US 11,736,744 B2
Classifying segments of media content using closed captioning
Aneesh Vartakavi, Emeryville, CA (US); Lakshika Balasuriya, Walnut Creek, CA (US); and Chin-Ting Ko, Dublin, CA (US)
Assigned to Gracenote, Inc., Emeryville, CA (US)
Filed by Gracenote, Inc., Emeryville, CA (US)
Filed on Jul. 8, 2022, as Appl. No. 17/861,112.
Application 17/861,112 is a continuation of application No. 17/359,433, filed on Jun. 25, 2021, granted, now 11,418,821.
Claims priority of provisional application 63/147,342, filed on Feb. 9, 2021.
Prior Publication US 2022/0345759 A1, Oct. 27, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 21/234 (2011.01); G11B 27/34 (2006.01); G06F 40/20 (2020.01); H04N 21/845 (2011.01); G06V 20/40 (2022.01)
CPC H04N 21/23418 (2013.01) [G06F 40/20 (2020.01); G11B 27/34 (2013.01); H04N 21/8456 (2013.01); G06V 20/41 (2022.01); G06V 20/49 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
retrieving, by a computing system from a text index, closed captioning repetition data for a segment of a sequence of media content;
generating, by the computing system, features using the closed captioning repetition data;
providing, by the computing system, the features as input to a classification model, wherein the classification model is configured to output classification data indicative of a likelihood of the features being characteristic of an advertisement segment;
obtaining, by the computing system, the classification data output by the classification model;
determining, by the computing system, a prediction of whether the segment is an advertisement segment using the classification data; and
storing, by the computing system, the prediction for the segment in a database.