US 12,481,896 B2
Utilizing vehicle sensors and machine learning training to target confident responses to user queries
Lisa Seacat DeLuca, Baltimore, MD (US); and Ronald Felice, Summerville, SC (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Nov. 20, 2019, as Appl. No. 16/689,198.
Prior Publication US 2021/0150386 A1, May 20, 2021
Int. Cl. G06F 7/00 (2006.01); G06F 16/2457 (2019.01); G06F 16/248 (2019.01); G06F 16/25 (2019.01); G06F 17/00 (2019.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01)
CPC G06N 5/04 (2013.01) [G06F 16/24575 (2019.01); G06F 16/24578 (2019.01); G06F 16/248 (2019.01); G06F 16/252 (2019.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for a query response system that provides targeted query response results related to a vehicle, comprising:
receiving a query from a user related to the vehicle;
determining a current status of one or more vehicle systems and one or more subsystems via a plurality of sensors associated with the vehicle;
identifying a problem event based on the current status of the one or more vehicle systems and the one or more subsystems;
training a machine learning system on digital twin content for the vehicle, wherein the trained machine learning system for the digital twin content is shared with the query response system;
linking the received query together with the determined current status of the one or more vehicle systems and the one or more subsystems and the problem event; and
providing targeted query response results based on the linking and the trained machine learning system.