Stress detector and stress detection method

Abstract

To provide a stress detector and a stress detection method which can determine a stress level according to a causing factor.SOLUTION: A stress detector comprises: a sensor which detects sound in an external acoustic meatus of a driver of a vehicle; and a processing part which processes a sound signal obtained by sound detection by the sensor. The processing part can estimate, based on at least one of magnitude of a signal level of the sound signal and change thereof and a changed frequency band in the sound signal, a factor that causes the change of the sound signal. Furthermore, the processing part can determine, based on the factor obtained by the estimation and the change of the signal level of the sound signal, a stress level of the driver.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to a stress detection device and a stress detection method. [Background technology]

[0002] Detecting the stress level of a vehicle occupant has been practiced for some time. For example, sound data can be used to detect the stress level of the occupant. Patent Document 1 below discloses a method of detecting bone-flesh-conducted sound by bringing a bone-flesh-conducted sound sensor into contact with the wall of the ear canal and calculating a stress index based on the detected bone-flesh-conducted sound. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6832549 Summary of the Invention [Problem to be solved by the invention]

[0004] A stress detection device according to a first aspect of the present disclosure includes a sensor capable of detecting sound in the ear canal of a vehicle driver and a processing unit capable of processing sound data obtained by the sound detection by the sensor. The processing unit is capable of estimating a factor that caused a change in the sound data based on at least one of the magnitude and change in the signal level of the sound data and the frequency band of the sound data in which a change occurred. The processing unit is further capable of determining the driver's stress level based on the factor obtained by the estimation and the change in the signal level of the sound data.

[0005] The stress detection method according to the second aspect of the present disclosure includes the following three aspects. (1) Acquiring sound data obtained by detecting sounds in the ear canal of a vehicle driver with a sensor. (2) Estimating the cause of the change in the sound data based on at least one of the magnitude and change in the signal level of the sound data and the frequency band in the sound data where the change occurred. (3) Determining the driver's stress level based on the factors obtained by the estimation and the change in the signal level of the sound data. [Brief explanation of the drawings]

[0006] The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification. The drawings illustrate one embodiment and, together with the description, serve to explain the principles of the disclosure.

[0007] [Figure 1] FIG. 1 is a diagram for explaining bone conduction sound propagating inside the body of an occupant. [Figure 2] FIG. 2 is a diagram illustrating an example of functional blocks of the earphone-type device of FIG. [Figure 3] FIG. 3 is a diagram illustrating an example of functional blocks of a vehicle according to the first embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram illustrating an example of a perspective configuration of the vehicle of FIG. [Figure 5] FIG. 5 is a diagram illustrating an example of the concept of the threshold table of FIG. [Figure 6] FIG. 6 is a diagram for explaining frequency bands in the threshold table of FIG. [Figure 7] FIG. 7 is a diagram showing an example of a procedure for estimating the stress level of an occupant in the vehicle of FIG. [Figure 8] FIG. 8 is a diagram showing an example of the estimation procedure following FIG. [Figure 9] FIG. 9 is a diagram showing a modified example of the functional blocks of the vehicle shown in FIG. [Figure 10] FIG. 10 is a diagram showing an example of a procedure for estimating the stress level of an occupant in the vehicle of FIG. [Figure 11] FIG. 11 is a diagram showing a modified example of the functional blocks of the vehicle shown in FIG. [Figure 12] FIG. 12 is a diagram illustrating an example of functional blocks of a vehicle according to the second embodiment of the present disclosure. [Figure 13] FIG. 13 is a diagram illustrating an example of a perspective configuration of the vehicle of FIG. [Figure 14] FIG. 14 is a diagram showing an example of a procedure for estimating the stress level of an occupant in the vehicle of FIG. [Figure 15] FIG. 15 is a diagram illustrating a modified example of the functional blocks of the vehicle in FIG. 3 and a server device. [Figure 16] FIG. 16 is a diagram illustrating an example of functional blocks of the server device of FIG. [Figure 17] FIG. 17 is a diagram illustrating a modified example of the functional blocks of the vehicle in FIG. 9 and a server device. [Figure 18] FIG. 18 is a diagram illustrating an example of functional blocks of the server device of FIG. [Figure 19] FIG. 19 is a diagram illustrating a modified example of the functional blocks of the vehicle in FIG. 12 and a server device. [Figure 20] FIG. 20 is a diagram illustrating an example of functional blocks of the server device of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0008] Detecting the stress level of a vehicle occupant has been practiced for some time. For example, sound data can be used to detect the stress level of the occupant. Patent Document 1 discloses that a bone-flesh-conducted sound sensor is brought into contact with the wall of the ear canal to detect bone-flesh-conducted sound, and a stress index is calculated based on the detected bone-flesh-conducted sound.

[0009] However, the invention described in Patent Document 1 does not identify the cause of stress, and therefore is unable to determine the stress level according to the cause. It is desirable to provide a stress detection device and a stress detection method that are capable of determining the stress level according to the cause of stress.

[0010] Some exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Note that the following description illustrates one specific example of the present disclosure and should not be construed as limiting the present disclosure. For example, each element, including numerical values, shapes, materials, parts, the position of each part, and the connection method of each part, is merely an example and should not be construed as limiting the present disclosure. Furthermore, in the following exemplary embodiments, components not described in independent claims based on the highest concept of the present disclosure are optional and may be provided as needed. The drawings are schematic and are not intended to be drawn to scale. Throughout this specification and the drawings, components having substantially the same function and configuration are designated by the same reference numerals, and redundant description will be omitted. Furthermore, components not directly related to one embodiment of the present disclosure are not shown in the drawings.

[0011] <1. Bone conduction sound> First, the bone conduction sound fx detected in each embodiment of the present disclosure will be described.

[0012] FIG. 1 is a diagram illustrating bone conduction sound fx propagating through the body of a vehicle occupant (driver). For example, when a vehicle goes over an uneven road surface while traveling or when an occupant chews, the resulting vibrations become bone conduction sound fx and propagate through the occupant's body. The bone conduction sound fx propagates to the brain via the temporal bone 170, cochlea 110, and auditory nerve 120, and the occupant recognizes the bone conduction sound fx as ambient sound. The bone conduction sound fx then propagates to, for example, the ossicles 130 and eardrum 140, vibrating the eardrum 140. This generates air vibrations (sound signals) due to the bone conduction sound fx in the ear canal 160. The air vibrations (sound signals) are detected by an earphone-type device 10 that is detachably fixed to the auricle 150 so as to block the ear canal 160. In the present disclosure, the air vibrations (sound signals) detected by the earphone-type device 10 are used to estimate the factors that caused the changes in the air vibrations (sound signals), and the stress level of the occupant is determined based on the factors obtained by the estimation and the changes in the signal level of the air vibrations (sound signals).

