Judgment System

Abstract

To provide a determination system capable of determining whether or not drowsiness is normal.SOLUTION: A determination system 10 comprises a determination unit 18 that determines whether or not drowsiness of a driver who is driving a vehicle 100 is normal on the basis of drowsiness data related to the drowsiness of the driver and reference data related to drowsiness as a reference for determining whether or not the drowsiness of the driver is normal.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a determination system. [Background technology]

[0002] Patent Document 1 discloses a drowsiness prediction device that predicts whether the drowsiness level will increase. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5696632 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the drowsiness prediction device of Patent Document 1 has a problem in that it is not intended to determine whether drowsiness is normal or not.

[0005] Therefore, the present disclosure provides a determination system that can determine whether drowsiness is normal or not. [Means for solving the problem]

[0006] A determination system according to one aspect of the present disclosure includes a determination unit that determines whether a driver's drowsiness is normal based on drowsiness data related to the drowsiness of a driver operating a mobile vehicle and reference data related to drowsiness that serves as a standard for determining whether the driver's drowsiness is normal.

[0007] These comprehensive or specific aspects may be realized as a system, a method, an integrated circuit, a computer program, or a computer-readable recording medium such as a CD-ROM, or may be realized as any combination of the system, the method, the integrated circuit, the computer program, and the recording medium. The recording medium may also be a non-transitory recording medium. [Effects of the Invention]

[0008] The determination system of the present disclosure can determine whether drowsiness is normal or not. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a schematic diagram showing a determination system according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing the functional configuration of the determination system and the like shown in FIG. [Figure 3] FIG. 3 is a block diagram showing the functional configuration of the determination system of FIG. [Figure 4] FIG. 4 is a flowchart showing an example of the operation of the determination system of FIG. [Figure 5] FIG. 5 is a flowchart showing an example of the operation in step S2 of FIG. [Figure 6] FIG. 6 is a flowchart showing an example of the operation in step S3 of FIG. [Figure 7] FIG. 7 is a flowchart showing an example of the operation in step S4 of FIG. [Figure 8] FIG. 8 is a flowchart showing an example of the operation in step S31 of FIG. [Figure 9] FIG. 9 is a flowchart showing an example of the operation in step S32 of FIG. [Figure 10] FIG. 10 is a flowchart showing an example of the operation subsequent to the operation of FIG. [Figure 11] FIG. 11 is a flowchart showing an example of the operation in step S7 of FIG. [Figure 12] FIG. 12 is a flowchart showing another example of the operation of the determination system of FIG. [Figure 13] FIG. 13 is a flowchart showing another example of the operation in step S7 of FIG. [Figure 14]FIG. 14 is a flowchart showing an example of the operation in step S93 of FIG. [Figure 15] FIG. 15 is a flowchart showing another example of the operation in step S4 of FIG. [Figure 16] FIG. 16 is a graph showing an example of normal sleepiness and abnormal sleepiness. DETAILED DESCRIPTION OF THE INVENTION

[0010] A determination system according to one aspect of the present disclosure includes a determination unit that determines whether a driver's drowsiness is normal based on drowsiness data related to the drowsiness of a driver operating a mobile vehicle and reference data related to drowsiness that serves as a standard for determining whether the driver's drowsiness is normal.

[0011] This makes it possible to determine whether the driver's drowsiness is normal or not based on the drowsiness data and the reference data.

[0012] In addition, in a determination system according to one aspect of the present disclosure, the determination unit may compare a first rate of change, which is the rate of change of drowsiness indicated by the drowsiness data, with a second rate of change, which is the rate of change of drowsiness indicated by the reference data, and determine that the driver's drowsiness is not normal if the first rate of change is greater than the second rate of change.

[0013] According to this, when the first rate of change is greater than the second rate of change, it can be determined that the driver's drowsiness is not normal.

[0014] In the determination system according to the aspect of the present disclosure, the determination unit may calculate a correction value for correcting the drowsiness data.

[0015] This allows a determination as to whether the driver's drowsiness is normal or not based on the drowsiness data corrected using the correction value and the reference data, thereby enabling a more accurate determination as to whether the driver's drowsiness is normal or not.

[0016] In the determination system according to an aspect of the present disclosure, the determination unit may calculate the correction value that reduces a change in the driver's drowsiness due to an external factor that affects the drowsiness.

[0017] This allows a determination of whether the driver's drowsiness is normal based on drowsiness data corrected to reduce changes in the driver's drowsiness due to external factors and reference data, thereby making it possible to more accurately determine whether the driver's drowsiness has become abnormal due to factors other than external factors.

[0018] In the determination system according to an aspect of the present disclosure, the determination unit may calculate the correction value to reduce a change in the driver's drowsiness caused by the driver having lunch.

[0019] This allows a determination as to whether the driver's drowsiness is normal or not based on the drowsiness data corrected to reduce the change in the driver's drowsiness due to eating lunch and the reference data, thereby making it possible to more accurately determine whether the driver's drowsiness has become abnormal due to factors other than eating lunch.

[0020] Furthermore, in a determination system according to one aspect of the present disclosure, the determination unit may compare a first drowsiness level, which is indicated by the drowsiness data and which is the driver's drowsiness at a driving start point where the driver started driving the moving object, with a second drowsiness level, which is indicated by the reference data and which is the driver's past drowsiness at the driving start point, and determine that the driver's drowsiness is not normal if the first drowsiness level is greater than the second drowsiness level.

[0021] According to this, if the first drowsiness level is greater than the second drowsiness level, it can be determined that the driver's drowsiness level is not normal.

[0022] In addition, in the determination system according to one aspect of the present disclosure, the determination unit may determine whether the driver's drowsiness is normal based on the drowsiness data indicating an increasing tendency of drowsiness and the reference data.

[0023] This makes it possible to determine whether the driver's drowsiness is normal or not when the driver's drowsiness is increasing.

[0024] Furthermore, the determination system according to one aspect of the present disclosure may include an estimation unit that, when the determination unit determines that the driver's drowsiness is not normal, estimates a factor that causes the driver's drowsiness to be abnormal.

[0025] This allows for estimation of the cause of abnormal driver drowsiness.

[0026] In the determination system according to the aspect of the present disclosure, the estimation unit may estimate the factor based on the drowsiness data and the reference data.

[0027] According to this, the cause of the driver's abnormal drowsiness can be estimated based on the drowsiness data and the reference data, so that the cause of the driver's abnormal drowsiness can be estimated with higher accuracy.

[0028] In addition, in a determination system according to one aspect of the present disclosure, the estimation unit may estimate the factor based on at least one of the section in which the determination unit determines that the driver's drowsiness is not normal, the driver's drowsiness at the driving start point where the driver starts driving the moving body, and the driver's biometric information.

[0029] This allows the factors causing the driver's drowsiness to be abnormal to be estimated based on at least one of the section in which the judgment unit judges that the driver's drowsiness is abnormal, the driver's drowsiness at the driving start point where the driver begins driving the mobile vehicle, and the driver's biometric information, thereby allowing the factors causing the driver's drowsiness to be estimated more accurately.

[0030] In the determination system according to an aspect of the present disclosure, the estimation unit may estimate an internal factor that affects drowsiness as the factor.

[0031] This makes it possible to estimate the internal factors that cause the driver's drowsiness to be abnormal.

[0032] Furthermore, the determination system according to one aspect of the present disclosure may include a control unit that controls reporting to the moving body based on the determination result of the determination unit.

[0033] This allows the report to the mobile body to be controlled based on the judgment result of the judgment unit, so that the driver of the mobile body does not receive any particular report if the driver's drowsiness is normal, but can receive a report if the driver's drowsiness is not normal.

[0034] In addition, a determination system according to one aspect of the present disclosure may include a generation unit that extracts one or more past data related to past drowsiness based on the route on which the drowsiness data was acquired and the time period in which the drowsiness data was acquired, and generates the reference data based on the one or more past data.

[0035] This allows reference data to be generated using one or more pieces of past data extracted based on the route and time period in which the drowsiness data was acquired, making it possible to more accurately determine whether the driver's drowsiness is normal.

[0036] In addition, in a determination system according to one aspect of the present disclosure, the generation unit may extract, as the one or more pieces of past data, a plurality of pieces of past data relating to past drowsiness that were acquired along a route that matches the route on which the drowsiness data was acquired, a plurality of pieces of past data relating to past drowsiness that were acquired along a route that partially matches the route on which the drowsiness data was acquired, or a plurality of pieces of past data relating to past drowsiness that were acquired within a predetermined section from a starting point on a route whose starting point matches the route on which the drowsiness data was acquired.

