US 12,093,863 B2
Machine learning labeling platform for enabling automatic authorization of human work assistance
Matthew Aaron Mifflin, Normal, IL (US)
Assigned to State Farm Mutual Automobile Insurance Company, Bloomington, IL (US)
Filed by State Farm Mutual Automobile Insurance Company, Bloomington, IL (US)
Filed on Aug. 30, 2022, as Appl. No. 17/898,988.
Application 17/898,988 is a continuation of application No. 16/429,960, filed on Jun. 3, 2019, granted, now 11,461,714.
Prior Publication US 2022/0405666 A1, Dec. 22, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/06 (2023.01); G06N 20/00 (2019.01); G06Q 10/0631 (2023.01); G06Q 40/08 (2012.01)
CPC G06Q 10/06313 (2013.01) [G06N 20/00 (2019.01); G06Q 40/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method implemented on a computing device having a processor and a non-transitory computer-readable medium, the method comprising:
receiving, by the processor and from a first electronic device, image data depicting a property;
inputting, by the processor, the image data as an input to a machine learning model;
determining, by the processor, based on the image data, and using the machine learning model, a first estimate of a damage to the property, the first estimate including a confidence level associated with the first estimate;
determining, by the processor, that the confidence level is below a threshold level;
based on determining that the confidence level is below the threshold level, transmitting, by the processor, to a second computing device in communication with the first computing device, and via a network, the image data, and a request executable by the second computing device, the request causing the second computing device to:
generate a damage assessment, the damage assessment including a second estimate of the damage, and an annotation associated with the image data, and
provide the damage assessment to the processor via the network;
updating, by the processor, the machine learning model using the damage assessment;
determining, by the processor, and using the updated machine learning model, a third estimate of the damage; and
transmitting, by the processor, via the network, and to the first electronic device, a work order including the third estimate of the damage.