Control device, vehicle, control method and program

Abstract

To restrict unintentional operation including operation by mischief and erroneous operation.SOLUTION: A control device 20 senses, as instructions, voice issued respectively by a plurality of occupants P boarding on a vehicle 30 and controls functions loaded on the vehicle on the basis of the sensed voice. The control device comprises a control part that determines an attribute of a first occupant P1 as a first attribute, when sensing first voice issued by the first occupant P1 of the plurality of occupants P, which has been issued as an instruction for activating the functions, and determines an attribute of a second occupant P2 issuing second voice as a second attribute, when sensing the second voice different from the first voice, which has been issued as an instruction for cancelling the activating of the functions until the functions are activated after the first voice is sensed, and determines whether control performed based on the first voice should be interrupted or not, in accordance with a result of comparison of the first attribute with the second attribute.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a control device, a vehicle, a control method, and a program.

Background Art

[0002] A system that executes control of in-vehicle devices based on the speech of vehicle occupants is known. Patent Document 1 discloses a vehicle device control device that controls in-vehicle devices based on the content of an instruction obtained by recognizing the speech of vehicle occupants. Patent Document 2 discloses a voice recognition device that controls a control device based on a registered vocabulary when it is recognized that the speech voice from a user corresponds to the registered vocabulary.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a system that executes control of in-vehicle devices based on the speech of occupants, for example, a method of restricting operations according to the attributes of the speaker, such as suppressing control by a child for a function that is dangerous to operate by a child, is known. However, even for a function that is considered to be operable by a child, if the operation is simply mischievous or a mere misoperation, it is necessary for an adult to interrupt and stop the operation.

[0005] An object of the present disclosure is to be able to restrict unintended operations such as mischievous operations and misoperations.

Means for Solving the Problems

[0006] The control device according to the present disclosure is a control device that detects, as commands, voices respectively issued by a plurality of passengers riding in a vehicle, and controls functions mounted on the vehicle based on the detected voices, when detecting a first voice issued by a first passenger among the plurality of passengers, the first voice being issued as a command for activating the function, determines the attribute of the first passenger as a first attribute, and when detecting a second voice different from the first voice, the second voice being issued as a command for canceling the activation of the function, between the detection of the first voice and the activation of the function, determines the attribute of the second passenger who issued the second voice as a second attribute, and includes a control unit that determines whether to interrupt the control performed based on the first voice according to the result of comparing the first attribute and the second attribute.

[0007] The control method according to the present disclosure is a control method in which a control device detects, as commands, voices respectively issued by a plurality of passengers riding in a vehicle, and controls functions mounted on the vehicle based on the detected voices, the control device detecting a first voice issued by a first passenger among the plurality of passengers, the first voice being issued as a command for activating the function; the control device determining the attribute of the first passenger as a first attribute; the control device detecting, between the detection of the first voice and the activation of the function, a second voice different from the first voice, the second voice being issued as a command for canceling the activation of the function; the control device determining the attribute of the second passenger who issued the second voice as a second attribute; the control device comparing the first attribute and the second attribute; the control device determining whether to interrupt the control performed based on the first voice based on the result of the comparison and includes the above control method.

[0008] The program according to the present disclosure detects, as commands, voices respectively emitted by a plurality of passengers in a vehicle, and causes a computer as a control device that controls functions mounted on the vehicle based on the detected voices to detect a first voice emitted by a first passenger among the plurality of passengers, the first voice being emitted as a command for activating the function to determine the attribute of the first passenger as a first attribute if, between when the first voice is detected and when the function is activated, a second voice different from the first voice is detected, the second voice being emitted as a command for canceling the activation of the function, to determine the attribute of a second passenger who emitted the second voice as a second attribute to compare the first attribute and the second attribute to determine whether to interrupt the control based on the first voice based on the result of the comparison and execute an operation including this

Advantages of the Invention

[0009] According to the present disclosure, it becomes possible to limit unintended operations such as mischievous operations and misoperations.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Modes for Carrying Out the Invention

[0011] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0012] In each figure, the same or corresponding parts are denoted by the same reference numerals. In the description of the present embodiment, the description of the same or corresponding parts will be omitted or simplified as appropriate.

[0013] Referring to FIG. 1, the configuration of the system 10 according to the present embodiment will be described.

[0014] The system 10 includes at least one control device 20 and at least one vehicle 30. Note that there may be a plurality of control devices 20 and vehicles 30, respectively.

[0015] The control device 20 can communicate with the vehicle 30 via the network 40.

[0016] The control device 20 is installed in a facility such as a data center. The control device 20 is, for example, a server belonging to a cloud computing system or other computing system.

[0017] The vehicle 30 is any type of automobile such as, for example, a gasoline vehicle, a diesel vehicle, a hydrogen vehicle, an HEV, a PHEV, a BEV, or an FCEV. "HEV" is an abbreviation for hybrid electric vehicle. "PHEV" is an abbreviation for plug-in hybrid electric vehicle. "BEV" is an abbreviation for battery electric vehicle. "FCEV" is an abbreviation for fuel cell electric vehicle. A plurality of passengers P including a first passenger P1 and a second passenger P2 are on board the vehicle 30. The plurality of passengers P may include passengers other than the first passenger P1 and the second passenger P2. The vehicle 30 is a private car in this embodiment, but is not limited thereto, and may be a taxi, a bus, or a nursing vehicle as long as it can transport a plurality of passengers P and the functions of in-vehicle devices are controlled based on the utterances of the passengers P. The vehicle 30 may be driven by a driver or may be an AV with automated driving at any level. "AV" is an abbreviation for autonomous vehicle. The level of automation is, for example, any one of levels 1 to 5 in the SAE level classification. "SAE" is an abbreviation for Society of Automotive Engineers.

