| Project/Area Number |
19500096
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | Kanagawa Institute of Technology |
|---|
Principal Investigator |
CHEN Yukio Kanagawa Institute of Technology, 情報学部, 教授 (10282344)
|
|---|
| Project Period (FY) |
2007 – 2009
|
| Project Status |
Completed (Fiscal Year 2009)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2009: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2008: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2007: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
|---|
| Keywords | 情報検索 / 情報システム / 検索システム / 文書検索 / 問い合わせ意図 / ベクトル空間 / 学習機能 / 情報機器 |
|---|
| Research Abstract |
With the rapid increase in utilization of information systems, digitalized information has increased dramatically. It is important to develop information retrieval system with high retrieval accuracy. In particular, it is desired to develop the information retrieval system with the mechanism to increase the retrieval accuracy by learning the retrieval characteristic of users during the retrieving processing. In this research, study and development are performed in order to develop a retrieval system with high retrieval accuracy along users' retrieval intentions based on the principle referred to as "potential conversation background" that is unconsciously used when people talking to each other. As the research results, we obtained the method of extracting users' retrieval intention, the method of performing information retrieval based on user's retrieval intention and the method of learning user's retrieval intention in order to increasing retrieval accuracy. In the same time, the effectiveness of these methods was demonstrated on the developed experimental system.
|
