US 11,868,492 B2
Systems and methods for mediating permissions
Mark Watson, Sedona, AZ (US); Jeremy Goodsitt, Champaign, IL (US); Austin Walters, Champaign, IL (US); Anh Truong, Champaign, IL (US); and Vincent Pham, Champaign, IL (US)
Assigned to CAPITAL ONE SERVICES, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jun. 20, 2022, as Appl. No. 17/844,244.
Application 17/844,244 is a continuation of application No. 16/849,723, filed on Apr. 15, 2020, granted, now 11,392,707.
Prior Publication US 2022/0327224 A1, Oct. 13, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 21/60 (2013.01); G06N 20/00 (2019.01); H04L 9/08 (2006.01); G06F 21/51 (2013.01)
CPC G06F 21/604 (2013.01) [G06F 21/51 (2013.01); G06N 20/00 (2019.01); H04L 9/0819 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A permission mediating system, comprising:
a memory;
a processor;
a permissions monitor executed by the processor, wherein the permission monitor is configured to:
identify permissions requests and manual permissions responses communicated between a client device and an application, and
store the permissions requests and the manual permissions responses in a database;
a predictive model stored in the memory, wherein the predictive model is capable of predicting a default permission response; and
a permission mechanism executed by the processor, wherein the permission mechanism is configured to:
select a seed model for training the predictive model based on a location associated with the client device,
train the predictive model using the seed model, the permissions requests, and the manual permissions responses stored in the database, and
provide the default permission response using the predictive model.