[0013] As shown in FIG. 2 , the earphone-type device 10 includes, for example, a communication unit 11, a signal processing unit 12, a vibrator 13, and a vibration unit 14. The communication unit 11 is a communication interface configured to be able to communicate with an external device and is capable of receiving sound data (e.g., music data or noise canceling data) from the external device. The signal processing unit 12 is capable of generating a voltage signal for vibrating the vibrator 13 based on the sound data acquired via the communication unit 11. The vibrator 13 is capable of vibrating the vibration unit 14 based on the voltage signal input from the signal processing unit 12. The signal processing unit 12 is configured by, for example, a CPU or MPU. The vibration unit 14 is vibrated by the vibrator 13, and is therefore capable of outputting air vibrations (sound signals) to the ear canal 160.

[0014] The earphone-type device 10 further includes a sound collection sensor 15 and an acceleration sensor 16, as shown in FIG. 2 . The sound collection sensor 15 is configured with, for example, a microphone. The sound collection sensor 15 is capable of detecting air vibrations (sound signals) generated in the ear canal 160 due to bone-conducted sound fx. The sound collection sensor 15 is capable of converting the air vibrations (sound signals) into electrical signals and outputting the electrical signals (sound data) obtained by the conversion to the signal processing unit 12. The acceleration sensor 16 is capable of detecting the tilt of the earphone-type device 10 (or the face). The acceleration sensor 16 is capable of outputting data on the detected tilt (tilt data) to the signal processing unit 12. The signal processing unit 12 is capable of outputting, for example, sound data input from the sound collection sensor 15 to a control device 20 (described later) via a communication unit 11. The signal processing unit 12 is capable of outputting the tilt data input from the acceleration sensor 16 to the control device 20 via the communication unit 11.

[0015] 2. First Embodiment [Configuration example] Next, a vehicle 1 according to a first embodiment of the present disclosure will be described. FIG. 3 illustrates an example of functional blocks of the vehicle 1 according to the first embodiment of the present disclosure. The vehicle 1 includes, for example, an earphone-type device 10, a control device 20, and a display device 30, as shown in FIG. 1. The earphone-type device 10 is worn on the ear of an occupant 100 of the vehicle 1, as shown in FIG. 4, for example. The display device 30 is fixed to the dashboard of the vehicle 1, for example. The earphone-type device 10 corresponds to a specific example of a "sensor" according to an embodiment of the present disclosure. The control device 20 corresponds to a specific example of a "stress detection device" according to an embodiment of the present disclosure. The vehicle 1 corresponds to a specific example of a "vehicle" according to an embodiment of the present disclosure. A "stress detection method" according to an embodiment of the present disclosure is executed by the control device 20.

[0016] The control device 20 is capable of processing data (sound data 21A and tilt data 21B) obtained from the earphone type device 10. The control device 20 has, for example, a communication unit 21, a signal processing unit 22, and a storage unit 23, as shown in FIG. 3 . The communication unit 21 is a communication interface capable of communicating with the earphone type device 10. The communication unit 21 is capable of outputting data (sound data 21A and tilt data 21B) input from the earphone type device 10 to the signal processing unit 22. The communication unit 21 is capable of outputting a signal (control signal) for controlling the earphone type device 10, which is input from the signal processing unit 22, to the earphone type device 10.

[0017] The signal processing unit 22 is capable of processing the sound data 21A obtained by sound detection in the earphone-type device 10. The signal processing unit 22 is capable of estimating the cause of the change in the sound data 21A based on a change in the signal level of the sound data 21A and the frequency band of the sound data 21A in which the change occurred. The signal processing unit 22 is capable of estimating the cause of the change in the sound data 21A in a specific frequency band fa to fb, which is the frequency band of a sound signal generated in the ear canal 160 due to bone conduction sound fx. Here, the "cause of the change in the sound data 21A" refers to, for example, a change in the road surface 200 on which the vehicle 1 is traveling from flat to rough (Type 1), a continuation of the rough road condition for a certain period of time (Type 2), a change in the road surface 200 from dry to wet (Type 3), or a change in the road surface 200 from dry to icy (Type 4).

[0018] When the vehicle 1 is traveling on a flat (dry) road surface 200, sound propagates as bone-conducted sound fx1 to the eardrum 140 via the body of the vehicle 1 and the body of the occupant 100, and as a result, air vibrations (sound signals) caused by the bone-conducted sound fx1 are generated in the ear canal 160. At this time, in the sound data 21A obtained by the earphone-type device 10, the vibrations caused by the vehicle 1 traveling on a flat road appear in the frequency band of f1 to f2.

[0019] When the vehicle 1 is traveling on a rough road as the road surface 200, sound propagates as bone conduction sound fx2 to the eardrum 140 via the body of the vehicle 1 and the body of the occupant 100, and as a result, air vibrations (sound signals) caused by the bone conduction sound fx2 are generated in the ear canal 160. At this time, in the sound data 21A obtained by the earphone-type device 10, the vibrations caused by the vehicle 1 traveling on the rough road appear in the frequency band of f3 to f2.

[0020] When the vehicle 1 is traveling on a wet road surface as the road surface 200, sound propagates as bone-conducted sound fx3 to the eardrum 140 via the body of the vehicle 1 and the body of the occupant 100, and as a result, air vibrations (sound signals) caused by the bone-conducted sound fx3 are generated in the ear canal 160. At this time, in the sound data 21A obtained by the earphone-type device 10, the vibrations caused by the vehicle 1 traveling on the wet road surface appear in the frequency band of f4 to f5.

[0021] When the vehicle 1 is traveling on an icy road surface as the road surface 200, sound propagates as bone conduction sound fx4 to the eardrum 140 via the body of the vehicle 1 and the body of the occupant 100, and as a result, air vibrations (sound signals) caused by the bone conduction sound fx4 are generated in the ear canal 160. At this time, in the sound data 21A obtained by the earphone-type device 10, the vibrations caused by the vehicle 1 traveling on the icy road surface appear in the frequency band of f6 to f7.

[0022] The signal processing unit 22 is capable of determining whether or not the cause is a change in the condition of the road surface 200 on which the vehicle 1 is traveling, based on the frequency band in which a change has occurred in the sound data 21A. The signal processing unit 22 is capable of determining that a change has occurred in the condition of the road surface 200 when there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f3 to f2. The signal processing unit 22 is also capable of determining that a change has occurred in the condition of the road surface 200 when there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f4 to f5. The signal processing unit 22 is also capable of determining that a change has occurred in the condition of the road surface 200 when there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f6 to f7.

