In-vehicle voice operation device, voice operation system, voice operation method, and program
The in-vehicle device dynamically classifies speakers and adjusts operation permissions based on the presence of adults or children, addressing uniform weighting issues in conventional systems by allowing or restricting operations as needed.
Patent Information
- Application Number
- JP2024035098
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-03-07
- Publication Date
- 2025-09-19
AI Technical Summary
Conventional voice-operated in-vehicle devices uniformly apply weightings to voice commands regardless of the presence of adults or children, failing to adapt operation restrictions based on situational needs.
An in-vehicle device that classifies speakers as adults or children through voice and image recognition, adjusting operation permissions based on the presence of authorized users, allowing or restricting operations accordingly.
Enables flexible adjustment of operation methods for prohibited users, reducing the need for adult intervention and minimizing confusion by permitting or limiting operations based on the presence of authorized users.
Smart Images

Figure 2025136484000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to an in-vehicle voice-operated device, a voice-operated system, a voice-operated method, and a program. [Background technology]
[0002] Conventionally, when receiving instructions to operate a device through voice recognition, different weights are assigned to the control value (e.g., temperature setting value) for the device to be controlled (e.g., air conditioner) depending on whether the speaker is not restricted in their operation (e.g., an adult) or is restricted in their operation (e.g., a child) (see Patent Document 1 below).
[0003] For example, if a voice control instruction includes a numerical value related to the volume setting of an audio device or a television device, or a numerical value related to the temperature setting of an air conditioner, the control unit that receives the control instruction will weight the numerical value spoken by an adult and the numerical value spoken by a child and calculate the setting value. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-207169 Summary of the Invention [Problem to be solved by the invention]
[0005] In the above-mentioned conventional technology, this weighting is set uniformly for each speaker. For example, the control unit of this technology applies 100% to a number spoken by an adult. On the other hand, the control unit applies 50% to a number spoken by a child. In other words, in the above-mentioned conventional technology, the control method does not change depending on whether or not a passenger is present or the situation.
[0006] In other words, while conventional technology restricts children's operation regardless of whether an adult is present, there may be cases where you do not want to restrict operation when an adult is present, or conversely, you want to restrict operation when an adult is present but not when there is no adult present.
[0007] Therefore, the object of the disclosed embodiment is to enable an in-vehicle device that accepts operations on target equipment via user voice and executes control to flexibly adjust the manner of operation in response to voice operations from prohibited users who are prohibited from operating, depending on the situation of the presence of prohibited users who are not prohibited from operating. [Means for solving the problem]
[0008] One aspect of the disclosed embodiment is exemplified by an in-vehicle voice-operated device that operates a controlled device in response to a speaker's utterance. The in-vehicle voice-operated device includes a control unit that determines whether the speaker is a prohibited user who is prohibited from operating the controlled device or an authorized user who is not prohibited. If the speaker is a prohibited user, the control unit determines whether to operate the controlled device in response to the speaker's utterance based on the presence or absence of authorized users other than the speaker, and operates the controlled device based on the determination result. [Effects of the Invention]
[0009] When the speaker is a prohibited user who is prohibited from operating the controlled device, the in-vehicle voice operation device determines whether or not to operate the controlled device in response to the speaker's utterance depending on whether or not authorized users other than the speaker are present, and operates the controlled device. This makes it possible to flexibly adjust the manner of operation in response to voice operations from prohibited users who are prohibited from operating the device. [Brief explanation of the drawings]
[0010] [Figure 1] FIG. 1 is a diagram illustrating the configurations of an in-vehicle device and a voice-operated system according to the first embodiment, and the control between them. [Figure 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of the in-vehicle device. [Figure 3] FIG. 3 is a diagram illustrating an example of the availability determination table. [Figure 4] FIG. 4 is a flowchart illustrating a processing procedure of the in-vehicle device in the first embodiment. [Figure 5] FIG. 5 is a flowchart illustrating details of a control process based on a detection result in the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a possibility determination table according to the second embodiment. [Figure 7] FIG. 7 is a flowchart illustrating a control process based on a detection result according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION
[0011] First Embodiment An in-vehicle device 10, a voice-operated system 50, a voice-operated method, and a program according to one embodiment will be described below with reference to the drawings. Here, the voice-operated system 50 includes the in-vehicle device 10, the vehicle 1 that receives commands or is controlled by the in-vehicle device 10, and the audiovisual navigation device 10A. Note that the audiovisual navigation device 10A may be partly or entirely built into the in-vehicle device 10, or may be provided separately from the in-vehicle device 10. Note that the in-vehicle device 10 is an example of an in-vehicle voice-operated device, as it accepts voice commands and operates devices to be controlled (the vehicle 1, the audiovisual navigation device 10A, etc.).