[0037] This allows reference data to be generated using one or more past data acquired on a route that matches or is similar to the route on which the drowsiness data was acquired, thereby making it possible to more accurately determine whether the driver's drowsiness is normal.

[0038] Hereinafter, the embodiments will be specifically described with reference to the drawings.

[0039] The embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component placement and connection configurations, steps, and step order shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not recited in independent claims are described as optional components. Furthermore, each drawing is a schematic diagram and is not necessarily an exact illustration. Furthermore, the same components are designated by the same reference numerals in each drawing.

[0040] (Embodiment) FIG. 1 is a schematic diagram showing a determination system 10 according to an embodiment.

[0041] The determination system 10 is a system that determines whether the drowsiness of the driver of a vehicle 100 is normal. As shown in FIG. 1, the determination system 10 includes a processing server 12 and a database 14. The processing server 12 performs various processes. The database 14 is a database that includes various data used in the processes performed by the processing server 12. For example, the determination system 10 is realized by a cloud.

[0042] Vehicle 100 is an example of a moving body. For example, vehicle 100 is an automobile. Note that the moving body may also be, for example, a vehicle without wheels. A driver of vehicle 100 gets into vehicle 100 and drives vehicle 100. For example, vehicle 100 is a vehicle for delivering luggage, and the driver drives vehicle 100 along a predetermined route. For example, vehicle 100 has one or more sensors and transmits sensor data acquired using the one or more sensors to determination system 10. For example, the one or more sensors include a sensor for estimating the driver's drowsiness, a sensor for detecting the driver's biological information, a sensor for detecting route information related to the route traveled by vehicle 100, and a sensor for detecting vehicle information related to vehicle 100. In this embodiment, the one or more sensors include a drive recorder 101 and a driver monitoring system 102.

[0043] The traffic management system 200 manages the operation of the vehicle 100. The traffic management system 200 has a database 201. The database 201 is a database that includes traffic management data related to the traffic management of the vehicle 100. For example, the traffic management data indicates the route that the vehicle 100 will travel, the time period during which the vehicle 100 will travel the route, etc. The traffic management system 200 transmits the traffic management data to the determination system 10. For example, the traffic management system 200 is realized by a computer or the like.

[0044] The determination system 10 performs a process of determining whether the driver's drowsiness is normal or not based on the sensor data and the operation management data, and transmits the process result to the vehicle 100 and the operation management system 200.

[0045] FIG. 2 is a block diagram showing the functional configuration of the determination system 10 and the like shown in FIG.

[0046] As shown in FIG. 2 , the vehicle 100 further includes a drowsiness estimation unit 103. The drowsiness estimation unit 103 estimates the drowsiness of the driver. For example, the drowsiness estimation unit 103 estimates the drowsiness level of the driver. The drowsiness level is an index indicating the degree (strength) of drowsiness, and a higher drowsiness level indicates greater (stronger) drowsiness. That is, for example, the drowsiness estimation unit 103 estimates the degree of drowsiness the driver feels. For example, the drowsiness estimation unit 103 estimates the drowsiness of the driver based on the frequency of the driver's blinks and the movement of the driver's mouth, etc., obtained by the driver monitoring system 102. For example, the drowsiness estimation unit 103 estimates that the drowsiness level of the driver is higher the more frequently the driver blinks. Furthermore, for example, the drowsiness estimation unit 103 estimates that the drowsiness level of the driver is higher the less frequently the driver's mouth moves. For example, the drowsiness estimation unit 103 repeatedly estimates the drowsiness of the driver at predetermined time intervals. The drowsiness estimation unit 103 transmits drowsiness data indicating the drowsiness of the driver to the determination system 10. For example, the drowsiness data is time-series data of the drowsiness level of the driver. For example, the drowsiness estimation unit 103 is realized by a processor or the like. Note that, for example, the determination system 10, rather than the vehicle 100, may have the drowsiness estimation unit 103.

[0047] The determination system 10 includes a generation unit 16, a determination unit 18, a factor estimation unit 20, and a control unit 22. For example, the generation unit 16, the determination unit 18, the factor estimation unit 20, and the control unit 22 are realized by a processor, a memory, a wireless communication module, etc.

[0048] The generation unit 16 extracts one or more pieces of past data related to past drowsiness based on the route on which the drowsiness data was acquired and the time period in which the drowsiness data was acquired, and generates reference data based on the one or more pieces of past data. The reference data is data related to drowsiness that serves as a reference for determining whether the driver's drowsiness is normal. For example, the reference data is time-series data on drowsiness levels. For example, the generation unit 16 generates the reference data based on the route on which the vehicle 100 is traveling, the time period in which the vehicle 100 is traveling on the route, the traffic conditions on the route on which the vehicle 100 is traveling, and the like. For example, information indicating the route on which the vehicle 100 is traveling, the time period in which the vehicle 100 is traveling on the route, the traffic conditions on the route on which the vehicle 100 is traveling, and the like is included in the sensor data, the traffic management data, and the like.

[0049] The determination unit 18 determines whether the driver's drowsiness is normal. The determination unit 18 determines whether the driver's drowsiness is normal based on drowsiness data related to the drowsiness of the driver who drives the vehicle 100 and reference data related to drowsiness that serves as a reference for determining whether the driver's drowsiness is normal. For example, the determination unit 18 compares the rate of increase (rate of increase) of the driver's drowsiness level with an allowable rate of increase, which is an allowable rate of increase (rate of increase) of drowsiness, and determines that the driver's drowsiness is abnormal if the rate of increase of the driver's drowsiness level is greater than the allowable rate of increase. Furthermore, for example, the determination unit 18 compares the driver's drowsiness level with an allowable drowsiness level, which is an allowable drowsiness level, and determines that the driver's drowsiness is abnormal if the driver's drowsiness level is greater than the allowable rate of increase. For example, the allowable rate of increase is the rate of increase obtained by adding a threshold value to the rate of increase of the drowsiness level indicated by the reference data, and the allowable drowsiness level is the drowsiness level obtained by adding a threshold value to the drowsiness level indicated by the reference data. Fig. 16 is a graph showing an example of normal drowsiness and abnormal drowsiness. Here, as shown in Fig. 16, drowsiness caused by boredom, long driving hours, etc. is considered to be normal drowsiness. On the other hand, drowsiness caused by lack of sleep, fatigue, etc. is considered to be abnormal drowsiness, i.e., abnormal drowsiness. When drowsiness progresses rapidly (when the rate of increase in drowsiness level is greater than the allowable rate of increase) due to factors related to the driver's physical condition, such as lack of sleep (see the area surrounded by the two-dot chain line in Fig. 16), drowsiness is considered to be abnormal, i.e., the driver's drowsiness is not normal.

[0050] The determination unit 18 outputs a determination result. For example, the determination result indicates whether the driver's sleepiness is normal or not, and how abnormal drowsiness manifests when the driver's sleepiness is not normal. For example, how abnormal drowsiness manifests when the driver's sleepiness is not normal is indicated by the rate of change in the driver's sleepiness, the level of the driver's sleepiness, the section in which the driver's sleepiness is not normal (abnormal), and the timing when the driver's sleepiness becomes abnormal (abnormal).

[0051] The factor estimation unit 20 is an example of an estimation unit that estimates factors that cause the driver's drowsiness to be abnormal when the determination unit 18 determines that the driver's drowsiness is abnormal. For example, the factor estimation unit 20 estimates factors that cause the driver's drowsiness to be abnormal based on the determination result of the determination unit 18, the route on which the vehicle 100 is traveling, the time period during which the vehicle 100 is traveling on the route, the traffic conditions on the route on which the vehicle 100 is traveling, and the like. For example, information indicating the route on which the vehicle 100 is traveling, the time period during which the vehicle 100 is traveling on the route, the traffic conditions on the route on which the vehicle 100 is traveling, and the like is included in sensor data, traffic management data, and the like. The factor estimation unit 20 outputs an estimation result. For example, the estimation result indicates factors that cause the driver's drowsiness to be abnormal. Specifically, for example, the estimation result indicates the degree of possibility that medication is a factor, the degree of possibility that lack of sleep is a factor, the degree of possibility that fatigue from the previous day is a factor, and the like.

