US 12,321,404 B2
Privacy preserving recommendation system
Rishav Anand, Mountain View, CA (US); Steven Guy Avery, Santa Clara, CA (US); and Sittichai Jiampojamarn, San Jose, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Appl. No. 18/562,943
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Dec. 8, 2022, PCT No. PCT/US2022/052253
§ 371(c)(1), (2) Date Nov. 21, 2023,
PCT Pub. No. WO2024/123335, PCT Pub. Date Jun. 13, 2024.
Prior Publication US 2025/0077594 A1, Mar. 6, 2025
Int. Cl. G06F 16/00 (2019.01); G06F 16/9535 (2019.01); G06F 16/955 (2019.01); G06F 21/62 (2013.01)
CPC G06F 16/9535 (2019.01) [G06F 16/955 (2019.01); G06F 21/6245 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, from a first user device and during a browsing session of content page at the first user device, (1) a request for a digital component and (2) contextual data representing a context within which the content page is provided for display on the first user device;
generating, based on the contextual data, a signal embedding vector that represents the contextual data as a set of features;
providing, to the first user device, the signal embedding vector and the digital component;
receiving, from the first user device, a content category embedding vector for each of one or more content categories associated with the first user device, wherein the content category vector is generated based on the signal embedding vector;
updating, using the received content category embedding vectors, a respective model for the content categories;
generating, based on an updated model and in response to data for a particular content category received from a second user device, a list of additional content categories; and
transmitting, to the second user device, the list of additional content categories.