[0018] The network 40 includes the Internet, at least one WAN, at least one MAN, or a combination thereof. "WAN" is an abbreviation for wide area network. "MAN" is an abbreviation for metropolitan area network. The network 40 may include at least one wireless network, at least one optical network, or a combination thereof. The wireless network is, for example, an ad hoc network, a cellular network, a wireless LAN, a satellite communication network, or a terrestrial microwave network. "LAN" is an abbreviation for local area network.

[0019] In FIG. 1, the control device 20 is connected to each vehicle 30 via the network 40. However, the control device 20 may be configured as an in-vehicle control device mounted on each vehicle 30.

[0020] Referring to FIG. 1, the outline of the present embodiment will be described.

[0021] Generally, in a system that executes control of in-vehicle devices based on the speech of vehicle occupants, an occupant who wishes to perform a voice operation activates a voice dialogue service called an agent by using a wake word or a talk switch as a trigger, and performs a voice operation from his / her seat. At that time, it is common that commands from seats other than the seat where the agent was activated are not recognized. Therefore, for example, when a voice operation is performed based on the speech of a certain occupant, another occupant may not be able to cancel the voice operation. Thus, for example, even if a voice operation performed by a child is mischievous or a misoperation, a parent sitting in a seat different from the child's seat cannot cancel it, so there is a risk that the in-vehicle device is controlled unintentionally.

[0022] In the system 10 according to the present embodiment, the control device 20 detects voices respectively uttered by a plurality of passengers P in the vehicle 30 as commands, and controls the function F mounted on the vehicle 30 based on the detected voices. In the present embodiment, the function F includes a function f realized by any one of a plurality of in-vehicle devices mounted on the vehicle 30. Examples of the in-vehicle devices include, for example, an air conditioner, a power door, a lighting device, a seat adjustment mechanism, and an audio device. The in-vehicle devices may include, for example, the seat at the driver's seat in the vehicle 30, the steering wheel, the side door mirror, the inner mirror, and the head-up display. When the control device 20 detects a first voice V1 uttered by a first passenger P1 among the plurality of passengers P and the first voice V1 is uttered as a command for activating the function f1, the control device 20 determines the attribute of the first passenger P1 as a first attribute T1. When the control device 20 detects a second voice V2 different from the first voice V1 and uttered as a command for canceling the activation of the function f1 during the period from when the first voice V1 is detected until the function f1 is activated, the control device 20 determines the attribute of the second passenger P2 who uttered the second voice V2 as a second attribute T2. The control device 20 determines whether to interrupt the control based on the first voice V1 according to the result of comparing the first attribute T1 and the second attribute T2.

[0023] According to the present embodiment, as a result of comparing the respective attributes T of the passengers P who uttered voices as commands, when a predetermined condition is satisfied, the control performed based on the first voice V1 can be interrupted by the second voice V2. That is, when a voice operation is performed based on the speech of a certain passenger, another passenger can cancel the voice operation as needed. As a result, it is possible to limit unintended operations such as mischievous operations and misoperations.

[0024] Referring to FIG. 2, the configuration of the control device 20 according to the present embodiment will be described.

[0025] The control device 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, and an output unit 25.

[0026] The control unit 21 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU or a GPU, or a dedicated processor specialized for specific processing. "CPU" is an abbreviation for central processing unit. "GPU" is an abbreviation for graphics processing unit. The programmable circuit is, for example, an FPGA. "FPGA" is an abbreviation for field-programmable gate array. The dedicated circuit is, for example, an ASIC. "ASIC" is an abbreviation for application specific integrated circuit. The control unit 21 executes processes related to the operation of the control device 20 while controlling each part of the control device 20.

[0027] The storage unit 22 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. The semiconductor memory is, for example, a RAM or a ROM. "RAM" is an abbreviation for random access memory. "ROM" is an abbreviation for read only memory. The RAM is, for example, an SRAM or a DRAM. "SRAM" is an abbreviation for static random access memory. "DRAM" is an abbreviation for dynamic random access memory. The ROM is, for example, an EEPROM. "EEPROM" is an abbreviation for electrically erasable programmable read only memory. The storage unit 22 functions as, for example, a main memory device, an auxiliary memory device, or a cache memory. The storage unit 22 stores data used for the operation of the control device 20 and data obtained by the operation of the control device 20. Further, in the present embodiment, when it is determined that the control performed based on the first voice V1 is to be interrupted, the storage unit 22 stores in association the type of function that was scheduled to be activated by the interrupted control and the attribute determined as the first attribute T1. Also, the storage unit 22 may store position attribute information D1 indicating the correspondence between the positions of the respective seats in the vehicle 30 and the attributes of the passengers sitting in those seats. Further, the storage unit 22 may store voice attribute information D2 indicating the correspondence between the voice characteristics of each passenger P and the attributes of that passenger.

[0028] The communication unit 23 includes at least one communication interface. The communication interface is, for example, a LAN interface. The communication unit 23 receives data used for the operation of the control device 20 and transmits data obtained by the operation of the control device 20. In the present embodiment, the communication unit 23 communicates with the vehicle 30.

[0029] The input unit 24 includes at least one input interface. The input interface is, for example, a physical key, a capacitive key, a pointing device, a touch screen provided integrally with a display, or a voice sensor. The input unit 24 receives an operation for inputting data used for the operation of the control device 20. Instead of being provided in the control device 20, the input unit 24 may be connected to the control device 20 as an external input device. As a connection method, for example, any method such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used. "USB" is an abbreviation for Universal Serial Bus. "HDMI (registered trademark)" is an abbreviation for High-Definition Multimedia Interface. In the present embodiment, the input unit 24 is a voice sensor. The voice sensor is, for example, a microphone. The voice sensors are installed for each seat of the vehicle 30. Further, the input unit 24 may include an imaging device (camera) used for image analysis described later.

