2023 Fiscal Year Final Research Report
A carputer to support a car trip by adapting to the individual
| Project/Area Number |
19K12548
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 80020:Tourism studies-related
|
|---|
| Research Institution | Tottori University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2019-04-01 – 2024-03-31
|
| Keywords | 観光振興 / 自動車旅行 / 車載器 / 自然言語処理 / 個人適応 / 音声入力 / 立ち寄り推薦 |
|---|
| Outline of Final Research Achievements |
This research develops a carputer that improves car trip experience. Since user's personal information is stored only in the carputer, the carputer services can refer detailed information about user, such as driving tendency and habits at the destination. The natural language interface developed in this research allows users to easily operate the services in the vehicle by voice. By inferring the user's common activities, the operation cost is reduced. Regarding the recommendation service for extra trip spots, area restriction is newly developed. The restriction is based on the driving situation, which includes personal information extracted from the dialogue, as well as the user's explicit requests. As the results of experiments based on actual trip logs, it was confirmed that the accuracy of the restriction is 92% of the recommendation scenes.
|
| Free Research Field |
知能情報学
|
| Academic Significance and Societal Importance of the Research Achievements |
社会的意義：自動車旅行への情報支援技術の開発は，国内旅行で盛んに利用される自動車の体験が改善され観光振興につながる．個人的情報が車載器内のみに蓄積される設計である．外部への情報流出の懸念がない技術の可能性が示された．
学術的意義：車内での音声操作に向けて，正確性および資源性（小型計算機で動作可能）の優れた発話文解析の手法が示された．ユーザによる入力の負担を軽減すべく，個人情報を利用しユーザのことを推定しながらの対話処理が示された．自動車旅行中の立ち寄り推薦において，ユーザ個人だけの情報を用いるルール型コンテンツベースの手法が示された．
|
