Information provision device for use in vehicle

摘要

A first driving instability determining unit estimates driving instability based on a difference value between plural traveling state distributions of different time ranges on the basis of the traveling state data. A second driving instability determining unit estimates driving instability by a process different from the process used in the first driving instability determining unit. A learning completion determining unit determines that the learning is completed when a predetermined learning time elapses from the start of collection of the traveling state data, depending on a degree of learning at which the traveling state distribution calculated by a first traveling state distribution calculating unit is matched with the driving characteristic of a driver. An instability selecting unit selects the instability estimated by the first driving instability determining unit when the learning is completed and selects the instability estimated by the second driving instability determining unit when the learning is not completed.

主权项

1. An information provision device for use in a vehicle, comprising:
a processor configured to: acquire first traveling state data including at least one of a driving operation of a driver and a vehicle state; calculate a plurality of traveling state distributions including a traveling state distribution of an immediately- previous time range indicating a current traveling state and a traveling state distribution of a time range different from the immediately-previous time range on the basis of the first traveling state data; estimate first driving instability on the basis of a difference value between the calculated plurality of traveling state distributions; determine, as a result of a learning completion determination, that learning is completed when a predetermined learning time elapses from start of collection of the first traveling state data; detect whether a driving scene is a specific driving scene set in advance for use when the learning is not completed, when it is determined that the learning is not completed on the basis of a result of the learning completion determination; calculate, when it is determined that the learning is not completed on the basis of a result of the learning completion determination and the specific driving scene is detected, a feature amount of the traveling state distribution of the immediately-previous time range which indicates a current traveling state based on the first traveling state data in the detected specific driving scene and estimate second driving instability on the basis of the calculated feature amount; select the first driving instability when the learning is completed and select the second driving instability when the learning is not completed, on the basis of a result of the learning completion determination; and present instability information based on instability selected between the first driving instability and the second driving instability to the driver.