[0023] When the signal processing unit 22 determines that the cause is a change in the state of the road surface 200 on which the vehicle 1 is traveling, the signal processing unit 22 is able to estimate the type of change in the state of the road surface 200 on which the vehicle 1 is traveling based on a change in the signal level of the sound data 21A. When there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f3 to f2, the signal processing unit 22 is able to estimate that a change of the first type has occurred. When there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f4 to f5, the signal processing unit 22 is able to estimate that a change of the third type has occurred. When there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f6 to f7, the signal processing unit 22 is also able to determine that a change of the fourth type has occurred.

[0024] The signal processing unit 22 is capable of determining the stress level of the occupant 100 based on the above factors and a change in the signal level of the sound data 21A. The signal processing unit 22 is capable of determining the stress level of the occupant 100, for example, by reading out the threshold value table 23B from the storage unit 23 and using the read out threshold value table 23B.

[0025] FIG. 5 shows an example of the concept of the threshold table 23B. FIG. 6 explains the frequency bands in the threshold table 23B of FIG. 5. The specific frequency bands fa to fb include frequency bands that can propagate as bone-conduction sound fx. The specific frequency bands fa to fb include the frequency bands f1 to f2, the frequency bands f3 to f2, the frequency bands f4 to f5, and the frequency bands f6 to f7. FIG. 5 defines frequency bands for each type. In FIG. 5, the frequency bands f1 to f2 and the frequency band f3 to f2 are defined as frequency bands corresponding to the first type, and the frequency bands f1 to f2 and the frequency band f3 to f2 are defined as frequency bands corresponding to the second type. The second type will be described in detail later. FIG. 5 further defines frequency bands f1 to f2 and f4 to f5 as frequency bands corresponding to the third type, and defines frequency bands f6 to f7 as frequency bands corresponding to the fourth type.

[0026] In FIG. 5, thresholds are defined for each type. In FIG. 5, ΔTh1 is defined as a threshold corresponding to the first type, and ΔTh2 is defined as a threshold corresponding to the second type. In FIG. 5, thresholds -ΔTh3 and -ΔTh4 are further defined as thresholds corresponding to the third type, and -ΔTh4 is defined as a threshold corresponding to the fourth type. ΔTh1 corresponds to a specific example of a "first threshold" according to an embodiment of the present disclosure. ΔTh2 corresponds to a specific example of a "second threshold" according to an embodiment of the present disclosure. -ΔTh3 corresponds to a specific example of a "third threshold" according to an embodiment of the present disclosure. -ΔTh4 corresponds to a specific example of a "third threshold" according to an embodiment of the present disclosure.

[0027] Here, the value obtained by subtracting the signal level of the frequency band f1 to f2 before the type change (flat road) from the signal level of the frequency band f3 to f2 after the type change (bad road) is defined as difference ΔS1. Also, the value obtained by subtracting the signal level of the frequency band f1 to f2 before the type change (flat road) from the signal level of the frequency band f4 to f5 after the type change (wet road) is defined as difference ΔS3. Also, the value obtained by subtracting the signal level of the frequency band f1 to f2 before the type change (flat road) from the signal level of the frequency band f6 to f7 after the type change (icy road) is defined as difference ΔS4. Here, the above "signal level" is, for example, the average value or mode value of the signal in a predetermined frequency band. The "signal level" described below is also, for example, the average value or mode value of the signal in a predetermined frequency band.

[0028] At this time, when the signal processing unit 22 estimates that a first type change has occurred, if the difference ΔS1 is larger than ΔTh1, it can determine that the stress level of the occupant 100 is high. When the signal processing unit 22 estimates that a third type change has occurred, if the difference ΔS3 is smaller than -ΔTh3 and larger than -ΔTh4, it can determine that the stress level of the occupant 100 is high. When the signal processing unit 22 estimates that a fourth type change has occurred, if the difference ΔS4 is smaller than -ΔTh4, it can determine that the stress level of the occupant 100 is high.

[0029] The signal processing unit 22 may further estimate the cause of the change in the sound data 21A based on the magnitude of the signal level of the sound data 21A and the frequency band of the sound data 21A that has changed. The difference ΔS2 is calculated by subtracting the signal level of the frequency band f1 to f2 on a flat road before entering the rough road from the signal level of the frequency band f3 to f2 when the rough road continues. The signal processing unit 22 can determine that the road surface 200 is of the second type if the difference ΔS2 is greater than ΔTh2, which is smaller than ΔTh1. The signal processing unit 22 can further determine that the stress level of the occupant 100 is high if the period Ta during which the signal level of the frequency band f3 to f2 is greater than ΔTh2 continues for a period longer than a predetermined period Td. The signal processing unit 22 can output information about the stress level obtained by the determination to the display device 30.

[0030] The signal processing unit 22 may be capable of correcting the stress level obtained by the determination based on the tilt data 21B. In this case, for example, if the change over time in the tilt data 21B is small, the signal processing unit 22 may determine that the occupant 100 is not feeling anxious about the surrounding situation and may reduce the stress level obtained by the determination by a predetermined amount. Also, for example, if the change over time in the tilt data 21B is large, the signal processing unit 22 may determine that the occupant 100 is feeling anxious about the surrounding situation and may increase the stress level obtained by the determination by a predetermined amount.

[0031] The storage unit 23 is configured with, for example, a rewritable nonvolatile memory such as a flash memory or a resistance change memory. The storage unit 23 stores, for example, a processing program 23A describing a series of processes to be executed by the signal generation unit 22, and a threshold value table 23B. The signal generation unit 22 is able to execute the above-mentioned processes by, for example, loading the processing program 23A. The threshold value table 23B defines frequency bands and threshold values ​​for each type, for example, as shown in FIG. 5.

[0032] Display device 30 has, for example, a liquid crystal panel or an organic EL panel. Display device 30 is capable of generating a video signal for displaying a video including information about the stress level obtained by signal processing unit 22, and displaying the video based on the generated video signal.

[0033] [Operation] Next, a procedure for estimating the stress level of the occupant 100 in the vehicle 1 will be described with reference to Figures 7 and 8. Figures 7 and 8 are diagrams for explaining an example of a procedure for estimating the stress level of the occupant 100 in the vehicle 1.

[0034] Assume that the vehicle 1 is traveling on a road. At this time, the earphone-type device 10 acquires, via the sound collection sensor 15, an electrical signal (sound data 21A) of air vibrations (sound signals) generated in the ear canal 160 due to bone-conduction sound fx. The earphone-type device 10 further acquires, via the acceleration sensor 16, tilt data 21B of the earphone-type device 10 (or the face). The earphone-type device 10 outputs the sound data 21A and tilt data 21B to the control device 20 via the communication unit 11.

