JP2020144285A - Agent system, information processing device, control method for mobile body mounted apparatus, and program - Google Patents

Abstract

To provide an agent system, an information processing device, a control method for a mobile body mounted device, and a program which enable occupants to control in-vehicle devices with desired voice.SOLUTION: The mobile device control device includes a voice recognition unit (216A) which recognizes voices collected by a microphone which collects the voices in a passenger's vehicle interior, a meaning interpretation unit (218A) which interprets meanings of the voices, and a mobile body apparatus control unit (134) which controls an in-vehicle device based on a meaning interpreted by the meaning interpretation unit. The meaning interpretation unit recognizes that the meaning of the voice instructs control of the in-vehicle device, using an utterance command dictionary stored by the storage unit and associated together with an utterance command (command) and a content indicated by the utterance command, and when it is interpreted that the recognized voice recognized by the voice recognition unit includes an instruction/command to register a new utterance command, the new utterance command is registered in the utterance command dictionary together with the contents indicated by the new utterance command.SELECTED DRAWING: Figure 2

Description

The present invention relates to an agent system, an information processing device, a mobile body-mounted device control method, and a program.

Research on human-machine interfaces that provide information through voice dialogue with humans is underway. In connection with this, the occupants use a technique to determine whether or not to speak to the person, the volume of speech, and the tone of speech based on the situation of the person to be communicated by the robot, and a dictionary in which vocabulary is registered. A technique of recognizing an uttered voice and controlling a plurality of in-vehicle devices according to the content of the recognized voice is known (see, for example, Patent Documents 1 and 2).

Japanese Patent No. 4976903 Japanese Unexamined Patent Publication No. 2007-286136

Here, the occupant may want to give instructions to the frequently used controlled device by simple words or short words, however, with the conventional technology, it is difficult to control the in-vehicle device by the voice desired by the occupant. Met.

Aspects of the present invention have been made in consideration of such circumstances, and are an agent system, an information processing device, and a mobile body-mounted device control method that enable an in-vehicle device to be controlled by a voice desired by an occupant. , And one of the purposes is to provide a program.

The agent system, information processing device, mobile body-mounted device control method, and program according to the present invention have the following configurations.
(1): The agent system according to one aspect of the present invention is a command for controlling a mobile body-mounted device mounted on a moving body on which an occupant is on board and the mobile body-mounted device, and the sound is picked up by a microphone. The voice recognition unit includes a voice recognition unit that recognizes a voice including an utterance command that is a voice of an occupant, and a meaning interpretation unit that interprets the meaning of the voice recognized by the voice recognition unit. When the meaning is interpreted to include an instruction to register a new utterance command, the new utterance command is registered in the storage unit.

(2): In the aspect of (1) above, when the meaning interpreting unit interprets that the meaning of the voice includes an instruction to delete the registered utterance command, the utterance command is deleted from the storage unit. To do.

(3): In the embodiment (1) or (2), the storage unit in which the utterance command is registered is provided, and the utterance command and the content of control indicated by the utterance command correspond to each other in the storage unit. The utterance command dictionary attached and registered is stored.

(4): In any of the above aspects (1) to (3), the agent system uses the utterance command dictionary to interpret the voice recognized by the voice recognition unit by the meaning interpretation unit. It is further provided with an on-board device control unit that controls the mobile on-board device based on the meaning of.

(5): In the aspect of (3) above, the semantic interpretation unit interprets the voice recognized by the voice recognition unit as including an instruction to register a new utterance command, and the moving body. The new utterance command is added to the basic utterance command dictionary based on the basic utterance command dictionary in which the basic voice command, which is the basic control command of the on-board device, and the content of control for the basic voice command are associated with each other. If it is not included, it is registered in the utterance command dictionary.

(6): In the embodiment (3) or (5) above, the semantic interpretation unit uses the voice recognized by the voice recognition unit as an instruction for control of the mobile-mounted device immediately before by the occupant. When it is interpreted that the instruction to register the new utterance command is included, the new utterance command is registered in the utterance command dictionary together with the content of the control performed by the occupant of the mobile body on the mobile body-mounted device immediately before. It is a thing.

(7): In any of the above aspects (3) to (6), an utterance that specifies the position of the speaker of the voice including the utterance command picked up by the microphone among the occupants of the moving body. The person position specifying unit, the position information of the speaker specified by the speaker position specifying unit, and the operation authority position information indicating the position of an occupant who has the operation authority for the moving body mounted device mounted on the moving body. , The speaker of the voice including the utterance command has the operation authority of the mobile-mounted device based on the mobile-mounted device information included in the meaning of the utterance command interpreted by the utterance interpreting unit. The operation authority determination unit for determining whether or not the utterance is further provided, and the semantic interpretation unit interprets the voice recognized by the voice recognition unit as including an instruction to register a new utterance command. When the authority determination unit determines that the speaker of the voice including the utterance command has the operation authority of the mobile body-mounted device, the new utterance command is controlled by the new utterance command. It is registered in the utterance command dictionary together with the contents.

(8): In the aspect of (4) above, the agent system identifies the position of the speaker of the voice including the utterance command picked up by the microphone among the occupants of the moving body. The unit, the position information of the speaker specified by the speaker position specifying unit, the operation authority position information indicating the position of an occupant having the operation authority for the mobile body-mounted device mounted on the moving body, and the meaning thereof. Whether or not the speaker of the voice including the utterance command has the operation authority of the mobile-mounted device based on the mobile-mounted device information included in the meaning of the utterance command interpreted by the interpretation unit. The on-board device control unit is further provided with an operation authority determination unit for determining the above, and the on-board device control unit recognizes that the meaning of the utterance indicates control of the mobile on-board device by the meaning interpretation unit. When the operation authority determination unit determines that the speaker of the voice including the utterance command has the operation authority of the mobile body-mounted device, the operation authority-mounted device is controlled.

(9): The information processing device according to one aspect of the present invention is a command for controlling a mobile body-mounted device mounted on the moving body, and includes an utterance command which is a voice of an occupant on the moving body. An acquisition unit that acquires voice, a storage unit that stores an utterance command dictionary in which the utterance command and the content of control including information on a mobile device mounted to be controlled indicated by the utterance command are associated with each other, and a storage unit. A voice recognition unit that recognizes the voice, a meaning interpretation unit that interprets the meaning of the voice recognized by the voice recognition unit, and a generation unit that generates information corresponding to the meaning content of the voice interpreted by the meaning interpretation unit. And.

(10): In the aspect of (9) above, the information processing apparatus controls the on-board device control unit that controls the mobile on-board device based on the information corresponding to the meaning and content of the voice generated by the generation unit. Further prepare.