[0030] The output unit 25 includes at least one output interface. The output interface is, for example, a display or a speaker. The display is, for example, an LCD or an organic EL display. "LCD" is an abbreviation for liquid crystal display. "EL" is an abbreviation for electro luminescence. The output unit 25 outputs data obtained by the operation of the control device 20. Instead of being provided in the control device 20, the output unit 25 may be connected to the control device 20 as an external output device. As a connection method, for example, any method such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used.

[0031] The functions of the control device 20 are realized by executing the control program according to the present embodiment on a processor as the control unit 21. That is, the functions of the control device 20 are realized by software. The control program causes a computer to execute the operations of the control device 20, thereby causing the computer to function as the control device 20. That is, the computer functions as the control device 20 by executing the operations of the control device 20 according to the control program.

[0032] The program can be stored in a non-transitory computer-readable medium. The non-transitory computer-readable medium is, for example, a flash memory, a magnetic recording device, an optical disc, a magneto-optical recording medium, or a ROM. The distribution of the program is performed, for example, by selling, transferring, or lending a portable medium such as an SD card, a DVD, or a CD-ROM storing the program. "SD" is an abbreviation for Secure Digital. "DVD" is an abbreviation for digital versatile disc. "CD-ROM" is an abbreviation for compact disc read only memory. The program may be distributed by storing the program in the storage of a server and transferring the program from the server to another computer. The program may be provided as a program product.

[0033] A computer stores, for example, a program stored in a portable medium or a program transferred from a server, once, in a main memory device. Then, the computer reads the program stored in the main memory device with a processor and executes processing according to the read program with the processor. The computer may directly read a program from a portable medium and execute processing according to the program. The computer may sequentially execute processing according to the received program each time a program is transferred from a server to the computer. Processing may be executed by a so-called ASP type service that realizes functions only by execution instructions and result acquisition without transferring a program from a server to a computer. "ASP" is an abbreviation for application service provider. A program includes information for use in processing by an electronic computer that conforms to the program. For example, data that is not a direct instruction to a computer but has a property of defining the processing of the computer corresponds to "something conforming to the program".

[0034] Some or all of the functions of the control device 20 may be realized by a programmable circuit or a dedicated circuit as the control unit 21. That is, some or all of the functions of the control device 20 may be realized by hardware.

[0035] With reference to FIGS. 3 and 4, the operation of the system 10 according to the present embodiment will be described. This operation corresponds to the control method according to the present embodiment.

[0036] In S101 of FIG. 3 (hereinafter, each step of the flowchart is specified as S and a number), the control unit 21 of the control device 20 detects the first voice V1 uttered by the first occupant P1 among the plurality of occupants P. The first voice V1 is a voice uttered as a command to activate the function f1 of the vehicle. The first voice V1 may be detected in any procedure, but for example, it is detected in the following procedure. First, the voice uttered by the first occupant P1 is picked up by the voice sensor as the input unit 24. The control unit 21 analyzes the voice picked up by the input unit 24 and determines whether a predetermined activation word is included. If it is determined that the activation word is included, the control unit 21 detects the voice uttered by the first occupant P1 following the activation word as the first voice V1.

[0037] In S102 of FIG. 3, the control unit 21 of the control device 20 determines the attribute of the first occupant P1 who uttered the first voice V1 as the first attribute T1. Specifically, the control unit 21 determines the attribute of the first occupant P1 based on the position of the seat on which the first occupant P1 is sitting. As an example, assume that the voice sensor as the input unit 24 is installed for each seat of the vehicle 30, and the storage unit 22 stores the position attribute information D1 indicating the correspondence between the position of each seat in the vehicle 30 and the attribute of the occupant sitting on the seat. The correspondence indicated by the position attribute information D1 is, for example, as follows. That is, the attribute corresponding to the seat position of "driver's seat" or "passenger seat" is "adult". Also, the attribute corresponding to the seat position of "rear seat driver's side" or "rear seat passenger's side" is "child". This position attribute information D1 can be set and registered when an occupant gets into the vehicle 30. When the control unit 21 detects the voice V via the voice sensor as the input unit 24, it specifies the position of the seat where the voice sensor that detected the voice V is installed. Then, the control unit 21 refers to the correspondence indicated by the position attribute information D1 stored in the storage unit 22 and determines the attribute of the passenger who uttered the voice based on the specified seat position.

[0038] On the premise as described above, assume that the control unit 21 of the control device 20 has identified that the position of the seat where the first occupant P1 is sitting is "the rear passenger seat side". As a result, the control unit 21 determines that the attribute of the first occupant P1 is "child". In this way, by determining the attribute of the occupant P based on the seat position of the occupant P, it is only necessary to recognize the occupant attribute of each seat once at first, which is simple and convenient.

[0039] Instead of identifying the position of the seat where the first occupant P1 is sitting, the control unit 21 of the control device 20 may determine the attribute of the first occupant P1 based on the characteristics of the first voice V1 uttered by the first occupant P1. Specifically, the control unit 21 acquires voice attribute information D2 indicating the correspondence between the characteristics of the voice Vi of each occupant Pi and the attribute Ti of the occupant Pi. As an example, the voice attribute information D2 indicating the correspondence between the characteristics of the voice of each occupant P and the attribute T of the occupant P is stored in the storage unit 22. When the control unit 21 detects the voice Vi uttered by each occupant Pi, it extracts the characteristics of the voice Vi by analyzing the voice Vi. The control unit 21 determines the attribute Ti of the occupant Pi who uttered the voice Vi based on the extracted characteristics by referring to the correspondence indicated by the voice attribute information D2. The correspondence indicated by the voice attribute information D2 is, for example, as follows. That is, the attribute corresponding to the frequency of the voice V being less than the threshold is "adult". Also, the attribute corresponding to the frequency of the voice V being greater than or equal to the threshold is "child". In this case, the control unit 21 of the control device 20 determines whether the frequency extracted as the characteristic of the first voice V1 uttered by the first occupant P1 is greater than or equal to the threshold, and if it is determined to be greater than or equal to the threshold, determines that the attribute of the first occupant P1 is "child". More advancedly, the voiceprint pattern of each occupant and the attribute of each occupant may be registered in advance, and the occupant Pi and his / her attribute Ti may be determined by analyzing the voiceprint pattern of the detected voice Vi. In this way, by determining the attribute of the first occupant P1 based on the characteristics of the first voice V1 uttered by the first occupant P1, even if the seat position of the first occupant P1 changes halfway, the attribute can be determined.

