IP Library Granted Patent US 12,651,298
Granted Patent B2
US 12,651,298 · App. 18/674,177 · Granted Jun 9, 2026

Systems and methods for obtaining incident information to reduce fraud

Inventors: Kenneth J. Sanchez (San Francisco, CA); Theobolt N. Leung (San Francisco, CA); Holger Struppek (San Francisco, CA); Scott Howard (Emeryville, CA); John Minichiello (Monticello, FL); Vinay Kumar (Fremont, CA)
Assignee: QUANATA, LLC
G06Q40/083G06N20/00G06Q10/00G06Q10/087G06Q40/00G06Q40/08G06V20/10G06Q10/10G06Q40/0841
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,651,298
App. No.
18/674,177
Granted
Jun 9, 2026
Kind
B2
Abstract

Systems and methods for analyzing documentation for assessing potential fraudulent user submissions are provided. According to certain aspects, a server computer may receive an initial set of documentation descriptive of damage to a property asset, and may analyze the initial set of documentation to determine whether additional documentation is needed. The server computer may initiate a communication channel with a user device via which the additional documentation may be submitted, and the server computer may similarly analyze the additional documentation to determine a likelihood of fraud. The server computer may process the user submission accordingly.

Claims (60)

1 . A computer-implemented method of analyzing device-submitted documentation, the method comprising:

receiving, by one or more processors, one or more initial images related to a damaged property;

analyzing, by the one or more processors using a trained machine learning model, the one or more initial images to generate a first result that comprises a determined amount of damage to the damaged property;

determining, by the one or more processors, an initial confidence level in the determined amount of damage based upon the first result;

determining, by the one or more processors using the trained 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, wherein the set of instructions indicates a time limit for capturing the additional set of one or more images;

receiving, by the one or more processors, the additional set of one or more images;

analyzing, by the one or more processors using the trained machine learning model, the additional set of one or more images, to generate a second result that comprises a confidence level, wherein analyzing the additional set of one or more images also includes (i) determining whether the one or more images of the additional set correspond to the set of instructions and (ii) analyzing, using the trained machine learning model, metadata associated with the additional set of one or more images to generate a metadata analysis result; and (iii) determining whether the additional set of one or more images was captured and submitted within the time limit;

determining, by the one or more processors using the trained machine learning model, whether the confidence level exceeds a threshold level; and

notifying the user, by the one or more processors, of an outcome corresponding to whether the confidence level exceeds the threshold level.

2 . The computer-implemented method of claim 1 , further comprising:

outputting, by the one or more processors using the trained machine learning model, an indication of completeness of the one or more initial images; and

determining, by the one or more processors using the trained machine learning model, the confidence level based at least in part upon the indication of completeness.

3 . The computer-implemented method of claim 1 , wherein

the trained machine learning model is trained using a set of training data.

4 . The computer-implemented method of claim 1 , wherein an image capture sensor is configured to capture the additional set of one or more images in accordance with the set of instructions.

5 . The computer-implemented method of claim 1 , further comprising:

determining, by the one or more processors using the trained machine learning model, the confidence level based at least in part on the metadata analysis result generated by analyzing metadata associated with the additional set of one or more images.

6 . The computer-implemented method of claim 1 further comprising:

receiving textual information describing the damaged property.

7 . The computer-implemented method of claim 6 , wherein determining the initial confidence level includes determining the initial confidence level based upon a comparison of the first result and the textual information describing the damaged property.

8 . The computer-implemented method of claim 7 , wherein determining the initial confidence level includes determining the initial confidence level using the trained machine learning model.