(11): In the mobile body-mounted device control method according to one aspect of the present invention, the utterance command and the content of the control including the information of the mobile-mounted device to be controlled indicated by the utterance command are associated with each other. A single or multiple computers in a system with a storage unit that stores an utterance command dictionary interpret the steps of recognizing a voice containing an utterance command spoken by an occupant on a moving object and the meaning of the recognized voice. Steps to be performed, steps to acquire information on the mobile device mounted device to be controlled and control contents by referring to the utterance command dictionary, and mobile mounted to be controlled based on the meaning of the interpreted voice. When it is interpreted that the step of controlling the device and the recognized voice include an instruction to register a new utterance command, the new utterance command is combined with the control content indicated by the new utterance command. It has a step of registering in a dictionary.

(12): In the aspect of (11) above, the mobile body-mounted device control method displays the meaning of the voice in the utterance command dictionary with respect to the meaning of the voice after the step of interpreting the meaning of the voice. If there is a corresponding control content, the interpretation content of the voice meaning generated by the step of interpreting the voice meaning is added to the standard character information control content by referring to the utterance command dictionary. It has additional steps to replace.

(13): The program according to one aspect of the present invention stores an utterance command dictionary in which an utterance command and a control content including information on a mobile device to be controlled indicated by the utterance command are associated with each other. A process of recognizing a voice including an utterance command uttered by an occupant on a moving object and a process of interpreting the meaning of the recognized voice, which is installed in one or more computers in a system having a storage unit. , The process of acquiring the information and the content of control of the mobile-mounted device to be controlled by referring to the utterance command dictionary, and the mobile-mounted device to be controlled based on the meaning of the interpreted voice. When it is interpreted that the process of controlling the above and the recognized voice include an instruction to register a new utterance command, the new utterance command is combined with the control content indicated by the new utterance command. It is to be performed by the computer including the process of registering in the dictionary.

According to the aspects (1) to (13), it is possible to enable the vehicle-mounted device to be controlled by the voice desired by the occupant.

It is a figure which shows an example of the configuration of the agent system 1 using the vehicle-mounted device control device which concerns on 1st Embodiment. It is a figure which shows an example of the structure of the agent apparatus 100 which concerns on 1st Embodiment. It is a figure which shows an example of the vehicle interior seen from the driver's seat. It is a figure which shows an example of the vehicle interior which looked at the vehicle M from above. It is a figure which shows an example of the content of operation authority position information 154. It is a figure which shows an example of the structure of the server apparatus 200 which concerns on 1st Embodiment. It is a figure which shows an example of the contents of the basic utterance command dictionary 232. It is a figure which shows an example of the contents of the user utterance command dictionary 234. It is a flowchart which shows the flow of a series of processing of the agent apparatus 100 which concerns on 1st Embodiment. It is a flowchart which shows the process flow of the example of the server apparatus 200 which concerns on 1st Embodiment. It is a figure which shows an example of the agent apparatus 100A which concerns on 2nd Embodiment. It is a flowchart which shows the flow of a series of processing of the agent apparatus 100A which concerns on 2nd Embodiment. It is a flowchart which shows the flow of a series of processing of the agent apparatus 100A which concerns on 2nd Embodiment.

Hereinafter, embodiments of the agent system, the information processing device, the mobile body-mounted device control method, and the program of the present invention will be described with reference to the drawings.

<Embodiment>
[System configuration]
FIG. 1 is a diagram showing an example of a configuration of an agent system 1 using the in-vehicle device control device according to the first embodiment. The agent system 1 according to the first embodiment includes, for example, an agent device 100 mounted on a vehicle (hereinafter, vehicle M) and a server device 200. The vehicle M is, for example, a vehicle such as two wheels, three wheels, or four wheels. The drive source of these vehicles may be an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination thereof. The electric motor operates by using the electric power generated by the generator connected to the internal combustion engine or the electric power generated by the secondary battery or the fuel cell.

The agent device 100 and the server device 200 are communicably connected via the network NW. The network NW includes a LAN (Local Area Network), a WAN (Wide Area Network), and the like. The network NW may include, for example, a network using wireless communication such as Wi-Fi or Bluetooth (registered trademark, hereinafter omitted). The agent system 1 may be composed of a plurality of agent devices 100 and a plurality of server devices 200.

The agent device 100 acquires a voice from the occupant of the vehicle M by using the agent function, and transmits the acquired voice to the server device 200. Further, the agent device 100 interacts with the occupants, provides information such as images and videos, and uses the in-vehicle device VE and other devices based on the data (for example, agent setting data) obtained from the server device. To control. For example, a plurality of in-vehicle devices VE are mounted on the vehicle M. The in-vehicle device VE includes, for example, devices related to automatic driving and advanced driving support (for example, devices related to ACC (Adaptive Cruise Control), VSA (Vehicle Stability Assist), etc.), air conditioners, power windows, audio, car navigation, and the like. ..

The server device 200 communicates with the agent device 100 mounted on the vehicle M and acquires various data from the agent device 100. The server device 200 generates agent setting data related to inquiries by voice or the like based on the acquired data, and provides the generated agent setting data to the agent device 100. The function of the server device 200 according to the first embodiment is included in the agent function. Further, the function of the server device 200 updates the agent function in the agent device 100 to a more accurate function.

[Agent device configuration]
FIG. 2 is a diagram showing an example of the configuration of the agent device 100 according to the first embodiment. The agent device 100 according to the first embodiment includes, for example, an agent-side communication unit 102, a microphone (microphone) 106, a speaker 108, a display unit 110, an agent-side control unit 120, and an agent-side storage unit 150. Be prepared. These devices and devices may be connected to each other by a multiplex communication line such as a CAN (Controller Area Network) communication line, a serial communication line, a wireless communication network, or the like. The configuration of the agent device 100 shown in FIG. 2 is merely an example, and a part of the configuration may be omitted or another configuration may be added.

The agent-side communication unit 102 includes a communication interface such as a NIC (Network Interface controller). The agent-side communication unit 102 communicates with the server device 200 and the like via the network NW.

The microphone 106 is a voice input device that converts the sound in the vehicle interior into an electric signal and collects the sound. The microphone 106 outputs the collected voice data (hereinafter referred to as voice data) to the agent side control unit 120. For example, the microphone 106 is installed near the front when the occupant sits on the seat in the vehicle interior. For example, the microphone 106 is installed near a mat lamp, steering wheel, instrument panel, or seat. A plurality of microphones 106 may be installed in the vehicle interior.

The speaker 108 is installed, for example, near the seat in the vehicle interior or near the display unit 110. The speaker 108 outputs sound based on the information output by the agent-side control unit 120.