[0012] (composition) 1 is a diagram illustrating the configuration of an in-vehicle device 10 and a voice-operated system 50 according to this embodiment, and the control therebetween. The in-vehicle device 10 receives voice operations via speech from a user inside the vehicle 1, such as a driver or a passenger, and controls or operates various parts of the vehicle 1. Targets of voice operation include, for example, the windows, parking brake, and air conditioner of the vehicle 1. Targets of voice operation also include, for example, the television function, audio function, telephone function, and navigation function of an audiovisual navigation device 10A.
[0013] The in-vehicle device 10 has a trained model that can classify people into at least adults and children through machine learning of human voices. The machine learning method is similar to general deep learning. That is, machine learning is performed using training data in which the voices of multiple people are labeled as either "adult" or "child," and a trained model is formed (S1). The voice includes features based on, for example, sound wavelength components or speech content contained in the voice, and is labeled as such. Examples of speech content features include the presence of child-specific terms such as "mom" in a voice with a higher pitch than adults, and the presence of a children's program or content designated in the television or audio function. The in-vehicle device 10 acquires the voice of a new speaker to be determined and inputs the acquired speech data into the trained model to recognize the speaker and determine whether the speaker is an adult or a child (S2).
[0014] The in-vehicle device 10 also has a trained model that can classify people into at least adults and children by machine learning images of people in advance. The machine learning method is similar to general deep learning. That is, machine learning is performed using training data including images of people in which multiple images of people are labeled as "adult" or "child," and a trained model is formed. The image includes features such as a face image (child's face, adult's face), an entire body image, and the like, and is labeled as described above. The in-vehicle device 10 acquires a new image of the speaker to be determined, and inputs the acquired image data into the trained model to recognize the speaker and determine whether the speaker is an adult or a child (S2).
[0015] The in-vehicle device 10 may also register in advance the voice of each individual user and the classification of the voice as either an adult or a child (S1). The data of the individual user's voice includes characteristics of the wavelength components of the sound and is used, for example, as a voiceprint. The in-vehicle device 10 acquires the voice of a new speaker to be determined and compares it with the registered voices. The in-vehicle device 10 then recognizes and identifies the speaker whose voice matches the registered voice and classifies the speaker as either an adult or a child (S2).
[0016] Furthermore, the in-vehicle device 10 can also register in advance an image of each individual user and the classification of the user as either an adult or a child (S1). The data of the image of each individual user includes image features and is used for image recognition. The image is, for example, an image of a face. The in-vehicle device 10 acquires a new image of the speaker to be judged and compares it with the registered images. Then, the in-vehicle device 10 recognizes and identifies the speaker of the image that matches the registered image and classifies the speaker as either an adult or a child (S2).
[0017] The in-vehicle device 10 classifies the speaker as an adult or a child, recognizes the speaker's voice, and accepts it as a voice operation command (S3). Examples of voice operations include "Turn on the TV" and "Set the TV to channel 1." Other examples of voice operations include "I want to listen to music..." and "Turn up the audio volume." Other examples of voice operations include "Turn on the air conditioning," "Raise the set temperature by 3 degrees," and "Open the windows one-third."
[0018] The in-vehicle device 10 manages a permission / prohibition determination table (see FIG. 3) in the main memory unit 12 (see FIG. 2) or the like. The permission / prohibition determination table sets whether or not control or operation corresponding to voice operation is permitted depending on whether or not there is a passenger in the vehicle 1. Restrictions, prohibitions, permission, etc. of voice operation by children, which are an example of prohibited users, are defined when an adult, which is an example of permitted users, is in the vehicle 1 and when no adult is in the vehicle 1. For example, whether or not a child is permitted to operate a device to be operated, or restrictions on the amount of operation of the device to be operated, etc. are defined.
