Information processing device, information processing system, and information processing method

Abstract

To more accurately and more flexibly grasp a driving state of a driver.SOLUTION: An information processing device according to an embodiment includes a control part. The control part includes the steps of: learning the driving tendency for each driver of a plurality of vehicles based on the recorded data including at least vehicle information acquired in each of the plurality of vehicles; learning the average driving tendency of a plurality of drivers from the learning result of the driving tendency for each driver; and determining a current driving state of the driver of the vehicle corresponding to the recorded data by comparing the current recording data with the learning result of the average driving tendency.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The disclosed embodiments relate to an information processing apparatus, an information processing system, and an information processing method.

Background Art

[0002] Conventionally, an event data recorder (EDR) which is a type of in-vehicle information recording device and records vehicle information before and after an accident has been known. By collecting and analyzing such an EDR, it becomes possible to grasp the behavior of the vehicle before and after the accident.

[0003] There are various types of EDRs, such as those that record for several minutes before a collision and continuously record data while overwriting, those that operate constantly and lock the operation record by detecting events similar to a collision such as sudden changes in speed and angular momentum, and the like. There are also types that can wirelessly send data to various related locations.

[0004] However, since the EDR is mounted inside an ECU (Electronic Control Unit) etc. to ensure shock resistance, it cannot record images. As an in-vehicle information recording device at the time of an accident including such images, there is a drive recorder. Therefore, in recent years, a technique has been proposed in which vehicle information similar to that of an EDR is recorded in synchronization with the images of a drive recorder, and such recorded data is transmitted to a server (see, for example, Patent Document 1).

[0005] When such a server is an operation management server for commercial vehicles etc., the operation manager can grasp the driving situation of each driver from the driving tendency etc. of each driver shown by the transmitted recorded data, and perform operation management according to such a driving situation.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

[0007] However, the conventional technologies described above still have room for improvement in terms of understanding the driver's driving situation with greater accuracy and flexibility.

[0008] For example, using conventional technology, while fleet managers can grasp the driving tendencies and driving conditions of each driver, this information is only obtained from a micro perspective, based on recorded data for each vehicle. In other words, the quality of the driving conditions grasped may not necessarily be the same when viewed from a macro perspective.

[0009] One embodiment, made in view of the above, aims to provide an information processing device, an information processing system, and an information processing method that can grasp the driver's driving conditions with greater accuracy and flexibility. [Means for solving the problem]

[0010] An information processing device according to one embodiment includes a control unit. The control unit learns the driving tendencies of each driver of a plurality of vehicles based on recorded data which includes at least vehicle information acquired in each of the plurality of vehicles, and from the learning results of the driving tendencies of each driver, it calculates the average driving tendencies of the plurality of drivers. This includes statistical data on operations during predetermined driving events on specific road sections. By learning and comparing the current recorded data with the learned results of the average driving trend, the system learns the corresponding data. subject vehicle no do Determining the driver's driving status The results of the determination are then notified to the driver of the vehicle in question. do. [Effects of the Invention]

[0011] According to one embodiment, the driver's driving conditions can be understood with greater accuracy and flexibility.

Brief Description of the Drawings

[0012] [Figure 1] FIG. 1 is a schematic explanatory diagram (Part 1) of an information processing method according to an embodiment. [Figure 2] FIG. 2 is a schematic explanatory diagram (Part 2) of an information processing method according to an embodiment. [Figure 3] FIG. 3 is a block diagram showing a configuration example of an in-vehicle device according to an embodiment. [Figure 4] FIG. 4 is a diagram showing an example of vehicle information acquired by the in-vehicle device. [Figure 5] FIG. 5 is a diagram showing an image of recording data. [Figure 6] FIG. 6 is a block diagram showing a configuration example of a server device according to an embodiment. [Figure 7] FIG. 7 is a diagram (Part 1) showing a first determination example by a determination unit. [Figure 8] FIG. 8 is a diagram (Part 2) showing a first determination example by a determination unit. [Figure 9] FIG. 9 is a diagram showing a second determination example by a determination unit. [Figure 10] FIG. 10 is a processing sequence (Part 1) of an information processing system according to an embodiment. [Figure 11] FIG. 11 is a processing sequence (Part 2) of an information processing system according to an embodiment. [Figure 12] FIG. 12 is a diagram showing an image of recording data according to a modification example.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, embodiments of an information processing device, an information processing system, and an information processing method disclosed in the present application will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited by the embodiments shown below.

