US 12,148,053 B2
Systems and methods for regression-based determination of expected energy consumption and efficient energy consumption
Mehdi Maasoumy Haghighi, Redwood City, CA (US); Jeremy Kolter, Pittsburgh, PA (US); and Henrik Ohlsson, San Francisco, CA (US)
Assigned to C3.ai, Inc., Redwood City, CA (US)
Filed by C3.ai, Inc., Redwood City, CA (US)
Filed on Apr. 22, 2021, as Appl. No. 17/237,977.
Application 17/237,977 is a continuation of application No. 16/427,066, filed on May 30, 2019, granted, now 11,010,847.
Application 16/427,066 is a continuation of application No. 14/621,228, filed on Feb. 12, 2015, granted, now 10,346,933, issued on Jul. 9, 2019.
Prior Publication US 2022/0067849 A1, Mar. 3, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 50/06 (2024.01); G06Q 10/06 (2023.01)
CPC G06Q 50/06 (2013.01) [G06Q 10/06 (2013.01); Y02D 10/00 (2018.01)] 16 Claims
OG exemplary drawing
 
1. A computer-implemented method for aiding management of consumption of one or more resources, comprising:
(a) identifying a set of features associated with a plurality of buildings, wherein the set of features comprises, for each building, a building size, heating degree days, cooling degree days, a quantity of occupants, or a combination thereof;
(b) acquiring, for each building or characteristic, measured consumption information and a plurality of feature values, each feature value in the plurality of feature values corresponding to a respective feature in the set of features;
(c) training a regression model based at least on the measured consumption information and the plurality of feature values for each building or characteristic in the plurality of buildings; and
(d) using the regression model to determine at least one expected consumption value for a building of interest other than one of the plurality of buildings, wherein the at least one expected consumption value is a predicted amount of energy that is expected to be used by the building of interest; and
(e) outputting the at least one expected consumption value of the building of interest to a resource management platform operating on a customer device.