Characteristic change detection system, characteristic change detection device, in-vehicle device, characteristic change detection method, and computer program

Abstract

A characteristic change detection system includes a characteristic change detection device that detects a characteristic change of a driver who drives a vehicle over the years using vehicle information related to running of the vehicle. The characteristic change detection device includes a determination section that determines whether the vehicle information indicates a normal characteristic or a dangerous characteristic with reference to a first distribution indicating the normal characteristic and a second distribution indicating the dangerous characteristic.

Description

Technical Field

[0001] This disclosure relates to a characteristic change detection system, a characteristic change detection device, an on-vehicle device, a characteristic change detection method, and a computer program. This application claims priority to Japanese Application No. 2024-020754, filed February 15, 2024. The entire contents of that application are incorporated herein by reference. Background Technology

[0002] As society ages, the proportion of elderly drivers is increasing, leading to a rise in traffic accidents caused by them. Elderly individuals experience physical changes due to age, including decreased dynamic vision, reduced ability to process multiple pieces of information simultaneously, and a decline in the capacity for instantaneous judgment. These changes manifest as slower steering or braking maneuvers in older drivers.

[0003] However, because human function tends to decline gradually, drivers may find it difficult to notice slowed judgment in steering wheel or brake operation during their daily driving.

[0004] As a technology related to driving, techniques for warning drivers when their condition is presumed to be abnormal are known. Such a technique is disclosed in Patent Document 1, which will be described later. In the technique disclosed in Patent Document 1, a probability distribution of normal and abnormal driving states is defined, and the appropriateness of the driver's driving is presumed based on this probability distribution. In Patent Document 1, a warning message is also displayed on a display device based on the presumed appropriateness of the driver's driving state.

[0005] Existing technical documents Patent documents Patent Document 1: Japanese Patent Application Publication No. 2009-145951 Summary of the Invention

[0006] A characteristic change detection system according to one aspect of this disclosure includes a characteristic change detection device, wherein the characteristic change detection device uses vehicle information related to vehicle operation to detect annual characteristic changes of the driver driving the vehicle. The characteristic change detection device includes a judgment unit, wherein the judgment unit determines whether the vehicle information represents normal characteristics or dangerous characteristics by referring to a pre-prepared first distribution representing normal characteristics and a second distribution representing dangerous characteristics.

[0007] This disclosure can be implemented not only as a characteristic change detection system, characteristic change detection device, vehicle-mounted device, characteristic change detection method, and computer program including such characteristic configurations, but also as other systems, devices, methods, or computer programs including a characteristic change detection system, characteristic change detection device, vehicle-mounted device, characteristic change detection method, or computer program. Attached Figure Description

[0008] Figure 1 This is a diagram used to illustrate a configuration example of the characteristic change detection system of the first embodiment.

[0009] Figure 2 It means Figure 1 The diagram shows a block diagram of an example of the hardware configuration of an in-vehicle device.

[0010] Figure 3 It means Figure 1 The diagram shown is a block diagram of an example of the hardware configuration of a server.

[0011] Figure 4 It means including Figure 1 The diagram shows an example of the functional configuration of an in-vehicle system for an in-vehicle device.

[0012] Figure 5 It means Figure 1 The diagram shown is a block diagram illustrating an example of the functional configuration of a server.

[0013] Figure 6 This is a diagram used to illustrate the method for detecting changes in characteristics.

[0014] Figure 7 This is a graph representing an example of driving data for a driver with normal characteristics.

[0015] Figure 8 This is a graph representing an example of driving data from a driver who may have dangerous characteristics.

[0016] Figure 9 It is a graph representing the frequency distribution of the difference in accelerator opening per unit time during cruise.

[0017] Figure 10 It is a graph representing the frequency distribution of the difference in accelerator opening per unit time during acceleration.

[0018] Figure 11 This is a flowchart illustrating an example of the control structure of a program executed on a server according to the first embodiment.

[0019] Figure 12 This is a flowchart illustrating an example of the control structure of a program executed on a server according to the first embodiment.

[0020] Figure 13 This is a flowchart illustrating an example of the control structure of a program executed on a server according to the first embodiment.

[0021] Figure 14 This is a flowchart illustrating an example of the control structure of a program executed on a server according to the first embodiment.

[0022] Figure 15 This is a diagram illustrating an example of grouping drivers based on their characteristics.

[0023] Figure 16 This is a diagram used to illustrate the update process for the cumulative risk value.

[0024] Figure 17 This is a flowchart illustrating an example of the control structure of a program executed on a server according to the first embodiment.

[0025] Figure 18 This is a flowchart illustrating an example of the control structure of a program executed on a server in the first variant.

[0026] Figure 19 This is a diagram used to illustrate a configuration example of the characteristic change detection system of the second embodiment.

[0027] Figure 20 This is a diagram used to illustrate a configuration example of the system in the third embodiment.

[0028] Figure 21 It means Figure 20 The diagram shows an example of the functional configuration of an on-board device. Detailed Implementation

[0029] [The problem this disclosure aims to solve] The technology disclosed in Patent Document 1 estimates a driver's appropriateness based on their state of being different from normal, such as drowsy, intoxicated, or inattentive. In other words, the technology disclosed in Patent Document 1 estimates the driver's state while driving. Therefore, even using the technology disclosed in Patent Document 1, it is difficult to detect changes in driver characteristics over time.

[0030] This disclosure was made to solve such problems, and one object of this disclosure is to provide a characteristic change detection system, characteristic change detection device, vehicle-mounted device, characteristic change detection method, and computer program capable of detecting changes in driver characteristics.

[0031] [Effects of this disclosure] According to this disclosure, a characteristic change detection system, a characteristic change detection device, an on-board device, a characteristic change detection method, and a computer program are provided that can detect changes in the characteristics of a driver.

[0032] [Description of embodiments of this disclosure] Preferred embodiments of this disclosure are described below. At least some of the embodiments described below may also be combined arbitrarily.

[0033] (1) The characteristic change detection system of the first aspect of this disclosure includes a characteristic change detection device, wherein the characteristic change detection device uses vehicle information related to the driving of the vehicle to detect the characteristic changes of the driver of the vehicle over the years. The characteristic change detection device includes a judgment unit, wherein the judgment unit determines whether the vehicle information represents normal characteristics or dangerous characteristics by referring to a first distribution representing normal characteristics and a second distribution representing dangerous characteristics prepared in advance.

[0034] The judgment unit refers to a first distribution representing normal characteristics and a second distribution representing dangerous characteristics to determine whether vehicle information represents normal or dangerous characteristics. Therefore, even if the driver's characteristics change over the years, changes in driver characteristics can be detected.

[0035] (2) In (1) above, the characteristic change detection device includes: an accumulation unit that performs the following processing: for vehicle information that the judgment unit determines to represent normal characteristics, it maintains the count value of the danger level; for vehicle information that the judgment unit determines to represent dangerous characteristics, it accumulates the danger level by increasing the count value of the danger level; and a characteristic change detection unit that detects that the driver's characteristics have changed to dangerous characteristics based on whether the count value of the danger level accumulated by the accumulation unit is greater than or equal to a predetermined threshold.

[0036] The accumulation unit performs the following processing: for vehicle information determined by the judgment unit to represent normal characteristics, the danger level count is maintained; for vehicle information determined by the judgment unit to represent dangerous characteristics, the danger level is accumulated by increasing the danger level count. The characteristic change detection unit detects whether the driver's characteristic has changed to a dangerous characteristic based on whether the danger level count is greater than or equal to a predetermined threshold. Therefore, even if the driver's characteristics change over the years, changes in driver characteristics can be detected.

[0037] (3) In (1) or (2) above, the device may also be configured such that the characteristic change detection device further includes a notification unit, which notifies at least one of the driver and the manager who manages the driver that the driver's characteristic has changed into a dangerous characteristic. This allows the driver to become aware that the driver's characteristic has changed.

[0038] (4) In any of (1) to (3) above, the vehicle information may also be configured such that it includes time-series information of at least one of the following: accelerator opening, brake pressure, and steering wheel angle. Thus, changes in the driver's driving characteristics can be detected with high precision.

[0039] (5) In (4) above, it can also be configured as follows: the judgment unit calculates the difference between the data in each unit of time in the time series information and the previous data which is the data in the previous unit of time, and judges whether the calculated difference represents normal characteristics or dangerous characteristics by referring to the first distribution and the second distribution. As a result, the changes in the driver's driving characteristics can be detected with higher precision.

[0040] (6) In any of (1) to (5) above, the device may also be configured such that the characteristic change detection device further includes: an information acquisition unit that acquires at least one of the following: the driver's biological information, the vehicle's driving information, and the environmental information outside the vehicle when the vehicle is in motion; and a characteristic estimation unit that estimates the driver's characteristics based on the information acquired by the information acquisition unit. Thus, when the driver's characteristics change, it is possible to estimate what kind of characteristic has changed.

