Event detection by microphone
AssigneeVivint, Inc.
InventorsShiwei Liu, Aaron Davis, Justin Peel, Rongbin Lanny Lin, Brandon Bunker
Life of this patent
Estimating the term…
Abstract
A method for security and/or automation systems is described. In one embodiment, the method includes detecting a sound using a microphone, generating an audio signature of the detected sound, comparing the audio signature of the detected sound to an audio signature of a characterized sound, and determining whether a recognizable event occurs based on the comparison. In some embodiments, the microphone is attached to a pipe at the premises.
Claims16
A method for security and/or automation systems, comprising:
- detecting a sound using a microphone;
- generating an audio signature of the detected sound;
- comparing the audio signature of the detected sound to an audio signature of a characterized sound;
- when the audio signature of the detected sound matches the audio signature of the characterized sound, logging information related to the detected sound to a database where the audio signature of the characterized sound is stored and performing an automation task, the automation task comprising at least one of adjustment of a light setting in the premises, adjustment of a thermostat setting of the premises, adjustment of an appliance setting in the premises, adjustment of a machine in the premises, adjustment of a machine setting in the premises, adjustment of an automated locking mechanism, adjustment of a setting of the automation system, or any combination thereof;
- and
- when the audio signature of the detected sound does not match the audio signature of the characterized sound, characterizing the non-matching detected sound.
An apparatus for an automation system, comprising:
- a processor;
- memory in electronic communication with the processor;
- and
- instructions stored in the memory, the instructions being executable by the processor to:
- detect a sound using a microphone;
- generate an audio signature of the detected sound;
- compare the audio signature of the detected sound to an audio signature of a characterized sound;
- when the audio signature of the detected sound matches the audio signature of the characterized sound, log information related to the detected sound to a database where the audio signature of the characterized sound is stored and perform an automation task, the automation task comprising at least one of adjustment of a light setting in the premises, adjustment of a thermostat setting of the premises, adjustment of an appliance setting in the premises, adjustment of a machine in the premises, adjustment of a machine setting in the premises, adjustment of an automated locking mechanism, adjustment of a setting of the automation system, or any combination thereof;
- and
- when the audio signature of the detected sound does not match the audio signature of the characterized sound, characterize the non-matching detected sound.
A non-transitory computer-readable medium storing computer-executable code for an automation system, the code executable by a processor to perform the steps of:
- detecting a sound using a microphone;
- generating an audio signature of the detected sound;
- comparing the audio signature of the detected sound to an audio signature of a characterized sound;
- when the audio signature of the detected sound matches the audio signature of the characterized sound, logging information related to the detected sound to a database where the audio signature of the characterized sound is stored and performing an automation task, the automation task comprising at least one of adjustment of a light setting in the premises, adjustment of a thermostat setting of the premises, adjustment of an appliance setting in the premises, adjustment of a machine in the premises, adjustment of a machine setting in the premises, adjustment of an automated locking mechanism, adjustment of a setting of the automation system, or any combination thereof;
- and
- when the audio signature of the detected sound does not match the audio signature of the characterized sound, characterizing the non-matching detected sound.
Dependencies are inferred from the claim text.