Information processing device, information processing method, and information processing program

Abstract

This technology provides a way to contribute to reducing accidents involving work vehicles by appropriately setting insurance premiums based on the operating conditions of the work vehicles. [Solution] The information processing device disclosed herein is an information processing device for setting the insurance premium for automobile insurance for a work vehicle 500. This information processing device comprises an acquisition unit that acquires detection information, which is information detected by a detection device 510 installed on the work vehicle 500; an extraction unit that extracts the driving state of the work vehicle 500 based on the detection information acquired by the acquisition unit; and a setting unit that sets the insurance premium based on the driving state extracted by the extraction unit. The setting unit sets the insurance premium by analyzing the driving state for a predetermined operation performed using the work vehicle 500.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program for setting an insurance premium for motor vehicle insurance for a work vehicle.

Background Art

[0002] In recent years, in vehicles such as automobiles, it is known to acquire data during driving of the vehicle by a driver and the operation behavior during driving of the vehicle by the driver, and to evaluate and diagnose the driving skills.

[0003] Furthermore, a method of setting an insurance premium for motor vehicle insurance using such evaluation and diagnosis of driving skills has been proposed so as to enhance the awareness of safe driving and reduce traffic accidents.

[0004] For example, Patent Document 1 discloses a technique for acquiring position information from a mobile terminal possessed by a driver and deriving a discount rate at the time of contracting the motor vehicle insurance of the driver according to the diagnosis result for the driving of the driver diagnosed based on the position information.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] Regarding the insurance premium of the insured of motor vehicle insurance for a work vehicle such as a shovel or a forklift, it is important to enhance the safety awareness of the crew who operates and drives the work vehicle and to improve the safety equipment provided on the work vehicle. Therefore, it is conceivable to give an incentive of a discount based on the driving state of the work vehicle for the insurance premium of the insured of motor vehicle insurance for such a work vehicle.

[0007] Here, according to the technology described in Patent Document 1, a driving diagnosis is performed based on the acquired location information, including driving operations during acceleration and deceleration, driving operations during right and left turns, vehicle driving data and vehicle behavior during acceleration and deceleration, and vehicle driving data and vehicle behavior during right and left turns, and an insurance premium discount is introduced based on the results. Therefore, it seems that it is possible to promote safe driving by encouraging drivers to obtain a more favorable discount rate. However, in the case of work vehicles such as excavators and forklifts, work is performed according to the purpose of the work vehicle. Therefore, setting insurance premiums based on driving diagnoses based on vehicle location information may not adequately reflect the safety awareness of the occupants operating and driving the work vehicle, or the impact of the safety equipment installed on the work vehicle, and the incentive effect of insurance premium discounts on reducing accidents involving work vehicles may not be fully realized.

[0008] The purpose of this disclosure is to provide a technology that can contribute to reducing accidents involving work vehicles by appropriately setting insurance premiums based on the driving conditions of said work vehicles. [Means for solving the problem]

[0009] The information processing device disclosed herein is an information processing device for setting automobile insurance premiums for work vehicles. This information processing device comprises: an acquisition unit that acquires detection information, which is information detected by a predetermined detection device installed on the work vehicle; an extraction unit that extracts the driving state of the work vehicle based on the detection information acquired by the acquisition unit; and a setting unit that sets the insurance premium based on the driving state extracted by the extraction unit. The setting unit sets the insurance premium by analyzing the driving state for a predetermined operation performed using the work vehicle.

[0010] Here, the above-mentioned work vehicles are equipped with safety features using detection devices to reduce accidents. Furthermore, by setting insurance premiums for work vehicles equipped with such safety features based on their operating status using the above-mentioned information processing device, it is possible to appropriately set insurance premiums for specific tasks performed using the work vehicles, thereby contributing to the reduction of accidents involving the work vehicles.

[0011] Furthermore, in the above-described information processing device, the detection device is configured to include a camera for photographing the area around the work vehicle, and / or a distance measuring sensor. The extraction unit extracts the status of the presence or absence of obstacles, including people, around the work vehicle that can be detected by the detection device during the work performed by the work vehicle in the monitored area monitored by the detection device, as the driving state. The setting unit may set the insurance premium based on the number of times the obstacle appears around the work vehicle, such that the insurance premium decreases as the number of occurrences decreases. This ensures that the incentive effect of discounts on insurance premiums is fully realized in order to reduce accidents involving work vehicles. In this case, the monitored area may be pre-set to include the work vehicle's travel area and turning area. By pre-setting the monitored area by the work vehicle user in this way, excessive detection and false detection of obstacles can be suppressed as much as possible when the area around the work vehicle is monitored at the work site where the work vehicle is used. Furthermore, in this case, the monitored area may be updated and set while the work vehicle is in motion, based on a predetermined identification that defines a predetermined exclusion area detected by the detection device, excluding the area defined by the identification. The above identification may be, for example, a gate or a marker displayed on the floor. By dynamically setting the monitored area while the work vehicle is in motion in this way, excessive detection or false detection of obstacles can be more effectively suppressed.

[0012] Furthermore, in the information processing device of the present disclosure, the detection device is configured to include a camera for photographing the occupant of the work vehicle, the extraction unit extracts the occupant's driving behavior of the work vehicle from the captured image data representing the occupant's image as the driving state, and the setting unit may set the insurance premium by comparing the occupant's driving behavior of the work vehicle with a predetermined safe driving behavior pattern. This would fully demonstrate the incentive effect of discounts on insurance premiums for reducing accidents in work vehicles and would also reduce the recurrence of dangerous behavior. In this case, the safe driving behavior pattern may be a pointing and calling out before the work is performed by the occupant, the extraction unit extracts the occupant's pointing behavior and face direction as the driving behavior, and the setting unit may set the insurance premium based on the degree of agreement between the occupant's pointing behavior and face direction and the pattern of the pointing and calling out.

[0013] Furthermore, in the information processing device of the present disclosure, the detection device is configured to include a camera for photographing the occupants of the work vehicle, the extraction unit extracts the occupants' driving behavior of the work vehicle and their personal identification information from the captured image data representing the occupants as the driving state, and the setting unit may set the insurance premium based on the occupants' driving behavior of the work vehicle and their personal identification information. According to this, since the occupants' personal identification information is automatically extracted from the captured image data, it becomes possible to set insurance premiums while easily reflecting each occupant's past performance.

[0014] The information processing device of this disclosure may further include a providing unit that provides the occupant of the work vehicle with factors that cause the insurance premium to fluctuate based on the driving conditions. In this case, the providing unit notifies the occupant of the factors that cause the insurance premium to fluctuate each time they occur using a predetermined output device installed in the work vehicle. This makes it possible to raise the safety awareness of the occupant of the work vehicle in real time regarding the reduction of accidents in the work vehicle from the perspective of insurance premiums.

[0015] Furthermore, this disclosure can be viewed from the perspective of a computer-based information processing method. Specifically, the information processing method of this disclosure is an information processing method for setting the insurance premium for automobile insurance for a work vehicle, wherein the computer performs an acquisition step of acquiring detection information, which is information detected by a predetermined detection device installed on the work vehicle; an extraction step of extracting the driving state of the work vehicle based on the detection information acquired in the acquisition step; and a setting step of setting the insurance premium based on the driving state extracted in the extraction step. The computer then sets the insurance premium in the setting step by analyzing the driving state for a predetermined operation performed using the work vehicle.

[0016] Furthermore, in the above-described information processing method, the detection device is configured to include a camera for photographing the area around the work vehicle, and / or a distance measuring sensor, and the computer, in the extraction step, extracts the state of whether or not there are obstacles, including people, around the work vehicle that can be detected by the detection device during the work performed by the work vehicle in the monitored area monitored by the detection device, as the driving state, and in the setting step, the insurance premium may be set based on the number of times the obstacles appear around the work vehicle, such that the insurance premium decreases as the number of occurrences decreases.

