Sensor based system and method for augmenting insurance claim filing

• US 10,296,979 B2
• Filed: 09/30/2015
• Issued: 05/21/2019
• Est. Priority Date: 09/30/2015
• Status: Active Grant

• Current Assignee: Johnson Controls Tyco IP Holdings LLP (Johnson Controls International plc)
• Original Assignee: Sensormatic Electronics LLC (Johnson Controls International plc)
• Inventors: Trainor, Christine, Vavrasek, David
• Primary Examiner(s): Trotter, Scott S
• Application Number:
  US14/870,404
• Publication Number:
  US 20170091868A1
• Time in Patent Office: 1,329 Days
• Field of Search: None
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

Techniques for detecting physical conditions at a physical premises from collection of sensor information from plural sensors execute one or more unsupervised learning models to continually analyze the collected sensor information to produce operational states of sensor information, produce sequences of state transitions, detect during the continual analysis of sensor data that one or more of the sequences of state transitions is a drift sequence, correlate determined drift state sequence to a stored determined condition at the premises, and generate an alert based on the determined condition. Various uses are described for these techniques.

Claims

1. A computer program product tangibly stored on a computer readable hardware storage device, the computer program product for supporting an insurance claim upon an occurrence of an insured event at a physical premises, the computer program product comprising instructions to cause a processor to:

receive a request to produce the insurance claim for the occurrence of the insured event at the physical premises, the insured event associated with one or more building devices that are insured by an insurance carrier;

generate the insurance claim from a template form of the insurance carrier, the insurance claim automatically populated with information required of the template form;

retrieve from a database, operational data for the one or more building devices, the operational data comprising raw sensor data from sensors deployed in the physical premises and alerts generated for the one or more building devices;

extract, from the operational data, one or more previous state sequences, the one or more previous state sequences indicating a sequence of a plurality of states over time of the one or more building devices before the insured event;

determine, based on a classification model, the one or more previous state sequences, and historical state sequence data, whether each of the plurality of states is a normal state or a drift state; and

augment the insurance claim with a report comprising a plurality of elements indicating the one or more previous state sequences and a plurality of elements identifying each of the plurality of states as the normal state or the drift state.

2. The computer program product of claim 1 further comprising instructions to:

collect sensor information from plural sensors deployed in the physical premises;

continually analyze the collected sensor information by one or more unsupervised learning models to determine one or more normal sets of states and drift states;

detect during the continual analysis the drift states based on the collected sensor information; and

correlate determined drift state specific objects being monitored at the identified premises.

3. The computer program product of claim 1 wherein the computer program product receives a trigger.

4. The computer program product of claim 1 further comprising instructions to:

parse a triggering message to extract information regarding the insured event.

5. The computer program product of claim 4 further comprising instructions to:

construct a request for a sensor-based state prediction system extract service and usage data for one or more monitored units within the physical premises.

6. The computer program product of claim 1 wherein the raw sensor data represents environmental conditions of the physical premises.

7. The computer program product of claim 1, wherein the report comprises a plurality of elements indicating values of the raw sensor data.

8. The computer program of claim 1 wherein the instructions cause the processor to augment the insurance claim with a service record indicating service performed on the one or more building devices by a technician.

9. The computer program of claim 8 wherein the service record comprises at least one of a job identifier identifying a particular service job associated with the one or more building devices, a cause identifier indicating a particular type of a fault experienced by the one or more building devices, or a resolution identifier indicating an action performed by the technician to resolve the fault.

10. A system comprises:

plural sensor devices installed at a physical premises;

a gateway to couple the plural devices to a network;

a server computer comprising processor and memory, the sever computer coupled to the network;

a storage device storing a computer program product for detecting conditions at the premises, the computer program product comprising instructions to cause the server to;

receive a request to produce an insurance claim for the occurrence of an insured event at the physical premises, the insured event associated with one or more building devices that are insured by an insurance carrier;

generate an insurance claim from a template form of the insurance carrier, the insurance claim automatically populated with information required of the template form;

retrieve from a database, operational data for the one or more building devices, the operational data comprising raw sensor data from the plural sensor devices installed at the physical premises and alerts generated for the one or more building devices;

extract, from the operational data, one or more previous state sequences, the one or more previous state sequences indicating a sequence of a plurality of states over time of the one or more building devices before the insured event;

determine, based on a classification model, the one or more previous state sequences, and historical state sequence data, whether each of the plurality of states is a normal state or a drift state; and

augment the insurance claim with a report comprising a plurality of elements indicating the one or more previous state sequences and a plurality of elements identifying each of the plurality of states as the normal state or the drift state.

11. The system of claim 10 further comprising instructions to:

collect sensor information from the plural sensors installed at the physical premises.

12. The system of claim 11 further comprising instructions to:

continually analyze the collected sensor information by one or more unsupervised learning models to determine one or more normal sets of states and drift states;

detect during the continual analysis the drift states based on the collected sensor information; and

correlate determined drift state specific objects being monitored at the identified premises.

13. The system of claim 11 wherein the computer program product receives a trigger.

14. The system of claim 11 further comprising instructions to:

parse a triggering message to extract information regarding the insured event.

15. The system of claim 11 further comprising instructions to:

construct a request for a sensor-based state prediction system extract service and usage data for one or more monitored units within the physical premises.

16. The system of claim 11 further comprising:

constructing by the one or more server computers a request for a sensor-based state prediction system extract service and usage data for one or more monitored units within the physical premises.

17. A computer implemented method comprises:

collecting sensor information from plural sensor devices installed at a physical premises;

sending by a gateway to one or more server computers, the collected sensor data, wherein the one or more server computers comprise one or more processors and memory devices, the sever computer coupled to a network;

receiving by the one or more server computers a request to produce an insurance claim for an occurrence of an insured event at the physical premises, the insured event associated with one or more building devices that are insured by an insurance carrier;

generating by the one or more server computers an insurance claim from a template form of the insurance carrier, the insurance claim automatically populated with information required of the template form;

retrieving by the one or more server computers from a database, operational data for the one or more building devices, the operational data comprising raw sensor data from sensors deployed in the physical premises and alerts generated for one or more building devices;

extracting by the one or more server computers from the operational data, one or more previous state sequences, the one or more previous state sequences indicating a sequence of a plurality of states over time of the one or more building devices before the insured event;

determining, by the one or more server computers based on a classification model, the one or more previous state sequences, and historical state sequence data, whether each of the one or more previous states is a normal state or a drift state; and

augmenting by the one or more server computers the insurance claim with a report comprising a plurality of elements indicating the one or more previous state sequences, a plurality of elements identifying each of the plurality of states of the one or more state sequences as the normal state or the drift state.

18. The method of claim 17 further comprising:

collecting by the one or more server computers sensor information from the plural sensor devices installed at the physical premises;

continually analyzing by the one or more server computers the collected sensor information by one or more unsupervised learning models to determine a normal sets of states and drift states;

detecting by the one or more server computers during the continual analysis the drift states based on the collected sensor information; and

correlating by the one or more server computers determined drift state specific objects being monitored at the identified premises.

19. The method of claim 17 wherein the computer program product receives a trigger.

20. The method of claim 17 further comprising:

parsing a triggering message to extract information regarding the insured event.