Aberration engine

• US 8,786,425 B1
• Filed: 09/10/2012
• Issued: 07/22/2014
• Est. Priority Date: 09/09/2011
• Status: Active Grant

• Current Assignee: Alarm.com Inc. (Alarm.com Holdings, Inc.)
• Original Assignee: Alarm.com Inc. (Alarm.com Holdings, Inc.)
• Inventors: Hutz, David James
• Primary Examiner(s): Mehmood, Jennifer
• Assistant Examiner(s): ALAM, MIRZA F
• Application Number:
  US13/608,148
• Time in Patent Office: 680 Days
• Field of Search: 340/526, 340/506, 340/531, 340/541, 340/3.1, 340/539.11, 340/574, 340/573.1, 340/545.1, 340/539.1, 340/10.42, 340/5.26, 235/458, 235/481, 235/460, 235/454, 379/40, 379/42, 379/44, 379/209.01, 379/51
• US Class Current: 340/526
• CPC Class Codes: G05B 23/02 Electric testing or monitoring
• CPC Class Codes: G08B 1/08 using electric transmission ; transformation of alarm signals to electrical signals from a different medium, e.g. transmission of an electric alarm signal upon detection of an audible alarm signal
• CPC Class Codes: G08B 13/00 Burglar, theft or intruder alarms
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G08B 21/0469 Presence detectors to detect unsafe condition, e.g. infrared sensor, microphone G08B21/0476 takes precedence
• CPC Class Codes: G08B 23/00 Alarms responsive to unspecified undesired or abnormal conditions
• CPC Class Codes: G08B 25/00 Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
• CPC Class Codes: G08B 25/009 Signalling of the alarm condition to a substation whose identity is signalled to a central station, e.g. relaying alarm signals in order to extend communication range
• CPC Class Codes: G08B 29/00 Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data
• CPC Class Codes: H04M 11/04 with alarm systems, e.g. fire, police or burglar alarm systems
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

An aberration engine that collects data sensed by a monitoring system that monitors a property of a user and aggregates the collected data over a period of a time. The aberration engine detects, within the aggregated data, patterns of recurring events and, based on detecting the patterns of recurring events within the aggregated data, takes action related to the monitoring system based on the detected patterns of recurring events within the aggregated data.

Claims

1. An electronic system comprising:

at least one processor; and

at least one non-transitory computer-readable storage medium coupled to the at least one processor having stored thereon instructions which, when executed by the at least one processor, causes the at least one processor to perform operations comprising;

collecting data sensed by a monitoring system that monitors a property of a user;

aggregating the collected data over a period of a time;

detecting, within the aggregated data, patterns of recurring events; and

based on detecting the patterns of recurring events within the aggregated data, taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data,

wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises;

determining to suggest a rule for the monitoring system based on the detected patterns of recurring events within the aggregated data;

sending, to the user of the monitoring system, a suggestion of the rule for the monitoring system, the suggestion including an interface that includes a description of the rule being suggested and interface controls that enable the user of the monitoring system to set the rule for the monitoring system, decline the rule for the monitoring system, or set a modified version of the rule for the monitoring system;

receiving user input provided through at least one of the interface controls included in the interface that indicates how the user of the monitoring system would like to handle the rule being suggested; and

handling the rule for the monitoring system based on the received user input that indicates how the user of the monitoring system would like to handle the rule being suggested.

2. The electronic system of claim 1, wherein detecting, within the aggregated data, patterns of recurring events comprises:

detecting, within the aggregated data, a series of events that have been repeated multiple times;

determining a confidence score associated with the series of events that reflects whether repetition of the series of events is a recurring pattern;

comparing the determined confidence score to a threshold;

based on the comparison, determining that the determined confidence score meets the threshold; and

detecting the series of events as a pattern of recurring events based on the determination that the determined confidence score meets the threshold.

3. The electronic system of claim 1:

wherein determining to suggest the rule for the monitoring system based on the detected patterns of recurring events within the aggregated data comprises determining to suggest a notification alert that notifies the user in response to data sensed by the monitoring system indicating activity that is inconsistent with the detected patterns of recurring events within the aggregated data; and

wherein sending, to the user of the monitoring system, the suggestion of the rule for the monitoring system comprises sending, to the user of the monitoring system, a suggestion of the notification alert that notifies the user in response to data sensed by the monitoring system indicating activity that is inconsistent with the detected patterns of recurring events within the aggregated data.

4. The electronic system of claim 1, wherein the operations further comprise:

receiving user input related to use of patterns of recurring events in performing actions related to the monitoring system;

based on the user input, updating settings that control use of patterns of recurring events in performing actions related to the monitoring system; and

using patterns of recurring events to perform actions related to the monitoring system based on the updated settings.

5. The electronic system of claim 1, wherein the operations further comprise:

tracking additional events after storing data related to taking action based on the detected patterns of recurring events;

analyzing the additional events with respect to the data related to taking action based on the detected patterns of recurring events; and

based on the analysis, taking action related to updating rules used in taking action for abnormal events.

