US 12,481,647 B1
Generating temporally-related search term recommendations
Adam Jamison Oliner, San Francisco, CA (US); Hongyang Zhang, Vancouver (CA); Sergey Slepian, Vancouver (CA); Di Lu, Vancouver (CA); XiaoYu Jia, Vancouver (CA); Peter Chongjin Kim, Vancouver (CA); and Manish Sainani, Kirkland, WA (US)
Assigned to Cisco Technology, Inc., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Oct. 18, 2021, as Appl. No. 17/503,625.
Application 17/503,625 is a continuation of application No. 15/420,618, filed on Jan. 31, 2017, granted, now 11,194,794.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/242 (2019.01); G06F 16/2457 (2019.01); G06F 16/2458 (2019.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01)
CPC G06F 16/242 (2019.01) [G06F 16/2457 (2019.01); G06F 16/2477 (2019.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
20. A computing device comprising:
one or more processors; and
a memory coupled with the one or more processors, the memory having instructions stored thereon, wherein the instructions, when executed by the one or more processors, cause the computing device to:
identify temporally related terms that occur in a set of training events, wherein the temporally related terms are identified from the set of training events based on occurrences of the temporally related terms within a predetermined period of time relative to occurrences of candidate terms in the set of training events;
generate a temporal map associated with the set of training events, the temporal map associating the candidate terms with the identified temporally related terms that occur in the set of training events within the predetermined period of time relative to the candidate terms; and
use the temporal map to identify one or more temporally related term recommendations that suggest new search terms for performing a search.