[0052] The control unit 22 controls the report to the vehicle 100 based on the determination result of the determination unit 18. For example, when the determination unit 18 determines that the driver's drowsiness is not normal, the control unit 22 reports to the vehicle 100 that the driver's drowsiness is not normal. For example, the control unit 22 reports to the vehicle 100 that the driver's drowsiness is not normal by transmitting information indicating that the driver's drowsiness is not normal to the vehicle 100. Also, for example, when a factor is estimated by the factor estimation unit 20, the control unit 22 reports to the vehicle 100 the factor that causes the driver's drowsiness to be abnormal. For example, the control unit 22 reports to the vehicle 100 the factor that causes the driver's drowsiness to be abnormal by transmitting information indicating the factor estimated by the factor estimation unit 20 to the vehicle 100. Also, for example, when the determination unit 18 determines that the driver's drowsiness is normal, the control unit 22 does not report to the vehicle 100. The control unit 22 similarly controls the report to the traffic management system 200.

[0053] FIG. 3 is a block diagram showing the functional configuration of the determination system 10 of FIG.

[0054] As shown in FIG. 3, the determination system 10 further includes a data acquisition unit 24.

[0055] The data acquisition unit 24 includes a sensor data acquisition unit 26 that acquires sensor data, a drowsiness data acquisition unit 28 that acquires drowsiness data, and a fleet management data acquisition unit 30 that acquires fleet management data. The data acquisition unit 24 transmits the acquired sensor data, drowsiness data, and fleet management data to the generation unit 16, the determination unit 18, and the factor estimation unit 20. For example, the data acquisition unit 24 is realized by a wireless communication module or the like.

[0056] The generation unit 16 has a database 32, an extraction unit 34, and a reference data generation unit 36. The database 32 is a database that includes one or more pieces of past data related to past drowsiness. For example, each of the one or more pieces of past data is time-series data of drowsiness levels. The extraction unit 34 extracts one or more pieces of past data based on the route on which the drowsiness data was acquired and the time period in which the drowsiness data was acquired. In this embodiment, the extraction unit 34 extracts one or more pieces of past data from the database 32. The reference data generation unit 36 generates reference data based on the one or more pieces of extracted past data.

[0057] The determination unit 18 has a database 38, a processing unit 40, a correction unit 42, and a comparison unit 44. The database 38 is a database that includes reference data and the like. The processing unit 40 performs various processes. For example, the processing unit 40 performs processes such as determining whether the drowsiness data acquired by the data acquisition unit 24 is appropriate as data for determining whether the driver's drowsiness is normal. The correction unit 42 calculates a correction value for correcting the drowsiness data and corrects the drowsiness data using the correction value. The comparison unit 44 compares the drowsiness data with the reference data.

[0058] The sensor data acquisition unit 26, the drowsiness data acquisition unit 28, the operation management data acquisition unit 30, the extraction unit 34, the reference data generation unit 36, the processing unit 40, the correction unit 42, the comparison unit 44, the factor estimation unit 20, and the control unit 22 are included in the processing server 12. The database 32 and the database 38 are included in the database 14.

[0059] FIG. 4 is a flowchart showing an example of the operation of the determination system 10 of FIG.

[0060] 4, first, the determination system 10 acquires sensor data, drowsiness data, and fleet management data (step S1). In this embodiment, the data acquisition unit 24 acquires the sensor data, drowsiness data, and fleet management data.

[0061] The determination system 10 extracts one or more pieces of past data for generating reference data (step S2). In this embodiment, the generation unit 16 extracts one or more pieces of past data.

[0062] The determination system 10 generates reference data (step S3). In this embodiment, the generation unit 16 generates the reference data using one or more pieces of past data.

[0063] The determination system 10 determines whether the driver's drowsiness is normal or not (step S4). In this embodiment, the determination unit 18 determines whether the driver's drowsiness is normal or not.

[0064] The determination system 10 determines whether or not the drowsiness of the driver is determined to be normal (step S5). In the present embodiment, the determination unit 18 determines whether or not the drowsiness of the driver is determined to be normal.

[0065] If the determination system 10 determines that the driver's drowsiness is normal (Yes in step S5), it does not make a report (step S6) and ends the process. For example, if the control unit 22 determines that the driver's drowsiness is normal, it does not make a report.

[0066] When it is determined that the driver's drowsiness is not normal (No in step S5), the determination system 10 estimates the factor that causes the driver's drowsiness to be abnormal (step S7). For example, when it is determined that the driver's drowsiness is not normal, the factor estimation unit 20 estimates the factor that causes the driver's drowsiness to be abnormal.

[0067] When the determination system 10 estimates the cause of the driver's abnormal drowsiness, it makes a report (step S8). For example, when it is determined that the driver's drowsiness is abnormal, the control unit 22 makes a report.

[0068] FIG. 5 is a flowchart showing an example of the operation in step S2 of FIG.

[0069] As shown in FIG. 5, first, the extraction unit 34 determines whether there is a predetermined number or more of past data related to a route that matches the route from the driving start point where the driver started driving the vehicle 100 to the current location of the vehicle 100 (step S11). For example, a route that matches the route from the driving start point where the driver started driving the vehicle 100 to the current location of the vehicle 100 is a route that matches the entire route from the driving start point where the driver started driving the vehicle 100 to the current location of the vehicle 100. For example, the past data is data related to past drowsiness and is time-series data of the drowsiness level. For example, the past data related to the route that matches the route from the driving start point where the driver started driving the vehicle 100 to the current location of the vehicle 100 is time-series data of the driver's drowsiness level acquired when the driver drove the vehicle 100 along the route in the past. For example, the extraction unit 34 determines whether there is a predetermined number or more of past data from a plurality of past data acquired within a predetermined number of years going back from the present.

[0070] When there is a predetermined number or more of past data relating to a route that matches the route from the driving start point to the current point of the vehicle 100 (Yes in step S11), the extraction unit 34 acquires the time period in which the past data was acquired (step S12). For example, the past data is associated with a timestamp indicating the time at which the past data was acquired. Specifically, for example, the past data is associated with a timestamp indicating the time at which each drowsiness level indicated by the past data was obtained.

[0071] If there is not a predetermined number or more of past data relating to a route that matches the route from the driving start point of vehicle 100 to the current point (No in step S11), extraction unit 34 determines whether there is a predetermined number or more of past data relating to a route that partially matches the route from the driving start point of vehicle 100 to the current point (step S13). For example, the past data relating to a route that partially matches the route from the driving start point of vehicle 100 to the current point is time-series data of the driver's drowsiness level acquired when the driver drove vehicle 100 along that route in the past.

[0072] When there is a predetermined number or more of past data relating to a route that partially matches the route from the driving start point of the vehicle 100 to the current point (Yes in step S13), the extraction unit 34 acquires the time period in which the past data relating to the matching section was acquired (step S14). The matching section is a section that matches the route from the driving start point of the vehicle 100 to the current point, among the routes that partially match the route from the driving start point of the vehicle 100 to the current point.

[0073] When the number of pieces of past data relating to a route that partially matches the route from the driving start point of the vehicle 100 to the current point is not equal to or greater than a predetermined number (No in step S13), the extraction unit 34 determines whether the number of pieces of past data relating to a route whose starting point matches the number of pieces of past data relating to a route from the driving start point of the vehicle 100 to the current point is equal to or greater than a predetermined number (step S15). In other words, when the number of pieces of past data relating to a route that partially matches the route from the driving start point of the vehicle 100 to the current point is not equal to or greater than a predetermined number, the extraction unit 34 determines whether the number of pieces of past data relating to a route whose starting point matches the route from the driving start point of the vehicle 100 to the current point is equal to or greater than a predetermined number.

[0074] If there is a predetermined number of pieces of past data relating to the route that matches the driving start point (Yes in step S15), the extraction unit 34 acquires a time period in which past data relating to the predetermined section was acquired (step S16). For example, the predetermined section is a time section of about several tens of minutes from the start of driving.

[0075] If the number of past data relating to the route having the same driving start point is less than the predetermined number (No in step S15), the extraction unit 34 ends the process.

