US 11,995,610 B2
Systems and methods for obtaining incident information to reduce fraud
Kenneth J. Sanchez, San Francisco, CA (US); Theobolt N. Leung, San Francisco, CA (US); Holger Struppek, San Francisco, CA (US); Scott Howard, Emeryville, CA (US); John Minichiello, Monticello, FL (US); and Vinay Kumar, Fremont, CA (US)
Assigned to BLUEOWL, LLC, San Francisco, CA (US)
Filed by BlueOwl, LLC, San Francisco, CA (US)
Filed on Feb. 16, 2023, as Appl. No. 18/110,716.
Application 18/110,716 is a continuation of application No. 16/540,952, filed on Aug. 14, 2019, granted, now 11,710,097.
Claims priority of provisional application 62/822,236, filed on Mar. 22, 2019.
Prior Publication US 2023/0196287 A1, Jun. 22, 2023
Int. Cl. G06Q 10/10 (2023.01); G06N 20/00 (2019.01); G06Q 40/08 (2012.01); G06V 20/10 (2022.01)
CPC G06Q 10/10 (2013.01) [G06N 20/00 (2019.01); G06Q 40/08 (2013.01); G06V 20/10 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method of analyzing device-submitted documentation, the method comprising:
receiving, by one or more processors, an initial set of documentation associated with a claim filing related to a damaged property, the initial set of documentation including one or more initial images depicting the damaged property;
analyzing, by the one or more processors using a machine learning model, the one or more initial images in a first analysis and determining a depicted amount of damage to the damaged property based upon the first analysis;
determining, by the one or more processors, an initial confidence level in the depicted amount of damage based upon the one or more initial images;
determining, by the one or more processors using the machine learning model, that additional documentation is needed when the initial confidence level does not exceed an initial threshold level;
in response to determining that the additional documentation is needed, transmitting to a user, by the one or more processors, a set of instructions for capturing an additional set of one or more images further depicting the damaged property, the set of instructions identifying one or more locations on the damaged property and a capture time limit;
receiving, by the one or more processors, the additional set of one or more images;
analyzing, by the one or more processors using the machine learning model, the additional set of one or more images in a second analysis, and calculating a confidence level in association with the claim filing based upon the second analysis, wherein the second analysis includes determining whether the one or more images correspond to the one or more locations on the damaged property and the capture time limit;
determining, by the one or more processors using the machine learning model, whether the confidence level in association with the claim filing exceeds a threshold level;
in response to determining that the confidence level in association with the claim filing exceeds the threshold level, notifying the user, by the one or more processors, that the claim filing is approved; and
in response to determining that the confidence level in association with the claim filing does not exceed the threshold level, notifying the user, by the one or more processors, that the claim filing is denied.