[0019] The in-vehicle device 10 determines whether the voice operation recognized in S3 is permitted in the permission determination table, depending on the presence or absence of passengers in the vehicle 1. Then, the in-vehicle device 10 accepts the voice operation for an operation permitted in the permission determination table or for an operation amount within a range permitted in the permission determination table, and sends a command to the controlled device to execute control or operation (S4). For example, the in-vehicle device 10 permits a prohibited user, a child, to perform operations within a more limited range (functions, operation amount) than that permitted for an authorized user, an adult.
[0020] 2 is a diagram illustrating an example of the hardware configuration of the in-vehicle device 10. The hardware configuration of the in-vehicle device 10 is similar to that of a normal computer. The in-vehicle device 10 has a CPU 11, a main memory unit 12, and external devices connected via an interface (I / F), and executes information processing by a program.
[0021] The CPU 11 executes a computer program that has been loaded in an executable manner into the main memory unit 12, thereby providing the functions of the in-vehicle device 10. The main memory unit 12 is also referred to simply as a memory, and stores the computer program executed by the CPU 11, the data processed by the CPU 11, and the like. The CPU 11 is also referred to as a processor. However, the CPU 11 is not limited to a single processor, and may have a multi-processor configuration. Furthermore, the CPU 11 may be a single processor connected via a single socket, and may have a multi-core configuration.
[0022] Furthermore, the CPU 11 may include a plurality of different types of processors. For example, at least a portion of the processing of the in-vehicle device 10 may be provided by a dedicated processor such as a digital signal processor (DSP), a graphics processing unit (GPU), a numerical calculation processor, a vector processor, or an image processing processor, or an application specific integrated circuit (ASIC). Also, at least a portion of the in-vehicle device 10 may be a dedicated large scale integration (LSI) such as a field-programmable gate array (FPGA), or other digital circuit. Also, at least a portion of the in-vehicle device 10 may include an analog circuit.
[0023] The main memory unit 12 is a memory device that includes a dynamic random access memory (DRAM) and a static random access memory (SRAM). The memory may be a static random access memory (SRAM), a read only memory (ROM), etc. The CPU 11 and the main memory unit 12 can be called a control unit.
[0024] Examples of external devices include an external storage unit 13, a display unit 14, an operation unit 15, a communication unit 16, a microphone 17, and a camera 18. The external devices do not have to be integrated with the control unit (CPU 11, main storage unit 12, etc.). Each of the external devices may be connected to the housing of the in-vehicle device 10 via an interface.
[0025] The external storage unit 13 is used, for example, as a storage area that supplements the main storage unit 12, and stores computer programs executed by the CPU 11, data processed by the CPU 11, etc. The external storage unit 13 is a hard disk drive, a solid state drive (SSD), etc. Furthermore, the in-vehicle device 10 may be provided with a drive device for a removable storage medium. The removable storage medium is, for example, a Blu-ray disc, a digital versatile disc (DVD), a compact disc (CD), a flash memory card, etc.
[0026] The display unit 14 is, for example, a liquid crystal display, an electroluminescence panel, an organic light emitting diode (OLED), etc. The operation unit 15 is, for example, an array of push buttons, a keyboard, a pointing device, etc. In this embodiment, a touch panel is exemplified as a pointing device. The communication unit 16 exchanges data with other devices on the network. The communication unit 16 is compatible with Long Term Evolution (LTE), 4th Generation Mobile The wireless communication device may be a wireless communication device that accesses a wireless network such as a 4th Generation Mobile Communication System (4G), a 5th Generation Mobile Communication System (5G), or a wireless local area network (LAN).
[0027] Microphone 17 detects the speaker's voice, converts it into an electrical signal, and transmits the generated voice data to CPU 11. Camera 18 captures an image of the speaker and transmits the image data to CPU 11. Camera 18 has, for example, a complementary metal oxide semiconductor (CMOS) sensor or a charge coupled device (CCD).
[0028] FIG. 3 is a diagram illustrating an example of a permission / prohibition determination table. The permission / prohibition determination table is an example of a table that defines, for each function of a device to be operated, at least one of permission and denial of operation depending on whether an authorized user is present. In the permission / prohibition determination table, each row of the table is created for each operation type. The table has three columns: "Operation Type," "Children Only," and "Adult Present." The "Operation Type" column specifies the type of operation defined in each row. In FIG. 3, the operation types are written in natural language, but may also be specified by numbers or other codes. In FIG. 3, the "operation types" are divided into hardware operations and voice operations, and the voice operations are further subdivided.