[0017] Furthermore, in the information processing method of the present disclosure, the detection device is configured to include a camera for photographing the occupants of the work vehicle, and the computer may, in the extraction step, extract the occupants' driving behavior of the work vehicle as the driving state from the captured image data representing the occupants' images, and in the setting step, set the insurance premium by comparing the occupants' driving behavior of the work vehicle with a predetermined safe driving behavior pattern.

[0018] Furthermore, this disclosure can be viewed from the perspective of an information processing program. Specifically, the information processing program of this disclosure is an information processing program for setting the insurance premium for automobile insurance for a work vehicle, and causes a computer to perform an acquisition step of acquiring detection information, which is information detected by a predetermined detection device installed on the work vehicle; an extraction step of extracting the driving state of the work vehicle based on the detection information acquired in the acquisition step; and a setting step of setting the insurance premium based on the driving state extracted in the extraction step. The computer is then caused in the setting step to set the insurance premium by analyzing the driving state for a predetermined operation performed using the work vehicle.

[0019] Furthermore, in the above-described information processing program, the detection device is configured to include a camera for photographing the area around the work vehicle, and / or a distance measuring sensor, and the computer may be instructed in the extraction step to extract, as the driving state, the presence or absence of obstacles, including people, that can be detected by the detection device during the work performed by the work vehicle in the monitored area monitored by the detection device, and in the setting step to set the insurance premium based on the number of times the obstacles appear around the work vehicle, such that the insurance premium decreases as the number of occurrences decreases.

[0020] Furthermore, in the information processing program of this disclosure, the detection device is configured to include a camera for photographing the occupants of the work vehicle, and the computer may be instructed in the extraction step to extract the occupants' driving behavior of the work vehicle as the driving state from the captured image data representing the occupants' images, and in the setting step to set the insurance premium by comparing the occupants' driving behavior of the work vehicle with a predetermined safe driving behavior pattern. [Effects of the Invention]

[0021] According to the present disclosure, by appropriately setting insurance premiums based on the operating state of a work vehicle, it is possible to contribute to reducing accidents in the work vehicle.

Brief Description of the Drawings

[0022] [Figure 1] It is a diagram showing a schematic configuration of an information processing system in the first embodiment. [Figure 2] It is a diagram showing the components of a server included in the information processing system in the first embodiment in more detail, as well as a user terminal that communicates with the server and the components of a work vehicle. [Figure 3] It is a diagram showing a schematic configuration of a work vehicle in the first embodiment. [Figure 4] It is a first diagram exemplifying the flow of operations of the information processing system in the first embodiment. [Figure 5] It is a diagram for explaining a monitoring target area that can be preset. [Figure 6] It is a diagram exemplifying an insurance premium setting table in the first embodiment. [Figure 7] It is a second diagram exemplifying the flow of operations of the information processing system in the first embodiment. [Figure 8] [[ID=二十九]]In the first embodiment, it is a diagram exemplifying a screen displayed on a display device of a work vehicle regarding the variation of insurance premiums based on the operating state. [Figure 9] It is a diagram showing the components of a server included in the information processing system in a modification of the first embodiment in more detail, as well as a user terminal that communicates with the server and the components of a work vehicle. [Figure 10] It is a diagram showing the components of a server included in the information processing system in the second embodiment in more detail, as well as a user terminal that communicates with the server and the components of a work vehicle. [Figure 11] It is a first diagram exemplifying the flow of operations of the information processing system in the second embodiment. [Figure 12]This figure illustrates the identification results obtained from the input to the pre-trained model in the second embodiment, and the neural network that constitutes the pre-trained model. [Figure 13] This figure illustrates the positions of skeletal parts of a work vehicle occupant user, as identified by the pre-trained model in the second embodiment. [Figure 14] This figure illustrates the insurance premium setting table in the second embodiment. [Figure 15] This is a second diagram illustrating the operation flow of the information processing system in the second embodiment. [Figure 16] In the second embodiment, this figure illustrates a screen displayed on a work vehicle's display device showing fluctuations in insurance premiums based on driving conditions. [Modes for carrying out the invention]

[0023] Embodiments of this disclosure will be described below with reference to the drawings. The configurations of the following embodiments are illustrative, and this disclosure is not limited to the configurations of these embodiments.

[0024] <First Embodiment> The overview of the information processing system in the first embodiment will be described with reference to Figure 1. Figure 1 is a diagram showing the schematic configuration of the information processing system in this embodiment. The information processing system 100 according to this embodiment is composed of a network 200, a server 300, a user terminal 400, and a work vehicle 500. The information processing system disclosed herein is a system for setting automobile insurance premiums for the work vehicle 500, and the setting of said premiums is performed by the server 300. In the following description, among the users who use the information processing system 100, the user who drives the work vehicle 500 will be referred to as a crew user, and the user who manages the work vehicle 500 as a business operator will be referred to as a business operator user. In the example shown in this embodiment, the business operator user may possess the user terminal 400.

[0025] Network 200 is, for example, an IP network. Network 200 can be wireless, wired, or a combination of both, as long as it is an IP network. For example, if communication is wireless, user terminals 400 and work vehicles 500 may access a wireless LAN access point (not shown) and communicate with server 300 via LAN or WAN. Furthermore, network 200 is not limited to these examples and may also be, for example, a public switched telephone network, fiber optic lines, ADSL lines, satellite communication networks, etc.

[0026] Server 300 is connected to user terminals 400 and work vehicles 500 via network 200. Note that in Figure 1, for the sake of simplicity, one server 300, one user terminal 400, and one work vehicle 500 are shown; however, the system is not limited to these.

[0027] Server 300 can be any electronic computer equipment with processing capabilities for computational and processing operations such as data acquisition, generation, and updating. For example, it may be a personal computer, server, mainframe, or other electronic device. In other words, Server 300 can be configured as a computer having a processor such as a CPU or GPU, main memory such as RAM or ROM, and auxiliary storage such as an EPROM, hard disk drive, or removable media. The removable media may be, for example, a USB memory stick or a disk recording medium such as a CD or DVD. The auxiliary storage device stores the operating system (OS), various programs, various tables, etc.

[0028] Furthermore, the server 300 may use SaaS (Software as a Service), PaaS (Platform as a Service), or IaaS (Infrastructure as a Service) via a cloud server as appropriate, without providing dedicated software, hardware, or OS for the information processing system 100 according to this embodiment.

[0029] The user terminal 400 may be any electronic device such as a mobile terminal owned by a user (business user) who uses the information processing system 100, and may be other terminal devices such as mobile terminals, tablet terminals, smartphones, wearable devices, personal computers, etc.

[0030] Next, a detailed explanation of the components of the server 300 will be given based on Figure 2. Figure 2 shows in more detail the components of the server 300 included in the information processing system 100 in the first embodiment, as well as the components of the user terminal 400 that communicates with the server 300 and the work vehicle 500.

[0031] The server 300 has a communication unit 301, a storage unit 302, and a control unit 303 as functional units. It loads a program stored in the auxiliary storage device into the working area of ​​the main memory and executes it. Through the execution of the program, each functional unit is controlled, thereby enabling each functional unit to perform its respective function according to its predetermined purpose. However, some or all of the functions may be implemented by hardware circuits such as ASICs or FPGAs.

[0032] Here, the communication unit 301 is a communication interface for connecting the server 300 to the network 200. The communication unit 301 is comprised of, for example, a network interface board and a wireless communication circuit for wireless communication. The server 300 is connected to user terminals 400, work vehicles 500, and other external devices via the communication unit 301, enabling communication.