The display unit 110 includes a display device such as an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence) display. The display unit 110 displays an image based on the information output by the agent-side control unit 120.

FIG. 3 is a diagram showing an example of the vehicle interior as seen from the driver's seat. Microphones 106A to 106C, speakers 108A to 108C, and display units 110A to 110C are installed in the vehicle interior of the illustrated example. The microphone 106A is provided on the steering wheel, for example, and mainly collects the voice spoken by the driver. The microphone 106B is provided, for example, on the instrument panel (dashboard or garnish) IP in front of the passenger seat, and mainly collects the voice spoken by the passenger in the passenger seat. The microphone 106C is installed, for example, near the center of the instrument panel (between the driver's seat and the passenger's seat).

The speaker 108A is installed, for example, below the door on the driver's side, the speaker 108B is installed, for example, below the door on the passenger side, and the speaker 108C is installed near, for example, the display 110C, that is, the instrument. It is installed near the center of the panel IP.

The display unit 110A is a HUD (Head-Up Display) device that displays a virtual image at the tip of the line of sight when the driver visually recognizes the outside of the vehicle, for example. The HUD device is, for example, a device that allows an occupant to visually recognize a virtual image by projecting light onto a front windshield of a vehicle M or a transparent member called a combiner having light transmission. The occupant is mainly a driver, but may be a occupant other than the driver.

The display unit 110B is provided on the instrument panel IP near the front of the driver's seat (the seat closest to the steering wheel), and is installed at a position where the occupant can see through the gap between the steering wheels or through the steering wheel. The display unit 110B is, for example, an LCD, an organic EL display device, or the like. On the display unit 110B, for example, an image of the speed of the vehicle M, the engine speed, the remaining fuel amount, the radiator water temperature, the mileage, and other information is displayed.

The display unit 110C is installed near the center of the instrument panel IP. The display unit 110C is, for example, an LCD, an organic EL display device, or the like, like the display unit 110B. The display unit 110C displays contents such as TV programs and movies.

The vehicle M may be further provided with a microphone and a speaker near the rear seats. FIG. 4 is a diagram showing an example of the vehicle interior when the vehicle M is viewed from above. In addition to the microphone speakers illustrated in FIG. 3, microphones 106D and 106E and speakers 108D and 108E may be further installed in the vehicle interior.

The microphone 106D is provided, for example, in the vicinity of the left rear seat ST3 installed behind the passenger seat ST2 (for example, the rear surface of the passenger seat ST2), and mainly transmits the voice spoken by the occupant seated in the left rear seat ST3. Pick up sound. The microphone 106E is provided, for example, in the vicinity of the right rear seat ST4 installed behind the driver's seat ST1 (for example, the rear surface of the driver's seat ST1), and mainly transmits the voice spoken by the occupant seated in the right rear seat ST4. Pick up sound.

The speaker 108D is installed, for example, below the door on the left rear seat ST3 side, and the speaker 108E is installed, for example, below the door on the right rear seat ST4 side. In the following description, when the driver's seat ST1, the passenger's seat ST2, the left rear seat ST3, and the right rear seat ST4 are not distinguished from each other, they are simply referred to as seat ST.

The vehicle M illustrated in FIG. 1 has been described as being a vehicle provided with a steering wheel that can be operated by a driver who is an occupant, as illustrated in FIG. 3 or 4, but is not limited thereto. For example, vehicle M may be a vehicle without a roof, i.e., without a cabin (or without a clear division thereof). Further, in the example of FIG. 3 or 4, it is assumed that the driver's seat in which the driver who drives the vehicle M sits and the passenger's seat and the rear seat in which the occupant who does not drive the vehicle M sits are in one room. However, it is not limited to this. Further, in the example of FIG. 3 or 4, the vehicle M is described as being a vehicle provided with a steering wheel, but the present invention is not limited to this. For example, the vehicle M may be an autonomous driving vehicle that is not provided with a driving operation device such as a steering wheel. The autonomous driving vehicle is, for example, to execute driving control by controlling one or both of steering and acceleration / deceleration of the vehicle without depending on the operation of an occupant.

Returning to the description of FIG. 2, the agent-side control unit 120 includes, for example, the acquisition unit 122, the voice synthesis unit 124, the output control unit 126, the communication control unit 128, the speaker position identification unit 130, and the operation authority determination. A unit 132 and an in-vehicle device control unit 134 are provided. These components are realized, for example, by executing a program (software) by a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). In addition, some or all of these components are determined by hardware (including circuit section; circuitry) such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), and FPGA (Field-Programmable Gate Array). It may be realized, or it may be realized by the cooperation of software and hardware. The program may be stored in advance in the agent-side storage unit 150 (a storage device including a non-transient storage medium), or a removable storage medium (non-transient storage) such as a DVD or a CD-ROM. It is stored in the medium), and may be installed in the agent-side storage unit 150 by mounting the storage medium on the drive device.

The agent-side storage unit 150 is realized by an HDD, a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), a ROM (Read Only Memory), a RAM (Random Access Memory), or the like. The agent-side storage unit 150 stores, for example, a program or the like referred to by the processor, in-vehicle device information 152, and operation authority position information 154. The in-vehicle device information 152 is information indicating (a list of) in-vehicle devices VE mounted on the vehicle M.

FIG. 5 is a diagram showing an example of the contents of the operation authority position information 154. The operation authority position information 154 corresponds to, for example, the position of the occupant in the vehicle M (in this example, the seat of the occupant) and the in-vehicle device VE to which the occupant riding in the position has the operation authority for each position of the occupant. This is the attached information. In the operation authority position information 154, for example, the in-vehicle device VE (for example, audio, air conditioner, etc.) that does not affect the behavior or state of the vehicle M has the operation authority for the occupant at any position, and the behavior or state of the vehicle M The affected in-vehicle device VE (for example, window opening / closing, door lock, driving support device, turn signal, headlight, etc.) is located in the occupant near the in-vehicle device VE or in the driver's seat. It is shown that only the occupant has operational authority.

Returning to FIG. 2, the acquisition unit 122 acquires voice data from the microphone 106 and other information.

The voice synthesis unit 124 is based on the voice data instructed by utterance (that is, voice instruction) as voice control when the agent setting data received from the server device 200 by the agent side communication unit 102 includes the voice control content. , Generates artificial synthetic voice (hereinafter referred to as agent voice).

When the agent voice is generated by the voice synthesis unit 124, the output control unit 126 causes the speaker 108 to output the agent voice. Further, the output control unit 126 causes the display unit 110 to display the image data instructed as the image control when the agent setting data includes the image control contents. Further, the output control unit 126 may display an image of the recognition result of voice data (text data such as a phrase) on the display unit 110.