[0041] (7) In (6) above, the system may also be configured such that the characteristic change detection system further includes a seating sensor, wherein the seating sensor is located on the seat where the driver sits, and the on-board device also sends sensor data from the seating sensor as biological information to the characteristic change detection device. Thus, for example, it is possible to infer changes in characteristics related to the driver's driving posture.

[0042] (8) In (6) or (7) above, the vehicle-mounted device may also be configured such that it sends the vehicle's position information during driving as driving information to the characteristic change detection device. Thus, for example, it is possible to infer changes in characteristics related to dynamic vision or information processing capabilities.

[0043] (9) In any of (6) to (8) above, the configuration may also be such that the characteristic change detection device communicates with an external server, and the information acquisition unit obtains weather information of the driving area of ​​the vehicle from the external server as environmental information. Thus, for example, it is possible to infer changes in characteristics related to vision or information processing ability.

[0044] (10) In (2) above, the device may also be configured such that the characteristic change detection device further includes a setting receiving unit, wherein the setting receiving unit accepts the setting of the period for accumulating the hazard level, and the accumulation unit accumulates the hazard level during the period accepted by the setting receiving unit. Thus, it is possible to prevent the hazard level from accumulating without limit.

[0045] (11) In (10) above, it can also be configured such that when the period for acceptance by the set acceptance unit is exceeded, the accumulation unit accumulates the hazard level by shifting the period and deletes the data that becomes outside the period due to the shift, thereby updating the hazard level count. The characteristic change detection device further includes: a normal characteristic detection unit that detects whether the driver's characteristic has changed from a hazardous characteristic to a normal characteristic based on whether the updated hazard level count is less than a predetermined threshold; and a normal characteristic change notification unit that notifies at least one of the driver and the manager who manages the driver that the driver's characteristic has changed to a normal characteristic. Thus, it is possible to detect whether the driver's characteristic has returned to a normal characteristic.

[0046] (12) The vehicle-mounted device of the second aspect of this disclosure is mounted on a vehicle and sends vehicle information to the characteristic change detection device of the characteristic change detection system described in (1) or (2) above. As a result, characteristic changes of the driver can be detected.

[0047] (13) The characteristic change detection device of the third aspect of this disclosure includes: an acquisition unit for acquiring vehicle information related to the driving of the vehicle; and a processing unit for performing processing to detect the annual characteristic changes of the driver of the vehicle using the vehicle information acquired by the acquisition unit. The processing unit includes a judgment unit, wherein the judgment unit determines whether the vehicle information represents normal characteristics or dangerous characteristics by referring to a first distribution representing normal characteristics and a second distribution representing dangerous characteristics prepared in advance. Thus, characteristic changes of the driver can be detected.

[0048] (14) In (13) above, the processing unit further includes: an accumulation unit that performs the following processing: for vehicle information that the determination unit determines represents a normal characteristic, it maintains the danger level count value; for vehicle information that the determination unit determines represents a dangerous characteristic, it accumulates the danger level by increasing the danger level count value; and a characteristic change detection unit that detects whether the driver's characteristic has changed to a dangerous characteristic based on whether the danger level count value accumulated by the accumulation unit is greater than or equal to a predetermined threshold. Thus, it is possible to detect changes in the driver's characteristics.

[0049] (15) In (13) or (14) above, the characteristic change detection device may also be a server device that communicates with the vehicle. In this way, the characteristic changes of the driver can be easily detected.

[0050] (16) In (13) or (14) above, the characteristic change detection device may also be an on-board device mounted on the vehicle. In this way, it is easy to detect the characteristic changes of the driver.

[0051] (17) The characteristic change detection method of the fourth aspect of this disclosure is a method for detecting annual characteristic changes of a driver of a vehicle, wherein the characteristic change detection method includes: an acquisition step in which a computer acquires vehicle information related to the driving of the vehicle; and a detection step in which the computer uses the vehicle information acquired in the acquisition step to detect characteristic changes of the driver of the vehicle. The characteristic change detection step includes a judgment step in which the vehicle information is judged to represent normal characteristics or dangerous characteristics by referring to a pre-prepared first distribution representing normal characteristics and a second distribution representing dangerous characteristics. Thus, characteristic changes of the driver can be detected.

[0052] (18) In (17) above, the detection step includes: an accumulation step, which performs the following processing: for vehicle information judged to represent normal characteristics in the judgment step, maintaining the danger level count value; for vehicle information judged to represent dangerous characteristics in the judgment step, accumulating the danger level by increasing the danger level count value; and a step of detecting whether the driver's characteristics have changed to dangerous characteristics based on whether the danger level count value accumulated in the accumulation step is greater than or equal to a predetermined threshold. Thus, changes in the driver's characteristics can be detected.

[0053] (19) The computer program of the fifth aspect of this disclosure enables a computer to detect changes in the characteristics of a driver of a vehicle over many years, wherein the computer program causes the computer to perform: an acquisition step, acquiring vehicle information related to the driving of the vehicle; and a detection step, using the vehicle information acquired in the acquisition step to detect changes in the characteristics of the driver of the vehicle. The detection step includes a judgment step, in which the vehicle information is judged to represent normal characteristics or dangerous characteristics by referring to a pre-prepared first distribution representing normal characteristics and a second distribution representing dangerous characteristics. Thus, changes in the driver's characteristics can be detected.

[0054] (20) In (19) above, the detection step includes: an accumulation step, which performs the following processing: for vehicle information judged to represent normal characteristics in the judgment step, maintaining the danger level count value; for vehicle information judged to represent dangerous characteristics in the judgment step, accumulating the danger level by increasing the danger level count value; and a step of detecting whether the driver's characteristics have changed to dangerous characteristics based on whether the danger level count value accumulated in the accumulation step is greater than or equal to a predetermined threshold. Thus, changes in the driver's characteristics can be detected.

[0055] [Details of the embodiments disclosed herein] Hereinafter, specific examples of characteristic change detection systems, characteristic change detection devices, vehicle-mounted devices, characteristic change detection methods, and computer programs according to embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be noted that in the following embodiments, the same reference numerals are used to label the same components, etc. Their functions and names are also the same. Therefore, detailed descriptions related to them will not be repeated.

[0056] (First Implementation) [Overall Composition] Reference Figure 1 The characteristic change detection system 50 of this embodiment includes an on-board unit 100 mounted on a vehicle 60 and a server 200 communicating with the on-board unit 100. This characteristic change detection system 50 detects changes in the characteristics of the driver of the vehicle 60 over the years and notifies the driver of these changes. By notifying the driver of changes in their characteristics, the characteristic change detection system 50 helps the driver recognize changes in their bodily functions. In the case of a manager 70 who manages the driver, the notification to the driver can also be made through the manager 70. Furthermore, it can also be configured such that the driver's relatives 80 or other relatives are notified of the characteristic change, and the relatives 80 or other relatives then inform the driver.

[0057] In this embodiment, the server 200 notifies the driver, the driver's manager 70, or the driver's relative 80 of a change in characteristics. Therefore, in addition to communicating with the vehicle-mounted device 100, the server 200 also communicates with the terminal device 72 used by the manager 70 and the portable terminal 82 held by the driver's relative 80. However, this disclosure is not limited to this configuration. For example, it could be configured such that the server 200 only notifies the manager 70 of a change in characteristics for the driver. In this case, it could also be configured such that the manager 70 informs the driver or the driver's relative 80 of the change in characteristics. For example, it could also be configured such that the server 200 only notifies the driver's relative 80 of a change in characteristics for the driver. In this case, it could also be configured such that the driver's relative 80 informs the driver of the change in characteristics.

[0058] Vehicle 60 may be a delivery vehicle such as a truck, and the driver of vehicle 60 may be an employee of a delivery company. In this case, the manager 70 manages vehicle 60 and its driver, which are the vehicles under surveillance. The manager 70 may also have the function of registering the monitored vehicles and drivers into the system. In this embodiment, such a configuration will be used as an example for explanation.

[0059] Server 200 uses data sent from the vehicle-mounted device 100 to detect changes in the characteristics of the driver of the vehicle 60 over the years. Therefore, server 200 can also be described as a characteristic change detection device. Server 200 is, for example, a cloud server. However, server 200 is not limited to this and can also be other server devices such as locally deployed servers or edge servers.

[0060] The vehicle-mounted device 100 sends vehicle data and other ancillary data related to the driving of the vehicle 60 equipped with the vehicle-mounted device 100 to the outside. Specifically, the vehicle-mounted device 100 communicates with the server 200 and sends vehicle data and ancillary data to the server 200.

