Granted Patent B2

US 12,657,633 · App. 17/954,015 · Granted Jun 16, 2026

Inventors: Joshua M. Mast (Bloomington, IL); Douglas L. Dewey (Bloomington, IL); Todd Binion (Bloomington, IL); Jeffrey Feid (Normal, IL)

Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

G06Q40/08G01W1/14

Abstract

Claims (51)

1 . A system for performing an insurance property loss mitigation process based on an event driven probable roof loss confidence score based on a particular weather event, wherein the event driven probable roof loss confidence score is associated with a roof of a building, the system comprising:

one or more processors;

a non-transitory computer-readable medium; and

instructions stored on the non-transitory computer-readable medium that, when executed by the one or more processors, cause the one or more processors to:

receive, by executing a base-line probable roof loss confidence score data receiving module, a base-line probable roof loss confidence score for the building, wherein the base-line probable roof loss confidence score is at least partially based on historical weather data representative of storm attributes associated with historical storms that have occurred in a geographic area that includes a geographic location of the building;

receive, by executing a weather data receiving module, weather data, wherein the weather data is representative of storm attributes associated with a storm, associated with the particular weather event, that occurred in the geographic area;

receive, by executing a roof data receiving module, audio data and roof data of the building collected by a smart home device in real-time;

detect from the audio data, by executing a roof data storage module, an audio signature of hail;

responsive to detecting the audio signature of hail, analyze, by executing the roof data storage module, the audio data in order to estimate at least one attribute of the hail based on the audio signature of the hail, wherein the at least one attribute of the hail includes at least one of an elevation of the building exposed to hail, a density of the hail, and a hardness of the hail;

generate, by executing a probable roof loss confidence score data generation module, the event driven probable roof loss confidence score based on the base-line probable roof loss confidence score, the weather data, the at least one estimated attribute of the hail the roof data, by implementing a probability function, wherein a first contribution of a first term of the probability function is weighted via a first weighting variable, relative to a second term of the probability function, and wherein the first weighting variable is dynamically determined based on at least one of the weather data or the at least one estimated attribute of the hail; and

determine, by executing an insurance claim data generation module, a level of damage to the roof of the building based on the event driven probable roof loss confidence score.

2 . The system of claim 1 , wherein the event driven probable roof loss confidence score indicates a probability that the roof is a total loss due to the particular weather event, and wherein the instructions further cause the one or more processors to:

in response to determining that the event driven probable roof loss confidence score indicates that the probability is above a predetermined percentage, automatically process an insurance claim for the roof.

3 . The system of claim 2 , wherein automatically processing the insurance claim includes:

causing a payment to be transmitted to a repair vendor for the roof.

4 . The system of claim 1 , wherein the event driven probable roof loss confidence score indicates a probability that the roof is a total loss due to the particular weather event, and wherein the instructions further cause the one or more processors to:

in response to determining that the event driven probable roof loss confidence score indicates that the probability is below a predetermined percentage, generate insurance claim data indicating that an insurance claim for the roof is to be manually verified.

5 . The system of claim 1 , wherein the at least one attribute of the hail further includes at least one of: a physical characteristic of the hail, a size of the hail, a shape of the hail, a resistance to flexing of the hail, and a temporal pattern of the hail.

6 . The system of claim 1 , wherein the storm attributes of the storm include at least one of: a storm meteorological signature, a storm duration, a storm direction, thermal shock, whether the storm is conducive to producing damaging hail, whether the storm is conducive to producing strong winds, key meteorological aspects of the storm, length of time that the storm impacted the roof, a direction from which the storm impacts the building, a roof temperature prior to the storm, a roof temperature after the storm, or a thermal shock to roofing material.

7 . The system of claim 1 , wherein the instructions further cause the one or more processors to:

responsive to detecting the audio signature of hail, transmit, by the one or more processors, a notification of hail to one or more computing devices associated with at least one of a property owner, an insurer, a property inspector, or a repair vendor.

8 . A method for performing an insurance property loss mitigation process based on an event driven probable roof loss confidence score based on a particular weather event, wherein the event driven probable roof loss confidence score is associated with a roof of a building, the method comprising:

receiving, by one or more processors executing a base-line probable roof loss confidence score data receiving module, a base-line probable roof loss confidence score for the building, wherein the base-line probable roof loss confidence score is at least partially based on historical weather data representative of storm attributes associated with historical storms that have occurred in a geographic area that includes a geographic location of the building;

receiving, by the one or more processors executing a weather data receiving module, weather data, wherein the weather data is representative of storm attributes associated with a storm, associated with the particular weather event, that occurred in the geographic area;

receiving by one or more processors executing a roof data receiving module, audio data and roof data of the building collected by a smart home device in real-time;

detecting, by the one or more processors executing a roof data storage module, an audio signature of hail from the audio data;

