JP2008301957A - Mental state inference device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To infer a mental state of a subject highly precisely. <P>SOLUTION: An irritation inference device 1 for inferring irritation of a driver is provided with: a biological information detecting means 15 for acquiring biological information about the driver; an environmental factor determining means 14 for determining generation of an environmental factor which can change the driver's mental state; a correlation determining means 16 for deriving a correlation between the generated environmental factor and the biological information acquired by the biological information detecting means 15; and an emotional state determining means 17 for inferring an irritation state of the driver on the basis of the correlation derived by the correlation determining means 16. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a psychological state estimation device for estimating a psychological state of a subject such as an irritated state.

In order to improve safety during driving, various devices for estimating a driver's psychological state such as an irritated state have been proposed. For example, Patent Document 1 discloses a biological information display device that detects biological information such as a heart rate and blood pressure of a subject and determines an irritated state based on the magnitude relationship between the detected biological information and a preset threshold value. Yes.
JP 2006-34803 A JP 2003-48448 A JP 2003-244758 A JP-A-2005-157762

  Since the apparatus described in Patent Document 1 determines an irritated state based on a numerical standard (threshold value) set in advance, an optimal result cannot be obtained for the individual subject. This is the same even if the numerical standard is set for everyone. For example, since the average value and the amount of change in heart rate and blood pressure vary greatly from person to person, setting a generalized value on the basis of a numerical value decreases the accuracy of determination of an irritated state.

  In addition, the biological information display device described in Patent Document 1 determines the psychological state of the subject based on the fact that when the subject is in an irritated state, the blood pressure of the subject increases and the heart rate increases. At this time, the biometric information display device is divided into two categories of “irritated” and “not frustrated” for an irritated state, three categories of rising, maintaining and decreasing for blood pressure, and increasing, maintaining and decreasing for heart rate. Three categories are set in advance, and the biological information and psychological state of the subject are applied to these categories. However, it is not possible to divide the subject's frustrated state in detail only by using such a method.

Then, this invention makes it a subject to provide the psychological state estimation apparatus which estimates a test subject's psychological state with high precision.

  The psychological state estimation device according to the present invention is a psychological state estimation device that estimates a subject's psychological state, and a biometric information acquisition unit that acquires biometric information of the subject and generation of environmental factors that can change the psychological state of the subject The environmental factor determination means for determining the correlation, and when the occurrence of the environmental factor is determined by the environmental factor determination means, the correlation for deriving the correlation between the generated environmental factor and the biological information acquired by the biological information acquisition means And a deriving unit and an estimating unit that estimates the psychological state of the subject based on the correlation derived by the correlation deriving unit.

  In this psychological state estimation device, first, the biological information of the subject and the occurrence of environmental factors that can change the psychological state of the subject are detected, and the correlation between these biological information and the environmental factors is derived. Then, the psychological state of the subject is estimated based on the derived correlation. Therefore, taking into account the occurrence of an environmental factor, the psychological state of the subject is estimated after considering the influence of the environmental factor on the subject's physiological information. That is, when estimating the psychological state, it is possible to incorporate biological information indicating the characteristics of the subject individual into the estimation, and as a result, the psychological state of the subject can be estimated with high accuracy. The environmental factor is an event that changes the emotional state of the driver, such as traffic jam or horn.

  The psychological state estimation apparatus of the present invention further includes storage means for storing psychological change data indicating changes in the psychological state of the subject according to environmental factors, and the environmental factor determining means is information for determining the occurrence of environmental factors. The psychological change data corresponding to the environmental factor is acquired from the storage means based on the psychological change data and the biological information corresponding to the environmental factor based on the psychological change data acquired by the environmental factor determining means. Is preferably derived.

  In this case, the correlation between environmental factors and biological information is derived based on pre-stored psychological change data. By using the correlation derivation data in this way, it is possible to suppress derivation fluctuations and more reliably estimate the subject's psychological state.

  The psychological state estimation apparatus according to the present invention further includes a learning unit that learns a change in the psychological state of the subject according to the environmental factor, and the environmental factor determination unit is configured based on the information for determining the occurrence of the environmental factor. The learning result of the learning means according to the condition is acquired, and the correlation derivation means derives the correlation between the learning result according to the environmental factor and the biological information based on the learning result acquired by the environmental factor determination means. Is preferred.

  In this case, the psychological state of the subject is learned, and the correlation between the environmental factor and the biological information is derived based on the learning result. As a result, the characteristics of the individual subject can be more accurately reflected in the derivation of the correlation, and as a result, the psychological state of the subject can be estimated with higher accuracy.

