US 12,244,473 B2
Predictive system for optimizing API behaviors
John A Joyce, Nashua, NH (US); Nathan J. Sowatskey, Madrid (ES); and Shridhar Saurin Shah, San Jose, CA (US)
Assigned to CISCO TECHNOLOGY, INC., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Jul. 17, 2023, as Appl. No. 18/353,247.
Prior Publication US 2025/0030616 A1, Jan. 23, 2025
Int. Cl. H04L 41/16 (2022.01); H04L 41/0816 (2022.01); H04L 41/5009 (2022.01); H04L 43/08 (2022.01)
CPC H04L 41/5009 (2013.01) [H04L 41/0816 (2013.01); H04L 41/16 (2013.01); H04L 43/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
collecting properties associated with each of a plurality of paths between at least one device and an Application Programing Interface (API) gateway, wherein the at least one device comprises at least an endpoint device;
monitoring the properties associated with each of the plurality of paths to determine a current level of performance for each of the plurality of paths;
monitoring the at least one device to determine a current load of the at least one device;
analyzing, using machine learning, the current level of performance for each of the plurality of paths and the current load of the at least one device to produce a predictive analytics model for congestion on each of the plurality of paths;
determining, using the predictive analytics model, if a corrective action is needed to maintain an optimal performance of the API gateway, the plurality of paths, and the at least one device based on at least the current level of performance for each of the plurality of paths and the current load of the at least one device; and
performing the corrective action when the predictive analytics model indicates that the corrective action is needed.