IoT device grouping and labeling
Techniques for grouping and labeling Internet of Things (IoT) devices are disclosed. A set of raw events associated with a first IoT device is identified. A context of the first IoT device is identified, and used to enrich at least some of the raw events. At least some of the raw events are aggregated. A context-based IoT device grouping model is generated based at least in part on the aggregated events and events associated with a second IoT device in operation. The model is applied to determine that a third IoT device belongs to a particular group. A deviation by the third IoT device from group behavior is detected and an alert is generated in response.
1. A method comprising:
identifying a set of raw events associated with a first Internet of Things (IoT) device in operation;
identifying a context of the first IoT device in operation and enriching at least some raw events in the set of raw events based at least in part on obtained additional contextual information to form a set of enriched events;
aggregating at least some of the raw events included in the set of raw events to form a set of aggregated events;
generating a context-based IoT device grouping model based at least in part on the set of enriched events, the set of aggregated events, and events associated with a second IoT device in operation;
applying the generated context-based IoT device grouping model to determine that a third IoT device belongs to a particular group; and
detecting, as an undesired behavior, a deviation by the third IoT device from group behavior, and generating an alert in response.
2. The method of claim 1 , further comprising: transforming at least a portion of the raw events included in the set of raw events into a format suitable for grouping and labeling the first and second IoT devices.
3. The method of claim 1 , further comprising: transforming at least a portion of the raw events included in the set of raw events into discrete events.
4. The method of claim 1 , further comprising: transforming at least a portion of the raw events included in the set of raw events into composite events comprising multiple event parameters.
5. The method of claim 1 , wherein the set of raw events includes one or more messages transmitted to the first IoT device, and wherein the method further comprises: examining the one or more messages transmitted to the first IoT device to determine an event which can subsequently be timestamped to create a formatted event of the first IoT device in operation.
6. The method of claim 1 , wherein identifying the set of raw events of the first IoT device in operation is performed at least in part within a data rollup window, and wherein the method further comprises: generating formatted events of the first IoT device within the data rollup window.
7. The method of claim 1 , wherein identifying the set of raw events of the first IoT device in operation is performed at least in part within a data rollup window, and wherein the method further comprises: aggregating events during the data rollup window to form the set of aggregated events.
8. The method of claim 1 , further comprising: transmitting event metadata of the set of aggregated events to a remote system for purposes of performing grouping of the first and second IoT devices.
9. The method of claim 1 , further comprising: determining that grouping the first and third IoT devices is unsuccessful, and carrying out assisted grouping and labeling of the first and third IoT devices.
10. The method of claim 1 , further comprising: determining that a new IoT device label has been added, and performing a new grouping operation to the first and second IoT devices.
11. A system comprising:
a processor configured to:
identify a set of raw events associated with a first Internet of Things (IoT) device in operation;
identify a context of the first IoT device in operation and enrich at least some raw events in the set of raw events based at least in part on obtained additional contextual information to form a set of enriched events;
aggregate at least some of the raw events included in the set of raw events to form a set of aggregated events;
generate a context-based IoT device grouping model based at least in part on the set of enriched events, the set of aggregated events, and events associated with a second IoT device in operation;
apply the generated context-based IoT device grouping model to determine that a third IoT device belongs to a particular group; and
detect, as an undesired behavior, a deviation by the third IoT device from group behavior, and generate an alert in response.
12. The system of claim 11 , wherein the processor is further configured to: transform at least a portion of the raw events included in the set of raw events into a format suitable for grouping and labeling the first and second IoT devices.
13. The system of claim 11 , wherein the processor is further configured to: transform at least a portion of the raw events included in the set of raw events into discrete events.
14. The system of claim 11 , wherein the processor is further configured to: transform at least a portion of the raw events included in the set of raw events into composite events comprising multiple event parameters.
15. The system of claim 11 , wherein the set of raw events includes one or more messages transmitted to the first IoT device, and wherein the processor is further configured to: examine the one or more messages transmitted to the first IoT device to determine an event which can subsequently be timestamped to create a formatted event of the first IoT device in operation.
16. The system of claim 11 , wherein identifying the set of raw events of the first IoT device in operation is performed at least in part within a data rollup window, and wherein the processor is further configured to: generate formatted events of the first IoT device within the data rollup window.
17. The system of claim 11 , wherein identifying the set of raw events of the first IoT device in operation is performed at least in part within a data rollup window, and wherein the processor is further configured to: aggregate events during the data rollup window to form the set of aggregated events.
18. The system of claim 11 , wherein the processor is further configured to: transmit event metadata of the set of aggregated events to a remote system for purposes of performing grouping of the first and second IoT devices.
19. The system of claim 11 , wherein the processor is further configured to: determine that grouping the first and third IoT devices is unsuccessful, and carry out assisted grouping and labeling of the first and third IoT devices.
20. The system of claim 11 , wherein the processor is further configured to: determine that a new IoT device label has been added, and perform a new grouping operation to the first and second IoT devices.
21. A computer program product embodied on a non-transitory medium, the computer program product including instructions which, when executed by a computer, cause the computer to carry out a method comprising:
identifying a set of raw events associated with a first Internet of Things (IoT) device in operation;
identifying a context of the first IoT device in operation and enriching at least some raw events in the set of raw events based at least in part on obtained additional contextual information to form a set of enriched events;
aggregating at least some of the raw events included in the set of raw events to form a set of aggregated events;
generating a context-based IoT device grouping model based at least in part on the set of enriched events, the set of aggregated events, and events associated with a second IoT device in operation;
applying the generated context-based IoT device grouping model to determine that a third IoT device belongs to a particular group; and
detecting, as an undesired behavior, a deviation by the third IoT device from group behavior, and generating an alert in response.