US 12,277,616 B2
Systems and methods for generating a home score for a user
Sharon Gibson, Carlock, IL (US); Nicholas Carmelo Marotta, Scottsdale, AZ (US); Daniel Wilson, Glendale, AZ (US); David Frank, Tempe, AZ (US); Phillip Michael Wilkowski, Phoenix, AZ (US); and Jason Goldfarb, Bloomington, 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 Oct. 24, 2022, as Appl. No. 17/972,261.
Application 17/972,261 is a continuation of application No. 17/816,379, filed on Jul. 29, 2022.
Claims priority of provisional application 63/333,513, filed on Apr. 21, 2022.
Claims priority of provisional application 63/332,956, filed on Apr. 20, 2022.
Prior Publication US 2023/0342868 A1, Oct. 26, 2023
Int. Cl. G06Q 50/16 (2012.01)
CPC G06Q 50/16 (2013.01) 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for evaluating and generating a home score for a property, the computer-implemented method comprising:
retrieving, by one or more processors, training home telematics sensor data captured by one or more sensors associated with one or more properties;
retrieving, by the one or more processors, home data for a property including sensor data captured by one or more sensors associated with the property, the sensor data including identification data for the one or more sensors;
determining, by the one or more processors and based upon the home data for the property, one or more home score factors, wherein the determining includes:
analyzing, using a trained machine learning data evaluation model, the home data for the property to determine home characteristic data for the property, wherein the trained machine learning data evaluation model is trained with the training home telematics sensor data to determine home characteristic data,
analyzing, using the trained machine learning data evaluation model, the home data for the property to determine a likelihood of loss associated with the property,
weighting, using the trained machine learning data evaluation model, the home characteristic data using at least the identification data to generate weighted home characteristic data, and
determining, based upon the weighted home characteristic data for the property and the likelihood of loss associated with the property, the one or more home score factors;
isolating, by the one or more processors, influential home characteristic factors, wherein the influential home characteristic factors are a subset of the weighted home characteristic data with the highest weight;
generating, by the one or more processors and based upon at least the influential home characteristic factors, a home score for the property; and
training, by the one or more processors, the trained machine learning data evaluation model using at least the home characteristic data, the home score, and the sensor data.