Method for intent-based interactive response and electronic device thereof
A method for providing intent-based interactive voice response by an electronic device. The method includes receiving, by the electronic device, a voice input while obtaining an image of an object by using an image sensor, and generating an interactive voice response associated with the object based on the voice input. The method may further include determining a first intent and a second intent from the voice input, and generating an interactive voice response to the voice input, based on the first intent and the second intent.
1. A method comprising:
obtaining, by an electronic device, a voice input of a user via a microphone of the electronic device, and an image of an object captured by using a camera of the electronic device;
identifying a plurality of intents of the user, based on the voice input of the user and the captured image of the object;
selecting a relevant voice prompt from among a plurality of voice prompts, based on at least one of the plurality of intents identified from the voice input, wherein the plurality of voice prompts is ranked based on relevance of the identified plurality of intents;
generating a response associated with the object, based on the selected voice prompt; and
displaying, via a display the electronic device, the captured image of the object while outputting the response audibly via a speaker of the electronic device,
wherein the identifying the plurality of intents comprises:
identifying the object;
identifying a first intent from the voice input based on a context of the object determined based on a plurality of contextual characteristics and a user gesture while providing the voice input; and
identifying a second intent from the voice input based on a user activity and the usage characteristics determined based on a usage history associated with the user and the object, wherein the usage history is obtained from a memory of the electronic device or an available database.
2. The method of claim 1 , further comprising recognizing the object based on information received from the camera of the electronic device.
3. The method of claim 1 , wherein the plurality of contextual characteristics comprises at least one from among a visual cue from the user while providing the voice input, a focal length of the camera, a distance between the user and the object, or an object usage behavior of the user.
4. The method of claim 1 , wherein the plurality of voice prompts is associated with a plurality of characteristics, and
wherein the plurality of characteristics comprises at least one from among an experience of an expert associated with the object, a level of knowledge of the expert about the object, a designation of the expert, or an interaction pattern of the user with the expert.
5. The method of claim 1 , further comprising:
displaying information regarding an alternative response; and
outputting the alternative response in response to a selection of the user.
6. An electronic device comprising:
a memory; and
a processor configured to:
obtain, via a microphone, a voice input of a user, and an image of an object captured by using a camera;
identify a plurality of intents of the user based on the voice input of the user and the captured image of the object;
select a relevant voice prompt from among a plurality of voice prompts, based on at least one of the plurality of intents identified from the voice input, wherein the plurality of voice prompts is ranked based on relevance of the identified plurality of intents;
generate a response associated with the object, based on the selected voice prompt; and
control a display to display the captured image of the object while controlling a speaker of the electronic device to output the response audibly,
wherein the processor is further configured to identify the plurality of intents by:
identifying the object;
identifying a first intent from the voice input based on a context of the object determined based on a plurality of contextual characteristics and a user gesture while providing the voice input; and
identifying a second intent from the voice input based on a user activity and a usage history associated with the user and the object, wherein the usage history is obtained from the memory or an available database.
7. The electronic device of claim 6 , wherein the processor is further configured to recognize the object based on information received from the camera.
8. The electronic device of claim 6 , wherein the plurality of contextual characteristics comprises at least one from among a visual cue from the user while providing the voice input, a focal length of the camera, a distance between the user and the object, or an object usage behavior of the user.
9. The electronic device of claim 6 , wherein the plurality of voice prompts is associated with a plurality of characteristics, and
wherein the plurality of characteristics comprises at least one from among an experience of an expert associated with the object, a level of knowledge of the expert about the object, a designation of the expert, or an interaction pattern of the user with the expert.
10. The electronic device of claim 6 , wherein the processor is further configured to:
control the display to display information regarding an alternative response; and
output the alternative response in response to a selection of the user.