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

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.

1 - 26 . (canceled) 
     
     
         27 . One or more non-transitory computer-readable storage media for monitoring a building having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
 receive an indication corresponding to an insurable event associated with a space, the indication including a period of time the insurable event is likely to occur;   retrieve, from devices monitoring the space, operational data associated with the insurable event based on characteristics associated with the insurable event included in the indication;   determine, based on the operational data, using an unsupervised learning algorithm, a status associated with an attribute of the space; and   generate a claim corresponding to the insurable event including the status associated with the attribute of the space.   
     
     
         28 . The one or more non-transitory computer-readable storage media of  claim 27 , wherein the insurable event is a predicted insurable event, and wherein the indication is received from an unsupervised learning model monitoring the space. 
     
     
         29 . The one or more non-transitory computer-readable storage media of  claim 27 , wherein the attribute includes equipment, and wherein the operational data includes state transitions associated with the equipment. 
     
     
         30 . The one or more non-transitory computer-readable storage media of  claim 29 , wherein the operational data further includes service records associated with the equipment, and wherein the status indicates a level of functionality associated with the equipment prior to the insurable event. 
     
     
         31 . The one or more non-transitory computer-readable storage media of  claim 27 , wherein the characteristics associated with the insurable event include at least one of an event type, a location, or an insurance carrier. 
     
     
         32 . The one or more non-transitory computer-readable storage media of  claim 27 , wherein the attribute includes an individual, wherein the devices include cameras, and wherein the instructions further cause the one or more processors to control a position of the cameras based on the status of the individual. 
     
     
         33 . The one or more non-transitory computer-readable storage media of  claim 27 , wherein determining the status using the unsupervised learning algorithm includes:
 generating a semantic representation of the attribute based on the operational data; and   comparing the semantic representation to a model associated with the attribute to determine a state associated with the attribute, wherein the state is one of a safe state or a drift state.   
     
     
         34 . A method, comprising:
 receiving an indication corresponding to an insurable event associated with a space, the indication including a period of time the insurable event is likely to occur;   retrieving, from devices monitoring the space, operational data associated with the insurable event based on characteristics associated with the insurable event included in the indication;   determining, based on the operational data, using an unsupervised learning algorithm, a status associated with an attribute of the space; and   generating a claim corresponding to the insurable event including the status associated with the attribute of the space.   
     
     
         35 . The method of  claim 34 , wherein the insurable event is a predicted insurable event, and wherein the indication is received from an unsupervised learning model monitoring the space. 
     
     
         36 . The method of  claim 34 , wherein the attribute includes equipment, and wherein the operational data includes state transitions associated with the equipment. 
     
     
         37 . The method of  claim 36 , wherein the operational data further includes service records associated with the equipment, and wherein the status indicates a level of functionality associated with the equipment prior to the insurable event. 
     
     
         38 . The method of  claim 34 , wherein the characteristics associated with the insurable event include at least one of an event type, a location, or an insurance carrier. 
     
     
         39 . The method of  claim 34 , wherein the attribute includes an individual, wherein the devices include cameras, and wherein the instructions further cause the one or more processors to control a position of the cameras based on the status of the individual. 
     
     
         40 . The method of  claim 34 , wherein determining the status using the unsupervised learning algorithm includes:
 generating a semantic representation of the attribute based on the operational data; and   comparing the semantic representation to a model associated with the attribute to determine a state associated with the attribute, wherein the state is one of a safe state or a drift state.   
     
     
         41 . A system, comprising:
 a server computer comprising a processor and memory, the server computer coupled to a network and wherein the memory has instructions stored thereon that, when executed by the processor, cause the server computer to:   receive an indication corresponding to an insurable event associated with a space, the indication including a period of time the insurable event is likely to occur;   retrieve, from devices monitoring the space, operational data associated with the insurable event based on characteristics associated with the insurable event included in the indication;   determine, based on the operational data, using an unsupervised learning algorithm, a status associated with an attribute of the space; and   generate a claim corresponding to the insurable event including the status associated with the attribute of the space.   
     
     
         42 . The system of  claim 41 , wherein the insurable event is a predicted insurable event, and wherein the indication is received from an unsupervised learning model monitoring the space. 
     
     
         43 . The system of  claim 41 , wherein the attribute includes equipment, and wherein the operational data includes state transitions associated with the equipment. 
     
     
         44 . The system of  claim 43 , wherein the operational data further includes service records associated with the equipment, and wherein the status indicates a level of functionality associated with the equipment prior to the insurable event. 
     
     
         45 . The system of  claim 41 , wherein the characteristics associated with the insurable event include at least one of an event type, a location, or an insurance carrier. 
     
     
         46 . The system of  claim 41 , wherein the attribute includes an individual, wherein the devices include cameras, and wherein the instructions further cause the one or more processors to control a position of the cameras based on the status of the individual.