US 11,704,898 B2
Machine learning system and method for determining or inferring user action and intent based on screen image analysis
Ali Jelveh, San Francisco, CA (US)
Assigned to M37 INC., San Francisco, CA (US)
Filed by M37 Inc., San Francisco, CA (US)
Filed on May 12, 2021, as Appl. No. 17/318,032.
Application 17/318,032 is a continuation of application No. 16/107,639, filed on Aug. 21, 2018, granted, now 11,042,784.
Claims priority of provisional application 62/559,180, filed on Sep. 15, 2017.
Claims priority of provisional application 62/641,486, filed on Mar. 12, 2018.
Prior Publication US 2021/0264219 A1, Aug. 26, 2021
Int. Cl. G06V 10/778 (2022.01); G06K 9/62 (2022.01); G06N 3/084 (2023.01); G06N 20/00 (2019.01); G06F 18/21 (2023.01); G06F 18/40 (2023.01); G06T 13/40 (2011.01); G06N 3/006 (2023.01); G06N 7/01 (2023.01)
CPC G06V 10/7784 (2022.01) [G06F 18/2178 (2023.01); G06F 18/41 (2023.01); G06N 3/084 (2013.01); G06N 20/00 (2019.01); G06N 3/006 (2013.01); G06N 7/01 (2023.01); G06T 13/40 (2013.01); G06V 2201/02 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a processor that executes computer executable components stored in memory, wherein the computer executable components comprise:
an input component that receives graphical image data regarding user interaction with a computing device;
a lifegraph that stores time series data related to the user interaction with the computing device, wherein the lifegraph is an n-dimensional graph that represents a web of people, objects and relationships connected to a user, wherein n is a positive integer;
a model generation component that learns user behavior and builds a model that facilitates providing recommendations to optimize future computing device interaction, wherein the model employs a recursive learning algorithm and wherein the model learns impact of respective images via focus objects that indicate relevant portions of an on-screen display;
an analysis component that employs the model to determine or infer user intent based on image analysis; and
an action component that provisions services to the user as a function of determined or inferred user intent.