[0035] The control device 20 determines whether there is a change in the signal level of the acquired sound data 21A. Specifically, the control device 20 determines whether there is a vibration change in the specific frequency band fa to fb of the acquired sound data 21A (step S101). As a result, if there is a vibration change in the specific frequency band fa to fb (step S101; Y), the control device 20 determines whether there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f3 to f2 (step S102). As a result, if there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f3 to f2 (step S102; Y), the control device 20 estimates that a change of the first type has occurred. Next, the control device 20 reads out a threshold value (ΔTh1) corresponding to the first type from the storage unit 23 and determines whether the difference ΔS1 is greater than ΔTh1 (step S103). As a result, if the difference ΔS1 is greater than ΔTh1 (step S103; Y), the control device 20 determines that the stress level of the occupant 100 is high (step S104).

[0036] If the control device 20 determines in step S102 that there is no change in the signal level of the sound data 21A in at least one of the frequency bands f1 to f2 and f3 to f2 (step S102; N), the control device 20 determines whether there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f4 to f5 (step S105). If there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f4 to f5 (step S105; Y), the control device 20 estimates that a third type of change has occurred. Next, the control device 20 reads out thresholds (-ΔTh3, -ΔTh4) corresponding to the third type from the storage unit 23 and determines whether the difference ΔS3 is smaller than -ΔTh3 and larger than -ΔTh4 (step S106). As a result, if the difference ΔS3 is smaller than −ΔTh3 and larger than −ΔTh4 (step S106; Y), the control device 20 determines that the stress level of the occupant 100 is high (step S104).

[0037] If the control device 20 determines in step S105 that there is no change in the signal level of the sound data 21A in at least one of the frequency bands f1 to f2 and f4 to f5 (step S105; N), the control device 20 determines whether there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f6 to f7 (step S107). If there is a change in the signal level of the sound data 21A in the frequency bands f1 to f2 and f6 to f7 (step S107; Y), the control device 20 estimates that a fourth type of change has occurred. Next, the control device 20 reads out the threshold value (-ΔTh4) corresponding to the fourth type from the storage unit 23 and determines whether the difference ΔS4 is greater than -ΔTh4 (step S108). As a result, if the difference ΔS4 is greater than −ΔTh4 (step S108; Y), the control device 20 determines that the stress level of the occupant 100 is high (step S104).

[0038] If the difference ΔS3 is greater than −ΔTh3 in step S106 (step S106; N), or if the difference ΔS4 is greater than −ΔTh4 in step S108 (step S108; N), the control device 20 determines that the stress level of the occupant 100 is low (step S109). The display device 30 displays an image including information about the stress level obtained by the determination (step S110).

[0039] If the difference ΔS2 is greater than ΔTh2 in step S103 (step S103; N), the control device 20 determines that the road surface 200 is of the second type. Subsequently, the control device 20 reads out the thresholds (ΔTh2, Td) corresponding to the second type from the storage unit 23, and determines whether the period Ta during which the difference ΔS2 is greater than ΔTh2 and the signal level in the frequency band of f3 to f2 is greater than ΔTh2 has continued longer than the predetermined period Td (step S111). As a result, if the period Ta during which the difference ΔS2 is greater than ΔTh2 and the signal level in the frequency band of f3 to f2 is greater than ΔTh2 has continued longer than the predetermined period Td (step S111; Y), the control device 20 determines that the stress level of the occupant 100 is high (step S112). On the other hand, if the period Ta during which the signal level in the frequency band from f3 to f2 is greater than ΔTh2 does not continue longer than the predetermined period Td (step S111; N), the control device 20 determines that the stress level of the occupant 100 is low (step S113). The display device 30 displays an image including information about the stress level obtained by the determination (step S114).

[0040] [effect] Next, the effects of the vehicle 1 according to the first embodiment of the present disclosure will be described.

[0041] In this embodiment, the cause of the change in the sound data 21A is estimated based on at least one of the magnitude and change in the signal level of the sound data 21A and the frequency band in the sound data 21A where the change occurred. The stress level of the occupant 100 is determined based on the cause (causing factor) obtained by estimation and the change in the signal level of the sound data 21A. This makes it possible to determine the stress level according to the causing factor.

[0042] In this embodiment, the cause of occurrence is estimated in the specific frequency band fa to fb, which is the frequency band of sound generated in the ear canal 26 due to bone conduction sound fx in the sound data 21A. This makes it possible to determine the stress level according to the cause of occurrence even in a situation where it is difficult to determine the stress level using air conduction sound.

[0043] In this embodiment, it is determined whether the cause of the noise is a change in the shape or condition of the road surface 200 on which the vehicle 1 is traveling, based on the frequency band in the sound data 21A that has changed. If it is determined that the cause of the noise is a change in the shape or condition of the road surface 200 on which the vehicle 1 is traveling, the type of change in the shape or condition of the road surface 200 on which the vehicle 1 is traveling is estimated based on the change in the signal level of the sound data 21A, and the stress level of the occupant 100 is determined by comparing the change in the signal level of the sound data 21A with a threshold value corresponding to the type. In this way, the stress level according to the cause of the noise can be determined.

[0044] In this embodiment, when the change ΔS1 in the signal level of the sound data 21A exceeds ΔTh1, or when the change ΔS2 in the signal level of the sound data 21A is greater than ΔTh2 for a predetermined period of time Td, it is determined that the stress level of the occupant 100 is high. This makes it possible to determine the stress levels of the first and second types.

[0045] In this embodiment, when the change ΔS3 in the signal level of the sound data 21A is smaller (below) −ΔTh3, the stress level of the occupant 100 is determined to be high. This makes it possible to determine the stress level of the third type. Also, in this embodiment, when the change ΔS4 in the signal level of the sound data 21A is smaller (below) −ΔTh4, the stress level of the occupant 100 is determined to be high. This makes it possible to determine the stress level of the fourth type.

[0046] In this embodiment, the stress level obtained by the determination is corrected based on the slope data 21 B. This allows the stress level to be determined with higher accuracy.

[0047] <3. Modification of the First Embodiment> Next, a modification of the vehicle 1 according to the first embodiment of the present disclosure will be described.

[0048] [Variation 3-1] In the above embodiment, the control device 20 may further include a learning model 24, as shown in FIG. 9 , for example. The learning model 24 is a model that has been trained using training sound data and a classification of changes in the shape or state of the road surface 200 as training data. As the training data, for example, a combination of training sound data corresponding to the first type and the first type (classification), a combination of training sound data corresponding to the second type and the second type (classification), a combination of training sound data corresponding to the third type and the third type (classification), and a combination of training sound data corresponding to the fourth type and the fourth type (classification) are used. When sound data is input, the learning model 24 is capable of outputting a classification of the input sound data (for example, the first type, the second type, the third type, or the fourth type).

