US 11,055,789 B1
Systems and methods for insurance fraud detection
Joshua Alexander Tabak, Los Angeles, CA (US); Adam Michael Wilbert, Los Angeles, CA (US); Mustafa Alammar, Los Angeles, CA (US); Rohit Sanjay Annigeri, Los Angeles, CA (US); and Cambron Neil Carter, Los Angeles, CA (US)
Assigned to Pearl Inc., Beverly Hills, CA (US)
Filed by Pearl Inc., West Hollywood, CA (US)
Filed on Sep. 4, 2020, as Appl. No. 17/13,418.
Claims priority of provisional application 62/962,828, filed on Jan. 17, 2020.
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 40/08 (2012.01); G16H 15/00 (2018.01); G16H 30/20 (2018.01); H04N 21/643 (2011.01); H04L 9/32 (2006.01); G06N 20/00 (2019.01); H04L 29/06 (2006.01); G06K 9/62 (2006.01)
CPC G06Q 40/08 (2013.01) [G06K 9/6215 (2013.01); G16H 15/00 (2018.01); G16H 30/20 (2018.01); H04L 9/3247 (2013.01); H04L 67/40 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer system comprising:
memory; and
a processor in communication with the memory and configured with processor-executable instructions to perform operations comprising:
obtaining, for a first insurance claim, insurance claim information and at least a first radiograph image associated with the first insurance claim, wherein the first radiograph image has been submitted by a healthcare provider to an insurance carrier as supporting evidence of a medical service indicated in the insurance claim information as having been performed by the healthcare provider;
generating a digital signature representing the first radiograph image, wherein the digital signature is generated based at least in part on image data within the first radiograph image, wherein generating the digital signature representing the first radiograph image comprises:
implementing a feature extraction process with respect to the image data within the first radiograph image to extract a plurality of features of the image data, wherein the feature extraction process comprises at least one of: (i) providing the image data within the first radiograph image as input to a convolutional neural network and extracting the plurality of features of the image data from one or more layers of the convolutional neural network, or (ii) applying mathematical transformations to image intensity data within the first radiograph image; and
applying a hashing function to at least a subset of the plurality of features of the image data to generate the digital signature representing the first radiograph image;
comparing the digital signature generated for the first radiograph image to previously generated digital signatures of other images that have been submitted in association with insurance claims other than the first insurance claim, wherein the previously generated digital signatures have been generated using the feature extraction process and the hashing function with respect to image data of the other images;
identifying a match between the digital signature generated for the first radiograph image submitted for the first insurance claim and one or more of the previously generated digital signatures of other images submitted in association with the insurance claims other than the first insurance claim;
determining, based on the match identified between the digital signature and the one or more of the previously generated digital signatures, that the first radiograph image submitted for the first insurance claim is a duplicate of at least one radiograph image previously submitted to the insurance carrier for a different insurance claim other than the first insurance claim;
determining that the first insurance claim is associated with potential fraud based at least in part on the identified match between the digital signature and the one or more of the previously generated digital signatures; and
based at least in part on the determining that the first insurance claim is associated with potential fraud, generating at least one of (a) a recommendation for the insurance carrier to deny the first insurance claim, or (b) user interface data that enables a user to review whether to approve or deny the first insurance claim.