Electronic device for processing multi-modal input, method for processing multi-modal input and server for processing multi-modal input
An electronic device is provided. The electronic device includes a housing, a touchscreen display exposed through a first portion of the housing, a microphone disposed at a second portion of the housing, a speaker disposed at a third portion of the housing, a memory disposed inside the housing, a processor disposed inside the housing, and electrically connected to the display, the microphone, the speaker, and the memory. The memory is configured to store a plurality of application programs, each of which includes a graphic user interface (GUI).
1. A portable communication device comprising:
a memory storing a rule database;
a touchscreen display;
a microphone;
communication circuitry configured to establish a wireless communication connection between a server and the portable communication device; and
a processor,
wherein the processor is configured to:
receive, via the microphone, a first user utterance,
transmit utterance information corresponding to the first user utterance to the server via the communication circuitry,
receive, from the server, first information corresponding to the utterance information,
perform a first set of operations according to a first path rule corresponding to the first information from among a plurality of path rules stored in the rule database,
identify at least one parameter necessary to perform a second set of operations subsequent to performing the first set of operations,
display, via the touchscreen display, a first user interface to receive a user input identifying the at least one parameter according to the first path rule,
receive, via the touchscreen display or the microphone, the user input, and
perform the second set of operations using the at least one parameter identified by the user input according to the first path rule, the second set of operations being subsequent to the first set of operations in the first path rule, and
wherein an application to perform the second set of operations is identified from the first path rule.
2. The portable communication device of claim 1 , wherein the processor is further configured to identify the first path rule from the plurality of path rules based on the first information.
3. The portable communication device of claim 1 , wherein the first path rule misses the at least one parameter used for the second set of operations.
4. The portable communication device of claim 1 , wherein the first path rule includes at least one operation for receiving the user input, the at least one operation being performed between the first set of operations and the second set of operations.
5. The portable communication device of claim 1 , wherein the processor is further configured to generate the plurality of path rules according to inputs from a user.
6. The portable communication device of claim 1 ,
wherein the first set of operations are bound to a first application according to the first path rule, and
wherein the second set of operations are bound to a second application according to the first path rule.
7. The portable communication device of claim 6 , wherein the first user interface corresponds to an execution screen of the first application.
8. The portable communication device of claim 7 , wherein the at least one parameter includes at least one image required for the second set of operations.
9. The portable communication device of claim 8 , wherein the second set of operations includes transmitting the at least one image using the communication circuitry.
10. The portable communication device of claim 1 , wherein the processor is further configured to:
receive, via the microphone, a wakeup utterance,
execute a voice agent application in response to receiving the wakeup utterance, and
receive the first user utterance using the voice agent application.
11. A portable communication device comprising:
a memory storing a rule database;
a touchscreen display;
a microphone; and
a processor,
wherein the processor is configured to:
receive, via the microphone, a first user utterance,
identify a first path rule corresponding to the first user utterance from among a plurality of path rules stored in the rule database,
perform a first set of operations according to the first path rule,
identify at least one parameter necessary to perform a second set of operations subsequent to performing the first set of operations,
display, via the touchscreen display, a first user interface to receive a user input identifying the at least one parameter according to the first path rule,
receive, via the touchscreen display or the microphone, the user input, and
perform the second set of operations using the at least one parameter identified by the user input according to the first path rule, the second set of operations being subsequent to the first set of operations in the first path rule, and
wherein an application to perform the second set of operations is identified from the first path rule.
12. The portable communication device of claim 11 , wherein the processor is further configured to convert the first user utterance into text data and identify the first path rule using the text data.
13. The portable communication device of claim 11 , wherein the first path rule misses the at least one parameter used for the second set of operations.
14. The portable communication device of claim 11 , wherein the first path rule includes at least one operation for receiving the user input, the at least one operation being performed between the first set of operations and the second set of operations.
15. The portable communication device of claim 11 , wherein the processor is further configured to generate the plurality of path rules according to inputs from a user.
16. The portable communication device of claim 11 ,
wherein the first set of operations are bound to a first application according to the first path rule, and
wherein the second set of operations are bound to a second application according to the first path rule.
17. The portable communication device of claim 16 , wherein the first user interface corresponds to an execution screen of the first application.
18. The portable communication device of claim 17 , wherein the at least one parameter includes at least one image required for the second set of operations.
19. The portable communication device of claim 18 , wherein the second set of operations includes transmitting the at least one image using communication circuitry.
20. The portable communication device of claim 11 , wherein the processor is further configured to:
receive, via the microphone, a wakeup utterance,
execute a voice agent application in response to receiving the wakeup utterance, and
receive the first user utterance using the voice agent application.