  In the psychological state estimation apparatus of the present invention, it is preferable that the correlation deriving unit derives the correlation using a parameter indicating a time related to the derivation of the correlation, which is determined based on the generated environmental factor.

  In this case, since the correlation is derived using the parameter indicating the time related to the derivation of the correlation determined for each environmental factor, the correlation can be derived in detail for each environmental factor. As a result, the psychological state of the subject can be estimated with higher accuracy.

  In the psychological state estimation apparatus of the present invention, the parameter is preferably a time interval necessary for deriving the correlation.

  In this case, the correlation is derived using a time interval necessary for deriving the correlation. The time required for deriving the correlation may differ for each environmental factor. For example, there are environmental factors that can derive the correlation instantaneously, and other environmental factors that cannot derive the correlation unless a relatively long time is used. Therefore, the correlation can be derived in detail for each environmental factor by using the time interval necessary for derivation of the correlation, and as a result, the psychological state of the subject can be estimated with higher accuracy.

  In the psychological state estimation device according to the present invention, the parameter is preferably a start time indicating a start timing of derivation of the correlation.

  In this case, the correlation is derived using the start time indicating the start timing of the correlation derivation. The timing for starting the derivation of the correlation may be different for each environmental factor. For example, some environmental factors are preferable to start derivation immediately, while other environmental factors are preferable to start derivation after some time. Accordingly, the correlation can be derived in detail for each environmental factor by using the start time indicating the derivation start timing, and as a result, the psychological state of the subject can be estimated with higher accuracy.

  In the psychological state estimation apparatus of the present invention, the parameter is preferably an end time indicating an end timing of derivation of the correlation.

  In this case, the correlation is derived using the end time indicating the end timing of the correlation derivation. The timing at which the derivation of the correlation is terminated may be different for each environmental factor. For example, there are environmental factors that may terminate the derivation immediately, and other environmental factors that preferably cease derivation after a relatively long time. Accordingly, the correlation can be derived in detail for each environmental factor by using the end time indicating the end timing of the derivation, and as a result, the psychological state of the subject can be estimated with higher accuracy.

  Since the present invention uses a correlation based on the biological information of the subject and environmental factors that can change the subject's psychological state when estimating the psychological state of the subject, the psychological state of the subject can be estimated with high accuracy.

  Hereinafter, an embodiment of a psychological state estimation device according to the present invention will be described with reference to the drawings.

  In this Embodiment, the psychological state estimation apparatus which concerns on this invention is mounted in a vehicle, and is applied to the frustration estimation apparatus which estimates a driver | operator's frustration state. The frustration estimation apparatus according to the present invention acquires a correlation between psychological change data set for each environmental factor that affects a driver's frustration state and the driver's biological information, and drives based on the acquired correlation. The person's frustration. And this irritation estimation device provides the estimated irritation state to other devices (not shown) such as a driver support device, an alarm device, and an irritation mitigation device.

  The frustration estimation apparatus 1 is demonstrated with reference to FIGS. FIG. 1 is a diagram illustrating a configuration of the frustration estimation apparatus 1 according to the present embodiment. 2-5 is a figure which shows the example of the psychological change data memorize | stored in the reference data memory | storage device 13 shown in FIG. 1, respectively, When a horn is sounded from another vehicle, When a driver sounds a horn In the case of interruption, etc., it indicates the case of traffic jam. 6 and 7 are diagrams showing examples of derivation of the correlation between the psychological change data and the biological information. FIG. 8 is a graph illustrating an example of a relational expression indicating a correlation between psychological change data and biological information. FIG. 9 is a diagram illustrating another example of derivation of the correlation between psychological change data and biological information. FIG. 10 is a graph showing another example of a relational expression indicating a correlation between psychological change data and biological information.

  The frustrated estimation device 1 estimates the frustrated level based on the biological information indicating the frustrated state and external environmental factors that affect the frustrated state. In particular, the frustration estimation device 1 estimates the frustration level using the correlation between the psychological change data set for each environmental factor and the driver's biological information in order to improve the estimation accuracy. For this reason, the frustration estimation device 1 includes vehicle information detection means 11, environmental information detection means 12, reference data storage device 13, environmental factor determination means 14, biological information detection means 15, correlation determination means 16, and emotional state determination means 17. It has. In particular, the reference data storage device 13, the environmental factor determination unit 14, the correlation determination unit 16, and the emotional state determination unit 17 are mounted on an ECU (Electronic Control Unit) of the frustration estimation device 1.