[0014] First, the outline of the information processing method according to the embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 is a schematic explanatory diagram (part 1) of the information processing method according to the embodiment. Further, FIG. 2 is a schematic explanatory diagram (part 2) of the information processing method according to the embodiment.

[0015] As shown in FIG. 1, the information processing system 1 according to the embodiment includes in-vehicle devices 10-1, 10-2, 10-3... respectively mounted on vehicles V-1, V-2, V-3... and a server device 100.

[0016] Hereinafter, when there is no need to distinguish vehicles V-1, V-2, V-3... from each other, they will be described as "vehicle V". Similarly, when there is no need to distinguish in-vehicle devices 10-1, 10-2, 10-3... from each other, they will be described as "in-vehicle device 10".

[0017] The in-vehicle device 10 is a device that has a camera and captures and records an out-of-vehicle image of the vehicle V with such a camera.

[0018] Further, the in-vehicle device 10 is connected to various in-vehicle sensors such as an acceleration sensor, an accelerator sensor, and a brake sensor via an in-vehicle network such as CAN (Controller Area Network). The in-vehicle device 10 records various vehicle information acquired from these in-vehicle sensors in synchronization with the captured video.

[0019] Further, the in-vehicle device 10 is provided so as to be able to upload recorded data in which the video and the vehicle information are synchronized to the server device 100 via the network N. The network N is the Internet, a C-V2X (Cellular Vehicle to Everything) communication network, or the like. The in-vehicle device 10 is, for example, a drive recorder.

[0020] The server device 100 is a device that collects recorded data recorded by the in-vehicle device 10. The server device 100 is configured, for example, as a cloud server that provides cloud services via network N. If the vehicle V is a commercial vehicle, the server device 100 is, for example, a fleet management server operated and managed by the operator.

[0021] Furthermore, the server device 100 learns the driving tendencies of each driver in each vehicle V based on the recorded data collected from the in-vehicle device 10. The server device 100 also learns the overall statistical driving tendencies of all drivers based on the results of learning these individual driver tendencies.

[0022] Furthermore, the server device 100 determines the current driver status by comparing the recorded data collected in real time with its learning results. The server device 100 also notifies each vehicle V of the determination result. The in-vehicle device 10 presents the notified determination result to the driver.

[0023] To explain the sequence of events in the information processing system 1 with this configuration, as shown in Figure 1, first, in the vehicle V, the on-board device 10 acquires various vehicle information from the on-board sensors (step S1). The on-board device 10 also records the acquired vehicle information along with the video (step S2). Then, the on-board device 10 uploads the recorded data to the server device 100 (step S3).

[0024] Meanwhile, the server device 100 collects the recorded data uploaded from each vehicle V (step S4). The collected recorded data is stored, for example, in a collection DB (Database).

[0025] Furthermore, in the event of a predetermined event, such as an accident, the in-vehicle device 10 and the server device 100 protect the recorded data corresponding to that event. Protecting the recorded data means preventing overwriting of the relevant recorded data. This ensures that important recorded data is secured with redundancy on both the in-vehicle device 10 and the server device 100.

[0026] Furthermore, as shown in Figure 2, the server device 100 learns the driving tendencies of individual drivers based on the collected recorded data, and then learns the average driving tendencies of all drivers based on the learning results (step S11). The server device 100 learns these driving tendencies using, for example, a multivariate analysis method. The server device 100 may also learn these driving tendencies using machine learning algorithms or the like. The server device 100 learns these driving tendencies based on at least vehicle information included in the recorded data.

[0027] The server device 100 then determines the current state of the driver by comparing the real-time recorded data with the learning results (step S12). By comparing the real-time recorded data for each driver with the learning results of the average driving tendencies of all drivers, the server device 100 can, so to speak, grasp the driving situation of each driver from a macro perspective.

[0028] Then, the server device 100 notifies the in-vehicle device 10 of the determination result (step S13), and the in-vehicle device 10 presents the notified determination result to the driver (step S14).