[0049] In this modification, instead of the processing program 23A and the threshold table 23B, the storage unit 23 stores a processing program 23C that describes a series of processes to be executed by the signal generating unit 22. For example, the signal generating unit 22 is enabled to execute the series of processes to be executed by the signal generating unit 22 by loading the program 23C.

[0050] Next, a procedure for estimating the stress level of the occupant 100 in the vehicle 1 will be described with reference to Fig. 10. Fig. 10 is a diagram for explaining an example of a procedure for estimating the stress level of the occupant 100 in the vehicle 1.

[0051] Assume that the vehicle 1 is traveling on a road. At this time, the earphone-type device 10 acquires, via the sound collection sensor 15, an electrical signal (sound data 21A) of air vibrations (sound signals) generated in the ear canal 160 due to bone-conduction sound fx. The earphone-type device 10 further acquires, via the acceleration sensor 16, tilt data 21B of the earphone-type device 10 (or the face). The earphone-type device 10 outputs the sound data 21A and tilt data 21B to the control device 20 via the communication unit 11.

[0052] The control device 20 determines whether there is a change in the signal level of the acquired sound data 21A. Specifically, the control device 20 determines whether there is a vibration change in the specific frequency band fa to fb of the acquired sound data 21A (step S201). As a result, if there is a vibration change in the specific frequency band fa to fb (step S201; Y), the control device 20 inputs the sound data 21A to the learning model 24 (step S202). Then, the control device 20 acquires a type classification (e.g., first type, second type, third type, or fourth type) of the input sound data 21A from the learning model 24 (step S203). The control device 20 determines the stress level (step S204) by executing the above-mentioned steps S103, S106, S108, S104, S109, S111, S112, and S113 based on the threshold corresponding to the classification obtained from the learning model 24 and the change in the signal level of the sound data 21A. The display device 30 displays an image including information about the stress level obtained by the determination (step S205).

[0053] In this modification, sound data 21A is input to the learning model 24, and a type of change in the shape or state of the road surface 200 on which the vehicle 1 is traveling is acquired from the learning model 24. Furthermore, the type obtained from the learning model 24 is compared with the change in the signal level of the sound data 21A to determine the stress level of the occupant 100. As a result, even if it is not easy to determine the type from the sound data 21A, the learning model 24 can accurately determine the type.

[0054] [Variation 3-2] In the above-described modification 3-1, the vehicle 1 may further include a face imaging device 40, for example, as shown in FIG. 11 . The face imaging device 40 includes a monocular or binocular camera. The face imaging device 40 is disposed in a position where it can capture an image of the face of the occupant 100. The face imaging device 40 is capable of generating image data including the face of the occupant 100 obtained by imaging, and outputting the image data to the control device 20.

[0055] The signal processing unit 22 may be capable of correcting the stress level obtained by the determination based on, for example, image data obtained by the face imaging device 40. In this case, for example, if there is little change over time in the face of the occupant 100 included in the image data, the signal processing unit 22 may determine that the occupant 100 is not feeling anxious about the surrounding situation and reduce the stress level obtained by the determination by a predetermined amount. Also, for example, if there is a large change over time in the face of the occupant 100 included in the image data, the signal processing unit 22 may determine that the occupant 100 is feeling anxious about the surrounding situation and increase the stress level obtained by the determination by a predetermined amount.

[0056] In this modification, the stress level obtained by the determination is corrected based on image data obtained by the face imaging device 40. This makes it possible to determine the stress level with greater accuracy.

[0057] 4. Second Embodiment [Configuration example] Next, a vehicle 2 according to a second embodiment of the present disclosure will be described. FIG. 12 illustrates an example of functional blocks of the vehicle 2 according to the second embodiment of the present disclosure. The vehicle 2 includes, for example, an earphone-type device 10, a control device 50, and a display device 30, as shown in FIG. 12. The earphone-type device 10 is worn on the earpinna of an occupant 100 of the vehicle 2, as shown in FIG. 13, for example. The display device 30 is fixed to the dashboard of the vehicle 2, for example. The control device 20 corresponds to a specific example of a "stress detection device" according to an embodiment of the present disclosure. The vehicle 2 corresponds to a specific example of a "vehicle" according to an embodiment of the present disclosure. A "stress detection method" according to an embodiment of the present disclosure is executed by the control device 50.

[0058] The control device 50 is capable of processing data (sound data 21A and tilt data 21B) obtained from the earphone type device 10. For example, as shown in FIG. 12 , the control device 50 has a communication unit 51, a signal processing unit 52, a storage unit 53, and learning models 54A, 54B, and 54C. The communication unit 51 is a communication interface capable of communicating with the earphone type device 10. The communication unit 51 is capable of outputting data (sound data 21A and tilt data 21B) input from the earphone type device 10 to the signal processing unit 52. The communication unit 51 is capable of outputting a signal (control signal) for controlling the earphone type device 10, which is input from the signal processing unit 52, to the earphone type device 10.

[0059] The signal processing unit 52 is capable of estimating the cause of the change in the sound data 21A based on the change in the signal level of the sound data 21A and the frequency band of the sound data 21A in which the change occurred. The signal processing unit 52 is capable of estimating the cause of the change in the sound data 21A in a specific frequency band fa to fb, which is the frequency band of the sound signal generated in the ear canal 160 due to the bone conduction sound fx. Here, the "cause of the change in the sound data 21A" refers to, for example, the tongue movement (fifth type) of the occupant 100 of the vehicle 2 and the chewing movement (sixth type) of the occupant 100 of the vehicle 2.

[0060] When the vehicle 2 is traveling or moving slowly on the road surface 200, or when the vehicle 2 is stopped, sound propagates through the head of the occupant 100 to the eardrum 140 as bone-conducted sound fx1, and as a result, air vibrations (sound signals) caused by the bone-conducted sound fx1 are generated in the ear canal 160. At this time, in the sound data 21A obtained by the earphone-type device 10, vibrations caused by the fifth or sixth type appear in the specific frequency bands fa to fb.

[0061] The signal processing unit 52 is capable of determining whether the cause of the change in the sound data 21A is the movement of the mouth of the occupant 100, based on the magnitude of the signal level of the sound data 21A. If the signal processing unit 52 determines that the cause of the change in the sound data 21A is the movement of the mouth of the occupant 100, the signal processing unit 52 is capable of estimating the type (the fifth type or the sixth type) based on the change in the signal level of the sound data 21A. The signal processing unit 52 is further capable of determining the stress level of the occupant 100, based on the estimated type.

