JP6969094B2 - Voice guidance method and voice guidance device - Google Patents

Description

The present invention relates to a voice guidance method and a voice guidance device.

Patent Document 1 discloses an agent device in which an anthropomorphic agent is made to appear in a vehicle by images and sounds, and the agent and the driver communicate with each other. The agent device switches the voice (sound quality) constituting the conversation when communicating by using the voice output form determination table based on the vehicle state, the user's preference regarding the agent, and the like.

Japanese Unexamined Patent Publication No. 11-259271

Crew sensations and preferences are not fixed and vary from situation to situation. However, it is difficult to anticipate all possible situations in advance and provide voice guidance suitable for the occupant so as to cover all of them, and there is a risk that smooth communication with the occupant may not be possible.
An object of the present invention is to provide voice guidance capable of smooth communication with an occupant under various situations.

In the voice guidance method according to one aspect of the present invention, it is determined whether or not the occupant's discomfort with respect to the voice guidance is detected. And do.

According to one aspect of the present invention, it is possible to provide voice guidance capable of smooth communication with an occupant under various situations.

It is a figure which shows the schematic configuration example of the vehicle which comprises the guidance device which concerns on embodiment. It is explanatory drawing of an example of the electroencephalogram measurement. It is a block diagram which shows an example of the functional structure of the controller shown in FIG. It is explanatory drawing of an example of an electroencephalogram feature vector. It is explanatory drawing of an example of a feature space map. It is a flowchart of an example of the voice guidance method which concerns on 1st Embodiment. It is a flowchart of an example of the detection mode determination process shown in FIG. It is a flowchart of an example of the presentation method change process shown in FIG. It is a flowchart of an example of the wording change processing shown in FIG. It is a flowchart of an example of the content change process shown in FIG. It is a flowchart of an example of the voice guidance method which concerns on 2nd Embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. It should be noted that the embodiments of the present invention shown below exemplify devices and methods for embodying the technical idea of the present invention, and the technical idea of the present invention describes the materials, shapes, and shapes of constituent parts. The structure, arrangement, etc. are not specified to the following. The technical idea of the present invention may be modified in various ways within the technical scope specified by the claims described in the claims.

(First Embodiment)
(composition)
See FIG. The vehicle 1 includes a guidance device 10 which is a voice guidance device according to one aspect of the present invention, a GPS (Global Positioning System) receiver 20, a map database 21, a beacon receiver 22, and a communication device 23. Further, the vehicle 1 includes a vehicle traveling controller 40, a driving operation sensor group 41, a vehicle control actuator 42, and a vehicle speed sensor 43. The database is referred to as "DB" in the attached drawings.

The guidance device 10 is a navigation device that performs voice guidance and display of route search, route guidance, road information, and other information.
The guidance device 10 is based on the destination input by the occupant such as the driver, the current position of the vehicle 1 acquired by using the GPS receiver 20, and the map data stored in the map database 21. The travel route of the vehicle 1 from the vehicle to the destination is searched for and displayed on the display device 14.

Further, the guidance device 10 guides the occupant to the destination by voice guidance based on the searched travel route. The guidance device 10 provides voice route guidance such as "Go straight for a while", "Turn left at the intersection 50m ahead", "Turn left at the next intersection", "Turn left soon", "Around the destination", etc. To present. The guidance device 10 may present voice guidance that calls attention to the occupants, for example, traffic guidance such as "there is a curve ahead" or "there is a railroad crossing ahead".

Further, the guidance device 10 has the current position of the vehicle 1 acquired by using the GPS receiver 20 and the road traffic information acquired by using the beacon receiver 22 (for example, VICS (registered trademark) (Vehicle Information and Communication) information). And, based on the map data stored in the map database 21, road information such as the type of road on which the vehicle travels, the state of occurrence of traffic congestion, regulation information, and parking lot information is acquired.

The guidance device 10 displays the acquired road information on the display device 14 and presents it to the occupant by voice guidance. The guidance device 10 presents voice traffic guidance such as "about 10 km ahead, traffic jam" and "about 5 km ahead, traffic closure". When the emergency information or the caution / warning information is received, the guidance device 10 presents voice guidance such as "received emergency information" or "received caution / warning information".

Further, the guidance device 10 communicates with a data server outside the vehicle 1 via a network such as the Internet or a communication line network, acquires weather information, displays the acquired weather information on the display device 14, and provides voice guidance. Present to the occupants. The communication device 23 connects the guidance device 10 to a network such as the Internet or a communication line network.
The guidance device 10 is, for example, "Weather information is provided here. Today's weather is sunny. Tomorrow's weather is expected to be cloudy. On weekends, it is expected to rain from Saturday to Sunday." Present voice guidance.
Further, the guidance device 10 communicates with a data server outside the vehicle 1 via a network such as the Internet or a communication line network, and acquires POI (Point Of Interest) information regarding a specific point, facility, or area. The POI information may be, for example, information on a building, equipment, a store, a company, an office, a public facility, an entertainment facility, an outdoor facility, a point such as a tourist spot or a scenic spot, a feature, or an area.

The vehicle travel controller 40 is an electronic control unit that controls the travel of the vehicle according to the driving operation of the occupant detected by the driving operation sensor group 41. The vehicle travel controller 40 includes a processor and peripheral parts such as a storage device. The processor may be, for example, a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit).
The storage device may include any of a semiconductor storage device, a magnetic storage device, and an optical storage device. The storage device may include a memory such as a register, a cache memory, a ROM (Read Only Memory) and a RAM (Random Access Memory) used as the main storage device.
The vehicle traveling controller 40 may be realized by a functional logic circuit set in a general-purpose semiconductor integrated circuit. For example, the vehicle travel controller 40 may have a programmable logic device (PLD: Programmable Logic Device) such as a field-programmable gate array (FPGA).

The operation sensor group 41 includes an accelerator opening sensor 44, a brake switch 45, and a steering operation amount sensor 46.
The accelerator opening sensor 44 detects the accelerator opening of the vehicle 1 as a driving operation, and outputs a signal indicating the accelerator opening to the vehicle traveling controller 40. For example, the accelerator opening sensor 44 detects the amount of depression of the accelerator pedal of the vehicle 1 as the accelerator opening.
The brake switch 45 detects the operating state of the vehicle braking operation by the occupant as a driving operation, and outputs a signal indicating the operating state to the vehicle traveling controller 40. For example, the brake switch 45 outputs an on state signal when the occupant depresses the brake pedal, and outputs an off state signal when the occupant releases the brake pedal.
The brake switch 45 may detect, for example, the amount of depression of the brake pedal of the vehicle 1 as the operating state of the brake operation, and output a signal indicating the amount of depression to the vehicle traveling controller 40.

