Granted Patent B2

US 12,737,775 · App. 19/044,190 · Granted Sep 15, 2026

Inventors: Phillip M. Wilkowski (Gilbert, AZ); Sharon Gibson (Apache Junction, AZ); Steve Kelley (Buckeye, AZ); John Mullins (Santa Monica, CA)

Assignee: State Farm Mutual Automobile Insurance Company

G06Q30/018G06Q30/0234G06Q50/06G06Q50/26

Abstract

Claims (80)

1 . A computer-implemented method for energy optimization and identifying an energy efficiency program for a property, the computer-implemented method performed by one or more processors of a computing system in communication with one or more data sources, the computer-implemented method comprising:

receiving, by the one or more processors, input data associated with the property from one or more sensors, wherein the input data includes attributes, and wherein the attributes include historical energy usage data, real-time energy consumption data, and location-specific attributes of the property;

analyzing, by the one or more processors, the input data to determine a property profile including integrating the input data into a unified framework and normalizing the input data for compatibility across a plurality of data formats;

inputting, by the one or more processors, the property profile and data from the one or more data sources for one or more energy efficiency programs into a machine-learning model;

in response to the inputting, processing, by the one or more processors utilizing the machine-learning model, the input data to (i) classify one or more energy usage patterns of the property, and (ii) predict one or more energy savings inefficiencies for the property;

adjusting, by the one or more processors, one or more weights of the machine-learning model in response to a deviation between a set of predicted savings and a set of actual energy savings;

matching, by the one or more processors utilizing the machine-learning model with the one or more adjusted weights, at least one energy efficiency program from the one or more energy efficiency programs to the property based upon the input data and the predicted one or more energy savings inefficiencies;

generating, by the one or more processors, an energy assessment of the property and a cost analysis based upon the predicted one or more energy savings inefficiencies and the at least one energy efficiency program; and

generating, by the one or more processors, an interactive visualization of the energy assessment and the at least one energy efficiency program in a graphical user interface of a device, wherein the visualization dynamically updates based upon real-time data received from the one or more sensors corresponding to energy usage, and wherein the dynamically updated interactive visualization displays (i) one or more energy consumption patterns over time, (ii) one or more projected impacts of applying one or more selected energy efficiency programs, and (ii) one or more highlighted inefficiencies and trends.

2 . The computer-implemented method of claim 1 , wherein classifying the one or more energy usage patterns of the property further comprises:

analyzing, by the one or more processors utilizing the machine-learning model, historical energy consumption data associated with one or more properties of a similar size, a similar location, or a similar type with the real-time energy consumption data associated with the property; and

classifying, by the one or more processors utilizing the machine-learning model, the one or more energy usage patterns of the property into one or more categories, wherein the one or more categories include a high-efficiency property category indicating one or more optimized energy consumption patterns, a moderate-efficiency property category indicating one or more standard energy consumption patterns with one or more minor inefficiencies, or a low-efficiency property category indicating an excessive energy consumption.

3 . The computer-implemented method of claim 2 , wherein predicting the one or more energy savings inefficiencies further comprises:

determining, by the one or more processors utilizing the machine-learning model, one or more energy consumption patterns as deviating from one or more optimal energy usage patterns; and

identifying, by the one or more processors utilizing the machine-learning model, the one or more energy consumption patterns as energy savings inefficient.

4 . The computer-implemented method of claim 1 , wherein matching the at least one energy efficiency program to the property further comprises:

analyzing, by the one or more processors, one or more eligibility criteria for the one or more energy efficiency programs, wherein the one or more eligibility criteria include location data, property type, or one or more energy usage requirements;

comparing, by the one or more processors, attribute data, the one or more energy usage patterns, or the predicted one or more energy savings inefficiencies associated with the property to the one or more eligibility criteria; and

selecting, by the one or more processors, the at least one energy efficiency program that aligns with the attribute data, the one or more energy usage patterns, or the predicted one or more energy savings inefficiencies associated with the property.

5 . The computer-implemented method of claim 1 , wherein generating the energy assessment of the property further comprises:

simulating, by the one or more processors, an impact of the at least one energy efficiency program based upon the predicted one or more energy savings inefficiencies;

estimating, by the one or more processors, a reduction in one or more of (i) one or more energy inefficiencies, (ii) the energy usage, or (iii) one or more associated costs; and

generating, by the one or more processors, a comparative analysis between a current energy profile of the property and a predicted energy profile of the property after implementing the at least one energy efficiency program.