  In the present embodiment, the reference data storage device 13 corresponds to the storage means described in the claims, the environmental factor determination means 14 corresponds to the environmental factor determination means described in the claims, and the biological information The detection means 15 corresponds to the biological information acquisition means described in the claims, the correlation determination means 16 corresponds to the correlation derivation means described in the claims, and the emotional state determination means 17 corresponds to the claims. It corresponds to the estimation means described.

  The vehicle information detection means 11 is a means for detecting information on the vehicle side for inferring that an environmental factor affecting a frustrating state such as a traffic jam or an interruption has occurred. For example, the vehicle information detection means 11 includes a vehicle speed sensor for detecting the vehicle speed, a brake sensor for detecting depression of the brake, a pressure sensor for detecting that the horn is pressed, and a steering angle for detecting the steering operation. Consists of sensors. Information detected by the vehicle information detection means 11 in this case is, for example, vehicle speed information detected by a vehicle speed sensor, pedaling force information detected by a brake sensor, pressure information detected by a pressure sensor, and a steering angle sensor. Steering angle information. In addition, the structure of the vehicle information detection means 11 is not limited, For example, you may comprise only a vehicle speed sensor and a brake sensor, and you may comprise using components other than the sensor mentioned above. Further, the type of information detected by the vehicle information detection means 11 is not limited.

  The environmental information detection means 12 is a means for detecting environmental information for estimating that an environmental factor affecting a frustrating state such as a traffic jam or an interruption has occurred. For example, the environment information detection unit 12 includes a map database and obtains VICS information (congestion information, etc.), a radar device for detecting a distance between vehicles, a camera for capturing a front image, and a horn sound of another vehicle. It consists of a sound sensor. Information detected by the vehicle information detection means 11 in this case includes, for example, position information and traffic information detected by a navigation device, inter-vehicle distance information detected by a radar sensor, image information acquired by a camera, and a sound sensor. Sound information to be detected can be mentioned. The configuration of the environment information detection unit 12 is not limited, and may be configured with only a navigation device, for example, or may be configured using components other than the above-described devices. Further, the type of information detected by the environment information detection unit 12 is not limited.

  The reference data storage device 13 is means for storing psychological change data indicating changes in the driver's frustration level according to environmental factors. Psychological change data is set based on experimental results and is shown by characteristic curves as shown in FIGS. In each graph of FIGS. 2-5, the vertical axis | shaft has shown the irritation level and the horizontal axis has each shown time. Further, time t in these graphs indicates the occurrence time of the environmental factor, and times t1 and t2 indicate the reference start time and reference end time of the psychological change data necessary for estimating the frustration level, respectively. These times t, t1, and t2 are components of psychological change data, and are set in advance for each environmental factor.

  The frustration level is an index indicating the frustration state of the driver, and a larger value indicates that the driver is more frustrated. In addition, the setting method of an irritated level is not limited. For example, when the irritability level is “0” indicating a calm state, “1” which is a stuffy state, “2” which is enduring anger and is in a state of immediate touch, and a state where anger is expelled There may be four types of “3”. Moreover, you may express an irritated state with the arbitrary real numbers of 0-3.

  The change in the driver's psychological state when a horn is sounded from another vehicle is shown by a characteristic curve as shown in FIG. 2, for example. Occurrence time t indicates when the horn is sounded. When the driver is honed from another vehicle, a surprising reaction occurs to the driver immediately thereafter, and then the driver's frustration level gradually increases. Surprising reactions can be handled in the same way as frustrating conditions. In order to characterize such a change in psychological state, the reference start time t1 is set relatively shortly before the occurrence time t, and the reference end time t2 is set relatively long after the occurrence time t. The psychological change data indicated by the characteristic curve in FIG. 2 is stored in the reference data storage device 13 in association with information indicating the horn sound (for example, amplitude and frequency).

  The change in the driver's psychological state when the driver rings the horn with respect to the other vehicle is shown by a characteristic curve as shown in FIG. 3, for example. Occurrence time t indicates the time when the driver rings the horn. As shown in FIG. 3, the driver's frustration level continues to rise before the driver rings the horn, and the frustration level gradually decreases from the moment the driver rings the horn. This is based on the idea that the high frustration level causes the act of sounding a horn, and the irritated state is gradually eliminated by the catharsis effect caused by sounding the horn. In order to characterize such changes in the psychological state, the interval between the reference start time t1 and the occurrence time t, and the occurrence time t and the reference end time t2 are relatively large. The psychological change data indicated by the characteristic curve of FIG. 3 is stored in the reference data storage device 13 in association with information indicating the operation of the horn (for example, the operation duration time, the number of operations within a predetermined time).