[0040] Note that the determination of the attribute may be made by the control unit 21 of the control device 20 obtaining the result obtained by the occupant recognition device instead. The occupant recognition device may be a separate device independent of the control device 20, or may be incorporated in the control device 20. The occupant recognition device may be, for example, an image analysis device, and may include an imaging device such as a camera. Then, the occupant recognition device may determine the attribute T of the occupant P who uttered the voice by analyzing the image captured by the imaging device.

[0041] In S103 of FIG. 3, the control unit 21 of the control device 20 determines whether a second voice V2 different from the first voice V1 is detected between the detection of the first voice V1 and the activation of the function f1. The second voice V2 is a voice issued as a command to cancel the activation of the function f1. Whether the second voice V2 is detected may be determined by an arbitrary procedure, but is determined by the following procedure, for example.

[0042] Among the voices V detected by the control unit 21 of the control device 20 between the detection of the first voice V1 and the activation of the function f1, a voice different from the first voice V1 and including a negative term is detected as the second voice V2 issued as a command to cancel the activation of the function f1. Examples of the "negative term" include terms such as "stop", "no good", and "stop". Here, the reason for detecting a voice including a negative term as the second voice V2 is as follows. As described above, usually, an occupant who intends to perform a voice operation activates a voice dialogue service called an agent by uttering an activation word or pressing a talk switch, etc., and starts the voice operation. However, in the present embodiment, since a voice including a negative term can be directly detected as the second voice V2, the second occupant P2 can cancel the activation of the function f1 by simply uttering a negative term without a trigger such as an activation word or a talk switch. Therefore, it is possible to quickly respond to pranks or incorrect operations.

[0043] In S103 of FIG. 3, when there is no voice among the voices V detected between the detection of the first voice V1 and the activation of the function f1 that contains a negative term in a voice different from the first voice V1, the control unit 21 determines that the second voice V2 has not been detected. If it is determined in S103 that the second voice V2 has not been detected, the processes from S104 to S106 are performed. The processes from S104 to S106 will be described later.

[0044] In S103 of FIG. 3, when it is determined that the second voice V2 has been detected, the process of S107 is performed.

[0045] In S107 of FIG. 3, the control unit 21 of the control device 20 determines the attribute of the second occupant P2 who uttered the second voice V2 as the second attribute T2. Since the specific method for determining the second attribute T2 is the same as the method for determining the first attribute T1 in S102, the description thereof is omitted.

[0046] In S108 of FIG. 3, the control unit 21 of the control device 20 compares the first attribute T1 determined in S102 with the second attribute T2 determined in S107. Specifically, the control unit 21 estimates the superiority relationship R between the first occupant P1 and the second occupant P2 by comparing the first attribute T1 with the second attribute T2. The superiority relationship R refers to a relationship in which one is in a position to protect and observe or command and supervise the other. The control unit 21 estimates which one is superior by comparing the first attribute T1 with the second attribute T2. The superiority relationship R includes a parent-child relationship, a master-disciple relationship, or a caregiver-care recipient relationship. For example, when the control unit 21 estimates a parent-child relationship as the superiority relationship R, in the determination of the attributes in S102 and S107, it determines and compares whether the attribute is "child" or "adult", and estimates that "adult" is superior to "child" as the superiority relationship R. Also, when the control unit 21 estimates a master-disciple relationship as the superiority relationship R, in the determination of the attributes in S102 and S107, it determines and compares whether the attribute is "student" or "teacher", and estimates that "teacher" is superior to "student" as the superiority relationship R. Alternatively, when the control unit 21 estimates a caregiver-care recipient relationship as the superiority relationship R, in the determination of the attributes in S102 and S107, it determines and compares whether the attribute is "nurse" or "patient", and estimates that "doctor or nurse" is superior to "patient" as the superiority relationship R.

[0047] In S109 of FIG. 3, based on the result of comparing the first attribute T1 with the second attribute T2, the control unit 21 of the control device 20 estimates whether the second occupant P2 is superior to the first occupant P1 as the superiority relationship R between the first occupant P1 and the second occupant P2. For example, in S108, when a parent-child relationship is estimated as the superiority relationship R, the control unit 21 estimates that the occupant P with the attribute "adult" is superior to the occupant P with the attribute "child". In S109, when the control unit 21 estimates that there is no superiority or inferiority between the first occupant P1 and the second occupant P2, or that the first occupant P1 is superior to the second occupant P2, it determines to continue the control performed based on the first voice V1. Specifically, the processes from S104 to S106 are performed.

[0048] In S104 of FIG. 3, the control unit 21 of the control device recognizes the first voice V1. Specifically, the control unit 21 performs voice recognition on the first voice V1 detected in S101 and converts the first voice V1 into text.

[0049] In S105 of FIG. 3, the control unit 21 of the control device estimates (interprets) the intention of the first voice V1 recognized in S104. For example, assume that the character string converted into text in S104 is "Air conditioner wind, max". The control unit 21 estimates the intention of "changing the air volume of the air conditioner to the maximum" as the semantic interpretation of "Air conditioner wind, max".