[0029] As described above, the information processing method according to the embodiment learns the driving tendencies of each driver of a plurality of vehicles V based on recorded data that includes at least vehicle information acquired for each of the plurality of vehicles V, learns the average driving tendencies of the plurality of drivers from the learning results of the driving tendencies of each driver, and determines the current driving status of the driver of the vehicle corresponding to the recorded data by comparing the current recorded data with the learning results of the average driving tendencies.

[0030] Therefore, according to the information processing method of the embodiment, by adding the content of the learning results from a macro perspective to the real-time recorded data, the driver's driving situation can be grasped with greater accuracy and flexibility.

[0031] Below, we will describe in more detail an example of the configuration of the information processing system 1 to which the information processing method according to the above embodiment is applied.

[0032] Figure 3 is a block diagram showing an example configuration of the in-vehicle device 10 according to the embodiment. Note that Figure 3 and Figure 6, shown later, only show the components necessary to explain the features of this embodiment, and descriptions of general components are omitted.

[0033] In other words, the components illustrated in Figures 3 and 6 are functional concepts and do not necessarily need to be physically configured as shown. For example, the specific forms of distribution and integration of each block are not limited to those shown, and it is possible to configure all or part of them by functionally or physically distributing and integrating them in any unit according to various loads and usage conditions.

[0034] Furthermore, in the explanations using Figures 3 and 6, explanations of components that have already been explained may be simplified or omitted.

[0035] As shown in Figure 3, the in-vehicle device 10 according to this embodiment includes a camera 11, an HMI (Human Machine Interface) unit 12, an in-vehicle communication unit 13, an external communication unit 14, a storage unit 15, and a control unit 16. In addition, various in-vehicle sensors 3, such as an acceleration sensor, an accelerator sensor, and a brake sensor, are connected to the in-vehicle device 10 via the aforementioned CAN or the like.

[0036] Camera 11 is mounted at various locations on the vehicle V, such as the windshield and rear window, and captures images of a predetermined imaging area around the vehicle V.

[0037] The HMI unit 12 is a human-machine interface component that includes means, devices, and software for the user and the in-vehicle device 10 to exchange information. The HMI unit 12 includes hardware components such as an LCD touch panel, speaker, and microphone, as well as software components such as a GUI (Graphical User Interface).

[0038] The in-vehicle communication unit 13 is implemented by a network adapter or the like. The in-vehicle communication unit 13 is wiredly connected to the aforementioned CAN, etc., and transmits and receives information with the in-vehicle sensor 3. Alternatively, the in-vehicle communication unit 13 may transmit and receive information with the in-vehicle sensor 3 using wireless communication such as Wi-Fi (registered trademark), Bluetooth (registered trademark), UWB (Ultra Wide Band), etc.

[0039] The external communication unit 14 is implemented by a network adapter or the like. The external communication unit 14 is wirelessly connected to the aforementioned network N and transmits and receives information with the server device 100.

[0040] The storage unit 15 is implemented by a storage device such as RAM (Random Access Memory) or flash memory, or by a disk device such as a hard disk drive or optical disk drive. In the example shown in Figure 3, the storage unit 15 stores the recorded information 15a.

[0041] Recorded information 15a is information that includes a group of recorded data in which various vehicle information is recorded in synchronization with the video captured by the camera 11.

[0042] The control unit 16 is a controller and is realized by the execution of various programs (not shown) stored in the memory unit 15 using RAM as a working area by a CPU (Central Processing Unit) or MPU (Micro Processing Unit), etc. Furthermore, the control unit 16 can be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0043] The control unit 16 includes an acquisition unit 16a, a recording unit 16b, a detection unit 16c, a recording protection unit 16d, an upload unit 16e, and a presentation unit 16f, and realizes or executes the information processing functions and operations described below.

[0044] The acquisition unit 16a acquires video footage captured by the camera 11. The acquisition unit 16a also acquires vehicle information, which is sensor data output from the on-board sensor 3, via the in-vehicle communication unit 13. Furthermore, the acquisition unit 16a acquires information transmitted from the server device 100 via the external communication unit 14.

[0045] The recording unit 16b generates recording data synchronized with the vehicle information output from the on-board sensor 3 for the video captured by the camera 11, and records it in the recording information 15a. The recording unit 16b also displays the generated recording data on the HMI unit 12.

