| Project/Area Number |
15K00154
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Multimedia database
|
|---|
| Research Institution | Iwate Prefectural University |
|---|
Principal Investigator |
Kurematsu Masaki 岩手県立大学, ソフトウェア情報学部, 准教授 (00305286)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 自然言語処理 / ラフセット理論 / 文書分類 / 特許処理 / ラフセット / 特許情報 / 情報検索 |
|---|
| Outline of Final Research Achievements |
It is important to research exists patents before submitting own patents or saleing new products. However, it is take long time to check a lot of patents. In this research, I propose a framework in order to this task. This framework estimates decision rules from labeled patent journals using Rough Set Theory and estimates a category from unlabeled patents using these rules.
At first, this framework extracts terms from abstracts of labeled patents in advance. Next, it selects terms based on document frequency and makes a Document Term Matrix. After that, it makes decision rules by Rough Set Theory. Finally, it estimates a category using these rules.
In order to evaluate this approach, I did experiments with an expert. In this experiment, this system could estimate correct categories from most of patents. However, the performance of this method is similar as exists methods. In order to enhance this system, I should to enhance term selection and evaluate new idea.
|
