Building management system to detect anomalousness with temporal profile

1. A method, comprising:

receiving a first set of data including a plurality of events that occurred in one or more buildings over a time period, wherein the time period extends over a plurality of second time units and each of the plurality of second time units extends over a plurality of first time units;

identifying respective timestamps of the plurality of events;

based on the respective timestamps, grouping the plurality of events into respective time buckets that extend over a predetermined time interval;

identifying a subset of the time buckets that are each associated with a particular time, a particular first time unit of the plurality of first time units, and a particular second time unit of the second plurality of time units;

counting a number of the events in each of the time buckets of the subset;

generating a temporal profile including an occurrence rate calculated based on the counted number of events in each of the time buckets of the subset;

receiving a second set of data including one or more events that belong to the subset of the time buckets;

calculating a probability of observing the one or more events in the predetermined time interval according to the temporal profile; and

determining whether the one or more events correspond to an anomalous behavior by comparing the calculated probability to one or more predefined thresholds.

2. The method of claim 1 , wherein the second plurality of time units are weeks and the first plurality of time units are days of a week.

3. The method of claim 1 , further comprising communicating with one or more security devices of a building management system associated with the one or more buildings to receive the first set of data and second set of data.

4. The method of claim 1 , wherein the timestamp corresponds to an occurrence time of each of the plurality of events.

5. The method of claim 1 , wherein the occurrence rate is an averaged value of the respective counted numbers of events of the subset of time buckets.

6. The method of claim 1 , further comprising notifying a user in response to determining that the calculated probability is greater than a first predefined threshold.

7. The method of claim 1 , further comprising notifying a user in response to determining that the calculated probability is less than a second predefined threshold.

8. The method of claim 1 , further comprising using the occurrence rate to calculate the probability of observing the one or more events in the predetermined time interval based on a Poisson distribution.

9. A computing device, comprising:

a memory; and

one or more processors operatively coupled to the memory, the one or more processors configured to:

receive a first set of data including a plurality of events that occurred over a time period, wherein the time period extends over a plurality of second time units and each of the plurality of second time units extends over a plurality of first time units;

identify respective timestamps of the plurality of events, wherein the timestamp corresponds to an occurrence time of each of the plurality of events;

based on the respective timestamps, group the plurality of events into respective time buckets that extend over a predetermined time interval;

identify a subset of the time buckets that are each associated with a particular time, a particular first time unit of the plurality of first time units, and a particular second time unit of the second plurality of time units;

count a number of the events in each of the time buckets of the subset;

generate a temporal profile including an occurrence rate calculated based on the counted number of events in each of the time buckets of the subset;

receive a second set of data including one or more events that belong to the subset of the time buckets;

calculate a probability of observing the one or more events in the predetermined time interval according to the temporal profile; and

determine whether the one or more events correspond to an anomalous behavior by comparing the calculated probability to one or more predefined thresholds.

10. The computing device of claim 9 , wherein the second plurality of time units are weeks and the first plurality of time units are days of a week.

11. The computing device of claim 9 , wherein the one or more processors are further configured to communicate with one or more security devices of a building management system to receive the first set of data and second set of data.

12. The computing device of claim 9 , wherein the occurrence rate is an averaged value of the respective counted numbers of events of the subset of time buckets.

13. The computing device of claim 9 , wherein the one or more processors are further configured to notify a user in response to determining that the calculated probability is greater than a first predefined threshold.

14. The computing device of claim 9 , wherein the one or more processors are further configured to notify a user in response to determining that the calculated probability is less than a second predefined threshold.

15. The computing device of claim 9 , wherein the one or more processors are further configured to use the occurrence rate to calculate the probability of observing the one or more events in the predetermined time interval based on a Poisson distribution.

16. A non-transitory computer readable medium storing program instructions for causing one or more processors to:

receive a first set of data including a plurality of events that occurred over a time period, wherein the time period extends over a plurality of second time units and each of the plurality of second time units extends over a plurality of first time units;

identify respective timestamps of the plurality of events, wherein the timestamp corresponds to an occurrence time of each of the plurality of events;

based on the respective timestamps, group the plurality of events into respective time buckets that extend over a predetermined time interval;

identify a subset of the time buckets that are each associated with a particular time, a particular first time unit of the plurality of first time units, and a particular second time unit of the second plurality of time units;

count a number of the events in each of the time buckets of the subset;

generate a temporal profile including an occurrence rate calculated based on the counted number of events in each of the time buckets of the subset;

receive a second set of data including one or more events that belong to the subset of the time buckets;

calculate a probability of observing the one or more events in the predetermined time interval according to the temporal profile; and

determine whether the one or more events correspond to an anomalous behavior by comparing the calculated probability to one or more predefined thresholds.

17. The non-transitory computer readable medium of claim 16 , wherein the program instructions further cause the one or more processors to communicate with one or more security devices of a building management system to receive the first set of data and second set of data.

18. The non-transitory computer readable medium of claim 16 , wherein the program instructions further cause the one or more processors to notify a user in response to determining that the calculated probability is greater than a first predefined threshold.

19. The non-transitory computer readable medium of claim 16 , wherein the program instructions further cause the one or more processors to notify a user in response to determining that the calculated probability is less than a second predefined threshold.

20. The non-transitory computer readable medium of claim 16 , wherein the program instructions further cause the one or more processors to use the occurrence rate to calculate the probability of observing the one or more events in the predetermined time interval based on a Poisson distribution.