[0046] The detection unit 16c detects the occurrence of an event requiring protection of recorded data, such as an accident, based on vehicle information output from the on-board sensor 3. The detection unit 16c also notifies the server device 100 of the detected event via the external communication unit 14.

[0047] When the detection unit 16c detects the occurrence of the above-mentioned event, the recording protection unit 16d protects the corresponding recording data at the time the event occurs.

[0048] The upload unit 16e uploads the recorded data generated by the recording unit 16b to the server device 100 as appropriate via the external communication unit 14.

[0049] When the acquisition unit 16a acquires the aforementioned determination result from the server device 100, the presentation unit 16f notifies the user of the determination result via the HMI unit 12.

[0050] Here, Figure 4 shows an example of vehicle information acquired by the in-vehicle device 10. Figure 5 shows an image of the recorded data.

[0051] The acquisition unit 16a acquires various vehicle information from the on-board sensor 3, as shown in Figure 4. As shown in the figure, this vehicle information includes the speed displayed on the speedometer, accelerator pedal operation, brake pedal operation, whether or not a seat belt is fastened, engine speed, steering angle, etc.

[0052] As shown in the figure, this vehicle information is based on the Ministry of Land, Infrastructure, Transport and Tourism's guidelines regarding EDRs. This allows the on-board device 10 to record vehicle information similar to that of an EDR. The example in the figure is merely one example, and other information such as the status of the turn signals, the status of the headlights, and location information may also be included.

[0053] Furthermore, the recording unit 16b generates recording data in the image shown in Figure 5, records it to the recording information 15a, and displays this recording data on the HMI unit 12. As shown in the figure, the recording data includes video from the camera 11 and M1 to M9 sections.

[0054] Sections M1 to M9 correspond to various vehicle information acquired by the acquisition unit 16a. Section M1 is an icon corresponding to the aforementioned brake pedal operation, and is a diagram of a brake pedal being pressed. Section M1 is drawn so that, for example, the angle of the brake pedal changes according to the amount of brake pedal operation in real time.

[0055] The M2 section is an icon corresponding to the aforementioned accelerator pedal operation, and depicts an image of pressing the accelerator pedal. The M2 section is drawn in accordance with the amount of accelerator pedal operation in real time, for example, by changing the angle of the accelerator pedal.

[0056] The M3 section is an icon corresponding to the turn signal illumination status mentioned above. The M3 section is drawn to reflect the real-time illumination status of the turn signals. The M4 section is an icon corresponding to the headlight illumination status mentioned above. The M4 section is drawn to reflect the real-time illumination status of the headlights.

[0057] The M5 section is an icon corresponding to the aforementioned steering angle, and it depicts a rotating steering wheel. The M5 section is drawn in accordance with the real-time steering angle, for example, so that the steering wheel's rotation angle changes.

[0058] The M6 ​​section is an icon corresponding to whether or not the seat belt is fastened, and it is a graphic representation of the buckle and tongue. The M6 ​​section is drawn in real time according to whether or not the seat belt is fastened, for example, by showing the buckle connecting to or detaching from the tongue.

[0059] Section M7 is a display showing the aforementioned location information. Section M8 is a display showing the speed indicated on the speedometer. Section M9 is a display showing the aforementioned engine speed. Recording such data and protecting it in both the on-board device 10 and the server device 100 in the event of an accident will be extremely useful for analyzing the circumstances of an accident.

[0060] Next, an example configuration of the server device 100 will be described using Figure 6. Figure 6 is a block diagram showing an example configuration of the server device 100 according to this embodiment.

[0061] As shown in Figure 6, the server device 100 according to this embodiment includes a communication unit 101, a storage unit 102, and a control unit 103.

[0062] The communication unit 101 is implemented by a network adapter or the like. The communication unit 101 is connected to the aforementioned network N by wire or wireless connection and transmits and receives information with the in-vehicle device 10.

[0063] The storage unit 102 is implemented by a storage device such as RAM or flash memory, or a disk device such as a hard disk drive or optical disk drive. In the example in Figure 6, the storage unit 102 stores the collected DB 102a, driver-specific driving trend information 102b, and average driving trend information 102c.

