking camera 14 with a hand. This waiting time is referred to as the fourth waiting time.

[0077] The relationship between the first to fourth standby times is: first standby time>second standby time>third standby time>fourth standby time.

[0078] Next, refer to Figures 11 and 12 An example of the operation of the information processing device 2 will be described below. Steps S201 to S205, S211, and S215 to S225 are similar to Figure 2 The processes shown in steps S101 to S105 , S107 , and S111 to S121 are the same, and therefore their description is omitted.

[0079] In step S207, the determination unit 25 receives signals from the microphone 11, touch panel 12, switch 13, and camera 14 indicating that the devices are operating normally. Upon receiving these signals, the determination unit 25 determines that the devices are usable. The determination unit 25 sends a signal indicating this determination to the standby time setting unit 26.

[0080] In step S209 , the waiting time setting unit 26 sets the waiting time based on the signal received from the determination unit 25 .

[0081] In step S213, the notification end determination unit 23 determines whether the standby time has ended. The notification end determination unit 23 determines that the standby time has ended if, after receiving a start signal from the voice output unit 22, it receives a signal from the standby time setting unit 26 indicating that the standby time has ended. For example, if the notification from the voice output unit 22 lasts for 2 seconds and the standby time set by the standby time setting unit 26 is 3 seconds, the standby time is determined to have ended 5 seconds after the start of the notification from the voice output unit 22. Furthermore, in step S213, the standby time ending means that the standby time has ended without a termination signal from the user.

[0082] (Effect)

[0083] User data includes multiple categories. Specifically, the devices that can send a stop signal include multiple categories (microphone 11, touch panel 12, switch 13, camera 14). The controller 20 changes the time (standby time) for accepting user data indicating the termination of control of the specified device according to the category of the user data. According to the information processing device 2 with such a structure, after feedback to the user, as long as there is no user's termination instruction, the control is quickly and automatically executed after waiting for the standby time to pass. In addition, the category of user data is used in the setting of the standby time, so that settings suitable for the user interface can be made.

[0084] The description has been made of setting the standby time based on the available device determined by the determination unit 25, but the present invention is not limited to this. The standby time may also be set based on the device corresponding to the user's instruction. In the case where the user's instruction is "open the driver's window" as described above, the device corresponding to the user's instruction is the electric window 32. In another example, when the user's instruction is "play radio broadcast", the device corresponding to the user's instruction is the audio device 39. Alternatively, the standby time may be set longer when the device corresponding to the user's instruction is a device that may be pinched, such as the electric window 32, sunroof 34, electric tailgate 36, electric trunk 37, etc., than when the device corresponding to the user's instruction is a device that will not be pinched. In this way, the time used by the user to determine whether to terminate the instruction can be ensured.

[0085] Furthermore, the standby time may be set longer when the device corresponding to the user instruction is a device that performs driving control, such as autonomous driving, than when the device corresponding to the user instruction is not a device that performs driving control. This is because the driving environment changes constantly, and determining whether to terminate a driving control instruction may take time.

[0086] Alternatively, the standby time may be set based on whether the vehicle is moving or stopped. Specifically, the standby time may be set longer when the vehicle is moving than when the vehicle is stopped. This is because it is assumed that the user's reaction will be slower when the vehicle is moving than when the vehicle is stopped.

[0087] Each function described in the above embodiments can be implemented by one or more processing circuits. The processing circuits include a processing device including a circuit, such as a programmed processing device. In addition, the processing circuits include devices such as application-specific integrated circuits (ASICs) and circuit components configured to perform the described functions.

[0088] While the embodiments of the present invention have been described above, the description and drawings constituting part of this disclosure should not be construed as limiting the present invention. Various alternative embodiments, examples, and operational techniques will become apparent to those skilled in the art based on this disclosure.

[0089] For example, a signal different from the stop signal may be input from the user while voice data for feedback is being notified from speaker 31. Controller 20 may also have a function of determining whether the signal input while voice data for feedback is being notified from speaker 31 is a stop signal.