[0061] Vehicle data includes location data indicating the driving position of vehicle 60 and driving data of vehicle 60 during driving. Location data includes, for example, GPS (Global Positioning System) data and other location coordinate data, including time information during driving. For example, location data can be obtained from a vehicle navigation device (hereinafter referred to as "in-vehicle navigation") installed in vehicle 60. Driving data includes, for example, time-series information of accelerator opening, brake pressure, and steering wheel angle. Driving data can also be time-series information of at least one of accelerator opening, brake pressure, and steering wheel angle. For example, CAN (Controller Area Network) information can be used for driving data.

[0062] The accompanying data includes biosensor data of the driver. This biosensor data is sensor data from a biosensor. The biosensor includes a seating sensor, which is a body pressure sensor located in the driver's seat within the vehicle 60. Alternatively, the biosensor may be configured to include a wearable device or fitness tracker worn by the driver instead of a seating sensor, or it may include both a seating sensor and a wearable device or fitness tracker worn by the driver. In this case, the measurement data used as biosensor data may include the driver's heart rate, driver's pressure, driver's physical condition data, etc. Furthermore, if the vehicle 60 is equipped with an onboard camera that captures images of the exterior of the vehicle 60, the image data captured by the onboard camera can also be used as accompanying data. Environmental information about the vehicle 60 while driving can be obtained from the onboard camera's image data. For example, information such as whether it is nighttime driving, whether there is traffic congestion, or whether visibility is poor due to rain, can be obtained from the image data.

[0063] The vehicle-mounted device 100 receives vehicle data and incidental data (including driver's biosensor data) from the vehicle 60 and the biosensor respectively during a predetermined cycle, and sends the received data to the server 200.

[0064] Server 200 receives vehicle data and associated data sent from vehicle-mounted device 100. Server 200 also communicates with external server 90, which serves as an external data source. External server 90 can be multiple servers or a single server. External server 90 provides information about the external environment of vehicle 60 while it is in motion. This environmental information includes, for example, weather data and time data. Server 200 primarily uses the vehicle data from this received data to detect changes in the characteristics of the driver of vehicle 60.

[0065] Changes in driver characteristics include shifts from normal to dangerous characteristics. Normal characteristics refer to the driver's ability to drive normally. Dangerous characteristics refer to the driver's physical decline that could lead to dangerous situations while driving. Such changes often occur over many years. Therefore, drivers may find it difficult to notice their characteristics changing to dangerous levels during daily driving.

[0066] For example, slow judgment in steering wheel or brake operation, which falls under the category of hazardous characteristics, can also occur within normal characteristics. That is, slow judgment can also be a fluctuation within the range of normal characteristics. Therefore, even if slow judgment occurs, it is difficult to immediately determine that the driver's characteristics have changed from normal to hazardous. The same applies to the driver themselves.

[0067] To address such adverse situations, the server 200 in this embodiment uses vehicle data sent from the vehicle-mounted device 100 to capture subtle changes in the driver's usual accelerator and brake operations. The server 200 accumulates these changes to detect when the driver's characteristics have changed to a dangerous characteristic. When a dangerous change in the driver's characteristics is detected, the characteristic change detection system 50 notifies the driver that their characteristics have changed to a dangerous characteristic, thus making the driver aware of the change.

[0068] Changes in these characteristics are often accompanied by a decline in physical function due to aging, and therefore these changes are more likely to occur in older drivers. Therefore, hazardous characteristics are treated in the same way as those observed in older drivers. Examples of characteristics associated with older drivers include the following.

[0069] Characteristics of elderly drivers (1) Due to overall physical decline, it is difficult to perform proper driving operations. In addition, it is difficult to drive for extended periods of time.

[0070] (2) Due to weakened vision, it is difficult to obtain information related to the surrounding situation and make appropriate judgments.

[0071] (3) Due to the dulling of reflexes, immediate responses may sometimes be slow.

[0072] (4) Drivers tend to become self-centered and find it difficult to objectively grasp traffic conditions.

[0073] As a characteristic of older drivers, slow reaction time is generally dominant. Therefore, it is important to detect the shift towards older driver characteristics before they become significant (i.e., before the characteristics of older drivers become salient) and to provide attentional reminders or guide drivers towards mechanisms that prevent slow reaction time.

[0074] As mentioned above, older drivers exhibit a variety of characteristics. Therefore, if it is known what characteristics have changed, then paying attention to reminding them or guiding them towards mechanisms that prevent slowed reaction times becomes more effective.

[0075] With this in mind, in the characteristic change detection system 50 of this embodiment, the changed characteristics of elderly drivers are inferred in more detail based on the vehicle location data and associated data received from the vehicle-mounted device 100 and environmental information from the external server 90.

[0076] [Hardware Configuration] (Vehicle-mounted device 100) Reference Figure 2 The vehicle-mounted device 100 includes a computer 102. The computer 102 includes: a control unit 110 for controlling the entire vehicle-mounted device 100; a memory 120 for storing various data; an in-vehicle communication unit 130 for communicating with the vehicle network; and a communication unit 140 for communicating with the external wireless device 62. The control unit 110, memory 120, in-vehicle communication unit 130, and communication unit 140 are all connected to a communication bus 150, and data exchange between them is performed via the communication bus 150.

[0077] The control unit 110 includes an arithmetic unit 112, a ROM (Read Only Memory) 114 storing the startup program of the computer 102, and a RAM (Random Access Memory) 116 capable of being written to and read from at any time. The arithmetic unit 112 includes, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) as the arithmetic element (processor). The memory 120 includes, for example, non-volatile memory such as flash memory. The ROM 114 or the memory 120 stores software (computer programs) and various information (data) for the arithmetic unit 112 to execute.

[0078] The in-vehicle communication unit 130 provides an IF (Interface) for communicating with the vehicle network. The in-vehicle communication unit 130 communicates with the vehicle network according to a defined communication protocol. The vehicle network can be any network such as CAN, LIN (Local Interconnect Network), MOST (Media Oriented Systems Transport), FlexRay, 10BASE-T1S, 100BASE-T1, 1000BASE-T1, CXPI (Clock Extension Peripheral Interface), or ASRB (Automotive Safety Restraints Bus), CAN XL, etc. In this embodiment, although not specifically limited, CAN is used as the vehicle network.

[0079] Under the control of the control unit 110, the vehicle-mounted device 100 (computer 102) receives data (vehicle data and incidental data) used to detect changes in driver characteristics via a vehicle network, and sends the received data to an external server 200 (see reference). Figure 1 The communication unit 140 provides an IF for communicating with the external wireless device 62. The external wireless device 62 is a wireless device for communicating with devices outside the vehicle 60. The communication unit 140 communicates with the server 200 via the external wireless device 62.

[0080] (Server 200) Reference Figure 3Server 200 includes computer 202. Computer 202 includes control unit 210, storage device 220, and communication unit 230. Control unit 210 includes CPU 212, GPU (Graphics Processing Unit) 214, ROM 216, and RAM 218. Control unit 210, storage device 220, and communication unit 230 are all connected to communication bus 240, and data exchange between them is performed via communication bus 240.

[0081] Storage device 220 includes, for example, non-volatile storage devices such as flash memory or hard disk drives. Computer programs and various information for execution by CPU 212 are stored in storage device 220. Communication unit 230 provides a connection to network 64, which enables communication with other devices, including vehicle-mounted device 100.

[0082] Server 200 connects to vehicle-mounted device 100 via network 64 and communication unit 230 (see reference). Figure 1 The server 200 also communicates with external devices other than the vehicle-mounted device 100 via the network 64 and the communication unit 230.

[0083] Server 200 acquires data from onboard unit 100 for detecting changes in the characteristics of the driver of the vehicle 60 equipped with onboard unit 100. Server 200 detects these changes based on the acquired data and provides the results back to the driver. Specifically, server 200 notifies the driver that their characteristics have changed to a state that may pose a danger while driving.

[0084] Computer programs that enable the server 200 to function as the various functional units of the server 200 in this embodiment are distributed via a specified storage medium such as a DVD (Digital Versatile Disc) or USB (Universal Serial Bus) memory, and then transferred from these storage media to the storage device 220. Alternatively, the computer programs may be sent from an external device to the computer 202 via a network 64 and stored in the storage device 220.

[0085] [Functional Composition] (Vehicle System 300) Reference Figure 4The vehicle 60 includes an in-vehicle system 300. The in-vehicle system 300 includes an in-vehicle camera 302, a biosensor 310, an in-vehicle navigation system 320, and an in-vehicle device 100. The in-vehicle camera 302, biosensor 310, in-vehicle navigation system 320, and in-vehicle device 100 are connected to each other via an in-vehicle network 330 in a manner capable of communication. The in-vehicle device 100 is also connected to various ECUs (Electronic Control Units) via the in-vehicle network 330 in a manner capable of communication.