  A change in the driver's psychological state when the host vehicle is suddenly interrupted by another vehicle or the distance between the vehicle and the preceding vehicle is suddenly reduced is shown by a characteristic curve as shown in FIG. 4, for example. Occurrence time t indicates when a sudden interruption or a sudden decrease in the inter-vehicle distance occurs. In this case, the frustration level rises rapidly in a short time, and then the frustration level maintains the value after the rise or gradually decreases. In order to characterize such a change in psychological state, the reference start time t1 is set relatively shortly before the occurrence time t, and the reference end time t2 is set relatively long after the occurrence time t. The reference time (t2-t1) is set relatively short.

  The change in the driver's psychological state when the driver encounters a traffic jam is shown by a characteristic curve as shown in FIG. 5, for example. The occurrence time t indicates when the driver encounters a traffic jam. In this case, the driver's frustration level continues to rise immediately before the driver encounters a traffic jam. In order to characterize such changes in the psychological state, the interval between the reference start time t1 and the occurrence time t, and the occurrence time t and the reference end time t2 are relatively large. The reference time (t2-t1) is set relatively long.

  The types of psychological change data stored in the reference data storage device 13 are not limited to the above four types.

  The environmental factor determination means 14 is a means for determining the occurrence of environmental factors that can change the driver's frustration level. Here, the environmental factor is an event that changes the emotional state of the driver, such as traffic jam or horn. The environmental factors to be judged by the environmental factor judging means 14 are highly related to changes in the driver's frustrating state, such as threats to other vehicles due to horns.

  Specifically, the environmental factor determination unit 14 responds to the environmental factor from the reference data storage device 13 based on the vehicle information detected by the vehicle information detection unit 11 and the environmental information detected by the environmental information detection unit 12. Obtain psychological change data. That is, vehicle information and environmental information are information for determining the occurrence of environmental factors. Subsequently, the environmental factor determination means 14 stores the occurrence time (actual occurrence time) T of the generated environmental factor, and based on the occurrence time T and the acquired psychological change data, the actual factor corresponding to the reference start time t1. An actual reference end time T2 corresponding to the reference start time T1 and the reference end time t2 is calculated. Subsequently, the environmental factor determination unit 14 outputs the acquired psychological change data, the stored actual occurrence time T, and the calculated actual reference start time T1 and actual reference end time T2 to the correlation determination unit 16.

  Below, the process of the environmental factor determination means 14 is demonstrated using some examples. First, a case where a horn is sounded from another vehicle will be described. In this case, the environmental factor determination unit 14 first acquires the amplitude and frequency of the waveform component indicated by the sound information input from the environmental information detection unit 12. Subsequently, the environmental factor determination unit 14 determines whether or not the acquired amplitude and frequency satisfy a preset reference value, and determines that a horn has been sounded when the reference value is satisfied. Subsequently, the environmental factor determination unit 14 acquires psychological change data (for example, psychological change data illustrated in FIG. 2) corresponding to the acquired amplitude and frequency from the reference data storage device 13. In addition, the acquisition method of the psychological change data based on sound information is not limited. For example, the psychological change data shown in FIG. 2 is stored in the reference data storage device 13 in association with the duration of the horn sound, and the psychological change data corresponding to the horn sound duration derived from the input sound information is acquired. The environmental factor determination means 14 may be configured to do so.

  Next, processing when the driver rings a horn for another vehicle will be described. In this case, the environmental factor determination unit 14 acquires the operation time of the horn from the pressure information input from the vehicle information detection unit 11. Subsequently, the environmental factor determination unit 14 acquires psychological change data (for example, psychological change data shown in FIG. 3) corresponding to the acquired operation time from the reference data storage device 13. In addition, the acquisition method of psychological change data based on pressure information is not limited. For example, the environmental factor determination means 14 may acquire the number of horn activations within a predetermined time from the input pressure information, and may acquire psychological change data corresponding to the number of activations. Also, the psychological change data shown in FIG. 3 is stored in the reference data storage device 13 in association with the pressure, and the environmental factor determination means so as to acquire the psychological change data corresponding to the pressure derived from the input pressure information. 14 may be configured.

