US 12,033,168 B2
Systems and methods using facial recognition for detecting previous visits of a plurality of individuals at a location
Ashwini Kumar, Brambelton, VA (US); and Yazdan Shirvany, Great Falls, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Dec. 19, 2022, as Appl. No. 18/067,949.
Application 18/067,949 is a continuation of application No. 17/350,584, filed on Jun. 17, 2021, granted, now 11,531,997, issued on Dec. 20, 2022.
Application 17/350,584 is a continuation of application No. 16/547,295, filed on Aug. 21, 2019, granted, now 11,042,888, issued on Jun. 22, 2021.
Application 16/547,295 is a continuation of application No. 16/100,114, filed on Aug. 9, 2018, granted, now 10,460,330, issued on Oct. 29, 2019.
Prior Publication US 2023/0120579 A1, Apr. 20, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/02 (2023.01); G06Q 30/0201 (2023.01); G06Q 30/0204 (2023.01); G06V 40/16 (2022.01)
CPC G06Q 30/0201 (2013.01) [G06Q 30/0204 (2013.01); G06Q 30/0281 (2013.01); G06V 40/173 (2022.01)] 14 Claims
OG exemplary drawing
 
1. A system, comprising:
a plurality of client computers associated with an entity; and
wherein the plurality of client computers is at a plurality of locations and is configured to communicate with each other and with a server associated with the entity over a communication network;
a plurality of image sensors configured to image the plurality of locations;
wherein each location of the plurality of locations comprises:
at least one client computer from the plurality of client computers,
at least one local visitor-profile database,
at least one individual from a plurality of individuals, and
at least one image sensor from the plurality of image sensors;
wherein data stored in the at least one local visitor-profile database comprises:
a facial feature data unique to each visitor from a plurality of visitors acquired by any of the plurality of image sensors during a previous visit to any of the plurality of locations, and
a visitor-profile data stored in a visitor-profile acquired during the previous visit for each of the plurality of visitors; and
wherein at least one client computer from the plurality of client computers, located in a first location from the plurality of locations, comprises at least one processor and at least one memory storing the at least one local visitor-profile database;
wherein the at least one processor is configured to execute computer code stored in the at least one memory that causes the at least one processor to:
input image data outputted by at least one image sensor at the first location into a facial recognition module that is configured to detect captured facial feature data of the at least one individual visiting the first location;
determine, based on the captured facial feature data and the facial feature data stored in the at least one local visitor-profile database at the first location for any of the plurality of visitors, that the at least one individual is:
at least one new visitor from the plurality of visitors to any of the plurality of locations, or
at least one previous visitor from the plurality of visitors to any of the plurality of locations;
perform at least one of:
obtain the visitor-profile data from the at least one local visitor-profile database for the at least one previous visitor, or
generate a visitor profile in the at least one local visitor-profile database for the at least one new visitor;
input the image data into an image recognition module that is configured to identify from the image data, at least one individual-specific action performed by the at least one individual at the first location;
transmit, over the communication network, to the server and each of the other client computers from the plurality of client computers at other locations from the plurality of locations
visitor-profile-update data for updating the visitor-profile of the least one individual in the at least one local visitor-profile database stored in each of the other locations from the plurality of locations and in at least one local visitor-profile database stored in the server in response to receiving a synchronization trigger;
wherein the visitor-profile-update data comprises:
the at least one individual-specific action, and
the captured facial feature data for the at least one new visitor; and
display on a display of the at least one client computer at the first location:
the visitor-profile data of the at least one previous visitor and
previously identified merchandise preferences of the at least one previous visitor;
 wherein the previously identified merchandise preferences of the at least one previous visitor is based at least in part on an image-based preference determination generated by the image recognition module by inputting image data from the plurality of image sensors at any of the plurality of locations into the image recognition module;
 wherein the image data to generate the image-based preference determination comprises:
 the at least one previous visitor physically handled a merchandise item at a particular location from the plurality of locations,
 an identification of the merchandise item at the particular location,
 an amount of time the at least one previous visitor visited the particular location, and
 interactions with a customer service representative at the particular location.