[0086] The vehicle-mounted camera 302 captures images of the exterior of the vehicle 60. Alternatively, it can be configured to include a camera that captures images of the interior of the vehicle 60. For example, this camera can also be used for driver facial recognition. This allows the system to determine whether the driver of the vehicle 60 is a registered driver, thus improving the accuracy of detecting changes in driver characteristics.

[0087] The biosensor 310 includes a seating sensor 312 and a biosensor data measuring device 314. The seating sensor 312 is a body pressure sensor installed in the driver's seat 66 within the vehicle. The seating sensor 312 periodically measures the distribution of body pressure of the driver seated in the seat 66 and outputs this distribution as sensor data. The sensor data output by the seating sensor 312 includes seat pressure data. The biosensor data measuring device 314 is, for example, a heart rate sensor that measures the driver's heart rate. As described above, the biosensor data measuring device 314 can also be a wearable device worn by the driver or a fitness tracker. In this case, the biosensor data from the biosensor data measuring device 314 can also be transmitted to the vehicle device 100 without passing through the vehicle network 330.

[0088] The in-vehicle navigation system 320 includes a location information acquisition unit 322, a route guidance unit 324, a display unit 326, and a voice output unit 328. The location information acquisition unit 322 acquires location data indicating the driving position of the vehicle 60. The route guidance unit 324 searches for a route to the destination and displays the route on the display unit 326, or receives congestion information and displays the status on the display unit 326. The display unit 326 displays various information, including map information. The voice output unit 328 provides route guidance and congestion information via voice. When the in-vehicle device 100 receives a notification indicating a change in driver characteristics, the in-vehicle navigation system 320 issues a warning to the driver.

[0089] In addition to the communication unit 140, the vehicle-mounted device 100 also includes a vehicle data receiving unit 160, an auxiliary data receiving unit 170, and a warning notification unit 180 as functional units. The vehicle data receiving unit 160, the auxiliary data receiving unit 170, and the warning notification unit 180 are each connected to the vehicle network 330. The vehicle data receiving unit 160, the auxiliary data receiving unit 170, and the warning notification unit 180 are also connected to the communication unit 140, and communicate with the server 200 (see reference 140) via the communication unit 140. Figure 1 ) to communicate.

[0090] The vehicle data receiving unit 160 includes a driving data receiving unit 162 and a position data receiving unit 164. The driving data receiving unit 162 receives driving data of the vehicle 60 while it is in motion from a vehicle control unit (not shown) such as an ECU. The driving data receiving unit 162 receives, for example, CAN information as driving data of the vehicle 60. The received CAN information includes information on at least one of accelerator opening, brake pressure, and steering wheel angle. As driving data, it may also include speed data and acceleration data of the vehicle 60 while it is in motion. The position data receiving unit 164 receives position data acquired by the in-vehicle navigation system 320. The driving data receiving unit 162 receives the driving data of the vehicle 60 via the in-vehicle network 330 and transmits the received driving data along with accompanying data to the server 200 via the communication unit 140.

[0091] The auxiliary data receiving unit 170 includes a biological data receiving unit 172 and an image data receiving unit 174. The biological data receiving unit 172 receives sensor data from the seating sensor 312 via the vehicle network 330 and transmits the received sensor data as auxiliary data to the server 200 via the communication unit 140. More specifically, the biological data receiving unit 172 receives the driver's seat pressure data from the seating sensor 312 and calculates the driver's center of gravity position based on the received seat pressure data. That is, the biological data receiving unit 172 extracts the driver's center of gravity position data from the received seat pressure data. The biological data receiving unit 172 transmits the seat pressure data or the extracted center of gravity position data as sensor data to the server 200. Alternatively, the biological data receiving unit 172 may receive the driver's biological data measured by the biological data measuring device 314 and transmit the biological data to the server 200 via the communication unit 140. The image data receiving unit 174 receives images captured by the vehicle-mounted camera 302 as image data, and sends the received sensor data as auxiliary data to the server 200 via the communication unit 140.

[0092] Warning notification unit 180 receives notification from server 200 via communication unit 140 (see reference). Figure 1The system receives notifications of changes in the driver's characteristics and sends these notifications, for example, to the vehicle navigation system 320 via the vehicle network 330. When a notification is received from the warning notification unit 180, the vehicle navigation system 320 reports a warning to the driver (e.g., a change in characteristics and the potential for danger).

[0093] (Server 200) Reference Figure 5 The control unit 210 of server 200 includes an information acquisition unit 250, a detection processing unit 252, a setting acceptance unit 254, a notification unit 256, and a normal characteristic change notification unit 258 as functional units. The information acquisition unit 250 controls the communication unit 230 to acquire various data such as vehicle data and incidental data, and stores the acquired data in the storage device 220. The detection processing unit 252 performs processing to detect changes in the driver's characteristics over the years using the data stored in the storage device 220.

[0094] The detection processing unit 252 includes a judgment unit 260, an accumulation unit 262, a characteristic change detection unit 264, a normal characteristic detection unit 266, and an estimation unit 268. The judgment unit 260 determines whether vehicle data (driving data) represents a normal characteristic or a dangerous characteristic by referring to a first distribution representing normal characteristics and a second distribution representing dangerous characteristics. The first distribution representing normal characteristics and the second distribution representing dangerous characteristics are, for example, pre-stored in a storage device 220. The accumulation unit 262 has a hazard counter, and performs the following processing: for vehicle data determined by the judgment unit 260 to represent normal characteristics, the hazard count is maintained (i.e., not counted as hazard); for vehicle data determined by the judgment unit 260 to represent dangerous characteristics, the hazard count is increased to accumulate the hazard. The characteristic change detection unit 264 detects whether the hazard count accumulated by the accumulation unit 262 is greater than or equal to a predetermined threshold, indicating that the driver's characteristic has changed to a dangerous characteristic. The normal characteristic detection unit 266 detects whether the driver's characteristics have returned to normal after transitioning to dangerous characteristics. The estimation unit 268 infers more detailed characteristics of the driver based on data such as the driver's biological data and environmental data (e.g., weather data) of the vehicle's external environment while the vehicle 60 is in motion.

[0095] The setting receiving unit 254 sets the period for accumulating the risk level during the process of detecting characteristic changes. The accumulation unit 262 of the detection processing unit 252 accumulates the risk level during the period received by the setting receiving unit 254. That is, the accumulation unit 262 calculates the accumulated value of the period received by the setting receiving unit 254. When the period received by the setting receiving unit 254 has elapsed, the period is shifted. The setting of the period via the setting receiving unit 254 can be achieved, for example, by the administrator 70 to the terminal device 72 (see reference). Figure 1 To perform the operation.

[0096] When the characteristic change detection unit 264 detects that the driver's characteristic has changed to a dangerous characteristic, the detection processing unit 252 notifies the notification unit 256 that the driver's characteristic has changed to a dangerous characteristic. The notification unit 256 receives the notification from the detection processing unit 252 and performs the following processing: notifying the driver of the change in characteristic via the communication unit 230.

[0097] When the normal characteristic detection unit 266 detects that the driver's characteristics have returned to normal, the detection processing unit 252 notifies the normal characteristic change notification unit 258 that the driver's characteristics have returned to normal. The normal characteristic change notification unit 258 receives the notification from the detection processing unit 252 and performs the following processing: notifying the driver of the change in characteristics via the communication unit 230.

[0098] Methods for detecting changes in characteristics Reference Figure 6 A method for detecting changes in driver characteristics is described. In this method, the likelihood of a hazard occurring while driving (also referred to as "hazard level") is counted over time. When the count value (cumulative value) is greater than or equal to a predetermined threshold (or when the count value (cumulative value) exceeds the predetermined threshold), the characteristic is determined to have changed into a hazardous characteristic.

[0099] - Definition of distribution - Figure 6 An example of the distribution is shown in (A). Figure 6 The horizontal axis of the chart described in (A) represents the value (x) of the analyzed object, and the vertical axis represents the distribution P(x) (e.g., frequency or probability).

[0100] For the value (x) being analyzed, the distribution representing normal characteristics is denoted as p(x), and the distribution representing hazardous characteristics (such as slow reaction) is denoted as p'(x). The distribution p(x) representing normal characteristics peaks at x = μ, and the distribution p'(x) representing hazardous characteristics peaks at x = μ'. Driving data can be used for the value (x) being analyzed.

[0101] - Analyze the time series evolution of the object value (x) - Figure 6 An example of the time series evolution of the value (x) of the analyzed object is shown in (B). Figure 6 The horizontal axis of the chart recorded in (B) represents time (t), and the vertical axis represents the value of the analyzed object (x).

[0102] The value (x) of the analyzed object is monitored. When the driver's characteristics are normal, the value (x) of the analyzed object takes a value near μ. When the driver's characteristics are dangerous, the value (x) of the analyzed object takes a value near μ'.