The communication control unit 128 transmits the voice data acquired by the acquisition unit 122 to the server device 200 via the agent-side communication unit 102.

The speaker position specifying unit 130 identifies the position of the occupant of the vehicle M who has spoken the voice picked up by the microphone 106. The speaker position specifying unit 130 uses, for example, the seat ST installed in the vicinity of the microphone 106 that picks up the voice at the loudest volume for a certain utterance among the microphones 106A to 106E as the position of the occupant who utters the voice. Identify. The speaker position specifying unit 130 sets the position of the occupant who is moving his / her mouth at the timing when the sound is picked up by the microphone 106 based on the image captured by the occupant by the in-vehicle camera (not shown). It may be specified as the position of the occupant who spoke.

For example, when the agent setting data includes information indicating control of the in-vehicle device VE, the operation authority determination unit 132 allows the occupant who gets on the position specified by the speaker position identification unit 130 to refer to the in-vehicle device VE to be instructed. Whether or not the user has the operation authority is determined based on the operation authority position information 154. First, the operation authority determination unit 132 searches for the operation authority position information 154 using the position of the occupant specified by the speaker position identification unit 130 as a search key. Then, the operation authority determination unit 132 utters when the in-vehicle device VE having the operation authority associated with the position of the specified occupant is associated with the in-vehicle device VE to be instructed shown in the agent setting data. It is determined that the occupant has the operation authority. The operation authority determination unit 132 transmits information indicating that the uttered occupant has the operation authority to the server device 200 by the agent side communication unit 102.

Further, the operation authority determination unit 132 gets on the position specified by the speaker position identification unit 130, for example, when the agent setting data includes the control content for registering a new utterance command instructing the control of the in-vehicle device VE. It is determined based on the operation authority position information 154 whether or not the occupant has the operation authority for the in-vehicle device VE to be instructed. Since the operation authority determination unit 132 determines the operation authority of the occupant in accordance with the process of registering a new utterance command, it is the same as the process of determining the operation authority of the occupant in accordance with the control of the in-vehicle device VE described above. , The description is omitted.

In the in-vehicle device control unit 134, the agent setting data includes the control content of the in-vehicle device VE, and the determination result of the operation authority determination unit 132 has the operation authority of the in-vehicle device VE to be instructed by the occupant who spoke the demonstrative word. When indicating that, the operation of the in-vehicle device VE is controlled.

[Server device configuration]
FIG. 6 is a diagram showing an example of the configuration of the server device 200 according to the first embodiment. The server device 200 according to the first embodiment includes, for example, a server-side communication unit 202, a server-side control unit 210, and a server-side storage unit 230.

The server-side communication unit 202 includes a communication interface such as a NIC. The server-side communication unit 202 communicates with the agent device 100 and the like mounted on each vehicle M via the network NW.

The server-side control unit 210 includes, for example, an acquisition unit 212, an utterance section extraction unit 214, a voice recognition unit 216, a meaning interpretation unit 218, an agent setting data generation unit 222, and a communication control unit 224. These components are realized, for example, by a processor such as a CPU or GPU executing a program (software). In addition, some or all of these components may be realized by hardware such as LSI, ASIC, FPGA (including circuit section; circuitry), or realized by collaboration between software and hardware. May be good. The program may be stored in advance in the server-side storage unit 230 (a storage device including a non-transient storage medium), or a removable storage medium (non-transient storage) such as a DVD or a CD-ROM. It is stored in the medium), and may be installed in the server-side storage unit 230 by mounting the storage medium on the drive device.

The server-side storage unit 230 is realized by an HDD, a flash memory, an EEPROM, a ROM, a RAM, or the like. In the server-side storage unit 230, for example, in addition to the program referenced by the processor, the basic utterance command dictionary 232, the user utterance command dictionary 234, and the like are stored. The basic utterance command dictionary 232 includes, for example, utterance command sentences and phrases (hereinafter, voice commands) including pre-registered voice commands, and the user utterance command dictionary 234 includes, for example, the occupant of the vehicle M. Includes utterance command sentences, phrases, etc. (hereinafter referred to as user utterance commands) registered by.

FIG. 7 is a diagram showing an example of the contents of the basic utterance command dictionary 232. In the basic utterance command dictionary 232, for example, an operation is instructed by a basic voice command, a basic voice command, and a basic voice command, which are sentences or phrases in which a command including a pre-registered voice command is uttered as standard. The vehicle-mounted device VE to be controlled and the control content to be executed by the agent-side control unit 120 are (together) associated with each other. The basic voice command includes, for example, the name of the in-vehicle device VE to be controlled and instructions / commands (what to be made) to the in-vehicle device VE to be controlled. In the control content, for example, the control of the operation of the in-vehicle device VE (what is desired to be operated) is input. For example, in the basic speech command dictionary 232, three pre-registered basics, "air conditioner ON", "air conditioner start", and "air conditioner operation", are used for the in-vehicle device control content "start the air conditioner (turn on the air conditioner)". Voice commands are associated.

FIG. 8 is a diagram showing an example of the contents of the user utterance command dictionary 234. In the user utterance command dictionary 234, for example, the user utterance command registered by the occupant, the in-vehicle device VE whose operation is instructed by the user utterance command, and the control content to be executed by the agent side control unit 120 are mutually present. (Both) are associated. The user utterance command includes, for example, a word indicating an instruction to the in-vehicle device VE (for example, a pronoun "that do" indicating an instruction). In the control content, for example, regarding the operation control (what is desired to be operated) for the in-vehicle device VE, the control including the name of the in-vehicle device VE is registered. For example, in the user utterance command dictionary 234, in response to the in-vehicle device control of "opening the driver's seat window (vehicle-mounted device VE) by 20%" and the user-spoken command of "usually doing", "in the driver's seat window". The in-vehicle device control content of "opening the driver's seat window by 20% with the elevating device (in-vehicle device VE)" is associated with it.

In the basic utterance command dictionary 232 and the user utterance command dictionary 234, the control contents include in-vehicle device control, voice control in which the output control unit 126 outputs voice to the speaker 108, and the output control unit 126 in the display unit 110. May include display control for displaying an image.

Returning to FIG. 6, the acquisition unit 212 acquires voice data from the agent device 100 via the server-side communication unit 202.

The utterance section extraction unit 214 extracts the period during which the occupant is speaking (hereinafter, referred to as the utterance section) from the voice data acquired by the acquisition unit 122. For example, the utterance section extraction unit 214 may extract the utterance section based on the amplitude of the voice signal included in the voice data by using the zero intersection method. Further, the utterance section extraction unit 214 may extract the utterance section from the voice data based on the Gaussian mixture model (GMM), or a database and a template in which the voice signal peculiar to the utterance section is templated. The utterance section may be extracted from the voice data by performing the matching process.

