US 11,695,645 B2Granted

Methods and systems for dynamic re-clustering of nodes in computer networks using machine learning models

AssigneeCapital One Services, LLC

InventorsAustin Walters, Mark Watson, Galen Rafferty, Jeremy Goodsitt

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods and systems for the dynamically re-clustering of nodes in clusters to provide optimal performance and/or the most efficient use of resources through the use of machine learning models. Specifically, the methods and systems may determine a cluster that optimally performs and/or has the most efficient use of resources based on a first machine learning model. The methods and system may then retrieve available substitute nodes from other domains and/or networks that may lie outside the cluster, but may nonetheless be available to, or accessed by the cluster. The methods and systems may then generate an additional plurality of clusters using one or more of the original nodes of the originally selected clusters and/or one or more of the available substitute nodes.

Claims20

Dependent claims

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.

12 more elements

A method for dynamic re-clustering of nodes in computer networks using machine learning models, the method comprising:

receiving a user request;
inputting the user request into a first machine learning model, wherein the first machine learning model is trained to determine one or more clusters of computing devices of a first cluster subset that corresponds to one or more user requests;
determining a second cluster subset based on an output of the first machine learning model;
retrieve available substitute nodes;
generating 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;
receiving a filtering criterion;
filtering the second cluster subset and the third cluster subset based on the filtering criterion to determine a fourth cluster subset;
and
generating for display, on a user interface, a list of nodes in a cluster of computing devices of the fourth cluster subset.

6 more elements

A non-transitory, computer-readable medium for dynamic re-clustering of nodes in computer networks using machine learning models comprising instructions that when executed by one or more processors cause operations comprising:

receiving a user request;
inputting the user request into a first machine learning model, wherein the first machine learning model is trained to determine one or more clusters of computing devices of a first cluster subset that corresponds to one or more user requests;
determining a second cluster subset based on an output of the first machine learning model;
retrieve available substitute nodes;
generating 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;
receiving a filtering criterion;
filtering the second cluster subset and the third cluster subset based on the filtering criterion to determine a fourth cluster subset;
and
generating for display, on a user interface, a list of nodes in a cluster of computing devices of the fourth cluster subset.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/469,577Filed 8 Sep 2021
Published: US 2023/0075894 A19 Mar 2023
Granted: 4 Jul 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification7 codes

H04L 41/16
Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks: using machine learning…
G06N 20/20
Machine learning: ensemble learning
H04L 41/0893
Configuration management of networks or network elements: assignment of logical groups to network elements
H04L 41/12
Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks: discovery or management…