6. The electronic system of claim 1:

wherein collecting data sensed by the monitoring system that monitors the property of the user comprises collecting historical sensor data captured by sensors of the monitoring system that are fixed at the property and that sense events at the property, collecting location data for the user that reflects a location of the user relative to events at the property sensed by the monitoring system, and collecting historical responses by the user to alerts provided automatically based on the detected patterns of recurring events within the aggregated data;

wherein aggregating the collected data over a period of a time comprises aggregating, over a period of time, the collected historical sensor data, the collected location data, and the collected historical responses;

wherein detecting, within the aggregated data, patterns of recurring events comprises detecting patterns of recurring events within the collected historical sensor data, the collected location data, and the collected historical responses; and

wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises taking action related to the monitoring system based on a current status of the monitoring system, a user-specified level of sensitivity for each sensor and a measure of how much false alarms bother them, and the detected patterns of recurring events within the collected historical sensor data, the collected location data, and the collected historical responses.

7. The electronic system of claim 1:

wherein detecting, within the aggregated data, patterns of recurring events comprises detecting timing patterns of recurring events within the aggregated data and detecting order patterns related to an order in which recurring events occur; and

wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises taking action related to the monitoring system based on the detected timing patterns of recurring events within the aggregated data and the detected order patterns related to the order in which recurring events occur.

8. The electronic system of claim 1, wherein sending, to the user of the monitoring system, the suggestion of the rule for the monitoring system comprises:

determining a confidence score for the rule being suggested; and

including the determined confidence score for the rule being suggested in the interface with the description of the rule being suggested and the interface controls that enable the user of the monitoring system to set the rule for the monitoring system, decline the rule for the monitoring system, or set a modified version of the rule for the monitoring system.

9. The electronic system of claim 1, wherein sending, to the user of the monitoring system, the suggestion of the rule for the monitoring system comprises:

determining a number of alerts that the rule being suggested is expected to generate over a period of time; and

including the determined number of alerts that the rule being suggested is expected to generate over the period of time in the interface with the description of the rule being suggested and the interface controls that enable the user of the monitoring system to set the rule for the monitoring system, decline the rule for the monitoring system, or set a modified version of the rule for the monitoring system.

10. An electronic system comprising:

at least one processor; and

at least one non-transitory computer-readable storage medium coupled to the at least one processor having stored thereon instructions which, when executed by the at least one processor, causes the at least one processor to perform operations comprising;

collecting data sensed by a monitoring system that monitors a property of a user;

aggregating the collected data over a period of a time;

detecting, within the aggregated data, patterns of recurring events;

based on detecting the patterns of recurring events within the aggregated data, taking action related to the monitoring system;

receiving user input related to use of patterns of recurring events in performing actions related to the monitoring system;

based on the user input, updating settings that control use of patterns of recurring events in performing actions related to the monitoring system; and

using patterns of recurring events to perform actions related to the monitoring system based on the updated settings,

wherein receiving user input related to use of patterns of recurring events in performing actions related to the monitoring system comprises receiving user input indicating that the user would like to be alerted more based on patterns of recurring events;

wherein updating settings that control use of patterns of recurring events in performing actions related to the monitoring system comprises updating settings to decrease a level of confidence of detected activity being abnormal activity needed to alert the user of abnormal activity; and

where using patterns of recurring events to perform actions related to the monitoring system based on the updated settings comprises using patterns of recurring events to perform actions in accordance with the decreased level of confidence.

11. An electronic system comprising:

at least one processor; and

at least one non-transitory computer-readable storage medium coupled to the at least one processor having stored thereon instructions which, when executed by the at least one processor, causes the at least one processor to perform operations comprising;

collecting data sensed by a monitoring system that monitors a property of a user;

aggregating the collected data over a period of a time;

detecting, within the aggregated data, patterns of recurring events;

based on detecting the patterns of recurring events within the aggregated data, taking action related to the monitoring system;

receiving user input related to use of patterns of recurring events in performing actions related to the monitoring system;

based on the user input, updating settings that control use of patterns of recurring events in performing actions related to the monitoring system; and

using patterns of recurring events to perform actions related to the monitoring system based on the updated settings,

wherein receiving user input related to use of patterns of recurring events in performing actions related to the monitoring system comprises receiving user input indicating that the user would like to be alerted less based on patterns of recurring events;

wherein updating settings that control use of patterns of recurring events in performing actions related to the monitoring system comprises updating settings to increase a level of confidence of detected activity being abnormal activity needed to alert the user of abnormal activity; and

where using patterns of recurring events to perform actions related to the monitoring system based on the updated settings comprises using patterns of recurring events to perform actions in accordance with the increased level of confidence.

12. The electronic system of claim 11, wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises automatically, without action by the user, setting a rule for the monitoring system based on the detected patterns of recurring events within the aggregated data.

