US 11,748,676 B1
Systems and methods for automated damage estimation
Andre Rene Buentello, San Antonio, TX (US); Jose L. Romero, Jr., San Antonio, TX (US); Garrett Rielly Rapport, San Antonio, TX (US); Gregory Brian Meyer, San Antonio, TX (US); Michael Jay Szentes, San Antonio, TX (US); Mark Anthony Lopez, Helotes, TX (US); and Ashley Raine Philbrick, San Antonio, TX (US)
Assigned to United Services Automobile Association (USAA), San Antonio, TX (US)
Filed by United Services Automobile Association (USAA), San Antonio, TX (US)
Filed on Feb. 13, 2020, as Appl. No. 16/790,309.
Claims priority of provisional application 62/805,778, filed on Feb. 14, 2019.
Int. Cl. G06Q 40/08 (2012.01); G06Q 10/0631 (2023.01); G06N 20/00 (2019.01); G06N 5/04 (2023.01); G06Q 10/0875 (2023.01); G06V 20/50 (2022.01); G06F 3/0484 (2022.01); G06F 3/04815 (2022.01)
CPC G06Q 10/06315 (2013.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06Q 10/0875 (2013.01); G06Q 40/08 (2013.01); G06V 20/50 (2022.01); G06F 3/0484 (2013.01); G06F 3/04815 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A tangible, non-transitory, machine-readable medium, comprising machine-readable instructions, that when executed by one or more processors, cause the one or more processors to:
receive, from a camera system, a pre-event capture of an environment;
generate a three-dimensional (3D) model of the environment based upon the pre-event capture, wherein generating the 3D model comprises identifying control software associated with an Internet of Things (IoT) device and associating a function of the control software with the 3D model to enable operation of the function via virtual interaction with the 3D model;
identify, using machine learning, items in the pre-event capture, wherein the operation of the function of the control software facilitates detection of at least a portion of pre-event information associated with one or more items of the items in the pre-event capture;
generate an inventory list, by accumulating the items and associated pre-event information from the pre-event capture;
apply the inventory list to the 3D model;
present the 3D model with selectable item indicators for each of the items in the inventory list;
upon selection of one of the selectable item indicators associated with an item, present a graphical dialog box with respective pre-event information associated with the item;
receive, from the camera system, a post-event capture of the environment;
identify, using machine learning, items in the post-event capture and receive post-event information associated with each item identified in the post-event capture;
compare the items and the associated pre-event information in the inventory list with the items and the associated post-event information in the post-event capture to determine a portion of the items in the inventory list that are damaged or missing;
generate a comparison report based upon comparing the items in the inventory list with the items in the post-event capture; and
predict a loss estimate based upon the comparison report.