US 11,682,093 B2
Document term recognition and analytics
Olalekan Awoyemi, Prosper, TX (US); Jason Hoover, Grapevine, TX (US); Staevan Duckworth, The Colony, TX (US); Geoffrey Dagley, McKinney, TX (US); Stephen Wylie, Carrollton, TX (US); Qiaochu Tang, The Colony, TX (US); and Micah Price, Anna, TX (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Oct. 22, 2021, as Appl. No. 17/451,856.
Application 17/451,856 is a continuation of application No. 16/244,844, filed on Jan. 10, 2019, granted, now 11,157,972.
Prior Publication US 2022/0044289 A1, Feb. 10, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/31 (2019.01); G06Q 50/18 (2012.01); G06N 20/00 (2019.01); G06V 30/413 (2022.01); G06Q 30/0282 (2023.01)
CPC G06Q 50/188 (2013.01) [G06F 16/313 (2019.01); G06N 20/00 (2019.01); G06V 30/413 (2022.01); G06Q 30/0282 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a device, contract data of a contractual document that includes an offer;
receiving, by the device, user data for a consumer associated with the offer;
identifying, by the device, a set of key terms within the contractual document by analyzing the contract data,
wherein the set of key terms includes one or more key terms that are part of the offer;
determining, by the device, a set of term scores that correspond to one or more likelihoods of the one or more key terms being favorable to the consumer as compared to being unfavorable to the consumer;
determining, by the device, one or more unfavorable key terms, from the set of key terms, having unfavorable term scores, from the set of term scores, that are less than a threshold,
wherein the threshold is based on the user data for the consumer;
running, by the device, one or more simulations with one or more proposed modifications of the one or more unfavorable key terms, by modifying a parameter of the one or more unfavorable key terms;
determining, by the device, a revised set of term scores based on running the one or more simulations to determine a recommendation,
wherein the recommendation includes one or more of the one or more proposed modifications to one or more of the one or more unfavorable key terms based on the revised set of term scores; and
providing, by the device, the recommendation to the consumer to be used in determining whether to accept the offer.