The steering operation amount sensor 46 detects the operation amount of the steering wheel of the vehicle 1 as a driving operation, and outputs a signal indicating the detected operation amount to the vehicle traveling controller 40. The steering operation amount sensor 46 is provided on the steering shaft or the like. The steering operation amount sensor 46 may detect the steering angle of the steering wheel as information on the operation amount of the steering wheel.
Signals indicating the accelerator opening, the operating state of the brake operation, and the operating amount of the steering wheel, which are output from the driving operation sensor group 41, may be collectively referred to as "vehicle signal".

The vehicle travel controller 40 controls the travel of the vehicle 1 by driving the vehicle control actuator based on the vehicle signal. The vehicle control actuator may include, for example, a steering actuator, an accelerator opening actuator, and a brake control actuator.
The steering actuator controls the steering direction and steering amount of the steering of the vehicle 1. The accelerator opening actuator controls the accelerator opening of the vehicle 1. The brake control actuator controls the braking operation of the brake device of the vehicle 1.
The vehicle speed sensor 43 detects the wheel speed of the vehicle 1 and calculates the speed of the vehicle 1 based on the wheel speed. The vehicle speed sensor 43 outputs a vehicle speed signal indicating the calculated vehicle speed to the vehicle travel controller 40.

(Structure of guidance device 10)
Subsequently, a configuration example of the guide device 10 will be described. The guidance device 10 includes a controller 11, an electroencephalogram sensor 12, a speaker 13, a display device 14, and a microphone 15.
The controller 11 is an electronic control unit that performs voice guidance and display of route search, route guidance, road information, and other information. The controller 11 includes a processor 50 and peripheral parts such as a storage device 51. The processor 50 may be, for example, a CPU or an MPU.

The storage device 51 may include any of a semiconductor storage device, a magnetic storage device, and an optical storage device. The storage device 51 may include a memory such as a register, a cache memory, a ROM and a RAM used as a main storage device.
The controller 11 may be realized by a functional logic circuit set in a general-purpose semiconductor integrated circuit. For example, the controller 11 may have a programmable logic device such as a field programmable gate array.

The storage device 51 stores a computer program executed on the processor 50 to cause the controller 11 to perform processing such as route search, route guidance, road information, and voice guidance and display of other information.
Further, the storage device 51 stores the discomfort database 52 and the guidance database 53.
The discomfort database 52 stores brain wave patterns used to detect discomfort of the occupant.
The guidance database 53 stores a voice waveform dictionary in which voice waveform data used for voice guidance processing by the guidance device 10 is registered.

The electroencephalogram sensor 12 is a sensor that detects an electroencephalogram of an occupant as a physiological index of the occupant. The electroencephalogram sensor 12 outputs the detected information about the occupant's electroencephalogram to the controller 11. The controller 11 receives the information of the brain wave detected by the brain wave sensor 12. The controller 11 detects the occupant's discomfort based on the brain waves detected by the brain wave sensor 12.

See FIG. The electroencephalogram sensor 12 measures the electroencephalogram signal of the occupant in real time while driving the vehicle. The electroencephalogram sensor 12 has a plurality of electrodes, and the plurality of electrodes are attached to the head of the occupant. The plurality of electrodes of the electroencephalogram sensor 12 conform to, for example, international 10-20 law, and are arranged on the crown Fz, Fcz, Cz, CPz of the occupant involved in cognitive function. The method of attaching the plurality of electrodes of the electroencephalogram sensor 12 to the head is not particularly limited, but for example, it may be configured with a wearable electrode cap so as to be easily placed on the head of the occupant.

See FIG. The controller 11 collates the current occupant's brain wave pattern measured in real time with the pre-measured brain wave pattern stored in the discomfort database 52, so that the current occupant feels discomfort (the occupant feels discomfort). Whether or not) is determined.
The microphone 15 converts the voice in the vehicle interior including the voice generated by the occupant into an electric voice signal and outputs it to the controller 11. The microphone 15 is used to collect the response voice of the occupant interacting with the guidance device 10 in the voice guidance by the guidance device 10.

An example of the functional configuration of the controller 11 is shown in FIG. The controller 11 realizes the functions of the discomfort detection unit 60, the voice guidance adjustment unit 61, and the voice recognition unit 62. For example, the controller 11 may realize the functions of the discomfort detection unit 60, the voice guidance adjustment unit 61, and the voice recognition unit 62 by executing the computer program stored in the storage device 51 by the processor 50.

In the discomfort database 52, for example, each feature vector P of the electroencephalogram potential of the occupant when an event that causes the occupant to feel discomfort and the potential of the brain wave when the event that causes the occupant to feel discomfort is generated is stored in the discomfort database 52. , The feature space map plotted in the feature space may be stored.
For the feature vector P, for example, as shown in FIG. 4, N feature quantities p1, p2, ..., PN are extracted from the electroencephalogram signal at a predetermined time T (for example, 500 milliseconds), and these are used as the feature vector P = (p1, p1, p1,). It may be generated by converting to p2, ..., PN). As the feature amount, for example, a value sampled at regular intervals can be used.
FIG. 5 shows an example of the feature space map 80. The hatched round plot points P1 show the feature vector when the occupant feels uncomfortable, and the unhatched round plot points P2 show the feature vector when the occupant does not feel uncomfortable. ..

The feature vector P1 when the occupant feels uncomfortable tends to concentrate in a certain area in the feature space. Further, the feature vector P2 when the occupant does not feel uncomfortable also tends to concentrate in a certain area as well.
In the example of FIG. 5, the feature vector P1 when the occupant feels uncomfortable is relatively concentrated in the upper left region D1, and the feature vector P2 when the occupant does not feel uncomfortable is relatively lower right. It is concentrated in the area D2 of.

By plotting the feature vector P1 when the occupant feels uncomfortable and the feature vector P2 when the occupant does not feel uncomfortable on the feature space to create the feature space map 80, the feature vector P1 can be created. A discrimination plane 81 that divides the range that can be taken and the range that the feature vector P2 can take can be set. The discrimination plane 81 can be set by using, for example, a linear discrimination method.
In the example of FIG. 5, if the feature vector Pc of the current brain wave of the occupant is located above the discrimination plane 81, the discomfort detection unit 60 determines that the occupant feels discomfort, that is, the occupant has detected the discomfort. do.
If the occupant's current EEG feature vector Pc is located below the discrimination plane 81, the discomfort detection unit 60 determines that the occupant does not feel discomfort, that is, the occupant does not detect discomfort. The discomfort detection unit 60 outputs the determination result to the voice guidance adjustment unit 61.

