Method and apparatus for tiered analytics in a multi-sensor environment
Disclosed is a networked system for detecting conditions at a physical premises. The networked system includes a local computer system configure to read a configuration file that determines processing performed by the local computer system and evaluate collected sensor data with respect to the configuration file, for first sensor data to be processed by the local computer, and execute unsupervised learning models to continually analyze the first sensor data to produce operational states and detect drift sequences that are correlated to stored determined conditions. The networked system also includes a remote computer system that execute unsupervised learning models to continually analyze the collected sensor information. An alert is asserted by at least one of the local computer and the remote computer based on the determined conditions.
1. A system, comprising:
a local computing system comprising a processing device and a memory, the memory including instructions stored thereon that, when executed by the processing device, cause the local computing system to:
receive sensor data from one or more sensors in a building;
generate a first state sequence using the received sensor data, wherein the first state sequence comprises one or more states representative of a condition being monitored by the one or more sensors; and
determine the first state sequence is a first drift sequence based on an analytic in a first set of analytics; and
a remote computing system comprising a processing device and a memory, the memory including instructions stored thereon that, when executed by the processing device, cause the local computing system to:
receive an indication of a transfer of processing control from the local computer system to the remote computer system in response to the local computing system determining the first drift sequence;
in response to receiving the indication, receive the sensor data from the one or more sensors in the building;
generate a second state sequence using the received sensor data; and
determine the second state sequence is a second drift sequence based on an analytic in a second set of analytics;
wherein the first drift sequence or the second drift sequence is reported to a user.
2. The system of claim 1 , wherein the local computing system is located within the building.
3. The system of claim 1 , wherein the one or more states are determined by an unsupervised learning model.
4. The system of claim 3 , wherein at least one of the local computing device or the remote computing device is further caused to train the unsupervised learning model using training data.
5. The system of claim 1 , wherein the first state sequence further comprises transition data for transitions between the one or more states.
6. The system of claim 1 , wherein the first set of analytics is stored in a first configuration file, wherein the remote computing system is further caused to send a second configuration file with a third set of analytics to the local computing system.
7. The system of claim 6 , wherein the local computing system is further caused to report the first drift sequence to the remote computing system, wherein the remote computing system sends the second configuration file responsive to receiving the report of the first drift sequence.
8. The system of claim 1 , wherein analytics in the first set of analytics analyze sensor data over a shorter period of time than analytics in the second set of analytics.
9. The system of claim 1 , wherein the local computing system is further caused to transfer processing control of the sensor data to the remote computing system.
10. The system of claim 9 , wherein the remote computing system is further caused to continue processing of the sensor data responsive to receiving an indication of the transferred processing control.
11. A method of analyzing sensor data, the method comprising:
receiving, by a local computing system, sensor data from one or more sensors in a building;
generating, by the local computing system, a first state sequence using the received sensor data, wherein the first state sequence comprises one or more states representative of a condition being monitored by the one or more sensors;
determining, by the local computing system, the first state sequence is a first drift sequence based on an analytic in a first set of analytics;
receiving, by a remote computing system, an indication of a transfer of processing control from the local computer system to the remote computer system in response to the local computing system determining the first drift sequence;
in response to receiving the indication, generating, by the remote computing system, a second state sequence using the received sensor data;
determining, by the remote computing system, the second state sequence is a second drift sequence based on an analytic in a second set of analytics; and
reporting, by the local computing system or the remote computing system, the first drift sequence or the second drift sequence to a user.
12. The method of claim 11 , further comprising determining the one or more states using an unsupervised learning model.
13. The method of claim 12 , further comprising training the unsupervised learning model using training data.
14. The method of claim 11 , wherein the first state sequence further comprises transition data for transitions between the one or more states.
15. The method of claim 11 , wherein analytics in the first set of analytics analyze sensor data over a shorter period of time than analytics in the second set of analytics.
16. The method of claim 11 , wherein the local computing system is further caused to transfer processing control of the sensor data to the remote computing system.
17. The method of claim 16 , wherein the remote computing system is further caused to continue processing of the sensor data responsive to receiving an indication of the transferred processing control.
18. One or more non-transitory, computer-readable storage media having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
receive sensor data from one or more sensors in a building;
generate a first state sequence using the received sensor data, wherein the first state sequence comprises one or more states representative of a condition being monitored by the one or more sensors; and
determine the first state sequence is a first drift sequence based on an unsupervised machine learning model in a first set of analytics;
transmit an indication of a transfer of processing control from to a remote computer system in response to determining the first drift sequence, wherein the remote computer system is configured to:
generate a second state sequence different than the first state sequence using the received sensor data, wherein the second state sequence comprises one or more states representative of the condition being monitored by the one or more sensors; and
determine the second state sequence is a second drift sequence based on an unsupervised machine learning model in a second set of analytics; and
report the first drift sequence or the second drift sequence to a user device.
19. The one or more storage media of claim 18 , wherein analytics in the first set of analytics analyze sensor data over a shorter period of time than analytics in the second set of analytics.
20. The one or more storage media of claim 18 , wherein the one or more processors are further caused to transfer processing control of the sensor data from a first computing system to the second computing system.