Method and system for processing user command to provide and adjust operation of electronic device by analyzing presentation of user speech

1. A non-transitory computer-readable recording medium storing instructions that, when executed by a processor of an electronic device, cause the processor to perform a user command processing method comprising:

managing at least one pre-defined operation to be performed according to a user command and a plurality of options preset in relation to each of the at least one pre-defined operation for modifying a corresponding pre-defined operation, wherein the corresponding pre-defined operation modified by one of the plurality of options performs a different operation than the corresponding pre-defined operation modified by another of the plurality of options;

receiving the user command including at least a voice input received from a user;

selecting an operation from the at least one pre-defined operation corresponding to a keyword extracted from the voice input;

determining at least one option according to a presentation of the voice input; and

performing the selected operation as modified by the determined at least one option.

2. The non-transitory computer-readable recording medium of claim 1 , wherein the determining of the at least one option comprises:

outputting information to receive, from the user, a selection of at least one option among the plurality of options, when the at least one option is indeterminable according to the presentation of the voice input; and

determining the at least one option among the plurality of options according to an additional voice input received in response to the output information.

3. The non-transitory computer-readable recording medium of claim 1 , wherein the performing of the selected operation comprises:

outputting information to receive, from the user, a confirmation on whether to continue performing the selected operation as modified by the determined at least one option;

receiving a first additional voice input in response to the output information; and

performing the selected operation as modified by the determined at least one option, when an answer for continuation consent is extracted from the first additional voice input.

4. The non-transitory computer-readable recording medium of claim 3 , wherein the performing of the selected operation comprises:

outputting information to receive, from the user, a selection of at least one other option among the plurality of options, when an answer for continuation refusal is extracted from the first additional voice input;

determining at least one other option among the plurality of options according to a second additional voice input received in response to the output information; and

performing the selected operation as modified by the determined at least one other option.

5. The non-transitory computer-readable recording medium of claim 1 , wherein the presentation of the voice input includes an expression representing a social relationship between a person associated with the selected operation and the user, and

the determining of the at least one option comprises determining from among the plurality of options based on the social relationship with the user which is analyzed according to the expression.

6. The non-transitory computer-readable recording medium of claim 5 , wherein the plurality of options corresponds to a plurality of devices interoperating with the electronic device,

the determining of the at least one option comprises determining at least one device associated with a person selected based on the social relationship with the user among the plurality of devices, and

the performing of the selected operation comprises performing the selected operation in association with the determined at least one device.

7. The non-transitory computer-readable recording medium of claim 5 , wherein the plurality of options corresponds to messenger accounts or phone numbers of other users having a personal relationship with the user,

the determining of the at least one option comprises determining a messenger account or phone number of another user selected based on the personal relationship with the user among the messenger accounts or phone numbers, and

the performing of the selected operation comprises performing the selected operation in association with the determined messenger account or phone number.

8. The non-transitory computer-readable recording medium of claim 1 , wherein the presentation of the voice input includes at least one of an urgency of a user command and a user emotion analyzed based on at least one of a manner of speaking and a tone of the user obtained through the voice input, and

the determining of the at least one option comprises determining from among the plurality of options based on at least one of the urgency of the user command and the user emotion.

9. The non-transitory computer-readable recording medium of claim 8 , wherein the plurality of options corresponds to characteristic classifications of contents to be associated with the selected operation or schemes of providing information related to the contents,

the determining of the at least one option comprises determining at least one classification among the characteristic classifications of the contents to be associated with the selected operation or determining at least one scheme among the schemes of providing information related to the contents based on at least one of the urgency of the user command and the user emotion, and

the performing of the selected operation comprises performing the selected operation in associated with the contents according to the determined at least one classification or the determined at least one scheme.

10. The non-transitory computer-readable recording medium of claim 1 , wherein the determining of the at least one option comprises determining the at least one option among the plurality of options by further utilizing situation data of the user, and

the situation data includes at least one of an instant message sent and received in association with a phone number of the user or a messenger account of the user and a facial expression of the user recognized through a camera included in the electronic device.

