Interpreting presence signals using historical data
A method includes obtaining historical event data for events detected over a past period of time by sensors within a property, receiving a set of current event data for one or more events detected by one or more of the sensors within the property, determining that the set of current event data matches a pattern of events indicated by the historical event data, generating, based on the pattern of events, a confidence score for the set of current event data, wherein the confidence scores reflects a confidence that a person is not within the property, determining that the confidence score satisfies a confidence threshold associated with an action to be performed when a person is not within the property, and triggering execution of the action.
1. A computer-implemented method comprising:
collecting data sensed by a monitoring system that monitors a property of a user;
aggregating, over a period of time, the collected data sensed by the monitoring system that monitors the property of the user;
detecting, within the aggregated data sensed over the period of time by the monitoring system that monitors the property of the user, patterns of recurring events at the property;
receiving at least one presence signal related to presence of the user at the property monitored by the monitoring system;
interpreting the at least one presence signal in accordance with the detected patterns of recurring events at the property; and
taking action related to the monitoring system based on the interpretation of the at least one presence signal in accordance with the detected patterns of recurring events at the property;
wherein detecting, within the aggregated data sensed over the period of time by the monitoring system that monitors the property of the user, patterns of recurring events at the property comprises assigning a confidence score for a pattern of recurring events that reflects a level of confidence that the detected pattern is actually a pattern of recurring events that will be observed in the future, the assigned confidence score being based on a percentage of time the pattern has occurred previously, an amount of data used in detecting the pattern, and a statistical technique that assesses whether the pattern is a statistically significant pattern of recurring events;
wherein receiving at least one presence signal related to presence of the user at the property monitored by the monitoring system comprises receiving at least one sensor signal from a door sensor, a motion detection sensor, or a window sensor.
2. The computer-implemented method of claim 1 , wherein
collecting data sensed by the monitoring system that monitors the property of the user comprises collecting contact sensor events detected by door and window sensors located at doors and windows of the property and motion sensor events detected by motion sensors located at the property.
3. The computer-implemented method of claim 1 , wherein aggregating, over the period of time, the collected data sensed by the monitoring system that monitors the property of the user comprises:
identifying the property associated with the collected data sensed by the monitoring system that monitors the property of the user; and
storing the collected data sensed by the monitoring system that monitors the property of the user with an indication of the identified property.
4. The computer-implemented method of claim 1 , wherein detecting, within the aggregated data sensed over the period of time by the monitoring system that monitors the property of the user, patterns of recurring events at the property comprises evaluating timing of events detected by the monitoring system and order of events detected by the monitoring system.
5. The computer-implemented method of claim 1 , wherein detecting, within the aggregated data sensed over the period of time by the monitoring system that monitors the property of the user, patterns of recurring events at the property comprises:
identifying groups of sensor events using cluster analysis, identifying unusual sensor events using anomaly detection, and identifying dependencies using association rule mining.
6. The computer-implemented method of claim 1 , wherein interpreting the at least one presence signal in accordance with the detected patterns of recurring events at the property comprises:
detecting a door open event at a particular time on a particular day;
detecting a lack of activity in the property after the detection of the door open event at the particular time on the particular day; and
interpreting the detected door open event and the detected lack of activity in the property as an indication that the property will be empty for an extended duration in accordance with the detected patterns of recurring events at the property.
7. The computer-implemented method of claim 1 , wherein taking action related to the monitoring system based on the interpretation of the at least one presence signal in accordance with the detected patterns of recurring events at the property comprises:
determining that the monitoring system is unarmed at a time when the detected patterns of recurring events at the property indicate that the property is empty; and
based on the determination that the monitoring system is unarmed at a time when the detected patterns of recurring events at the property indicate that the property is empty, sending an alert to a mobile device of the user indicating that the user may have forgotten to arm the monitoring system and asking the user whether the user would like to arm the monitoring system.