See FIG. The voice guidance adjustment unit 61 generates voice guidance that guides route guidance, traffic guidance, weather information, POI information, and the like by voice, and outputs the voice guidance from the speaker 13.
Further, when the discomfort detection unit 60 detects the discomfort of the occupant with respect to the voice guidance, the voice guidance adjustment unit 61 confirms with the occupant whether or not the voice guidance is appropriate by dialogue with the occupant.
The voice guidance adjustment unit 61 includes a content setting unit 63, a guidance information acquisition unit 64, a detection mode determination unit 65, a dialogue processing unit 66, and a presentation method setting unit 67.

The content setting unit 63 sets the content of the voice guidance. The "content" of the voice guidance means the information of the voice guidance itself, that is, the content, and also means the wording used to express the information of the voice guidance, that is, the wording or the wording. Hereinafter, it is simply referred to as "voice guidance wording".
For example, a route guidance that guides the content of the voice guidance to turn left at the T-junction in front of the vehicle will be described as an example. In this case, there are multiple phrases such as "Turn left at the next intersection", "Turn left at the next T-junction", and "Left along the road" for the same content.

The content setting unit 63 uses the GPS receiver 20 to generate a text for voice guidance that guides the vehicle 1 to the destination based on the current position of the vehicle 1 and the map data stored in the map database 21.
Further, the content setting unit 63 generates a text for traffic guidance based on the current position of the vehicle 1 acquired by using the GPS receiver 20 and the road traffic information acquired by using the beacon receiver 22.

In addition, the content setting unit 63 generates a text for voice-guided weather information and POI information acquired from an external data server. The guidance information acquisition unit 64 acquires these weather information and POI information from an external data server of the vehicle 1.
The content setting unit 63 generates voice data for voice guidance by converting the generated texts into voice data based on the voice waveform dictionary stored in the guidance database 53.

When the generated voice data is output from the speaker 13, the discomfort detection unit 60 determines whether or not the occupant's discomfort with respect to the voice guidance is detected.
When it is determined that the occupant's discomfort with respect to the voice guidance is detected, the detection mode determination unit 65 determines the detection mode of the occupant's discomfort with respect to the voice guidance.

For example, the detection mode determination unit 65 may determine whether or not the voice guidance is sufficiently completed at the time of detecting the discomfort as the detection mode of the discomfort. Here, "the voice guidance was sufficiently completed" includes the case where the voice guidance was completed, and all the contents of the voice guidance even in the middle of the voice guidance, for example, just before the completion. It may include cases where it is understandable or where there is a rough idea.
Further, for example, when the voice guidance is not sufficiently completed at the time of detecting the discomfort, the detection mode determination unit 65 may have detected the discomfort in the middle of the voice guidance as the detection mode of the discomfort, or the discomfort immediately after the start of the voice guidance. May be determined if was detected.

For example, the detection mode determination unit 65 detected the discomfort in the middle of the voice guidance depending on whether or not the voice guidance output from the start of the voice guidance to the detection of the discomfort can be meaningful. It may be determined whether or not the discomfort is detected immediately after the start of the voice guidance.
That is, the detection mode determination unit 65 may determine that the discomfort is detected in the middle of the voice guidance when the voice guidance output from the start of the voice guidance to the detection of the discomfort can be meaningful. .. Further, the detection mode determination unit 65 determines that the discomfort is detected immediately after the start of the voice guidance when the voice guidance output from the start of the voice guidance to the detection of the discomfort cannot be meaningful. It's okay.

For example, when the output voice guidance is completed as a sentence, contains a subject and a predicate, and contains a characteristic proper noun, the detection mode determination unit 65 can give meaning to the voice guidance. May be determined.
Further, for example, when the output voice guidance sentence is interrupted in the middle, a characteristic noun is not included, or the part of speech is not completed, the detection mode determination unit 65 cannot make sense in the voice guidance. It may be determined that there is.
For example, the detection mode determination unit 65 determines that it can be meaningful when the number of proper nouns included in the voice guidance output from the start of the voice guidance to the detection of the discomfort is larger than the threshold value TH. good. When the number of proper nouns is equal to or less than the threshold value TH, it may be determined that the meaning is impossible.

For example, when the guidance content set by the content setting unit 63 is labeled with a part of speech or the like, the detection mode determination unit 65 may detect a noun using a label. When the guidance content set in the content setting unit 63 is not labeled, for example, the detection mode determination unit 65 performs morphological analysis used in the natural language understanding processing technology to perform the morphological analysis of the words included in the text of the guidance content. The part of speech may be determined.

When it is determined that the occupant's discomfort is detected, the dialogue processing unit 66 performs dialogue processing for confirming with the occupant whether or not the voice guidance is appropriate.
For example, the dialogue processing unit 66 outputs a question voice of a question asking the occupant whether or not the voice guidance is appropriate from the speaker 13.
Further, for example, the dialogue processing unit 66 acquires the response of the occupant to the question voice output from the speaker 13.

The occupant's response voice to the question voice output from the speaker 13 is collected by the microphone 15 and converted into an electrical voice signal, and then input to the voice recognition unit 62. The voice recognition unit 62 performs voice recognition processing on the input voice signal, converts it into text data, and inputs it to the dialogue processing unit 66.
The dialogue processing unit 66 may determine the response result of the occupant to the question voice based on the text data of the response voice.

The dialogue processing unit 66 engages in different dialogues with the occupant depending on the mode of detecting the discomfort.
For example, when the voice guidance is not sufficiently completed at the time of detecting the discomfort, and the detection of the discomfort is not immediately after the start of the voice guidance but in the middle of the voice guidance (that is, the voice output from the start of the voice guidance to the detection of the discomfort). (When the guidance can be meaningful), the dialogue processing unit 66 determines that the wording of the voice guidance feels uncomfortable.

In this case, the dialogue processing unit 66 simply outputs a question voice such as "Is it okay?", Or repeats the word output immediately before and outputs a question voice such as "Are you sure you want XX?" By outputting, a dialogue is performed to confirm the appropriateness of the wording of the voice guidance.
The dialogue processing unit 66 determines the response result of the occupant to the question voice confirming the appropriateness of the wording of the voice guidance.
When the dialogue processing unit 66 determines that the wording of the voice guidance is not appropriate (for example, when the response voice is "No" or the like), the content setting unit 63 changes the wording of the voice guidance.

