Electronic device for outputting response to speech input by using application and operation method thereof

1. A method performed by an electronic device, the method comprising:

receiving, by a user inputter of the electronic device, a speech input;

in response to receiving the speech input, obtaining, by at least one processor of the electronic device, text corresponding to the speech input by performing speech recognition on the speech input;

obtaining, by the at least one processor, metadata for the speech input based on the obtained text;

based on the metadata, obtain preference information about a plurality of applications for processing the speech input, the preference information comprising at least one of information about a result of processing the speech input by the plurality of applications or information about a time taken for the plurality of applications to output responses;

based on the metadata and the preference information, selecting, by the at least one processor, at least one application from among the plurality of applications for outputting a response to the speech input;

outputting, by the at least one processor, the response to the speech input by using the selected at least one application;

updating the preference information based on information about speech output successful for outputting the response to the speech input by each application and the time taken for each application to output the response to the speech input; and

storing the updated preference information.

2. The method of claim 1 , wherein the metadata comprises at least one of a keyword extracted from the obtained text, information about an intention of a user obtained based on the obtained text, information about a sound characteristic of the speech input, or information about the user of the electronic device.

3. The method of claim 1 , wherein the preference information further comprises information about feedback information of a user about responses output by the plurality of applications.

4. The method of claim 1 , wherein the outputting of the response comprises:

obtaining, by the at least one processor, at least one response to the speech input from the selected at least one application;

determining, by the at least one processor, a priority of the at least one response; and

outputting, by the at least one processor, the at least one response according to the determined priority.

5. The method of claim 4 , wherein the determining of the priority comprises determining, by the at least one processor, the priority based on at least one of an intention of a user related to the at least one response, a size of the at least one response, whether the at least one response comprises a characteristic preferred by the user, or information about a time taken to output the at least one response after obtaining the at least one response.

6. The method of claim 4 , wherein the determining of the priority comprises, in response to the user inputter receiving a plurality of speech inputs, determining, by the at least one processor, the priority based on metadata of each of the plurality of speech inputs.

7. The method of claim 1 , further comprising, based on detecting an event comprising a state in which an application previously determined as an application for outputting the response to the speech input cannot output the response to the speech input, selecting, by the at least one processor, at least one of the plurality of applications for outputting the response to the speech input.

8. An electronic device comprising:

an outputter;

a user inputter configured to receive a speech input; and

at least one processor configured to:

in response to the user inputter receiving the speech input, obtain text by performing speech recognition on the speech input,

obtain metadata for the speech input based on the obtained text,

based on the metadata, obtain preference information about a plurality of applications for processing the speech input, the preference information comprising at least one of information about a result of processing the speech input by the plurality of applications or information about a time taken for the plurality of applications to output responses,

based on the metadata and the preference information, select at least one application from among the plurality of applications for outputting a response to the speech input,

control the outputter to output the response to the speech input by using the selected at least one application,

update the preference information based on information about speech output successful for outputting the response to the speech input by each application and the time taken for each application to output the response to the speech input, and

store the updated preference information.

9. The electronic device of claim 8 , wherein the metadata comprises at least one of a keyword extracted from the obtained text, information about an intention of a user obtained based on the obtained text, information about a sound characteristic of the speech input, or information about the user of the electronic device.

10. The electronic device of claim 8 , wherein the preference information further comprises information about feedback information of a user about responses output by the plurality of applications.

11. The electronic device of claim 8 , wherein the at least one processor is further configured to:

obtain at least one response to the speech input from the selected at least one application,

determine a priority of the at least one response, and

control the outputter to output the at least one response according to the determined priority.

12. The electronic device of claim 11 , wherein the at least one processor is further configured to determine the priority based on at least one of an intention of a user related to the at least one response, a size of the at least one response, whether the at least one response comprises a characteristic preferred by the user, or information about a time taken to output the at least one response after obtaining the at least one response.

13. The electronic device of claim 11 , wherein the at least one processor is further configured to, in response to the user inputter receiving a plurality of speech inputs, determine the priority based on metadata of each of the plurality of speech inputs.

14. The electronic device of claim 8 , wherein the at least one processor is further configured to, based on detecting an event comprising a state in which an application previously determined as an application for outputting the response to the speech input cannot output the response to the speech input, select at least one of the plurality of applications for outputting the response to the speech input.

15. A non-transitory computer-readable storage medium configured to store one or more computer programs including instructions that, when executed by at least one processor of an electronic device, cause the at least one processor to control to:

receive a speech input;

in response to receiving the speech input, obtain text corresponding to the speech input by performing speech recognition on the speech input;

obtain metadata for the speech input based on the obtained text;

based on the metadata, obtain preference information about a plurality of applications for processing the speech input, the preference information comprising at least one of information about a result of processing the speech input by the plurality of applications or information about a time taken for the plurality of applications to output responses;

based on the metadata and the preference information, select at least one application from among the plurality of applications for outputting a response to the speech input;

output the response to the speech input by using the selected at least one application;

update the preference information based on information about speech output successful for outputting the response to the speech input by each application and the time taken for each application to output the response to the speech input; and

store the updated preference information.