[0029] Hardware operation means operating the hardware, such as the handbrake lever of vehicle 1, the buttons for electrically opening and closing the windows, the air conditioning switch, and the temperature setting volume. Voice operation is a function that recognizes the speaker's voice, interprets the speaker's intention as a command, and executes the control or operation corresponding to the command on the controlled device.
[0030] The categories subdivided by voice operation include, for example, turning a television (TV) on and off, operating channels on a television or audio system, volume control, etc. Further, the categories subdivided include making and receiving phone calls, turning an air conditioner on and off and setting the temperature, opening and closing windows, etc.
[0031] In FIG. 3, the column "children only" defines whether or not each row can be operated when the in-vehicle device 10 cannot recognize an adult as a passenger in the vehicle 1 and only recognizes a child. However, the in-vehicle device 10 may recognize passengers in the vehicle 1 from the voice of the speaker, or may recognize passengers in the vehicle 1 from an image captured by the camera 18 inside the vehicle. Furthermore, "adult present" defines whether or not voice operation (i.e., operation of each row) by a child can be performed when the in-vehicle device 10 can recognize an adult as a passenger in the vehicle 1.
[0032] In this embodiment, for example, hardware operations by children are prohibited, and operations are permitted only when an adult is present. Also, in this embodiment, when "children only" is selected, operations of the television function (on, off, volume control) and the audio function are permitted. On the other hand, when "children only" is selected, telephone operations (making and receiving calls) are prohibited.
[0033] Furthermore, in the "Children Only" setting, the air conditioner is permitted to be turned on but prohibited from being turned off. This is because the temperature inside the vehicle may become high or low, and it is desirable to permit the air conditioner to be turned on. Furthermore, window operation is generally prohibited, but may be permitted when the temperature inside the vehicle is high or low. The in-vehicle device 10 may monitor the temperature inside the vehicle using, for example, a temperature sensor. The in-vehicle device 10 may prohibit window operation when the temperature is between 15 and 20 degrees Celsius, and permit window operation when the temperature is below 15 degrees Celsius or above 20 degrees Celsius, for example.
[0034] Furthermore, when "an adult is present," the in-vehicle device 10 permits most voice operations to be performed by the child. However, if the content of the voice operation performed by the adult differs from the content of the voice operation performed by the child, the in-vehicle device 10 prioritizes the voice operation performed by the adult.
[0035] (Processing Procedure) 4 is a flowchart illustrating steps of a processing procedure of the in-vehicle device 10 in this embodiment. This processing is started, for example, when the in-vehicle device 10 is started. This processing may also be started when the ignition power supply or accessory power supply of the vehicle 1 is turned on. However, the in-vehicle device 10 may receive power from a power supply other than the ignition power supply or accessory power supply, and start the processing of FIG. 4 when a passenger gets into the vehicle 1.
[0036] In this process, first, the in-vehicle device 10 identifies the passengers (S11). For example, the in-vehicle device 10 may detect the voices of the passengers using the microphone 17 and input the detected voices into the trained model (a model that classifies people based on their voices) described in FIG. 1, thereby classifying the passengers into children and adults. Alternatively, the in-vehicle device 10 may compare the voices detected by the microphone 17 with the voices of registered users, identify each speaker (passenger), and then classify the passengers into children and adults.
[0037] In this process, the in-vehicle device 10 may classify the passengers into children and adults by inputting images of the passengers captured by the camera 18 into the trained model (a model that classifies people based on images) described in Fig. 1. The in-vehicle device 10 may also compare the images captured by the camera 18 with images of registered users to identify each passenger and then classify them into children and adults.
[0038] Next, the in-vehicle device 10 detects whether or not an adult, who is a permitted user, is present among the passengers based on the passenger information obtained in S11 (S12).Then, the in-vehicle device 10 executes control processing based on the detection result in S12 (S13).That is, the in-vehicle device 10 executes processing on the control target device while determining whether or not to accept voice operation by a child, who is a prohibited user, depending on whether or not an adult is present among the passengers.
