Granted Patent B2

US 12,682,401 · App. 18/643,603 · Granted Jul 14, 2026

Inventors: Sharon Gibson (Apache Junction, AZ); Daniel Wilson (Phoenix, AZ); Phillip Michael Wilkowski (Gilbert, AZ); Jason Goldfarb (Bloomington, IL); Arsh Singh (Frisco, TX); Dustin Helland (Morton, IL)

Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

G06Q40/08

Abstract

Claims (68)

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

retrieving, by one or more processors, home data for a first property;

determining, by the one or more processors and using a first trained machine learning evaluation model, one or more weighted home score factors based upon at least the home data, wherein the first trained machine learning evaluation model determines the one or more weighted home score factors by:

identifying at least a portion of the home data as statistically significant,

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

weighting the one or more home score factors based upon the at least the portion of the home data to generate the one or more weighted home score factors;

generating, by the one or more processors and based upon the one or more weighted home score factors, a home score for the first property;

performing, by the one or more processors and responsive to an indication to train the first trained machine learning evaluation model, additional training of the first trained machine learning evaluation model by modifying corresponding weights of the first trained machine learning evaluation model using at least the one or more weighted home score factors;

determining, by the one or more processors and using a second trained machine learning evaluation model, that one or more additional properties are similar to the first property;

retrieving, by the one or more processors, past hazard data associated with a second property of the one or more additional properties; and

generating, by the one or more processors and based upon at least the past hazard data and at least one of the one or more weighted home score factors, a learning module for the first property.

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

receiving, by the one or more processors, an indication that the user completed the learning module for the first property; and

modifying, by the one or more processors and based upon at least the past hazard data, the home score to create a modified home score in response to receiving the indication.

3 . The computer-implemented method of claim 1 , wherein each of the one or more weighted home score factors has an equal weight.

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

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

one or more hazards associated with the past hazard data; and

one or more solutions to the one or more hazards, wherein the one or more solutions would, if implemented at the first property, cause an improvement to the home score for the first property.

6 . The computer-implemented method of claim 5 , wherein the one or more solutions to the one or more hazards are based at least partially upon one or more real-world solutions based upon the past hazard data.

7 . A computing device for evaluating and gamifying 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 home data for a first property;

determine, using a first trained machine learning evaluation model, one or more weighted home score factors based upon at least the home data, wherein the first trained machine learning evaluation model determines the one or more weighted home score factors by:

identifying at least a portion of the home data identified as statistically significant,

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

weighting the one or more home score factors based upon the at least the portion of the home data to generate the one or more weighted home score factors;

generate, based upon the one or more weighted home score factors, a home score for the first property;

perform, responsive to an indication to train the first trained machine learning evaluation model, additional training of the first trained machine learning evaluation model by modifying corresponding weights of the first trained machine learning evaluation model using at least the one or more weighted home score factors;

determine, using a second trained machine learning evaluation model, that one or more additional properties are similar to the first property;

retrieve past hazard data associated with a second property of the one or more additional properties; and

generate, based upon at least the past hazard data and at least one of the one or more weighted home score factors, a learning module for the first 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:

receive an indication that the user completed the learning module for the first property; and

modify, based upon at least the past hazard data, the home score to create a modified home score in response to receiving the indication.

9 . The computing device of claim 7 , wherein each of the one or more weighted home score factors has an equal weight.

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

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

one or more hazards associated with the past hazard data; and

one or more solutions to the one or more hazards, wherein the one or more solutions would, if implemented at the first property, cause an improvement to the home score for the first property.

12 . The computing device of claim 11 , wherein the one or more solutions to the one or more hazards are based at least partially upon one or more real- world solutions based upon the past hazard data.

13 . A tangible, non-transitory computer-readable medium storing instructions for evaluating and gamifying 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 home data for a first property;

determine, using a first trained machine learning evaluation model, one or more weighted home score factors based upon at least the home data, wherein the first trained machine learning evaluation model determines the one or more weighted home score factors by:

identifying at least a portion of the home data identified as statistically significant,

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

weighting the one or more home score factors based upon the at least the portion of the home data to generate the one or more weighted home score factors;

generate, based upon the one or more weighted home score factors, a home score for the first property;

perform, responsive to an indication to train the first trained machine learning evaluation model, additional training of the first trained machine learning evaluation model by modifying corresponding weights of the first trained machine learning evaluation model using at least the one or more weighted home score factors;

determine, using a second trained machine learning evaluation model, that one or more additional properties are similar to the first property;

retrieve past hazard data associated with a second property of the one or more additional properties; and

generate, based upon at least the past hazard data and at least one of the one or more weighted home score factors, a learning module for the first 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:

receive an indication that the user completed the learning module for the first property; and

modify, based upon at least the past hazard data, the home score to create a modified home score in response to receiving the indication.

15 . The tangible, non-transitory computer-readable medium of claim 13 , wherein each of the one or more weighted home score factors has an equal weight.

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

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

one or more hazards associated with the past hazard data; and

one or more solutions to the one or more hazards, wherein the one or more solutions would, if implemented at the first property, cause an improvement to the home score for the first property.

Assignments (1)

Continuity (6)

References Cited (400)