[0076] The extraction unit 34 extracts past data whose time slot match rate is higher than a threshold (step S17). For example, 24 hours (one day) is divided into six time slots of four hours each, and if the time slot in which past data was acquired is the same time slot in which drowsiness data was acquired, the match rate is 100; if it is a time slot adjacent to the time slot in which drowsiness data was acquired, the match rate is 80; if it is a time slot adjacent to the time slot in which drowsiness data was acquired with one time slot in between, the match rate is 60; and if it is a time slot adjacent to the time slot in which drowsiness data was acquired with two time slots in between, the match rate is 40. For example, the threshold is 50, and the extraction unit 34 extracts past data whose match rate is higher than 50 from a predetermined number or more of past data determined to be in step S11, step S13, or step S15.

[0077] The extraction unit 34 determines whether or not the number of pieces of extracted past data is equal to or greater than a predetermined number (step S18). Specifically, the extraction unit 34 determines whether or not the number of pieces of past data extracted in step S17 is equal to or greater than a predetermined number.

[0078] If the number of extracted past data is equal to or greater than the predetermined number (Yes in step S18), the extraction unit 34 ends the process.

[0079] If the number of extracted past data is less than the predetermined number (No in step S18), the extraction unit 34 extracts past data with a time zone matching rate equal to or less than the threshold value in order of higher time zone matching rate so that the number of past data is equal to or greater than the predetermined number (step S19), and terminates the processing.

[0080] In this way, the generation unit 16 extracts, as one or more pieces of past data, a plurality of pieces of past data relating to past drowsiness that were acquired on a route that matches the route on which the drowsiness data was acquired, a plurality of pieces of past data relating to past drowsiness that were acquired on a route that partially matches the route on which the drowsiness data was acquired, or a plurality of pieces of past data relating to past drowsiness that were acquired within a specified section from the starting point of a route whose starting point matches the route on which the drowsiness data was acquired.

[0081] FIG. 6 is a flowchart showing an example of the operation in step S3 of FIG.

[0082] 6, first, the reference data generating unit 36 determines whether the past data is related to a route that matches the route from the driving start point of the vehicle 100 to the current point (step S21). For example, the reference data generating unit 36 determines whether the one or more past data extracted in step S2 is related to a route that matches the route from the driving start point of the vehicle 100 to the current point.

[0083] If the past data is not related to a route that matches the route from the driving start point of the vehicle 100 to the current point (No in step S21), the reference data generation unit 36 determines whether the past data is related to a route that partially matches the route from the driving start point of the vehicle 100 to the current point (step S22). For example, the reference data generation unit 36 determines whether the one or more past data extracted in step S2 is related to a route that partially matches the route from the driving start point of the vehicle 100 to the current point.

[0084] If the past data is related to a route that partially matches the route from the driving start point to the current point of the vehicle 100 (Yes in step S22), the reference data generating unit 36 extracts the past data related to the matching section (step S23).

[0085] If the past data is not related to a route that partially matches the route from the driving start point of the vehicle 100 to the current point (No in step S22), the reference data generation unit 36 determines whether or not the past data is related to a route with the matching driving start point (step S24). For example, the reference data generation unit 36 determines whether or not the one or more past data extracted in step S2 is related to a route with the matching driving start point.

[0086] If the past data does not relate to a route having the same driving start point (No in step S24), the reference data generating unit 36 ends the process.

[0087] If the past data is related to a route having the same driving start point (Yes in step S24), the reference data generating unit 36 extracts past data related to a predetermined section (step S25).

[0088] The reference data generating unit 36 determines whether the time periods match (step S26). For example, if the time period during which each of one or more pieces of past data relating to a route matching the route from the driving start point of the vehicle 100 to the current location was acquired matches the time period during which the drowsiness data was acquired, the reference data generating unit 36 determines that the time periods match. On the other hand, if the time period during which at least one of the pieces of past data relating to the route matching the route from the driving start point of the vehicle 100 to the current location was acquired does not match the time period during which the drowsiness data was acquired, the reference data generating unit 36 determines that the time periods do not match. Also, for example, if the time period during which each of the one or more pieces of past data extracted in step S23 or step S25 was acquired matches the time period during which the drowsiness data was acquired, the reference data generating unit 36 determines that the time periods match. On the other hand, if the time period during which at least one of the one or more pieces of past data extracted in step S23 or step S25 was acquired does not match the time period during which the drowsiness data was acquired, the reference data generating unit 36 determines that the time periods do not match.

[0089] If the time periods match (Yes in step S26), the reference data generating unit 36 calculates the reference data by (Σ(past data)) / (number of past data) (step S27). For example, the reference data generating unit 36 calculates the reference data by adding up one or more pieces of past data related to a route that matches the route from the driving start point of the vehicle 100 to the current point, and dividing the added data by the number of one or more pieces of past data. Also, for example, the reference data generating unit 36 calculates the reference data by adding up one or more pieces of past data extracted in step S23 or step S25, and dividing the added data by the number of one or more pieces of past data. For example, adding up one or more pieces of past data means adding up the drowsiness levels at each time indicated by the one or more pieces of past data, and dividing the added up data by the number of one or more pieces of past data means dividing the drowsiness levels at each time obtained by adding up by the number of one or more pieces of past data.

[0090] If the time periods do not match (No in step S26), the reference data generation unit 36 calculates drowsiness data by (Σ(weighting coefficient × past data)) / (Σ(weighting coefficient)) (step S28). The weighting coefficient is set to a larger value as the time period match rate increases. For example, past data with a time period match rate of 100 is multiplied by a weighting coefficient of 10, past data with a time period match rate of 80 is multiplied by a weighting coefficient of 8, past data with a time period match rate of 60 is multiplied by a weighting coefficient of 6, past data with a time period match rate of 40 is multiplied by a weighting coefficient of 4, and past data with a time period match rate of 20 is multiplied by a weighting coefficient of 2. For example, the reference data generation unit 36 multiplies each of one or more pieces of past data related to a route that matches the route from the driving start point of the vehicle 100 to the current point by a weighting coefficient, adds them up, and calculates the reference data by dividing the sum of the data by the sum of the values of one or more weighting coefficients multiplied by one or more pieces of past data. Furthermore, for example, the reference data generating unit 36 calculates the reference data by multiplying each of the one or more pieces of past data extracted in step S23 or step S25 by a weighting factor, adding up the combined data, and dividing the combined data by the combined value of the one or more weighting factors multiplied by the one or more pieces of past data. For example, multiplying each of the one or more pieces of past data by a weighting factor and adding up the combined data means multiplying the drowsiness level at each time indicated by the one or more pieces of past data by a weighting factor and adding up the drowsiness levels at each time obtained by multiplying by the weighting factor, and dividing the combined data by the combined value of the one or more weighting factors multiplied by the one or more pieces of past data means dividing the drowsiness level at each time obtained by adding up the values by the one or more weighting factors multiplied by the one or more pieces of past data.

[0091] FIG. 7 is a flowchart showing an example of the operation in step S4 of FIG.

[0092] As shown in FIG. 7, first, the determination unit 18 corrects the drowsiness data (step S31).

[0093] The determination unit 18 compares the drowsiness data with the reference data to determine whether the drowsiness is normal or not (step S32).

[0094] FIG. 8 is a flowchart showing an example of the operation in step S31 of FIG.

[0095] As shown in Fig. 8, first, the correction unit 42 acquires a correction value according to an external factor (step S41). The external factor is an external factor that affects drowsiness. The correction value according to the external factor is a correction value that reduces a change in the driver's drowsiness due to the external factor. For example, the external factor is weather, traffic congestion, month, day, room temperature, etc.

[0096] The correction unit 42 corrects the drowsiness data using the correction value (step S42).

[0097] The correction unit 42 determines whether or not correction has been completed for all external factors (step S43).

[0098] If correction has not been completed for all external factors (No in step S43), the correction unit 42 acquires correction values corresponding to external factors that have not yet been acquired (step S41).

[0099] If correction has been completed for all external factors (Yes in step S43), the correction unit 42 ends the process.

[0100] Fig. 9 is a flowchart showing an example of the operation in step S32 of Fig. 7. Fig. 10 is a flowchart showing an example of the operation subsequent to the operation of Fig. 9.

[0101] 9, first, the processing unit 40 determines whether the reference data is related to a route that matches the route from the driving start point of the vehicle 100 to the current point (step S51). The reference data related to the route that matches the route from the driving start point of the vehicle 100 to the current point is reference data that has been generated using one or more past data related to the route that matches the route from the driving start point of the vehicle 100 to the current point.