[0033] The storage unit 302 comprises a main memory and an auxiliary storage device. The main memory is a memory where programs executed by the control unit 303 and data used by said control programs are stored. The auxiliary storage device is a device where programs executed by the control unit 303 and data used by said control programs are stored. The storage unit 302 pre-stores the insurance premium setting table, which will be described later. The storage unit 302 also stores captured image data and the like transmitted from the work vehicle 500. The server 300 can acquire data transmitted from the work vehicle 500, etc., via the communication unit 301. Furthermore, in this embodiment, the number of times obstacles appear, which will be described later, is stored in the storage unit 302.

[0034] The control unit 303 is a functional unit that manages the control performed by the server 300. The control unit 303 can be implemented by a processing unit such as a CPU. The control unit 303 is further composed of four functional units: an acquisition unit 3031, an extraction unit 3032, a setting unit 3033, and a provision unit 3034. Each functional unit may be implemented by executing a stored program using the CPU.

[0035] The acquisition unit 3031 acquires captured image data (detection information of this disclosure) captured by a camera 510 installed on the work vehicle 500 and which photographs the area around the work vehicle 500.

[0036] Figure 3 shows a schematic configuration of the work vehicle 500 in this embodiment. The work vehicle 500 in this embodiment is a forklift and includes a camera 510, a display device 520, and a communication device 530.

[0037] The imaging device 510 is installed on a work vehicle 500 and is used to photograph the area around the work vehicle 500. It has the function of accepting image input such as still images and videos, and is specifically implemented using a camera with an image sensor such as a Charged-Coupled Device (CCD), Metal-oxide-semiconductor (MOS), or Complementary Metal-Oxide-Semiconductor (CMOS).

[0038] The display device 520 is configured to display image data captured by the camera 510 and the insurance premium setting notification described later. Such a display device 520 is installed, for example, in the driver's cab of a forklift. This allows the forklift operator to check the surrounding conditions of the work vehicle 500 and information regarding the insurance premiums that may be set in real time via the display device 520.

[0039] The communication device 530 is a communication interface for connecting the work vehicle 500 to the network 200, and is comprised of, for example, a network interface board and a wireless communication circuit for wireless communication.

[0040] Thus, in this embodiment, the work vehicle 500 is equipped with safety features using the camera device 510 to reduce accidents.

[0041] Returning to Figure 2, the extraction unit 3032 extracts the operating state of the work vehicle 500 based on the captured image data (detection information of this disclosure) acquired by the acquisition unit 3031. Specifically, in this embodiment, the extraction unit 3032 extracts the state regarding the presence or absence of obstacles around the work vehicle 500 as the operating state.

[0042] Here, the above-mentioned obstacles are obstacles, including people, that can be detected by the camera 510 while the work vehicle 500 is working in the monitored area. The extraction unit 3032 can detect obstacles around the work vehicle 500 by, for example, comparing the height coordinates of the road surface the work vehicle 500 travels on with those of the detected objects. Alternatively, the extraction unit 3032 may detect obstacles around the work vehicle 500 based on well-known techniques using captured image data from the camera 510.

[0043] In this embodiment, the work vehicle 500 may be configured to include a distance measuring sensor as a detection device of the present disclosure. Here, the distance measuring sensor is, for example, a so-called LiDAR (Light Detection And Ranging) that measures the distance to an object by irradiating an object in the target space with laser light and receiving the reflected light reflected from the object, and can detect obstacles at a relatively long distance. Then, the extraction unit 3032 can extract whether or not there are obstacles around the work vehicle 500 based on the output from such a distance measuring sensor.

[0044] Furthermore, the above-mentioned monitoring area is the area monitored by the imaging device 510 and the distance measuring sensor, and can be pre-set to include the travel area and turning area of ​​the work vehicle 500. The setting of such a monitoring area will be explained later with reference to Figure 5.

[0045] The setting unit 3033 sets the automobile insurance premium for the work vehicle 500 based on the driving conditions for a predetermined operation performed using the work vehicle 500. In this embodiment, the setting unit 3033 sets the insurance premium based on the number of times obstacles appear around the work vehicle 500, such that the premium decreases as the number of obstacle appearances decreases. Details of the processing performed by the setting unit 3033 will be explained later with reference to Figure 6.

[0046] The provisioning unit 3034 notifies the business user who manages the work vehicle 500 of the automobile insurance premium for the work vehicle 500, as set by the setting unit 3033. At this time, the provisioning unit 3034 can notify the business user of the insurance premium by transmitting the above insurance premium to the business user's user terminal 400. In addition, the provisioning unit 3034 notifies the passenger user who drives the work vehicle 500 of the automobile insurance premium for the work vehicle 500, as set by the setting unit 3033, in real time. At this time, the provisioning unit 3034 can notify the passenger user of the insurance premium via the display device 520 of the work vehicle 500 by transmitting the above insurance premium to the work vehicle 500. Details of the processing performed by the provisioning unit 3034 will be explained later based on Figure 7.

[0047] In this embodiment, the user terminal 400 has a communication unit 401, an input / output unit 402, and a storage unit 403 as functional units. The communication unit 401 is a communication interface for connecting the user terminal 400 to the network 200, and is configured to include, for example, a network interface board and a wireless communication circuit for wireless communication. The input / output unit 402 is a functional unit for displaying information transmitted from the outside via the communication unit 401, and for inputting information when transmitting information to the outside via the communication unit 401. The storage unit 403 is configured to include a main memory and an auxiliary memory, similar to the storage unit 302 of the server 300.

[0048] The input / output unit 402 further includes a display unit 4021, an operation input unit 4022, and an image / audio input / output unit 4023. The display unit 4021 has the function of displaying various information and is implemented by, for example, an LCD (Liquid Crystal Display) display, an LED (Light Emitting Diode) display, or an OLED (Organic Light Emitting Diode) display. The operation input unit 4022 has the function of receiving operation input from the user and is specifically implemented by soft keys such as a touch panel or hard keys. The image / audio input / output unit 4023 has the function of receiving image input such as still images and videos and is specifically implemented by a camera using an image sensor such as Charged-Coupled Devices (CCD), Metal-oxide-semiconductor (MOS), or Complementary Metal-Oxide-Semiconductor (CMOS). The image / audio input / output unit 4023 also has the function of receiving audio input and output and is specifically implemented by a microphone or speaker.

[0049] Next, the operation flow of the information processing system 100 in this embodiment will be described. Figure 4 is a first diagram illustrating the operation flow of the information processing system 100 in this embodiment. Figure 4 describes the operation flow between the server 300, the user terminal 400, and the work vehicle 500 in the information processing system 100 in this embodiment, and the processing performed by the server 300, the user terminal 400, and the work vehicle 500. The flow shown in Figure 4 is repeatedly executed at predetermined intervals while the work vehicle 500 is in operation during a predetermined setting period for setting insurance premiums using the information processing system 100.

[0050] In this embodiment, first, captured image data, which is an image of the surroundings of the work vehicle 500 captured by the camera device 510 of the work vehicle 500, is transmitted to the server 300 (S101).

[0051] Then, the server 300 acquires the captured image data transmitted from the work vehicle 500 as detection information (S102).

[0052] The server 300 then performs an extraction process to extract the operating status of the work vehicle 500 (S103). As described above, in this embodiment, the status of whether or not there are obstacles around the work vehicle 500 is extracted as the operating status.

[0053] In the process of S103, the server 300 extracts the status of whether or not there are obstacles in the pre-configured monitoring area from the captured image data. As will be explained in the modified example of the first embodiment described later, if the extraction process is performed by the control device 540 of the work vehicle 500, the setting and updating of the monitoring area may be performed by the control device 540.