[0050] In S106 of FIG. 3, the control unit 21 of the control device 20 activates the function f1 of the vehicle 30 based on the intention interpreted in S105. For example, when the intention estimated in S105 is "changing the air volume of the air conditioner to the maximum", the control unit 21 activates the function f1 of the vehicle 30 by performing control to maximize the air volume of the air conditioner mounted on the vehicle 30. At that time, prior to activating the function f1 of the vehicle 30, the control unit 21 may output a guidance to notify that the function f1 is to be activated via the output unit 25. For example, the control unit 21 may create a message "Maximize the air conditioner wind" and output the created message as voice from a speaker as the output unit 25. Alternatively, the control unit 21 may display the created message on a display as the output unit 25.

[0051] On the other hand, in S109 of FIG. 3, when it is determined that the second occupant P2 is more dominant than the first occupant P1, the process of S110 is performed.

[0052] In S110 of FIG. 3, the control unit 21 of the control device 20 performs control to interrupt the control performed based on the first voice V1. Specifically, the control unit 21 performs control to abort the activation of the function f1 controlled based on the first voice V1.

[0053] In this way, the control device 20 detects the voices V respectively uttered by a plurality of passengers P who have boarded the vehicle 30 as commands, and controls the function F mounted on the vehicle 30 based on the detected voices V. The control device 20 detects a first voice V1 uttered by any one of the passengers P, which is the first voice V1 uttered as a command for activating the function f1. The control device 20 determines the attribute of the first passenger P1 who uttered the first voice V1 as the first attribute T1. Between the detection of the first voice V1 and the activation of the function f1, the control device 20 detects a second voice V2 different from the first voice V1, which is the second voice V2 uttered as a command for canceling the activation of the function f1. The control device 20 determines the attribute of the second passenger P2 who uttered the second voice V2 as the second attribute T2. The control device 20 compares the first attribute T1 and the second attribute T2, and determines whether to interrupt the control performed based on the first voice V1 based on the comparison result.

[0054] According to the present embodiment, as a result of comparing the respective attributes T of the passengers P who uttered voices as commands, when a predetermined condition is satisfied, the control performed based on the first voice V1 can be interrupted by the second voice V2. That is, when a voice operation is performed based on the speech of a certain passenger, another passenger can cancel the voice operation as needed. As a result, it is possible to limit unintended operations such as mischievous operations and misoperations.

[0055] In the present embodiment, after determining the attribute of the first passenger P1 who uttered the first voice V1 as the first attribute T1 in S102, it is a flowchart for performing the second voice detection in S103 or the comparison between the first attribute T1 and the second attribute T2 in S109. However, immediately after S102, a step of determining the superiority of the first attribute T1 may be added. When the first attribute T1 is the most dominant attribute in the dominance relationship R, the process may proceed directly to S104 without performing the step of S103, and when the first attribute T1 is not the most dominant attribute in the dominance relationship R, the process may proceed to S103. Thereby, when the first attribute T1 is a dominant attribute (for example, an adult), the processes from S103 and S107 to S110 can be omitted.

[0056] As a modification example of the present embodiment, after the control unit 21 of the control device 20 interrupts the control performed based on the first voice V1 in S110 of FIG. 3, the control unit 21 may associate the type of the function f1 that was scheduled to be activated by the interrupted control with the attribute determined as the first attribute T1 and store the association in the storage unit 22. For example, when the first attribute T1 determined in S102 is "child" and the type of the function f1 interrupted in S110 is "air conditioner", the control unit 21 associates "child" as an attribute with "air conditioner" as the type of the function f1 and stores the association in the storage unit 22. Then, before a predetermined period elapses after the control performed based on the first voice V1 is interrupted, when the control unit 21 detects the voice V emitted by each occupant P as a command, for each detected voice V, the control unit 21 determines the type of the function fi activated by the control performed based on each voice Vi and the attribute Ti of the occupant Pi who emitted the voice Vi. Then, the control unit 21 determines whether the combination of the determined type of the function fi and the attribute Ti matches the combination of the type of the function f and the attribute T stored in the storage unit 22 in association therewith. For example, as a result of determining the type of the function fi activated by the control performed based on the voice Vi and the attribute Ti of the occupant Pi who emitted the voice Vi, when it is determined that the type of the function fi is "air conditioner" and the attribute Ti is "child", the control unit 21 determines that the combination of the determined type of the function fi and the attribute Ti matches the combination of the type of the function f and the attribute T stored in the storage unit 22 in association therewith, and may invalidate the command by the voice Vi. That is, the control unit 21 may perform control not to activate the "air conditioner" in the vehicle 30. Specifically, the following processing from S201 to S205 may be further performed.

[0057] In S201 of FIG. 4, the control unit 21 of the control device 20 detects the voice V uttered by each passenger P as a command. Specifically, the voice sensor serving as the input unit 24 picks up the voice Vi uttered by the passenger Pi. The control unit 21 analyzes the voice Vi picked up by the input unit 24 and determines whether a predetermined activation word is included in the voice Vi. When it is determined that the activation word is included in the voice Vi, the control unit 21 detects the voice uttered by the passenger Pi following the activation word as a command.

[0058] In S202 of FIG. 4, the control unit 21 of the control device 20 determines whether a predetermined period has elapsed since the control performed based on the first voice V1 in S110 of FIG. 3 was interrupted. The predetermined period can be arbitrarily set to a desired period, such as several minutes, several hours, or until the engine of the vehicle 30 is turned off, for example, to prohibit the same operation as the interrupted operation from being repeated by the speech of a passenger with the same attribute. In S202, when it is determined that the predetermined period has not elapsed, the process of S203 is performed. On the other hand, in S202, when it is determined that the predetermined period has elapsed, the control based on the voice Vi is continued. Specifically, the processes from S206 to S208 are performed. The processes from S206 to S208 will be described later.

[0059] In S203 of FIG. 4, for each of the voices V detected in S201, the control unit 21 of the control device 20 determines the type of the function fi activated by the control performed based on each voice Vi and the attribute Ti of the passenger Pi who uttered the voice Vi. For example, assume that the control unit 21 determines that the type of the function fi is "air conditioner" and the attribute Ti is "child".

