公开(公告)号：US11461674B2

公开(公告)日：2022-10-04

申请号：US15967680

申请日：2018-05-01

Applicant: Kyndryl, Inc.

Inventor： Michael Bender ,  Rhonda L. Childress ,  Kim A. Eckert ,  Minh Q. Pham

IPC: G06N5/04 ,  G07C5/08 ,  G06N20/00

Abstract: Disclosed embodiments provide techniques for providing vehicular recommendations based on driver habits. Embodiments utilize a variety of input data, including, but not limited to, static vehicular data, dynamic vehicular data, and/or environmental data. In embodiments, empirical rules are used to adjust recommended maintenance schedules based on the input conditions. Additionally, the adjusted recommendations along with unscheduled maintenance data are input to a machine learning system, such as a neural network. The machine learning system is used to further revise the maintenance schedule, estimate end of life of the vehicle, and issue recommendations for when to sell a vehicle and recommendations on attributes of a new vehicle for acquisition.