Detecting abnormal events for a monitoring system
AssigneeComcast Cable Communications, LLC
InventorZhen Zhao
Life of this patent
Estimating the term…
Abstract
Systems, apparatuses, and methods are described for detecting a state transition for sensors of a monitoring system, and determining whether the state transition is abnormal such that further action is warranted. The determination may be based on a history of state transitions in the monitoring system, and may be based on whether the same state transition has previously occurred at a corresponding time in the history, whether the new state has previously occurred following the corresponding time in the history, and other factors.
Claims21
A method comprising:
- maintaining, by a computing device, historical sensor state values indicating historical states of a plurality of sensors;
- determining:
- a current state transition time;
- a first set of current sensor state values indicating states of the plurality of sensors prior to the current state transition time;
- and
- a second set of current sensor state values indicating states of the plurality of sensors after the current state transition time;
- and
- sending an anomalous activity alert, wherein the sending is based on:
- a first plurality of historical sensor state values, of a first set of historical sensor state values, matching the first set of current sensor state values;
- a second plurality of historical sensor state values, of a second set of historical sensor state values, matching the second set of current sensor state values;
- and
- a time, associated with the current state transition time, corresponding to a time window associated with the first plurality of historical sensor state values and the second plurality of historical sensor state values.
An apparatus comprising:
- one or more processors;
- and
- memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
- maintain historical sensor state values indicating historical states of a plurality of sensors;
- determine:
- a current state transition time;
- a first set of current sensor state values indicating states of the plurality of sensors prior to the current state transition time;
- and
- a second set of current sensor state values indicating states of the plurality of sensors after the current state transitions time;
- and
- send an anomalous activity alert based on:
- a first plurality of historical sensor state values, of a first set of historical sensor state values, matching the first set of current sensor state values;
- and
- a second plurality of historical sensor state values, of a second set of historical sensor state values, matching the second set of current sensor state values;
- a time, associated with the current state transition time, corresponding to a time window associated with the first plurality of historical sensor state values and the second plurality of historical sensor state values.
A non-transitory computer-readable medium storing instructions, when executed, cause:
- maintaining historical sensor state values indicating historical states of a plurality of sensors;
- determining:
- a current state transition time;
- a first set of current sensor state values indicating states of the plurality of sensors prior to the current state transition time;
- and
- a second set of current sensor state values indicating states of the plurality of sensors after the current state transition time;
- and
- sending an anomalous activity alert based on:
- a first plurality of historical sensor state values, of a first set of historical sensor state values, matching the first set of current sensor state values;
- a second plurality of historical sensor state values, of a second set of historical sensor state values, matching the second set of current sensor state values;
- and
- a time, associated with the current state transition time, corresponding to a time window associated with the first plurality of historical sensor state values and the second plurality of historical sensor state values.
Dependencies are inferred from the claim text.