[0060] In S204 of FIG. 4, the control unit 21 of the control device 20 determines whether the combination of the determined type of function fi and the attribute Ti matches the combination of the type of function f1 and the attribute T1 stored in the storage unit 22 in an associated manner. As an example, in S110, since the first attribute T1 is "child" and the type of the interrupted function f1 is "air conditioner", it is assumed that in the storage unit 22, "child" as an attribute is stored in association with "air conditioner" as the type of function f1. At this time, in S203, when it is determined that the type of function fi is "air conditioner" and the attribute Ti is "child", the control unit 21 determines that the combination of the determined type of function fi and the attribute Ti matches the combination of the type of function f1 and the attribute T1 stored in the storage unit 22 in an associated manner. In S204, when it is determined that the combinations match, the process of S205 is performed.

[0061] In S205 of FIG. 4, the control unit 21 of the control device 20 invalidates the command by the voice Vi. Specifically, the control unit 21 performs control so that the function fi is not activated.

[0062] On the other hand, in S204 of FIG. 4, when it is determined that the combinations do not match, the control unit 21 continues the control based on the voice Vi. Specifically, the processes of S206 to S208 in FIG. 4 are performed. The processes of S206 to S208 are the same as the processes of S104 to S106 in FIG. 3, except that the voice Vi is recognized instead of the first voice V1 in the processes of S104 to S106 in FIG. 3. Therefore, the description is omitted.

[0063] When it is determined that the control based on the first voice V1 is to be interrupted, the control device 20 stores in association the type of the function f1 that was scheduled to be activated by the interrupted control and the attribute determined as the first attribute T1. Then, before a predetermined period elapses after the control based on the first voice V1 is interrupted, when the control device 20 detects, as a command, the voice V issued by each occupant P, for each detected voice V, it determines the type of the function fi that is activated by the control performed based on each voice Vi and the attribute Ti of the occupant Pi who issued the voice Vi. Then, the control device 20 determines whether the combination of the determined type of the function fi and the attribute Ti matches the combination of the type of the function and the attribute that is stored in association in advance, and if it is determined that they match, it invalidates the command by the voice Vi.

[0064] According to this modification, in a case where the first occupant P1 himself or an occupant Pi having the same attribute as the first occupant P1 repeatedly makes the same utterance mischievously within a certain period, the operation can be automatically invalidated without waiting for the utterance of the second occupant P2. Therefore, it is possible to more reliably limit unintended operations such as mischievous operations and misoperations.

[0065] The present disclosure is not limited to the above-described embodiments. For example, a plurality of blocks described in the block diagram may be integrated, or one block may be divided. Instead of executing a plurality of steps described in the flowchart in time series according to the description, depending on the processing ability of the device that executes each step or as necessary, they may be executed in parallel or in a different order. In addition, modifications can be made without departing from the gist of the present disclosure.

