Granted Patent B2

US 12,737,818 · App. 18/643,572 · Granted Sep 15, 2026

Inventors: Sharon Gibson (Apache Junction, AZ); Nicholas Carmelo Marotta (Phoenix, AZ); Daniel Wilson (Phoenix, AZ); David Frank (Tempe, AZ); Phillip Michael Wilkowski (Gilbert, AZ); Jason Goldfarb (Bloomington, IL)

Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

G06Q40/08G06N20/00G06Q50/163

Abstract

Claims (62)

1 . A computer-implemented method for evaluating maintenance for a property by a user, the computer-implemented method comprising:

retrieving, by one or more processors, first home data for a first property including first home score factors and second home data for a second property, wherein a user is associated with the first property;

calculating, by the one or more processors and using a trained machine learning evaluation model, one or more second home score factors based upon the second home data, wherein the trained machine learning evaluation model calculates the one or more second home score factors based upon at least a portion of the second home data identified as statistically significant;

training, by the one or more processors and responsive to an indication to train the trained machine learning evaluation model including a condition that the one or more second home score factors are accurately representative of the second property, the trained machine learning evaluation model using at least (i) the one or more second home score factors, (ii) the first home data, and (iii) the second home data;

detecting, by the one or more processors, that the user is to be associated with the second property;

detecting, by the one or more processors and based upon the first home score factors and the one or more second home score factors, one or more local environmental differences indicative of differences in home score between the first property and the second property; and

generating, by the one or more processors, a learning module for the user for improving or maintaining the one or more second home score factors based upon the one or more local environmental differences indicative of the differences in home score between the first property and the second property.

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

retrieving, by the one or more processors, training telematics sensor data captured by one or more sensors associated with one or more properties or one or more users;

wherein the trained machine learning evaluation model is trained with the training telematics sensor data.

3 . The computer-implemented method of claim 1 , wherein at least some of the second home data is retrieved from one or more smart devices on the property and the second home data includes at least one of: location data, environment data, first responder data, home structure data, or adherence to local construction codes.

4 . The computer-implemented method of claim 1 , wherein the calculating includes:

receiving, by the one or more processors, the second home data as an input at the trained machine learning evaluation model;

calculating, by the one or more processors, the one or more second home score factors based upon the second home data; and

weighting, by the one or more processors, the one or more second home score factors to generate weighted second home score factors.

5 . The computer-implemented method of claim 1 , wherein the learning module includes:

one or more differences between the first property and the second property;

teaching information associating the one or more differences with the one or more local environmental differences; and

one or more recommendations for improving or maintaining the one or more second home score factors based upon the one or more differences between the first property and the second property.

6 . The computer-implemented method of claim 5 , wherein the learning module is a first learning module and the one or more recommendations include completion of a second learning module corresponding to an environment associated with the second property.

7 . A computing device for evaluating maintenance for a property by a user, the computing device comprising:

one or more processors;

a communication unit; and

a non-transitory computer-readable medium coupled to the one or more processors and the communication unit and storing instructions thereon that, when executed by the one or more processors, cause the computing device to:

retrieve first home data for a first property including first home score factors and second home data for a second property, wherein a user is associated with the first property;

calculate, using a trained machine learning evaluation model, one or more second home score factors based upon the second home data, wherein the trained machine learning evaluation model calculates the one or more second home score factors based upon at least a portion of the second home data identified as statistically significant;

train, responsive to an indication to train the trained machine learning evaluation model including a condition that the one or more second home score factors are accurately representative of the property, the trained machine learning evaluation model using at least (i) the one or more second home score factors, (ii) the first home data, and (iii) the second home data;

detect that the user is to be associated with the second property;

detect, based upon the first home score factors and the one or more second home score factors, one or more local environmental differences indicative of differences in home score between the first property and the second property; and

generate a learning module for the user for improving or maintaining the one or more second home score factors based upon the one or more local environmental differences indicative of the differences in home score between the first property and the second property.

8 . The computing device of claim 7 , wherein the non-transitory computer-readable medium further stores instructions thereon that, when executed by the one or more processors, further cause the computing device to:

retrieve training telematics sensor data captured by one or more sensors associated with one or more properties or one or more users;

wherein the trained machine learning evaluation model is trained with the training telematics sensor data.

9 . The computing device of claim 7 , wherein at least some of the second home data is retrieved from one or more smart devices on the property and the second home data includes at least one of: location data, environment data, first responder data, home structure data, or adherence to local construction codes.

10 . The computing device of claim 7 , wherein calculating the one or more second home score factors includes:

receiving the second home data as an input at the trained machine learning evaluation model;

calculating the one or more second home score factors based upon the second home data; and

weighting the one or more second home score factors to generate weighted second home score factors.

11 . The computing device of claim 7 , wherein the learning module includes:

one or more differences between the first property and the second property;

teaching information associating the one or more differences with the one or more local environmental differences; and

one or more recommendations for improving or maintaining the one or more second home score factors based upon the one or more differences between the first property and the second property.

12 . The computing device of claim 11 , wherein the learning module is a first learning module and the one or more recommendations include completion of a second learning module corresponding to an environment associated with the second property.

13 . A tangible, non-transitory computer-readable medium storing instructions for evaluating maintenance for a property by a user that, when executed by one or more processors of a computing device, cause the computing device to:

retrieve first home data for a first property including first home score factors and second home data for a second property, wherein a user is associated with the first property;

calculate, using a trained machine learning evaluation model, one or more second home score factors based upon the second home data, wherein the trained machine learning evaluation model calculates the one or more second home score based upon at least a portion of the second home data identified as statistically significant;

train, responsive to an indication to train the trained machine learning evaluation model including a condition that the one or more second home score factors are accurately representative of the property, the trained machine learning evaluation model using at least (i) the one or more second home score factors, (ii) the first home data, and (iii) the second home data;

detect that the user is to be associated with the second property;

detect, based upon the first home score factors and the one or more second home score factors, one or more local environmental differences indicative of differences in home score between the first property and the second property; and

generate a learning module for the user for improving or maintaining the one or more second home score factors based upon the one or more local environmental differences indicative of the differences in home score between the first property and the second property.

14 . The tangible, non-transitory computer-readable medium of claim 13 , further storing instructions that, when executed by the one or more processors, cause the computing device to:

retrieve training telematics sensor data captured by one or more sensors associated with one or more properties or one or more users;

wherein the trained machine learning evaluation model is trained with the training telematics sensor data.

15 . The tangible, non-transitory computer-readable medium of claim 13 , wherein at least some of the second home data is retrieved from one or more smart devices on the property and the second home data includes at least one of: location data, environment data, first responder data, home structure data, and adherence to local construction codes.

16 . The tangible, non-transitory computer-readable medium of claim 13 , wherein calculating the one or more second home score factors includes:

receiving the second home data as an input at the trained machine learning evaluation model;

calculating the one or more second home score factors based upon the second home data; and

weighting the one or more second home score factors to generate weighted second home score factors.

17 . The tangible, non-transitory computer-readable medium of claim 13 , wherein the learning module includes:

one or more differences between the first property and the second property;

teaching information associating the one or more differences with the one or more local environmental differences; and

one or more recommendations for improving or maintaining the one or more second home score factors based upon the one or more differences between the first property and the second property.

Assignments (1)

Continuity (5)

References Cited (400)