[0064] The collected DB 102a is a database where recorded data collected from each in-vehicle device 10 is stored. The driver-specific driving tendency information 102b is a learning model of the driving tendencies of each driver. The average driving tendency information 102c is a learning model of the average driving tendencies of all drivers. The driver-specific driving tendency information 102b and the average driving tendency information 102c correspond to the learning results explained using Figure 2.

[0065] The control unit 103 is a controller and is implemented by a CPU, MPU, etc., which executes various programs (not shown) stored in the memory unit 102 using RAM as the working area. The control unit 103 can also be implemented by an integrated circuit such as an ASIC or FPGA.

[0066] The control unit 103 includes a collection unit 103a, an acquisition unit 103b, a record protection unit 103c, a learning unit 103d, a determination unit 103e, and a notification unit 103f, and realizes or executes the information processing functions and operations described below.

[0067] The collection unit 103a collects recorded data from each in-vehicle device 10 via the communication unit 101 and stores it in the collection DB 102a. The acquisition unit 103b acquires the occurrence of events notified from each in-vehicle device 10 via the communication unit 101.

[0068] When the in-vehicle device 10 notifies the in-vehicle device 10 of the occurrence of an event requiring protection of recorded data, the record protection unit 103c protects the corresponding recorded data at the time such an event occurs.

[0069] The learning unit 103d learns the driving tendencies of each driver based on the recorded data stored in the collection DB 102a, and generates driver-specific driving tendency information 102b as a learning result. The learning unit 103d also learns the average driving tendencies of all drivers based on the driver-specific driving tendency information 102b, and generates average driving tendency information 102c as a learning result. The learning unit 103d also updates the driver-specific driving tendency information 102b and the average driving tendency information 102c as appropriate based on the recorded data newly stored in the collection DB 102a.

[0070] The determination unit 103e determines the current driving status of the driver by comparing the real-time recorded data with the driver-specific driving tendency information 102b and the average driving tendency information 102c. The notification unit 103f notifies each in-vehicle device 10 of the determination result made by the determination unit 103e via the communication unit 101.

[0071] Next, examples of determinations made by the determination unit 103e will be explained using Figures 7 to 9. Figure 7 is a diagram (part 1) showing the first determination example made by the determination unit 103e. Figure 8 is a diagram (part 2) showing the first determination example made by the determination unit 103e. Figure 9 is a diagram showing the second determination example made by the determination unit 103e.

[0072] In the first judgment example, regarding the braking timing of all drivers who are driving on a certain road at the legal speed limit after seeing a red light, it is assumed that the braking timing of the driver of the target vehicle Vs was late compared to the average driving tendency, as shown in Figure 7.

[0073] In such a case, the determination unit 103e determines that the driver of the target vehicle Vs is highly fatigued, as shown in the figure. The determination unit 103e then notifies the onboard device 10 of the target vehicle Vs of this determination result.

[0074] Upon receiving the notification, the in-vehicle device 10, as shown in Figure 8, displays guidance to the HMI unit 12 based on the notification, for example, suggesting that the driver may be tired because the brakes are applied later than usual, and therefore urging them to take a break. This allows for early detection of potential problems and enables measures to be taken to mitigate the possibility of a major accident.

[0075] Furthermore, in the second judgment example, the driver of the target vehicle Vs does not typically exceed the legal speed limit based on individual driver driving tendencies, but as shown in Figure 9, in a certain section, the driver was driving at a speed faster than usual compared to the legal speed limit.

[0076] In the first judgment example, it is conceivable that a warning or other action would be taken in response to such driving conditions. However, as shown in the figure, the speed of the vehicle in question Vs is not considered high in light of the average driving trends in that section.

[0077] In such cases, the determination unit 103e determines that the speed of the target vehicle Vs is reasonable, as shown in the figure. In other words, the determination unit 103e determines that the target vehicle Vs is able to travel in the same flow as the flow of vehicles V in that section. For this reason, the determination unit 103e does not cause the in-vehicle device 10 to display a warning or anything similar. This allows for a more accurate and flexible understanding of the driver's driving situation by incorporating a macro perspective.

[0078] Next, the processing sequence of the information processing system 1 will be explained using Figures 10 and 11. Figure 10 shows the processing sequence (part 1) of the information processing system 1 according to the embodiment. Figure 11 shows the processing sequence (part 2) of the information processing system 1 according to the embodiment.