[0066] Some of the embodiments of the present disclosure will be exemplified below. However, note that the embodiments of the present disclosure are not limited thereto. [Appendix 1] A control device that detects, as commands, voices respectively issued by a plurality of occupants riding in a vehicle and controls functions mounted on the vehicle based on the detected voices, When a first voice uttered by a first occupant among a plurality of occupants and issued as a command for activating a function is detected, the attribute of the first occupant is determined as a first attribute. If, between the detection of the first voice and the activation of the function, a second voice different from the first voice and issued as a command for canceling the activation of the function is detected, the attribute of the second occupant who uttered the second voice is determined as a second attribute. A control device comprising a control unit that determines whether to interrupt the control based on the first voice according to the result of comparing the first attribute and the second attribute. [Appendix 2] In the vehicle, a voice sensor is installed for each seat. The control unit acquires position-attribute information indicating the correspondence between the position of each seat and the attribute of the occupant sitting in that seat. When the control unit detects a voice via the voice sensor, it identifies the position of the seat where the voice sensor that detected the voice is installed, and by referring to the correspondence indicated by the position-attribute information, determines the attribute of the passenger who uttered the voice based on the identified position of the seat. The control device according to Appendix 1. [Appendix 3] The control unit acquires voice-attribute information indicating the correspondence between the characteristics of the voice of each occupant and the attribute of that occupant. When the control unit detects a voice uttered by each occupant, it extracts the characteristics of the voice by analyzing the voice, and by referring to the correspondence indicated by the voice-attribute information, determines the attribute of the occupant who uttered the voice based on the extracted characteristics. The control device according to Appendix 1 or Appendix 2. [Appendix 4] Among the voices detected between the detection of the first voice and the activation of the function, the control unit detects a voice different from the first voice and containing a negative term as the second voice issued as a command for canceling the activation of the function. The control device according to any one of Appendix 1 to Appendix 3. [Appendix 5] The control unit estimates the superiority relationship between the first occupant and the second occupant by comparing the first attribute and the second attribute. The control device according to any one of Appendix 1 to Appendix 4. [Appendix 6] When the control unit determines that there is no superiority or inferiority between the first occupant and the second occupant, or when it is presumed that the first occupant is superior to the second occupant, the control unit determines to continue the control performed based on the first voice. The control device according to any one of Supplementary Notes 1 to 5. [Supplementary Note 7] When the control unit determines that the second occupant is superior to the first occupant, the control unit determines to interrupt the control performed based on the first voice. The control device according to any one of Supplementary Notes 1 to 6. [Supplementary Note 8] The control unit estimates a parent-child relationship, a master-disciple relationship, or a caregiver-care recipient relationship as the superiority relationship. The control device according to any one of Supplementary Notes 1 to 7. [Supplementary Note 9] When, as a result of comparing the first attribute and the second attribute by the control unit, it is determined to interrupt the control performed based on the first voice, a storage unit is further provided that associates and stores the type of function that was scheduled to be activated by the interrupted control with the attribute determined as the first attribute. Before a predetermined period elapses after the control performed based on the first voice is interrupted, when the control unit detects the voices emitted by each occupant as commands, for each of the detected voices, the control unit determines the type of function activated by the control performed based on each voice and the attribute of the occupant who emitted the voice, refers to the storage unit, and determines whether the combination of the determined function type and attribute matches the combination of the function type and attribute stored in association with the storage unit. When it is determined that they match, the control device according to any one of Supplementary Notes 1 to 8 invalidates the command by the voice. [Supplementary Note 10] A vehicle equipped with the control device according to any one of Supplementary Notes 1 to 9. [Supplementary Note 11] A control method for detecting, as commands, the voices emitted by a plurality of occupants riding in a vehicle by a control device and controlling the functions mounted on the vehicle based on the detected voices, detecting, by the control device, a first voice emitted by a first occupant among the plurality of occupants, the first voice being emitted as a command for activating a function; The control device determines the attribute of the first occupant as the first attribute; The control device detects a second voice different from the first voice, which is issued as a command to cancel the activation of the function, during the period from when the first voice is detected to when the function is activated; The control device determines the attribute of the second occupant who issued the second voice as the second attribute; The control device compares the first attribute and the second attribute; The control device determines whether to interrupt the control based on the first voice based on the comparison result; A control method including the above. [Appendix 12] In the vehicle, a voice sensor is installed for each seat. The control device further includes obtaining position-attribute information indicating the correspondence between the position of each seat and the attribute of the occupant sitting in that seat. Determining the attribute includes, when detecting a voice via the voice sensor, identifying the position of the seat where the voice sensor that detected the voice is installed, and referring to the correspondence indicated by the position-attribute information to determine the attribute of the passenger who issued the voice based on the identified seat position. The control method according to Appendix 11. [Appendix 13] The control device further includes obtaining voice-attribute information indicating the correspondence between the voice characteristics of each occupant and the attribute of the occupant. Determining the attribute includes, when detecting a voice issued by each occupant, extracting the voice characteristics by analyzing the voice, and referring to the correspondence indicated by the voice-attribute information to determine the attribute of the occupant who issued the voice based on the extracted characteristics. The control method according to Appendix 11 or Appendix 12. [Appendix 14] Detecting the second voice includes detecting, among the voices detected during the period from when the first voice is detected to when the function is activated, a voice different from the first voice and including a negative term as the second voice issued as a command to cancel the activation of the function. The control method according to any one of Appendix 11 to Appendix 13. [Appendix 15] The control method according to any one of Appendices 11 to 14, wherein comparing the first attribute and the second attribute includes estimating the superiority relationship between the first occupant and the second occupant. [Appendix 16] A computer as a control device that detects voices respectively emitted by a plurality of occupants in a vehicle as commands and controls functions mounted on the vehicle based on the detected voices, detecting a first voice emitted by a first occupant among the plurality of occupants, the first voice being emitted as a command for activating a function; determining the attribute of the first occupant as the first attribute; when, after the first voice is detected and before the function is activated, a second voice different from the first voice and emitted as a command for canceling the activation of the function is detected, determining the attribute of the second occupant who emitted the second voice as the second attribute; comparing the first attribute and the second attribute; determining whether to interrupt the control based on the first voice based on the result of the comparison; A program for executing an operation including the above. [Appendix 17] In the vehicle, a voice sensor is installed for each seat, The operation further includes obtaining position-attribute information indicating the correspondence between the position of each seat and the attribute of the occupant sitting in that seat, Determining the attribute includes, when detecting a voice via the voice sensor, identifying the position of the seat where the voice sensor that detected the voice is installed, and referring to the correspondence indicated by the position-attribute information, and determining the attribute of the passenger who emitted the voice based on the identified position of the seat. The program according to Appendix 16. [Appendix 18] The operation further includes obtaining voice-attribute information indicating the correspondence between the voice characteristics of each occupant and the attribute of the occupant. Determining an attribute includes, when detecting the voice emitted by each occupant, extracting the features of the voice by analyzing the voice, and referring to the correspondence relationship indicated by the voice attribute information, and determining the attribute of the occupant who emitted the voice based on the extracted features, which is the program described in Supplementary Note 16 or Supplementary Note 17. [Supplementary Note 19] Detecting the second voice includes, among the voices detected between when the first voice is detected and when the function is activated, detecting, as the second voice, a voice different from the first voice and including a negative term, which is emitted as a command for canceling the activation of the function, which is the program described in any one of Supplementary Notes 16 to 18. [Supplementary Note 20] Comparing the first attribute and the second attribute includes estimating the superiority relationship between the first occupant and the second occupant, which is the program described in any one of Supplementary Notes 16 to 19.

Explanation of Signs

[0067] 10 System 20 Control Device 21 Control Unit 22 Storage Unit 23 Communication Unit 24 Input Unit 25 Output Unit 30 Vehicle 40 Network P, P1, P2 Occupants

Claims

1. A control device that detects voices emitted by a plurality of passengers in a vehicle as commands and controls functions mounted on the vehicle based on the detected voices, wherein, among the plurality of passengers, when detecting a first voice emitted by a first passenger, which is a first voice emitted as a command for activating the function, determines the attribute of the first passenger as a first attribute, and between when the first voice is detected and when the function is activated, when detecting a second voice different from the first voice, which is a second voice emitted as a command for canceling the activation of the function, determines the attribute of the second passenger who emitted the second voice as a second attribute, and includes a control unit that determines whether to interrupt control based on the first voice according to the result of comparing the first attribute and the second attribute.

2. Voice sensors are installed in the vehicle for each seat, the control unit acquires position-attribute information indicating the correspondence between the position of each seat and the attribute of the passenger sitting in that seat, when the control unit detects a voice via the voice sensor, identifies the position of the seat where the voice sensor that detected the voice is installed, and determines the attribute of the passenger who emitted the voice based on the identified position of the seat by referring to the correspondence indicated by the position-attribute information. The control device according to claim 1.

