Real property monitoring systems and methods for detecting damage and other conditions

• US 10,497,250 B1
• Filed: 09/20/2018
• Issued: 12/03/2019
• Est. Priority Date: 09/27/2017
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Hayward, Gregory L, Goldfarb, Meghan Sims, Christopulos, Nicholas U., Donahue, Erik
• Primary Examiner(s): Tweel, Jr., John A
• Application Number:
  US16/136,501
• Time in Patent Office: 439 Days
• Field of Search: 340540
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06V 20/00 Scenes; Scene-specific elements control of digital cameras H04N23/60
• CPC Class Codes: G06V 30/194 References adjustable by an adaptive method, e.g. learning
• CPC Class Codes: G06V 30/274 Syntactic or semantic context, e.g. balancing
• CPC Class Codes: G08B 19/00 Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
• CPC Class Codes: G08B 23/00 Alarms responsive to unspecified undesired or abnormal conditions
• CPC Class Codes: G08B 25/016 Personal emergency signalling and security systems emergency non-personal manually actuated alarm activators G08B25/12
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Machine learning systems, methods, and techniques for detecting damage and/or other conditions associated with a building, land, structure, or other real property using a real property monitoring system are disclosed. The property monitoring system is used in conjunction with machine learning techniques to determine and/or predict various conditions associated with the real property, including particular damage thereto, e.g., based upon dynamic characteristic data obtained via on-site sensors, static characteristic data, third-party input descriptive of an event impacting the building, etc. Accordingly, damage and/or loss associated with the building/real property is more quickly and/or accurately ascertained so that suitable mitigation techniques may be applied. In some scenarios, previously undetectable or uncharacterized damage and/or other conditions may be discovered and mitigated.

Claims

1. A real property monitoring system, comprising:

a plurality of sensors fixedly disposed at respective locations at a building, each sensor monitoring a respective dynamic, physical characteristic associated with the building, and at least some of the plurality of sensors being fixedly attached to the building;

a user interface via which the real property monitoring system and end-users of the real property monitoring system communicate;

a data storage entity communicatively connected to the plurality of sensors and storing dynamic characteristic data that is indicative of respective dynamic, physical characteristics detected by the plurality of sensors, the dynamic characteristic data generated based upon signals transmitted by the plurality of sensors;

a network interface via which third-party input is received by the real property monitoring system, the third-party input including digitized information that is descriptive of an event impacting the building;

one or more processors; and

a damage detection module comprising a set of computer-executable instructions stored on one or more memories, wherein the set of computer-executable instructions, when executed by the one or more processors, cause the system to;

train, by utilizing the third-party input and the dynamic characteristic data corresponding to the building, an analytics model that is predictive of one or more conditions associated with the building;

apply the trained-analytics model to at least one of the dynamic characteristic data corresponding to the building or additional characteristic data corresponding to the building to thereby discover at least one of the one or more conditions associated with the building, the at least one of the one or more conditions including particular damage to the building that is associated with the event; and

cause an indication of the particular damage to the building to be transmitted to at least one of a remote computing device or a user interface.

2. The real property monitoring system of claim 1, wherein the dynamic characteristic data is time-series data, and the digitized information descriptive of the event includes one or more timestamps indicative of the occurrence of the event.

3. The real property monitoring system of claim 1, wherein the third-party input includes at least one of digital notes or digital images associated with a file of an insurance claim, the at least one of the digital notes or the digital images generated by an insurance provider corresponding to the insurance claim.

4. The real property monitoring system of claim 3, wherein the at least one of the digital notes or the digital images are generated by at least one of a computing device or system, an adjuster, a call-center representative, an insurance agent, an imaging system, or a drone of the insurance provider.

5. The real property monitoring system of claim 3, wherein a content of the digitized information included in the third-party input is generated by a party that is not associated with the insurance provider and is not an end-user of the real property monitoring system corresponding to the building.