[0079] As shown in Figure 10, the in-vehicle device 10 acquires vehicle information (step S101), and records this vehicle information together with the video in synchronization with the video (step S102). Then, the in-vehicle device 10 uploads the recorded data to the server device 100 (step S103). The server device 100 collects this recorded data (step S104).

[0080] Furthermore, if the in-vehicle device 10 detects an accident (step S105), it uploads the recorded data to the server device 100 (step S106). At this time, the in-vehicle device 10 also notifies the server of the accident event, as shown in the figure. The in-vehicle device 10 also protects the corresponding recorded data when an accident occurs (step S107). When the server device 100 receives notification of the accident event, it also protects the corresponding recorded data when an accident occurs (step S108).

[0081] Furthermore, as shown in Figure 11, the server device 100 learns the driving tendencies of each driver based on the collected recorded data periodically or as needed (step S109). The server device 100 also learns the average driving tendencies of all drivers based on the results of learning the driving tendencies of each driver (step S110).

[0082] Furthermore, the server device 100 determines the current driver status by comparing the real-time recorded data with the learning results from steps S109 and S110 (step S111). The server device 100 then notifies the in-vehicle device 10 of the determination result (step S112), and the in-vehicle device 10 presents the determination result to the driver (step S113).

[0083] By the way, so far we have given examples where the recorded data includes vehicle information from the on-board sensor 3, but it may also include other information that indicates the driver's driving condition, not just vehicle information. Other information may include, for example, vital information from the vital sensor.

[0084] Figure 12 shows an image of the recorded data related to the modified example. In addition to the image of the recorded data shown in Figure 5, Figure 12 also includes the M10 section.

[0085] In the example shown in Figure 12, section M10 is an icon capable of displaying an indicator corresponding to the alcohol concentration in the driver's breath. In this case, the in-vehicle device 10 obtains the alcohol concentration in the driver's breath from an alcohol checker installed in the vehicle cabin as one of the vital sensors.

[0086] Alcohol testers that can communicate via Bluetooth or similar technologies are commercially available, and operators of fleet management systems can provide them as equipment for the commercial vehicles under their management.

[0087] In such a case, the in-vehicle device 10 obtains the alcohol concentration in the driver's breath from the alcohol checker via the in-vehicle communication unit 13, and generates recorded data that includes this alcohol concentration along with video and vehicle information.

[0088] Furthermore, vital sensors are not limited to alcohol checkers; they can be any device capable of detecting various vital information, such as the driver's respiratory rate, heart rate, and gaze.

[0089] As described above, the server device 100 (corresponding to an example of an "information processing device") according to the embodiment includes a control unit 103. The control unit 103 learns the driving tendencies of each driver of a plurality of vehicles V based on recorded data that includes at least vehicle information acquired in each of the plurality of vehicles V, learns the average driving tendencies of the plurality of drivers from the learning results of the driving tendencies of each driver, and determines the current driving status of the driver of the vehicle V corresponding to the recorded data by comparing the current recorded data with the learning results of the average driving tendencies.

[0090] Therefore, according to the server device 100 of this embodiment, the driver's driving status can be grasped with greater accuracy and flexibility.

[0091] Furthermore, the control unit 103 learns the driving tendencies of each driver and the average driving tendencies based at least on the vehicle information.

[0092] Therefore, according to the server device 100 of the embodiment, it is possible to learn the driving tendencies of each driver and the average driving tendencies based on sensor data from at least the on-board sensor 3.

[0093] Furthermore, the control unit 103 determines that the driver of the target vehicle Vs is highly fatigued if the braking timing of the target vehicle Vs is late in light of the average driving tendencies described above.

[0094] Therefore, according to the server device 100 of this embodiment, it is possible to grasp early signs of driver abnormalities, such as fatigue levels, from a macro perspective.

[0095] Furthermore, if the control unit 103 determines that the driver of the target vehicle Vs is highly fatigued, it will notify the driver of the target vehicle Vs to take a break.

[0096] Therefore, according to the server device 100 of this embodiment, it is possible to present signs of abnormality to the user at an early stage and take measures to reduce the possibility of it leading to a major accident.

