Information processing device, information processing method, server device, vehicle device, and information processing program
An information processing device ( 100 ) includes an acquisition unit ( 131 ) that acquires a fault percentage rule defined according to a situation at a time of occurrence of an accident and indicating a percentage of fault of a party of the accident, a moving image generation unit ( 132 ) that generates a simulated moving image assuming the situation at the time of occurrence of the accident which situation corresponds to the fault percentage rule, and a learning data generation unit ( 133 ) that generates learning data in which a learning moving image in which a component included in the simulated moving image is changed as a parameter is associated with the percentage of fault.
1 . An information processing device comprising: circuitry configured to:
acquire a fault percentage rule defined according to a situation at a time of occurrence of an accident and indicating a percentage of fault of a party of the accident;
generate a simulated moving image assuming the situation at the time of occurrence of the accident which situation corresponds to the fault percentage rule;
generate learning data in which a learning moving image in which a component included in the simulated moving image is changed as a parameter is associated with the percentage of fault;
acquire, as a target moving image, a drive recorder moving image recorded by a vehicle in response to the vehicle sensing the accident occurs;
generate a moving image determination model that determines to which learning moving image the target moving image is similar by using the generated learning data;
input the target moving image into the moving image determination model to obtain a moving image vector corresponding to the target moving image;
determine, to which learning moving image the target moving image is similar by comparing the moving image vector corresponding to the target moving image with moving image vectors of the learning moving images; and
determine to which percentage of fault an accident in the target moving image corresponds by using the percentage of fault associated with the determined learning moving image.
2 . The information processing device according to claim 1 , wherein
the circuitry is further configured to
generate the simulated moving image by using, as the component, at least one of an attribute of the party of the accident, a scene situation of the accident, or an operation condition of the party in the accident as the situation at the time of occurrence of the accident which situation corresponds to the fault percentage rule.
3 . The information processing device according to claim 2 , wherein
the circuitry is further configured to
generate the simulated moving image by using, as the component, at least one of whether the party has been in a vehicle, an age of the party, or a type of the vehicle in which the party has been in as the attribute of the party of the accident.
4 . The information processing device according to claim 2 , wherein
the circuitry is further configured to
generate the simulated moving image by using, as the component, at least one of a size, classification, and visibility of a road at the time of occurrence of the accident, priority of intersecting roads, presence or absence of a traffic light, time of occurrence of the accident, or presence or absence of an obstacle as the scene situation of the accident.
5 . The information processing device according to claim 2 , wherein
the circuitry is further configured to
generate the simulated moving image by using, as the component, at least one of a traveling speed, acceleration, or a moving route of the party as the operation condition of the party in the accident.
6 . The information processing device according to claim 2 , wherein
the circuitry is further configured to
generate the simulated moving image by using at least one of a direction or a distance of a viewpoint of when the situation at the time of occurrence of the accident is looked down as a component.
7 . The information processing device according to claim 1 , wherein
when the vehicle detects an impact, the circuitry is further configured to acquire a moving image recorded by the vehicle before and after the impact as the drive recorder moving image.
8 . The information processing device according to claim 1 , wherein
the circuitry is further configured to
calculate insurance of the accident corresponding to the drive recorder moving image on a basis of insurance contract information of a transmission source of the drive recorder moving image and the determined percentage of fault.
9 . An information processing method performed by a computer, the method comprising:
acquiring a fault percentage rule defined according to a situation at a time of occurrence of an accident and indicating a percentage of fault of a party of the accident;
generating a simulated moving image assuming the situation at the time of occurrence of the accident which situation corresponds to the fault percentage rule;
generating learning data in which a learning moving image in which a component included in the simulated moving image is changed as a parameter is associated with the fault percentage rule;
acquiring, as a target moving image, a drive recorder moving image recorded by a vehicle in response to the vehicle sensing the accident occurs;
generating a moving image determination model that determines to which learning moving image the target moving image is similar by using the generated learning data;
inputting the target moving image into the moving image determination model to obtain a moving image vector corresponding to the target moving image;
determining, to which learning moving image the target moving image is similar by comparing the moving image vector corresponding to the target moving image with moving image vectors of the learning moving images; and
determining to which percentage of fault an accident in the target moving image corresponds by using the percentage of fault associated with the determined learning moving image.
10 . A non-transitory computer-readable medium having embodied thereon a program, which when executed by a computer causes the computer to execute an information processing method, the method comprising:
acquiring a fault percentage rule defined according to a situation at a time of occurrence of an accident and indicating a percentage of fault of a party of the accident;
generating a simulated moving image assuming the situation at the time of occurrence of the accident which situation corresponds to the fault percentage rule;
generating learning data in which a learning moving image in which a component included in the simulated moving image is changed as a parameter is associated with the fault percentage rule;
acquiring, as a target moving image, a drive recorder moving image recorded by a vehicle in response to the vehicle sensing the accident occurs;
generating a moving image determination model that determines to which learning moving image the target moving image is similar by using the generated learning data;
inputting the target moving image into the moving image determination model to obtain a moving image vector corresponding to the target moving image;
determining, to which learning moving image the target moving image is similar by comparing the moving image vector corresponding to the target moving image with moving image vectors of the learning moving images; and
determining to which percentage of fault an accident in the target moving image corresponds by using the percentage of fault associated with the determined learning moving image.