System and method for using self-learning rules to enable adaptive security monitoring
View Patent ↗Rules “learn” what is typical or expected for a certain attribute of device data for a given location, premises, time period, etc. Using a rule for a standard deviation the variance between newly collected data and the data stored in a fact table is either ignored or an alert (or some action) is generated. Data in the fact table is sampled for a specific time, or time period. Newly collected data may be used to update the fact table or discarded.
1. A method for processing device data comprising:
obtaining device data corresponding to one or more monitoring devices;
comparing the monitoring device data to a set of previously collected device data; and
generating an output if the monitoring device data substantially deviates from the set of previously collected monitoring device data,
wherein the monitoring device data is stored in tables that include dimensions and measures, wherein the monitoring device data stored in the tables is updated periodically to reflect desired norms within a given dimension, and wherein the monitoring device data is compared to the desired norms to determine a rule violation.
2. The method as recited in claim 1 , wherein comparing the monitoring device data to a set of previously collected monitoring device data includes comparing the monitoring device data to a subset of the previously collected monitoring device data.
3. The method as recited in claim 2 further comprising selecting a subset of the collected monitoring device data according to time criteria.
4. The method as recited in claim 2 further comprising selecting a subset of the collected monitoring device data according to a specified event.
5. The method as recited in claim 1 , wherein the output corresponding to the generation of an alarm signal.
6. The method as recited in claim 1 , wherein the output corresponding to an activation of one or more devices.
7. The method as recited in claim 1 , wherein the output corresponding to the generation of notification or notification sequences.
8. The method of claim 1 , further comprising:
obtaining collected normative dimensions for the monitoring device data; and
comparing the monitoring device data with the collected normative dimensions to determine if a threshold tolerance for variance is exceeded.
9. The method of claim 1 , further comprising communicating the at least one output to an authorized user using a hierarchy of communication mediums.
10. The method of claim 1 , wherein the tables are fact tables that employ data cubes that include dimensions and measures.
11. A computer-readable medium having computer-executable components for processing monitoring device data comprising:
a data interface component for obtaining monitoring device data;
a rules component for storing a set of previously collected monitoring device data; and
a data processing application for determining whether the monitoring device data substantially deviates from the set of previously collected monitoring device data,
wherein the monitoring device data is stored in tables that include dimensions and measures, wherein the monitoring device data stored in the tables is updated periodically to reflect desired norms within a given dimension, and wherein the monitoring device data is compared to the desired norms to determine a rule violation.
12. The computer-readable medium as recited in claim 11 , wherein the monitoring device data corresponds to information from an analog or digital video camera.
13. The computer-readable medium as recited in claim 11 further comprising an output component for generating an output if the monitoring device data substantially deviates from the set of previously collected monitoring device data.
14. The computer-readable medium of claim 11 , wherein the data processing application obtains collected normative dimensions for the monitoring device data and compares the monitoring device data with the collected normative dimensions to determine if a threshold tolerance for variance is exceeded.
15. The computer-readable medium of claim 11 , wherein the data processing application communicates the at least one output to an authorized user using a hierarchy of communication mediums.
16. The computer-readable medium of claim 11 , wherein the tables are fact tables that employ data cubes that include dimensions and measures.
17. A system for processing monitoring device data comprising:
at least one information collection computing device for obtaining monitoring device data from a number of monitoring devices, wherein the video analytics monitoring device data corresponds to at least one identifiable target;
a central processing server in communication with the at a least one information collection computing device and operable to receive the monitoring device data;
a processing rules data store having a set previously collected monitoring device data;
wherein the central processing server determines whether the monitoring device data substantially deviates form the set of previously collected monitoring device data and generates at least one output corresponding to determination, wherein the monitoring device data is stored in tables that include dimensions and measures, wherein the monitoring device data stored in the tables is updated periodically to reflect desired norms within a given dimension, and wherein the monitoring device data is compared to the desired norms to determine a rule violation.
18. The system of claim 17 , wherein the central processing server obtains collected normative dimensions for the monitoring device data and compares the monitoring device data with the collected normative dimensions to determine if a threshold tolerance for variance is exceeded.
19. The system of claim 17 , wherein the central processing server communicates the at least one output to an authorized user using a hierarchy of communication mediums.
20. The system of claim 17 , wherein the tables are fact tables that employ data cubes that include dimensions and measures.