  Next, processing when an interruption by another vehicle or a sudden decrease in the inter-vehicle distance occurs will be described. In this case, the environmental factor determination means 14 is based on the vehicle speed information and the pedal effort information input from the vehicle information detection means 11 and the inter-vehicle distance information input from the environmental information detection means 12. It is determined whether or not a significant decrease has occurred. For example, when the distance between the vehicles is equal to or less than a preset reference value and the amount of decrease in the vehicle speed during a predetermined time is equal to or greater than the predetermined reference value, the environmental factor determination unit 14 interrupts another vehicle or suddenly increases the distance between the vehicles. It is determined that a significant decrease has occurred. Further, the environmental factor determination means 14 may determine that an interruption or the like has occurred when the inter-vehicle distance is equal to or less than a preset reference value and the amount of increase in treading force during a predetermined time is equal to or greater than a predetermined reference value. Good. The reference value of the inter-vehicle distance may be constant or may be a value that changes based on the vehicle speed.

  Subsequently, the environmental factor determination means 14 uses the psychological change data (for example, the psychological change data shown in FIG. 4) as reference data based on one or more information among the acquired inter-vehicle distance, the change amount of the vehicle speed, and the change amount of the brake pedal force. Obtained from the storage device 13.

  Next, a process when the own vehicle is involved in a traffic jam or the traffic jam is resolved will be described. In this case, the environmental factor determination unit 14 first determines whether or not the host vehicle is involved in a traffic jam based on the vehicle speed information and the pedal effort information input from the vehicle information detection unit 11. For example, the environmental factor determination means 14 causes the host vehicle to be involved in a traffic jam when the vehicle speed indicated by the vehicle speed information is within a preset reference range and satisfies a traffic jam condition that the state has continued for a certain period of time. It is determined that Apart from this, the environmental factor determination means 14 may set as a traffic jam condition that the pedaling force indicated by the pedaling force information exceeds the set reference value by a predetermined number of times within a predetermined time set in advance. Good. Moreover, the environmental factor determination means 14 may set as a traffic jam condition that both the vehicle speed information and the pedaling force information are satisfied.

  Furthermore, the environmental factor determination means 14 can also determine whether or not the traffic jam has been resolved. Specifically, the environmental factor determination means 14 continues to determine whether or not the host vehicle satisfies the traffic jam condition even after the time when the host vehicle is determined to have been involved in the traffic jam, and no longer satisfies the traffic jam condition. It is determined that the traffic jam has been resolved. When the environmental factor determination unit 14 determines that a traffic jam has been encountered, the environmental factor determination unit 14 holds the time from the determination time (the traffic jam encounter time) to the current time as a duration. In addition, when the environmental factor determination unit 14 determines that the traffic jam has been resolved, the environmental factor determination unit 14 holds the time from the traffic jam encounter time to the traffic jam resolution time as the continuous time, and the time from the traffic jam resolution time to the current time as the elapsed time. Hold.

  Subsequently, the environmental factor determination unit 14 acquires psychological change data (for example, psychological change data shown in FIG. 5) from the reference data storage device 13 based on the held duration. The environmental factor determination unit 14 may acquire psychological change data based on the elapsed time. The environmental factor determination unit 14 may use the VICS information input from the environmental information detection unit 12 in order to determine whether a traffic jam has occurred or whether the traffic jam has been resolved. Also in this case, the environmental factor determination unit 14 calculates and holds the duration time and the elapsed time, and acquires psychological change data based on these information.

  The biological information detection means 15 is a means for acquiring the driver's biological information. Specifically, the biological information detection means 15 includes a skin potential sensor, a heart rate sensor (which may be an electrocardiographic sensor), a blood pressure sensor, an electroencephalogram sensor, and the like. As biological information, the heart rate, blood pressure, skin surface temperature, skin Detect electrical resistance, brain waves, etc. The biological information detection unit 15 outputs the detected biological information to the correlation determination unit 16 and the emotion state determination unit 17.

  When the environmental factor determination unit 14 determines the occurrence of an environmental factor, the correlation determination unit 16 acquires psychological change data (change in frustration level) corresponding to the generated environmental factor and the biological information detection unit 15 It is a means for deriving a correlation with biological information. In other words, the correlation determination unit 16 derives a correlation between environmental factors and biological information. Specifically, the correlation determination unit 16 first sets the measurement time based on the actual reference start time T1 and the actual reference end time T2 input from the environmental factor determination unit 14. This measurement time is represented by T2-T1. Subsequently, the environmental factor determination unit 14 acquires biological information such as heartbeat, blood pressure, skin surface temperature, skin electrical resistance, and electroencephalogram detected by the biological information detection unit 15 during the measurement time.