[0103] - Time series evolution of hazard level (a) - Figure 6 An example of the time series evolution of hazard (a) is shown in (C). Figure 6 The horizontal axis of the chart shown in (C) represents time (t), and the vertical axis represents the degree of danger (a).

[0104] Set the function a(x) as the danger level, and define the danger level a(x) as in the following formula (1).

[0105] a(x)=ln(p'(x) / p(x)) (1) When the value of a(x) is positive, it is more likely to be judged as a dangerous characteristic; when the value of a(x) is negative, it is more likely to be judged as a normal characteristic.

[0106] - Time series evolution of cumulative risk value (I) - Figure 6 An example of the time series evolution of the cumulative risk value (I) is shown in (D). Figure 6 The horizontal axis of the chart recorded in (D) represents time (t), and the vertical axis represents the cumulative risk value (I).

[0107] Let the function I(t) be the accumulation of the danger level, denoted as t. n =nΔt, x(t) n ) = x n It is defined by the following formula. Here, Δt is a unit of time (not limited to 1 second).

[0108] I(0) = 0 I(t) n ) = I(t n－1 ) + η(a(x) n ))a(x n ) η(a) = 1 (a ≥ 0) η(a) = 0 (a < 0) When the cumulative risk value (I) exceeds a predetermined threshold, it is determined that the characteristic has changed from a normal characteristic to a dangerous characteristic.

[0109] Examples of data becoming the object of analysis Figure 7 The image shows an example of driving data from a driver with normal characteristics. Figure 8 The image shows an example of driving data from a driver who may have dangerous characteristics. Figure 7 and Figure 8 The horizontal axis represents time t, and the vertical axis represents velocity v(t) and accelerator opening ac(t). As a driver with normal characteristics, we assume a skilled driver in their thirties; as a driver with potentially dangerous characteristics, we assume an elderly driver.

[0110] Reference Figure 7 A driver with normal characteristics will have a relatively smooth accelerator opening. (Refer to...) Figure 8 Conversely, drivers with potentially dangerous characteristics may exhibit significant variations in accelerator opening, making it difficult to describe the accelerator opening as smooth. This could be attributed to factors such as stiffening of ankle joints with age, or impaired judgment leading to hasty decisions like deceleration, resulting in uneven accelerator operation.

[0111] Therefore, it is believed that the accelerator opening during driving can easily reflect the characteristics of older drivers. Thus, the time series data of the accelerator opening during acceleration and cruising (the difference in accelerator opening per unit time) can be set as the data to be analyzed (analyzed value (x)).

[0112] An example of a distribution representing normal characteristics and a distribution representing hazardous characteristics. Figure 9 The diagram shows the frequency distribution of the accelerator opening difference per unit time during cruise. It should be noted that "accelerator opening difference per unit time" refers to the time series data x(t) with the accelerator opening set to the aforementioned unit time (Δt) interval. n (Hereinafter also referred to as "data per unit time") and the difference between adjacent data (i.e., x(t) n )-x(t n－1 )). Figure 10 The frequency distribution of the accelerator opening difference per unit time during acceleration is shown in the figure. Figure 9 and Figure 10 The horizontal axis represents the difference in accelerator opening per unit time, and the vertical axis represents the frequency.

[0113] Reference Figure 9For experienced drivers in their thirties, accelerator opening differences are concentrated between 0 and 5, indicating uniform accelerator operation. On the other hand, for older drivers, compared to experienced drivers in their thirties, accelerator opening differences of 0 and 5 are less frequent; instead, larger accelerator opening differences such as 20 and -30 are observed. As a distribution, a trend of lateral expansion is observed in the distribution of older drivers compared to that of experienced drivers in their thirties. These two distributions are not as... Figure 6 The distributions shown in (A) do not have different peak positions (mode values), but rather the peak positions are approximately equal and the variances are different. Even in such a case, the degree of danger can be represented by formula (1). That is, when the total number of frequencies in the two distributions is equal, near the peak position, p'(x) < p(x), ln(p'(x) / p(x)) < 0, and when deviating from the peak position, p'(x) > p(x), ln(p'(x) / p(x)) > 0.

[0114] Reference Figure 10 The frequency distribution during acceleration also shows the same frequency distribution as during cruising (see reference). Figure 9 The same trend is observed. That is, as a distribution, a trend of lateral expansion is observed in the distribution of older individuals compared to the distribution of skilled drivers in their thirties.

[0115] These trends are used to determine the distributions representing normal characteristics and the distributions representing dangerous characteristics, respectively. It should be noted that driving data is not limited to accelerator opening; for example, time-series data such as brake pressure and steering wheel angle can also be used.

[0116] [Software Composition] Hereinafter, it is assumed that the storage device 220 of the server 200 stores vehicle data and associated data sent from the vehicle device 100, as well as environmental data obtained from the external server 90.

[0117] (Server 200) Period Setting Processing Reference Figure 11 For server 200 (refer to) Figure 1 The control structure of a computer program that executes within a given timeframe to set the period for accumulating hazard levels is described. This program, for example, begins in response to input of the hazard accumulation period via an external terminal.

[0118] The procedure includes: step S1000, setting the input period as the period for accumulating the hazard level, and ending the procedure. The input of the hazard level accumulation period can, for example, be provided by the administrator 70 to the terminal device 72 (see reference). Figure 1 This can be done by performing the operation. The period for accumulating the risk level is arbitrary, but it can be set to, for example, 30 days.

[0119] Characteristic Change Detection and Processing Reference Figure 12 For server 200 (refer to) Figure 1 The control structure of a computer program that executes to detect changes in driver characteristics based on cruise data is described. This program, for example, begins according to a pre-set schedule. For instance, the program starts at a certain time each day.

[0120] The procedure includes: step S2000, from storage device 220 (refer to...) Figure 3 The procedure includes: acquiring driving data; and step S2010, executed after step S2000, extracting cruise data from the acquired driving data. The procedure also includes: step S2020, executing steps S2030 to S2060 (described below) for each unit of time data, and repeating this process until all unit-time data has been processed. In step S2010, for example, a determination is made as to whether it is cruise time based on whether the speed change is within a specified range.

[0121] In step S2020, the process that is repeatedly executed until all data for each unit time has been processed (the process of calculating and accumulating hazard levels) includes: step S2030, calculating the difference between each unit time and the previous data; and step S2040, executed after step S2030, using the calculated difference as the analysis object value (x), and calculating the hazard level (a) with reference to the distribution representing normal characteristics and the distribution representing hazardous characteristics. "The difference between each unit time and the previous data" refers to the difference between adjacent data in the time series data within a unit time interval. The repeatedly executed process also includes: step S2050, executed after step S2040, accumulating the hazard level based on the calculated hazard level (a); and step S2060, executed after step S2050, determining whether the accumulated hazard level is greater than or equal to a predetermined threshold, and branching the control flow according to the determination result. In step S2030, for example, when the time series data of the unit time interval is set to t0 = 1, t1 = 3, t2 = -2, the difference (d) is d1 = 2, d2 = -5. In step S2050, if the calculated hazard (a) is positive, the hazard is accumulated.

[0122] If the cumulative value of the danger level determined in step S2060 is not greater than or equal to the specified threshold, the processing in step S2020 is repeated.

[0123] The procedure also includes step S2070, executed if the cumulative value of the hazard level determined in step S2060 is greater than or equal to a predetermined threshold, notifying an external party that the driver's characteristic has changed to a hazardous characteristic (that the driver's characteristic has changed from a normal characteristic to a hazardous characteristic). In step S2070, for example, a manager 70 is notified that the driver's characteristic has changed to a hazardous characteristic.

[0124] The program ends when step S2020 has been repeated until all data for all units of time has been processed, or when the processing in step S2070 is completed.

[0125] Reference Figure 13 For server 200 (refer to) Figure 1 The control structure of a computer program that executes to detect changes in driver characteristics based on acceleration data is described. This program, for example, begins according to a pre-set schedule. For instance, the program starts at a certain time each day.

[0126] The procedure includes step S2012 instead of... Figure 12 Step S2010 in the program. Figure 13 The processing in steps S2000, S2020 and S2070 Figure 12 The processes in each step shown are the same. The differences are explained below.

[0127] The procedure includes: step S2012, executed after step S2000, which extracts acceleration data from the acquired driving data. The processing in step S2020 (the processing of hazard calculation and accumulation) is performed on the acceleration data extracted in step S2012.

[0128] Feature Classification Processing Reference Figure 14 For server 200 (refer to) Figure 1 The control structure of a computer program that performs classification of driver characteristics to provide a detailed description of those characteristics is described below. This program, for example, begins in response to a cumulative value of danger determined in the aforementioned characteristic change detection process being greater than or equal to a predetermined threshold.

