2021 Fiscal Year Final Research Report
A study of a method to collect the properties of a person who to talk to from light conversation
Project/Area Number |
19K12073
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 61020:Human interface and interaction-related
|
Research Institution | Aichi Institute of Technology |
Principal Investigator |
|
Project Period (FY) |
2019-04-01 – 2022-03-31
|
Keywords | 雑談 / 人工対話 / 年齢推定 / 距離推定 / 人物分類 / 関係性分析 / 感情推定 |
Outline of Final Research Achievements |
In this research, we started on two main themes. One is a technique for estimating the attributes of the talk pertner from the contents of chats in artificial dialogue systems. We proposed an event history collection system that converts the date and time of occurrence from historical events contained in the chat dialogue, and constructed a chat generation mechanism that can be used on LINE and Chatwork. The other is a technique for obtaining peripheral information the talk pertner, which is necessary for dialogue between a computer system and a human being. We mainly examined the basic technique for estimating the distance around the entire circumference using two omnidirectional cameras.
|
Free Research Field |
教育工学
|
Academic Significance and Societal Importance of the Research Achievements |
本研究では,人工的な対話が可能なインターフェイスを試作し,対話を進めることで相手の属性の一部を推定することが可能であることを示した.また,話し相手の周辺の情報を収集するための距離推定手法の提案も行った. これらの成果によって人工的な雑談型対話システムにおける機能性の向上が期待できる.意図的な質問をすることなく雑談を交わす中で話し相手の経歴や出自を含めた人間的な背景、現在の会話環境を知ることで,様々なサービスにおいて相手をより満足させる提案が可能となる.
|