US 11,694,281 B1
Personalized conversational recommendations by assistant systems
Honglei Liu, San Mateo, CA (US); Hao Zhou, Menlo Park, CA (US); Seungwhan Moon, Seattle, WA (US); Bing Liu, Sunnyvale, CA (US); Yulong Qiu, Newark, CA (US); Daniel Chai, Marlboro, NJ (US); Pararth Paresh Shah, Sunnyvale, CA (US); Xiaolei Li, Los Altos, CA (US); Rajen Subba, San Carlos, CA (US); and Hu Xu, Sunnyvale, CA (US)
Assigned to Meta Platforms, Inc., Menlo Park, CA (US)
Filed by Meta Platforms, Inc., Menlo Park, CA (US)
Filed on Jul. 6, 2020, as Appl. No. 16/921,665.
Claims priority of provisional application 62/923,342, filed on Oct. 18, 2019.
Int. Cl. H04L 51/52 (2022.01); H04L 51/18 (2022.01); G06F 16/9032 (2019.01); G06F 40/56 (2020.01); G06F 9/451 (2018.01)
CPC H04L 51/52 (2022.05) [G06F 9/453 (2018.02); G06F 16/90332 (2019.01); G06F 40/56 (2020.01); H04L 51/18 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising, by one or more computing systems:
receiving, from a client system associated with a user during a first dialog session, a first user request associated with a first domain;
generating a first response to the first user request, wherein the first response references one or more entities associated with the first domain;
sending, to the client system, instructions for presenting the first response during the first dialog session;
generating, by a recommendation module grounding on a memory graph of user memory associated with the first user, a first personalized recommendation based on the first user request and the first response, wherein the first personalized recommendation references one or more of the entities of the first response, and wherein the referenced one or more of the entities are associated with the first domain; and
sending, to the client system, instructions for presenting the first personalized recommendation during the first dialog session.