Methods and systems for recommending dialogue sticker based on similar situation detection

• US 9,792,909 B2
• Filed: 07/14/2015
• Issued: 10/17/2017
• 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
• Primary Examiner(s): ADESANYA, OLUJIMI A
• Application Number:
  US14/799,560
• Publication Number:
  US 20160210117A1
• Time in Patent Office: 826 Days
• Field of Search: 704 9
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04M 1/7243 with interactive means for internal management of messages

Abstract

Provided is a method of recommending a dialogue sticker through similar situation retrieval. The method includes: generating dialogue situation information on the last utterances of the first user terminal and the second user terminal; retrieving a candidate situation having the most similar context from a dialogue situation information database, the situation including a plurality of continuous utterances; acquiring sticker information from pairs of utterance-sticker derived from the retrieved candidate situation and providing the sticker information for the first user terminal.

Claims

1. A method of recommending a dialogue sticker through similar situation retrieval by use of a server that is connected to a first user terminal and a second user terminal through a network and relays an utterance inputted to a messenger between the first user terminal and the second user terminal, the utterance including at least one of a text and an image, the method comprising:

generating a dialogue situation information database that includes multiple situations, each of the situations including a plurality of pairs that each include an utterance and a sticker, the utterances in each of the situations including a plurality of contiguous utterances from two terminals;

generating dialogue situation information based on utterances that include a last utterance of the first user terminal and a last utterance of the second user terminal;

retrieving a candidate situation having a most similar context as the generated dialogue situation information from the dialogue situation information database;

determining whether the first user terminal is in a speaker utterance situation or a response utterance situation;

retrieving, from the candidate situation, a pair that includes a speaker utterance when the first user terminal is in the speaker utterance situation and retrieving, from the candidate situation, a pair that includes a response utterance when the first user terminal is in the response utterance situation; and

providing the sticker in the retrieved pair on a display device of the first user terminal.

2. A non-transitory computer readable medium storing one or more sequences of pattern data for recommending a dialogue sticker by use of a server that is connected to a database, a first user terminal and a second user terminal through a network and relays an utterance inputted to a messenger between the first user terminal and the second user terminal, the utterance including at least one of a text and an image, wherein execution of the one or more sequences of the pattern data by one or more processors causes the one or more processors to perform the steps of:

generating a dialogue situation information database that includes multiple situations, each of the situations including a plurality of pairs that each include an utterance and a sticker, the utterances in each of the situations including a plurality of contiguous utterances from two terminals;

generating dialogue situation information based on based on utterances that include a last utterance of the first user terminal and a last utterance of the second user terminal;

retrieving a candidate situation having a most similar context as the generated dialogue situation information from the dialogue situation information database;

determining whether the first user terminal is in a speaker utterance situation or a response utterance situation;

retrieving, from the candidate situation, a pair that includes a speaker utterance when the first user terminal is in the speaker utterance situation and retrieving, from the candidate situation, a pair that includes a response utterance when the first user terminal is in the response utterance situation; and

providing the sticker in the retrieved pair on a display device of the first user terminal.

3. The non-transitory computer readable medium of claim 2, wherein the retrieving of the candidate situation comprises retrieving a situation having continuous utterances that match a flow of dialogue act of the last utterances inputted by the first and second user terminals from the dialogue situation information database.

4. The computer program non-transitory computer readable medium of claim 3, wherein the retrieving of the candidate situation comprises retrieving a situation that matches a relationship between a first user of the first user terminal and a second user of the second user terminal from the dialogue situation information database when inferring the relationship between the first user and the second user from the generated dialogue situation information.