For example, the content setting unit 63 may extract phrases other than the phrases used this time from a plurality of phrases stored in the guidance database 53 and use them for voice guidance.
For example, the content setting unit 63 may set priorities in descending order of general usage frequency, and change the wording in descending order of priority.

Further, the content setting unit 63 may output the changed wording again every time the wording is changed. Each time the dialogue processing unit 66 outputs the changed wording, the dialogue processing unit 66 may output a question voice confirming the appropriateness of the wording of the voice guidance and determine the response result of the occupant to the question voice. The content setting unit 63 may output while changing the wording until the dialogue processing unit 66 determines that the wording of the voice guidance is appropriate (for example, the response voice is “Yes” or the like).

In addition, when the voice guidance is not sufficiently completed at the time of detecting the discomfort, and the detection of the discomfort is immediately after the start of the voice guidance (that is, when the voice guidance output from the start of the voice guidance to the detection of the discomfort cannot be meaningful). In addition, the dialogue processing unit 66 determines that the method of presenting the voice guidance feels uncomfortable.
In this case, the dialogue processing unit 66 asks, "Are you hearing the voice?", "Is the voice clear?", "Is the speaking speed appropriate?", "Is the pitch appropriate?" By outputting the question voice, a dialogue is conducted to confirm the suitability of the voice guidance presentation method.
The "presentation method" of voice guidance means, for example, whether or not a noise filter is applied and its strength, voice volume, voice pitch (that is, pitch), speaking speed, pitch, intonation, and voice pattern. Here, the voice pattern means the sound quality of voice guidance, and for example, the voice quality may include a masculine voice, a feminine voice, a young voice, a middle-aged voice, and an elderly voice.

The dialogue processing unit 66 determines the response result of the occupant to the question voice confirming the suitability of the voice guidance presentation method.
When the dialogue processing unit 66 determines that the voice guidance presentation method is not appropriate (for example, when the response voice is "No" or the like), the presentation method setting unit 67 changes the voice guidance presentation method.
For example, the dialogue processing unit 66 classifies the presentation method of voice guidance into a plurality of classifications such as "application of noise filter", "volume", "pitch", "speaking speed", and "voice pattern", and each of them is classified. A question voice for confirming whether or not the presentation method is appropriate for each classification may be output from the speaker 13. The presentation method setting unit 67 may change the presentation method of the classification in which the occupant responded that it was not appropriate.

For example, the dialogue processing unit 66 outputs a question voice confirming whether or not the first classification (for example, “application of a noise filter”) is appropriate, and determines the response result of the occupant to the question voice. When the dialogue processing unit 66 determines that the presentation method of the first classification is not appropriate (for example, when the response voice is "No" or the like), the presentation method setting unit 67 determines the presentation method of the first classification. change.
Each time the dialogue processing unit 66 changes the presentation method and outputs the voice guidance, the dialogue processing unit 66 outputs a question voice confirming the suitability of the voice guidance presentation method, and determines the response result of the occupant to the question voice.
The content setting unit 63 outputs voice guidance while changing the presentation method until the dialogue processing unit 66 determines that the presentation method of the first classification is appropriate (for example, the response voice is "Yes" or the like). do.

When the dialogue processing unit 66 determines that the presentation method of the first classification is appropriate after the change of the presentation method of the first classification is completed, or when the dialogue processing unit 66 determines that the presentation method of the first classification is appropriate, the next second classification ( Similarly, for (for example, "volume"), confirm with the occupants whether or not the presentation method is appropriate. The presentation method setting unit 67 changes the presentation method until the presentation method becomes appropriate.
Hereinafter, for each of the classifications after the third classification (for example, "pitch"), the occupant is similarly confirmed whether or not the presentation method is appropriate. The presentation method setting unit 67 changes the presentation method until the presentation method becomes appropriate.
The order of classification for confirming the suitability of the presentation method is, for example, in descending order of influence on the audibility of voice guidance (for example, "whether or not noise filter is applied and strength", "volume", "pitch", "pitch". It may be set in the order of "speaking speed" and "intonation").

Further, when the voice guidance is sufficiently completed at the time of detecting the discomfort, the dialogue processing unit 66 determines that the content of the voice guidance feels discomfort.
In this case, the dialogue processing unit 66 is interested in the presented content of the voice guidance by outputting a question voice such as "Are you interested in the current content?" Or "Did you need the current guidance?" Have a dialogue to confirm whether or not.

The dialogue processing unit 66 determines the response result of the occupant to the question voice confirming whether or not he / she is interested in the presented content.
When the dialogue processing unit 66 determines that the content to be presented is not interesting (for example, when the response voice is "No" or the like), the content setting unit 63 changes the content to be presented at the next voice guidance.
In this way, the guidance device 10 not only unilaterally provides information to the occupant, but also enables smooth communication with the occupant while confirming the response of the occupant by voice dialogue.

(motion)
Next, an example of the voice guidance method according to the first embodiment will be described with reference to FIG.
In step S1, the voice guidance adjusting unit 61 starts voice guidance.
In step S2, the discomfort detection unit 60 determines whether or not the occupant's discomfort with respect to the voice guidance started in step S1 is detected in order to determine whether or not it is necessary to change the voice guidance method. When a sense of incongruity is detected (step S2: Y), the process proceeds to step S3. When no discomfort is detected (step S2: N), the voice guidance is completed without executing the subsequent processing for changing the voice guidance method, and the processing ends.

In step S3, the detection mode determination unit 65 executes a detection mode determination process for determining the detection mode of the discomfort in order to determine the cause of the discomfort with respect to the voice guidance.
An example of the detection mode determination process will be described with reference to FIG. 7.
In step S10, the detection mode determination unit 65 determines whether or not the voice guidance is sufficiently completed at the time of detecting the discomfort as the detection mode of the discomfort. This is to determine whether or not the occupant fully understands the content of the audio content and feels uncomfortable with the content.

When the voice guidance is sufficiently completed (step S10: Y), the process proceeds to step S11. If the voice guidance is not sufficiently completed (step S10: N), the process proceeds to step S12.

In step S11, the detection mode determination unit 65 determines that the voice guidance is sufficiently completed. After that, the detection mode determination process ends.
In step S12, the detection mode determination unit 65 decomposes the text of the voice guidance output from the start of the voice guidance to the detection of the discomfort into part speech. The detection mode determination unit 65 determines the number of proper nouns included in the output voice guidance from the start of the voice guidance to the detection of the discomfort. Depending on whether the voice guidance output from the start of the voice guidance to the detection of the discomfort can be meaningful, did the occupants feel discomfort with the wording of the voice guidance, or did the voice guidance feel uncomfortable? This is to determine whether the presentation method feels strange.

