CPC H04N 21/2387 (2013.01) [H04N 21/4325 (2013.01)] | 14 Claims |
1. A method comprising:
generating, at a computing device, a content item for output at a first time;
receiving a first input associated with navigating the content item;
receiving a second input to provide feedback associated with the first input;
identifying metadata associated with a plurality of segments of the content item, wherein identifying the metadata comprises:
analyzing a frame of the content item via a trained machine learning model; and
identifying, based on the analyzing, an element in the frame as the metadata;
tagging the identified metadata based on the first input and the second input;
identifying, based on the identified metadata, segments of the plurality of segments having the identified metadata as common metadata;
identifying, based on the first input, the common metadata and the tagged metadata, a subset of the plurality of segments to skip;
skipping a segment of the subset of segments;
generating the content item for output at a second time; and
for each subsequent segment of the subset of segments,
skipping a respective segment of the subset of segments as the content item progresses.
|