Electronic device for processing user utterance and controlling method thereof
A system includes at least one communication interface, at least one processor operatively connected to the at least one communication interface, and at least one memory operatively connected to the at least one processor and storing a plurality of natural language understanding (NLU) models. The at least one memory stores instructions that, when executed, cause the processor to receive first information associated with a user from an external electronic device associated with a user account, using the at least one communication interface, to select at least one of the plurality of NLU models, based on at least part of the first information, and to transmit the selected at least one NLU model to the external electronic device, using the at least one communication interface such that the external electronic device uses the selected at least one NLU model for natural language processing.
1. A server comprising:
a communication interface;
a processor operatively connected to the communication interface; and
a memory operatively connected to the processor and configured to store a plurality of natural language understanding (NLU) models and instructions that, when executed by the processor, cause the processor to:
receive, from an external electronic device associated with a user account using the communication interface, first information associated with a user, the first information including a voice input of the user, an intent of the user determined by the external electronic device, and at least one of:
information of the external electronic device or
preference information of the user;
based on a number of times that a specified voice input of the user is received not being less than a specified value during a specified period, select at least one of the plurality of NLU models based on at least part of the first information; and
transmit the selected at least one of the plurality of NLU models of the external electronic device using the communication interface such that the external electronic device uses the selected at least one of the plurality of NLU models for natural language processing.
2. The server of claim 1 , wherein the memory stores instructions that, when executed by the processor, cause the processor to:
based on the information of the external electronic device being changed, select at least one of the plurality of NLU models.
3. The server of claim 1 , wherein the memory stores instructions that, when executed by the processor, cause the processor to:
based on the preference information of the user being changed, select at least one of the plurality of NLU models.
4. The server of claim 1 , wherein the memory stores instructions that, when executed by the processor, cause the processor to:
generate text data by processing voice data of the user received from the external electronic device using an automatic speech recognition (ASR) model.
5. The server of claim 1 , wherein the memory stores instructions that, when executed by the processor, cause the processor to:
identify an NLU model corresponding to an intent of a specified number.
6. The server of claim 1 , wherein the memory stores instructions that, when executed by the processor, cause the processor to:
select at least one NLU model corresponding to an intent for performing a function of a specified application program.
7. The server of claim 1 , wherein the memory stores instructions that, when executed by the processor, cause the processor to:
select at least one NLU model corresponding to an intent selected by the user.
8. A controlling method of a system for updating an NLU model, the method comprising:
receiving, from an external electronic device associated with a user account, first information associated with a user, the first information including a voice input of the user, an intent of the user determined by the external electronic device, and at least one of:
information of the external electronic device or
preference information of the user;
selecting at least one of a plurality of natural language understanding (NLU) models based on at least part of the first information, wherein the at least one of the plurality of NLU models is selected based on a number of times that a specified voice input of the user is received not being less than a specified value during a specified period; and
transmitting the selected at least one of the plurality of NLU models to the external electronic device using at least one communication interface such that the external electronic device uses the selected at least one of the plurality of NLU models for natural language processing.
9. The method of claim 8 , wherein the at least one of the plurality of NLU models is selected based on the information of the external electronic device being changed.
10. The method of claim 8 , wherein the at least one of the plurality of NLU models is selected based on the preference information of the user being changed.
11. The method of claim 8 , further comprising:
generating text data by processing voice data of the user received from the external electronic device using an ASR model.
12. The method of claim 8 , wherein the at least one of the plurality of NLU models is selected based on the voice input corresponding to a specified intent includes:
identifying an NLU model corresponding to an intent of a specified number.
13. The method of claim 8 , wherein the at least one of the plurality of NLU models is selected based on the voice input corresponding to a specified intent includes:
identifying the at least one of the plurality of NLU models corresponding to an intent for performing a function of a specified application program.
14. The method of claim 8 , wherein the at least one of the plurality of NLU models is selected based on the voice input corresponding to a specified intent includes:
identifying the at least one the plurality of NLU models corresponding to an intent determined by the user.