US 12,147,991 B2
Machine learning-driven servicing interface
Koon Heng Ivan Teo, San Francisco, CA (US); Volodymyr Orlov, San Jose, CA (US); Yazdan Shirvany, Great Falls, VA (US); Fernando San Martin Jorquera, Los Altos, CA (US); Francisco Perez Leon, Richmond, CA (US); Yoonseong Kim, Berkeley, CA (US); and Mohammad Shami, Foster City, CA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jun. 21, 2023, as Appl. No. 18/212,650.
Application 18/212,650 is a continuation of application No. 16/141,521, filed on Sep. 25, 2018, granted, now 11,715,111.
Prior Publication US 2023/0334506 A1, Oct. 19, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/00 (2023.01); G06N 20/00 (2019.01); G06Q 30/016 (2023.01); G06Q 30/02 (2023.01); H04L 67/306 (2022.01); H04M 3/51 (2006.01)
CPC G06Q 30/016 (2013.01) [G06N 20/00 (2019.01); G06Q 30/0281 (2013.01); H04L 67/306 (2013.01); H04M 3/5183 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
identifying a trained machine learning model associated with a user interacting with a business application;
using the trained machine learning model to determine a probability that the user will engage in a specific activity while interacting with the business application;
retrieving a business value factor for the specific activity;
calculating a user intent score for a user intent regarding a user interaction with the business application, the user intent score including a combination of the probability that the user will engage in the specific activity while interacting with the business application and the business value factor; and
reprogramming the business application, based on the user intent score, to provide an update to information for the business application to present to the user.