6. The real property monitoring system of claim 1, wherein the third-party input, the dynamic characteristic data corresponding to the building, and data indicative of one or more static characteristics of the building are utilized to train the analytics model.

7. The real property monitoring system of claim 6, wherein the one or more static characteristics of the building include at least one of:

a type of the building;

a material or product used in construction of the building;

or a make, model, and/or year of an appliance inside the building.

8. The real property monitoring system of claim 1, wherein the third-party input, the dynamic characteristic data corresponding to the building, and historical insurance claim data are utilized to train the analytics model.

9. The real property monitoring system of claim 8, wherein the historical insurance claim data includes historical insurance claim data corresponding to one or more other buildings.

10. The real property monitoring system of claim 1, wherein the at least one of the one or more conditions associated with the building further includes a cause of loss corresponding to the particular damage to the building, and an indication of the cause of loss is transmitted to the at least one of the remote computing device or the user interface.

11. A computer-implemented method of detecting damage and other conditions at a building, the method comprising:

monitoring, using a plurality of sensors included in a real property monitoring system, a plurality of dynamic, physical characteristics associated with the building, the plurality of sensors fixedly disposed at respective locations at the building and at least some of the plurality of sensors being fixedly attached to the building;

storing, in a data storage entity included in the real property monitoring system, dynamic characteristic data that is indicative of the plurality of dynamic, physical characteristics associated with the building and monitored by the plurality of sensors, the dynamic characteristic data generated based upon signals transmitted by the plurality of sensors;

obtaining, via a network interface of the real property monitoring system, input whose content is generated by a third-party, the network interface excluded from a set of user interfaces via which end-users of the real property monitoring system communicate with the real-property monitoring system, and the third-party input including digital data that is descriptive of an event impacting the building;

training, by an information processor of the real property monitoring system and by using the third-party input and the dynamic characteristic data of the building, an analytics model that is predictive of one or more conditions associated with the building;

applying, by the information processor, the trained, analytics model to at least one of the dynamic characteristic data corresponding to the building or additional characteristic data corresponding to the building, thereby discovering at least one of the one or more conditions associated with the building, the at least one of the one or more conditions including particular damage to the building that is associated with the event; and

transmitting an indication of the particular damage to the building to at least one of a remote computing device or a user interface.

12. The method of claim 11, wherein obtaining the third-party input descriptive of the event corresponding to the building comprises receiving at least one of digital notes or digital images associated with a file of an insurance claim.

13. The method of claim 12, wherein at least a portion of the at least one of the digital notes or digital images were generated by an insurance provider corresponding to the insurance claim.

14. The method of claim 13, wherein at least another portion of the at least one of the digital notes or digital images were generated by a party other than the insurance provider and other than an end-user of the real property monitoring system.

15. The method of claim 11, wherein training the analytics model by using the third-party input and the dynamic characteristic data of the building comprises training the analytics model by using the third-party input, the dynamic characteristic data of the building, and data indicative of one or more static characteristics of the building.

16. The method of claim 15, wherein the one or more static characteristics of the building include at least one of:

a type of the building, a material or product used to construct the building, or a make, model, and/or year of an appliance inside the building.

17. The method of claim 11, wherein training the analytics model by using third-party input and the dynamic characteristic data of the building comprises training the analytics model by using the third-party input, the dynamic characteristic data of the building, and historical insurance claim data.

18. The method of claim 11, wherein the historical insurance claim data includes at least one of:

data included in respective files of one or more historical insurance claims corresponding to the building or data included in respective files of one or more historical insurance claims corresponding to another building.

19. The method of claim 11, wherein discovering the at least one of the one or more conditions associated with both the building and the event further includes discovering a cause of loss corresponding to the particular damage associated with the building.

20. The method of claim 11, wherein discovering the cause of loss comprises discovering a new cause of loss that is not included in a set of causes of loss utilized by an insurance provider.