The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Oct. 20, 2020

Filed:

Mar. 22, 2016
Applicant:

Emc Ip Holding Company Llc, Hopkinton, MA (US);

Inventor:

André de Almeida Maximo, Rio de Janeiro, BR;

Assignee:

EMC IP Holding Company LLC, Hopkinton, MA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 20/00 (2019.01); G06K 9/62 (2006.01); G06F 16/35 (2019.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06K 9/00 (2006.01);
U.S. Cl.
CPC ...
G06N 20/00 (2019.01); G06F 16/35 (2019.01); G06K 9/6269 (2013.01); G06K 2009/00738 (2013.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); Y02P 80/15 (2015.11);
Abstract

Methods and apparatus are provided for classifying and discovering historical and future operational states. An exemplary method comprises obtaining historical Boolean sensor data from sensors for a given time; generating a plurality of signatures over time comprised of the historical Boolean sensor data from the sensors for a corresponding given time; determining a plurality of time intervals having a corresponding interval signature, wherein each time interval is comprised of consecutive time units having a substantially same signature; assigning a predefined state to each time interval based on the interval signatures using a clustering method; obtaining, for each time interval, historical numerical sensor data from the sensors corresponding to measurements of the sensors during the associated time interval; and training a model using the historical numerical sensor data as an input, and the predefined state assigned to each time interval as a target output, to obtain coefficients of the machine learning model.


Find Patent Forward Citations

Loading…