In step S13, the detection mode determination unit 65 determines whether or not the number of proper nouns included in the voice guidance output from the start of the voice guidance to the detection of the discomfort is larger than the threshold value TH. When the number of proper nouns is larger than the threshold value TH (step S13: Y), the process proceeds to step S14. When the number of proper nouns is equal to or less than the threshold value TH (step S13: N), the process proceeds to step S15.

In step S14, the detection mode determination unit 65 determines that the voice guidance output from the start of the voice guidance to the detection of the discomfort can be meaningful. After that, the detection mode determination process ends.
In step S15, the detection mode determination unit 65 determines that the voice guidance output from the start of the voice guidance to the detection of the discomfort cannot be meaningful. After that, the detection mode determination process ends.

See FIG. After the detection mode determination process (S3) is completed, the process proceeds to step S4. In step S4, the dialogue processing unit 66 determines whether or not the voice guidance is sufficiently completed at the time of detecting the discomfort, based on the determination result of the detection mode determination unit 65.
When the voice guidance is sufficiently completed (step S4: Y), the dialogue processing unit 66 determines that the content of the voice guidance feels uncomfortable, and the process proceeds to the content change process of step S8.
If the voice guidance is not sufficiently completed (step S4: N), the process proceeds to step S5 in order to determine whether the voice guidance presentation method or the wording feels uncomfortable.

In step S5, the dialogue processing unit 66 determines, based on the determination result of the detection mode determination unit 65, whether or not the voice guidance output from the start of the voice guidance to the detection of the discomfort can be meaningful. do.
When the meaning is impossible (step S5: N), the dialogue processing unit 66 determines that the voice guidance presentation method feels uncomfortable, and the process proceeds to the presentation method change process in step S6. When the meaning is possible (step S5: Y), the dialogue processing unit 66 determines that the wording of the voice guidance feels strange, and the process proceeds to the wording change process of step S7.

In step S6, the dialogue processing unit 66 and the presentation method setting unit 67 execute a presentation method change process for changing the voice guidance presentation method in order to eliminate the discomfort of the occupant with respect to the voice guidance presentation method.
The presentation method change process will be described with reference to FIG.
In step S20, the dialogue processing unit 66 outputs a question voice confirming the suitability of the noise filter, which is the first classification of the presentation method, in order to confirm with the occupant whether or not the noise filter is applied and the suitability of the strength. The dialogue processing unit 66 acquires the response of the occupant to the question voice.

In step S21, the dialogue processing unit 66 determines whether or not the occupant's response is "Yes" or the like, that is, whether or not the noise filter is applied and whether or not the strength is appropriate.
When the response of the occupant is "Yes" or the like (step S21: Y), the process proceeds to step S23 for confirming the suitability of "volume", which is the second category of the presentation method.
If the occupant's response is "No" or the like (step S21: N), the process proceeds to step S22. In step S22, the presentation method setting unit 67 changes the type and intensity of the noise filter to be applied. After that, the process returns to step S20.

In step S23, the dialogue processing unit 66 outputs a question voice confirming the suitability of the voice guidance volume, which is the second classification of the presentation method, in order to confirm with the occupant the suitability of the volume. The dialogue processing unit 66 acquires the response of the occupant to the question voice.
In step S24, the dialogue processing unit 66 determines whether or not the occupant's response is "Yes" or the like, that is, whether or not the volume is appropriate.

When the response of the occupant is "Yes" or the like (step S24: Y), the process proceeds to step S26 for confirming the suitability of "pitch", which is the third classification of the presentation method.
If the occupant's response is "No" or the like (step S24: N), the process proceeds to step S25. In step S25, the presentation method setting unit 67 changes the volume of the voice guidance. After that, the process returns to step S23.

In step S26, the dialogue processing unit 66 outputs a question voice confirming the suitability of the voice guidance pitch, which is the third classification of the presentation method, in order to confirm the suitability of the pitch with the occupant. The dialogue processing unit 66 acquires the response of the occupant to the question voice.
In step S27, the dialogue processing unit 66 determines whether or not the occupant's response is "Yes" or the like, that is, whether or not the pitch is appropriate.

When the occupant's response is "Yes" or the like (step S27: Y), the process proceeds to step S29 for confirming the suitability of "speaking speed", which is the fourth classification of the presentation method.
If the occupant's response is "No" or the like (step S27: N), the process proceeds to step S28. In step S28, the presentation method setting unit 67 changes the pitch of the voice guidance. After that, the process returns to step S.

In step S29, the dialogue processing unit 66 outputs a question voice confirming the suitability of the voice guidance, which is the fourth classification of the presentation method, in order to confirm with the occupant the suitability of the speech speed. The dialogue processing unit 66 acquires the response of the occupant to the question voice.
In step S30, the dialogue processing unit 66 determines whether or not the occupant's response is "Yes" or the like, that is, whether or not the speaking speed is appropriate.

When the occupant's response is "Yes" or the like (step S30: Y), the process proceeds to step S32 for confirming "voice preference", which is the fifth classification of the presentation method.
If the occupant's response is "No" or the like (step S30: N), the process proceeds to step S31. In step S31, the presentation method setting unit 67 changes the speaking speed. After that, the process returns to step S29.

In step S32, the dialogue processing unit 66 outputs a question voice confirming the suitability of the voice preference, which is the fifth classification of the presentation method, in order to confirm with the occupant. The dialogue processing unit 66 acquires the response of the occupant to the question voice.
In step S30, the dialogue processing unit 66 determines whether or not the occupant's response is "Yes" or the like, that is, whether or not the voice of the voice guidance matches the occupant's preference.

The process ends when the occupant's response is "Yes" or the like (step S33: Y).
If the occupant's response is "No" or the like (step S33: N), the process proceeds to step S34. In step S34, the presentation method setting unit 67 changes the voice pattern of the voice guidance, and then the process returns to step S32.

See FIG. In step S7, the dialogue processing unit 66 and the content setting unit 63 execute a wording change process for changing the wording of the voice guidance in order to eliminate the discomfort of the occupant with respect to the wording of the voice guidance.
The wording change process will be described with reference to FIG.
In step S40, the dialogue processing unit 66 outputs a question voice confirming the suitability of the wording of the voice guidance in order to confirm with the occupant the suitability of the wording. The dialogue processing unit 66 acquires the response of the occupant to the question voice.

