US 12,444,178 B2
Inferring the user experience for voice and video applications using perception models
Mukund Yelahanka Raghuprasad, San Jose, CA (US); Jean-Philippe Vasseur, Saint Martin d'Uriage (FR); and Vinay Kumar Kolar, 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. 20, 2022, as Appl. No. 17/869,015.
Prior Publication US 2024/0029417 A1, Jan. 25, 2024
Int. Cl. G06V 10/776 (2022.01); G06V 10/778 (2022.01)
CPC G06V 10/776 (2022.01) [G06V 10/7784 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining, by a device, perception results generated by one or more perception models that use media data as input that is transmitted between endpoints of an online application via a network, the perception results indicative of human perceptible information contained in the media data as perceived by the one or more perception models;
computing, by the device, performance measures for the one or more perception models, based in part on the perception results and on the media data, the performance measures indicative of a quality of the human perceptible information based on an accuracy of the one or more perception models;
quantifying, by the device and based on the performance measures, quality of experience for the online application; and
causing, by the device, a configuration change to be made with respect to the online application, based on the quality of experience as quantified by the performance measures indicative of the quality of the human perceptible information based on the accuracy of the one or more perception models.