[0129] The procedure includes: step S3000, from storage device 220 (refer to...) Figure 3The procedure involves acquiring vehicle data, incidental data, and environmental data corresponding to data with a positive hazard level (a); and step S3010, executed after step S3000, classifying the hazardous characteristics based on the acquired incidental data and environmental data, and ending the procedure. The classification result in step S3010 can be notified along with the notification to the manager 70 that the driver's characteristics have been transformed into hazardous characteristics.

[0130] It should be noted that it can also be set to... Figure 12 and Figure 13 In step S2040 of the procedure, if the risk level (a) is positive, the data is executed. Figure 14 The program.

[0131] Reference Figure 15 ,exist Figure 14 In step S3010 of the program, for example, it is classified into four characteristics (groups).

[0132] (1) Group 1 Based on the time and weather information, we can determine whether it is nighttime or daytime, and whether it is a dark area. Given this situation, and assuming the hazard level is counted (i.e., when the hazard level (a) is positive), it is inferred that due to decreased night vision, it is difficult to see objects in the dark. Therefore, this set of characteristics can be described as decreased night vision.

[0133] (2) Group 2 Based on vehicle location information (location data), it can be determined whether the vehicle is traveling on a highway. Given that the level of danger was assessed while traveling on a highway, it is speculated that due to decreased dynamic vision, the vehicle is unable to match the speed of other vehicles. Therefore, this characteristic can be attributed to both decreased dynamic vision and reduced information processing ability.

[0134] (3) Group 3 Based on time information and biological information (seat pressure / center of gravity position, etc.), the continuous driving time (e.g., more than 30 minutes) and driving posture can be determined. For example, in cases of long continuous driving time or frequent shifts in the center of gravity, it is presumed that due to decreased muscle strength and physical strength, the correct driving position cannot be adopted, leading to rapid fatigue accumulation. Therefore, this set of characteristics can be described as a decrease in muscle strength and physical strength.

[0135] (4) Group 4 Based on vehicle location information (location data) and driving history information, it can be determined whether the vehicle is driving in an unfamiliar location. If the level of danger is calculated while driving in an unfamiliar location, it is inferred that in unfamiliar environments, drivers need to process a great deal of information simultaneously. However, due to a narrowed field of vision and decreased dynamic visual acuity, the brain struggles to recognize the surrounding visual field. Therefore, this characteristic can be described as a decline in both peripheral vision and information processing ability.

[0136] Thus, by classifying hazardous characteristics more precisely, it is possible to more effectively provide attention alerts or guide drivers towards mechanisms that prevent delayed reactions. As will be described later, for example, when observing the first set of characteristics, the in-vehicle navigation system can be remotely controlled to select routes with abundant streetlights, ideally during nighttime driving, for instance. When observing the second set of characteristics, the in-vehicle navigation system can be remotely controlled to select routes that utilize the shortest possible route, primarily using general roads and highways, for instance. When observing the third set of characteristics, the in-vehicle navigation system can be remotely controlled to select routes that appropriately include rest stops, for instance. When observing the fourth set of characteristics, the in-vehicle navigation system can be remotely controlled to select routes that are easy to understand, even if they take longer.

[0137] "Hazard Accumulation Value Update Processing" Reference Figure 16 The hazard accumulation occurs within the period set in the period setting process. However, even after the set period has elapsed, the hazard accumulation will not stop. In this case, the oldest data is excluded (subtracted) from the accumulated value, and the hazard accumulation value is updated within the set period. That is, the set period is shifted to the right. Here, the oldest data to be subtracted is called data outside the monitoring period. By shifting the set period and updating the hazard accumulation value in this way, it can be known that a driver whose behavior has temporarily changed to hazardous characteristics has returned to normal characteristics. For example, by carefully following improvement instructions from the system or advice from relatives, a driver's characteristics may sometimes improve to normal characteristics. By detecting such changes, it is possible to prevent the behavior from changing to hazardous characteristics again.

[0138] Reference Figure 17 For server 200 (refer to) Figure 1 The control structure of the computer program that executes the update process for such cumulative risk values ​​is described. This program, for example, begins according to a pre-set schedule.

[0139] The procedure includes: step S4000, determining whether there is data outside the monitoring period, and branching the control flow based on the determination result; and step S4010, executed if it is determined in step S4000 that there is data outside the monitoring period, and acquiring the data. The procedure also includes: step S4020, executed after step S4010, subtracting the value of the data from the accumulated hazard level (accumulated hazard value); and step S4030, executed after step S4020, determining whether the accumulated hazard value is lower than a predetermined threshold, and branching the control flow based on the determination result. The procedure further includes: step S4040, executed if it is determined in step S4030 that the accumulated hazard value is lower than the predetermined threshold, and notifying the outside that the driver's characteristics have recovered from hazardous characteristics to normal characteristics.

[0140] The procedure ends if, in step S4000, it is determined that there is no data outside the monitored period; in step S4030, it is determined that the cumulative value of the danger level is not lower than a predetermined threshold; or in step S4040, the processing has ended. In step S4040, for example, the manager 70 is notified that the driver's characteristics have returned to normal.

[0141] [action] The characteristic change detection system 50 of this embodiment operates as follows. (Refer to...) Figure 1 The on-board unit 100 sends vehicle data and associated data of vehicle 60 to server 200. Server 200 receives and accumulates the vehicle data and associated data sent from on-board unit 100. Server 200 also obtains environmental data corresponding to the vehicle data from external server 90, and stores the vehicle data and associated data in storage device 220 accordingly.

[0142] Server 200 performs processing to detect changes in the characteristics of the driver of vehicle 60 using vehicle data (driving data) stored in storage device 220. Figure 12 and Figure 13 Step S020). When it is detected that the driver's characteristics have changed from normal characteristics to dangerous characteristics (in Figure 12 and Figure 13 In step S2060, if the condition is "Yes", the server 200 notifies the administrator 70 that the driver's characteristics have changed from normal to dangerous. Figure 12 and Figure 13 Step S2070).

[0143] Server 200 continues to perform the process of detecting changes in driver characteristics and monitors whether the driver's characteristics have returned to normal. Specifically, in the case of data outside the period of monitoring (in... Figure 17 In step S4000 (if "Yes"), the data is acquired and the data value is subtracted from the cumulative hazard value (steps S4010 and S4020). Furthermore, if the cumulative hazard value is lower than a predetermined threshold (if "Yes" in step S4030), the manager 70 is notified that the cumulative hazard value is lower than the predetermined threshold (step S4040).

[0144] Thus, in the characteristic change detection system 50 of this embodiment, the determination unit 260 determines whether vehicle data (driving data) represents normal or dangerous characteristics by referring to a first distribution representing normal characteristics and a second distribution representing dangerous characteristics. The accumulation unit 262 performs the following processing: for vehicle data that the determination unit 260 determines represents normal characteristics, the danger level count is maintained; for vehicle data that the determination unit 260 determines represents dangerous characteristics, the danger level is accumulated by increasing the danger level count. The characteristic change detection unit 264 detects whether the driver's characteristics have changed to dangerous characteristics based on whether the danger level count is greater than or equal to a predetermined threshold. Therefore, even if the driver's characteristics change over the years, changes in the driver's characteristics can be detected.

[0145] The server 200, which serves as a characteristic change detection device, also includes a notification unit 256, which notifies at least one of the driver and the manager 70 who manages the driver that the driver's characteristic has changed to a dangerous characteristic. This allows the driver to become aware that their characteristic has changed.

[0146] Alternatively, the vehicle data (driving data) could include time-series information on at least one of the following: accelerator opening, brake pressure, and steering wheel angle. This allows for high-precision detection of changes in the driver's driving characteristics.

[0147] Alternatively, the judgment unit 260 can calculate the difference between the data at each unit time in the time series data and the previous data at the previous unit time, and determine whether the calculated difference represents normal or dangerous characteristics by referring to a first distribution and a second distribution. This allows for more precise detection of changes in the driver's driving characteristics.

[0148] Alternatively, the server 200 may be configured as follows: an information acquisition unit 250 acquires at least one of the following: driver's biological data, vehicle driving data, and environmental data of the vehicle's external environment during driving; and an inference unit 268 infers the driver's characteristics based on the information acquired by the information acquisition unit 250. Thus, when the driver's characteristics change, it is possible to infer what kind of characteristic has changed.

[0149] Alternatively, the vehicle 60 may also include a seating sensor 312, located in the seat where the driver sits. The onboard device 100 also transmits sensor data from the seating sensor 312 as biometric data to the server 200. This allows, for example, the inference of changes in characteristics related to the driver's driving posture.

[0150] Alternatively, the on-board unit 100 may also send vehicle location data during vehicle movement to the server 200 as vehicle data. This allows, for example, the ability to infer changes in characteristics related to dynamic vision or information processing capabilities.

