Voice assistant device and method thereof
Embodiments of present disclosure relates to a voice assistant device and method for controlling the voice assistant device. The voice assistant device comprising receiver configured to receive at least one voice input from user, when operated in wake-up mode. Intent associated with the at least one voice input from the at least one user. Further, probability of issuance of a subsequent voice input from the at least one user is determined based on at least one of the intent, historic data and one or more contextual factors. An extended wake-up duration of the voice assistant device is estimated, when the probability is greater than a predefined threshold value. Further, duration of the wake-up mode is extended for the extended wake-up duration to receive the subsequent voice input from the at least one user.
1. A method of a voice assistant device, the method comprising:
receiving, by the voice assistant device, at least one voice input from a user during wake-up mode of the voice assistance device;
identifying, by the voice assistant device, intent associated with the at least one voice input from the user;
determining, by the voice assistant device, a probability of issuance of a subsequent voice input from the user based on at least one of the intent, historic data and one or more contextual factors;
comparing, by the voice assistant device, the probability with a threshold value; and
extending, by the voice assistant device, a duration of the wake-up mode of the voice assistant device based on comparing the probability with the threshold value, for a extended wake-up duration to receive the subsequent voice input from the at least one user.
2. The method as claimed in claim 1 , wherein the threshold value is determined by analysis of the historic data, through devices connected to the voice assistance device.
3. The method as claimed in claim 1 , further comprising:
determining, by a control apparatus, the probability to be lesser than the threshold value; and
configuring, by the control apparatus, the voice assistant device to be in sleep-mode until a trigger to operate in the wake-up mode is detected.
4. The method as claimed in claim 1 , further comprising configuring, by a control apparatus, the voice assistant device to be in sleep-mode if absence of the subsequent voice input is detected during the extended wake-up duration.
5. The method as claimed in claim 1 , wherein the intent associated with the at least one voice input is identified by performing Natural-Language Understanding on the at least one voice input.
6. The method as claimed in claim 1 , wherein the one or more contextual factors comprises at least one of user related factors, time related factors data and environment related factors.
7. The method as claimed in claim 1 , wherein determining the probability of issuance of the subsequent voice input comprises:
extract one or more keywords from plurality of words in the at least one voice input;
identify a domain associated with the at least one voice input based on the one or more keywords;
compute domain matching scores for the identified domain with plurality of pre-stored domains associated with the user; and
determine probability of issuance of the subsequent voice input to the voice assistant device, based on the domain matching scores.
8. The method as claimed in claim 7 , wherein extracting the one or more keywords comprises:
assigning weightage to each of the plurality of words of the at least one voice input; and
identifying the one or more keywords from the plurality of words, with weightage greater than a weightage value, to be the one or more keywords.
9. The method as claimed in claim 1 , further comprising:
build a conversation knowledge for the at least one voice input, based on one or more extracted keywords, wherein the conversation knowledge is used for identifying the intent of the subsequent voice input to the voice assistant device.
10. The method of claim 1 , further comprising:
determining, by the voice assistant device, the extended wake-up duration of the voice assistant device based on comparing the probability with the threshold value, when the probability is greater than the threshold value.
11. A voice assistant device, comprising:
a receiver configured to receive at least one voice input from at least one user, when operated in a wake-up mode;
a processor; and
a memory communicatively coupled to the processor,
wherein the memory stores processor-executable instructions that, when executed by the processor, cause the processor to:
identify intent associated with the at least one voice input from the user;
determine a probability of issuance of a subsequent voice input from the user based on at least one of the intent, historic data and one or more contextual factors;
compare the probability with a threshold value;
determine an extended wake-up duration of the voice assistant device based on comparing the probability with the threshold value, when the probability is greater than the threshold value; and
extend a duration of the wake-up mode based on comparing the probability with the threshold value, for a extended wake-up duration to receive the subsequent voice input from the user.
12. The voice assistant device as claimed in claim 11 , wherein the threshold value is determined by analysis of the historic data, through devices connected to the voice assistance device.
13. The voice assistant device as claimed in claim 11 , further comprises the processor configured to:
determine the probability to be lesser than the threshold value; and
configure to be operated in sleep-mode until a trigger to be operated in the wake-up mode is detected.
14. The voice assistant device as claimed in claim 11 , wherein the intent associated with the at least one voice input is determined by performing Natural-Language Understanding (NLU) on the at least one voice input.
15. The voice assistant device as claimed in claim 11 , wherein the one or more contextual factors comprises at least one of user related factors, time related factors data and environment related factors.
16. The voice assistant device as claimed in claim 11 , wherein the processor is configured to determine the probability of issuance of the subsequent voice input by performing the steps of:
extract one or more keywords from plurality of words in the at least one voice input;
identify a domain associated with the at least one voice input based on the one or more keywords;
compute domain matching scores for the identified domain with plurality of pre-stored domains associated with the user; and
determine the probability of issuance of the subsequent voice input to the voice assistant device, based on the domain matching scores.
17. The voice assistant device as claimed in claim 16 , wherein extraction of the one or more keywords is performed by:
assigning weightage to each of the plurality of words of the at least one voice input; and
identifying one or more keywords from the plurality of words, with weightage greater than a weightage value, to be the one or more keywords.
18. The voice assistant device as claimed in claim 11 , further comprises the processor configured to:
build a conversation knowledge for the at least one voice input, based on one or more extracted keywords, wherein the conversation knowledge is used for identifying the intent of the subsequent voice input to the voice assistant device.
19. The voice assistant device as claimed in claim 11 , further comprises the processor configured to:
configure the voice assistant device to be in sleep-mode if absence of the subsequent voice input is detected during the extended wake-up duration.
20. The voice assistant device of claim 11 , wherein the processor is further configured to:
determine the extended wake-up duration of the voice assistant device based on comparing the probability with the threshold value, when the probability is greater than the threshold value.