[0054] Here, Figure 5 is a diagram illustrating a pre-configured monitoring area. The monitoring area includes an area that can be set by the crew user from among the areas detectable by the imaging device 510, and the crew user can input the selection of the monitoring area based, for example, on distance information around the work vehicle 500 (for example, generated as a mesh map with 1m intervals).

[0055] For example, as shown in Figure 5, the crew user can select a monitoring area by excluding objects installed at the work site, such as shelves, that are included in the detectable area of ​​the camera 510 (such objects can be excluded because the crew user is already well aware of their existence). More specifically, the crew user can select a monitoring area by excluding the area on the map that contains objects installed at the work site. The gray area in Figure 5 represents the area selected by the user as the monitoring area. By pre-setting the monitoring area in this way by the crew user, excessive detection and false detection of obstacles can be suppressed as much as possible when the area around the work vehicle 500 is monitored at a work site where the work vehicle 500 is used. In other words, in the processing described later, when the number of times obstacles appear around the work vehicle 500 is counted, it is possible to suppress the excessive counting of objects installed at the work site that the crew user is well aware of as major causes of accidents in the work vehicle 500.

[0056] Furthermore, the monitoring area may be updated and set while the work vehicle 500 is in motion, based on a predetermined identification that defines a predetermined exclusion area, while excluding the area defined by the identification. The exclusion area is, for example, a pedestrian-only area. The identification is, for example, a gate or a marker displayed on the floor. In this way, by dynamically setting the monitoring area while the work vehicle 500 is in motion, excessive detection or false detection of obstacles can be more effectively suppressed.

[0057] Furthermore, the process of extracting information about the presence or absence of obstacles in the monitored area from the captured image data, and the process of extracting the above identification from the captured image data while the work vehicle 500 is in motion, can be performed based on well-known technologies.

[0058] Returning to Figure 4, in the process of S104, the server 300 determines whether or not an obstacle exists in the monitored area based on the operating status extracted in the process of S103. If the determination in the process of S104 is positive, the server 300 proceeds to the process of S105; if the determination in the process of S104 is negative, the server 300 proceeds to the process of S108.

[0059] If the S104 process is positive, the server 300 then counts that positive result as the number of times the obstacle has appeared (S105). As described above, the flow shown in Figure 4 is executed repeatedly at predetermined intervals during a predetermined setting period for setting insurance premiums using the information processing system 100. Therefore, the server 300 initializes the current number of appearances to 0 when the flow shown in Figure 4 is executed for the first time, and updates the current number of appearances by adding 1 to the current number of appearances in the S105 process each time the S104 process is positive during the above setting period.

[0060] The server 300 then provides the current occurrence count, which was counted and updated in the processing of S105, as a factor influencing the insurance premium (S106). Here, the server 300 transmits the factor influencing the insurance premium to the work vehicle 500.

[0061] Then, the work vehicle 500 receives the information transmitted from the server 300 and displays it on the display device 520 (corresponding to the output device in this disclosure) (S107). In other words, the occupant user of the work vehicle 500 is notified of the factors that cause the insurance premium to fluctuate based on the driving conditions. The output device in this disclosure is not limited to the display device 520 described above, and any device that can notify the factors that cause the insurance premium to fluctuate based on the driving conditions may be used, for example, an audio device that notifies the occupant user of the work vehicle 500 of the information by voice.

[0062] Thus, by notifying the occupant users of the work vehicle 500 of the factors affecting insurance premiums in real time, it becomes possible to raise the occupant users' safety awareness in real time regarding the reduction of accidents in the work vehicle 500 from the perspective of insurance premiums.

[0063] Next, the server 300 determines whether the end of the set period has arrived (S108). Here, the set period is a predetermined period for setting insurance premiums using the information processing system 100, and is, for example, equivalent to three days of the operating time of the work vehicle 500 (for example, if the work vehicle 500 operates for 6 hours a day, then 18 hours). If the determination in S108 is positive, the server 300 proceeds to the process in S109, and if the determination in S108 is negative, one execution of this flow is terminated.

[0064] If the S108 process is deemed positive, the server 300 then sets the insurance premium based on the cumulative number of occurrences during the set period (S109). Here, the server 300 calculates the insurance premium based on the number of occurrences of obstacles around the work vehicle 500, such that the insurance premium decreases as the number of occurrences decreases. This will be explained with reference to Figure 6.

[0065] Figure 6 illustrates an example of an insurance premium setting table in this embodiment. In this embodiment, insurance premiums are set so that they fluctuate according to the average number of occurrences per hour for the next contract (for example, the following month, six months later, one year later, three years later, etc.). In the example shown in Figure 6, if the average number of occurrences per hour is 0 to 3, the insurance premium for the next contract will be -30%; if the average number of occurrences per hour is 3 to 5, the insurance premium for the next contract will be -20%; and if the average number of occurrences per hour is 5 to 10, the insurance premium for the next contract will be -10%. Furthermore, if the average number of occurrences per hour is 10 to 20, the insurance premium may be set so that there is no change in the insurance premium for the next contract. Additionally, if the average number of occurrences per hour is 20 to 25, the insurance premium for the next contract will be +10%; if the average number of occurrences per hour is 25 to 40, the insurance premium for the next contract will be +20%; and if the average number of occurrences per hour is 40 or more, the insurance premium for the next contract will be +30%.

[0066] Thus, by calculating the insurance premium in such a way that the less frequently obstacles appear around the work vehicle 500, the lower the insurance premium becomes, the incentive effect of a discount on the insurance premium will be fully realized in order to reduce accidents involving the work vehicle 500.

[0067] In the S109 process, the insurance premium is set based on the insurance premium setting table shown in Figure 6 above, so that the insurance premium for the next contract (for example, the following month, six months later, one year later, three years later, etc.) varies according to the average number of occurrences per hour during the set period. For example, if the cumulative number of occurrences during the 18-hour set period is 126, the average number of occurrences per hour during the set period is 7, so the insurance premium for the next contract is set to be -10%. The server 300 then sends the insurance premium set in this way to the user terminal 400 of the business user.

[0068] Then, the user terminal 400 of the business operator receives the information transmitted from the server 300 and displays it on the display unit 4021 (S110). In other words, the business operator is provided with insurance premiums based on the driving status.

[0069] Furthermore, the server 300 may calculate the fluctuation of the insurance premium in real time based on the number of times obstacles appear around the work vehicle 500, such that the insurance premium decreases as the number of obstacle appearances decreases. This will be explained with reference to Figures 7 and 8.

[0070] Figure 7 is a second diagram illustrating the flow of operation of the information processing system 100 in this embodiment. Figure 7 describes the flow of operation between the server 300, the user terminal 400, and the work vehicle 500 in the information processing system 100 in this embodiment, and the processes executed by the server 300, the user terminal 400, and the work vehicle 500. The flow shown in Figure 7 is repeatedly executed at predetermined intervals while the work vehicle 500 is in operation during a predetermined setting period for setting insurance premiums using the information processing system 100. Furthermore, in each process shown in Figure 7, processes that are substantially the same as those shown in Figure 4 are denoted by the same reference numerals, and their detailed explanation is omitted.

[0071] In the flow shown in Figure 7, the server 300 calculates the change in insurance premium in real time based on the current number of occurrences counted and updated in the processing of S105 (S1061). Here, the server 300 calculates the change in insurance premium based on the number of times obstacles appear around the work vehicle 500, such that the insurance premium decreases as the number of occurrences decreases, as shown in the insurance premium setting table in Figure 6 above.

[0072] The server 300 then transmits the changes in insurance premiums calculated as described above to the work vehicle 500.

[0073] Then, the work vehicle 500 receives the information transmitted from the server 300 and displays it on the display device 520 (S1071). In other words, the occupant user of the work vehicle 500 is provided with information on the fluctuation of insurance premiums based on the driving conditions. This will be explained with reference to Figure 8.