In step S41, the dialogue processing unit 66 determines whether or not the occupant's response is "Yes" or the like, that is, whether or not the wording is appropriate.
When the occupant's response is "Yes" or the like (step S41: Y), the process ends without changing the wording. If the occupant's response is "No" or the like (step S41: N), the process proceeds to step S42.

In step S42, the content setting unit 63 changes the wording of the voice guidance in order to eliminate the discomfort with the wording of the voice guidance.
For example, the content setting unit 63 extracts a phrase other than the phrase used this time from a plurality of phrases stored in the guidance database 53, and selects the phrase to be used for voice guidance. After that, the process ends.

See FIG. In step S8, the dialogue processing unit 66 and the content setting unit 63 execute a content change process for changing the content of the voice guidance in order to eliminate the discomfort of the occupant with respect to the content of the voice guidance.
The content change process will be described with reference to FIG.
In step S50, the dialogue processing unit 66 outputs a question voice confirming the suitability of the voice guidance content in order to confirm the suitability of the content with the occupant. The dialogue processing unit 66 acquires the response of the occupant to the question voice.

In step S51, the dialogue processing unit 66 determines whether or not the occupant's response is "Yes" or the like, that is, whether or not the content is appropriate.
When the occupant's response is "Yes" or the like (step S51: Y), the process ends without changing the classification of the content to be presented next time.

If the occupant's response is "No" or the like (step S51: N), the process proceeds to step S52.
In step S52, the content setting unit 63 changes the classification of the content to be presented next time. After that, the process ends.

(Effect of the first embodiment)
(1) The voice guidance adjustment unit 61 executes a process of outputting voice guidance from the speaker. The discomfort detection unit 60 executes a process of determining whether or not the occupant's discomfort with respect to the voice guidance is detected. When it is determined that the occupant's discomfort is detected, the dialogue processing unit 66 engages with the occupant in different dialogues depending on the mode of detecting the discomfort.
As a result, the guidance device 10 not only unilaterally provides information to the occupant, but also can change the dialogue according to the detection mode of the discomfort, so that smooth communication with the occupant becomes possible.

(2) The dialogue processing unit 66 conducts a dialogue to confirm the suitability of voice guidance according to the detection mode of discomfort.
As a result, the guidance device 10 not only unilaterally provides information to the occupant, but also can confirm the appropriateness of the voice guidance while confirming the response of the occupant through dialogue, so that smooth communication with the occupant can be performed. Will be possible.

(3) If the detection of discomfort is immediately after the start of voice guidance, for example, if the voice guidance output from the start of voice guidance to the detection of discomfort cannot be meaningful, the occupant feels discomfort in the method of presenting the voice guidance. Probability is high.
Therefore, when a sense of incongruity is detected immediately after the start of the voice guidance, the dialogue processing unit 66 engages in a dialogue to confirm with the occupant whether or not the method of presenting the voice guidance is appropriate. The presentation method setting unit 67 changes the presentation method of the voice guidance according to the result of the dialogue.
This makes it possible to change the method of presenting the voice guidance in a situation where there is a high possibility that the method of presenting the voice guidance feels uncomfortable.

(4) The method of presenting voice guidance consists of various elements such as whether or not a noise filter is applied and its strength, voice volume, voice pitch (that is, pitch), speaking speed, pitch, intonation, voice pattern, and the like. ..
Therefore, the dialogue processing unit 66 classifies the presentation method into each element, and performs a dialogue for confirming the suitability of the voice guidance presentation method for each presentation method classification. The presentation method setting unit 67 changes the presentation method of the classification in which the occupant responded that it was inappropriate.
This makes it possible to determine an appropriate combination of presentation methods that the occupant does not feel uncomfortable without changing the elements that the occupant does not feel uncomfortable with.

(5) If the detection of discomfort is in the middle of voice guidance, for example, if the voice guidance output from the start of voice guidance to the detection of discomfort can be meaningful, the occupant feels discomfort in the content of the voice guidance such as wording. There is a high possibility that it is.
Therefore, when a discomfort is detected in the middle of the voice guidance, the dialogue processing unit 66 conducts a dialogue to confirm the suitability of the content of the voice guidance performed between the start of the voice guidance and the detection of the discomfort. ..
As a result, the content of the voice guidance can be changed in a situation where there is a high possibility that the content of the voice guidance feels strange.

(6) If a sense of discomfort is detected after the voice guidance is sufficiently completed, it is highly possible that the occupant feels a sense of discomfort in the content of the voice guidance such as the content.
Therefore, when a sense of incongruity is detected after the voice guidance is completed, the dialogue processing unit 66 conducts a dialogue to confirm whether or not the occupant is interested in the content of the voice guidance.
As a result, the content of the voice guidance can be changed in a situation where there is a high possibility that the content of the voice guidance feels strange.
(7) When it is determined that the occupant is not interested in the content of the voice guidance, the content setting unit 63 changes the classification of the content of the voice guidance to be output.
By changing the classification of the contents of the voice guidance, it is possible to eliminate the discomfort of the occupants with respect to the contents of the voice guidance.

(Modification example)
(1) In the above-mentioned detection mode determination process, the detection mode determination unit 65 may determine, as a detection mode of discomfort, whether or not the occupant has felt discomfort in the past with voice guidance having the same content.
When it is determined that the occupant feels uncomfortable with the same content in the past, the dialogue processing unit 66 may determine that the occupant feels uncomfortable with the content of the voice guidance. When it is determined that the occupant did not feel uncomfortable with the same content in the past, the dialogue processing unit 66 may determine that the occupant felt uncomfortable with the method of presenting the voice guidance.

(2) The guidance device 10 may include a sensor for detecting another physiological index of the occupant indicating brain activity or the like, instead of the electroencephalogram sensor 12. For example, the sensor that detects the physiological index may detect the cerebral blood flow, heart rate, respiratory rate, and sweating amount of the occupant as the physiological index. For example, a sensor that detects a physiological index may include a near-infrared light emitting probe and a light receiving probe, and may measure the state of occupant's cerebral blood flow from the absorbance of the near infrared rays.
The discomfort detection unit 60 may measure the brain activity of the occupant based on these physiological indexes and determine the presence or absence of discomfort. This makes it possible to appropriately detect the discomfort of the occupant.
Further, instead of the occupant's brain wave, the occupant's face image may be detected as a physiological index. Instead of the electroencephalogram sensor 12, the guidance device 10 may include an image pickup device installed in front of the vehicle interior of the vehicle 1 so as to face the front of the occupant. The discomfort detection unit 60 may analyze the facial image of the occupant captured by the image pickup apparatus and determine the presence or absence of discomfort based on the brain activity of the occupant estimated from the analysis result. This makes it possible to appropriately detect the discomfort of the occupant.
Further, instead of the occupant's brain wave, the occupant's autonomic nerve activity may be detected as a physiological index. The discomfort detection unit 60 may determine the presence or absence of discomfort based on the amount of autonomic nerve activity of the occupant. This makes it possible to appropriately detect the discomfort of the occupant.