The voice recognition unit 216 recognizes voice data for each utterance section extracted by the utterance section extraction unit 214, and converts the recognized voice data into text to generate text data including the utterance content. For example, the voice recognition unit 216 divides the voice signal in the utterance section into a plurality of frequency bands such as low frequency and high frequency, and Fourier transforms each classified voice signal to generate a spectrogram. The voice recognition unit 216 obtains a character string from the spectrogram by inputting the generated spectrogram into the recursive neural network. The recursive neural network learns in advance by using, for example, teacher data in which a known character string corresponding to the learning voice is associated with a teacher label for a spectrogram generated from the learning voice. May be done. Then, the voice recognition unit 216 outputs the data of the character string obtained from the recursive neural network as text data.

The semantic interpretation unit 218 performs syntactic analysis of the natural language text data based on the text data recognized by the speech recognition unit 216, divides the text data into morphemes, and means the words included in the text data from each morpheme. To interpret. The meaning interpretation unit 218 uses, for example, the basic utterance command dictionary 232 and the user utterance command dictionary 234 stored in the server-side storage unit 230, and the meaning of the text data recognized by the voice recognition unit 216 is the meaning of the in-vehicle device VE. Interpret that you are instructing control. Specifically, from the recognized text data (utterance content), at least the name of the vehicle-mounted device VE as the instruction control target and the vehicle-mounted device control content are grasped.

The agent setting data generation unit 222 interpreted that the utterance content whose meaning was interpreted by the meaning interpretation unit 218 indicates control of the in-vehicle device VE (basic voice command or user utterance command is included in the utterance content. When it is recognized that the utterance command is used, the basic utterance command dictionary 232 and the user utterance command dictionary 234 are referred to, and the matching basic voice command or the control content associated with the user utterance command is acquired. The agent setting data generation unit 222 generates agent setting data for executing a process corresponding to the acquired control content (for example, at least one of in-vehicle device control, voice control, or display control). When the meanings of "ON air conditioner", "air conditioner operation", etc. are interpreted as the interpretation result, the agent setting data generation unit 222 uses the above meanings as standard character information "start the air conditioner" or standard command information. Replace with "TURN AC ON" or the like. As a result, even if there is a character fluctuation in the request for the utterance content, it is possible to easily acquire the control content that meets the request.

The communication control unit 224 transmits the agent setting data generated by the agent setting data generation unit 222 to the vehicle M via the server-side communication unit 202. As a result, the vehicle M is controlled by the agent-side control unit 120 in response to the agent setting data.

[Registration of new utterance commands in the user utterance command dictionary 234]
Further, the meaning interpretation unit 218 interprets that the meaning of the text data recognized by the voice recognition unit 216 includes an instruction to register a new utterance command. The "instruction to register a new utterance command" is indicated by, for example, a word including at least the new utterance command itself and the instruction to the in-vehicle device VE instructed by the new utterance command. For example, "the driver's seat window". Register to open (in-vehicle device VE) 20% with "Usually do". ] Etc. In this case, the name of the in-vehicle device VE is "driver's seat window", and "usually doing" is a new utterance command in this example. When the agent setting data generation unit 222 is interpreted by the semantic interpretation unit 218 to include an instruction to register a new utterance command, the interpreted new utterance command and the in-vehicle device VE to be controlled by the new utterance command. The agent setting data including the information indicating the above (for example, the name of the in-vehicle device VE) and the control content for registering a new utterance command is generated, and transmitted to the agent device 100 by the server-side communication unit 202.

As described above, when the operation authority determination unit 132 receives the agent setting data including the control content for registering a new utterance command, the operation authority determination unit 132 registers a new utterance command for the in-vehicle device VE to be controlled by the user utterance command. It is determined whether or not the instructed occupant has the operation authority, and information indicating the determination result is transmitted to the server device 200 by the agent-side communication unit 102.

When the information received by the server-side communication unit 202 indicates that the occupant who has spoken has the operation authority of the in-vehicle device VE, the semantic interpretation unit 218 is instructed by the interpreted new utterance command and the new utterance command. It is registered in the user utterance command dictionary 234 in association with the control content of the in-vehicle device VE.

[Exception to registration of new utterance command]
The semantic interpretation unit 218 searches the basic utterance command dictionary 232 using the new utterance command as a search key, and when the new utterance command is already registered as the basic voice command to be registered in advance, the new utterance is made. The process of registering the command in the user utterance command dictionary 234 is not executed. In this case, the semantic interpretation unit 218 does not cause the agent setting data generation unit 222 to generate the agent setting data related to the process of registering a new utterance command.

[Register user utterance command for the previous operation]
Further, the meaning interpretation unit 218 gives an instruction that the meaning of the text data recognized by the voice recognition unit 216 registers the instruction (or control) that the occupant has given to the in-vehicle device VE immediately before as a new utterance command. Interpret to include. "Instruction to register the instruction given immediately before as a new utterance command" is, for example, a word including the new utterance command itself. For example, "Register the control that has just been performed with" usual do ". .. ] Etc. The control just performed is a control performed on the in-vehicle device VE in response to an instruction given immediately before by the occupant, a control performed on the in-vehicle device VE by the occupant himself / herself, and the like. When the agent setting data generation unit 222 interprets that the instruction given immediately before by the semantic interpretation unit 218 includes an instruction for registering a new utterance command, the interpreted new utterance command and the instruction given immediately before are interpreted. The agent setting data including the control content for registering a new utterance command is generated, and is transmitted to the agent device 100 by the server-side communication unit 202.

In this case, the operation authority determination unit 132 receives the agent setting data including the control content for registering a new utterance command for the instruction given immediately before, and displays the history of the control performed on the in-vehicle device VE. Based on this, the vehicle-mounted device VE to be controlled in the control content performed immediately before is specified. The history information is stored (stored) in, for example, the agent side storage unit 150. The operation authority determination unit 132 determines whether or not the occupant who has instructed to register a new utterance command has the operation authority for the specified in-vehicle device VE, and the information indicating the determination result and the control content performed immediately before Information indicating that is transmitted to the server device 200 by the agent-side communication unit 102.

When the determination result based on the information received by the server-side communication unit 202 indicates that the uttered occupant has the operation authority of the in-vehicle device VE, the semantic interpretation unit 218 interprets the new utterance command and immediately before receiving it. It is registered in the user utterance command dictionary 234 in association with the control content performed in.

