Vehicle abnormality detection device and vehicle abnormality detection method
A vehicle abnormality detection device includes a receiver that receives: abnormality information data indicating that an abnormality has been detected from a first vehicle while traveling, first detection data detected from the first vehicle while stationary in a state in which the abnormality has occurred, and second detection data detected from a second vehicle while stationary. The vehicle abnormality detection device further includes a storage unit that stores the abnormality information data, and an abnormality determination unit that determines, using the first detection data and the second detection data, whether the second vehicle has the abnormality that is detected from the first vehicle while traveling. Finally, the vehicle abnormality detection device includes a transmitter that, when it is determined that the second vehicle has the abnormality, transmits the abnormality information data to a notification device that is provided in or related to the second vehicle.
1 . A vehicle abnormality detection device comprising:
a receiver that receives:
abnormality information data indicating that an abnormality has been detected from a first vehicle while traveling;
first detection data detected from the first vehicle while stationary in a state in which the abnormality has occurred;
second detection data detected from a second vehicle while stationary, the second vehicle being different from the first vehicle, and
third detection data detected from the first vehicle while stationary in a normal state in which the abnormality has not occurred;
a storage unit that stores the abnormality information data in association with the first detection data;
an association unit configured to generate training data that associates the first detection data with a faulty part and a cause of the abnormality, where the training data is stored in the storage unit;
a learning model generation unit configured to generate a machine learning model and train the machine learning model using the training data, thereby generating a trained machine learning model;
an abnormality determination unit that determines, using the trained machine learning model, whether the second vehicle has the abnormality that is detected from the first vehicle while traveling, by calculating a precision ratio between the first detection data and the second detection data; and
a transmitter that, when it is determined by the abnormality determination unit that the second vehicle has the abnormality, transmits the abnormality information data to a notification device that is provided in the second vehicle or is related to the second vehicle,
wherein the first detection data comprises a portion of all data detected from the first vehicle while stationary, where the portion diverges from the third detection data by a predetermined value or more.
2 . The vehicle abnormality detection device according to claim 1 , wherein the abnormality determination unit determines there is the abnormality when similarity between the first detection data and the second detection data is equal to or greater than a threshold value.
3 . The vehicle abnormality detection device according to claim 1 , wherein:
the receiver further receives fourth detection data that is detected from the first vehicle while traveling in the state in which the abnormality has occurred, and fifth detection data that is detected from the first vehicle while traveling in the normal state in which the abnormality has not occurred, and
the abnormality determination unit determines whether the second vehicle has the abnormality using a first correlation between the first detection data and the fourth detection data and a second correlation between the third detection data and the fifth detection data.
4 . The vehicle abnormality detection device according to claim 1 , wherein the transmitter transmits traveling condition information indicating a traveling condition in which a fault is expected to occur, to the notification device when the second vehicle is stationary.
5 . The vehicle abnormality detection device according to claim 1 , wherein the transmitter transmits travel restriction information indicating a traveling condition limited by a fault, to the notification device when the second vehicle is stationary.
6 . The vehicle abnormality detection device according to claim 1 , further comprising an abnormality degree calculation unit that calculates an abnormality degree of the second vehicle obtained by quantifying an amount of deviation from a normal state, wherein the transmitter transmits the abnormality degree of the second vehicle to the notification device.
7 . The vehicle abnormality detection device according to claim 1 , further comprising an abnormality degree calculation unit that calculates an abnormality degree obtained by quantifying an amount of deviation from a normal state, wherein the abnormality degree calculation unit:
calculates an abnormality degree of the first vehicle,
stores the abnormality degree of the first vehicle in association with the first detection data in the storage unit,
calculates an abnormality degree of the second vehicle,
calculates a relative value of the abnormality degree of the second vehicle based on the abnormality degree of the first vehicle, and
the transmitter transmits the relative value to the notification device.
8 . A vehicle abnormality detection method comprising:
receiving abnormality information data indicating that an abnormality has been detected from a first vehicle while traveling and first detection data detected from the first vehicle while stationary in a state in which the abnormality has occurred;
receiving second detection data detected from a second vehicle while stationary, the second vehicle being different from the first vehicle;
receiving third detection data detected from the first vehicle while stationary in a normal state in which the abnormality has not occurred;
storing the abnormality information data in association with the first detection data;
generating training data that associates the first detection data with a faulty part and a cause of the abnormality,
storing the training data in a storage unit;
generating a machine learning model and training the machine learning model using the training data, thereby generating a trained machine learning model;
determining, using the trained machine learning model, whether the second vehicle has the abnormality that is detected from the first vehicle while traveling, by calculating a precision ratio between the first detection data and the second detection data; and
when it is determined that the second vehicle has the abnormality based on the precision ratio, transmitting the abnormality information data to a notification device that is provided in the second vehicle or is related to the second vehicle,
wherein the first detection data comprises a portion of all data detected from the first vehicle while stationary, where the portion diverges from the third detection data by a predetermined value or more.