[0090] Alternatively, the controller 20 may receive user data indicating the suspension of control of a specific device only when the specific device is a mechanically operated device or a device that controls the vehicle interior environment. Mechanically operated devices include the power windows 32, sunroof 34, power tailgate 36, and power trunk 37. The device that controls the vehicle interior environment is the air conditioning unit 33. This allows the user to suspend control of devices that could cause entrapment or that could affect driving through an action.

[0091] Navigation devices in recent years have various functions in addition to route guidance. For example, these functions include providing weather information, providing news, etc. Therefore, the user's instructions input to the microphone 11 include instructions requesting weather information, news, etc.

[0092] Furthermore, the controller 20 may not accept a stop signal for a request for weather information and news because provision of weather information and news does not involve any action that would affect the operation or driving of the machine.

[0093] The microphone 11 is not limited to a microphone installed in a vehicle. A microphone of a portable terminal (eg, a smartphone) may be used instead. In this case, the portable terminal and the controller 20 are connected in a communicable manner.

[0094] Description of Reference Numerals

[0095] 1, 2: information processing device; 10: input device; 11: microphone; 12: touch panel; 13: switch; 14: camera; 20: controller; 21: speech recognition unit; 22: speech output unit; 23: notification end determination unit; 24: control signal sending unit; 25: determination unit; 26: standby time setting unit; 30: database; 31: speaker.

Claims

1. An information processing device, characterized in that have: a voice data input device into which voice data is input; A user data input device into which user data is input by a user; and controller, The controller performs the following processing: recognizing first voice data input to the voice data input device, outputting second voice data indicating control of a prescribed device based on a result obtained by recognizing the first voice data, A waiting time is set according to the predetermined device, the waiting time being used to receive user data indicating that control of the predetermined device is to be suspended after notification of the second voice data is completed. After the notification of the second voice data is completed, the prescribed device is controlled based on the result of the recognition, and on the other hand, when user data indicating suspension of control of the prescribed device is input within the standby time, the control of the prescribed device is suspended. Here, the waiting time when the predetermined device is a device that may cause entrapment or a device that performs travel control is set to be longer than the waiting time when the predetermined device is a device that does not cause entrapment or a device that does not perform travel control.

2. The information processing device according to claim 1, wherein The predetermined device is a device mounted on a vehicle.

3. The information processing device according to claim 2, wherein The prescribed equipment includes at least any one of a power window, an air conditioning device, a sunroof, a sun visor, a power tailgate, a power trunk, a navigation device, and an audio device.

4. The information processing device according to any one of claims 1 to 3, wherein The notification based on the second voice data is a notification indicating control of the predetermined device.

5. The information processing device according to any one of claims 1 to 3, wherein The controller performs control of the prescribed device in a case where notification based on the second voice data ends without input of user data indicating suspension of control of the prescribed device.

6. The information processing device according to any one of claims 1 to 3, wherein: The user data is data indicating that the user has operated a touch panel, image data obtained by capturing the user's posture, data indicating that the user has operated a switch provided on a steering wheel, or voice data input to the voice data input device.

7. The information processing device according to any one of claims 1 to 3, wherein: After the notification of the second voice data is completed is defined as after the output of the second voice data is completed, The period for notifying the second voice data is defined as a period from the start to the end of output of the second voice data.

8. The information processing device according to claim 6, wherein The user data includes multiple categories. The controller changes the time for accepting user data indicating suspension of control of the predetermined device according to the type of the user data.

9. The information processing device according to any one of claims 1 to 3, wherein: The controller accepts user data indicating suspension of control of the predetermined device only when the predetermined device is a mechanically operated device or a device that controls the vehicle interior environment.

10. An information processing method, characterized in that: recognizing first voice data input to the voice data input device, outputting second voice data indicating control of a prescribed device based on a result obtained by recognizing the first voice data, A waiting time is set according to the predetermined device, the waiting time being used to receive user data indicating that control of the predetermined device is to be suspended after notification of the second voice data is completed. After the notification of the second voice data is completed, the prescribed device is controlled based on the result of the recognition, and on the other hand, when user data indicating suspension of control of the prescribed device is input within the standby time, the control of the prescribed device is suspended. Here, the waiting time when the predetermined device is a device that may cause entrapment or a device that performs travel control is set to be longer than the waiting time when the predetermined device is a device that does not cause entrapment or a device that does not perform travel control.

Images