US 11,706,104 B2
Inferring quality of experience (QoE) based on choice of QoE inference model
Giulio Grassi, Paris (FR); Giovanna Carofiglio, Paris (FR); Michele Papalini, Issy les Moulineaux (FR); Enrico Loparco, Boulogne-Billancourt (FR); and Jacques Olivier Samain, Paris (FR)
Assigned to CISCO TECHNOLOGY, INC., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Jun. 15, 2021, as Appl. No. 17/347,728.
Prior Publication US 2022/0400063 A1, Dec. 15, 2022
Int. Cl. H04L 41/5006 (2022.01); H04L 47/11 (2022.01); G06N 5/04 (2023.01); H04L 43/04 (2022.01); H04L 43/062 (2022.01); H04L 47/2441 (2022.01)
CPC H04L 41/5006 (2013.01) [G06N 5/04 (2013.01); H04L 43/04 (2013.01); H04L 43/062 (2013.01); H04L 47/11 (2013.01); H04L 47/2441 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
identifying a location of a potential bottleneck of network traffic in a network based on network flows of the network traffic that are streamed from a network traffic distribution node in the network to a plurality of client nodes;
based on the location of the potential bottleneck, selecting a first Quality of Experience (QoE) inference model from a plurality of respective QoE inference models that are each trained to infer a respective QoE of the network traffic based on one or more respective network traffic metrics generated by monitoring the network traffic at a respective location in the network;
generating one or more first network traffic metrics of the one or more respective network traffic metrics by monitoring the network traffic at a first respective location; and
providing the one or more first network traffic metrics to the first QoE inference model to infer a first respective QoE.