US 12,299,726 B2
System and method for making content-based recommendations using a user profile likelihood model
Zexi Mao, Millbrae, CA (US)
Assigned to PAYPAL, INC., San Jose, CA (US)
Filed by PayPal, Inc., San Jose, CA (US)
Filed on Oct. 17, 2023, as Appl. No. 18/380,792.
Application 18/380,792 is a continuation of application No. 17/234,533, filed on Apr. 19, 2021, granted, now 11,823,246.
Application 17/234,533 is a continuation of application No. 16/232,907, filed on Dec. 26, 2018, granted, now 10,984,461, issued on Apr. 20, 2021.
Prior Publication US 2024/0193665 A1, Jun. 13, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/06 (2023.01); G06Q 30/0601 (2023.01); G06N 7/01 (2023.01)
CPC G06Q 30/0631 (2013.01) [G06Q 30/0603 (2013.01); G06N 7/01 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a non-transitory memory; and
one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
identifying a user interaction with a user device, the user interaction associated with content presentation on a network in at least a portion of a user interface;
extracting, using a natural language algorithm, first semantic attributes associated with a set of products from a product catalog, the natural language algorithm configured to extract the first semantic attributes in a structured format;
compressing data for user events from a user profile of a user that enables a conversion to second semantic attributes, wherein the user events are associated with time-based indications of user interest in a subset of products of the set of products;
converting the compressed data to the second semantic attributes associated with product interests of the user;
determining, based on the extracted first semantic attributes and the second semantic attributes converted from the user events from the user profile, a probability indicating a relevance of each product from the subset of products of the set of products based in part on a frequency of the user interaction on the network; and
generating a content presentation for one or more products from the subset of products based on the probability.