US 12,314,272 B2
Online meta-learning for scalable item-to-item relationships
Dimitrios Bermperidis, Seattle, WA (US); Sofia M. Nikolakaki, San Jose, CA (US); Rabi S. Chakraborty, San Jose, CA (US); Rajesh Kumar, Singapore (SG); Chandrasekar Venkataraman, Los Altos, CA (US); Natalia G. Silveira, Campbell, CA (US); and Puja Das, San Francisco, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Sep. 23, 2022, as Appl. No. 17/934,854.
Claims priority of application No. 22386056 (EP), filed on Aug. 12, 2022.
Prior Publication US 2024/0054138 A1, Feb. 15, 2024
Int. Cl. G06F 17/00 (2019.01); G06F 7/00 (2006.01); G06F 8/61 (2018.01); G06F 16/2457 (2019.01)
CPC G06F 16/24578 (2019.01) [G06F 8/61 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
responsive to a request to present a landing page for a seed application within a distribution platform interface, determining a target relationship type of a plurality of target relationship types based on characteristics associated with the seed application;
identifying, based on the seed application and the target relationship type, one or more candidate related applications, wherein the one or more candidate related applications are selected based on an item-to-item relationship between the seed application and the one or more candidate related applications; and
presenting an indication of at least one of the one or more candidate related applications on the landing page for the seed application.