6 . The computer-implemented method of claim 1 , wherein the cost analysis includes a calculation of expected savings, one or more payback periods, and a return upon investments for implementing one or more upgrades.

7 . The computer-implemented method of claim 1 , wherein the at least one energy efficiency program includes one or more of (i) a financial assistance for upgrading one or more energy-efficient appliances, (ii) a tax credit or deduction for implementing one or more energy-saving improvements, (iii) a subsidy for installation of one or more renewable energy systems, (iv) a discount upon an energy-efficient home insulation, or (v) financing options for purchasing an energy-efficient equipment with one or more reduced interest rates.

8 . The computer-implemented method of claim 1 , further comprising:

determining, by the one or more processors, a completion of one or more actions recommended by the at least one energy efficiency program by a user; and

providing, by the one or more processors, one or more rewards to the user, wherein the one or more rewards includes one or more of (i) one or more loyalty points redeemable for one or more energy-efficient products or one or more services, (ii) one or more discounts upon one or more future energy-efficient upgrades, (iii) a membership program offering one or more personalized energy savings consultations, or (iv) one or more tiered benefits based upon one or more energy savings milestones achieved.

9 . The computer-implemented method of claim 8 , wherein the one or more actions include one or more of (i) purchasing and installing the one or more energy-efficient products, (ii) completing a home energy evaluation, (iii) sharing energy usage data for tracking and analysis, (iv) adhering to timelines specified by the at least one energy efficiency program, (v) participating in educational programs or workshops related to the energy savings offered by the at least one energy efficiency program, (vi) referring other users to the at least one energy efficiency program, or (vii) sharing feedback or reviews upon effectiveness of energy-saving upgrades.

10 . The computer-implemented method of claim 1 , wherein matching the at least one energy efficiency program further comprises:

analyzing, by the one or more processors, local climate patterns and seasonal variations to predict their influence upon the one or more energy usage patterns of the property;

identifying, by the one or more processors, the at least one energy efficiency program that specializes upon energy-saving upgrades during such environmental conditions; and

generating, by the one or more processors, a recommendation of the at least one energy efficiency program to optimize energy efficiency.

11 . The computer-implemented method of claim 1 , further comprising:

determining, by the one or more processors, an environmental benefit of implementing the at least one energy efficiency program, wherein the environmental benefit includes a reduced carbon footprint, a reduced energy wastage, or an alignment with one or more renewable energy utilization goals; and

assigning, by the one or more processors, a score indicating a contribution by the property to an environmental conservation and an energy efficiency.

12 . A computer system for energy optimization and identifying an energy efficiency program for a property, comprising:

one or more processors of a computing system in communication with one or more data sources; and

at least one non-transitory computer readable medium storing instructions which, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving input data associated with the property from one or more sensors, wherein the input data includes attributes, and wherein the attributes include historical energy usage data, real-time energy consumption data, and location-specific attributes of the property;

analyzing the input data to determine a property profile including integrating the input data into a unified framework and normalizing the input data for compatibility across a plurality of data formats;

inputting the property profile and data from the one or more data sources for one or more energy efficiency programs into a machine-learning model;

in response to the inputting, processing, utilizing the machine-learning model, the input data to (i) classify one or more energy usage patterns of the property, and (ii) predict one or more energy savings inefficiencies for the property;

adjusting one or more weights of the machine-learning model in response to a deviation between a set of predicted savings and a set of actual energy savings;

matching, utilizing the machine-learning model with the one or more adjusted weights, at least one energy efficiency program from the one or more energy efficiency programs to the property based upon the input data and the predicted one or more energy savings inefficiencies;

generating an energy assessment of the property and a cost analysis based upon the predicted one or more energy savings inefficiencies and the at least one energy efficiency program; and

generating an interactive visualization of the energy assessment and the at least one energy efficiency program in a graphical user interface of a device, wherein the visualization dynamically updates based upon real-time data received from the one or more sensors corresponding to energy usage, and wherein the dynamically updated interactive visualization displays (i) one or more energy consumption patterns over time, (ii) one or more projected impacts of applying one or more selected energy efficiency programs, and (ii) one or more highlighted inefficiencies and trends.

13 . The system of claim 12 , wherein classifying the one or more energy usage patterns of the property further comprises:

analyzing, utilizing the machine-learning model, historical energy consumption data associated with one or more properties of a similar size, a similar location, or a similar type with the real-time energy consumption data associated with the property; and

classifying, utilizing the machine-learning model, the one or more energy usage patterns of the property into one or more categories, wherein the one or more categories include a high-efficiency property category indicating one or more optimized energy consumption patterns, a moderate-efficiency property category indicating one or more standard energy consumption patterns with one or more minor inefficiencies, or a low-efficiency property category indicating an excessive energy consumption.

