US 11,729,071 B1
Selection of SaaS endpoint instances based on local service provider connectivity statistics
Vinay Kumar Kolar, San Jose, CA (US); Jean-Philippe Vasseur, Saint Martin d'Uriage (FR); Grégory Mermoud, Venthône (CH); and Pierre-André Savalle, Rueil-Malmaison (FR)
Assigned to Cisco Technology, Inc., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Mar. 3, 2021, as Appl. No. 17/190,811.
Int. Cl. H04L 41/5009 (2022.01); H04L 67/141 (2022.01); H04L 41/50 (2022.01); H04L 67/10 (2022.01)
CPC H04L 41/5009 (2013.01) [H04L 41/5032 (2013.01); H04L 67/141 (2013.01); H04L 67/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, at a device, application experience metrics for a software-as-a-service application served by a plurality of application endpoints;
generating, by the device and based on the application experience metrics, a predictive model that predicts application experience scores for connections between a service provider network and the plurality of application endpoints;
selecting, by the device, a particular application endpoint for the service provider network, based on an application experience score predicted by the predictive model; and
sending, by the device, an indication of the particular application endpoint selected by the device to the software-as-a-service application, wherein the indication is used to assign a connection between the service provider network and the particular application endpoint.