US 11,669,590 B2
Managing predictions for vehicle repair estimates
Joseph Hyland, San Diego, CA (US); Abhijeet Gulati, San Diego, CA (US); Dmitri Soloviev, San Diego, CA (US); Chenlei Zhang, San Diego, CA (US); and Prarit Lamba, San Diego, CA (US)
Assigned to Mitchell International, Inc., San Diego, CA (US)
Filed by Mitchell International, Inc., San Diego, CA (US)
Filed on Jul. 15, 2020, as Appl. No. 16/929,984.
Prior Publication US 2022/0019858 A1, Jan. 20, 2022
Int. Cl. G06N 20/00 (2019.01); G06F 18/21 (2023.01); G06Q 10/20 (2023.01); G06Q 10/10 (2023.01); G06Q 40/08 (2012.01); G06F 18/40 (2023.01); G06Q 10/0875 (2023.01)
CPC G06F 18/2178 (2023.01) [G06F 18/41 (2023.01); G06N 20/00 (2019.01); G06Q 10/10 (2013.01); G06Q 10/20 (2013.01); G06Q 40/08 (2013.01); G06Q 10/0875 (2013.01)] 23 Claims
OG exemplary drawing
 
17. A computer-implemented method comprising:
providing one or more images of a damaged vehicle as input to a machine learning model, wherein the machine learning model has been trained with images of other damaged vehicles and corresponding vehicle operations, wherein each of the vehicle operations represents the repair or replacement of a vehicle component;
receiving output of the machine learning model responsive to the input, wherein the output comprises a plurality of values each corresponding to a respective one of a plurality of the vehicle operations;
determining a confidence metric based on the values;
making a comparison between the confidence metric and a confidence threshold value; and
selecting the one of the plurality of the vehicle operations corresponding to the highest value as a predicted operation based on the comparison.