[0039] Then, the in-vehicle device 10 determines whether the door is opened or closed (S14). The in-vehicle device 10 can detect whether the door is opened or closed from a Controller Area Network (CAN) signal. If the door is not opened or closed, the in-vehicle device 10 returns to S13 and continues the process. On the other hand, if the door is opened or closed, the in-vehicle device 10 returns to S11 and continues the process from identifying the occupants again. This is because if the door is opened or closed, there is a possibility that the occupants will be replaced. Therefore, the in-vehicle device 10 can identify the occupants and continue the process even if the occupants of the vehicle 1 are replaced, if a new occupant gets on, or if at least some of the occupants get off.
[0040] FIG. 5 is a flowchart illustrating the details of the control process (S13 in FIG. 4) based on the detection result. In this embodiment, this process is referred to as control process (A) based on the detection result. In this process, first, the in-vehicle device 10 detects a voice operation from the passenger (speaker) (S130). In the voice operation, the in-vehicle device 10 analyzes the voice (natural language) from the passenger (speaker) to understand a command for the controlled device. Then, the in-vehicle device 10 operates the controlled device according to the understood command.
[0041] Next, the in-vehicle device 10 determines whether or not only children are passengers (S131). If not only children who are prohibited users but also adults who are permitted users are passengers, the in-vehicle device 10 inquires of the permitted users to confirm whether or not the restriction on the prohibited users (prohibition of operation) can be lifted (S132). This inquiry is made, for example, by displaying on the display unit 14 or outputting audio from the speaker. Furthermore, a confirmation response from the permitted users is received, for example, through the microphone 17 or the operation unit 15. The processing of S132 is an example of outputting a notification inquiring whether or not to operate the controlled device and receiving input of a response from the permitted users indicating that they will operate the controlled device.
[0042] Then, if the restriction (prohibition of operation) can be released by a confirmation response from the adult, the in-vehicle device 10 releases the function restriction, i.e., the prohibition of operation, and executes control corresponding to the voice operation, i.e., operation (S134). The control for releasing the function restriction is, for example, the process corresponding to the column "Adult is present" in Fig. 3, and executes the process corresponding to the voice operation from the child. In this case, the in-vehicle device 10 may refer to the possibility determination table to confirm the functions for which the function restriction (prohibition of operation) can be released.
[0043] For example, if voice operations by an adult and a child are detected simultaneously, or if an adult's voice operation is already valid, the in-vehicle device 10 gives priority to the adult's voice operation and executes the operation corresponding to the voice operation. For example, if a song specified by an adult is already playing, a child's request to "stop playing" will not be accepted.
[0044] On the other hand, if the determination in S133 indicates that the restriction (i.e., prohibition of operation) cannot be lifted, the in-vehicle device 10 proceeds to S135. Also, if the determination in S131 indicates that only children are occupants, the in-vehicle device 10 proceeds to S135. Then, the in-vehicle device 10 refers to the permission / prohibition determination table in the main storage unit 12, and confirms the function restriction (permitted operation or prohibited operation) for the voice operation detected in S130 (S135).
[0045] Then, the in-vehicle device 10 executes the control with the function restriction (S136). The control is, for example, a process corresponding to the "Children Only" column in FIG. 4. That is, the in-vehicle device 10 executes a process corresponding to a voice operation from a child within the range limited by the "Children Only" column. For example, the in-vehicle device 10 accepts voice operation commands (functions) that are permitted even when only a child is present. Furthermore, the in-vehicle device 10 accepts the amount of operation by voice operation that is permitted even when only a child is present. For example, the volume of the television function and audio function is limited. Furthermore, the set temperature of the air conditioning is limited. That is, operations other than the voice operation commands (functions) that are permitted when only a child is present are prohibited. Furthermore, operations that exceed the amount of operation by voice operation that is permitted when only a child is present are prohibited.
[0046] 4 and proceeds to S14. The in-vehicle device 10 may omit the processes of S132 and S133. That is, when an adult who is a permitted user is present among the passengers, the in-vehicle device 10 does not necessarily have to confirm with the adult whether or not to accept voice operation from a child who is a prohibited user.
