Methods and systems for automatically recognizing actions in a call center environment using video data

A system for recognizing processes performed by a call center agent during a session may receive input data from a screen recording system that includes a video signal representing a plurality of frames from a time-series video recording or video stream of a desktop of a user electronic device. The...

Full description

Saved in:
Bibliographic Details
Main Authors Yao, Jinhui, Kulkarni, Rakesh S, Gross, Eric Michael, Wu, Wencheng, Mongeon, Michael C
Format Patent
LanguageEnglish
Published 31.07.2018
Subjects
ACOUSTICS
CALCULATING
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
HANDLING RECORD CARRIERS
MUSICAL INSTRUMENTS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
TELEPHONIC COMMUNICATION
Online AccessGet full text

Cover

More Information
Summary:A system for recognizing processes performed by a call center agent during a session may receive input data from a screen recording system that includes a video signal representing a plurality of frames from a time-series video recording or video stream of a desktop of a user electronic device. The system processes the video signal to identify one or more frames of interest from the plurality of frames. Each frame of interest includes a change in a layout of the corresponding one or more screens as compared to a preceding frame in the time-series video recording. The system automatically identifies actions performed by the call center agent that represent an interaction that the call center agent had with one or more screens corresponding to the frame of interest. The system generates an event log that includes a timeline depicting a visual representation of the identified actions.
Bibliography:Application Number: US201715479660