9 . A system for analyzing device-submitted documentation, the system comprising:

a memory storing a set of computing instructions including a trained machine learning model; and

a processor coupled to the memory, and configured to:

receive one or more initial images related to a damaged property;

analyze, using the trained machine learning model, the one or more initial images to generate a first result that comprises a determined amount of damage to the damaged property;

determine an initial confidence level in the determined amount of damage based upon the first result;

determine, using the trained 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, transmit to a user, a set of instructions for capturing an additional set of one or more images further depicting the damaged property, wherein the set of instructions indicates a time limit for capturing the additional set of one or more images;

receive the additional set of one or more images;

analyze, using the trained machine learning model, the additional set of one or more images, to generate a second result that comprises a confidence level, wherein analyzing the additional set of one or more images also includes (i) determining whether the one or more images of the additional set correspond to the set of instructions and (ii) analyzing, using the trained machine learning model, metadata associated with the additional set of one or more images to generate a metadata analysis result; and (iii) determining whether the additional set of one or more images was captured and submitted within the time limit;

determine, using the trained machine learning model, whether the confidence level exceeds a threshold level; and

notify the user, of an outcome corresponding to whether the confidence level exceeds the threshold level.

10 . The system of claim 9 , wherein the processor is further configured to:

output, using the trained machine learning model, an indication of completeness of the one or more initial images; and

determine, using the trained machine learning model, the confidence level based at least in part upon the indication of completeness.

11 . The system of claim 9 , wherein the processor is further configured to:

use a set of training data to train the trained machine learning model.

12 . The system of claim 9 , wherein an image capture sensor is configured to capture the additional set of one or more images in accordance with the set of instructions.

13 . The system of claim 9 , wherein the processor is further configured to:

determine, using the trained machine learning model, the confidence level based at least in part on the metadata analysis result generated by analyzing metadata associated with the additional set of one or more images.

14 . The system of claim 9 , wherein the processor is further configured to:

receive textual information describing the damaged property.

15 . The system of claim 14 , wherein the processor is further configured to determine the initial confidence level based upon a comparison of the first result and the textual information describing the damaged property.

16 . The system of claim 15 , wherein the processor is further configured to determine the initial confidence level using the trained machine learning model.

17 . A computer-implemented method of analyzing device-submitted documentation, the method comprising:

receiving, by one or more processors, one or more initial images related to a damaged property;

analyzing, by the one or more processors using a trained machine learning model, the one or more initial images to generate a first result that comprises a determined amount of damage to the damaged property;

determining, by the one or more processors, an initial confidence level in the determined amount of damage based upon the first result;

determining, by the one or more processors using the trained 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, a set of instructions for capturing an additional set of one or more images further depicting the damaged property, wherein the set of instructions indicates a time limit for capturing the additional set of one or more images;

receiving, by the one or more processors, the additional set of one or more images;

analyzing, by the one or more processors using the trained machine learning model, the additional set of one or more images, to generate a second result that comprises a confidence level, wherein analyzing the additional set of one or more images also includes (i) determining whether the one or more images of the additional set correspond to the set of instructions and (ii) analyzing, using the trained machine learning model, metadata associated with the additional set of one or more images to generate a metadata analysis result; and (iii) determining whether the additional set of one or more images was captured and submitted within the time limit;

determining, by the one or more processors using the trained machine learning model, whether the confidence level exceeds a threshold level; and

notifying the user, by the one or more processors, of an outcome corresponding to whether the confidence level exceeds the threshold level.

18 . The computer-implemented method of claim 17 further comprising:

receiving textual information describing the damaged property.

19 . The computer-implemented method of claim 18 , wherein determining the initial confidence level includes determining the initial confidence level based upon a comparison of the first result and the textual information describing the damaged property.

20 . The computer-implemented method of claim 19 , wherein determining the initial confidence level includes determining the initial confidence level using the trained machine learning model.