14 . The system of claim 13 , wherein predicting the one or more energy savings inefficiencies further comprises:

determining, utilizing the machine-learning model, one or more energy consumption patterns as deviating from one or more optimal energy usage patterns; and

identifying, utilizing the machine-learning model, the one or more energy consumption patterns as energy savings inefficient.

15 . The system of claim 12 , wherein matching the at least one energy efficiency program to the property further comprises:

analyzing one or more eligibility criteria for the one or more energy efficiency programs, wherein the one or more eligibility criteria include location data, property type, or one or more energy usage requirements;

comparing attribute data, the one or more energy usage patterns, or the predicted one or more energy savings inefficiencies associated with the property to the one or more eligibility criteria; and

selecting the at least one energy efficiency program that aligns with the attribute data, the one or more energy usage patterns, or the predicted one or more energy savings inefficiencies associated with the property.

16 . The system of claim 12 , wherein generating the energy assessment of the property further comprises:

simulating an impact of the at least one energy efficiency program based upon the predicted one or more energy savings inefficiencies;

estimating a reduction in one or more of (i) one or more energy inefficiencies, (ii) the energy usage, or (iii) one or more associated costs; and

generating a comparative analysis between a current energy profile of the property and a predicted energy profile of the property after implementing the at least one energy efficiency program.

17 . A non-transitory computer readable medium for energy optimization and identifying an energy efficiency program for a property, the non-transitory computer readable medium storing instructions which, when executed by one or more processors of a computing system in communication with one or more data sources, cause the one or more processors to perform operations comprising:

receiving input data associated with the property from one or more sensors, wherein the input data includes attributes, and wherein the attributes include historical energy usage data, real-time energy consumption data, and location-specific attributes of the property;

analyzing the input data to determine a property profile including integrating the input data into a unified framework and normalizing the input data for compatibility across a plurality of data formats;

inputting the property profile and data from the one or more data sources for one or more energy efficiency programs into a machine-learning model;

in response to the inputting, processing, utilizing the machine-learning model, the input data to (i) classify one or more energy usage patterns of the property, and (ii) predict one or more energy savings inefficiencies for the property;

adjusting one or more weights of the machine-learning model in response to a deviation between a set of predicted savings and a set of actual energy savings;

matching, utilizing the machine-learning model with the one or more adjusted weights, at least one energy efficiency program from the one or more energy efficiency programs to the property based upon the input data and the predicted one or more energy savings inefficiencies;

generating an energy assessment of the property and a cost analysis based upon the predicted one or more energy savings inefficiencies and the at least one energy efficiency program; and

generating an interactive visualization of the energy assessment and the at least one energy efficiency program in a graphical user interface of a device, wherein the visualization dynamically updates based upon real-time data received from the one or more sensors corresponding to energy usage, and wherein the dynamically updated interactive visualization displays (i) one or more energy consumption patterns over time, (ii) one or more projected impacts of applying one or more selected energy efficiency programs, and (ii) one or more highlighted inefficiencies and trends.

18 . The non-transitory computer readable medium of claim 17 , wherein classifying the one or more energy usage patterns of the property further comprises:

analyzing, utilizing the machine-learning model, historical energy consumption data associated with one or more properties of a similar size, a similar location, or a similar type with the real-time energy consumption data associated with the property; and

classifying, utilizing the machine-learning model, the one or more energy usage patterns of the property into one or more categories, wherein the one or more categories include a high-efficiency property category indicating one or more optimized energy consumption patterns, a moderate-efficiency property category indicating one or more standard energy consumption patterns with one or more minor inefficiencies, or a low-efficiency property category indicating an excessive energy consumption.

19 . The non-transitory computer readable medium of claim 18 , wherein predicting the one or more energy savings inefficiencies further comprises:

determining, utilizing the machine-learning model, one or more energy consumption patterns as deviating from one or more optimal energy usage patterns; and

identifying, utilizing the machine-learning model, the one or more energy consumption patterns as energy savings inefficient.

20 . The system of claim 12 , wherein matching the at least one energy efficiency program further comprises:

analyzing local climate patterns and seasonal variations to predict their influence upon the one or more energy usage patterns of the property;

identifying the at least one energy efficiency program that specializes upon energy-saving upgrades during such environmental conditions; and

generating a recommendation of the at least one energy efficiency program to optimize energy efficiency.

Assignments (1)

Continuity (2)

References Cited (60)