US 12,271,284 B2
Unification of disparate cloud resources using machine learning
Leonid Kuperman, Toronto (CA); and Laurent Gil, Miami, FL (US)
Assigned to CAST AI Group, Inc., Miami, FL (US)
Filed by CAST AI Group, Inc., North Miami Beach, FL (US)
Filed on Nov. 28, 2023, as Appl. No. 18/520,692.
Application 18/520,692 is a continuation of application No. 17/321,856, filed on May 17, 2021, granted, now 11,868,227.
Claims priority of provisional application 63/029,104, filed on May 22, 2020.
Prior Publication US 2024/0134770 A1, Apr. 25, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 11/34 (2006.01); G06F 11/30 (2006.01); G06F 11/32 (2006.01); G06N 20/00 (2019.01)
CPC G06F 11/3428 (2013.01) [G06F 11/3006 (2013.01); G06F 11/3075 (2013.01); G06F 11/328 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium comprising instructions encoded thereon that, when executed by at least one processor, cause the at least one processor to:
receive a request from a user to rank cloud service provider (CSP) shapes from different CSPs based on a user-input parameter;
responsive to receiving the request, re-rank from a default ranking the CSP shapes based on the user-input parameter, wherein the CSP shapes are grouped by:
inputting performance benchmark data for each cloud service provider (CSP) shape running on a plurality of CSPs into a model, the plurality of CSPs including two or more distinct CSPs; and
receiving, as output from the model, a determination of, for each CSP shape, a group of a plurality of groups to which the CSP shape belongs; and
provide for display to a user a recommended CSP shape based on the output from the model and based on the user-input parameter, the recommended CSP shape implemented using one of the two or more distinct CSPs.