US 12,093,680 B2
Methods and apparatus for automatically labeling data processing events in autonomous driving vehicles via machine learning
Gael Gurvan Colas, San Mateo, CA (US); Mayank Gupta, Mountain View, CA (US); Anurag Ganguli, Saratoga, CA (US); and Timothy P. Daly, Jr., San Jose, CA (US)
Assigned to PlusAI, Inc., Santa Clara, CA (US)
Filed by PlusAI, Inc., Santa Clara, CA (US)
Filed on Jun. 19, 2023, as Appl. No. 18/211,451.
Application 18/211,451 is a continuation of application No. 17/981,014, filed on Nov. 4, 2022, granted, now 11,720,343.
Application 17/981,014 is a continuation of application No. 17/571,424, filed on Jan. 7, 2022, granted, now 11,520,576, issued on Dec. 6, 2022.
Prior Publication US 2023/0350664 A1, Nov. 2, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 8/65 (2018.01); G06N 20/00 (2019.01)
CPC G06F 8/65 (2013.01) [G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
extracting, by a computing system, an attribute associated with an identified event;
based at least in part on the attribute, determining, by the computing system, an unidentified event associated with the attribute;
determining, by the computing system, a false negative label for the unidentified event without human intervention; and
based on the unidentified event and false negative label, updating, by the computing system, a machine learning model configured to identify an event type associated with the identified event and the unidentified event.