8. The computer-implemented method of claim 1 , wherein taking action related to the monitoring system based on the interpretation of the at least one presence signal in accordance with the detected patterns of recurring events at the property comprises modifying a temperature setting of the property from a first pre-set temperature appropriate for a time when someone occupies the property to a second pre-set temperature appropriate for a time when the property is empty, the second pre-set temperature being different from the first pre-set temperature.
9. A monitoring system that is configured to monitor a property, the monitoring system comprising:
one or more sensors that are located at the property; and a monitoring server configured to perform operations comprising:
collecting data sensed by the monitoring system that monitors a property of a user;
aggregating, over a period of time, the collected data sensed by the monitoring system that monitors the property of the user;
detecting, within the aggregated data sensed over the period of time by the monitoring system that monitors the property of the user, patterns of recurring events at the property;
receiving at least one presence signal related to presence of the user at the property monitored by the monitoring system;
interpreting the at least one presence signal in accordance with the detected patterns of recurring events at the property; and
taking action related to the monitoring system based on the interpretation of the at least one presence signal in accordance with the detected patterns of recurring events at the property;
wherein detecting, within the aggregated data sensed over the period of time by the monitoring system that monitors the property of the user, patterns of recurring events at the property comprises assigning a confidence score for a pattern of recurring events that reflects a level of confidence that the detected pattern is actually a pattern of recurring events that will be observed in the future, the assigned confidence score being based on a percentage of time the pattern has occurred previously, an amount of data used in detecting the pattern, and a statistical technique that assesses whether the pattern is a statistically significant pattern of recurring events;
wherein receiving at least one presence signal related to presence of the user at the property monitored by the monitoring system comprises receiving at least one sensor signal from a door sensor, a motion detection sensor, or a window sensor.
10. The monitoring system of claim 9 , wherein collecting data sensed by the monitoring system that monitors the property of the user comprises collecting contact sensor events detected by door and window sensors located at doors and windows of the property and motion sensor events detected by motion sensors located at the property.
11. The monitoring system of claim 9 , wherein aggregating, over the period of time, the collected data sensed by the monitoring system that monitors the property of the user comprises:
identifying the property associated with the collected data sensed by the monitoring system that monitors the property of the user; and
storing the collected data sensed by the monitoring system that monitors the property of the user with an indication of the identified property.
12. The monitoring system of claim 9 , wherein detecting, within the aggregated data sensed over the period of time by the monitoring system that monitors the property of the user, patterns of recurring events at the property comprises evaluating timing of events detected by the monitoring system and order of events detected by the monitoring system.
13. The monitoring system of claim 9 , wherein detecting, within the aggregated data sensed over the period of time by the monitoring system that monitors the property of the user, patterns of recurring events at the property comprises:
identifying groups of sensor events using cluster analysis, identifying unusual sensor events using anomaly detection, and identifying dependencies using association rule mining.
14. The monitoring system of claim 9 , wherein interpreting the at least one presence signal in accordance with the detected patterns of recurring events at the property comprises:
detecting a door open event at a particular time on a particular day;
detecting a lack of activity in the property after the detection of the door open event at the particular time on the particular day; and
interpreting the detected door open event and the detected lack of activity in the property as an indication that the property will be empty for an extended duration in accordance with the detected patterns of recurring events at the property.
15. The monitoring system of claim 9 , wherein taking action related to the monitoring system based on the interpretation of the at least one presence signal in accordance with the detected patterns of recurring events at the property comprises:
determining that the monitoring system is unarmed at a time when the detected patterns of recurring events at the property indicate that the property is empty; and
based on the determination that the monitoring system is unarmed at a time when the detected patterns of recurring events at the property indicate that the property is empty, sending an alert to a mobile device of the user indicating that the user may have forgotten to arm the monitoring system and asking the user whether the user would like to arm the monitoring system.
16. The monitoring system of claim 9 , wherein taking action related to the monitoring system based on the interpretation of the at least one presence signal in accordance with the detected patterns of recurring events at the property comprises modifying a temperature setting of the property from a first pre-set temperature appropriate for a time when someone occupies the property to a second pre-set temperature appropriate for a time when the property is empty, the second pre-set temperature being different from the first pre-set temperature.