[0062] The storage unit 53 is configured by, for example, a rewritable nonvolatile memory such as a flash memory or a resistance change memory. The storage unit 53 stores, for example, a program 53A describing a series of processes to be executed by the signal generation unit 52, and a threshold value 53B. The signal generation unit 52 is able to execute the above-mentioned processes by, for example, loading the program 53A. The threshold value 53B is, for example, a threshold value ΔTh5 that can determine whether or not a movement is occurring inside the mouth of the occupant 100.

[0063] The learning model 54A is a model that has been trained using training sound data and a classification of the movement inside the mouth of the occupant 100 as training data. As the training data, for example, a combination of training sound data corresponding to the fifth type and the fifth type (classification), or a combination of training sound data corresponding to the sixth type and the sixth type (classification) is used. When sound data is input, the learning model 54A is capable of outputting a classification of the input sound data (for example, the fifth type or the sixth type).

[0064] Learning model 54B is a model that has been trained using, as teaching data, learning sound data corresponding to Type 5 and a stress level corresponding to the learning sound data in Type 5. When sound data is input, learning model 54B is capable of outputting a stress level corresponding to the input sound data.

[0065] Learning model 54C is a model trained using training data corresponding to type 6 and stress levels corresponding to the training sound data in type 6. When sound data is input, learning model 54C is capable of outputting a stress level corresponding to the input sound data.

[0066] Display device 30 has, for example, a liquid crystal panel or an organic EL panel. Display device 30 is capable of generating a video signal for displaying a video including information about the stress level obtained by signal processing unit 52, and displaying the video based on the generated video signal.

[0067] [Operation] Next, a procedure for estimating the stress level of the occupant 100 in the vehicle 2 will be described with reference to Fig. 14. Fig. 14 is a diagram for explaining an example of a procedure for estimating the stress level of the occupant 100 in the vehicle 2.

[0068] Assume that the vehicle 2 is traveling or moving slowly on the road surface 200, or is stopped. At this time, the earphone type device 10 acquires, via the sound collection sensor 15, an electrical signal (sound data 21A) of air vibrations (sound signals) generated in the ear canal 160 due to bone-conduction sound fx. The earphone type device 10 further acquires, via the acceleration sensor 16, tilt data 21B of the earphone type device 10 (or the face). The earphone type device 10 outputs the sound data 21A and tilt data 21B to the control device 50 via the communication unit 11.

[0069] The control device 50 determines whether there is a change in the signal level of the acquired sound data 21A. Specifically, the control device 50 determines whether there is a vibration change in the acquired sound data 21A in the specific frequency band fa to fb (step S301). As a result, if there is a vibration change in the specific frequency band fa to fb (step S301; Y), the control device 50 determines whether the signal level of the sound data 21A in the specific frequency band fa to fb exceeds the threshold value ΔTh5 (step S302). As a result, if the signal level of the sound data 21A exceeds the threshold value ΔTh5, the control device 50 inputs the sound data 21A to the learning model 54A, and acquires an estimated result of the classification of the movement inside the mouth of the occupant 100 from the learning model 54A as a response (steps S303 and S304).

[0070] If the estimation result is the fifth type (step S305; Y), the control device 50 inputs the sound data 21A to the learning model 54B and acquires the stress level of the occupant 100 from the learning model 54B as a response (steps S306, S307). On the other hand, if the estimation result is the sixth type (step S305; N, step S308; Y), the control device 50 inputs the sound data 21A to the learning model 54C and acquires the stress level of the occupant 100 from the learning model 54C as a response (steps S309, S310). The display device 30 displays an image including information about the stress level obtained from the learning models 54B and 54C (step S311). If the estimation result is neither the fifth type nor the sixth type (step S308; N), the control device 50 terminates the execution of this series of estimation procedures.

[0071] In this modification, it is determined whether the cause of the change in the sound data 21A is the movement of the mouth of the occupant 100, based on the magnitude of the signal level of the sound data 21A. Furthermore, if it is determined that the cause of the change in the sound data 21A is the movement of the mouth of the occupant 100, a type (fifth type or sixth type) is estimated based on the change in the signal level of the sound data 21A, and the stress level of the occupant 100 is determined based on the estimated type. This makes it possible to determine the stress level according to the cause.

[0072] In this modification, sound data 21A is input to learning model 54A, and a classification of the movement inside the mouth of occupant 100 is obtained from learning model 54A. Furthermore, sound data 21A is input to learning models 54B and 54C, and a stress level according to the type is obtained from learning models 54B and 54C. As a result, even if it is not easy to determine the type from sound data 21A, the type can be determined with high accuracy by learning model 24. Furthermore, even if it is not easy to estimate the stress level from sound data 21A, the stress level can be estimated with high accuracy by learning model 24.

[0073] 5. Modifications of each embodiment Although the present disclosure has been described above using two embodiments, the present disclosure is not limited to these embodiments and various modifications are possible.

[0074] [Variation 5-1] In the first embodiment, the vehicle 1 (control device 20) may have a communication unit 25 capable of communicating with a server device 60, for example, as shown in FIG. 15 . In this case, the processing program 23A and the threshold table 23B are omitted from the storage unit 23, and instead, a processing program 23D is stored in the storage unit 23. The processing program 23D is a program in which a series of procedures to be executed by the signal processing unit 22 are written. In this modification, the signal processing unit 22 is capable of outputting data (sound data 21A and tilt data 21B) input from the earphone-type device 10 to the server device 60 via the communication unit 25.

[0075] 16 shows an example of functional blocks of the server device 60. The server device 60 includes, for example, a communication unit 61, a signal processing unit 62, and a storage unit 63, as shown in FIG.

[0076] The communication unit 61 is a communication interface capable of communicating with the vehicle 1 (control device 20). The communication unit 61 is capable of outputting data received from the vehicle 1 (sound data 21A and tilt data 21B) to the signal processing unit 62. The communication unit 61 is capable of transmitting data acquired from the signal processing unit 62 (for example, a stress level) to the vehicle 1.

[0077] The signal processing unit 62 is capable of executing the series of processes (e.g., steps S101 to S109 and S111 to S113 shown in FIGS. 7 and 8) executed by the signal processing unit 22 of the first embodiment. The storage unit 63 is configured by, for example, a rewritable nonvolatile memory such as a flash memory or a resistance change memory. The storage unit 63 stores, for example, a program 23A describing the series of processes executed by the signal generating unit 62, and a threshold value table 23B. For example, the signal generating unit 62 is capable of executing the above-mentioned processes (e.g., steps S101 to S109 and S111 to S113 shown in FIGS. 7 and 8) by loading the program 23A.