[0097] Furthermore, if the driving conditions of the driver of the target vehicle Vs do not match the driver's normal driving tendencies, the control unit 103 will determine the driver's driving conditions based on the learned results of the average driving tendencies during the section in which the target vehicle Vs is traveling.

[0098] Therefore, according to the server device 100 of this embodiment, it is possible to appropriately determine the driver's driving situation from a macro perspective, without unconditionally issuing warnings when the situation does not match the driver's normal driving tendencies.

[0099] Furthermore, even if the speed of the target vehicle Vs is faster than the normal speed of the driver of the target vehicle Vs, the control unit 103 determines that it is appropriate if it is not too fast in light of the learning results of the average driving tendency in the above section.

[0100] Therefore, according to the server device 100 of this embodiment, even if the driver is traveling at a speed faster than their normal speed, it is possible to determine, from a macro perspective, that the vehicle is traveling in line with the flow of traffic in that section.

[0101] Furthermore, the information processing system 1 according to the embodiment comprises a plurality of in-vehicle devices 10 and a server device 100. The in-vehicle devices 10 generate recorded data that includes at least vehicle information of the vehicle V on which the in-vehicle devices 10 are installed and transmit it to the server device 100. The server device 100 collects the recorded data, learns the driving tendencies of each driver corresponding to the plurality of in-vehicle devices 10 based on the recorded data, learns the average driving tendencies of the plurality of drivers from the learning results of the driving tendencies of each driver, and determines the current driving status of the driver of the vehicle corresponding to the recorded data by comparing the current recorded data with the learning results of the average driving tendencies.

[0102] Therefore, according to the information processing system 1 of this embodiment, the driver's driving conditions can be grasped with greater accuracy and flexibility.

[0103] Furthermore, the in-vehicle device 10 and the server device 100 protect the aforementioned recorded data when a predetermined event requiring protection of the recorded data occurs, respectively.

[0104] Therefore, according to the information processing system 1 of this embodiment, important recorded data can be secured with redundancy in both the in-vehicle device 10 and the server device 100.

[0105] Furthermore, the server device 100 is a fleet management server that manages the operation of commercial vehicles.

[0106] Therefore, according to the information processing system 1 of this embodiment, the driving conditions of drivers can be grasped with greater accuracy and flexibility in the operation management of commercial vehicles.

[0107] Furthermore, the information processing method according to the embodiment is an information processing method executed by the server device 100, which includes: learning the driving tendencies of each driver of a plurality of vehicles V based on recorded data that includes at least vehicle information acquired for each of the plurality of vehicles V; learning the average driving tendencies of the plurality of drivers from the results of learning the driving tendencies of each driver; and determining the current driving status of the driver of the vehicle corresponding to the recorded data by comparing the current recorded data with the results of learning the average driving tendencies.

[0108] Therefore, according to the information processing method of the embodiment, the driver's driving conditions can be grasped with greater accuracy and flexibility.

[0109] In the embodiment described above, the server device 100 determines the driver's driving status, but this is not limited to this, and the in-vehicle device 10 may also perform such determination. In this case, the server device 100 distributes, for example, the learned driver-specific driving tendency information 102b and the average driving tendency information 102c to each in-vehicle device 10. The in-vehicle device 10 then uses the distributed driver-specific driving tendency information 102b and the average driving tendency information 102c to determine the driver's driving status.

[0110] Further effects and modifications can be readily derived by those skilled in the art. Therefore, broader aspects of the present invention are not limited to the specific details and representative embodiments expressed and described above. Accordingly, various modifications are possible without departing from the spirit or scope of the overall concept of the invention as defined by the appended claims and their equivalents. [Explanation of Symbols]

[0111] 1. Information Processing System 3. Vehicle sensors 10 Onboard equipment 11 Cameras 12 HMI section 13. In-vehicle communications unit 14. External communications unit 15 Storage section 15a Record Information 16 Control Unit 16a Acquisition part 16b Recording Section 16c Detection unit 16d Record Protection Unit 16e Upload Section 16f Presentation section 100 Server Devices 101 Communications Department 102 Storage section 102a Collection DB 102b Driver-Specific Driving Trends Information 102c Average driving tendency information 103 Control Unit 103a Collection Department 103b Acquisition Department 103c Record Protection Section 103d Learning Department 103e Judgment section 103f Notification Department V Vehicle Vs Target Vehicles