[0047] (Effects of the embodiment) As described above, the in-vehicle device 10 determines whether the speaker who is a passenger is a prohibited user (child) who is prohibited from operating the controlled device, or an authorized user (adult) who is not prohibited. If the speaker is a prohibited user, the in-vehicle device 10 determines whether to allow or disallow operation of the controlled device in response to the speaker's speech, depending on whether authorized users other than the speaker are present, and operates the controlled device based on the determination result. In other words, the in-vehicle device 10 can flexibly adjust the operation method (prohibition or permission of operation, etc.) for voice operations from prohibited users who are prohibited from operating, depending on the presence or absence of passengers.
[0048] Furthermore, when operating a controlled device based on the above determination result, the in-vehicle device 10 operates the controlled device when an authorized user is present, and does not operate the controlled device when an authorized user is not present. In other words, even a prohibited user (child) can operate the device under the adult's supervision when an authorized user (adult) is present in the vehicle. As a result, the effort required of an adult to operate the device on behalf of the prohibited user is reduced. Therefore, when a prohibited user, a child, is present in the vehicle, voice operations from speakers such as children can be appropriately processed. In other words, the in-vehicle device 10 can flexibly adjust the operation method, the method and scope of prohibition, and the method and scope of permission for voice operations from prohibited users who are prohibited from operating the device, depending on the presence or absence of passengers.
[0049] Furthermore, when an authorized user is present, the in-vehicle device 10 operates the controlled device by voice operations from the prohibited user within a more limited range (functions, operation amount) than that permitted for the authorized user. Therefore, the in-vehicle device 10 accepts and executes voice operations from the prohibited user within an appropriate range.
[0050] Furthermore, when an adult who is an authorized user is present, the in-vehicle device 10 outputs a notification asking whether or not to operate the controlled device, and operates the controlled device when it receives an answer from the authorized user indicating that it will operate the controlled device (S132 to S134 in FIG. 5 above). Thus, the in-vehicle device 10 can flexibly accept decisions according to the situation of the adult who is an authorized user.
[0051] Furthermore, the in-vehicle device 10 includes a main storage unit 12 that stores a permission / prohibition determination table (see FIG. 3) that defines, for each function of a control target device, whether or not the operation is permitted in response to the speaker's utterance, depending on whether or not an authorized user is present. The in-vehicle device 10 then refers to this table to determine whether or not the control target device is permitted to be operated. Therefore, the in-vehicle device 10 can flexibly execute control corresponding to the presence or absence of an authorized user, using the permission / prohibition determination table, which is control information in the main storage unit 12.
[0052] Second Embodiment In the first embodiment, when the speaker is a prohibited user and it is determined that an authorized user is present, the in-vehicle device 10 permits the operation and operates the controlled device. On the other hand, when the speaker is a prohibited user and it is determined that an authorized user is not present, the in-vehicle device 10 does not permit the operation or limits the range of the permitted operation and operates the controlled device.
[0053] In this embodiment, conversely, when the speaker is a prohibited user and it is determined that there are no permitted users, the in-vehicle device 10 permits the operation and controls or operates the controlled device, because, for example, when only a child is present in the vehicle, it may be desirable to execute functions such as air conditioning, opening and closing windows, or making an emergency call.
[0054] On the other hand, in this embodiment, when the speaker is a prohibited user and it is determined that a permitted user is present, the operation is not permitted or the permitted range is limited to control or operate the controlled device, because, for example, while adults can be considerate of children, if a child freely performs voice operations, it may cause confusion in the vehicle interior.
[0055] (composition) The configuration of the in-vehicle device 10 in this embodiment is the same as that in the first embodiment, and therefore a description thereof will be omitted. FIG. 6 is a diagram illustrating an example of a feasibility determination table in this embodiment. The structure of the feasibility determination table in this embodiment is the same as that in FIG. 3 of the first embodiment. However, in this embodiment, in the "children only" column, hard operations other than hard operations for driving are permitted. Here, a hard operation for driving is, for example, operation of the parking brake. Note that hard operations for driving by children are prohibited even when "an adult is present." Furthermore, hard operations other than hard operations for driving are, for example, operation of the air conditioning function (turning on the air conditioning, setting the temperature), etc.
