US 12,271,420 B1
Video segments for a video related to a task
Kerwell Liao, San Francisco, CA (US); Nikhil Sharma, Mountain View, CA (US); LaDawn Risenmay Jentzsch, Mountain View, CA (US); and Jennifer Ellen Fernquist Seth, San Francisco, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Jun. 6, 2022, as Appl. No. 17/833,790.
Application 17/833,790 is a continuation of application No. 16/416,882, filed on May 20, 2019, granted, now 11,354,356.
Application 16/416,882 is a continuation of application No. 15/055,000, filed on Feb. 26, 2016, granted, now 10,296,640, issued on May 21, 2019.
Application 15/055,000 is a continuation of application No. 13/927,533, filed on Jun. 26, 2013, granted, now 9,304,648, issued on Apr. 5, 2016.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/783 (2019.01); G06F 3/0481 (2022.01); G06F 16/73 (2019.01); G06F 16/78 (2019.01); G06F 16/70 (2019.01); G06F 16/738 (2019.01); G06F 16/74 (2019.01); G06F 16/93 (2019.01); G06F 16/951 (2019.01); G06F 16/9535 (2019.01)
CPC G06F 16/7837 (2019.01) [G06F 3/0481 (2013.01); G06F 16/73 (2019.01); G06F 16/78 (2019.01); G06F 16/7844 (2019.01); G06F 16/7867 (2019.01); G06F 16/70 (2019.01); G06F 16/738 (2019.01); G06F 16/74 (2019.01); G06F 16/743 (2019.01); G06F 16/783 (2019.01); G06F 16/93 (2019.01); G06F 16/951 (2019.01); G06F 16/9535 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors, the method comprising:
identifying, for a given video, one or more transitional indicators indicative of a transition of the given video;
determining a motion flow based on a gradient flow that is quantitatively grouped to identify the one or more transitional indicators;
segmenting the given video, based on a transcript and the motion flow of the given video, into a plurality of video segments;
determining that a given segment of the plurality of video segments is associated with a key phrase;
associating the given segment with the key phrase;
subsequent to the associating
receiving a query; and
in response to receiving the query:
identifying the given video as being responsive to the query,
selecting a given segment from the plurality of video segments of the identified given video, based on a confidence measure of the given segment satisfying a threshold, and
providing a search result for the query.