Method and apparatus for increasing the density of data surrounding an event

• US 10,810,676 B2
• Filed: 06/06/2016
• Issued: 10/20/2020
• Est. Priority Date: 06/06/2016
• 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: Vavrasek, David
• Primary Examiner(s): Lemieux, Jessica
• Application Number:
  US15/173,795
• Publication Number:
  US 20170352102A1
• Time in Patent Office: 1,597 Days
• Field of Search: 705 4
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 21/02 electric
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

Techniques for controlling operation of sensors at a physical premises are described. The techniques process received messages corresponding to a prediction of an impending event and produce commands that modify operation of one or more specific sensors at the physical premises, send the commands that modify the operation of the one or more sensor devices at the physical premises at a period of time prior to a likely occurrence of the predicted insurable event, collect sensor information from the plurality of sensor devices deployed at the premises, and store the sensor information in a remote persistent storage system.

Claims

1. A computer program product tangibly stored on a non-transitory computer readable hardware storage device, the computer program product for controlling operation of sensors at a physical premises, the computer program product comprising instructions to cause a processor to:

receive a message corresponding to a prediction of an impending insurable event at the physical premises, wherein the prediction is based on analysis performed by one or more unsupervised learning models on sensor information collected from one or more sensors deployed at the premises, and wherein the prediction includes a period of time the predicted insurable event is likely to occur;

process the received message according to an algorithm that is selected in accordance with the predicted insurable event, the algorithm producing one or more commands to modify operation of one or more specific sensors of a plurality of sensor devices that collect the sensor information at the physical premises;

send the commands that modify the operation of the one or more specific sensors to the one or more specific sensors at the physical premises prior to the period of time;

collect the sensor information from the plurality of sensor devices deployed at the premises; and

store the sensor information in a persistent storage system.

2. The computer program product of claim 1 wherein the message includes a calculated indication produced by instructions to:

continually analyze the collected sensor information by one or more unsupervised learning models to determine normal sets of states and drift states for the premises to produce the prediction of an occurrence of the insurable event.

3. The computer program product of claim 2 wherein the algorithm to process the received message includes instructions to:

determine modifications of the operation of the one or more specific sensors devices at the identified premises according to an occurrence of a drift state; and

produce the message including the commands that modify the operation of the one or more specific sensors from the determined modifications that are based on the drift state.

4. The computer program product of claim 1 wherein the instructions to determine modification further comprise instructions to:

analyze the prediction of the event;

determine sensor devices that are in proximity to a location of the predicted event;

determine modifications to the sensor devices in proximity to the location, which modifications are based on the predicted event, specific locations of the sensor devices and specific types of the sensor devices;

determine the commands based on the determined modifications; and

send the commands to the sensor devices.

5. The computer program product of claim 1 wherein the message is received from an external service.

6. The computer program product of claim 1 wherein the computer program product further comprises instructions to:

generate an insurance claim form by automatically populating a template insurance claim form with information required by the template insurance claim form.

7. The computer program product of claim 1 wherein the computer program product further comprises instructions to:

detect an actual occurrence of the insurable event based on actual sensor data received from the plurality of sensor devices to provide a trigger to generate an insurance claim form; and

generate an insurance claim form subsequent to the actual occurrence of the event by automatically populating a template insurance claim form with information required by the template insurance claim form.

8. The computer program product of claim 7 further comprising instructions to:

retrieve from a database, operational data for specified equipment that are insured by an insurance carrier, the operational data comprising service records, raw sensor data, and/or alerts generated for the specified equipment; and

augment the insurance claim form with a report that includes the operational data for the specified equipment at a time period prior to the event.

9. The computer program product of claim 1 wherein the algorithm being of a weather-related event, and the computer program product further comprises instructions to:

receive an indication from an external services, the indication being of the weather-related event;

parse the received indication to produce a representation of the indication that identifies a type of weather-related event;

analyze the parsed indication according to a location of the physical premises to produce a likely prediction of damage to the physical premises; and

produce the commands to modify the operation of the one or more specific sensors of the plurality of sensors, according to the likely prediction of damage to the physical premises.

10. The computer program product of claim 8 wherein the computer program product further comprises instructions to:

produce a request to upload service and usage data for one or more monitored units within the premises to an external database; and

send to the system at the physical premises the request to upload to the external database, the service and usage data.

11. The computer program product of claim 1 wherein the one or more specific sensors include one or more video cameras, and the algorithm, comprises instructions to:

receive current positioning information for each of the one or more video cameras;

calculate based at least in part on a received indication repositioning information for the one or more video cameras; and

send the repositioning information to at least some of the one or more video cameras to modify operation of the one or more video cameras by repositioning at least some of the one or more video cameras.