3. the control unit acquires voice-attribute information indicating the correspondence between the voice characteristics of each passenger and the attribute of that passenger, when the control unit detects a voice emitted by each passenger, extracts the characteristics of the voice by analyzing the voice, and determines the attribute of the passenger who emitted the voice based on the extracted characteristics by referring to the correspondence indicated by the voice-attribute information. The control device according to claim 1.

4. Among the voices detected between when the first voice is detected and when the function is activated, the control unit detects, as the second voice, a voice different from the first voice and including a negative term as a voice emitted as a command for canceling the activation of the function. The control device according to claim 1.

5. The control unit according to claim 1, wherein by comparing the first attribute and the second attribute, estimates the superiority relationship between the first passenger and the second passenger.

6. The control device according to claim 5, wherein when the control unit estimates that there is no superiority or inferiority between the first occupant and the second occupant, or the first occupant is superior to the second occupant, the control unit determines to continue the control performed based on the first voice.

7. The control device according to claim 5, wherein when the control unit estimates that the second occupant is superior to the first occupant, the control unit determines to interrupt the control performed based on the first voice.

8. The control device according to claim 5, wherein the control unit estimates a parent-child relationship, a master-disciple relationship, or a caregiver-care recipient relationship as the superiority relationship.

9. When, as a result of comparing the first attribute and the second attribute by the control unit, it is determined to interrupt the control performed based on the first voice, the control device further includes a storage unit that associates and stores the type of function that was scheduled to be activated by the interrupted control with the attribute determined as the first attribute. After the control based on the first voice is interrupted and before a predetermined period elapses, when the control unit detects, as a command, the voice emitted by each occupant, for each of the detected voices, the control unit determines the type of function activated by the control based on each voice and the attribute of the occupant who emitted the voice, refers to the storage unit, and determines whether the combination of the determined type of function and attribute matches the combination of the type of function and attribute stored in association with the storage unit. If it is determined that they match, the control device invalidates the command by the voice.

10. A vehicle equipped with the control device according to any one of claims 1 to 9.

11. A control method for detecting, as commands, voices respectively emitted by a plurality of occupants in a vehicle by a control device and controlling functions mounted on the vehicle based on the detected voices, comprising: detecting, by the control device, a first voice emitted by a first occupant among the plurality of occupants, the first voice being emitted as a command for activating the function; determining, by the control device, the attribute of the first occupant as a first attribute; detecting, by the control device, a second voice different from the first voice between the detection of the first voice and the activation of the function, the second voice being emitted as a command for canceling the activation of the function. The control device determines the attribute of the second occupant who uttered the second voice as the second attribute; The control device compares the first attribute and the second attribute; The control device determines whether to interrupt the control performed based on the first voice based on the result of the comparison; A control method including the above.

12. In the vehicle, a voice sensor is installed for each seat, The control device further includes acquiring position-attribute information indicating the correspondence between the position of each seat and the attribute of the occupant sitting in that seat, Determining the attribute includes, when detecting a voice via the voice sensor, identifying the position of the seat where the voice sensor that detected the voice is installed, and referring to the correspondence indicated by the position-attribute information, and based on the position of the identified seat, determining the attribute of the passenger who uttered the voice. The control method according to claim 11.

13. The control device further includes acquiring voice-attribute information indicating the correspondence between the characteristics of the voice of each occupant and the attribute of the occupant, Determining the attribute includes, when detecting a voice uttered by each occupant, extracting the characteristics of the voice by analyzing the voice, and referring to the correspondence indicated by the voice-attribute information, and based on the extracted characteristics, determining the attribute of the occupant who uttered the voice. The control method according to claim 11.

14. Detecting the second voice includes detecting, among the voices detected between the detection of the first voice and the activation of the function, a voice that is different from the first voice and includes a negative term, as the second voice uttered as a command to cancel the activation of the function. The control method according to claim 11.

15. Comparing the first attribute and the second attribute includes estimating the superiority relationship between the first occupant and the second occupant. The control method according to claim 11.

16. In a computer as a control device that detects voices uttered by a plurality of occupants in a vehicle as commands and controls functions mounted on the vehicle based on the detected voices, Detecting a first voice uttered by a first occupant among the plurality of occupants, the first voice uttered as a command to activate the function; Determining the attribute of the first occupant as the first attribute; If, between the detection of the first voice and the activation of the function, a second voice different from the first voice is detected, and the second voice is issued as a command to cancel the activation of the function, determine the attribute of the second occupant who issued the second voice as the second attribute. Compare the first attribute and the second attribute. Based on the result of the comparison, determine whether to interrupt the control performed based on the first voice. A program that executes an operation including the above.

17. In the vehicle, a voice sensor is installed for each seat. The operation further includes obtaining position-attribute information indicating the correspondence between the position of each seat and the attribute of the occupant sitting in that seat. Determining the attribute includes, when detecting a voice via the voice sensor, identifying the position of the seat where the voice sensor that detected the voice is installed, and referring to the correspondence indicated by the position-attribute information, and determining the attribute of the passenger who issued the voice based on the identified seat position. The program according to claim 16.

18. The operation further includes obtaining voice-attribute information indicating the correspondence between the voice characteristics of each occupant and the attribute of the occupant. Determining the attribute includes, when detecting a voice issued by each occupant, extracting the characteristics of the voice by analyzing the voice, and referring to the correspondence indicated by the voice-attribute information, and determining the attribute of the occupant who issued the voice based on the extracted characteristics. The program according to claim 16.

19. Detecting the second voice includes detecting, among the voices detected between the detection of the first voice and the activation of the function, a voice different from the first voice and including a negative term, as the second voice issued as a command to cancel the activation of the function. The program according to claim 16.

20. Comparing the first attribute and the second attribute includes estimating the superiority relationship between the first occupant and the second occupant. The program according to claim 16.

Images