US 11,695,645 B2
Methods and systems for dynamic re-clustering of nodes in computer networks using machine learning models
Austin Walters, McLean, VA (US); Mark Watson, McLean, VA (US); Galen Rafferty, McLean, VA (US); and Jeremy Goodsitt, McLean, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Sep. 8, 2021, as Appl. No. 17/469,577.
Prior Publication US 2023/0075894 A1, Mar. 9, 2023
Int. Cl. H04L 29/08 (2006.01); H04L 41/16 (2022.01); G06N 20/20 (2019.01); H04L 41/12 (2022.01); H04L 41/22 (2022.01)
CPC H04L 41/16 (2013.01) [G06N 20/20 (2019.01); H04L 41/12 (2013.01); H04L 41/22 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for dynamic re-clustering of nodes in computer networks using machine learning models, the system comprising:
storage circuitry configured to:
store a first cluster subset, wherein each cluster of computing devices in the first cluster subset comprises one or more respective original nodes determined by a first machine learning model that comprises a topic modeling algorithm;
store a second machine learning model, wherein the second machine learning model is trained to determine one or more clusters of computing devices of the first cluster subset that corresponds to one or more user requests; and
control circuitry configured to:
receive a user request;
input the user request into the second machine learning model to determine a second cluster sub set;
retrieve respective node characteristics for each node in each cluster of computing devices of the second cluster subset;
retrieve available substitute nodes;
determine the available substitute nodes corresponding to each cluster of computing devices of the second cluster subset based on a comparison of respective node characteristics of each of the available substitute nodes and the respective node characteristics for each node in each cluster of the second cluster subset;
generate a third cluster subset, wherein the third cluster subset is based on substituting one or more of the available substitute nodes with one or more nodes in one or more clusters of computing devices of the second cluster subset;
receive a filtering criterion;
filter the second cluster subset and the third cluster subset based on the filtering criterion to determine a fourth cluster subset;
input/output circuitry configured to:
generate for display, on a user interface, a list of nodes in a cluster of computing devices of the fourth cluster subset.