[0056] In this embodiment, most voice operations are permitted in the "Children Only" column. Examples of voice operations that are not permitted include operating the parking brake. On the other hand, television functions, audio functions, telephone calls, air conditioning functions, window opening and closing, emergency call functions, and the like are permitted. Furthermore, the volume of television and audio functions may be limited by voice operations performed by children. Furthermore, the temperature setting range for air conditioning functions may be limited by voice operations performed by children.
[0057] On the other hand, when "an adult is present," the television function, audio function, telephone, air conditioning function, window opening / closing, emergency call function, etc. are not permitted. These functions can be set by adults, and allowing voice control by children may cause confusion. However, FIG. 6 is merely an example, and the processing of the in-vehicle device 10 of this embodiment is not limited by the permission / prohibition determination table in FIG. 6. For example, the emergency call function may be permitted even when "an adult is present."
[0058] (Processing Procedure) 7 is a flowchart illustrating the control process (B) based on the detection result of this embodiment. The process of FIG. 4 is also applied to this embodiment as it is. FIG. 7 is also a flowchart illustrating the details of the control process (S13 in FIG. 4) based on the detection result. In the process of FIG. 7, the processes of S130 and S131 are the same as those in FIG. 5, so their description will be omitted.
[0059] If it is determined in S131 that not only children but also adults are occupants, the in-vehicle device 10 refers to the permission / prohibition determination table in the main storage unit 12 and determines whether the voice operation detected in S130 is permitted. The function restrictions for the device are checked (S137). Here, the function restrictions include, for example, permitted operations, prohibited operations, permitted operation amounts, prohibited operation amounts, etc.
[0060] Then, the in-vehicle device 10 executes control with restricted functions (S138). Control with restricted functions is, for example, processing corresponding to the column "Adult is present" in FIG. 6. That is, the in-vehicle device 10 executes processing corresponding to voice operations from a child within the range limited by the column "Adult is present." For example, as shown in FIG. 6, the in-vehicle device 10 basically does not accept voice operations from a child when "Adult is present." That is, the processing of S138 can be said to be an example of the in-vehicle device 10 prohibiting operations and controlling a control target device. However, as explained in FIG. 6, the control of the in-vehicle device 10 is not limited to that shown in FIG. 6, and some processing may be accepted.
[0061] On the other hand, if it is determined in S131 that only children are in the vehicle, the in-vehicle device 10 checks the function restriction on the voice operation detected in S130 (S139). Then, the in-vehicle device 10 releases the function restriction (prohibition of operation when an adult is present) and executes control or operation corresponding to the voice operation (S13A). The control or operation performed when the function restriction (prohibition of operation) is released is, for example, the process corresponding to the "Children Only" column in FIG. 6, and executes the process corresponding to the voice operation from the child. That is, in this embodiment, when only children are present in the vehicle, the in-vehicle device 10 accepts, for example, the air conditioning function, window opening / closing, emergency call function, etc. That is, the process of S13A can be said to be an example of the in-vehicle device 10 permitting operation and operating a control target device. However, for example, operation of the parking brake, etc. is not accepted.
[0062] While there are no restrictions on voice operations for adults who are authorized users, children who are prohibited users are permitted to operate a more limited range (functions, operation amounts) of functions than those permitted for authorized users. For example, children are not permitted to operate the parking brake through voice operations. Furthermore, children may be permitted to limit the volume of television and audio functions through voice operations. Furthermore, children may be permitted to limit the temperature setting range for air conditioning functions through voice operations.
[0063] (Effects of the embodiment) As described above, in this embodiment, the in-vehicle device 10 determines whether to operate the controlled device in response to the speaker's utterance depending on whether an authorized user is present, and operates the controlled device based on the determination result. In this case, the in-vehicle device 10 operates the controlled device when an authorized user is not present, and does not operate the controlled device when an authorized user is present. Therefore, when an authorized user, for example, an adult, is present in the vehicle, it is possible to avoid confusion in operating the vehicle 1 due to voice operations by a prohibited user, such as a child. This is because when an adult is present in the vehicle, the adult can operate the vehicle 1.
[0064] On the other hand, when only a child is present in the vehicle, the air conditioning function (air conditioner), opening and closing of windows, emergency call function, etc. are permitted. When there is no adult to operate the device for the child, the child is allowed to operate the device to a certain extent. That is, the in-vehicle device 10 allows the child to perform minimum operations even when the child is alone in the vehicle or when only the child is in the vehicle. That is, when only the child is present in the vehicle, the in-vehicle device 10 can appropriately accept requests from the child.
