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. |