Method and apparatus for providing contents about conversation

Patent metadata

Field	Value
Publication number	US-9230543-B2
Application number	US-201213592615-A
Country	US
Kind code	B2
Filing date	Aug 23, 2012
Priority date	Dec 20, 2011
Publication date	Jan 5, 2016
Grant date	Jan 5, 2016

Abstract

Disclosed are a method and an apparatus for providing contents about conversation, which collect voice information from conversation between a user and another person, search contents on the basis of the collected voice information, and provide contents about the conversation between the user and the person. The method of providing contents about conversation includes: a voice information collecting step of collecting voice information from conversation between a user and another person; a keyword creating control step of creating search keywords by using the collected voice information; and a contents providing control step of searching contents by using the created search keywords, and providing the searched contents.

First claim

What is claimed is:

1. A method of providing contents about conversation, comprising using voice recognition technology to perform the following steps:
a voice information collecting step of collecting voice information from conversation between a user and another person;
a keyword creating control step of creating search keywords by using the collected voice information; and
a contents providing control step of searching contents by using the created search keywords, and providing the searched contents;
wherein the keyword creating control step includes a morpheme extracting step of extracting morphemes from the collected voice information;
wherein the keyword creating control step further includes a subject word extracting step of extracting subject words relating to the conversation subject between the user and the person from the morphemes extracted in the morpheme extracting step, based on Ontology;
wherein the keyword creating control step further includes a subject word mapping step of mapping the subject words extracted in the subject word extracting step into representative words corresponding to the meanings of the subject words; and
wherein the keyword creating control step further includes a search keyword creating step of selecting a point word from the mapped words and creating search keywords for contents by using the selected point word, in consideration of at least one of the relationship between the mapped words in the subject words mapped as the representative words in the subject word mapping step and the frequency in use of the subject words.

2. The method of claim 1 , wherein the voice information collecting step includes:
a voice information input step of receiving voice information from the conversation between the user and the person; and
an end point detection (EDP) detecting step of detecting the end point of the start of the utterance to find out sections of a sentence unit from the input voice information.

3. The method of claim 2 , wherein the voice information collecting step further includes a sentence divider collecting step of dividing the voice information in a sentence unit in accordance with the end point of the start of the utterance detected in the EPD detecting step, and collecting the voice information divided in a sentence unit.

4. The method of claim 1 , wherein the contents providing control step includes a contents searching step of searching the contents, based on a search engine based on Ontology, by using the created search keywords.

5. The method of claim 4 , wherein the contents providing control step further includes a contents providing step of asking the user in character or voice whether to be provided with the searched contents when there are contents searched in the contents searching step, and of providing the searched contents when the user consents to be provided with the searched contents.

6. An apparatus for providing contents about conversation, comprising:
a voice information collecting unit configured to collect voice information from conversation between a user and another person;
a keyword creating control unit configured to create search keywords by using the collected voice information; and
a contents providing control unit configured to search contents by using the created search keywords, and provide the searched contents;
wherein the keyword creating control unit includes a morpheme extracting unit configured to extract morphemes from the collected voice information;
wherein the keyword creating control unit further includes a subject word extracting unit configured to extract subject words relating to the conversation subject between the user and the person from the morphemes extracted by the morpheme extracting unit, based on Ontology;
wherein the keyword creating control unit further includes a subject word mapping unit configured to map the subject words extracted by the subject word extracting unit into representative words corresponding to the meanings of the subject words; and
wherein the keyword creating control unit further includes a search keyword creating unit configured to select a point word from the mapped words and create search keywords for contents by using the selected point word, in consideration of at least one of the relationship between the mapped words in the subject words mapped as the representative words by the subject word mapping unit and the frequency in use of the subject words.

7. The apparatus of claim 6 , wherein the voice information collecting unit includes:
a voice information input unit configured to receive voice information from the conversation between the user and the person; and
an EPD detecting unit configured to detect the end point of the start of the utterance to find out sections of a sentence unit from the input voice information.

8. The apparatus of claim 7 , wherein the voice information collecting unit further includes a sentence divider collecting unit configured to divide the voice information in a sentence unit in accordance with the end point of the start of the utterrance detected by the EPD detecting unit, and collect the voice information divided in a sentence unit.

9. The apparatus of claim 6 , wherein the contents providing control unit includes a contents searching unit configured to search the contents, based on a search engine based on Ontology, by using the created search keywords.

10. The apparatus of claim 9 , wherein the contents providing control unit further includes a contents providing unit configured to ask the user in character or voice whether to be provided with the searched contents when there are contents searched in the contents searching unit, and provide the searched contents when the user consents to be provided with the searched contents.

Assignees

• Kim Hyun
• Lee Kang Woo
• Suh Young Ho
• Kim Hyoung Sun
• Korea Electronics Telecomm

Inventors

• Kim Hyun
• Lee Kang Woo
• Suh Young Ho
• Kim Hyoung Sun

Classifications

• G06F17/30746

  Physics · mapped topic

• G10L15/1822 Primary

  Parsing for meaning understanding · CPC title

• G10L2015/088

  Word spotting · CPC title

• G10L25/54

  for retrieval · CPC title

• G06F3/16

  Sound input; Sound output (speech processing G10L) · CPC title