[0065] In this embodiment, when an authorized user is not present, the in-vehicle device 10 operates in a more limited range (functions, operation amount) than that permitted for authorized users. Therefore, when only a child is present in the vehicle, the in-vehicle device 10 can appropriately accept voice operations and control the control target devices.
[0066] Furthermore, in the same manner as in the first embodiment, the in-vehicle device 10 determines the authorized users for each function of the control target device. The in-vehicle device 10 includes a main storage unit 12 that stores a permission / prohibition determination table (see FIG. 6) that defines whether or not an operation is permitted in response to an utterance of a speaker, depending on whether or not the speaker is a permitted user. The in-vehicle device 10 then refers to this table to determine whether or not to permit an operation of a controlled device. Therefore, the in-vehicle device 10 can flexibly execute control depending on whether or not there is an authorized user, using the permission / prohibition determination table, which is control information stored in the main storage unit 12. [Explanation of symbols]
[0067] 1 vehicle 10 Onboard equipment 11 CPU 12 Main memory 13 External memory unit 14 Display section 15 Control section 16 Communications Department 16. Mike 18 Camera 50 Voice-operated system
Claims
1. An in-vehicle voice-operated device that operates a control target device in response to a speaker's speech, determining whether the speaker is a prohibited user who is prohibited from operating the control target device or an authorized user who is not prohibited; and a control unit that executes a step of determining whether or not to operate the control-target device in response to the utterance of the speaker, depending on whether or not there are permitted users other than the speaker, when the speaker is the prohibited user, and operating the control-target device based on the determination result. In-car voice control device.
2. The in-vehicle voice-operated device according to claim 1, wherein, in the operating step, the control unit operates the controlled device when the authorized user is present, and does not operate the controlled device when the authorized user is not present.
3. The in-vehicle voice-operated device according to claim 2 , wherein the control unit, when the authorized user is present, operates the control target device within a more limited range than that permitted for the authorized user.
4. The in-vehicle voice-operated device of claim 2, wherein the control unit, when the authorized user is present, outputs a notification asking whether or not to operate the controlled device, and operates the controlled device when it receives an input from the authorized user indicating that it will operate the controlled device.
5. The in-vehicle voice-operated device according to claim 1, wherein, in the operating step, the control unit operates the controlled device when the authorized user is not present, and does not operate the controlled device when the authorized user is present.
6. The in-vehicle voice-operated device according to claim 5 , wherein the control unit, when the authorized user is not present, operates the control target device within a more limited range than that permitted for the authorized user.
7. The in-vehicle voice operation device of claim 1 further comprises a memory unit storing a table that defines, for each function of the controlled device, at least one of permission and denial of operation in accordance with the speaker's speech depending on whether or not the authorized user is present, and the control unit determines whether or not to operate the controlled device by referring to the table.
8. A voice operation system having a control target device and an in-vehicle voice operation device that operates the control target device in response to an utterance of a speaker, wherein the in-vehicle voice operation device determining whether the speaker is a prohibited user who is prohibited from operating the control target device or an authorized user who is not prohibited; and a control unit that executes a step of determining whether or not to operate the control-target device in response to the utterance of the speaker, depending on whether or not there are permitted users other than the speaker, when the speaker is the prohibited user, and operating the control-target device based on the determination result. Voice-operated system.
9. A voice operation method in which a computer operates a control target device in response to a speaker's speech, comprising: determining whether the speaker is a prohibited user who is prohibited from operating the control target device or an authorized user who is not prohibited; If the speaker is the prohibited user, determining whether or not to operate the control-target device in response to the utterance of the speaker depending on whether or not there are permitted users other than the speaker, and operating the control-target device based on the determination result. Voice control method.
10. A program for causing a computer to operate a control target device in response to a speaker's utterance, determining whether the speaker is a prohibited user who is prohibited from operating the control target device or an authorized user who is not prohibited; and when the speaker is the prohibited user, determining whether or not to operate the control-target device in response to the utterance of the speaker depending on whether or not there are permitted users other than the speaker, and operating the control-target device based on the determination result. program.
Citation Information
Patent Citations
Apparatus controller and apparatus control method
JP2018207169A