12. The computer program product of claim 1 wherein the one or more specific sensors include one or more video cameras, and the algorithm, comprises instructions to:

receive current frame rate information of each of the one or more video cameras, frame rate information being information of the frequency at which images are taken and sent by the one or more video cameras;

calculate based at least in part on a received indication a modified frame rate information for the one or more video cameras; and

send the modified frame rate information to at least some of the one or more video cameras to modify frame rate operation of the one or more video cameras.

13. A system comprises:

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

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

receive a message corresponding to a prediction of an impending insurable event at the physical premises, wherein the prediction is based on analysis performed by one or more unsupervised learning models on sensor information collected from one or more sensors deployed at the premises, and wherein the prediction includes a period of time the predicted insurable event is likely to occur;

process the received message according to an algorithm that is selected in accordance with the predicted insurable event, the algorithm producing one or more commands to modify operation of one or more specific sensors of a plurality of sensor devices that collect the sensor information at the physical premises;

send the commands that modify the operation of the one or more specific sensors to the one or more specific sensors at the physical premises prior to the period of time;

collect the sensor information from the plurality of sensor devices deployed at the premises; and

store the sensor information in a remote persistent storage system.

14. The system of claim 13 wherein the message includes a calculated indication produced by instructions to:

continually analyze the collected sensor information by one or more unsupervised learning models to determine normal sets of states and drift states for the premises to produce the prediction of an occurrence of the insurable event.

15. The system of claim 14 wherein the algorithm to process the received message includes instructions to:

determine modifications of the operation of the one or more specific sensors at the premises according to an occurrence of a drift state; and

produce the message including the commands that modify the operation of the one or more specific sensors from the determined modifications that are based on the drift state.

16. The system of claim 13 wherein the instructions to determine modifications further comprise instructions to:

analyze the prediction of the event;

determine sensor devices that are in proximity to a location of the predicted event;

determine modifications to the sensor devices in proximity to the location, which modifications are based on the predicted event, specific locations of the sensor devices and specific types of the sensor devices;

determine the commands based on the determined modifications; and

send the commands to the one or more specific sensors.

17. The system of claim 13 wherein the message is received from an external service.

18. The system of claim 13 further comprising instructions to:

generate an insurance claim form by automatically populating a template insurance claim form with information required by the template insurance claim form.

19. The system of claim 13 further comprising instructions to:

detect an actual occurrence of the insurable event based on actual sensor data received from the plurality of sensor devices to provide a trigger to generate an insurance claim form; and

generate an insurance claim form subsequent to the actual occurrence of the event by automatically populating a template insurance claim form with information required by the template insurance claim form.

20. The system of claim 19 further comprising instructions to:

retrieve from a database, operational data for specified equipment that are insured by an insurance carrier, the operational data comprising at least one of service records, raw sensor data, and alerts generated for the specified equipment; and

augment the insurance claim form with a report that includes the operational data for the specified equipment at a time period prior to the event.

21. A computer implemented method comprises:

receiving by one or more server computers a message corresponding to a prediction of an impending insurable event at a physical premises, wherein the prediction is based on analysis performed by one or more unsupervised learning models on sensor information collected from one or more sensors deployed at the premises, and wherein the prediction includes a period of time the predicted insurable event is likely to occur;

processing by the one or more server computers, the received message according to an algorithm that is selected in accordance with the predicted insurable event, the algorithm producing one or more commands to modify operation of one or more specific sensors of a plurality of sensor devices that collect the sensor information at the physical premises;

sending by the one or more server computers, the commands that modify the operation of the one or more specific sensors to the one or more specific sensors at the physical premises prior to the period of time; and

generating by the one or more server computers an insurance claim form subsequent to occurrence of the event by automatically populating a template insurance claim form with information required of the insurance claim form according to the template.

22. The method of claim 21 further comprising:

collecting by the one or more server computers sensor information from plural sensors deployed in the premises;

continually analyze the collected sensor information by one or more unsupervised learning models to determine normal sets of states and drift states for the premises to produce the prediction of an occurrence of the insurable event.

23. The method of claim 22 further comprising:

determining by the one or more computers a modification of the operation of the one or more specific sensors at the premises according to an occurrence of a drift state; and

producing by the one or more computers the message including the commands that modify the operation of the one or more specific sensors from the determined modification that are based on the drift state.

24. The method of claim 21 further comprising:

detecting by the one or more computers an actual occurrence of the insurable event based on actual sensor data received from the plurality of sensor devices to provide a trigger to generate an insurance claim form; and

generating by the one or more computers the insurance claim form subsequent to the actual occurrence of the event.