[0102] If the reference data relates to a route that matches the route from the driving start point of the vehicle 100 to the current point (Yes in step S51), the processing unit 40 sets the time window for comparing the drowsiness data with the reference data from the driving start point to the current point (step S52).

[0103] If the reference data does not relate to a route that matches the route from the driving start point of the vehicle 100 to the current point (No in step S51), the processing unit 40 determines whether the reference data relates to a route that partially matches the route from the driving start point of the vehicle 100 to the current point (step S53). The reference data relating to a route that partially matches the route from the driving start point of the vehicle 100 to the current point is reference data that has been generated using one or more past data relating to a route that partially matches the route from the driving start point of the vehicle 100 to the current point.

[0104] If the reference data relates to a route that partially matches the route from the driving start point of the vehicle 100 to the current point (Yes in step S53), the processing unit 40 sets a time window for comparing the drowsiness data with the reference data to the matching section (step S54).

[0105] After setting the time window, the processing unit 40 determines whether the drowsiness data is on an increasing trend (step S55). For example, the processing unit 40 passes the drowsiness data (time-series data) through a low-pass filter to generate drowsiness data without small vibrations, then calculates a time difference value for the drowsiness data, determines whether the drowsiness data is monotonically increasing, and determines whether the drowsiness data is on an increasing trend.

[0106] If the drowsiness data is not on an increasing trend (No in step S55), the processing unit 40 ends the process.

[0107] If the drowsiness data is on the rise (Yes in step S55), the comparison unit 44 determines whether the drowsiness at the driving start point is greater than the reference drowsiness by a threshold or more (step S56), as shown in Fig. 10. The reference drowsiness is the drowsiness indicated by the reference data. For example, if the threshold is 0.5, the comparison unit 44 determines whether the drowsiness level at the driving start point is equal to or greater than the level obtained by adding 0.5 to the reference drowsiness level at the driving start point.

[0108] If the drowsiness at the driving start point is greater than the reference drowsiness by the threshold or more (Yes in step S56), the comparison unit 44 determines that the initial drowsiness is not normal (step S57).

[0109] If the drowsiness level at the driving start point is not greater than the reference drowsiness level by the threshold value or more (No in step S56), the comparison unit 44 determines whether the rate of change in drowsiness is greater than the reference drowsiness level by the threshold value or more (step S58). For example, if the threshold value is 0.5, the comparison unit 44 determines whether the rate of increase in drowsiness (rate of change) is equal to or greater than the rate obtained by adding 0.5 to the rate of increase in the reference drowsiness (rate of change).

[0110] If the rate of change in drowsiness is greater than the reference rate of change in drowsiness by the threshold or more (Yes in step S58), the comparison unit 44 determines that the rate of change in drowsiness is not normal (step S59).

[0111] If the rate of change in drowsiness is not greater than the threshold value above the rate of change in the reference drowsiness (No in step S58), the comparison unit 44 determines whether or not the initial drowsiness has been determined to be abnormal (step S60).

[0112] When the comparison unit 44 determines that the rate of change in drowsiness is not normal (step S59) and when it determines that the initial drowsiness is not normal (Yes in step S60), it determines that the drowsiness is not normal (step S61).

[0113] If the comparison unit 44 has not determined that the initial drowsiness is not normal (No in step S60), it determines that the drowsiness is normal (step S62), and ends the process.

[0114] Returning to Figure 9, if the reference data does not relate to a route that partially matches the route from the driving start point of the vehicle 100 to the current point (No in step S53), the processing unit 40 determines whether the reference data relates to a route that matches the driving start point (step S63).

[0115] If the past data relates to a route that matches the driving start point (Yes in step S63), the comparison unit 44 determines whether the drowsiness at the driving start point is greater than the reference drowsiness by a threshold or more (step S64), as shown in Fig. 10. The comparison unit 44 determines whether the drowsiness at the driving start point is greater than the reference drowsiness by a threshold or more, in the same manner as in step S56.

[0116] If the drowsiness at the driving start point is greater than the reference drowsiness by the threshold or more (Yes in step S64), the comparison unit 44 determines that the initial drowsiness is not normal (step S65).

[0117] If the drowsiness level at the driving start point is not greater than the reference drowsiness level by the threshold value or more (No in step S64), the comparison unit 44 determines that the drowsiness level is normal (step S62), and ends the process.

[0118] Returning to FIG. 9, if the past data does not relate to a route having a matching driving start point (No in step S63), the processing unit 40 ends the processing as shown in FIG.

[0119] In this way, the judgment unit 18 compares the first rate of change, which is the rate of change of drowsiness indicated by the drowsiness data, with the second rate of change, which is the rate of change of drowsiness indicated by the reference data, and if the first rate of change is greater than the second rate of change, it judges that the driver's drowsiness is not normal.

[0120] In addition, the judgment unit 18 compares the first drowsiness, which is indicated by the drowsiness data and is the driver's drowsiness at the driving start point when the driver started driving the vehicle 100, with the second drowsiness, which is indicated by the reference data and is the driver's past drowsiness at the driving start point, and if the first drowsiness is greater than the second drowsiness, judges that the driver's drowsiness is not normal.

[0121] Furthermore, the determination unit 18 determines whether the driver's drowsiness is normal or not based on the drowsiness data indicating an increasing tendency of drowsiness and the reference data.

[0122] FIG. 11 is a flowchart showing an example of the operation in step S7 of FIG.

[0123] 11, first, the factor estimating unit 20 determines whether or not there is reference data for factor estimation (step S71). For example, the reference data is data indicating the month or day when the drowsiness data was acquired.

[0124] If there is reference data (Yes in step S71), the factor estimation unit 20 estimates the factor based on the reference data (step S72). For example, if the month indicated by the reference data is a pollen month with a lot of pollen, the factor estimation unit 20 estimates that taking medication for hay fever is the factor. In this way, for example, the factor estimation unit 20 estimates that the internal factor is that the driver's drowsiness is abnormal. For example, the internal factor is taking medication, lack of sleep, fatigue from the previous day, etc.

[0125] If there is no reference data (No in step S71), the factor estimation unit 20 ends the process.

[0126] FIG. 12 is a flowchart showing another example of the operation of the determination system 10 of FIG.

[0127] As shown in FIG. 12, first, the correction unit 42 classifies the past data by type of external factor (step S81). For example, if the external factor is weather, the types of external factors are sunny, cloudy, rainy, snowy, etc. For example, if the external factor is traffic congestion, the types of external factors are present and absent, etc. For example, if the external factor is room temperature, humidity, atmospheric pressure, or illuminance, the types of external factors are their respective ranges. For example, if the external factor is month, the types of external factors are January to December. For example, the correction unit 42 classifies the past data into past data acquired on sunny days, past data acquired on cloudy days, past data acquired on rainy days, and past data acquired on snowy days.

[0128] The correction unit 42 extracts routes for which there is a predetermined number or more of past data for each type (step S82). For example, the correction unit 42 extracts routes for which there is a predetermined number or more of past data acquired on sunny days, past data acquired on cloudy days, past data acquired on rainy days, and past data acquired on snowy days.

[0129] The correction unit 42 determines whether there is an influencing external factor (step S83). For example, weather, traffic congestion, room temperature, humidity, atmospheric pressure, and illuminance are uninfluenced external factors, while the month is an influencing external factor. For example, the correction unit 42 determines that there is an influencing external factor when the types of months in which multiple pieces of past data classified by weather type were acquired are different.

[0130] If there is an influencing external factor (Yes in step S83), the correction unit 42 corrects the past data for the influencing external factor (step S84). For example, the correction unit 42 corrects the past data classified by weather type, such that the past data classified into pollen months (e.g., March and April) is smaller.

[0131] If there are no influencing external factors (No in step S83), or if the past data has been corrected for influencing external factors (step S84), the correction unit 42 calculates average data for each type of external factor and compares the multiple average data sets (step S85). For example, the correction unit 42 calculates average data obtained by averaging one or more past data sets acquired when it is sunny, average data obtained by averaging one or more past data sets acquired when it is cloudy, average data obtained by averaging one or more past data sets acquired when it is rainy, and average data obtained by averaging one or more past data sets acquired when it is snowy, and compares these multiple average data sets.

[0132] The correction unit 42 determines whether there is a significant difference between the plurality of average data (step S86). For example, a significant difference is a difference in drowsiness level equal to or greater than a predetermined level, a difference in the rate of change (rate of increase) in drowsiness level equal to or greater than a predetermined level, etc.

