US 12,393,880 B1
Iterative attention-based neural network training and processing
Steven Dennis Flinn, Sugar Land, TX (US); and Naomi Felina Moneypenny, Bellevue, WA (US)
Assigned to Steven D. Flinn, Sugar Land, TX (US)
Filed by Steven D Flinn, Sugar Land, TX (US)
Filed on Dec. 6, 2024, as Appl. No. 18/972,763.
Application 18/972,763 is a division of application No. 18/810,464, filed on Aug. 20, 2024, granted, now 12,293,270.
Application 18/810,464 is a continuation of application No. 18/101,612, filed on Jan. 26, 2023, granted, now 12,223,404.
Application 18/101,612 is a continuation of application No. 16/660,908, filed on Oct. 23, 2019, granted, now 11,593,708, issued on Feb. 8, 2023.
Application 16/660,908 is a continuation of application No. 15/000,011, filed on Jan. 18, 2016, granted, now 10,510,018, issued on Dec. 17, 2019.
Application 15/000,011 is a continuation in part of application No. 14/816,439, filed on Aug. 3, 2015, abandoned.
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01); G06F 40/211 (2020.01); G06F 40/216 (2020.01); G06F 40/30 (2020.01); G06N 3/02 (2006.01); G06N 3/045 (2023.01); G06N 5/048 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 40/211 (2020.01); G06F 40/216 (2020.01); G06F 40/30 (2020.01); G06N 3/045 (2023.01); G06N 5/048 (2013.01); G06N 3/02 (2013.01)] 100 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
at a system including one or more processors and one or more memories in communication with the one or more processors and with instructions stored therein:
causing generation of a plurality of preference vector representations based on a plurality of usage behaviors represented by a plurality of behavior syntactical elements, utilizing a computer-implemented trained neural network and by prioritization of a first plurality of attentions of the system that correspond to representations of different subsets of the plurality of behavior syntactical elements, the computer-implemented trained neural network being trained utilizing hardware that processes a plurality of training syntactical elements by prioritization of a training plurality of attentions that correspond to representations of different subsets of the plurality of training syntactical elements;
causing identification, based on the plurality of preference vector representations, of one or more vector representations that represent a user's preference of a user;
causing access to a plurality of content vector representations that each represent at least one of a plurality of distinct items of content including one or more syntactical elements, and that is generated utilizing the computer-implemented trained neural network;
causing comparison of the one or more vector representations that represent the user's preference with the plurality of content vector representations;
causing selection of one or more of the plurality of content vector representations based on the comparison; and
causing a communication, to be sent to the user, based on one or more of the plurality of distinct items of content that correspond to the selected one or more of the plurality of content vector representations.