13. The electronic system of claim 12, wherein automatically, without action by the user, setting the rule for the monitoring system based on the detected patterns of recurring events within the aggregated data comprises automatically, without action by the user, setting a notification alert that notifies the user in response to data sensed by the monitoring system indicating activity that is inconsistent with the detected patterns of recurring events within the aggregated data.

14. The electronic system of claim 12, wherein automatically, without action by the user, setting the rule for the monitoring system based on the detected patterns of recurring events within the aggregated data comprises automatically, without action by the user, extending a dialer delay for an alarm condition detected by the monitoring system based on activity that is consistent with the detected patterns of recurring events within the aggregated data, but that occurs at a time when the monitoring system is armed, the dialer delay being a time period during which the user is able to deactivate the alarm condition prior to the monitoring system notifying a central monitoring station about the alarm condition.

15. The electronic system of claim 11, wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises sending, to the user and at a time when the monitoring system is in an unarmed state, a notification alert that notifies the user that data sensed by the monitoring system indicates activity that is inconsistent with the detected patterns of recurring events within the aggregated data.

16. The electronic system of claim 11, wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises sending, to a central monitoring station and at a time when the monitoring system is in an unarmed state, an alarm notification that notifies the central monitoring station of a potential alarm condition based on data sensed by the monitoring system indicating activity that is inconsistent with the detected patterns of recurring events within the aggregated data, the central monitoring station being authorized to dispatch emergency services based on alarm conditions detected by the monitoring system.

17. The electronic system of claim 11, wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises:

identifying a series of events detected by the monitoring system;

determining abnormality measures based on the detected patterns of recurring events within the aggregated data, the determined abnormality measures including an abnormality measure for each event included in the series of events;

determining an abnormality score for the series of events based on the determined abnormality measures;

comparing the abnormality score to a threshold;

based on the comparison, determining that the abnormality score meets the threshold; and

based on the determination that the abnormality score meets the threshold, sending, to the user, an alert indicating that the monitoring system has detected abnormal activity at the property of the user.

18. The electronic system of claim 11, wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises:

assigning scores to rules related to the detected patterns of recurring events within the aggregated data;

comparing events detected by the monitoring system to the rules related to the detected patterns of recurring events within the aggregated data;

based on the comparison, identifying one or more events that meet at least two of the rules;

based on identifying the one or more events that meet the at least two rules, accessing scores associated with the at least two rules;

combining the accessed scores to determine an abnormality score for the events detected by the monitoring system;

comparing the abnormality score to a threshold;

based on the comparison, determining that the abnormality score meets the threshold; and

based on the determination that the abnormality score meets the threshold, taking action for abnormal activity detected by the monitoring system.

19. The electronic system of claim 11, wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises:

assigning scores to rules related to the detected patterns of recurring events within the aggregated data;

comparing events detected by the monitoring system to the rules related to the detected patterns of recurring events within the aggregated data;

based on the comparison, identifying one or more events that meet at least two of the rules;

based on identifying the one or more events that meet the at least two rules, accessing scores associated with the at least two rules;

combining the accessed scores to determine an abnormality score for the events detected by the monitoring system;

comparing the abnormality score to a threshold;

based on the comparison, determining that the abnormality score does not meet the threshold; and

based on the determination that the abnormality score does not meet the threshold, continuing to monitor events detected by the monitoring system and updating the abnormality score based on events newly detected by the monitoring system and timing of the events newly detected by the monitoring system.

20. The electronic system of claim 11, wherein receiving user input indicating that the user would like to be alerted less based on patterns of recurring events comprises:

presenting an interface that requests feedback on how the monitoring system has performed in taking action based on patterns of recurring events and that includes interface controls that enable a user to indicate that the user would like the monitoring system to continue taking action as it has been, that the user would like to be alerted less by the monitoring system, that the user would like to be alerted more by the monitoring system, or that the user would like the monitoring system to stop taking action; and

receiving, through the presented interface, user input provided using at least one of the interface controls that indicates that the user would like to be alerted less by the monitoring system.

21. The electronic system of claim 11, wherein detecting, within the aggregated data, patterns of recurring events comprises:

detecting, within the aggregated data, a series of events that have been repeated multiple times;

determining a confidence score associated with the series of events that reflects whether repetition of the series of events is a recurring pattern;

comparing the determined confidence score to a threshold;

based on the comparison, determining that the determined confidence score meets the threshold; and

detecting the series of events as a pattern of recurring events based on the determination that the determined confidence score meets the threshold.

22. The electronic system of claim 11:

wherein detecting, within the aggregated data, patterns of recurring events comprises detecting timing patterns of recurring events within the aggregated data and detecting order patterns related to an order in which recurring events occur; and

wherein taking action related to the monitoring system based on the detected patterns of recurring events within the aggregated data comprises taking action related to the monitoring system based on the detected timing patterns of recurring events within the aggregated data and the detected order patterns related to the order in which recurring events occur.