responsive to detecting the audio signature of hail, analyzing, by the one or more processors executing the roof data storage module, the audio data in order to estimate, by the one or more processors, at least one attribute of the hail based on the audio signature of the hail, wherein at least one attribute of one or more attributes of the hail includes at least one of an elevation of the building exposed to hail, a density of the hail, and a hardness of the hail;

generating, by the one or more processors executing a probable roof loss confidence score data generation module, the event driven probable roof loss confidence score based on the base-line probable roof loss confidence score, the weather data, the at least one estimated attribute of the hail and the roof data, by implementing a probability function, wherein a first contribution of a first term of the probability function is weighted via a first weighting variable, relative to a second term of the probability function, and wherein the first weighting variable is dynamically determined based on at least one of the weather data or the at least one estimated attribute of the hail; and

determining, by the one or more processors executing an insurance claim data generation module, a level of damage to the roof of the building based on the event driven probable roof loss confidence score.

9 . The method of claim 8 , wherein the event driven probable roof loss confidence score indicates a probability that the roof is a total loss due to the particular weather event, and wherein the method further comprises:

in response to determining that the event driven probable roof loss confidence score indicates that the probability is above a predetermined percentage, automatically processing, by the one or more processors, an insurance claim for the roof.

10 . The method of claim 9 , wherein automatically processing the insurance claim includes:

causing a payment to be transmitted to a repair vendor for the roof.

11 . The method of claim 8 , wherein the event driven probable roof loss confidence score indicates a probability that the roof is a total loss due to the particular weather event, and wherein the method further comprises:

in response to determining that the event driven probable roof loss confidence score indicates that the probability is below a predetermined percentage, generating, by the one or more processors, insurance claim data indicating that an insurance claim for the roof is to be manually verified.

12 . The method of claim 8 , wherein the at least one attribute of the hail includes at least one of: a physical characteristic of the hail, a size of the hail, a shape of the hail, a resistance to flexing of the hail, and a temporal pattern of the hail.

13 . A non-transitory computer-readable medium storing instructions for performing an insurance property loss mitigation process based on an event driven probable roof loss confidence score based on a particular weather event, wherein the event driven probable roof loss confidence score is associated with a roof of a building, and wherein the instructions, when executed by one or more processors, cause the one or more processors to:

receive, by executing a base-line probable roof loss confidence score data receiving module, a base-line probable roof loss confidence score for the building, wherein the base-line probable roof loss confidence score is at least partially based on historical weather data representative of storm attributes associated with historical storms that have occurred in a geographic area that includes a geographic location of the building;

receive, by executing a weather data receiving module, weather data, wherein the weather data is representative of storm attributes associated with a storm, associated with the particular weather event, that occurred in the geographic area;

receive, by executing a roof data receiving module, audio data and roof data of the building collected by a smart home device in real-time;

detect from the audio data, by executing a roof data storage module, an audio signature of hail;

responsive to detecting the audio signature of hail, analyze, by executing the roof data storage module, the audio data in order to estimate at least one attribute of the hail based on the audio signature of the hail, wherein the at least one attribute of the hail includes at least one of an elevation of the building exposed to hail, a density of the hail, and a hardness of the hail;

generate, by executing a probable roof loss confidence score data generation module, the event driven probable roof loss confidence score based on the base-line probable roof loss confidence score, the weather data, the at least one estimated attribute of the hail and the roof data, by implementing a probability function, wherein a first contribution of a first term of the probability function is weighted via a first weighting variable, relative to a second term of the probability function, and wherein the first weighting variable is dynamically determined based on at least one of the weather data or the at least one estimated attribute of the hail; and

determine, by executing an insurance claim data generation module, a level of damage to the roof of the building based on the event driven probable roof loss confidence score.

14 . The non-transitory computer-readable medium of claim 13 , wherein the event driven probable roof loss confidence score indicates a probability that the roof is a total loss due to the particular weather event, and wherein the instructions further cause the one or more processors to:

in response to determining that the event driven probable roof loss confidence score indicates that the probability is above a predetermined percentage, automatically process an insurance claim for the roof.

15 . The non-transitory computer-readable medium of claim 14 , wherein automatically processing the insurance claim includes:

causing a payment to be transmitted to a repair vendor for the roof.

16 . The non-transitory computer-readable medium of claim 13 , wherein the event driven probable roof loss confidence score indicates a probability that the roof is a total loss due to the particular weather event, and wherein the instructions further cause the one or more processors to:

in response to determining that the event driven probable roof loss confidence score indicates that the probability is below a predetermined percentage, generate insurance claim data indicating that an insurance claim for the roof is to be manually verified.

17 . The non-transitory computer-readable medium of claim 13 , wherein the at least one attribute of the hail further includes at least one of: a physical characteristic of the hail, a size of the hail, a shape of the hail, a resistance to flexing of the hail, and a temporal pattern of the hail.

Assignments (1)

Continuity (2)

References Cited (307)