[0133] If there is a significant difference between the plurality of average data (Yes in step S86), the correction unit 42 stores a value that eliminates the significant difference as a correction value (step S87).

[0134] The correction unit 42 determines whether or not the process has been completed for all external factors (step S88).

[0135] If the process has not been completed for all external factors (No in step S88), the correction unit 42 classifies the past data for the external factors that have not yet been completed by type of the external factor (step S81).

[0136] If there is no significant difference between the plurality of average data (No in step S86) and if all external factors have been considered (Yes in step S88), the correction unit 42 ends the process.

[0137] In this way, the determination unit 18 calculates a correction value that reduces the change in the driver's drowsiness due to external factors that affect drowsiness. For example, the determination unit 18 calculates a correction value that reduces the change in the driver's drowsiness due to weather.

[0138] FIG. 13 is a flowchart showing another example of the operation in step S7 of FIG.

[0139] 13, when the factor estimation unit 20 estimates the factors based on the reference data (step S72), it corrects the drowsiness data based on the reference data (step S91). For example, if the drowsiness data was acquired in a pollen month, the factor estimation unit 20 corrects the drowsiness data so that the rate of change in drowsiness becomes slower.

[0140] The factor estimation unit 20 determines whether the corrected rate of change in drowsiness is greater than the reference rate of change in drowsiness (step S92). The corrected rate of change in drowsiness is the rate of change in drowsiness indicated by the drowsiness data corrected in step S91.

[0141] If the rate of change in drowsiness after correction is greater than the reference rate of change in drowsiness (Yes in step S92), the factor estimation unit 20 estimates a factor derived from the driver (step S93). For example, a factor derived from the driver is an example of an internal factor.

[0142] If the corrected rate of change in drowsiness is not greater than the reference rate of change in drowsiness (No in step S92) and if a factor derived from the driver is estimated (step S93), the factor estimation unit 20 estimates the main factor (step S94). For example, if the drowsiness data was acquired in a pollen month and the corrected rate of change in drowsiness indicated by the drowsiness data corrected to reduce the rate of change in drowsiness is not greater than the reference rate of change in drowsiness, the factor estimation unit 20 estimates that medication for hay fever is the main factor. Also, for example, if the factor estimation unit 20 estimates a factor derived from the driver, the factor estimation unit 20 estimates that the driver's factor is the main factor.

[0143] FIG. 14 is a flowchart showing an example of the operation in step S93 of FIG.

[0144] 14, the factor estimation unit 20 determines whether the drowsiness in the first half section is normal or not (step S101). The first half section is the first half section of the route from the driving start point to the current point of the vehicle 100. For example, the factor estimation unit 20 determines whether the drowsiness in the first half section is normal or not based on the drowsiness data and the reference data.

[0145] If the sleepiness in the first half section is not normal (No in step S101), the factor estimating unit 20 weights the candidate factors of fatigue from the previous day and lack of sleep (step S102).

[0146] The factor estimation unit 20 determines whether the initial drowsiness is normal or not (step S103). For example, the factor estimation unit 20 determines whether the drowsiness is greater than the reference drowsiness by a threshold or more at the driving start point based on the drowsiness data and the reference data, and determines that the initial drowsiness is normal if the drowsiness is not greater than the reference drowsiness by the threshold or more at the driving start point, and determines that the initial drowsiness is not normal if the drowsiness is greater than the reference drowsiness by the threshold or more at the driving start point.

[0147] If the initial sleepiness is not normal (No in step S103), the factor estimating unit 20 weights the candidate factor of fatigue from the previous day (step S104).

[0148] If the drowsiness level in the first half of the vehicle is normal (Yes in step S101), if the initial drowsiness level is normal (Yes in step S103), or if the candidate factor of fatigue from the previous day is weighted (step S104), the factor estimation unit 20 determines whether the driver has recently gotten off and gotten in the vehicle (step S105). For example, if the factor estimation unit 20 determines that the driver's door of the vehicle 100 has been opened and closed twice based on the opening and closing record of the driver's door, the factor estimation unit 20 determines that the driver has recently gotten off and gotten in the vehicle. For example, if the driver has gotten off and gotten in within a predetermined time prior to the current time, the factor estimation unit 20 determines that the driver has recently gotten off and gotten in the vehicle.

[0149] If the driver has not gotten off or gotten back on the vehicle immediately before (No in step S105), the factor estimation unit 20 determines whether the driver's stress level is high (step S106). Specifically, the factor estimation unit 20 determines whether the driver's stress level is higher than a threshold. For example, the factor estimation unit 20 calculates the driver's stress level based on the driver's biological information. For example, the biological information includes the heart rate, body temperature, respiratory rate, etc.

[0150] If the driver's stress level is high (Yes in step S106), the factor estimating unit 20 assigns a weight to the candidate factor of stress (step S107).

[0151] If the driver has just gotten off or gotten on the vehicle (Yes in step S105), if the driver's stress level is not high (No in step S106), or if stress is weighted as a candidate factor (step S107), the factor estimation unit 20 extracts the heart rate, body temperature, and respiratory rate for a predetermined number of days (step S108). For example, the factor estimation unit 20 extracts them from biological information.

[0152] The factor estimation unit 20 determines whether the stress level for the predetermined number of days is high (step S109). Here, the factor estimation unit 20 determines whether the stress level of the driver for the predetermined number of days is higher than a threshold value that is lower than the threshold value used in step S106. In other words, the threshold value used in step S106 is higher than the threshold value used in step S109.

[0153] If the stress level for the predetermined number of days is high (Yes in step S109), the factor estimation unit 20 assigns a weight to the candidate factor of lack of sleep (step S110).

[0154] If the stress level for a specified number of days is not high (No in step S109), and if the candidate factor of lack of sleep is weighted (step S110), the factor estimation unit 20 determines whether the heart rate, body temperature, and respiratory rate have increased compared to the reference data (step S111).

[0155] If the heart rate, body temperature, and respiratory rate are increased compared to the reference data (Yes in step S111), the factor estimating unit 20 assigns a weight to the candidate factor of cold (step S112).

[0156] The factor estimating unit 20 ends the process if the heart rate, body temperature, and respiratory rate have not increased compared to the reference data (No in step S111) and if the candidate factor of cold has been weighted (step S112).

[0157] The factor estimation unit 20 estimates the factor candidate with the largest weight as the main factor (step S94) (see FIG. 13).

[0158] In this way, the factor estimation unit 20 estimates the factor based on at least one of the section in which the judgment unit 18 judges that the driver's drowsiness is not normal, the driver's drowsiness at the driving start point where the driver starts driving the vehicle 100, and the driver's biometric information.

[0159] Furthermore, the factor estimation unit 20 estimates internal factors that affect drowsiness as factors.

[0160] FIG. 15 is a flowchart showing another example of the operation in step S4 of FIG.

[0161] As shown in FIG. 15, after correcting the drowsiness data (step S31), the determination unit 18 determines whether the time period in which the drowsiness data was acquired is daytime (step S121).

[0162] If the time period during which the drowsiness data was acquired is daytime (Yes in step S121), the determination unit 18 determines whether the driver has got off and gotten in (step S122). For example, the determination unit 18 determines whether the driver has got off and gotten in based on the record of opening and closing of the driver's door of the vehicle 100.

[0163] When the driver gets off and gets back on (Yes in step S122), the determination unit 18 determines that the driver has eaten lunch and corrects the rate of change in drowsiness to slow down (step S123). For example, the determination unit 18 obtains in advance by measuring how much the rate of change in drowsiness will increase as a result of eating lunch, and calculates in advance a correction value that will reduce the change in drowsiness due to eating lunch. The determination unit 18 corrects the rate of change in drowsiness to slow down by multiplying the correction value by the drowsiness data.

[0164] If the time period during which the drowsiness data was acquired is not daytime (No in step S121), if the driver has not gotten off or gotten back in the vehicle (No in step S122), or if the rate of change in drowsiness has been corrected to slow down (step S123), the judgment unit 18 compares the drowsiness data with the reference data and makes a judgment (step S32).

[0165] In this way, the judgment unit 18 calculates a correction value that reduces the change in the driver's drowsiness caused by the driver having lunch, corrects the drowsiness data using the correction value, and compares the corrected drowsiness data with the reference data to judge whether the driver's drowsiness is normal or not.

