US 12,354,023 B2
Private artificial intelligence (AI) model of a user for use by an autonomous personal companion
Erik Beran, Redwood, CA (US); Michael Taylor, San Mateo, CA (US); and Masanori Omote, San Mateo, CA (US)
Assigned to Sony Interactive Entertainment Inc., Tokyo (JP)
Filed by Sony Interactive Entertainment Inc., Tokyo (JP)
Filed on Oct. 30, 2023, as Appl. No. 18/497,893.
Application 18/497,893 is a continuation of application No. 15/724,011, filed on Oct. 3, 2017, granted, now 11,803,764.
Claims priority of provisional application 62/566,170, filed on Sep. 29, 2017.
Prior Publication US 2024/0062081 A1, Feb. 22, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 5/025 (2023.01); G05B 23/02 (2006.01); G06F 11/34 (2006.01); G06N 3/008 (2023.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06N 5/02 (2023.01); G06N 20/00 (2019.01); H04L 67/50 (2022.01)
CPC G06N 5/025 (2013.01) [G05B 23/0216 (2013.01); G05B 23/0294 (2013.01); G06F 11/3438 (2013.01); G06N 3/008 (2013.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06N 5/02 (2013.01); G06N 20/00 (2019.01); H04L 67/535 (2022.05)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
building a local artificial intelligence (AI) model that determines a first plurality of learned patterns for predicting behavior of a user based on:
randomly filtered objective data of the user that represents monitored behavior of the user, wherein the objective data of the user is shared among a plurality of users,
subjective data of the user that represents monitored behavior of the user and is confined to the user, and
a randomly filtered plurality of objective data of the plurality of users that represents monitored behavior of the plurality of users, wherein the plurality of objective data is shared among the plurality of users;
capturing private data of the user at an autonomous personal companion, wherein the private data is confined to the autonomous personal companion for internal use;
building a private AI model of the user at the autonomous personal companion based on the first plurality of learned patterns of the local AI model and the private data of the user; and
storing the private AI model at the autonomous personal companion of the user for execution by the autonomous personal companion.