  Subsequently, the correlation determination unit derives a relational expression indicating a correlation between the psychological change data input from the environmental factor determination unit 14 and the acquired biological information, and outputs the derived relational expression to the emotional state determination unit 17. . That is, the correlation determination unit 16 has three types of parameters: an actual reference start time indicating the start timing of the derivation of the correlation, an actual reference end time indicating the end timing of the derivation, and a measurement time required for derivation of the correlation. Is used to derive the correlation. That is, the actual reference start time, the actual reference end time, and the measurement time are parameters indicating the time related to the correlation derivation. The correlation determination unit 16 updates the relational expression between the psychological change data and the biological information at a predetermined time interval, and outputs the updated relational expression to the emotional state determination unit 17.

  An example in which the correlation determination unit 16 derives a relational expression will be described with reference to FIGS. In this example, the psychological change data D (data similar to that shown in FIG. 4) extracted when it is determined that an interruption has occurred is input to the correlation determination means 16. At this time, the correlation determination means 16 is the biological information from the actual reference start time T1 corresponding to the reference start time t1 of the psychological change data D to the actual reference end time T2 corresponding to the reference end time t2 (section I). Is obtained and labeled as biological information B1. Subsequently, the correlation determination unit 16 calculates the correlation between the labeled biological information B and the psychological change data D, and derives a relational expression indicating the relationship between the biological information and the frustration level. The correlation determination means 16 derives a relational expression (regression expression) by using, for example, regression analysis.

  For example, the psychological change data D (irritated level) and the biological information B1 (blood pressure) shown in FIG. 6 have a certain degree of correlation as shown in FIG. Then, by performing regression analysis, it is understood that the psychological change data D (irritated level) and the biological information B1 (blood pressure) are in a proportional relationship as shown by the straight line L1 in FIG. In the graph of FIG. 8, the vertical axis indicates the frustrated level, and the horizontal axis indicates the blood pressure. The correlation determination unit 16 outputs the relational expression indicated by the straight line L to the emotional state determination unit 17. Note that a broken line L ′ in FIG. 8 is a determination formula (threshold value) used for the conventional determination method shown for comparison.

  Examples of derivation for another driver are shown in FIGS. Also in this case, there is a certain degree of correlation between the psychological change data D (irritated level) and the biological information B2 (blood pressure), and a proportional relationship as shown by the straight line L2 in FIG. 10 is derived by regression analysis. . In FIG. 10, a broken line L ′ is also shown for comparison. As can be seen from FIGS. 6 and 9, the average blood pressure and the variation in blood pressure are different for each driver, but the relational expression derived by the correlation determining means 16 (relational expression indicated by the straight line L1 or L2) is also: It is derived for each individual reflecting such a difference in blood pressure.

  The correlation determination unit 16 may label the biological information in the section indicating the normal state. Further, the method used by the correlation determination unit 16 to calculate the correlation between the psychological change data and the biological information is not limited to regression analysis. Furthermore, the relational expression output from the correlation determining unit 16 to the emotional state determining unit 17 is not limited to a linear function as indicated by the straight lines L1 and L2, but can be defined by an arbitrary function such as a quadratic function. is there.

  The emotional state determination unit 17 is a unit that estimates the driver's frustration based on the correlation determined by the correlation determination unit 16. Specifically, the emotional state determining unit 17 determines the driver's frustrated state based on the relational expression input from the correlation determining unit 16 and the biological information detected by the biological information detecting unit 15. And the emotional state determination means 17 outputs a determination result to other apparatuses (not shown), such as an irritation mitigation apparatus. Thereby, control according to a driver | operator's irritation state is performed in the other apparatus which is not illustrated.

  For example, when the relational expression shown in FIG. 8 is input and the blood pressure Bx is detected by the biological information detection unit 15, the emotional state determination unit 17 determines that the driver's frustration level is 1.5. When the blood pressure By is detected by the biological information detection unit 15, the emotional state determination unit 17 determines that the driver's frustration level is 2. The emotional state determination means 17 may set the value derived using the relational expression as shown in FIG. 8 as it is as an irritated level, or a value obtained by truncating or rounding off the derived value. May be set as For example, the emotional state determination unit 17 may determine that the frustration level for the blood pressure Bx shown in FIG.

