US 12,335,584 B2
Method and system for generating smart thumbnails
Shenglong Lyu, Beijing (CN); Jian Hui, Beijing (CN); Lu Zhang, Beijing (CN); Deming Lu, Beijing (CN); and Tao Xiong, Beijing (CN)
Assigned to STAR INDIA PRIVATE LIMITED, Mumbai (IN)
Appl. No. 18/288,344
Filed by Star India Private Limited, Mumbai (IN)
PCT Filed May 11, 2021, PCT No. PCT/CN2021/092947
§ 371(c)(1), (2) Date Oct. 25, 2023,
PCT Pub. No. WO2022/236651, PCT Pub. Date Nov. 17, 2022.
Prior Publication US 2024/0214651 A1, Jun. 27, 2024
Int. Cl. H04N 21/8549 (2011.01); G06T 13/40 (2011.01); G06T 13/80 (2011.01); H04N 21/84 (2011.01); H04N 21/8545 (2011.01)
CPC H04N 21/8549 (2013.01) [G06T 13/40 (2013.01); G06T 13/80 (2013.01); H04N 21/84 (2013.01); H04N 21/8545 (2013.01); G06T 2210/61 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating a smart thumbnail, the method comprising:
receiving a thumbnail and metadata in relation to a content stored in a content store;
analyzing the metadata to identify a key content element of the content;
determining presence of the key content element in the thumbnail;
when the key content element is present in the thumbnail, extracting a portion comprising the key content element from the thumbnail, wherein extraction of the portion comprises, at least in part, extracting one or more features related to the key content element;
causing the one or more features of the key content element to be animated to create an animated content element;
generating one or more textual snippets in relation to the content, the one or more textual snippets generated, at least in part, based on the metadata;
converting a textual snippet selected from among the one or more textual snippets into a speech form to configure an audio version of the textual snippet;
combining the audio version of the textual snippet with the animated content element to create a speaking content element, wherein the speaking content element is configured to provide an impression of the key content element speaking the audio version of the textual snippet; and
embedding the speaking content element in place of the key content element in the thumbnail to generate the smart thumbnail.