[0166] The determination system 10 according to this embodiment includes a determination unit 18 that determines whether the driver's drowsiness is normal or not based on drowsiness data related to the drowsiness of the driver driving the moving body (vehicle 100) and reference data related to drowsiness that serves as a standard for determining whether the driver's drowsiness is normal or not.

[0167] This makes it possible to determine whether the driver's drowsiness is normal or not based on the drowsiness data and the reference data.

[0168] Furthermore, in the determination system 10 according to this embodiment, the determination unit 18 compares a first rate of change, which is the rate of change of drowsiness indicated by the drowsiness data, with a second rate of change, which is the rate of change of drowsiness indicated by the reference data, and if the first rate of change is greater than the second rate of change, determines that the driver's drowsiness is not normal.

[0169] According to this, when the first rate of change is greater than the second rate of change, it can be determined that the driver's drowsiness is not normal.

[0170] In the determination system 10 according to the present embodiment, the determination unit 18 calculates a correction value for correcting the drowsiness data.

[0171] This allows a determination as to whether the driver's drowsiness is normal or not based on the drowsiness data corrected using the correction value and the reference data, thereby enabling a more accurate determination as to whether the driver's drowsiness is normal or not.

[0172] Furthermore, in the determination system 10 according to this embodiment, the determination unit 18 calculates a correction value that reduces changes in the driver's drowsiness due to external factors that affect the drowsiness.

[0173] This allows a determination of whether the driver's drowsiness is normal based on drowsiness data corrected to reduce changes in the driver's drowsiness due to external factors and reference data, thereby making it possible to more accurately determine whether the driver's drowsiness has become abnormal due to factors other than external factors.

[0174] Furthermore, in the determination system 10 according to this embodiment, the determination unit 18 calculates a correction value that reduces the change in the driver's sleepiness caused by the driver having lunch.

[0175] This allows a determination as to whether the driver's drowsiness is normal or not based on the drowsiness data corrected to reduce the change in the driver's drowsiness due to eating lunch and the reference data, thereby making it possible to more accurately determine whether the driver's drowsiness has become abnormal due to factors other than eating lunch.

[0176] Furthermore, in the determination system 10 according to this embodiment, the determination unit 18 compares the first drowsiness, which is the driver's drowsiness indicated by the drowsiness data and which is the driver's drowsiness at the driving start point when the driver started driving the moving body (vehicle 100), with the second drowsiness, which is the driver's past drowsiness indicated by the reference data and which is the driver's past drowsiness at the driving start point, and determines that the driver's drowsiness is not normal if the first drowsiness is greater than the second drowsiness.

[0177] According to this, if the first drowsiness level is greater than the second drowsiness level, it can be determined that the driver's drowsiness level is not normal.

[0178] Furthermore, in the determination system 10 according to this embodiment, the determination unit 18 determines whether the driver's drowsiness is normal or not based on drowsiness data indicating an increasing tendency of drowsiness and reference data.

[0179] This makes it possible to determine whether the driver's drowsiness is normal or not when the driver's drowsiness is increasing.

[0180] Furthermore, the determination system 10 according to this embodiment includes an estimation unit (factor estimation unit 20) that, when the determination unit 18 determines that the driver's drowsiness is not normal, estimates the factor that causes the driver's drowsiness to be abnormal.

[0181] This allows for estimation of the cause of abnormal driver drowsiness.

[0182] In the determination system 10 according to the present embodiment, the estimation unit (factor estimation unit 20) estimates the factor based on the drowsiness data and the reference data.

[0183] According to this, the cause of the driver's abnormal drowsiness can be estimated based on the drowsiness data and the reference data, so that the cause of the driver's abnormal drowsiness can be estimated with higher accuracy.

[0184] Furthermore, in the determination system 10 according to this embodiment, the estimation unit (factor estimation unit 20) estimates the factor based on at least one of the section in which the determination unit 18 determines that the driver's drowsiness is not normal, the driver's drowsiness at the driving start point where the driver starts driving the moving body (vehicle 100), and the driver's biometric information.

[0185] This allows the factors causing the driver's drowsiness to be abnormal to be estimated based on at least one of the section where the judgment unit 18 judges that the driver's drowsiness is abnormal, the driver's drowsiness at the driving start point where the driver starts driving the moving body (vehicle 100), and the driver's biometric information, thereby allowing the factors causing the driver's drowsiness to be estimated more accurately.

[0186] In the determination system 10 according to the present embodiment, the estimation unit (factor estimation unit 20) estimates, as a factor, an internal factor that influences drowsiness.

[0187] This makes it possible to estimate the internal factors that cause the driver's drowsiness to be abnormal.

[0188] The determination system 10 according to this embodiment also includes a control unit 22 that controls reporting to the moving body (vehicle 100) based on the determination result of the determination unit 18.

[0189] According to this, the report to the moving body (vehicle 100) can be controlled based on the judgment result of the judgment unit 18, so that the driver of the moving body (vehicle 100) does not receive any particular report if the driver's drowsiness is normal, but can receive a report if the driver's drowsiness is not normal.

[0190] In addition, the determination system 10 according to this embodiment includes a generation unit 16 that extracts one or more past data related to past drowsiness based on the route on which the drowsiness data was acquired and the time period in which the drowsiness data was acquired, and generates reference data based on the one or more past data.

[0191] This allows reference data to be generated using one or more pieces of past data extracted based on the route and time period in which the drowsiness data was acquired, making it possible to more accurately determine whether the driver's drowsiness is normal.

[0192] Furthermore, in the determination system 10 according to this embodiment, the generation unit 16 extracts, as one or more pieces of past data, a plurality of pieces of past data relating to past drowsiness that were acquired along a route that matches the route on which the drowsiness data was acquired, a plurality of pieces of past data relating to past drowsiness that were acquired along a route that partially matches the route on which the drowsiness data was acquired, or a plurality of pieces of past data relating to past drowsiness that were acquired within a predetermined section from the starting point of a route whose starting point matches the route on which the drowsiness data was acquired.

[0193] This allows reference data to be generated using one or more past data acquired on a route that matches or is similar to the route on which the drowsiness data was acquired, thereby making it possible to more accurately determine whether the driver's drowsiness is normal.

[0194] (Other embodiments, etc.) Although the determination system according to one or more aspects has been described based on the embodiments, the present disclosure is not limited to these embodiments. As long as the modifications do not deviate from the spirit of the present disclosure, modifications that are conceivable by those skilled in the art may also be included within the scope of the present disclosure.

[0195] In the above-described embodiments, each component may be configured with dedicated hardware, or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU (Central Processing Unit) or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory. Here, the software that realizes the devices and the like of the above-described embodiments is a program that causes a computer to execute each step included in the flowcharts shown in Figures 4 to 15.

[0196] The following cases are also included in this disclosure:

[0197] (1) Each of the above devices is specifically a computer system consisting of a microprocessor, ROM, RAM, hard disk unit, display unit, keyboard, mouse, etc. A computer program is stored in the RAM or hard disk unit. Each device achieves its function when the microprocessor operates in accordance with the computer program. Here, a computer program is composed of a combination of multiple instruction codes that indicate commands to a computer to achieve a predetermined function.

[0198] (2) Some or all of the components constituting each of the above devices may be configured as a single system LSI (Large Scale Integration). A system LSI is an ultra-multifunctional LSI manufactured by integrating multiple components on a single chip, and specifically, is a computer system configured to include a microprocessor, ROM, RAM, etc. A computer program is stored in the RAM. The system LSI achieves its functions when the microprocessor operates in accordance with the computer program.

[0199] (3) Some or all of the components constituting each of the above devices may be configured as an IC card or a standalone module that can be attached to each device. The IC card or module is a computer system composed of a microprocessor, ROM, RAM, etc. The IC card or module may include the above-mentioned ultra-multifunctional LSI. The IC card or module achieves its functions when the microprocessor operates according to a computer program. The IC card or module may be tamper-resistant.

[0200] (4) The present disclosure may be embodied as the methods described above, a computer program for implementing these methods on a computer, or a digital signal comprising the computer program.

[0201] The present disclosure may also be the computer program or the digital signal recorded on a computer-readable recording medium, such as a flexible disk, hard disk, CD-ROM, MO, DVD, DVD-ROM, DVD-RAM, BD (Blu-ray (registered trademark) Disc), semiconductor memory, etc. Alternatively, the present disclosure may be the digital signal recorded on such a recording medium.