[0074] Figure 8 illustrates a screen displayed on the display device 520 of the work vehicle 500, showing the fluctuation of insurance premiums based on the driving conditions, in this embodiment.

[0075] The screen SC1 illustrated in Figure 7(a) shows a message field SC11 regarding changes in insurance premiums based on driving conditions. In the example shown in Figure 7(a), it is displayed that an obstacle has been detected around the work vehicle 500, and further, the cumulative number of occurrences to date and the current average number of occurrences per hour are displayed. According to the insurance premium setting table shown in Figure 6 above, if the average number of occurrences per hour is between 5 and 10, the insurance premium for the next contract will be reduced by 10%, so the message field SC11 notifies that the insurance premium for the next contract will be reduced by 10%.

[0076] Similarly, in the example shown in Figure 7(b), a message is displayed indicating that an obstacle has been detected around the work vehicle 500, and the cumulative number of occurrences to date is also displayed. In the example shown in Figure 7(b), since the operating time of the work vehicle 500 since the start of the flow shown in Figure 4 is less than one hour, the predicted number of occurrences per hour, calculated based on the cumulative number of occurrences to date, is displayed. In the example shown in Figure 7(b), if the current situation continues, the predicted average number of occurrences per hour will be 20 to 25, so the message field SC11 notifies that the insurance premium for the next contract will be increased by 10%.

[0077] Thus, by notifying the occupant users of the work vehicle 500 in real time of the real-time changes in insurance premiums, it becomes possible to raise safety awareness among the occupant users in real time regarding the reduction of accidents in the work vehicle 500 through monetary value such as discounts or surcharges on insurance premiums.

[0078] As described above, according to this embodiment, by appropriately setting insurance premiums based on the driving conditions of the work vehicle, it is possible to contribute to reducing accidents involving the work vehicle.

[0079] <Modified form of the first embodiment> A modified example of the first embodiment will be described with reference to Figure 9. In the first embodiment described above, an example was described in which the server 300 extracts the operating state of the work vehicle 500 based on the captured image data (detection information of this disclosure) acquired by the acquisition unit 3031. In contrast, in this modified example, the extraction of the operating state is performed by the work vehicle 500.

[0080] Figure 9 shows in more detail the components of the server 300 included in the information processing system 100 in a modified example of the first embodiment, as well as the components of the user terminal 400 that communicates with the server 300 and the work vehicle 500.

[0081] In this modified example, the control unit 303 of the server 300 is configured to have two functional units: a setting unit 3033 and a providing unit 3034. The functions of the acquisition unit 3031 and extraction unit 3032 described in the first embodiment above are provided in the work vehicle 500.

[0082] More specifically, the work vehicle 500 in this modified example is equipped with a control device 540. The control device 540 is a functional unit that manages the processing performed by the work vehicle 500. The control device 540 can be implemented by an arithmetic processing unit such as a CPU. The control device 540 is further composed of two functional units: an acquisition unit 5041 and an extraction unit 5042. Each functional unit may be implemented by the CPU executing a stored program.

[0083] The acquisition unit 5041 then acquires image data (detection information of this disclosure) captured by a camera 510 installed on the work vehicle 500 and used to photograph the area around the work vehicle 500. The extraction unit 5042 then extracts the operating status of the work vehicle 500 based on the image data (detection information of this disclosure) acquired by the acquisition unit 5041.

[0084] Furthermore, when the driving status is extracted by the work vehicle 500 in this manner, the processes S101 to S103 in the flows shown in Figures 4 and 7 above are executed by the work vehicle 500, and the server 300 sets the insurance premium by obtaining the above driving status extracted by the work vehicle 500.

[0085] <Second Embodiment> A second embodiment will be described with reference to Figures 10 to 16. In the first embodiment described above, an example was described in which the presence or absence of obstacles, including people, that can be detected in the monitored area around the work vehicle 500 is extracted as the driving state, and the insurance premium is set based on the number of times the obstacles appear around the work vehicle 500. In contrast, in this embodiment, as the driving state, the driving behavior of the occupant of the work vehicle 500 is extracted from captured image data representing an image of the occupant of the work vehicle 500, and an example is described in which the insurance premium is set by comparing the driving behavior of the occupant of the work vehicle 500 with a predetermined safe driving behavior pattern.

[0086] Here, Figure 10 shows in more detail the components of the server 300 included in the information processing system 100 in the second embodiment, as well as the components of the user terminal 400 that communicates with the server 300 and the work vehicle 500.

[0087] In this embodiment, as shown in Figure 10, the safe driving behavior patterns described later are pre-stored in the storage unit 302 of the server 300.

[0088] Furthermore, in this embodiment, the camera device 510 of the work vehicle 500 is configured to be able to photograph the occupant user.

[0089] Figure 11 is a first diagram illustrating the flow of operation of the information processing system 100 in this embodiment. Figure 11 describes the flow of operation between the server 300, the user terminal 400, and the work vehicle 500 in the information processing system 100 in this embodiment, as well as the processes performed by the server 300, the user terminal 400, and the work vehicle 500. The flow shown in Figure 11 is repeatedly executed at predetermined intervals during a predetermined setting period for setting insurance premiums using the information processing system 100.

[0090] In this embodiment, similar to Figure 4 described in the first embodiment above, first, the image data captured by the camera 510 of the work vehicle 500 is transmitted to the server 300 (S201). Here, the image data captured in this embodiment is image data representing the image of the occupant user of the work vehicle 500.

[0091] Then, the server 300 acquires the captured image data transmitted from the work vehicle 500 as detection information (S202).

[0092] Then, the server 300 performs an extraction process to extract the driving status of the work vehicle 500 (S203). In this embodiment, the driving actions of the occupant user of the work vehicle 500 are extracted as the driving status of the work vehicle 500.

[0093] (Extraction process) Here, the details of the extraction process in this embodiment will be described. In the extraction process of this embodiment, captured image data is input to a pre-trained model, and the driving behavior of the work vehicle 500 by the occupant user is extracted. The pre-trained model is constructed by training with data that includes images representing people.

[0094] Here, Figure 12 is a diagram illustrating the identification result obtained from the input to the pre-trained model in this embodiment, and the neural network constituting the pre-trained model. In this embodiment, a neural network model generated by deep learning is used as the pre-trained model. The pre-trained model 30 in this embodiment has an input layer 31 that accepts predetermined image data as input, an intermediate layer (hidden layer) 32 that extracts feature quantities representing the skeletal information of a person from the image data input to the input layer 31, and an output layer 33 that outputs an identification result based on the feature quantities. In the example of Figure 12, the pre-trained model 30 has one intermediate layer 32, and the output of the input layer 31 is input to the intermediate layer 32, and the output of the intermediate layer 32 is input to the output layer 33. However, the number of intermediate layers 32 is not limited to one, and the pre-trained model 30 may have two or more intermediate layers 32.

[0095] Furthermore, as shown in Figure 12, each layer 31-33 has one or more neurons. For example, the number of neurons in the input layer 31 can be set according to the input image data. Also, the number of neurons in the output layer 33 can be set according to the identified driving behavior.

[0096] Then, neurons in adjacent layers are connected as appropriate, and each connection is assigned a weight (connection weight) based on the results of machine learning. In the example in Figure 12, each neuron is connected to all neurons in the adjacent layer, but the connections between neurons are not limited to this example and can be set as appropriate.

[0097] Such a pre-trained model 30 is constructed, for example, by performing supervised learning using training data that consists of pairs of image data containing images representing people and image labels representing the positions of parts of the person's skeleton. Specifically, the pairs of features and labels are given to a neural network, and the weights of the connections between neurons are tuned so that the output of the neural network is the same as the labels. In this way, a pre-trained model for learning the features of the training data and estimating results from inputs is inductively acquired.

