Method and apparatus for evaluating risk based on sensor monitoring
Described are techniques for determining a quotation score that would be applicable across lines of insurance and/or carriers, and which involves the collection in real time of sensor information from plural groups of sensors deployed in a specific premises and associated with intrusion detection, access control, burglar, fire alarm systems and surveillance systems and/or other systems that monitor for physical/chemical/biological conditions. The techniques execute unsupervised learning models to continually analyze the collected sensor information to produce sequences of state transitions that are assign scores and from which a quotation score is produced.
1. One or more non-transitory computer-readable storage media for monitoring drift states within a building having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
receive a request associated with a line of insurance for a space, the space comprising a portion or all of the building;
identify, based on the request, sensors measuring attributes of the space associated with the line of insurance, wherein the sensors include at least one of smoke detectors, fire detectors, or cameras;
collect sensor information from the identified sensors;
update state transition sequences associated with the identified sensors based on the sensor information;
identify drift states associated with a change in risk associated with the space by traversing the state transition sequences associated with the identified sensors;
execute an unsupervised learning model using as input to the model at least the identified drift states; and
generate, based on the model, a quotation score for the line of insurance, wherein the quotation score reflects the change in risk.
2. The one or more non-transitory computer-readable storage media of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to encrypt the quotation score using an encryption key to generate an encrypted quotation score and transmit the encrypted quotation score to a requestor device associated with the received request.
3. The one or more non-transitory computer-readable storage media of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
receive an incident report request associated with an incident at the space;
identify, based on the incident report request, additional sensors measuring attributes of the space associated with the incident; and
traverse state transition sequences associated with the additional sensors to identify drift states indicating a root cause of the incident.
4. The one or more non-transitory computer-readable storage media of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to generate a state transition matrix associated with the sensors, and execute an unsupervised learning algorithm using the state transition matrix to identify the drift states.
5. The one or more non-transitory computer-readable storage media of claim 1 , wherein the state transition sequences are part of a second model that represents the space.
6. A system for detecting conditions at a physical premises, comprising:
one or more server computers comprising processing circuitry configured to:
receive a request associated with a line of insurance for a space, the space comprising a portion or all of the physical premises;
identify, based on the request, sensors measuring attributes of the space associated with the line of insurance, wherein the sensors include at least one of smoke detectors, fire detectors, or cameras;
collect sensor information from the identified sensors;
update state transition sequences associated with the identified sensors based on the sensor information;
identify drift states associated with a change in risk associated with the space by traversing the state transition sequences associated with the identified sensors;
execute an unsupervised learning model using as input to the model at least the identified drift states; and
generate, based on the model, a quotation score for the line of insurance, wherein the quotation score reflects the change in risk.
7. The system of claim 6 , wherein the processing circuitry is further configured to encrypt the quotation score using an encryption key to generate an encrypted quotation score and transmit the encrypted quotation score to a requestor device associated with the received request.
8. The system of claim 6 , wherein the processing circuitry is further configured to:
receive an incident report request associated with an incident at the space;
identify, based on the incident report request, additional sensors measuring attributes of the space associated with the incident; and
traverse state transition sequences associated with the additional sensors to identify drift states indicating a root cause of the incident.
9. The system of claim 6 , wherein the processing circuitry is further configured to generate a state transition matrix associated with the sensors, and execute an unsupervised learning algorithm using the state transition matrix to identify the drift states.
10. The system of claim 6 , wherein the state transition sequences are part of a second model that represents the space.
11. A method for monitoring drift states within a building, comprising:
receiving a request associated with a line of insurance for a space, the space comprising a portion or all of the building;
identifying, based on the request, sensors measuring attributes of the space associated with the line of insurance, wherein the sensors include at least one of smoke detectors, fire detectors, or cameras;
collecting sensor information from the identified sensors;
updating state transition sequences associated with the identified sensors based on the sensor information;
identifying drift states associated with a change in risk associated with the space by traversing state transition sequences associated with the identified sensors;
executing an unsupervised learning model using as input to the model at least the identified drift states; and
generating, based on the model, a quotation score for the line of insurance, wherein the quotation score reflects the change in risk.
12. The method of claim 11 , further comprising encrypting the quotation score using an encryption key to generate an encrypted quotation score and transmitting the encrypted quotation score to a requestor device associated with the received request.
13. The method of claim 11 , further comprising:
receiving an incident report request associated with an incident at the space;
identifying, based on the incident report request, additional sensors measuring attributes of the space associated with the incident; and
traversing state transition sequences associated with the additional sensors to identify drift states indicating a root cause of the incident.
14. The method of claim 11 , further comprising generating a state transition matrix associated with the sensors, and execute an unsupervised learning algorithm using the state transition matrix to identify the drift states.