Monitoring device having 360 degree sensing
Aspects of the present invention are directed towards identifying users in a room by an intelligent personal assistant for automatic control of certain devices controlled by the assistant. The assistant may have a retractable, reflector that is used to identify persons in the vicinity of the assistant when the retractable, reflector is in an extended position. The retractable, reflector may additionally be stowed inside the assistant to stop processing visual information in the vicinity of the assistant.
1. A method, performed by a device coupled to a digital camera, a microphone, a network interface for communicating with a local area network, and a speaker, comprising:
receiving via use of the digital camera an image data;
determining from the image data that a user is gazing at the device;
receiving via use of the microphone an audio utterance from the user; and
providing the audio utterance to a cloud-based server via use of the network interface for processing without regard to whether a wake word was provided to the device via use of the microphone within a first period of time prior to the audio utterance being received by the device when the audio utterance is received by the device during a second period of time that includes the user having been determined to be gazing at the device.
2. The method of claim 1 , further comprising:
prior to determining that a user is gazing at the device:
monitoring a data received via the microphone for utterance of a wake word;
determining from the data that the user has uttered the wake word; and
providing via use of the speaker a response to a phrase spoken by the user and received via the microphone after the user has uttered the wake word.
3. The method of claim 2 , wherein the second period of time comprises
a predetermined amount of time measured from the providing of the response.
4. The method of claim 1 , wherein determining that a user is gazing at the device comprises:
determining the presence of two eyes and a mouth within the image data.
5. The method of claim 1 , wherein the second period of time comprises
a predetermined amount of time.
6. The method of claim 1 , where the device is coupled to an output device and the method further comprises:
providing an indication to the use via the output device that the device is listening for a further audio utterance.
7. The method of claim 1 , wherein receiving the audio utterance from the user comprises:
monitoring a data received via the microphone for a further audio utterance within a predetermined time after determining that the user is gazing at the intelligent personal assistant;
when the predetermined time has elapsed without receipt of the further audio utterance, requiring the wake word to be re-provided to the device before allowing the device to provide any subsequently received audio utterance to the cloud-based server via use of the network interface for processing.
8. A device, comprising:
a digital camera;
a microphone;
a network interface for communicating with a local area network;
a memory for storing processor-executable instructions; and
a processor coupled to the memory, the digital camera, the network interface and the microphone, for executing the processor-executable instructions that cause the device to:
receive via use of the digital camera an image data;
determine from the image data that a user is gazing at the intelligent personal assistant via the digital camera;
receive an audio utterance from the user via the microphone; and
provide the audio utterance to a cloud-based server via the network interface for processing without regard to whether a wake word was provided to the device via use of the microphone within a first period of time prior to the audio utterance being received by the device when the audio utterance is received by the device during a second period of time that includes the user having been determined to be gazing at the device.
9. The device of claim 8 , further comprising a speaker and additional processor-executable instructions that cause the device to:
prior to determining that a user is gazing at the device:
monitor a data received via the microphone for utterance of a wake word;
determine from the data that the user has uttered the wake word; and
provide via use of the speaker a response to a phrase spoken by the user and received via use of the microphone after the user has uttered the wake word.
10. The device of claim 9 , wherein the second period of time comprises
a predetermined period of time measured from the providing of the response.
11. The device of claim 8 , wherein the processor-executable instructions that cause the device to determine that a user is gazing at the device comprises instructions that cause the intelligent personal assistant to:
determine the presence of two eyes and a mouth within the image data.
12. The device of claim 8 , wherein the second period of time comprises
a predetermined period time.
13. The device of claim 8 , further comprising:
a visual indicator;
wherein the processor-executable instructions further comprise additional processor-executable instructions that cause the device to:
cause the visual indicator to illuminate when the intelligent personal assistant is listening for a further audio utterance.
14. The device of claim 8 , wherein the processor-executable instructions that cause the device to receive the audio utterance from the user comprises instructions that cause the intelligent personal assistant to:
monitor a data received via the microphone for a further audio utterance within a predetermined time after determining that the user is gazing at the intelligent personal assistant;
when the predetermined time has elapsed without receipt of the further audio utterance, requiring the wake word to be re-provided to the device before allowing the device to provide any subsequently received audio utterance to the cloud-based server via use of the network interface for processing.