Assignments (2)
CHANGE OF NAME Recorded Jun 22, 2024
From: BLUEOWL, LLC
To: QUANATA, LLC
Reel/Frame 067808/0380 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 19, 2024
From: SANCHEZ, KENNETH J.; LEUNG, THEOBOLT N.; STRUPPEK, HOLGER; HOWARD, SCOTT; MINICHIELLO, JOHN; KUMAR, VINAY
To: BLUEOWL, LLC
Reel/Frame 067769/0913 →
Continuity (4)
Continuation 18110716 · Feb 16, 2023
Continuation 16540952 · Aug 14, 2019
Provisional Application 62822236 · Mar 22, 2019
Related Publication 20240311759A1 · Sep 19, 2024
References Cited (81)
US 7813944B1 · Luk et al. · 2010 [cited by applicant]
US 8117049B2 · Berkobin et al. · 2012 [cited by applicant]
US 9047778B1 · Cazanas et al. · 2015 [cited by applicant]
US 9151692B2 · Breed · 2015 [cited by applicant]
US 9275417B2 · Binion et al. · 2016 [cited by applicant]
US 9299108B2 · Diana et al. · 2016 [cited by applicant]
US 9311676B2 · Helitzer et al. · 2016 [cited by applicant]
US 9679487B1 · Hayward · 2017 [cited by applicant]
US 9712549B2 · Almurayh · 2017 [cited by applicant]
US 9870448B1 · Myers et al. · 2018 [cited by applicant]
US 9904928B1 · Leise · 2018 [cited by applicant]
US 9984419B1 · Manzella et al. · 2018 [cited by applicant]
US 9984420B1 · Manzella et al. · 2018 [cited by applicant]
US 10026130B1 · Konrardy et al. · 2018 [cited by applicant]
US 10032225B1 · Fox et al. · 2018 [cited by applicant]
US 10055794B1 · Konrardy et al. · 2018 [cited by applicant]
US 10086782B1 · Konrardy et al. · 2018 [cited by applicant]
US 10089693B1 · Konrardy et al. · 2018 [cited by applicant]
US 10102590B1 · Farnsworth et al. · 2018 [cited by applicant]
US 10106083B1 · Fields et al. · 2018 [cited by applicant]
US 10134278B1 · Konrardy et al. · 2018 [cited by applicant]
US 10156848B1 · Konrardy et al. · 2018 [cited by applicant]
US 10157423B1 · Fields et al. · 2018 [cited by applicant]
US 10163327B1 · Potter et al. · 2018 [cited by applicant]
US 10163350B1 · Fields et al. · 2018 [cited by applicant]
US 10166994B1 · Fields et al. · 2019 [cited by applicant]
US 10168703B1 · Konrardy et al. · 2019 [cited by applicant]
US 10181161B1 · Konrardy et al. · 2019 [cited by applicant]
US 10185997B1 · Konrardy et al. · 2019 [cited by applicant]
US 10185998B1 · Konrardy et al. · 2019 [cited by applicant]
US 10185999B1 · Konrardy et al. · 2019 [cited by applicant]
US 10269074B1 · Patel et al. · 2019 [cited by applicant]
US 10354333B1 · Hayward · 2019 [cited by applicant]
US 10410289B1 · Tofte et al. · 2019 [cited by applicant]
US 10534968B1 · Clauss et al. · 2020 [cited by applicant]
US 10832327B1 · Potter et al. · 2020 [cited by applicant]
US 11216888B2 · Perl et al. · 2022 [cited by applicant]
US 11417208B1 · Leung et al. · 2022 [cited by applicant]
US 20030200123A1 · Burge et al. · 2003 [cited by applicant]
US 20040243423A1 · Rix et al. · 2004 [cited by applicant]
US 20080243558A1 · Gupte · 2008 [cited by applicant]
US 20100088123A1 · Mccall et al. · 2010 [cited by applicant]
US 20100145734A1 · Becerra et al. · 2010 [cited by applicant]
US 20120076437A1 · King · 2012 [cited by applicant]
US 20140081675A1 · Ives et al. · 2014 [cited by applicant]
US 20150039397A1 · Fuchs · 2015 [cited by applicant]
US 20150179062A1 · Ralston et al. · 2015 [cited by applicant]
US 20150204684A1 · Rostamian et al. · 2015 [cited by applicant]
