US 11,670,153 B2
Sensing peripheral heuristic evidence, reinforcement, and engagement system
Aaron Williams, Congerville, IL (US); Joseph Robert Brannan, Bloomington, IL (US); Christopher N. Kawakita, Normal, IL (US); and Dana C. Hunt, Normal, IL (US)
Assigned to STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed by STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed on Jul. 26, 2022, as Appl. No. 17/874,010.
Application 17/874,010 is a continuation of application No. 17/574,874, filed on Jan. 13, 2022, granted, now 11,462,094.
Application 17/574,874 is a continuation of application No. 17/077,785, filed on Oct. 22, 2020, granted, now 11,423,758.
Application 17/077,785 is a continuation of application No. 16/169,544, filed on Oct. 24, 2018, granted, now 10,825,318.
Claims priority of provisional application 62/658,682, filed on Apr. 17, 2018.
Claims priority of provisional application 62/654,975, filed on Apr. 9, 2018.
Prior Publication US 2022/0358825 A1, Nov. 10, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G08B 21/04 (2006.01); G16H 80/00 (2018.01); G06N 20/00 (2019.01)
CPC G08B 21/0484 (2013.01) [G06N 20/00 (2019.01); G08B 21/0423 (2013.01); G08B 21/0469 (2013.01); G08B 21/0476 (2013.01); G16H 80/00 (2018.01)] 23 Claims
OG exemplary drawing
 
1. A computer-implemented method for training a machine learning module to identify abnormalities or anomalies corresponding to historically identified conditions associated with one or more individuals in a home environment, comprising:
receiving, by a processor, historical sensor data detected by one or more sensors associated with the home environment;
identifying, by the processor, one or more abnormalities or anomalies in the historical sensor data;
receiving, by the processor, historical condition data indicating historically identified conditions associated with one or more individuals in the home environment, wherein the historically identified conditions include one or more of: a medical condition, a health condition, a cognitive condition, a forgetfulness condition, an insomnia condition, a fatigue condition, a hygiene condition, an emergency condition, or an urgent condition;
analyzing, by the processor, using the machine learning module, the one or more abnormalities or anomalies in the historical sensor data and the historical condition data; and
identifying, by the processor, using the machine learning module, based upon the analysis, the one or more abnormalities or anomalies in the historical sensor data corresponding to one or more of the historically identified conditions associated with the one or more individuals in the home environment.