Apparatus, server, and method for providing conversation topic

1. A device comprising:

a display;

a memory storing one or more instructions; and

a processor configured to executing the one or more instructions to:

convert voice data of a conversation of a user into text during the conversation of the user;

determine at least one keyword from the text;

obtain detail information by searching for the at least one keyword and collecting information corresponding to interests of the user from a searched result;

determine conversation topics related to the at least one keyword using a user interest model and the at least one keyword; and

control the display to display both the detail information and the determined conversation topics during the conversation of the user,

wherein the user interest model is generated by using information of the user and comprises a plurality of topic candidates.

2. The device of claim 1 , wherein the processor is further configured to determine sub topics which correspond to a sub concept of the at least one keyword, and determine related topics which correspond to a concept equivalent to the at least one keyword in consideration of the information of the user.

3. The device of claim 1 , wherein the conversation topics are determined by inputting the at least one keyword into the user interest model.

4. The device of claim 1 , wherein the processor is configured to control the display to display, when the user selects one of the displayed conversation topics, the selected display conversation topic as the detail information.

5. The device of claim 1 , wherein the user interest model being updated by correcting a weight given to each of the plurality of topic candidates when the information of the user is updated.

6. The device of claim 1 , wherein, when a word such as a place, time, or a person is detected from the text, the processor is configured to determine the word indicating the place, the time, or the person as the at least one keyword.

7. The device of claim 6 , wherein the processor is configured to search for a word identical to the word indicating the place, the time, or the person in an SMS or SNS message of the user, and determine the SMS or SNS message of the user including the identical word as the detail information with respect to the at least one keyword.

8. The device of claim 1 , wherein the processor is configured to extract the information corresponding to the interests of the user from the searched result, and reconfigure the extracted information.

9. The device of claim 1 , wherein the processor is configured to control the display to display previous detail information that was previously obtained and displayed,

wherein the previous detail information is displayed to be smaller than the displayed previous detail information.

10. The device of claim 1 , wherein the processor is configured to control the display to display the detail information in a largest display region and the conversation topics on a lowermost display region.

11. A method performed by a device, the method comprising:

converting voice data of a conversation of a user into text during the conversation of the user;

determining at least one keyword from the text;

obtaining detail information by searching for the at least one keyword and collecting information corresponding to interests of the user from a searched result;

determining conversation topics related to the at least one keyword using a user interest model and the at least one keyword; and

displaying both the detail information and the determined conversation topics during the conversation of the user,

wherein the user interest model is generated by using information of the user and comprises a plurality of topic candidates.

12. The method of claim 11 , wherein the determining the conversation topics comprises: determining sub topics which correspond to a sub concept of the at least one keyword; and

determining related topics which correspond to a concept equivalent of the at least one keyword in consideration of the information of the user.

13. The method of claim 11 , wherein the conversation topics are determined by inputting the at least one keyword into the user interest model.

14. The method of claim 11 , further comprising displaying, when the user selects one of the displayed conversation topics, the selected conversation topic as the detail information.

15. The method of claim 11 , wherein the user interest model being updated by correcting a weight given to each of the plurality of topic candidates when the information of the user is updated.

16. The method of claim 11 , wherein when a word such as a place, time, or a person is detected from the text, the determining the at least one keyword comprises determining the word indicating the place, the time, or the person as the at least one keyword.

17. The method of claim 16 , wherein the obtaining the detail information comprises:

searching for a word identical to the word indicating the place, the time, or the person in an SMS or SNS message of the user; and

determining the SMS or SNS message of the user including the identical word as the detail information with respect to the at least one keyword.

18. The method of claim 11 , wherein the obtaining the detail information comprises:

extracting the information corresponding to the interests of the user from the searched result; and

reconfiguring the extracted information.

19. The method of claim 11 , further comprising displaying previous detail information that was previously obtained and displayed,

wherein the previous detail information is displayed to be smaller than the displayed previous detail information.

20. The method of claim 11 , wherein the displaying both the detail information and the determined conversation topics comprises displaying the detail information in a largest display region and the conversation topics on a lowermost display region.