US 12,265,972 B2
Methods and systems for concierge network
Muhammad Ziauddin Yusuf, London (GB); Alexander MacDonald, London (GB); Sune Westphalen, London (GB); and Dylan Plofker, New York, NY (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Aug. 31, 2022, as Appl. No. 17/823,623.
Application 17/823,623 is a continuation of application No. PCT/GB2021/050596, filed on Mar. 10, 2021.
Claims priority of provisional application 62/987,822, filed on Mar. 10, 2020.
Prior Publication US 2023/0036167 A1, Feb. 2, 2023
Int. Cl. G06Q 30/00 (2023.01); G06Q 30/016 (2023.01); G06Q 30/0203 (2023.01)
CPC G06Q 30/016 (2013.01) [G06Q 30/0203 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for reducing processing resources utilized for applying machine learning, the system comprising:
a server in communication with a plurality of user devices over a network, wherein the server comprises:
memory, and
one or more processors configured to cause the system to:
determine to process a request using a virtual agent that is associated with a training using at least one of a deep neural network, a convolutional neural network (CNN), or recurrent neural network (RNN);
analyze, based on determining to process the request using the virtual agent, dialog states of a dialog with the virtual agent;
redirect, based on analyzing the dialog states of the dialog with the virtual agent and based on a virtual agent data structure, the request to a different virtual agent that has undergone continual re-training that is different from the training of the virtual agent and that is based on changes in an implementation environment;
generate, using a first machine learning algorithm trained model of the different virtual agent and based on redirecting the request to the different virtual agent, one or more proposals based on request data related to a service the request; and
provide editable fields for modifying one or more fields of the one or more proposals via a first graphical user interface, wherein at least one of the one or more fields includes insight data extracted by processing feedback data received from a second graphical user interface.