公开(公告)号：US20150193505A1

公开(公告)日：2015-07-09

申请号：US14260828

申请日：2014-04-24

Applicant: Electronics and Telecommunications Research Institute

Inventor： Pum-Mo RYU ,  Hyun-Ki KIM ,  Sang-Kyu PARK ,  Yong-Jin BAE ,  Jeong HEO ,  Hyo-Jung OH ,  Chung-Hee LEE ,  Soo-Jong LIM ,  Myung-Gil JANG ,  Mi-Ran CHOI ,  Yoon-Jae CHOI ,  Yeo-Chan YOON ,  Yo-Han JO

IPC: G06F17/30

CPC classification number: G06F17/30864 ,  G06F17/30657

Abstract: The present invention is to provide an apparatus for searching information based on Wikipedia's contents comprising: a document converting part extracting fulltext documents, section title documents, info-box documents, category documents and definition statement documents from Wikipedia original documents and generating at least one of Wikipedia documents for questions and answers; a document indexing part analyzing the Wikipedia document for questions and answers, extracting POS-based index terms from the Wikipedia document for questions and answers, and generating a Wikipedia document index for questions and answers; a question analyzing part receiving a natural language question, analyzing a question pattern, an answer pattern and a question focus from the natural language question, and extracting document search keywords; a document searching part performing document search by using the document search keywords from the Wikipedia document index for questions and answers and generating document search result from each Wikipedia document index for questions and answers; an answer extracting part extracting first answers by using information about the question pattern, the answer pattern and the question focus from the document search result; and an answer integrating part integrating and prioritizing the first answer and generating a second answer.

Abstract translation: 本发明提供一种基于维基百科内容搜索信息的装置，包括：从维基百科原始文档中提取全文文件，部分标题文档，信息文件，类别文档和定义声明文档的文档转换部分，并且生成以下各项中的至少一个： 维基百科文件提问和答案; 分析维基百科文档中的问题和答案的文档索引部分，从维基百科文档中提取基于POS的索引条款以获取问题和答案，以及生成维基百科文档索引的问题和答案; 接收自然语言问题的问题分析部分，分析问题模式，答案模式和自然语言问题的问题焦点，提取文档搜索关键词; 通过使用维基百科文件索引中的文档搜索关键字进行文本搜索以获取问题和答案的文档搜索部分，并从每个维基百科文档索引生成用于问题和答案的文档搜索结果; 通过使用关于问题模式的信息，答案模式和来自文档搜索结果的问题焦点来提取第一答案的答案提取部分; 以及一个整合部分的答案，整合并优先考虑第一个答案并产生第二个答案。