[0098] Furthermore, the image data used to train the pre-trained model may include images representing a person in a neutral state, or images representing a person driving a work vehicle, etc.

[0099] Furthermore, the pre-trained model 30 may be constructed by performing unsupervised learning. For example, domain adaptation, a type of transfer learning, can be used for unsupervised learning. This allows for the acquisition of a pre-trained model without having to prepare a large amount of labeled training data.

[0100] Then, when the captured image data is input to this pre-trained model 30, the positions of the skeletal parts of the occupant user of the work vehicle 500 are identified in the captured image data, and based on this, the driving actions of the occupant user of the work vehicle 500 are extracted.

[0101] Here, Figure 13 illustrates the positions of the skeletal parts of a crew member of a work vehicle 500, as identified by the pre-trained model 30 in this embodiment. In Figure 13, the arms, torso, and face, which are the skeletal parts of the crew member, are represented by points and line segments in the image of the crew member included in the captured image data.

[0102] In this way, the server 300 can extract the direction of the occupant user's face (whether it is facing left, right, forward, backward, or diagonally) and pointing behavior (whether the arm is pointing left, right, forward, backward, or diagonally) as the occupant user's driving behavior of the work vehicle 500. In the example shown in Figure 13, it is extracted that the occupant user's face is facing forward.

[0103] Thus, according to the extraction process of this embodiment, by using the pre-trained model 30 to identify the positions of the skeletal parts of the occupant user in the captured image data and the driving actions of the occupant user based on these positions, driving actions can be extracted with high accuracy from the captured image data.

[0104] In the above description of the extraction process, an example was given in which the driving behavior of the work vehicle 500 by the occupant user is extracted based on the position of the occupant user's skeletal parts. However, in the extraction process of this embodiment, the driving behavior of the occupant user of the work vehicle 500 may also be extracted by inputting captured image data into the pre-trained model 30 and identifying the orientation of the occupant user's face and arms in the captured image data. In this case, the pre-trained model 30 has an input layer 31 that accepts predetermined image data as input, an intermediate layer (hidden layer) 32 that extracts feature quantities representing the orientation of the person's face and / or the orientation of the person's arms from the image data input to the input layer 31, and an output layer 33 that outputs identification results based on the feature quantities. Such a pre-trained model 30 can be constructed, for example, by performing supervised learning using training data which is a pair of image data containing an image representing a person and image labels representing the orientation of the person's face and / or the orientation of the person's arms.

[0105] Furthermore, the server 300 may extract pre-inspection actions performed by the occupant user before boarding the work vehicle 500 as driving actions of the occupant user. In this case, the image data acquired will be image data of the occupant user before boarding the work vehicle 500. The server 300 may also extract whether or not the occupant user is wearing safety equipment (helmet, safety vest, safety shoes, etc.) in conjunction with the above driving actions.

[0106] Returning to Figure 11, in S204, the server 300 performs a determination process to determine whether the driving behavior of the occupant user of the work vehicle 500 belongs to a safe driving behavior pattern, based on the driving state extracted by the processing in S203.

[0107] In the determination process in S204, by comparing the safe driving behavior patterns predetermined and stored in the storage unit 302 of the server 300 with the driving behaviors of the occupant user extracted by the extraction process, it is possible to determine whether or not the driving behavior of the work vehicle 500 by the occupant user belongs to a predetermined safe driving behavior pattern. The safe driving behavior patterns described above are, for example, pointing and calling out before work is performed on the work vehicle 500 by the occupant user. The pointing and calling out described above is a pointing and confirming of the operation of the work vehicle 500, and is performed when the forklift, which is the work vehicle 500, starts, stops, turns, or when the forks of the forklift are inserted into the load.

[0108] (Decision process) Here, the details of the determination process in this embodiment will be explained. In this embodiment, the pointing actions and facial orientation of the occupant user are extracted as driving actions. The server 300 then determines whether or not the extracted pointing actions and facial orientation of the occupant user belong to a pointing and calling implementation pattern. The above pointing and calling implementation patterns are predetermined and stored in the storage unit 302 of the server 300, and include, for example, pointing actions forward when the work vehicle 500 starts moving, pointing actions backward when the work vehicle 500 reverses, pointing actions to the stop line when the work vehicle 500 stops, pointing actions to the left and right when the work vehicle 500 turns, and pointing actions to the cargo when inserting the claws of the work vehicle 500 into the cargo.

[0109] Furthermore, the server 300 can determine, for example, whether the pointing action of the occupant user is pointing forward when the work vehicle 500 starts moving. The work vehicle 500 is equipped with vehicle sensors such as a speed sensor and an acceleration sensor, and the server 300 can recognize the starting, stopping, turning, etc. of the work vehicle 500 based on the values ​​detected by the vehicle sensors.

[0110] Furthermore, at this time, the server 300 may recognize information regarding the starting, stopping, turning, etc. of the work vehicle 500 based on image data representing the surroundings of the work vehicle 500, which is captured by the camera 510 of the work vehicle 500. In this case, the camera 510 may be positioned to capture both the occupant user of the work vehicle 500 and the surroundings of the work vehicle 500. The image data representing the surroundings of the work vehicle 500 that can be captured by the camera 510 includes stop lines and their positions, no-entry signs and their text, which are related to the starting and stopping of the work vehicle 500, and the server 300 can recognize these through image recognition processing. In this case, the server 300 can, for example, recognize the stop line based on the image data representing the surroundings of the work vehicle 500 captured by the camera 510, and determine whether the occupant user's pointing action is a forward pointing action at the timing when the work vehicle 500 reaches the stop line.

[0111] Furthermore, the above-mentioned patterns of pointing and calling include the fact that the person's face is turned towards the direction in which the pointing action is being performed.

[0112] Therefore, the server 300 determines whether the extracted crew user's face is facing the direction in which the pointing action is to be performed.

[0113] Returning to Figure 11, if the S204 process is positive, the server 300 proceeds to the S208 process; if the S204 process is negative, the server 300 proceeds to the S205 process.

[0114] If a negative result is obtained in the S204 process, the server 300 then counts the number of times the driver's actions of the work vehicle 500 by the occupant user are deemed to be unsafe driving behaviors that do not belong to the safe driving behavior pattern (S205). As described above, the flow shown in Figure 11 is executed repeatedly at predetermined intervals during a predetermined setting period for setting insurance premiums using the information processing system 100. Therefore, the server 300 initializes the current occurrence count to 0 when the flow shown in Figure 11 is executed for the first time, and updates the current unsafe behavior count in the S205 process each time a negative result is obtained in the S204 process during the above setting period by adding 1 to the current unsafe behavior count.

[0115] The server 300 then provides the current number of malfunctions counted and updated in processing S205 as a factor influencing the insurance premium (S206). Here, the server 300 transmits the factor influencing the insurance premium to the work vehicle 500.

[0116] The work vehicle 500 then receives the information transmitted from the server 300 and displays it on the display device 520 (corresponding to the output device in this disclosure) (S207). In other words, the occupant user of the work vehicle 500 is notified of the factors that cause the insurance premium to fluctuate based on the driving conditions. The output device in this disclosure is not limited to the display device 520 described above, and any device that can notify the factors that cause the insurance premium to fluctuate based on the driving conditions may be used, for example, an audio device that notifies the occupant user of the work vehicle 500 of the information by voice.

[0117] Thus, by notifying the occupant user of the work vehicle 500 in real time of factors that affect insurance premium fluctuations based on the occupant user's risky behavior, the occupant user will be more aware of the need to reduce accidents in the work vehicle 500 from an insurance premium perspective, and the recurrence of risky behavior can also be reduced.