[Processing flow]
Next, the processing flow of the agent system 1 according to the first embodiment will be described with reference to a flowchart. In the following, the processing of the agent device 100 and the processing of the server device 200 will be described separately. Further, the processing flow shown below may be repeatedly executed at a predetermined timing. The predetermined timing is, for example, the timing at which a specific word (for example, a wakeup word) for activating the agent device is extracted from the voice data, or a switch for activating the agent device 100 among various switches mounted on the vehicle M. It is the timing when the selection of is accepted.

FIG. 9 is a flowchart showing a series of processing flows of the agent device 100 according to the first embodiment. First, the acquisition unit 122 of the agent-side control unit 120 determines whether or not the voice data of the occupant has been collected by the microphone 106 (step S100). The acquisition unit 122 waits until the voice data of the occupant is collected. Next, the communication control unit 128 transmits voice data to the server device 200 via the agent-side communication unit 102 (step S102).

Next, the communication control unit 128 receives the agent setting data from the server device 200 (step S104). Next, the operation authority determination unit 132 identifies the in-vehicle device VE included in the received agent setting data (step S106). The speaker position specifying unit 130 identifies the position of the occupant who uttered the voice collected in step S100 (step S108). The operation authority determination unit 132 determines whether or not the received agent setting data includes the control content for registering a new utterance command instructing the control of the vehicle-mounted device VE (step S110). When the agent setting data does not include the control content for registering a new utterance command, the operation authority determination unit 132 includes other instructions (for example, voice control, display control, in-vehicle device control, etc.). The process proceeds to step S118.

When the agent setting data includes the control content for registering a new utterance command, the operation authority determination unit 132 determines the position of the specified in-vehicle device VE based on the operation authority position information 154 by the speaker position identification unit 130. It is determined whether or not the specified occupant has the operation authority (step S112). When the operation authority determination unit 132 determines that the occupant does not have the operation authority of the in-vehicle device VE, the agent-side communication unit 102 provides the server device 200 with information indicating that the occupant does not have the operation authority of the in-vehicle device VE. Transmit (step S114). When the operation authority determination unit 132 determines that the occupant has the operation authority of the in-vehicle device VE, the agent-side communication unit 102 transmits information indicating that the occupant has the operation authority of the in-vehicle device VE to the server device 200 ( Step S116).

When the agent setting data includes the control content for the in-vehicle device VE, the operation authority determination unit 132 specifies the position of the specified in-vehicle device VE by the speaker position identification unit 130 based on the operation authority position information 154. It is determined whether or not the occupant has the operation authority (step S118). When the in-vehicle device control unit 134 determines that the occupant does not have the operation authority of the in-vehicle device VE by the operation authority determination unit 132, the in-vehicle device control unit 134 does not execute the control for the in-vehicle device VE and ends the process (step S120). When the in-vehicle device control unit 134 determines that the occupant has the operation authority of the in-vehicle device VE by the operation authority determination unit 132, the in-vehicle device control unit 134 executes control for the in-vehicle device VE based on the control content included in the agent setting data (step). S122). As a result, the processing of this flowchart ends.

FIG. 10 is a flowchart showing a processing flow of an example of the server device 200 according to the first embodiment. First, the server-side communication unit 202 acquires voice data, first image data, and second image data from the agent device 100 (step S200). Next, the utterance section extraction unit 214 extracts the utterance section included in the voice data (step S202). Next, the voice recognition unit 216 performs voice recognition of the voice data in the extracted utterance section (step S203). Next, the meaning interpretation unit 218 interprets the meaning of the voice data in the extracted utterance section (step S204). The meaning interpretation unit 218 determines whether or not the meaning of the interpreted voice indicates an instruction to register a new utterance command (step S206). The agent setting data generation unit 222 determines that the meaning of the voice interpreted by the meaning interpretation unit 218 does not indicate an instruction to register a new utterance command (that is, indicates voice control, display control, or in-vehicle device control). If so, agent setting data based on the meaning of the entire utterance content is generated (step S208). The communication control unit 224 of the server side control unit 210 transmits the agent setting data to the agent device 100 via the server side communication unit 202 (step S210).

When the agent setting data generation unit 222 determines that the meaning of the voice interpreted by the meaning interpretation unit 218 indicates an instruction to register a new utterance command, the interpreted new utterance command and the new utterance command are used. Agent setting data including information indicating the vehicle-mounted device VE to be controlled, control contents for registering a new utterance command, and agent setting data is generated (step S212). The communication control unit 224 of the server side control unit 210 transmits the agent setting data to the agent device 100 via the server side communication unit 202 (step S214). In the semantic interpretation unit 218, the occupant has the authority to operate the in-vehicle device VE with the information generated / transmitted in the above-mentioned steps S114 and S116 as the agent setting data is transmitted by the server device 200 in step S214. It is determined whether or not to indicate that (step S216).

If the received information does not indicate that the occupant has the operation authority of the in-vehicle device VE, the semantic interpretation unit 218 does not register a new utterance command in the user utterance command dictionary 234 and ends the process. When the received information indicates that the occupant has the operation authority of the in-vehicle device VE, the semantic interpretation unit 218 determines whether or not the interpreted new utterance command is included in the basic utterance command dictionary 232 (step S218). ). When the new utterance command is included in the basic utterance command dictionary 232, the semantic interpretation unit 218 ends the process because the new utterance command cannot be registered as the user utterance command. When the semantic interpretation unit 218 determines that the occupant has the operation authority of the in-vehicle device VE and the new utterance command is not included in the basic utterance command dictionary 232, the new utterance command and the new utterance command are used. It is registered in the user utterance command dictionary 234 in association with the control content of the in-vehicle device VE instructed (step S220). As a result, the processing of this flowchart ends.

According to the agent system 1 of the first embodiment described above, the vehicle-mounted device VE can be controlled by the voice desired by the occupant, and the vehicle-mounted device VE can be operated more easily by the occupant. ..

<Second Embodiment>
In the above-described first embodiment, the agent device 100 mounted on the vehicle M and the server device 200 have been described as different devices from each other, but the present invention is not limited thereto. For example, the component of the server device 200 related to the agent function may be included in the component of the agent device 100. In this case, the server device 200 may function as a virtual machine virtually realized by the agent side control unit 120 of the agent device 100. Hereinafter, the agent device 100A including the components of the server device 200 will be described as the second embodiment. In this case, the agent device 100A is an example of the "agent system". In the second embodiment, the same components as those in the first embodiment described above are designated by the same reference numerals, and specific description thereof will be omitted here.

