US 11,055,642 B1
Verification of proof of work using computer vision and/or machine learning
Michael Mossoba, Arlington, VA (US); Abdelkader M'Hamed Benkreira, New York, NY (US); and Latika Gulati, Annandale, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jan. 30, 2020, as Appl. No. 16/777,397.
Int. Cl. G06Q 10/06 (2012.01); G06N 20/00 (2019.01)
CPC G06Q 10/0631 (2013.01) [G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a device, image data associated with an environment of an individual,
wherein the image data is received from a wearable device associated with the individual;
identifying, by the device and using a data model, sensitive information in the image data;
filtering, by the device, the image data to obscure the sensitive information by changing a first color of pixels that are part of the sensitive information to a second color;
identifying, by the device, verifiable content by using one or more content recognition techniques to process the filtered image data,
wherein the verifiable content includes:
user data that depicts at least a portion of the individual,
environment data that depicts at least a portion of the environment, and
time data that indicates one or more times at which the image data was captured;
determining, by the device and by processing the verifiable content, a threshold likelihood that the individual is a particular employee or a particular agent of an organization;
determining, by the device and by processing the verifiable content, one or more threshold likelihoods of the environment depicted by the image data being a work environment;
determining, by the device and based on the threshold likelihood and the one or more threshold likelihoods, a number of verifiable hours worked by the individual during a given time period;
identifying, by the device, wages data that specifies a number of hours worked that has been credited to the individual for the given time period;
determining, by the device and based on the number of verifiable hours worked by the individual and the number of hours worked that has been credited to the individual, whether an amount of wages paid to the individual is an incorrect amount of wages; and
performing, by the device, an update to reflect a correct amount of wages based on determining that the amount of wages paid to the individual is the incorrect amount of wages.