Device and method for providing recommended sentence related to utterance input of user

1. A method, performed by a device for providing a voice assistant service, of providing a recommended utterance sentence related to an utterance input of a user, the method comprising:

receiving the utterance input of the user;

determining whether the utterance input is a short utterance input based on at least one of a part-of-speech (POS) of a word included in the utterance input or a length of the utterance input, wherein the POS is one of: a verb, noun, verb phrase, or noun phrase;

in response to the utterance input being determined as the short utterance input, generating a search query based on the POS of the utterance input to obtain application history data related to the utterance input from among application history data representing an execution history of one or more applications executed by the user in the device;

generating the recommended utterance sentence related to the utterance input by combining the word included in the utterance input with at least one recommended word from the obtained application history data;

determining whether the recommended utterance sentence is supported by the voice assistant service provided by the device; and

based on the recommended utterance sentence being determined to be supported by the voice assistant service, outputting the recommended utterance sentence.

2. The method of claim 1 , wherein:

the generating the search query to obtain the application history data related to the utterance input comprises:

comparing the word included in the utterance input with a parameter in the application history data representing the execution history of the one or more applications, and

extracting the application history data related to the utterance input from among the application history data representing the execution history of the one or more applications based on the comparing; and

wherein the generating the recommended utterance sentence comprises generating the recommended utterance sentence by using the extracted application history data.

3. The method of claim 2 , wherein the extracting the application history data related to the utterance input comprises:

extracting the application history data related to the utterance input from among the application history data representing the execution history of the one or more applications, based on an execution frequency of an operation corresponding to the application history data related to the utterance input.

4. The method of claim 1 , wherein the generating the recommended utterance sentence comprises:

identifying the POS of the word included in the utterance input; and

generating the at least one recommended word corresponding to a POS different from the identified POS based on the application history data.

5. The method of claim 1 , wherein the determining whether the recommended utterance sentence is supported by the voice assistant service comprises:

obtaining a service utterance sentence related to the recommended utterance sentence from among service utterance sentences provided by the voice assistant service;

obtaining a similarity between the obtained service utterance sentence and the recommended utterance sentence; and

determining whether the recommended utterance sentence is supported by the voice assistant service based on the obtained similarity.

6. The method of claim 1 , further comprising:

receiving a selection input of the user with respect to the output recommended utterance sentence; and

providing the voice assistant service based on the selected recommended utterance sentence based on the output recommended utterance sentence being selected by the user.

7. The method of claim 1 , wherein the application history data representing the execution history of the one or more applications is previously generated by the device before the utterance input is received.

8. The method of claim 1 , further comprising:

generating the application history data representing the execution history of the one or more applications executed by the user in the device;

selecting application history data related to an operation supported by the voice assistant service from among the generated application history data; and

storing the selected application history data in a memory of the device,

wherein the extracting the application history data related to the utterance input of the user comprises extracting the application history data related to the utterance input of the user from among the application history data stored in the memory.

9. A non-transitory computer-readable recording medium having recorded thereon a computer program for performing the method of claim 1 .

10. A device for providing a voice assistant service, the device comprising:

a microphone configured to receive an utterance input of a user;

a memory storing one or more instructions; and

a processor configured to provide a recommended utterance sentence related to the utterance input of a user by executing the one or more instructions to:

determine whether the utterance input is a short utterance input based on at least one of a part-of-speech (POS) of a word included in the utterance input or a length of the utterance input, wherein the POS is one of: a verb, noun, verb phrase, or noun phrase;

in response to the utterance input being determined as the short utterance input, generate a search query based on the POS of the utterance input to obtain application history data related to the utterance input from among application history data representing an execution history of one or more applications executed by the user in the device;

generate the recommended utterance sentence related to the utterance input by combining a word included in the utterance input with at least one recommended word from the obtained application history data;

determine whether the recommended utterance sentence is supported by the voice assistant service provided by the device; and

based on the recommended utterance sentence being determined to be supported by the voice assistant service, control to output the recommended utterance sentence.

11. The device of claim 10 , wherein the processor is configured to execute the one or more instructions to:

compare the word included in the utterance input with a parameter in the application history data representing the execution history of the one or more applications;

extract the application history data related to the utterance input from among the application history data representing the execution history of the one or more applications based on the comparing; and

generate the recommended utterance sentence by using the extracted application history data.

12. The device of claim 11 , wherein the processor is configured to execute the one or more instructions to extract the application history data related to the utterance input from among the application history data representing the execution history of the one or more applications, based on an execution frequency of an operation corresponding to the application history data related to the utterance input.

13. A device for providing a voice assistant service, the device comprising:

a memory storing one or more instructions; and

a processor configured to provide a recommended utterance sentence related to an utterance input of a user by executing the one or more instructions to:

obtain the utterance input of the user;

determine whether the utterance input is a short utterance input based on at least one of a part-of-speech (POS) of a word included in the utterance input or a length of the utterance input, wherein the POS is one of: a verb, noun, verb phrase, or noun phrase;

based in response to the utterance input being determined as the short utterance input, generate a search query based on the POS of the utterance input to obtain application history data related to the utterance input from among application history data representing an execution history of one or more applications executed by the user in at least one of the device or another device;

generate the recommended utterance sentence related to the utterance input by combining a word included in the utterance input with at least one recommended word from the obtained application history data;

determine whether the recommended utterance sentence is supported by the voice assistant service provided by the device; and

control to output the recommended utterance sentence based on the recommended utterance sentence being determined to be supported by the voice assistant service.

14. The device of claim 13 , wherein the processor is configured to execute the one or more instructions to:

compare a word included in the utterance input with a parameter in the application history data representing the execution history of the one or more applications;

extract the application history data related to the utterance input from among the application history data representing the execution history of the one or more applications based on the comparing; and

generate the recommended utterance sentence by using the extracted application history data.

15. The device of claim 14 , wherein the processor is configured to execute the one or more instructions to extract the application history data related to the utterance input from among the application history data representing the execution history of the one or more applications, based on an execution frequency of an operation corresponding to the application history data related to the utterance input.