  Next, with reference to FIG. 11, the process of the frustration estimation apparatus 1 is demonstrated. FIG. 11 is a flowchart showing processing of the frustration estimation apparatus 1 shown in FIG.

  The vehicle information detection means 11 always detects vehicle information such as the vehicle speed and the depression of the brake (step S11). In addition, the environmental information detection means 12 always detects environmental information such as the inter-vehicle distance, position information, and traffic information (step S12). Further, the biological information detection means 15 always detects biological information such as heart rate, blood pressure, skin surface temperature (step S13).

  Subsequently, the environmental factor determination means 14 determines an environmental factor based on the detected vehicle information and environmental information (step S14). Specifically, the environmental factor determination means 14 acquires psychological change data corresponding to the environmental factor from the reference data storage device 13 based on the vehicle information and the environmental information, and the occurrence time (actual occurrence time) of the generated environmental factor. ) Is memorized. Then, the environmental factor determination unit 14 calculates an actual reference start time and an actual reference end time based on the psychological data and the actual occurrence time.

  Subsequently, the correlation determining unit 16 derives a correlation between the psychological change data corresponding to the environmental factor and the detected biological information (step S15). Specifically, the environmental factor determination unit 14 derives a relational expression indicating the correlation between the biological information detected at the measurement time determined by the actual reference start time and the actual reference end time and the psychological change data.

  Subsequently, the emotional state determination unit 17 estimates an irritated state based on the derived correlation (relational expression) and the detected biological information (step S16), and then the emotional state determination unit 17 obtains the estimation result. Output to another device (not shown). Thereby, control based on the frustrated state estimated in the other apparatus is performed.

  As described above, according to the frustration estimation device 1 of the present embodiment, when estimating the frustration state of the driver, it is possible to incorporate biometric information indicating the characteristics of the individual driver into the estimation. As a result, the driver's frustrated state can be estimated with high accuracy. Specifically, as shown in FIGS. 8 and 10, by deriving a different relational expression for each driver, it is possible to accurately determine the frustrated state in consideration of individual characteristics of the driver. For example, if the driver's blood pressure corresponding to the relational expression in FIG. 8 is b12, the driver's frustration level is determined to be 2, but the driver's blood pressure corresponding to the relational expression in FIG. In this case, it is determined that the driver's frustration level is less than 1.

  On the other hand, when it is determined using a fixed threshold value as in the prior art, both the driver's blood pressure corresponding to the relational expression of FIG. 8 and the driver's blood pressure corresponding to the relational expression of FIG. If both are present, it is uniformly determined that the frustration level is 2. This is because the threshold values b11 to b13 for everyone are used without taking into account the characteristics of individual drivers.

  Moreover, according to the irritation estimation apparatus 1, by using the psychological change data prepared in advance, it is possible to suppress the fluctuation of the derivation of the correlation and more reliably estimate the driver's irritation state. In addition, since this psychological change data is prepared for each environmental factor determined based on vehicle information or environmental information, more accurate depending on not only the characteristics of the individual driver but also the situation encountered by the driver. The frustrated state can be judged well.

  Further, according to the frustrated estimation device 1, since the correlation is derived using the parameter indicating the time related to the derivation of the correlation determined based on each environmental factor, the correlation is determined in detail for each environmental factor. it can. Specifically, the actual reference start time T1, the actual reference end time T2, and the measurement time (T2-T1) are determined based on the correlation reference start time t1, the reference end time t2, and the reference time (t2-t1). A correlation is derived based on these determined parameters. As a result, the driver's frustrated state can be estimated with higher accuracy.

  As mentioned above, although embodiment which concerns on this invention was described, this invention is implemented in various forms, without being limited to the said embodiment.

  In the frustration estimation apparatus 1 of the present invention, the correlation determination unit 16 derives the correlation between the biological information and the environmental factor using the psychological change data read from the reference data storage device 13, but the correlation is obtained by another method. It may be derived. For example, the frustration estimation device 1 further includes a learning unit (not shown) that learns a change in the driver's frustration according to environmental factors, and the correlation determination unit 16 replaces the psychological change parameter or the psychological change parameter. The correlation is determined using the learning result of the learning means (not shown) together with the change parameter.