FIG. 11 is a diagram showing an example of the agent device 100A according to the second embodiment. The agent device 100A includes, for example, an agent-side communication unit 102, a microphone 106, a speaker 108, a display unit 110, an agent-side control unit 120A, and an agent-side storage unit 150A. The agent-side control unit 120A includes, for example, an acquisition unit 122, a voice synthesis unit 124, an output control unit 126, a communication control unit 128, a speaker position identification unit 130, an operation authority determination unit 132, and an in-vehicle device control. It includes a unit 134, an acquisition unit 212A, an utterance section extraction unit 214A, a voice recognition unit 216A, a semantic interpretation unit 218A, and an agent setting data generation unit 222A.

Further, the agent-side storage unit 150A stores, for example, in-vehicle device information 152, operation authority position information 154, basic utterance command dictionary 232A, user utterance command dictionary 234A, and the like, in addition to the program referenced by the processor. The basic utterance command dictionary 232A may be updated with the latest information acquired from the server device 200.

[Processing flow]
12 and 13 are flowcharts showing a series of processing flows of the agent device 100A according to the second embodiment. Further, the processing flow shown below may be repeatedly executed at a predetermined timing in the same manner as the processing flow in the first embodiment. First, the acquisition unit 122 of the agent-side control unit 120 determines whether or not the voice data of the occupant has been collected by the microphone 106 (step S300). Next, the utterance section extraction unit 214 extracts the utterance section included in the voice data (step S302). Next, the meaning interpretation unit 218 interprets the meaning of the voice data in the extracted utterance section (step S304).

The meaning interpretation unit 218 determines whether or not the meaning of the interpreted voice indicates an instruction to register a new utterance command (step S306). The agent setting data generation unit 222 determines that the meaning of the voice interpreted by the meaning interpretation unit 218 does not indicate an instruction to register a new utterance command (that is, indicates voice control, display control, or in-vehicle device control). If so, agent setting data based on the meaning of the entire utterance content is generated (step S308). When the agent setting data generation unit 222 determines that the meaning of the voice interpreted by the meaning interpretation unit 218 indicates an instruction to register a new utterance command, the interpreted new utterance command and the new utterance command are used. Agent setting data including information indicating the vehicle-mounted device VE to be controlled, control contents for registering a new utterance command, and agent setting data is generated (step S310). The operation authority determination unit 132 identifies the in-vehicle device VE included in the agent setting data generated in step S208 or step S212 (step S312). The speaker position specifying unit 130 identifies the position of the occupant who uttered the voice collected in step S100 (step S314).

The operation authority determination unit 132 determines whether or not the agent setting data includes the control content for registering a new utterance command instructing the control of the vehicle-mounted device VE (step S316). When the operation authority determination unit 132 does not include the control content for registering the user utterance command in the agent setting data and includes the control content for the in-vehicle device VE, the operation authority determination unit 132 regards the specified in-vehicle device VE based on the operation authority position information 154. It is determined whether or not the occupant whose position is specified by the speaker position specifying unit 130 has the operation authority (step S318). When the in-vehicle device control unit 134 determines that the occupant does not have the operation authority of the in-vehicle device VE by the operation authority determination unit 132, the in-vehicle device control unit 134 does not execute the control for the in-vehicle device VE and ends the process (step S320). When the in-vehicle device control unit 134 determines that the occupant has the operation authority of the in-vehicle device VE by the operation authority determination unit 132, the in-vehicle device control unit 134 executes control for the in-vehicle device VE based on the control content included in the agent setting data (step). S322).

When the agent setting data includes the control content for registering a new utterance command, the operation authority determination unit 132 determines the position of the specified in-vehicle device VE based on the operation authority position information 154 by the speaker position identification unit 130. It is determined whether or not the identified occupant has the operation authority (step S324). When the operation authority determination unit 132 determines that the occupant does not have the operation authority of the in-vehicle device VE, the semantic interpretation unit 218 does not register a new utterance command in the user utterance command dictionary 234 and ends the process. When the operation authority determination unit 132 determines that the occupant has the operation authority of the in-vehicle device VE, the semantic interpretation unit 218 determines whether or not the interpreted new utterance command is included in the basic utterance command dictionary 232 ( Step S326). When the new utterance command is included in the basic utterance command dictionary 232, the semantic interpretation unit 218 ends the process because the new utterance command cannot be registered as the user utterance command. When the semantic interpretation unit 218 determines that the occupant has the operation authority of the in-vehicle device VE and the new utterance command is not included in the basic utterance command dictionary 232, the new utterance command and the new utterance command are used. It is registered in the user utterance command dictionary 234 in association with the control content of the in-vehicle device VE instructed (step S328).

According to the agent device 100A of the second embodiment described above, the same effect as that of the first embodiment is obtained, and each time a voice from an occupant is acquired, the agent device 200 communicates with the server device 200 via the network NW. Since it is not necessary, the content of the utterance can be recognized more quickly. Further, even when the vehicle M cannot communicate with the server device 200, the vehicle-mounted device VE can be controlled by the voice desired by the occupant so that the occupant can operate the vehicle-mounted device VE more easily. Can be done.

Although the embodiments for carrying out the present invention have been described above using the embodiments, the present invention is not limited to these embodiments, and various modifications and substitutions are made without departing from the gist of the present invention. Can be added.

For example, in the above-described embodiment, the moving body is described as a vehicle as an example, but the present invention is not limited to this. For example, the moving body may be another moving body such as a ship or a flying object. In this case, for example, the agent device 100 may be arranged in the cabins of a plurality of pleasure boats or a plurality of pleasure airplanes. Further, if the moving body has a helmsman who operates the moving body, the agent device 100 can serve the customer by performing a voice dialogue with another occupant (passenger) who does not perform the driving operation. The cabin attendant can focus on other services to the passengers. Further, the agent device 100 may be arranged in a taxi, a bus, or the like. In this case, since the agent device 100 can serve passengers by having a voice dialogue with the passengers, the drivers of those vehicles can focus on the driving operation.