(Second Embodiment)
Subsequently, the guide device 10 of the second embodiment will be described. The configuration of the guidance device 10 and the functional configuration of the controller 11 of the second embodiment are the same as the configuration shown in FIG. 1 and the functional configuration shown in FIG. 3, respectively.
The guidance device 10 of the second embodiment classifies the contents of the voice guidance into a plurality of categories. For example, the content of the voice guidance is classified into categories such as stores, tourist spots, traffic guidance, weather information, etc. from labeling including road traffic information, POI information, weather information, and the like.

When the guidance device 10 determines that the occupant is not interested in the first voice guidance of the contents of the first classification, the guidance device 10 stores the first classification in the storage device 51 as the classification to which the voice guidance to which the occupant is not interested belongs. Remember.

The guidance device 10 may determine that the occupant is not interested in voice guidance when the discomfort detection unit 60 detects the discomfort of the occupant. Further, the guidance device 10 may determine whether or not he / she is interested in the voice guidance by having a dialogue in which the dialogue processing unit 66 confirms whether or not he / she is interested in the presentation content of the voice guidance.
Alternatively, when the discomfort detection unit 60 detects the discomfort of the occupant, the dialogue processing unit 66 determines whether or not the user is interested in the voice guidance by performing a dialogue to confirm whether or not he / she is interested in the presented content of the voice guidance. You may.

Next, the guidance device 10 outputs the classification stored in the storage device 51, that is, the second voice guidance in the same first classification. For example, when the first classification is "restaurant" and the first voice guidance "There is a soba shop XX nearby" is output, the guidance device 10 uses the guidance device 10 as the second voice guidance "Italian food nearby". There is a store △△ ”is output.
The guidance device 10 determines whether or not the occupant is interested in the second voice guidance.

When it is determined that the occupant is interested in the second voice guidance, the content setting unit 63 determines that the first voice guidance is not appropriate and that there is no problem in the first classification. In this case, the content setting unit 63 does not change the classification of the content of the voice guidance to be output from the first classification, and continues the voice guidance of the content of the first classification. For example, the content setting unit 63 outputs other similar information in the first category, such as "people who go to the Italian restaurant △△ often go to the Italian restaurant XX".

When it is determined that the occupant is not interested in the second voice guidance, the content setting unit 63 determines that there is a problem in the first classification. The content setting unit 63 changes the classification of the content of the output voice guidance to a second classification, for example, "sightseeing spot".
Then, the content setting unit 63 outputs the third voice guidance "there is a famous tourist attraction-nearby" in the second classification "sightseeing spot".

If the occupant determines that the occupant is not interested in the voice guidance even after the classification is changed, the content setting unit 63 outputs the voice guidance while repeating the change of the classification. When the occupant no longer feels uncomfortable (when the occupant becomes interested), the guidance information acquisition unit 64 selects information similar to or related to the voice guidance of the category of interest, or information often searched for in this category. Search and get it on the Internet.

An example of the voice guidance method according to the second embodiment will be described with reference to FIG. Here, an example is shown in which the occupant is not interested in voice guidance when the discomfort detection unit 60 detects the discomfort of the occupant.
However, it may be determined whether or not there is an interest in the voice guidance by having the dialogue processing unit 66 perform a dialogue to confirm whether or not the presentation content of the voice guidance is interested. When the discomfort detection unit 60 detects the discomfort of the occupant, the dialogue processing unit 66 determines whether or not the user is interested in the voice guidance by performing a dialogue to confirm whether or not he / she is interested in the presented content of the voice guidance. May be good.
Further, although an example of providing POI information as the content of voice guidance is shown, traffic guidance, weather information, and the like may be included.

In step S60, the content setting unit 63 outputs the first POI information of the first classification as voice guidance.
In step S61, the discomfort detection unit 60 determines whether or not the discomfort detection unit 60 has detected the discomfort of the occupant in order to determine whether or not the occupant is interested in the first POI information of the first classification. .. When the occupant's discomfort is detected (step S61: Y), the process proceeds to step S62.

When the occupant's discomfort is not detected (step S61: N), the content setting unit 63 determines that there is no problem in the first classification, and changes the classification of the content of the output voice guidance from the first classification. End the process without. As a result, the content setting unit 63 continues the voice guidance of the content of the first classification.
In step S62, the content setting unit 63 outputs the second POI information in the first classification in order to determine which of the first classification and the first POI information has a problem. For example, the second POI information may be information similar to the first POI information.

In step S63, the discomfort detection unit 60 determines whether or not the discomfort detection unit 60 has detected the occupant's discomfort. When the occupant's discomfort is detected (step S63: Y), the process proceeds to step S64.
When the occupant's discomfort is not detected (step S63: N), the content setting unit 63 determines that there is no problem in the first classification, and changes the classification of the content of the output voice guidance from the first classification. End the process without. As a result, the content setting unit 63 continues the voice guidance of the content of the first classification. The process ends.
In step S64, the content setting unit 63 changes the classification of the provided POI information to the second classification because it is considered that there is a problem in the first classification. After that, the process returns to step S60.

(Effect of the second embodiment)
(1) When it is determined that the occupant is not interested in the first voice guidance of the contents of the first classification, the content setting unit 63 outputs the second voice guidance of the first classification. At least one of the discomfort detection unit 60 and the dialogue processing unit 66 determines whether or not the occupant feels discomfort with respect to the second voice guidance. When it is determined that the occupant does not feel uncomfortable with respect to the second voice guidance, the content setting unit 63 does not change the classification of the content of the output voice guidance from the first classification. When it is determined that the occupant feels uncomfortable with respect to the second voice guidance, the content setting unit 63 changes the classification of the content of the output voice guidance to the second classification.
As a result, the content setting unit 63 can appropriately set the classification of the voice guidance that the occupant is interested in and provide similar recommended information within the same classification.

