US 11,676,604 B2
Natural language based electronic communication profile system
Christopher Camenares, Falls Church, VA (US); Joseph Boayue, Reston, VA (US); Lee Adcock, Midlothian, VA (US); Ana Cruz, Arlington, VA (US); and Nahid Farhady Ghalaty, Fairfax, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jun. 8, 2020, as Appl. No. 16/895,923.
Prior Publication US 2021/0383810 A1, Dec. 9, 2021
Int. Cl. G06F 40/20 (2020.01); G10L 15/26 (2006.01); G10L 15/18 (2013.01); G06F 40/289 (2020.01); G06F 21/30 (2013.01); G06F 21/31 (2013.01); G06F 40/253 (2020.01); G10L 17/02 (2013.01)
CPC G10L 15/26 (2013.01) [G06F 40/289 (2020.01); G10L 15/1822 (2013.01); G06F 21/30 (2013.01); G06F 21/316 (2013.01); G06F 40/253 (2020.01); G10L 17/02 (2013.01)] 20 Claims
OG exemplary drawing
 
20. A system comprising:
one or more processors programmed with instructions that, when executed by the one or more processors, cause operations comprising:
receiving, from a database, a plurality of communications in which a user participated;
performing natural language processing on the plurality of communications to obtain communication data associated with the user;
executing a statistical analysis on the communication data to obtain statistical communication data of the user;
generating, using the statistical communication data of the user, a communication profile of the user, the communication profile comprising a data structure storing a user identifier associated with a personalized linguistic syntax of the user and the statistical communication data of the user;
receiving media containing audio purported to be from the user;
performing natural language processing on audio purported to be from the user to obtain analyzed audio;
comparing a syntax of analyzed audio to the personalized linguistic syntax stored within the communication profile of the user to obtain a syntax similarity score;
comparing words used within analyzed audio with the statistical communication data of the user to obtain a word usage similarity score; and
identifying, based on the syntax similarity score and the word usage similarity score, the media as a fake.