Q'ligent Corporation

Victor Zaguskin

Andrey Kochetkov

Sergey Lobanov

Anatoly Shishin

Ted Korte

A method and apparatus for estimating bitrate, buffering events and/or other QoE metrics of video reception, based on CDN logs, are provided. The method and apparatus may rely on an AI model, including a neural network. The neural network may receive a training data set comprised of a plurality of CDN server logs. The CDN server logs may be associated with known QoE metrics collected from a plurality of user devices. Once the neural network is trained, a CDN server log, without associated QoE metrics, may be received as input. With the trained neural network and the CDN server log, buffering events and average bitrate QoE metrics may be estimated for one or more user devices without explicitly receiving QoE metrics from the user device.

Estimating OTT player QoE metrics from CDN logs using AI and machine learning

A method and system may input telemetry into a data structure. The telemetry may comprise a plurality of measurement results or other data collected from remote network nodes. Subscriber use metrics may be determined from the telemetry. From the use metrics and habits of the subscriber, user characteristics may be determined. A likelihood of service cancellation, based on the user characteristics, may be estimated in an embodiment. In another embodiment, a likelihood of receiving an inquiry from the subscriber at a subscriber support center may be estimated. Service enhancements may be proactively provided to the subscriber, based on the telemetry, the subscriber use metrics and the user characteristics in advance of service cancellation or receiving the inquiry. Last mile equipment may provide telemetry. The last mile equipment may include set top boxes, cellular phones, tablets and the like.

Growing community of inventors

Nizhny Novgorod, Russia

Victor Zaguskin