(2) The content setting unit 63 executes a process of outputting the first voice guidance of the content of the first classification from the speaker. The discomfort detection unit 60 executes a process of determining whether or not the occupant's discomfort with respect to the first voice guidance is detected. The content setting unit 63 performs a process of outputting the second voice guidance of the first classification from the speaker when the discomfort with respect to the first voice guidance is detected. The discomfort detection unit 60 performs a process of determining whether or not the occupant's discomfort with respect to the second voice guidance is detected. When the content setting unit 63 determines that the occupant does not feel uncomfortable with respect to the second voice guidance, the content setting unit 63 does not change the classification of the content of the voice guidance to be output from the first classification, but instead uses the second voice guidance. On the other hand, when it is determined that the occupant feels uncomfortable, the process of changing the classification of the content of the output voice guidance to the second classification is performed.
As a result, the content setting unit 63 can appropriately set the classification of the voice guidance that the occupant is interested in and provide similar recommended information within the same classification.

It goes without saying that the present invention includes various embodiments not described here. Therefore, the technical scope of the present invention is defined only by the matters specifying the invention relating to the reasonable claims from the above description.

1 ... vehicle, 10 ... guidance device, 11 ... controller, 12 ... brain wave sensor, 13 ... speaker, 14 ... display device, 15 ... microphone, 20 ... GPS receiver, 21 ... map database, 22 ... beacon receiver, 23 ... Communication device, 40 ... Vehicle travel controller, 41 ... Driving operation sensor group, 42 ... Vehicle control actuator, 43 ... Vehicle speed sensor, 44 ... Accelerator opening sensor, 45 ... Brake switch, 46 ... Steering operation amount sensor, 50 ... Processor, 51 ... Storage device, 52 ... Discomfort database, 53 ... Guidance database, 60 ... Discomfort detection unit, 61 ... Voice guidance adjustment unit, 62 ... Voice recognition unit, 63 ... Content setting unit, 64 ... Guidance information acquisition unit, 65 ... Detection Aspect determination unit, 66 ... Dialogue processing unit, 67 ... Presentation method setting unit

Claims (12)

The process of outputting voice guidance from the speaker and
The process of detecting the driver's discomfort by measuring the driver's brain wave pattern with the brain wave sensor and collating the measured brain wave pattern with the pre-measured pattern.
The process of determining whether or not the driver feels uncomfortable with the voice guidance and
When it is determined that the driver 's discomfort is detected, a process of performing a different dialogue with the driver depending on whether or not the voice guidance is completed at the time of detecting the discomfort, and a process.
A voice guidance method characterized by the controller performing. The voice guidance method according to claim 1 , wherein when the voice guidance is not completed at the time of detecting the discomfort, a dialogue for confirming the suitability of the voice guidance is performed. When the discomfort is detected immediately after the start of the voice guidance, a dialogue is held to confirm with the driver the suitability of the voice guidance presentation method.
Change the presentation method of voice guidance according to the result of the dialogue,
The voice guidance method according to claim 2, wherein the voice guidance method is characterized in that. Dialogue to confirm the suitability of the voice guidance presentation method is conducted for each presentation method classification.
Change the method of presenting the classification that the driver responded to as inappropriate,
The voice guidance method according to claim 3, wherein the voice guidance method is characterized in that. When the discomfort is detected in the middle of the voice guidance, a dialogue is performed to confirm the suitability of the content of the voice guidance performed between the start of the voice guidance and the detection of the discomfort. The voice guidance method according to any one of claims 2 to 4. Any of claims 2 to 5, wherein when the discomfort is detected after the voice guidance is completed, the driver conducts a dialogue to confirm whether or not he / she is interested in the content of the voice guidance. The voice guidance method described in paragraph 1. The voice guidance method according to claim 6, wherein when it is determined that the driver is not interested in the content of the voice guidance, the classification of the content of the voice guidance to be output is changed. When it is determined that the driver is not interested in the first voice guidance of the contents of the first classification, the second voice guidance of the first classification is output.
It is determined whether or not the driver feels uncomfortable with respect to the second voice guidance.
When it is determined that the driver does not feel uncomfortable with respect to the second voice guidance, the classification of the content of the voice guidance to be output is not changed from the first classification, and the second voice guidance is not changed. When it is determined that the driver feels uncomfortable, the classification of the content of the voice guidance to be output is changed to the second classification.
The voice guidance method according to claim 6 or 7. The process of outputting the first voice guidance of the contents of the first classification from the speaker, and
The process of detecting the driver's discomfort by measuring the driver's brain wave pattern with the brain wave sensor and collating the measured brain wave pattern with the pre-measured pattern.
The process of determining whether or not the driver feels uncomfortable with respect to the first voice guidance, and
A process of outputting the second voice guidance of the first classification from the speaker when the discomfort with respect to the first voice guidance is detected.
The process of determining whether or not the driver 's discomfort with respect to the second voice guidance is detected, and
When it is determined that the driver does not feel uncomfortable with respect to the second voice guidance, the classification of the content of the voice guidance to be output is not changed from the first classification, and the second voice guidance is not changed. When it is determined that the driver feels uncomfortable, the process of changing the classification of the content of the voice guidance to be output to the second classification, and
A voice guidance method characterized by the controller performing. A brain wave sensor that detects the driver 's brain wave,
A speaker that outputs voice guidance and
The driver's brain wave pattern is measured by the brain wave sensor, and the measured brain wave pattern is collated with the pre-measured pattern to detect the driver's discomfort, and the driver with respect to the voice guidance output from the speaker. It determines whether the it has detected the discomfort, if it is determined that detects the discomfort of the driver is performed with the driver different interaction depending on whether the voice guidance has been completed formation during discomfort detection With the controller
A voice guidance device characterized by being provided with. A brain wave sensor that detects the driver 's brain wave,
A speaker that outputs voice guidance and
The driver's brain wave pattern is measured by the brain wave sensor, and the measured brain wave pattern is collated with the pre-measured pattern to detect the driver's discomfort, and the first voice of the content of the first classification is detected. It is determined whether or not the driver 's discomfort with respect to the guidance is detected, and when the discomfort with respect to the first voice guidance is detected, the second voice guidance of the first classification is output from the speaker. based on the physiological indices of the driver in which the sensor detects the second to determine whether the detected driver's uncomfortable feeling with respect to voice guidance, the driver uncomfortable feeling with respect to the second voice guidance When it is determined that the driver does not change the classification of the content of the voice guidance to be output from the first classification and the driver feels uncomfortable with respect to the second voice guidance. A controller that changes the classification of the output voice guidance content to the second classification,
A voice guidance device characterized by being provided with. The controller, if the voice guidance at the discomfort detection is not completed, the voice guidance device according to claim 10, wherein the TURMERIC line dialogue to confirm the appropriateness of the voice guidance.

Images