Claims

1. Based on recorded data which includes at least vehicle information acquired for each of the multiple vehicles, learn the driving tendencies of each driver of the multiple vehicles. Based on the learning results of each driver's driving tendencies, statistical data regarding operations in predetermined driving events on a specific road section is learned as the average driving tendencies of multiple drivers. By comparing the current recorded data with the learning results of the average driving tendency, the driving status of the driver of the target vehicle corresponding to the recorded data is determined, and the result of the determination is notified to the driver of the target vehicle. An information processing device equipped with a control unit.

2. The control unit is When the average braking timing of the driver of the target vehicle is slower than the average braking timing of multiple drivers in the aforementioned specific road section, the driver of the target vehicle is notified accordingly. The information processing apparatus according to claim 1.

3. The control unit is When the vehicle speed of the driver of the aforementioned vehicle is faster than usual based on the driver's individual driving tendencies, and also faster than the average vehicle speed of multiple drivers in the aforementioned specific road section, the driver of the aforementioned vehicle is notified accordingly. The information processing apparatus according to claim 1 or 2.

4. The control unit, Based at least the vehicle information, the system learns the driving tendencies of each driver and the average driving tendencies. The information processing apparatus according to claim 1, 2, or 3.

5. The control unit, If the aforementioned driving event involves braking after recognizing a red light, and the braking timing of the vehicle in question is late compared to the average braking timing of multiple drivers, which is the result of learning the average driving tendencies, then it is determined that the driver of the vehicle in question is highly fatigued. An information processing apparatus according to any one of claims 1 to 4.

6. The control unit, If it is determined that the driver of the aforementioned vehicle is highly fatigued, the system will notify the driver of the aforementioned vehicle to encourage them to take a break. The information processing apparatus according to claim 5.

7. The control unit, If the aforementioned driving event is driving on a specific road section, and the driving behavior of the target vehicle does not match the driver's normal driving tendencies, the appropriateness of the driver's driving behavior is determined based on the average speed of multiple drivers, which is the result of learning the average driving tendencies of the average drivers in the section the target vehicle is driving. The information processing apparatus according to any one of claims 1 to 6.

8. The control unit, Even if the speed of the subject vehicle is faster than the normal speed of the subject vehicle's driver, the driving will be deemed appropriate if it is not faster than the average speed of multiple drivers, which is the result of learning the average driving tendencies of the average drivers in the specific road section. The information processing apparatus according to claim 7.

9. Equipped with multiple in-vehicle devices and an information processing device, The in-vehicle device is The system generates record data that includes at least vehicle information of the vehicle on which the in-vehicle device is installed and transmits it to the information processing device. The aforementioned information processing device is The aforementioned record data is collected, Based on the recorded data, the driving tendencies of each driver corresponding to the multiple in-vehicle devices are learned. Based on the learning results of each driver's driving tendencies, statistical data regarding operations in predetermined driving events on a specific road section is learned as the average driving tendencies of multiple drivers. By comparing the current recorded data with the learning results of the average driving tendency, the driving status of the driver of the target vehicle corresponding to the recorded data is determined, and the result of the determination is notified to the driver of the target vehicle. Information processing system.

10. The in-vehicle device and the information processing device are, When a predetermined event occurs that necessitates the protection of the aforementioned recorded data, the corresponding recorded data is protected at the time of the event. The information processing system according to claim 9.

11. The aforementioned information processing device is This is a fleet management server that manages the operation of commercial vehicles. The information processing system according to claim 9 or 10.

12. An information processing method performed by an information processing device, Learning the driving tendencies of each driver of multiple vehicles based on recorded data that includes at least vehicle information acquired for each of the multiple vehicles, Based on the learning results of each driver's driving tendencies, statistical data regarding operations in predetermined driving events on a specific road section is learned as the average driving tendencies of multiple drivers. The current recorded data is compared with the learning results of the average driving tendency to determine the driving status of the driver of the target vehicle corresponding to the recorded data, and the result of the determination is notified to the driver of the target vehicle. Information processing methods, including those mentioned above.

Images