1 ... Agent system, 100 ... Agent device, 100A ... Agent device, 102 ... Agent side communication unit, 106, 106, 106A, 106B, 106C, 106D, 106E ... Mike, 108, 108A, 108B, 108C, 108D, 108E ... Speaker, 110, 110A, 110B, 110C ... Display unit, 120, 120A ... Agent side control unit, 122 ... Acquisition unit, 124 ... Voice synthesis unit, 126 ... Output control unit, 128 ... Communication control unit, 130 ... Speaker position Specific unit, 132 ... Operation authority determination unit, 134 ... In-vehicle device control unit, 150, 150A ... Agent side storage unit, 152 ... In-vehicle device information, 154 ... Operation authority position information, 200 ... Server device, 202 ... Server side communication unit , 210 ... Server-side control unit, 212, 212A ... Acquisition unit, 214, 214A ... Speech section extraction unit, 216, 216A ... Speech recognition unit, 218, 218A ... Semantic interpretation unit, 222, 222A ... Agent setting data generation unit, 224 ... Communication control unit, 230 ... Server side storage unit, 232, 232A ... Basic utterance command dictionary, 234, 234A ... User utterance command dictionary, M ... Vehicle, VE ... In-vehicle device

Claims (13)

The mobile body-mounted equipment mounted on the mobile body on which the occupants board,
A voice recognition unit that recognizes a voice including a utterance command, which is a command for controlling the mobile body-mounted device and is a voice of the occupant picked up by a microphone.
A meaning interpreting unit for interpreting the meaning of the voice recognized by the voice recognition unit is provided.
When the meaning of the voice is interpreted to include an instruction to register a new utterance command, the meaning interpreting unit registers the new utterance command in the storage unit.
Agent system. When the meaning interpreting unit interprets that the meaning of the voice includes an instruction to delete the registered utterance command, the meaning interpreting unit deletes the utterance command from the storage unit.
The agent system according to claim 1. The storage unit in which the utterance command is registered is provided.
The utterance command dictionary in which the utterance command and the content of the control indicated by the utterance command are associated with each other and registered is stored in the storage unit.
The agent system according to claim 1 or 2. An on-board device control unit that controls the mobile on-board device based on the meaning of the voice interpreted by the meaning interpreting unit from the voice recognized by the voice recognition unit using the utterance command dictionary is further provided.
The agent system according to claim 3. The semantic interpretation unit interprets the voice recognized by the voice recognition unit as including an instruction to register a new utterance command, and is a basic voice which is a basic control command of the mobile device. If the new utterance command is not included in the basic utterance command dictionary, it is registered in the utterance command dictionary based on the basic utterance command dictionary in which the command and the content of control for the basic voice command are associated with each other. To do,
The agent system according to claim 3. When the semantic interpretation unit interprets the voice recognized by the voice recognition unit as including an instruction to register a new utterance command related to a control instruction to the mobile-mounted device immediately before the occupant. The new utterance command is registered in the utterance command dictionary together with the content of the control performed by the occupant of the mobile body on the mobile body-mounted device immediately before.
The agent system according to claim 3 or 5. Among the occupants of the moving body, a speaker position specifying unit for specifying the position of the speaker of the voice including the utterance command picked up by the microphone, and
The position information of the speaker specified by the speaker position specifying unit, the operation authority position information indicating the position of an occupant having the operation authority for the moving body-mounted device mounted on the moving body, and the meaning interpreting unit. Based on the interpreted meaning of the utterance command and the mobile-mounted device information, it is determined whether or not the speaker of the voice including the utterance command has the operation authority of the mobile-mounted device. Further equipped with an operation authority judgment unit
When the semantic interpretation unit interprets the voice recognized by the voice recognition unit as including an instruction to register a new utterance command, the speaker of the voice including the utterance command by the operation authority determination unit. However, when it is determined that the mobile body-mounted device has the operation authority, the new utterance command is registered in the utterance command dictionary together with the control content indicated by the new utterance command.
The agent system according to any one of claims 3 to 6. Among the occupants of the moving body, a speaker position specifying unit for specifying the position of the speaker of the voice including the utterance command picked up by the microphone, and
The position information of the speaker specified by the speaker position specifying unit, the operation authority position information indicating the position of an occupant having the operation authority for the moving body-mounted device mounted on the moving body, and the meaning interpreting unit. Based on the interpreted meaning of the utterance command and the mobile-mounted device information, it is determined whether or not the speaker of the voice including the utterance command has the operation authority of the mobile-mounted device. Further equipped with an operation authority judgment unit
The on-board device control unit recognizes that the meaning of the voice indicates control of the mobile body-mounted device by the meaning interpretation unit, and the operation authority determination unit includes the utterance command. When it is determined that the speaker has the operating authority of the mobile body-mounted device, the mobile body-mounted device is controlled.
The agent system according to claim 4. An acquisition unit that acquires a voice including a utterance command, which is a command for controlling a mobile body-mounted device mounted on the moving body and is a voice of an occupant on the moving body.
A storage unit that stores an utterance command dictionary in which the utterance command and the content of control including information on the mobile body-mounted device to be controlled indicated by the utterance command are associated with each other.
A voice recognition unit that recognizes the voice and
A meaning interpretation unit that interprets the meaning of the voice recognized by the voice recognition unit,
A generation unit that generates information corresponding to the meaning content of the voice interpreted by the meaning interpretation unit, and a generation unit.
Information processing device equipped with. An on-board device control unit that controls the mobile body-mounted device is further provided based on the information corresponding to the meaning and content of the voice generated by the generation unit.
The information processing device according to claim 9. A single or multiple computers in a system including a storage unit that stores an utterance command dictionary in which an utterance command and a control content including information on a mobile device to be controlled indicated by the utterance command are associated with each other. ,
The step of recognizing the voice including the utterance command spoken by the occupant on the moving body, and
Steps to interpret the meaning of the recognized speech,
With reference to the utterance command dictionary, a step of acquiring information on the mobile device to be controlled and the content of control, and
Steps to control mobile-mounted equipment to be controlled, based on the interpreted audio meaning,
When it is interpreted that the recognized voice includes an instruction to register a new utterance command, the step of registering the new utterance command in the utterance command dictionary together with the control content indicated by the new utterance command. ,
Mobile body-mounted device control method having. After the step of interpreting the meaning of the speech
When the speech command dictionary has a control content corresponding to the voice meaning with respect to the voice meaning, the interpretation content of the voice meaning generated by the step of interpreting the voice meaning is displayed. Further having a step of referring to the speech command dictionary and replacing it with the content of standard character information control.
The mobile body-mounted device control method according to claim 11. A single or multiple computers in a system having a storage unit that stores an utterance command dictionary in which an utterance command and a control content including information on a mobile device to be controlled indicated by the utterance command are associated with each other. Installed and
The process of recognizing the voice including the utterance command spoken by the occupant on the moving object, and
The process of interpreting the meaning of the recognized voice,
With reference to the utterance command dictionary, a process of acquiring information on the mobile body-mounted device to be controlled and the content of control, and
The process of controlling the mobile-mounted device to be controlled based on the meaning of the interpreted voice,
When it is interpreted that the recognized voice includes an instruction to register a new utterance command, the process of registering the new utterance command in the utterance command dictionary together with the control content indicated by the new utterance command. ,
A program to be executed by the computer including.

Images