Method and apparatus for interaction with an intelligent personal assistant
Aspects of the present invention are directed towards a more natural way to interact with an intelligent personal assistant. An intelligent personal assistant comprises a camera that provides images of an area surrounding the assistant. The assistant monitors images provided by the camera to determine when a user is addressing the assistant. When voice input is received after determining that a user is addressing the assistant, the assistant understands that the voice input is intended for the assistant, and acts on the voice input to respond to the user.
1 . An intelligent personal assistant, comprising:
a memory for storing processor-executable instructions;
a camera for generating digital images;
a microphone; and
a processor coupled to the memory, the camera and the microphone for executing the processor-executable instructions that causes the processor to:
receive, via the microphone, a voice input comprising a wake word and a query;
cause the wake word and the query to be processed;
receive, via the microphone, a second voice input;
determine, via the camera, that a person is addressing the intelligent personal assistant; and
cause the second voice input to be processed only when it is determined that the person is addressing the intelligent personal assistant within a predetermined time period from when the first voice input was received.
2 . The intelligent personal assistant of claim 1 , wherein the processor-executable instructions that causes the processor to determine that the person is addressing the intelligent personal assistant comprise instructions that causes the processor to:
determine, via the camera, that the person is gazing at the intelligent personal assistant.
3 . The intelligent personal assistant of claim 2 , wherein the processor-executable instructions that cause the processor to determine that the person is gazing at the intelligent personal assistant comprise instructions that causes the processor to:
determine, via the camera, the presence of a first eye, a second eye and a mouth of the person.
4 . The intelligent personal assistant of claim 1 , further comprising:
a reflective, convex surface positioned above the camera, for allowing the camera to view an area around the intelligent personal assistant;
wherein the camera is positioned inside the intelligent personal assistant pointing upwards towards the reflective, convex surface.
5 . The intelligent personal assistant of claim 4 , comprising further processor-executable instructions that causes the processor to:
apply an inverse function related to a curvature of the reflective, convex surface to the digital images to reduce visual distortion caused by the curvature.
6 . A method performed by an intelligent personal assistant for interacting with a person, comprising:
receiving a voice input comprising a wake word and a query;
causing the wake word and the query to be processed;
receiving a second voice input;
determining that a person is addressing the intelligent personal assistant; and
causing the second voice input to be processed only when it is determined that the person is addressing the intelligent personal assistant within a predetermined time period from when the first voice input was received.
7 . The method of claim 6 , wherein the processor-executable instructions that causes the processor to determine that the person is addressing the intelligent personal assistant comprise instructions that causes the processor to:
determine, via the camera, that the person is gazing at the intelligent personal assistant.
8 . The method of claim 7 , wherein the processor-executable instructions that cause the processor to determine that the person is gazing at the intelligent personal assistant comprise instructions that causes the processor to:
determine, via the camera, the presence of a first eye, a second eye and a mouth of the person.
9 . The method of claim 6 , further comprising:
a reflective, convex surface positioned above the camera, for allowing the camera to view an area around the intelligent personal assistant;
wherein the camera is positioned inside the intelligent personal assistant pointing upwards towards the reflective, convex surface.
10 . The method of claim 9 , comprising further processor-executable instructions that causes the processor to:
apply an inverse function related to a curvature of the reflective, convex surface to the digital images to reduce visual distortion caused by the curvature.