[0078] In this modification, a series of processes (for example, steps S101 to S109 and S111 to S113 shown in FIGS. 7 and 8) executed by the signal processing unit 22 in the first embodiment are executed by the server device 60. This makes it possible to determine the stress level according to the stress-causing factor while reducing the computational load on the vehicle 1.

[0079] [Variation 5-2] In the above-described modification 3-1, the vehicle 1 (control device 20) may have, for example, a communication unit 25 capable of communicating with the server device 70, as shown in FIG. 17 . In this case, the processing program 23A and the threshold table 23B are omitted from the storage unit 23, and instead, a processing program 23D is stored in the storage unit 23. The processing program 23D is a program in which a series of procedures to be executed by the signal processing unit 22 are described. In this modification, the signal processing unit 22 is capable of outputting data (sound data 21A and tilt data 21B) input from the earphone-type device 10 to the server device 70 via the communication unit 25.

[0080] 18 illustrates an example of functional blocks of the server device 70. The server device 70 includes, for example, a communication unit 71, a signal processing unit 72, a storage unit 73, and a learning model 24, as shown in FIG.

[0081] The communication unit 71 is a communication interface capable of communicating with the vehicle 1 (control device 20). The communication unit 71 is capable of outputting data received from the vehicle 1 (sound data 21A and tilt data 21B) to the signal processing unit 72. The communication unit 71 is capable of transmitting data acquired from the signal processing unit 72 (for example, stress level) to the vehicle 1.

[0082] The signal processing unit 72 is capable of executing the series of processes (e.g., steps S101 to S109 and S111 to S113 shown in FIGS. 7 and 8) executed by the signal processing unit 22 of the first embodiment. The storage unit 63 is configured by, for example, a rewritable nonvolatile memory such as a flash memory or a resistance change memory. The storage unit 63 stores, for example, a program 23A describing the series of processes executed by the signal generating unit 62, and a threshold value table 23B. The signal generating unit 62 is capable of executing the above-mentioned processes (e.g., steps S101 to S109 and S111 to S113 shown in FIGS. 7 and 8) by, for example, loading the program 23A.

[0083] In this modification, the series of processes (for example, steps S201 to S204 shown in FIG. 10) executed by the signal processing unit 22 in the modification 3-1 above are executed by the server device 70. This makes it possible to determine the stress level according to the stress-causing factor while reducing the computational load on the vehicle 1.

[0084] [Variation 5-3] In the second embodiment, the vehicle 2 (control device 50) may have a communication unit 54 capable of communicating with a server device 80, for example, as shown in FIG. 19 . In this case, the processing program 53A and the threshold value 53B are omitted from the storage unit 53, and instead, a processing program 53C is stored in the storage unit 53. The processing program 53C is a program in which a series of procedures to be executed by the signal processing unit 52 are written. In this modification, the signal processing unit 52 is capable of outputting data (sound data 21A and tilt data 21B) input from the earphone-type device 10 to the server device 80 via the communication unit 54.

[0085] Fig. 20 illustrates an example of functional blocks of the server device 80. As shown in Fig. 20, the server device 80 includes, for example, a communication unit 81, a signal processing unit 82, a storage unit 83, and learning models 54A, 54B, and 54C.

[0086] The communication unit 81 is a communication interface capable of communicating with the vehicle 2 (control device 50). The communication unit 81 is capable of outputting data (sound data 21A and tilt data 21B) received from the vehicle 2 to the signal processing unit 82. The communication unit 81 is capable of transmitting data (for example, stress level) acquired from the signal processing unit 82 to the vehicle 2.

[0087] The signal processing unit 82 is capable of executing the series of processes (for example, steps S301 to S310 shown in FIG. 14) executed by the signal processing unit 52 of the second embodiment. The storage unit 83 is configured by, for example, a rewritable nonvolatile memory such as a flash memory or a resistance change memory. The storage unit 83 stores, for example, a program 53A describing the series of processes executed by the signal generating unit 82, and a threshold value 53B. The signal generating unit 82 is capable of executing the above-mentioned processes (for example, steps S301 to S310 shown in FIG. 14) by, for example, loading the program 53A.

[0088] In this modification, the series of processes (for example, steps S301 to S310 shown in FIG. 14) executed by the signal processing unit 52 in the second embodiment are executed by the server device 80. This makes it possible to determine the stress level according to the stress-causing factor while reducing the computational load on the vehicle 2.

[0089] [Variation 5-4] In the first embodiment and its modified example, the control device 20 may further include the components included in the control device 50 in the second embodiment and its modified example (for example, the signal processing unit 52, the storage unit 53, and the learning models 54A, 54B, and 54C). In this case, it is possible to determine not only the stress level caused by a change in the shape or condition of the road surface 200, but also the stress level caused by the surrounding situation or condition that causes the occupant 100 to move inside the mouth.

[0090] The effects described in this specification are merely examples, and the effects of the present disclosure are not limited to the effects described in this specification. Therefore, other effects may be obtained with respect to the present disclosure.

[0091] Furthermore, the present disclosure may take the following aspects. (1) a sensor capable of detecting sound in the ear canal of a driver of the vehicle; a processing unit capable of processing sound data obtained by sound detection by the sensor; Equipped with The processing unit estimating a factor that caused a change in the sound data based on at least one of the magnitude and change in the signal level of the sound data and the frequency band in the sound data where the change occurred; The stress level of the driver can be determined based on the factors and the change in the signal level of the sound data. Stress detection device. (2) The processing unit is capable of estimating the cause in a specific frequency band of the sound data, which is a frequency band of sound generated in the ear canal due to bone conduction sound. (1) A stress detection device according to (1). (3) The processing unit determines whether the cause is the movement of the driver's mouth based on the magnitude of the signal level of the sound data, and if it determines that the cause is the movement of the driver's mouth, it estimates the tongue movement or chewing movement of the driver based on the change in the signal level of the sound data, and is able to determine the stress level of the driver based on the estimated movement. (2) A stress detection device according to the present invention. (4) The processing unit determines whether the cause is a change in the shape or condition of the road surface on which the vehicle is traveling, based on the frequency band in the sound data that has changed. If it determines that the cause is a change in the shape or condition of the road surface on which the vehicle is traveling, the processing unit estimates the type of change in the shape or condition of the road surface on which the vehicle is traveling, based on the change in the signal level of the sound data, and compares the change in the signal level of the sound data with a threshold value corresponding to the type, thereby making it possible to determine the stress level of the driver. (2) A stress detection device according to the present invention. (5) The processing unit is capable of determining that the stress level of the driver is high when a change in the signal level of the sound data exceeds a first threshold value, or when a period in which the change in the signal level of the sound data exceeds a second threshold value that is smaller than the first threshold value continues for a predetermined period of time. (4) A stress detection device according to (4). (6) The processing unit is capable of determining that the stress level of the driver is high when a change in the signal level of the sound data falls below a third threshold. (4) A stress detection device according to (4). (7) The processing unit inputs the sound data to a learning model that has been trained using learning sound data and classifications of changes in the shape or condition of the road surface as teaching data, thereby acquiring from the learning model a type of change in the shape or condition of the road surface on which the vehicle is traveling, and is capable of determining the driver's stress level based on a threshold value corresponding to the type and changes in the signal level of the sound data. (4) A stress detection device according to (4). (8) A vehicle equipped with a stress detection device, The stress detection device a sensor capable of detecting sound in the ear canal of a driver of the vehicle; a processing unit capable of processing sound data obtained by sound detection by the sensor; and The processing unit estimating a factor that caused a change in the sound data based on at least one of the magnitude and change in the signal level of the sound data and the frequency band in the sound data where the change occurred; The stress level of the driver can be determined based on the factors and the change in the signal level of the sound data. vehicle. (9) Acquiring sound data obtained by detecting sound in the ear canal of a vehicle driver with a sensor; estimating a factor that caused a change in the sound data based on at least one of the magnitude and change of the signal level of the sound data and a frequency band in the sound data where a change occurred; determining a stress level of the driver based on the factors and a change in the signal level of the sound data; Contains Stress detection method.