US 20150363886A1 · Fernandes et al. · 2015 [cited by applicant]
US 20160001544A1 · Gydesen · 2016 [cited by applicant]
US 20170075740A1 · Breaux et al. · 2017 [cited by applicant]
US 20170089710A1 · Slusar · 2017 [cited by applicant]
US 20170109827A1 · Huang et al. · 2017 [cited by applicant]
US 20170192428A1 · Vogt et al. · 2017 [cited by applicant]
US 20170200367A1 · Mielenz · 2017 [cited by applicant]
US 20170212511A1 · Paiva et al. · 2017 [cited by applicant]
US 20170270615A1 · Fernandes et al. · 2017 [cited by applicant]
US 20170270617A1 · Fernandes et al. · 2017 [cited by applicant]
US 20170293894A1 · Taliwal et al. · 2017 [cited by applicant]
US 20180070290A1 · Breaux et al. · 2018 [cited by applicant]
US 20180070291A1 · Breaux et al. · 2018 [cited by applicant]
US 20180182039A1 · Wang et al. · 2018 [cited by applicant]
US 20180194343A1 · Lorenz · 2018 [cited by applicant]
US 20180307250A1 · Harvey · 2018 [cited by applicant]
US 20190102840A1 · Perl et al. · 2019 [cited by applicant]
US 20210042844A1 · Potter et al. · 2021 [cited by applicant]
US 20210078629A1 · Boss et al. · 2021 [cited by applicant]
CN 103810637 · 2014 [cited by applicant]
WO 2017176304 · 2017 [cited by applicant]
<https://gilsmethod.com/how-to-create-albums-and-upload-pictures-to-facebook-on-your-iphone>. GilsMethod, Oct. 5, 2019. [cited by applicant]
<https://grytics.com/blog/create-album-facebook-groups/>. Grytics. Oct. 15, 2019. [cited by applicant]
<https://www.dummies.com/social-media/facebook/how-to-edit-a-facebook-album/>. Dummies. Oct. 15, 2019. [cited by applicant]
<https://www.socmedsean.com/updated-facebook-tip-organizing-moving-and-editing-your-photos-and-albums/.SocMedSean. Oct. 15, 2019. [cited by applicant]
<https://www.thesocialmediahat.com/blog/how-to-update-your-new-mobile-facebook-profile/>. The Social Media Hat, Oct. 15, 2019. [cited by applicant]
Aleksandrowicz, P., Verification of motor vehicle post accident insurance claims. University of Science and Technology, Institute of Automation and Transport, Machine Maintenance Department, vol. 15, No. 1, 2020, pp. 25… [cited by applicant]
fidelity.com, “Mobile Check Deposit”, Deposit checks on the go. Just snap a photo of a check with your iPhone (Registered), iPad(Registered), or AndroidTM device to make deposits directly into the Fidelity account of yo… [cited by applicant]
Jiangqin Peng, Nanjie Lui, Haitao Zhao and Minglu Yu, “Usage-based insurance system based on carrier-cloud-client,” 2015 10th International Conference on Communication and Networking in China (ChinaCom), 2015 pp. 579-58… [cited by applicant]
leadtools.com, “Credit Card Recognition SOK Technology”, Copyright 2019 LEAD Technologies, Inc, pp. 1-2. Retried from the Internet on Aug. 15, 2019: https://www.leadtools.com/sdk/forms/credit-card. [cited by applicant]
Li et al., An Anti-Fraud System for Car Insurance Claim Based on Visual Evidence, Retrieved from https://arxiv.org/pdf/1804.11207, Apr. 2018, 6 pages. [cited by applicant]
Ruchi Verma and Sathyan Ramakrishna Mani, “Using Analytics for Insurance Fraud Detection”, Digital Transformation, pp. 1-10. [cited by applicant]
truepic.com, “Photo and Video Verification You Can Trust”, 2019 World Economic Forum Tech Pioneer, pp. 1-4. Retired from the Internet on Aug. 15, 2019: https://truepic.com/. [cited by applicant]