Interpreting presence signals using historical data

1. A computer-implemented method comprising:

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 that indicates the likeliness that a person is not within the property;

determining, based on analyzing a cost for performing an action and a convenience to a resident of the property for performing the action, a confidence threshold for the action;

comparing the confidence score for the set of current event data to the confidence threshold for the action;

based on comparing the confidence score for the set of current event data to the confidence threshold for the action, determining that the confidence score satisfies the confidence threshold; and

in response to determining that the confidence score satisfies the confidence threshold for the action, performing the action.

2. The computer-implemented method of claim 1 , wherein determining that the set of current event data matches a pattern of events indicated by the historical event data comprises:

identifying the pattern of events is associated with no persons being within the property based on determining the pattern reoccurs multiple times in the historical event data when no persons are within the property.

3. The computer-implemented method of claim 1 , wherein receiving event data comprises:

receiving one or more of motion sensor data, contact sensor data, or appliance usage data.

4. The computer-implemented method of claim 1 , wherein generating, based on the pattern of events, a confidence score for the set of current event data comprises:

generating the confidence score based on how closely the received set of current event data matches the pattern of events.

5. The computer-implemented method of claim 1 , wherein generating, based on the pattern of events, a confidence score for the set of current event data comprises:

generating the confidence score based on how often the pattern of events is followed by detecting no one is at the property.

6. The computer-implemented method of claim 1 , wherein generating, based on the pattern of events, a confidence score for the set of current event data comprises:

generating a confidence score that reflects a low confidence that a person is not within the property when it is determined that a more definitive set of event data will be received within a short period of time.

7. The computer-implemented method of claim 1 , wherein determining that the confidence score satisfies a confidence threshold associated with an action to be performed when a person is not within the property comprises:

determining that the confidence score satisfies a confidence threshold associated with at least one action from a set of actions, wherein each action from the set of actions is associated with a respective confidence threshold.

8. The computer-implemented method of claim 1 , wherein performing the action comprises:

providing an instruction to a HVAC system at the property to change the temperature setting to low energy setting.

9. The computer-implemented method of claim 1 , wherein performing the action comprises:

providing, to a user device of a resident of the property, a notification indicating that a monitoring system at the property is disarmed;

receiving, from the user device, an instruction to arm the monitoring system; and

in response to receiving, from the user device, an instruction to arm the monitoring system, arming the monitoring system.

10. The computer-implemented method of claim 1 , wherein performing the action comprises:

providing an instruction to a smart appliance device to change to a low power mode.

11. The computer-implemented method of claim 1 , wherein performing the action comprises:

providing an instruction to one or more lights to switch on or off.

12. A monitoring system that is configured to monitor a property, the monitoring system comprising:

a monitor control unit; and

one or more sensors that are located at the property, and are in communication with the monitor control unit,

wherein the monitor control unit is configured to:

obtain historical event data for events detected over a past period of time by sensors within a property;

receive a set of current event data for one or more events detected by one or more of the sensors within the property;

determine that the set of current event data matches a pattern of events indicated by the historical event data;

generate, based on the pattern of events, a confidence score for the set of current event data that indicates the likeliness that a person is not within the property;

determine, based on analyzing a cost for performing an action and a convenience to a resident of the property for performing the action, a confidence threshold for the action;

compare the confidence score for the set of current event data to the confidence threshold for the action;

based on comparing the confidence score for the set of current event data to the confidence threshold for the action, determine that the confidence score satisfies the confidence threshold; and

in response to determining that the confidence score satisfies the confidence threshold for the action, perform the action.

13. The system of claim 12 , wherein determining that the set of current event data matches a pattern of events indicated by the historical event data comprises:

identifying the pattern of events is associated with no persons being within the property based on determining the pattern reoccurs multiple times in the historical event data when no persons are within the property.

14. The system of claim 12 , wherein receiving event data comprises:

receiving one or more of motion sensor data, contact sensor data, or appliance usage data.

15. The system of claim 12 , wherein generating, based on the pattern of events, a confidence score for the set of current event data comprises:

generating the confidence score based on how closely the received set of current event data matches the pattern of events.

16. The system of claim 12 , wherein generating, based on the pattern of events, a confidence score for the set of current event data comprises:

generating the confidence score based on how often the pattern of events is followed by detecting no one is at the property.

17. The system of claim 12 , wherein generating, based on the pattern of events, a confidence score for the set of current event data comprises:

generating a confidence score that reflects a low confidence that a person is not within the property when it is determined that a more definitive set of event data will be received within a short period of time.

18. The system of claim 12 , wherein determining that the confidence score satisfies a confidence threshold associated with an action to be performed when a person is not within the property comprises:

determining that the confidence score satisfies a confidence threshold associated with at least one action from a set of actions, wherein each action from the set of actions is associated with a respective confidence threshold.

19. A non-transitory computer-readable storage device encoded with a computer program, the program comprising instructions that when executed by a data processing apparatus cause the data processing apparatus to perform operations comprising:

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 that indicates the likeliness that a person is not within the property;

determining, based on analyzing a cost for performing an action and a convenience to a resident of the property for performing the action, a confidence threshold for the action;

comparing the confidence score for the set of current event data to the confidence threshold for the action;

based on comparing the confidence score for the set of current event data to the confidence threshold for the action, determining that the confidence score satisfies the confidence threshold; and

in response to determining that the confidence score satisfies the confidence threshold for the action, performing the action.