[0202] Furthermore, the present disclosure may involve transmitting the computer program or the digital signal via a telecommunications line, a wireless or wired communication line, a network such as the Internet, data broadcasting, or the like.

[0203] The present disclosure may also be a computer system including a microprocessor and a memory, the memory storing the computer program, and the microprocessor operating in accordance with the computer program.

[0204] The program or the digital signal may also be implemented by another independent computer system by recording it on the recording medium and transferring it, or by transferring it via the network or the like.

[0205] (5) The above-described embodiments and other embodiments may be combined.

[0206] (Addendum) The above description of the embodiments and the like discloses the following techniques.

[0207] (Technology 1) a determination unit that determines whether the drowsiness of a driver who drives a moving object is normal or not based on drowsiness data related to the drowsiness of the driver and reference data related to drowsiness that serves as a reference for determining whether the drowsiness of the driver is normal or not, Judging system.

[0208] (Technology 2) The determination unit compares a first rate of change, which is a rate of change in drowsiness indicated by the drowsiness data, with a second rate of change, which is a rate of change in drowsiness indicated by the reference data, and determines that the driver's drowsiness is not normal when the first rate of change is greater than the second rate of change. The determination system described in Technology 1.

[0209] (Technology 3) The determination unit calculates a correction value for correcting the drowsiness data. The determination system according to technique 1 or 2.

[0210] (Technology 4) the determination unit calculates the correction value to reduce a change in the driver's drowsiness due to an external factor that affects the drowsiness. The determination system described in Technology 3.

[0211] (Technology 5) the determination unit calculates the correction value to reduce a change in the driver's drowsiness caused by the driver having lunch. The determination system described in Technology 3.

[0212] (Technology 6) the determination unit compares a first drowsiness level, which is indicated by the drowsiness data and is the drowsiness of the driver at a driving start point where the driver started driving the moving object, with a second drowsiness level, which is indicated by the reference data and is the driver's past drowsiness at the driving start point, and determines that the driver's drowsiness is not normal when the first drowsiness level is greater than the second drowsiness level. 6. A determination system according to any one of techniques 1 to 5.

[0213] (Technology 7) the determination unit determines whether the driver's drowsiness is normal or not based on the drowsiness data indicating an increasing tendency of drowsiness and the reference data. 7. A determination system according to any one of techniques 1 to 6.

[0214] (Technology 8) an estimation unit that, when the determination unit determines that the driver's drowsiness is not normal, estimates a factor that causes the driver's drowsiness to be abnormal; The determination system described in Technology 1.

[0215] (Technology 9) The estimation unit estimates the factor based on the drowsiness data and the reference data. The determination system described in Technology 8.

[0216] (Technology 10) the estimation unit estimates the factor based on at least one of a section in which the determination unit determines that the driver's drowsiness is not normal, the driver's drowsiness at a driving start point where the driver starts driving the moving object, and biological information of the driver. The determination system according to technique 8 or 9.

[0217] (Technology 11) The estimation unit estimates an internal factor affecting drowsiness as the factor. A determination system according to any one of techniques 8 to 10.

[0218] (Technology 12) a control unit that controls a report to the moving object based on a determination result of the determination unit; A determination system according to any one of techniques 1 to 11.

[0219] (Technology 13) a generation unit that extracts one or more pieces of past data related to past drowsiness based on a route on which the drowsiness data was acquired and a time period on which the drowsiness data was acquired, and generates the reference data based on the one or more pieces of past data; 13. A determination system according to any one of techniques 1 to 12.

[0220] (Technology 14) the generation unit extracts, as the one or more pieces of past data, a plurality of pieces of past data relating to past drowsiness that have been acquired along a route that matches the route on which the drowsiness data has been acquired, a plurality of pieces of past data relating to past drowsiness that have been acquired along a route that partially matches the route on which the drowsiness data has been acquired, or a plurality of pieces of past data relating to past drowsiness that have been acquired along a route whose starting point matches the route on which the drowsiness data has been acquired in a predetermined section from the starting point of the route on which the drowsiness data has been acquired. The determination system described in Technology 13. [Industrial Applicability]

[0221] The present disclosure can be used in a system that determines whether a driver's drowsiness is normal or not. [Explanation of symbols]

[0222] 10 Judgment System 12 Processing Server 14,32,38,201 databases 16 Generation part 18 Judgment section 20 Factor estimation section 22 Control Unit 24 Data Acquisition Section 26 Sensor data acquisition unit 28 Drowsiness data acquisition unit 30 Operation management data acquisition unit 34 Extraction part 36 Reference data generation unit 40 Processing section 42 Correction unit 44 Comparison section 100 vehicles 101 Drive Recorder 102 Driver Monitoring System 103 Drowsiness estimation unit 200 Traffic Management System

Claims

1. A determination system including a determination unit that extracts a plurality of past data from drowsiness data, which is time-series data on the drowsiness level of a driver who drives a mobile object, and past data, which is drowsiness data previously acquired based on a route on which the drowsiness data was acquired and a time period on which the drowsiness data was acquired, and compares the plurality of past data with reference data, which is time-series data on the drowsiness level, generated as a reference for determining whether the drowsiness level of the driver is within a normal range, to determine whether the drowsiness level of the driver is normal, The determination system includes: an extraction unit that extracts a plurality of past data acquired along a route that matches a route from a driving start point of the mobile body to a current point, a plurality of past data acquired along a route that partially matches a route from a driving start point of the mobile body to a current point, or a plurality of past data acquired along a route where a driving start point of the mobile body matches a driving start point; a reference data generating unit that generates the reference data by adding up the plurality of pieces of past data when the time period during which the plurality of pieces of past data extracted by the extracting unit was acquired coincides with the time period from the driving start point of the mobile body to the current point, and dividing the added up data by the number of the plurality of pieces of past data; The drowsiness level is an index indicating the intensity of drowsiness, and a higher drowsiness level indicates a stronger drowsiness, The determination unit compares a first rate of change, which is an increase rate of time-series data of the drowsiness level indicated by the drowsiness data during a time period when the drowsiness level is acquired, with a second rate of change, which is an increase rate of time-series data of the drowsiness level indicated by the reference data, and determines that the driver's drowsiness is not normal when the first rate of change is greater than an increase rate obtained by adding a threshold value to the second rate of change. Judging system.

2. the determination unit compares a first drowsiness level, which is indicated by the drowsiness data and which is the drowsiness of the driver at a driving start point where the driver started driving the moving object, with a second drowsiness level, which is indicated by the reference data and which is the past drowsiness of the driver at the driving start point, and determines that the drowsiness of the driver is not normal when the first drowsiness level is greater than the second drowsiness level. The determination system according to claim 1 .

3. the determination unit determines whether the driver's drowsiness is normal based on the drowsiness data in which time-series data of the drowsiness level shows an increasing trend and the reference data. The determination system according to claim 1 .

4. an estimation unit that estimates that there is an internal factor that affects the drowsiness of the driver when the determination unit determines that the drowsiness of the driver is not normal and when at least one of the drowsiness data, the past data, the sensor data acquired using one or more sensors, and the operation management data related to operation management of the mobile body satisfies a predetermined condition; The determination system according to claim 1 .

5. the estimation unit estimates that the internal factor exists when at least one of the section in which the determination unit determines that the driver's drowsiness is not normal, the rate of increase in the driver's drowsiness level at the driving start point where the driver starts driving the moving object, the driver's biological information, and the month in which the past data was acquired satisfies a predetermined condition. The determination system according to claim 4 .

6. The estimation unit estimates, as the driver's internal factors that affect drowsiness, at least one of taking medication, eating lunch, feeling unwell, lack of sleep, fatigue the day before, and pollen season. The determination system according to claim 5 .

7. the estimation unit estimates that the internal cause is fatigue or lack of sleep the previous day when the drowsiness level in the first half of the route from the driving start point to the current point is abnormal and when the drowsiness level at the driving start point is greater than the drowsiness level of the reference data by a threshold or more. The determination system according to claim 6 .

8. the estimation unit estimates poor physical condition as the internal cause when the heart rate, body temperature, and respiratory rate are increased compared to reference data; The determination system according to claim 6 .

9. a control unit that controls a report to the moving object based on a determination result of the determination unit; The determination system according to claim 1 .

Images