[0118] Next, the server 300 determines whether the end of the set period has arrived (S208). Here, the set period is a predetermined period for setting insurance premiums using the information processing system 100, and is, for example, equivalent to three days of the operating time of the work vehicle 500 (for example, if the work vehicle 500 operates for 6 hours a day, then 18 hours). If the S208 process is positive, the server 300 proceeds to the S209 process; if the S208 process is negative, one execution of this flow is terminated.

[0119] If the S208 process is deemed positive, the server 300 then sets the insurance premium based on the cumulative number of bad actions during the set period (S209). Here, the server 300 can calculate the insurance premium such that the lower the number of bad actions, the lower the insurance premium. This will be explained with reference to Figure 14.

[0120] Figure 14 illustrates an example of an insurance premium setting table in this embodiment. In the example shown in Figure 14(a), the insurance premium is set so that it fluctuates according to the average number of misconducts per hour (for example, the following month, six months later, one year later, three years later, etc.). Specifically, in the example shown in Figure 14(a), if the average number of misconducts per hour is 0, the insurance premium for the next contract will be -30%; if the average number of misconducts per hour is 1 to 2, the insurance premium for the next contract will be -20%; and if the average number of misconducts per hour is 2 to 3, the insurance premium for the next contract will be -10%. In addition, if the average number of misconducts per hour is 3 to 5, the insurance premium may be set so that there is no change in the insurance premium for the next contract. Furthermore, insurance premiums may be set such that if the average number of misconduct incidents per hour is 5 to 7, the premium for the next contract will be increased by 10%, if the average number of misconduct incidents per hour is 7 to 10, the premium for the next contract will be increased by 20%, and if the average number of misconduct incidents per hour is 10 or more, the premium for the next contract will be increased by 30%.

[0121] Thus, by calculating insurance premiums in such a way that the fewer instances of unsafe driving behavior by the occupant user of the work vehicle 500 occur, the lower the insurance premium becomes, the incentive effect of insurance premium discounts will be fully realized in reducing accidents involving the work vehicle 500.

[0122] Furthermore, in the example shown in Figure 14(b), the insurance premium is set based on the degree of agreement (degree of agreement) between the occupant user's pointing behavior and facial orientation and the pattern of pointing and calling. The higher the safety rank based on the degree of agreement, the lower the insurance premium. Specifically, in the example shown in Figure 14(b), if the safety rank based on the degree of agreement is S, the insurance premium may be set so that the premium for the next contract is reduced by 20%. Here, a safety rank of S means that the degree of agreement is 95% or higher. The degree of agreement can be calculated by dividing the number of times the occupant user's driving behavior of the work vehicle 500 matches the safe driving behavior pattern by the total number of times determined. For example, if the occupant user is pointing, but their face is not facing the direction in which the pointing is being made, and the occupant user's driving behavior of the work vehicle 500 partially matches the safe driving behavior pattern, the number of matches may be counted as 0.5. And, if the safety rank based on the degree of agreement is A, the insurance premium may be set so that the premium for the next contract is reduced by 10%. Furthermore, if the safety rank based on the degree of agreement is B, the premium may be set so that there is no change in the premium for the next contract. If the safety rank based on the degree of agreement is C, the premium for the next contract may be set to increase by 10%, and if the safety rank based on the degree of agreement is D, the premium for the next contract may be set to increase by 20%.

[0123] Furthermore, when insurance premiums are set as shown in the example in Figure 14(b), in the S204 process described above, a positive determination may be made when the occupant user's driving behavior of the work vehicle 500 perfectly matches the safe driving behavior pattern, and a negative determination may be made when the occupant user's driving behavior of the work vehicle 500 partially matches the safe driving behavior pattern (for example, when the occupant user points, but their face is not turned in the direction of the pointing) or when they do not match. Then, in the S205 process described above, the degree of match may be calculated as described above.

[0124] In this case, the insurance premium may be set taking into consideration the personal identification information of the occupant user. Specifically, the storage unit 302 of the server 300 stores for each occupant user the number of times their past driving behavior was judged to match a safe driving behavior pattern, and the total number of judgments, and in the processing of S205 above, these counts may be updated to calculate the degree of match mentioned above. This makes it possible to set the insurance premium while reflecting the past performance of each occupant user.

[0125] In this case, the extraction process in S203 described above can extract personal identification information of the occupant user from the captured image data. For example, the server 300 can extract facial recognition information of the occupant user as personal identification information of the occupant user. As a result, by automatically extracting personal identification information of the occupant user from the captured image data, it becomes possible to set insurance premiums while easily reflecting the past performance of each occupant user.

[0126] Then, returning to Figure 11, the server 300 sends the insurance premium set as described above to the user terminal 400 of the business user.

[0127] Then, the user terminal 400 of the business operator receives the information transmitted from the server 300 and displays it on the display unit 4021 (S210). In other words, the business operator is provided with insurance premiums based on the driving status.

[0128] Furthermore, the server 300 may calculate the fluctuation of the insurance premium in real time based on the detected misconduct, such that the insurance premium decreases as the number of misconduct incidents decreases. This will be explained with reference to Figures 15 and 16.

[0129] Figure 15 is a second diagram illustrating the flow of operation of the information processing system 100 in this embodiment. Figure 15 describes the flow of operation between the server 300, the user terminal 400, and the work vehicle 500 in the information processing system 100 in this embodiment, and the processes executed by the server 300, the user terminal 400, and the work vehicle 500. The flow shown in Figure 15 is repeatedly executed at predetermined intervals while the work vehicle 500 is in operation during a predetermined setting period for setting insurance premiums using the information processing system 100. Furthermore, in each process shown in Figure 15, processes that are substantially the same as those shown in Figure 11 are denoted by the same reference numerals, and their detailed explanation is omitted.

[0130] In the flow shown in Figure 15, the server 300 calculates the change in insurance premium in real time (S2061) based on the current number of bad behaviors counted and updated in the processing of S205. Here, the server 300 calculates the change in insurance premium based on the detected bad behaviors, such that the insurance premium decreases as the number of bad behaviors decreases, as shown in the insurance premium setting table in Figure 14 above.

[0131] The server 300 then transmits the changes in insurance premiums calculated as described above to the work vehicle 500.

[0132] Then, the work vehicle 500 receives the information transmitted from the server 300 and displays it on the display device 520 (S2071). In other words, the occupant user of the work vehicle 500 is provided with information on the fluctuation of insurance premiums based on the driving conditions. This will be explained with reference to Figure 16.

[0133] Figure 16 is a diagram illustrating the screen displayed on the display device 520 of the work vehicle 500 regarding fluctuations in insurance premiums based on driving conditions in this embodiment.

[0134] The screen SC1 illustrated in Figure 16(a) shows a message field SC21 regarding changes in insurance premiums based on driving conditions. In the example shown in Figure 16(a), it displays that misconduct has been detected, and further displays the cumulative number of detections to date and the current average number of detections per hour. According to the insurance premium setting table shown in Figure 14 above, if the average number of detections per hour is 1, the insurance premium for the next contract will be -20%, so the message field SC21 notifies that the insurance premium for the next contract will be -20%.

[0135] Furthermore, in the example shown in Figure 16(b), although the occupant user is pointing, their face is not facing the direction of the pointing action. Therefore, a message is displayed indicating that the occupant user's driving behavior of the work vehicle 500 does not partially match the safe driving behavior pattern, and the current safety rank is also displayed. In the example shown in Figure 16(b), it is also displayed that if a notification is issued again indicating that the driving behavior does not match the safe driving behavior pattern, the safety rank will be downgraded, along with the change in insurance premiums for the next contract if the rank is downgraded.

