US 11,947,577 B2
Auto-completion based on content similarities
Jeffrey Harris, Oakland, CA (US); Lulu Cheng, San Francisco, CA (US); Xixia Wang, Oakland, CA (US); Matthew Chun-Bong Fong, San Francisco, CA (US); Joseph Vito Zingarelli, San Francisco, CA (US); and Long Cheng, San Francisco, CA (US)
Assigned to Pinterest, Inc., San Francisco, CA (US)
Filed by Pinterest, Inc., San Francisco, CA (US)
Filed on Jun. 24, 2021, as Appl. No. 17/356,966.
Application 17/356,966 is a continuation of application No. 16/105,413, filed on Aug. 20, 2018, granted, now 11,048,734.
Prior Publication US 2021/0319050 A1, Oct. 14, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/332 (2019.01); G06F 16/338 (2019.01); G06F 16/35 (2019.01)
CPC G06F 16/3323 (2019.01) [G06F 16/338 (2019.01); G06F 16/355 (2019.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method for providing auto-completion options to input characters, the method comprising:
receiving a plurality of input characters;
identifying a set of content items from a corpus of content items relating to the plurality of input characters;
clustering content items of the set of content items into a plurality of initial clusters, the plurality of initial clusters comprising a number of initial clusters determined according to an amount of space available for presenting auto-completion options;
for each initial cluster, determining a descriptive title for the initial cluster from the content items in the initial cluster; and
providing the descriptive titles of the plurality of initial clusters as auto-completion options for the plurality of input characters.