[0151] Alternatively, the configuration could be such that server 200 communicates with external server 90, and information acquisition unit 250 obtains weather information of the driving area of ​​vehicle 60 from external server 90 as environmental data. This allows, for example, the inference of changes in characteristics related to vision or information processing ability.

[0152] Alternatively, the server 200 may include a setting receiving unit 254, which receives settings for the period during which the risk level is accumulated, and an accumulation unit 262 accumulates the risk level during the period received by the setting receiving unit 254. This prevents the risk level from accumulating without limit.

[0153] When the processing period set by the acceptance unit 254 is exceeded, the accumulation unit 262 extends the period to accumulate the hazard level and deletes data that has become outside the period due to the extension, thereby updating the hazard level count. Alternatively, the server 200 may also include: a normal characteristic detection unit 266, which detects whether the driver's characteristic has changed from a dangerous characteristic to a normal characteristic based on whether the updated hazard level count is lower than a predetermined threshold; and a normal characteristic change notification unit 258, which notifies at least one of the driver and the manager 70 who manages the driver that the driver's characteristic has changed to a normal characteristic. This allows for the detection and notification that the driver's characteristic has returned to a normal characteristic.

[0154] (First variation) In the first embodiment described above, an example is shown where characteristic classification processing is performed when the cumulative value of the determined hazard level is greater than or equal to a predetermined threshold or when the hazard level (a) is positive. However, this disclosure is not limited to such an embodiment. For example, it is also possible to pre-group vehicle data (driving data) based on vehicle data, incidental data, and environmental data, and perform characteristic classification processing on each group. In the first variation, such a configuration example will be described.

[0155] The server execution in the first variant Figure 18 The procedure shown is used to replace Figure 14 The program shown is based on a pre-set schedule, for example, starting at a specific time each day.

[0156] Reference Figure 18 The procedure includes: step S3100, from storage device 220 (refer to...) Figure 3 The process involves: acquiring vehicle data, incidental data, and environmental data; and step S3110, which is executed after step S3100, whereby the driving data contained in the vehicle data (such as location data), incidental data, and environmental data are grouped into multiple groups, the multiple groups are saved in the storage device 220, and the program is terminated.

[0157] In the first variation, during the characteristic change detection process, Figure 12 and Figure 13 The program shown executes the driving data for each group after grouping.

[0158] (Second Implementation) Reference Figure 19 The characteristic change detection system 50A of this embodiment differs from the first embodiment in that it detects and notifies the driver of changes in their characteristics over the years. The vehicle 60a is a private car or other general vehicle. In this case, the manager is, for example, a relative of the driver.

[0159] The vehicle 60a is equipped with the same on-board unit 100 as in the first embodiment. Other configurations are the same as in the first embodiment.

[0160] (Third implementation method) Reference Figure 20 The characteristic change detection device in this embodiment differs from that in the first embodiment in that it is an on-board device 400 mounted on a vehicle 60b. That is, in this embodiment, the on-board device 400 has the server 200 from the first embodiment (see...). Figure 1 () function.

[0161] The on-board device 400 detects changes in the characteristics of the driver of the vehicle 60b over the years and notifies the driver or the driver's relatives of these changes.

[0162] Reference Figure 21The vehicle-mounted device 400 also includes a detection processing unit 410 and a setting receiving unit 420 as functional units. Vehicle data received by the vehicle data receiving unit 160 and incidental data received by the incidental data receiving unit 170 are stored in the storage device 402. The vehicle-mounted device 400 communicates with an external server 90 (see reference 140), which serves as an external data source, via the communication unit 140. Figure 20 The vehicle-mounted device 400 communicates with the external server 90. It obtains environmental information and other data from the external server 90 and stores the environmental information and other data in the storage device 402.

[0163] The detection processing unit 410 and the setting acceptance unit 420 each have a detection processing unit 252 and a setting acceptance unit 254 respectively connected to the server 200 (see reference). Figure 5 The same function. The detection processing unit 410 performs the same operation using the data stored in the storage device 402 to analyze the driving vehicle 60b (see reference). Figure 20 The detection and processing unit 410 detects changes in the characteristics of drivers over the years. It includes a judgment unit 430, an accumulation unit 432, a characteristic change detection unit 434, a normal characteristic detection unit 436, and an estimation unit 438. These functional units have similar characteristics to the server 200 in the first embodiment (see reference 438). Figure 5 The functions of each part are the same.

[0164] When the characteristic change detection unit 434 detects that the driver's characteristic has changed to a dangerous characteristic, the detection processing unit 410 notifies the warning notification unit 180 that the driver's characteristic has changed to a dangerous characteristic. The warning notification unit 180 receives the notification from the detection processing unit 410 and performs the following processing: notifying (warning) the driver that the driver's characteristic has changed to a dangerous characteristic, or notifying an external terminal of the driver's characteristic change (e.g., a portable terminal held by the driver's relatives, etc.) via the communication unit 140.

[0165] When the normal characteristic detection unit 436 detects that the driver's characteristics have returned to normal, the detection processing unit 410 notifies the warning notification unit 180 that the driver's characteristics have returned to normal. The warning notification unit 180 receives the notification from the detection processing unit 410 and performs the following processing: notifying the driver that the driver's characteristics have returned to normal, or notifying an external terminal of the vehicle 60b (e.g., a portable terminal held by the driver's relatives, etc.) via the communication unit 140.

[0166] This configuration also allows for the detection of changes in driver characteristics.

[0167] The other components and effects are the same as those in the first embodiment.

[0168] (Modified example) In the above embodiments, an example is shown using a single threshold as the threshold for the cumulative hazard value, but this disclosure is not limited to such embodiments. For example, multiple thresholds may be used, and notifications (warnings) may be issued in stages as the cumulative hazard value increases.

[0169] In the above embodiments, four groups are shown for grouping driver characteristics, but this disclosure is not limited to such embodiments. The groups used for grouping can be two, three, or five or more. The four groups (characteristics) can also be groups (characteristics) other than those shown in the above embodiments. Furthermore, in addition to the four groups, other groups (characteristics) can be added.

[0170] In the above embodiments, an example of using CAN information as vehicle data is shown. However, this disclosure is not limited to such embodiments. Vehicle data may also be information other than CAN information.

[0171] In the above embodiments, an example is shown of using time-series data of at least one of accelerator opening, brake pressure, and steering wheel angle as vehicle data (driving data), but this disclosure is not limited to such embodiments. Vehicle data (driving data) can be data that can detect changes in the driver's characteristics over the years, or it can be other data.

[0172] It should be noted that the various processes (functions) in the above-described embodiments can also be implemented by a processing circuit including one or more processors. Alternatively, the processing circuit may be composed of an integrated circuit consisting of one or more processors combined with one or more memories, various analog circuits, and various digital circuits. The one or more memories store programs (instructions) that cause the one or more processors to execute the various processes. The one or more processors may execute the various processes according to the programs read from the one or more memories, or they may execute the various processes according to logic circuits pre-designed to execute the various processes. The processors may be various processors suitable for computer control, such as CPUs, GPUs, DSPs (Digital Signal Processors), FPGAs (Field Programmable Gate Arrays), and ASICs (Application Specific Integrated Circuits). It should also be noted that the various processes can be executed by multiple physically separate processors cooperating with each other. For example, the processors in each of multiple physically separate computers may cooperate with each other to execute the various processes via networks such as LANs (Local Area Networks), WANs (Wide Area Networks), and the Internet.

[0173] In addition, a record may be provided containing the processing performed by the computer execution server 200 (e.g., Figure 12 or Figure 13 The recording medium is a program for processing (as shown). The recording medium may be, for example, an optical disc (DVD (Digital Universal Optical Disc) or a removable semiconductor memory (USB (Universal Serial Bus) memory, etc.). Although computer programs can be transmitted via communication lines, the recording medium refers to a non-transitory recording medium. By having the computer read the program stored on the recording medium, the computer can detect changes in the driver's characteristics over the years, as described above.

[0174] (Postscript) That is, a computer-readable non-transitory recording medium stores a computer program that enables a computer to detect changes in the characteristics of a driver of a vehicle over many years. The computer program enables the computer to perform: an acquisition step, acquiring vehicle information related to the driving of the vehicle; and a detection step, using the vehicle information acquired in the acquisition step to detect changes in the characteristics of the driver of the vehicle. The detection step includes a judgment step, in which the vehicle information is judged to represent either normal or dangerous characteristics by referring to a pre-prepared first distribution representing normal characteristics and a second distribution representing dangerous characteristics.

[0175] Implementations obtained by appropriately combining the technologies disclosed above are also included within the scope of this disclosure.