[0136] This allows for real-time notification of changes in insurance premiums based on the driver's risky behavior. For example, retrospective determination based on driving history results in notification after a considerable amount of time has passed since the risky behavior occurred, providing little motivation for behavioral correction and making the risky behavior more likely to recur. In contrast, real-time notification like this allows for a stronger safety awareness among drivers regarding accident reduction in the work vehicle 500, through monetary value such as discounts or surcharges on insurance premiums, thereby reducing the likelihood of subsequent risky behavior recurrence.

[0137] In this embodiment as well, the extraction of the operating state may be performed by the work vehicle 500 in the same manner as described in the description of the modified example of the first embodiment above.

[0138] As described above, this embodiment also contributes to reducing accidents involving work vehicles by appropriately setting insurance premiums based on the driving conditions of the work vehicles.

[0139] <Other variations> The embodiments described above are merely examples, and this disclosure may be modified as appropriate without departing from its essence. For example, the processes and means described in this disclosure can be freely combined and implemented as long as no technical inconsistencies arise.

[0140] Furthermore, processes described as being performed by a single device may be divided and executed by multiple devices. For example, the acquisition unit 3031 may be formed in a separate arithmetic processing unit. In this case, these arithmetic processing units are preferably configured to cooperate. Also, processes described as being performed by different devices may be executed by a single device. In a computer system, the hardware configuration (server configuration) by which each function is implemented can be flexibly changed.

[0141] The present disclosure can also be realized by supplying a computer program implementing the functions described in the embodiments above to a computer, and having one or more processors in the computer read and execute the program. Such a computer program may be provided to the computer by a non-temporary computer-readable storage medium that can be connected to the computer's system bus, or it may be provided to the computer via a network. Non-temporary computer-readable storage mediums include, for example, any type of disk such as magnetic disks (floppy disks, hard disk drives (HDDs), etc.), optical disks (CD-ROMs, DVDs, Blu-ray discs, etc.), read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic cards, flash memory, optical cards, and any type of medium suitable for storing electronic instructions. [Explanation of Symbols]

[0142] 100... Information Processing Systems 200 Network 300 servers 301... Communications Department 302...Storage section 303... Control Unit 400...User terminals 500... Work vehicles 510... Imaging device 520...Display device

Claims

1. An information processing device for setting insurance premiums for automobile insurance on work vehicles, An acquisition unit that acquires detection information, which is information detected by a predetermined detection device installed on the aforementioned work vehicle, Based on the detection information acquired by the acquisition unit, an extraction unit extracts the operating status of the work vehicle, Based on the operating conditions extracted by the extraction unit, a setting unit sets the insurance premium, Equipped with, The setting unit sets the insurance premium by analyzing the driving conditions for a predetermined task performed using the work vehicle. Information processing device.

2. The detection device comprises a camera for photographing the area around the work vehicle, and / or a distance measuring sensor. The extraction unit extracts, as the operating state, the presence or absence of obstacles, including people, around the work vehicle that can be detected by the detection device during the work performed by the work vehicle in the monitored area monitored by the detection device, The setting unit sets the insurance premium based on the number of times the obstacle appears around the work vehicle, such that the insurance premium decreases as the number of occurrences decreases. The information processing apparatus according to claim 1.

3. The monitoring area is predetermined to include the area where the work vehicle is moving and the area where it is turning. The information processing apparatus according to claim 2.

4. The monitored area is updated and set while the work vehicle is in motion, based on a predetermined identification that defines a predetermined exclusion area detected by the detection device, with the area defined by the identification being excluded. The information processing apparatus according to claim 3.

5. The detection device is configured to include a camera for photographing the occupants of the work vehicle, The extraction unit extracts the driver's actions of the work vehicle from the captured image data representing the driver's image as the driving state. The setting unit sets the insurance premium by comparing the driver's actions of the work vehicle with a predetermined safe driving behavior pattern. The information processing apparatus according to claim 1.

6. The aforementioned safe driving behavior pattern is a pointing and calling out by the occupant before performing the work on the work vehicle, The extraction unit extracts the occupant's pointing gesture and the direction of their face as the driving behavior, The setting unit sets the insurance premium based on the degree of agreement between the occupant's pointing action and facial orientation and the pattern of the pointing and calling. The information processing apparatus according to claim 5.

7. The detection device is configured to include a camera for photographing the occupants of the work vehicle, The extraction unit extracts, as the driving state, the driver's actions of the work vehicle and the personal identification information of the driver from the captured image data representing the driver's image. The setting unit sets the insurance premium based on the driver's actions of the occupant and the occupant's personal identification information. The information processing apparatus according to claim 1.

8. The vehicle further comprises a provisioning unit that provides the occupants of the work vehicle with the factors that cause the insurance premium to fluctuate based on the driving conditions, The provisioning unit shall, with respect to the factors causing fluctuations in the insurance premium, notify the occupant of such factors using a predetermined output device installed in the work vehicle each time such factors occur. The information processing apparatus according to claim 1.

9. A method for processing information to set insurance premiums for automobile insurance on work vehicles, Computers An acquisition step of acquiring detection information which is information detected by a predetermined detection device installed on the work vehicle, Based on the detection information obtained in the acquisition step, an extraction step is performed to extract the operating status of the work vehicle, Based on the driving conditions extracted in the extraction step, a setting step is performed to set the insurance premium, The aforementioned computer, In the setting step, the insurance premium is set by analyzing the driving conditions for a predetermined task performed using the work vehicle. Information processing methods.

10. The detection device comprises a camera for photographing the area around the work vehicle, and / or a distance measuring sensor. The aforementioned computer, In the extraction step, with respect to obstacles, including people, that can be detected by the detection device during the work performed by the work vehicle in the monitored area monitored by the detection device, the state of whether or not such obstacles exist around the work vehicle is extracted as the operating state. In the setting step, the insurance premium is set based on the number of times the obstacle appears around the work vehicle, such that the insurance premium decreases as the number of occurrences decreases. The information processing method according to claim 9.

11. The detection device is configured to include a camera for photographing the occupants of the work vehicle, The aforementioned computer, In the extraction step, the driving actions of the occupant of the work vehicle are extracted from the captured image data representing the occupant's image as the driving state. In the setting step, the insurance premium is set by comparing the driver's actions of the work vehicle with a predetermined safe driving behavior pattern. The information processing method according to claim 9.

12. An information processing program for setting insurance premiums for automobile insurance on work vehicles, On the computer, An acquisition step of acquiring detection information which is information detected by a predetermined detection device installed on the work vehicle, Based on the detection information obtained in the acquisition step, an extraction step is performed to extract the operating status of the work vehicle, Based on the driving conditions extracted in the extraction step, the system performs a setting step to set the insurance premium. To the aforementioned computer, In the setting step, the insurance premium is set by analyzing the driving conditions for a predetermined task performed using the work vehicle. Information processing program.

13. The detection device comprises a camera for photographing the area around the work vehicle, and / or a distance measuring sensor. To the aforementioned computer, In the extraction step, for obstacles including people that can be detected by the detection device during the work performed by the work vehicle in the monitored area monitored by the detection device, the state of whether or not such obstacles exist around the work vehicle is extracted as the operating state. In the setting step, the insurance premium is set such that the insurance premium decreases as the number of occurrences of the obstacle around the work vehicle decreases. The information processing program according to claim 12.

14. The detection device is configured to include a camera for photographing the occupants of the work vehicle, To the aforementioned computer, In the extraction step, the driving actions of the occupant of the work vehicle are extracted from the captured image data representing the occupant's image as the driving state. In the setting step, the insurance premium is set by comparing the driver's actions of the work vehicle with a predetermined safe driving behavior pattern. The information processing program according to claim 12.

Images