Browse Prior Art Database

A method to customize online video to user defined length of time

IP.com Disclosure Number: IPCOM000248283D
Publication Date: 2016-Nov-15
Document File: 3 page(s) / 63K

Publishing Venue

The IP.com Prior Art Database

Abstract

This invention discloses a system and method to extract video frames and corresponding audio which contains key plots from original video and construct into a simplified video with user defined length of time. Plot script is used to extract video segments which contains key plots. Semantic analysis engine parse the plot script sentence by sentence to extract information. The output contains actor, actor words/description, action, event, actor emotion and etc. With this information, image parse engine start to identify actor, actor action, scene and actor emotion with timeline from frames in the video. In the meanwhile, audio process engine starts to extract narratage, actor, actor dialog and actor voice mood with timeline. After that, AI engine starts to match extracted information between plot script and video. key-plot segments in the video are extracted and constructed into a simplified video. Poster processor gets time length parameter from end user then starts to extract, cut off and construct video and audio segment into a customized video with user defined length of time.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 01 of 3

A method to customize online video to user defined length of time

Online video websites provide all kinds of movies and TV plays to the audiences. For each online material, it has fixed length of time. In today's busy life, some people don't have so much time to watch the video from the beginning to the end. In such a situation, people may try skipping some segments manually. Most of time, it will miss some key plots. Besides, the user experience is not good because the segmentboundary is not clear to end users.

Is there a method to provide a simplified video with user defined length of time but keep the story complete?

This invention discloses a system and method to extract video segments and corresponding audio which contains key plots from online video and construct into a simplified video with user defined length of time.

For most of online movies or TV plays, plot script is always available in many websites. Plot script is used to extract video segments which contains key plots. Semantic analysis engineparse the plot script sentence by sentence to extract information from plot script. The output contains actor, actor words/description, action, event, actor emotion and etc. With this information, image parse enginestart to identify actor, actor action, scene and actor emotion with timeline from frames in the video. In the meanwhile, audio process enginestarts to extract narratage, actor, actor dialog and actor voice mood with timeline.

After that, AI engine starts to match extracted information between plot script and video. key-plot segments in the video are extracted and construc...