US 11,687,612 B2
Deep learning approach to mitigate the cold-start problem in textual items recommendations
Elik Sror, Hod Hasharon (IL); Oren Sar Shalom, Nes Ziona (IL); and Rami Cohen, Ashkelon (IL)
Assigned to INTUIT INC, Mountain View, CA (US)
Filed by Intuit Inc., Mountain View, CA (US)
Filed on Nov. 19, 2021, as Appl. No. 17/531,530.
Application 17/531,530 is a continuation of application No. 16/699,545, filed on Nov. 29, 2019, granted, now 11,210,358.
Prior Publication US 2022/0075840 A1, Mar. 10, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/957 (2019.01); G06F 17/16 (2006.01); G06N 3/08 (2023.01); G06F 12/06 (2006.01); G06F 12/02 (2006.01); G06F 12/0895 (2016.01)
CPC G06F 16/9574 (2019.01) [G06F 17/16 (2013.01); G06N 3/08 (2013.01); G06F 12/0238 (2013.01); G06F 12/0692 (2013.01); G06F 12/0895 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a request that identifies a requested page;
identifying a content vector of the requested page, the content vector generated based on providing text of the requested page to a neural network text encoder;
selecting, based on the content vector, a link to a cold start page, the cold start page not satisfying a threshold level of interaction data, the selected link ranked above a second link to a warm page that does satisfy the threshold level of the interaction data; and
presenting the requested page with the selected link.