METHODS AND SYSTEMS FOR RECOMMENDING RESPONSIVE STICKER

• US 20160210116A1
• Filed: 07/14/2015
• Published: 07/21/2016
• Est. Priority Date: 01/19/2015
• Status: Active Grant

• Current Assignee: NCSoft Corporation
• Original Assignee: NCSoft Corporation
• Inventors: Kim, Taek Jin, Lee, Jay June, Jang, Jungsun, Chung, Sehee, Lee, Kyeong Jong, Lee, Yeonsoo
• Granted Patent: US 9,626,152 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

Provided are a method and a computer program of recommending a responsive sticker. The method includes: generating dialogue situation information by analyzing pairs of the last utterance of a second user and previous utterances and previous utterances of a first user as an utterance of the second user terminal is inputted into the server; determining a similar situation from a dialogue situation information database that is already collected and constructed, using the generated dialogue situation information; determining whether it is a turn for the first user terminal to input a response; selecting a responsive sticker candidate group from the determined similar situation when it is a turn for the first user terminal to input the response; and providing information on at least one responsive sticker of the responsive sticker candidate group for the first user terminal.

Claims

1. A method of recommending a responsive sticker, comprising:

by a server connected to a first user terminal and a second user terminal through a network,

generating dialogue situation information by analyzing pairs of the last utterance of a second user—

in this case, the last utterance of the second user including a text type of dialogue contents—

and previous utterances and previous utterances of a first user as an utterance of the second user terminal is inputted into the server;

determining a similar situation from a dialogue situation information database that is already collected and constructed, using the generated dialogue situation information;

determining whether it is a turn for the first user terminal to input a response;

selecting a responsive sticker candidate group from the determined similar situation when it is a turn for the first user terminal to input the response; and

providing information on at least one responsive sticker of the responsive sticker candidate group for the first user terminal.

2. The method of claim 1, wherein the dialogue situation information comprises dialogue act information, emotion information, keywords of a certain number of previous utterances of the first user and the last utterance and a certain number of previous utterances of the second user.

3. The method of claim 1, wherein the determining of the similar situation comprises determining a dialogue in which the dialogue situation information generated from the dialogue situation information database is similar to the flow of dialogue act information or the flow of emotion information as a similar situation.

4. The method of claim 3, wherein the determining of the similar situation comprises retrieving a dialogue in which the flow of dialogue act information or the flow of emotion information corresponding to pairs of dialogue act information or emotion information of the last utterance and the previous utterances of the second user and the previous utterances of the first user.

5. The method of claim 3, wherein in the dialogue that is determined as the similar situation, when an utterance corresponding to the last utterance of the second user terminal is an utterance that starts a theme, it is determined that it is a turn for the first user terminal to input a response.

6. The method of claim 3, wherein in the dialogue that is determined as the similar situation, when there exists an utterance corresponding to a response immediately after an utterance corresponding to the last utterance of the second user terminal, it is determined that it is a turn for the first user terminal to input a response.

7. The method of claim 3, wherein a dialogue act category of the last utterance of the second user terminal has a certain value, it is determined that it is a turn for the first user terminal to input a response.

11. The method of claim 1, wherein the providing of information for the first user terminal comprises displaying the recommended sticker on a screen of the first user terminal at the same time when a dialogue input window is selected by a user of the first user terminal.

12. The method of claim 5, wherein the providing of information for the first user terminal comprises displaying the recommended sticker on a screen of the first user terminal at the same time when a dialogue input window is selected by a user of the first user terminal.

13. The method of claim 1, wherein the providing of information for the first user terminal comprises displaying the recommended sticker and a send button on a screen of the first user terminal immediately after the last utterance of the second user terminal is sent to the first user terminal.

14. The method of claim 5, wherein the providing of information for the first user terminal comprises displaying the recommended sticker and a send button on a screen of the first user terminal immediately after the last utterance of the second user terminal is sent to the first user terminal.

8. A method of recommending a responsive sticker, comprising:

by a server connected to a first user terminal and a second user terminal through a network,

generating dialogue situation information by analyzing pairs of the last utterance of a second user—

in this case, the last utterance of the second user including only a sticker—

and previous utterances and previous utterances of a first user as an utterance of the second user terminal is inputted into the server;

determining a similar situation from dialogues of a dialogue situation information database that is already constructed, using the generated dialogue situation information;

determining whether it is a turn for the first user terminal to input a response, using a result of the similar situation determination;

selecting a responsive sticker candidate group matching with the determined similar situation when it is a turn for the first user terminal to input the response; and

providing information on at least one responsive sticker of the responsive sticker candidate group for the first user terminal.

9. The method of claim 8, wherein the generating of the dialogue situation information comprises generating dialogue situation information from metadata of a sticker comprised in the last utterance of the second user.

10. The method of claim 8, wherein the metadata of the sticker have values corresponding to at least one of keywords, dialogue act information and emotion information, and

the generating of the dialogue situation information comprises generating dialogue situation information by substituting the values of the metadata of the sticker with the dialogue act information, the emotion information and the keywords, respectively.

15. A computer program recorded in a recoding medium comprising commands for executing a method of recommending a responsive sticker on a computer, the method comprising:

generating dialogue situation information by analyzing pairs of the last utterance of a second user—

in this case, the last utterance of the second user including a text type of dialogue contents—

and previous utterances and previous utterances of a first user as an utterance of the second user terminal is inputted into the server;

determining a similar situation from dialogues of a dialogue situation information database that is already constructed, using the generated dialogue situation information;

determining whether it is a turn for the first user terminal to input a response, using a result of the similar situation determination;

selecting a responsive sticker candidate group matching with the determined similar situation when it is a turn for the first user terminal to input the response; and

providing information on at least one responsive sticker of the responsive sticker candidate group for the first user terminal.

16. A computer program recorded in a recoding medium comprising commands for executing a method of recommending a responsive sticker on a computer, the method comprising:

generating dialogue situation information by analyzing pairs of the last utterance of a second user—

in this case, the last utterance of the second user including only a sticker—

and previous utterances and previous utterances of a first user as an utterance of the second user terminal is inputted into the server;

determining a similar situation from dialogues of a dialogue situation information database that is already constructed, using the generated dialogue situation information;

determining whether it is a turn for the first user terminal to input a response, using a result of the similar situation determination;

selecting a responsive sticker candidate group matching with the determined similar situation when it is a turn for the first user terminal to input the response; and

providing information on at least one responsive sticker of the responsive sticker candidate group for the first user terminal.