[0176] The embodiments disclosed herein are merely examples, and this disclosure should not be limited to the embodiments described above. The scope of this disclosure is shown by the various technical solutions in the claims based on the detailed description of the invention, including all modifications with the equivalent meaning and scope of the statements described in those technical solutions.

[0177] Explanation of reference numerals in the attached figures 50, 50A: Characteristic change detection system; 60, 60a, 60b: Vehicle; 62: External wireless device; 64: Network; 66: Seat; 70: Administrator; 72: Terminal device; 80: Relative; 82: Portable terminal; 90: External server; 100, 400: Vehicle-mounted device; 102, 202: Computer; 110, 210: Control unit; 112: Computing unit; 114, 216: ROM; 116, 218: RAM; 120: Memory; 130: In-vehicle communication unit; 140, 230: Communication unit; 150, 240: Communication bus; 160: Vehicle data receiving unit; 162: Driving data receiving unit; 164: Location data receiving unit; 170: Auxiliary data receiving unit; 172: Biological data receiving unit; 174: Image data receiving unit; 180: Alarm Notification Unit; 200: Server; 212: CPU; 214: GPU; 220, 402: Storage Device; 250: Information Acquisition Unit; 252, 410: Detection and Processing Unit; 254, 420: Setting and Acceptance Unit; 256: Notification Unit; 258: Normal Characteristic Change Notification Unit; 260, 430: Judgment Unit; 262, 432: Accumulation Unit; 264, 434: Characteristic Change Detection Unit; 266, 436: Normal Characteristic Detection Unit; 268, 438: Inference Unit; 300: Vehicle System; 302: Vehicle Camera; 310: Biosensor; 312: Seating Sensor; 314: Biosensor Data Measurement Device; 320: Vehicle Navigation; 322: Location Information Acquisition Unit; 324: Route Guidance Unit; 326: Display Unit; 328: Voice Output Unit; 330: Vehicle Network.

Claims

1. A characteristic change detection system, comprising a characteristic change detection device, wherein, This characteristic change detection device uses vehicle information related to vehicle operation to detect changes in the characteristics of the driver who drives the vehicle over the years. The characteristic change detection device includes a judgment unit, wherein the judgment unit determines whether the vehicle information represents normal characteristics or dangerous characteristics by referring to a first distribution representing normal characteristics and a second distribution representing dangerous characteristics prepared in advance.

2. The characteristic change detection system according to claim 1, wherein, The characteristic change detection device includes: The accumulation unit performs the following processing: for vehicle information determined by the determination unit to represent normal characteristics, it maintains the danger level count; for vehicle information determined by the determination unit to represent dangerous characteristics, it accumulates the danger level by increasing the danger level count. The characteristic change detection unit detects whether the driver's characteristic has changed into a dangerous characteristic based on whether the count value of the danger accumulated by the accumulation unit is greater than or equal to a predetermined threshold.

3. The characteristic change detection system according to claim 1 or 2, wherein, The characteristic change detection device further includes a notification unit, wherein the notification unit notifies at least one of the driver and the manager who manages the driver that the driver's characteristic has changed into a dangerous characteristic.

4. The characteristic change detection system according to any one of claims 1 to 3, wherein, The vehicle information includes time-series information on at least one of the following: accelerator opening, brake pressure, and steering wheel angle.

5. The characteristic change detection system according to claim 4, wherein, The judgment unit calculates the difference between the data in each unit of time in the time series information and the previous data that is the data in the previous unit of time, and judges whether the calculated difference represents normal characteristics or dangerous characteristics by referring to the first distribution and the second distribution.

6. The characteristic change detection system according to any one of claims 1 to 5, wherein, The characteristic change detection device further includes: The information acquisition unit acquires at least one of the following: the driver's biological information, the vehicle's driving information, and the environmental information outside the vehicle during driving; and The characteristic estimation unit estimates the characteristics of the driver based on the information obtained by the information acquisition unit.

7. The characteristic change detection system according to claim 6, wherein, The characteristic change detection system also includes: An on-board unit, mounted in a vehicle, transmits the vehicle information to a characteristic change detection device; and A seating sensor is installed in the seat where the driver will sit. The vehicle-mounted device also sends sensor data from the seating sensor as biological information to the characteristic change detection device.

8. The characteristic change detection system according to claim 6, wherein, The on-board device also sends the vehicle's location information during driving as driving information to the characteristic change detection device.

9. The characteristic change detection system according to any one of claims 6 to 8, wherein, The characteristic change detection device communicates with an external server. The information acquisition unit obtains the weather information of the driving area of ​​the vehicle from the external server as the environmental information.

10. The characteristic change detection system according to claim 2, wherein, The characteristic change detection device further includes a setting receiving unit, wherein the setting receiving unit accepts the setting of the period for accumulating the hazard level. The accumulation unit accumulates the degree of danger during the period when the set acceptance unit accepts the case.

11. The characteristic change detection system according to claim 10, wherein, When the period for handling by the designated acceptance unit is exceeded, the accumulation unit shifts the period to accumulate the risk level and deletes data that has become outside the period due to the shift, thereby updating the risk level count. The characteristic change detection device further includes: The normal characteristic detection unit detects whether the driver's characteristic has changed from a dangerous characteristic to a normal characteristic based on whether the updated hazard count value is less than a predetermined threshold; and The normal characteristic change notification unit notifies at least one of the driver and the manager who manages the driver that the driver's characteristic has changed to a normal characteristic.

12. A vehicle-mounted device, mounted on a vehicle, transmits the vehicle information to the characteristic change detection device of the characteristic change detection system as described in claim 1 or 2.

13. A characteristic change detection device, comprising: The acquisition department acquires vehicle information related to the vehicle's operation. as well as The processing unit performs a process that uses the vehicle information acquired by the acquisition unit to detect changes in the characteristics of the driver who drives the vehicle over the years. The processing unit includes a judgment unit, wherein the judgment unit determines whether the vehicle information represents normal characteristics or dangerous characteristics by referring to a first distribution representing normal characteristics and a second distribution representing dangerous characteristics prepared in advance.

14. The characteristic change detection device according to claim 13, wherein, The processing unit further includes: The accumulation unit performs the following processing: for vehicle information determined by the determination unit to represent normal characteristics, it maintains the danger level count; for vehicle information determined by the determination unit to represent dangerous characteristics, it accumulates the danger level by increasing the danger level count. The characteristic change detection unit detects whether the driver's characteristic has changed into a dangerous characteristic based on whether the count value of the danger accumulated by the accumulation unit is greater than or equal to a predetermined threshold.

15. The characteristic change detection device according to claim 13 or 14, wherein, The characteristic change detection device is a server device that communicates with the vehicle.

16. The characteristic change detection device according to claim 13 or 14, wherein, The characteristic change detection device is an on-board device mounted on the vehicle.

17. A method for detecting characteristic changes, which is a method for detecting the changes in the characteristics of a driver of a vehicle over many years, wherein, The method for detecting changes in characteristics includes: The acquisition process involves the computer acquiring vehicle information related to the vehicle's operation; and In the detection step, the computer uses the vehicle information acquired in the acquisition step to detect changes in the characteristics of the driver driving the vehicle. The detection step includes a judgment step, in which the vehicle information is judged to represent normal characteristics or dangerous characteristics by referring to a first distribution representing normal characteristics and a second distribution representing dangerous characteristics prepared in advance.

18. The characteristic change detection method according to claim 17, wherein, The detection steps also include: The accumulation step involves the following processing: for vehicle information determined in the judgment step to represent normal characteristics, the hazard count is maintained; for vehicle information determined in the judgment step to represent hazardous characteristics, the hazard is accumulated by increasing the hazard count. The step of detecting whether the driver's characteristics have turned into dangerous characteristics is based on whether the count value of the danger accumulated in the accumulation step is greater than or equal to a predetermined threshold.

19. A computer program that enables a computer to detect changes in the characteristics of a driver of a vehicle over many years, wherein, The computer program causes the computer to perform: The steps involve obtaining vehicle information related to the vehicle's operation. as well as The detection step uses the vehicle information obtained in the acquisition step to detect changes in the characteristics of the driver driving the vehicle. The detection step includes a judgment step, in which the vehicle information is judged to represent normal characteristics or dangerous characteristics by referring to a first distribution representing normal characteristics and a second distribution representing dangerous characteristics prepared in advance.

20. The computer program according to claim 19, wherein, The detection steps also include: The accumulation step involves the following processing: for vehicle information determined to represent normal characteristics in the judgment step, the hazard count is maintained; for vehicle information determined to represent hazardous characteristics in the judgment step, the hazard is accumulated by increasing the hazard count. The step of detecting whether the driver's characteristics have turned into dangerous characteristics is based on whether the count value of the danger accumulated in the accumulation step is greater than or equal to a predetermined threshold.

Images