[0092] The signal processing unit 12 shown in Figure 2, the signal processing unit 22 shown in Figures 3, 9, 11, 15, and 17, the signal processing unit 52 shown in Figures 12 and 19, the signal processing unit 62 shown in Figure 16, the signal processing unit 72 shown in Figure 18, and the signal processing unit 82 shown in Figure 20 can be implemented by circuitry including at least one semiconductor integrated circuit, such as at least one processor (e.g., a central processing unit (CPU)), at least one application specific integrated circuit (ASIC), and / or at least one field programmable gate array (FPGA). The at least one processor can be configured to perform all or part of the various functions of the signal processing unit 12 shown in Figure 2, the signal processing unit 22 shown in Figures 3, 9, 11, 15, and 17, the signal processing unit 52 shown in Figures 12 and 19, the signal processing unit 62 shown in Figure 16, the signal processing unit 72 shown in Figure 18, and the signal processing unit 82 shown in Figure 20 by reading instructions from at least one non-transitory, tangible computer-readable medium. Such media may take various forms, including, but not limited to, various magnetic media such as hard disks, various optical media such as CDs or DVDs, and various semiconductor memories (i.e., semiconductor circuits) such as volatile or nonvolatile memory. Volatile memory may include DRAM and SRAM. Nonvolatile memory may include ROM and NVRAM. The ASIC is an integrated circuit (IC) specialized to perform all or part of the various functions of signal processing unit 12 shown in FIG. 2, signal processing unit 22 shown in FIGS. 3, 9, 11, 15, and 17, signal processing unit 52 shown in FIGS. 12 and 19, signal processing unit 62 shown in FIG. 16, signal processing unit 72 shown in FIG. 18, and signal processing unit 82 shown in FIG. 20. The FPGA is an integrated circuit designed to be configurable after manufacture so as to perform all or part of the various functions of the signal processing unit 12 shown in FIG. 2, the signal processing unit 22 shown in FIGS. 3, 9, 11, 15, and 17, the signal processing unit 52 shown in FIGS. 12 and 19, the signal processing unit 62 shown in FIG. 16, the signal processing unit 72 shown in FIG. 18, and the signal processing unit 82 shown in FIG. 20. [Explanation of symbols]

[0093] 1, 2...vehicle, 10...earphone-type device, 11...communication unit, 12...signal processing unit, 13...vibrator, 14...vibration unit, 15...sound collection sensor, 16...acceleration sensor, 20...control device, 21, 25...communication unit, 22...signal processing unit, 23...memory unit, 23A, 23C, 23D...processing program, 23B...threshold value table, 24, 54A, 54B, 54C...learning model, 30...display device, 40...face imaging device, 50...control device, 51...communication unit, 52...signal processing unit, 53...memory unit, 53A, 53C... Processing program, 53B... threshold, 54A, 54B, 54C... learning model, 60, 70, 80... server device, 61, 71, 81... communication unit, 62, 72, 82... signal processing unit, 63, 73, 83... memory unit, 100... occupant, 110... cochlea, 120... auditory nerve, 130... ossicles, 140... eardrum, 150... pinna, 160... external auditory canal, 170... temporal bone, 200... road surface, fx... bone conduction sound, fa, fb, f1, f2, f3, f4, f5, f6, f7... frequency, ΔTh1, ΔTh2, ΔTh3, ΔTh4.

Claims

1. a sensor capable of detecting sound in the ear canal of a driver of the vehicle; a processing unit capable of processing sound data obtained by sound detection by the sensor; Equipped with The processing unit estimating a factor that caused a change in the sound data based on at least one of the magnitude and change in the signal level of the sound data and the frequency band in the sound data where the change occurred; The stress level of the driver can be determined based on the factors and the change in the signal level of the sound data. Stress detection device.

2. The processing unit is capable of estimating the cause in a specific frequency band of the sound data, which is a frequency band of sound generated in the ear canal due to bone conduction sound. The stress detection device according to claim 1 .

3. The processing unit determines whether the cause is the movement of the driver's mouth based on the magnitude of the signal level of the sound data, and if it determines that the cause is the movement of the driver's mouth, it estimates the tongue movement or chewing movement of the driver based on the change in the signal level of the sound data, and is able to determine the stress level of the driver based on the estimated movement. The stress detection device according to claim 2 .

4. The processing unit determines whether the cause is a change in the shape or condition of the road surface on which the vehicle is traveling, based on the frequency band in the sound data that has changed. If it determines that the cause is a change in the shape or condition of the road surface on which the vehicle is traveling, the processing unit estimates the type of change in the shape or condition of the road surface on which the vehicle is traveling, based on the change in the signal level of the sound data, and compares the change in the signal level of the sound data with a threshold value corresponding to the type, thereby making it possible to determine the stress level of the driver. The stress detection device according to claim 2 .

5. Acquiring sound data obtained by detecting sound in the ear canal of a vehicle driver with a sensor; estimating a factor that caused a change in the sound data based on at least one of the magnitude and change of the signal level of the sound data and a frequency band in the sound data where a change occurred; determining a stress level of the driver based on the factors and a change in the signal level of the sound data; Contains Stress detection method.

Images