US 12,266,197 B2
Detection of manual entry error
Tyler Maiman, Melville, NY (US); Joshua Edwards, Philadelphia, PA (US); Feng Qiu, Newark, DE (US); Michael Mossoba, Great Falls, VA (US); Alexander Lin, Arlington, VA (US); Meredith L Critzer, Midlothian, VA (US); Guadalupe Bonilla, Hyattsville, MD (US); Vahid Khanagha, Rockville, MD (US); Mia Rodriguez, Broomfield, CO (US); and Aysu Ezen Can, Cary, NC (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Apr. 28, 2022, as Appl. No. 17/731,936.
Prior Publication US 2023/0351780 A1, Nov. 2, 2023
Int. Cl. G06V 30/12 (2022.01); G06F 40/295 (2020.01); G06V 30/19 (2022.01); G10L 15/26 (2006.01)
CPC G06V 30/12 (2022.01) [G06F 40/295 (2020.01); G06V 30/19013 (2022.01); G10L 15/26 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An error detection system, comprising:
a processor coupled to a memory that includes instructions that, when executed by the processor, cause the processor to:
identify, during a live conversation between a first user and a second user, a named entity from the live conversation using a named entity recognition model that employs natural language processing and machine learning to detect at least one spoken word in the live conversation that corresponds to a named entity category;
determine, during the live conversation, whether data entered into a field on a service platform by the first user during the live conversation includes an error by comparing the data entered with the named entity; and
transmit an alert to the first user through the service platform when the comparison indicates a mismatch between the named entity and the data entered.