  For example, the learning means collects the estimated frustrated state for a predetermined time, thereby acquiring, for example, data similar to that shown in FIGS. 2 to 5 (hereinafter referred to as “learning data”). The learning means associates the acquired learning data with the vehicle information and the environment information collected at the time of learning data acquisition, and holds them as a learning result. The learning means updates the learning result every time. Thereafter, the environmental factor determination unit 14 acquires a learning result corresponding to the environmental factor based on the vehicle information and the environmental information for determining the occurrence of the environmental factor. Then, the correlation determination unit 16 determines the correlation based on the learning result input from the environmental factor determination unit 14 and the biological information input from the biological information detection unit 15.

  In this case, the driver's frustration (change in frustration level) is learned, and the correlation between the environmental factors and the biological information is derived based on the learning result. As a result, the individual characteristics of the driver can be more accurately reflected in the derivation of the correlation, and as a result, the psychological state of the driver can be estimated with higher accuracy.

  Moreover, in the said embodiment, although the correlation determination means 16 determined correlation based on real reference start time T1, real reference end time T2, and measurement time (T2-T1), the determination method of correlation is not limited to this. . For example, the correlation determination unit 16 may determine the correlation based on only one parameter among these three types of parameters.

  Moreover, in the said embodiment, although this invention was applied to the irritation | stimulation estimation apparatus which is mounted in a vehicle and estimates a driver | operator's irritation | stimulation state, this invention has other states, such as an angry state and an uneasy state besides an irritated state. The present invention is also applicable to a device that estimates a predetermined psychological state. Further, the present invention can be applied to other objects such as drivers of other vehicles, supervisors of various plants, and night workers.

It is a figure which shows the structure of the irritation | stimulation estimation apparatus which concerns on this embodiment. It is a figure which shows the example of the psychological change data when a horn is sounded from another vehicle. It is a figure which shows the example of the psychological change data when a driver | operator rings a horn. It is a figure which shows the example of the psychological change data in the case of interruption. It is a figure which shows the example of the psychological change data in the case of traffic jam. It is a figure which shows the derivation example of correlation. It is a figure which shows the derivation example of correlation. It is a graph which shows the example of the relational expression which shows correlation. It is a figure which shows another example about derivation | leading-out of correlation. It is a graph which shows another example of the relational expression which shows correlation. It is a flowchart which shows the process of the irritation | stimulation estimation apparatus shown in FIG.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Irritated estimation apparatus, 11 ... Vehicle information detection means, 12 ... Environmental information detection means, 13 ... Reference data storage device, 14 ... Environmental factor determination means, 15 ... Biological information detection means, 16 ... Correlation determination means, 17 ... Emotion State determination means

Claims (7)

A psychological state estimation device that estimates a subject's psychological state,
Biological information acquisition means for acquiring biological information of the subject;
Environmental factor determination means for determining the occurrence of an environmental factor that can change the psychological state of the subject;
A correlation deriving unit for deriving a correlation between the generated environmental factor and the biological information acquired by the biological information acquiring unit when the environmental factor is determined to be generated by the environmental factor determining unit;
Estimating means for estimating the psychological state of the subject based on the correlation derived by the correlation deriving means;
A psychological state estimation device comprising: Further comprising storage means for storing psychological change data indicating a change in the psychological state of the subject according to the environmental factor,
The environmental factor determination means acquires psychological change data corresponding to the environmental factor from the storage means based on information for determining the occurrence of the environmental factor,
The correlation deriving unit derives a correlation between the psychological change data corresponding to the environmental factor and the biological information based on the psychological change data acquired by the environmental factor determining unit.
The psychological state estimation apparatus according to claim 1. Learning means for learning a change in the psychological state of the subject according to the environmental factor;
The environmental factor determination unit acquires a learning result of the learning unit according to the environmental factor based on information for determining the occurrence of the environmental factor,
The correlation deriving unit derives a correlation between the learning result according to the environmental factor and the biological information based on the learning result acquired by the environmental factor determining unit.
The psychological state estimation apparatus according to claim 1 or 2, characterized in that. The correlation deriving means derives the correlation using a parameter indicating a time related to the derivation of the correlation, which is determined based on the generated environmental factor,
The psychological state estimation apparatus according to any one of claims 1 to 3. The parameter is a time interval necessary for deriving the correlation.
The psychological state estimation apparatus according to claim 4. The parameter is a start time indicating a start timing of derivation of the correlation.
The psychological state estimation apparatus according to claim 4 or 5, characterized in that. The parameter is an end time indicating an end timing of deriving the correlation.
The psychological state estimation device according to any one of claims 4 to 6.

Images