11. The non-transitory computer-readable recording medium of claim 1 , wherein the electronic device includes an artificial intelligence (AI) speaker configured to control devices included in a smart home by interoperating with the devices or provide contents according to the user command through the Internet.

12. The non-transitory computer-readable recording medium of claim 1 , wherein the user command processing method further comprises:

transmitting the voice input to a cloud AI platform connected to the electronic device through an interface connect; and

receiving, from the cloud AI platform, information related to at least one of the keyword extracted from the voice input, an operation recommended based on the extracted keyword, the option corresponding to the extracted keyword, and the option determined according to the presentation of the voice input.

13. A user command processing method, comprising:

managing at least one pre-defined operation to be performed according to a user command and a plurality of options preset in relation to each of the at least one pre-defined operation for modifying a corresponding pre-defined operation, wherein the corresponding pre-defined operation modified by one of the plurality of options performs a different operation than the corresponding pre-defined operation modified by another of the plurality of options;

receiving the user command including at least a voice input received from a user;

selecting an operation from the at least one pre-defined operation corresponding to a keyword extracted from the voice input;

determining at least one option according to a presentation of the voice input; and

performing the selected operation as modified by the determined at least one option.

14. The user command processing method of claim 13 , wherein the presentation of the voice input includes an expression representing a social relationship between a person associated with the selected operation and the user, and

the determining of the at least one option comprises determining from among the plurality of options based on the social relationship with the user which is analyzed according to the expression.

15. The user command processing method of claim 14 , wherein the plurality of options corresponds to a plurality of devices interoperating with an electronic device,

the determining of the at least one option comprises determining at least one device associated with a person selected based on the social relationship with the user among the plurality of devices, and

the performing of the selected operation comprises performing the selected operation in association with the determined at least one device.

16. The user command processing method of claim 13 , wherein the presentation of the voice input includes at least one of an urgency of a user command and a user emotion analyzed based on at least one of a manner of speaking and a tone of the user obtained through the voice input, and

the determining of the at least one option comprises determining from among the plurality of options based on at least one of the urgency of the user command and the user emotion.

17. The user command processing method of claim 16 , wherein the plurality of options corresponds to characteristic classifications of contents to be associated with the selected operation or schemes of providing information related to the contents,

the determining of the at least one option comprises determining at least one classification among the characteristic classifications of the contents to be associated with the selected operation or determining at least one scheme among the schemes of providing information related to the contents based on at least one of the urgency of the user command and the user emotion, and

the performing of the selected operation comprises performing the selected operation in associated with the contents according to the determined at least one classification or the determined at least one scheme.

18. A user command processing system, comprising:

at least one processor implemented to execute computer-readable instructions,

wherein the at least one processor is configured to:

manage at least one pre-defined operation to be performed according to a user command and a plurality of options preset in relation to each of the at least one pre-defined operation for modifying a corresponding pre-defined operation, wherein the corresponding pre-defined operation modified by one of the plurality of options performs a different operation than the corresponding pre-defined operation modified by another of the plurality of options,

receive the user command including at least a voice input received from a user,

select an operation from the at least one pre-defined operation corresponding to a keyword extracted from the voice input,

determine at least one option according to a presentation of the voice input, and

perform the selected operation as modified by the determined at least one option.

19. The user command processing system of claim 18 , wherein the presentation of the voice input includes an expression representing a social relationship between a person associated with the selected operation and the user, and

the at least one processor is configured to determine the at least one option among the plurality of options based on the social relationship with the user which is analyzed according to the expression.

20. The user command processing system of claim 18 , wherein the presentation of the voice input includes at least one of an urgency of a user command and a user emotion analyzed based on at least one of a manner of speaking and a tone of the user obtained through the voice input, and

the at least one processor is configured to determine the at least one option among the plurality of options based on at least one of the urgency of the user command and the user emotion.