Construction of an Intellectual Information System that Complements the "Care Knowledge" of Care Staff Using Natural Language and Demonstration at Care Facilities
| Project/Area Number |
17H01950
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Home economics/Human life
|
|---|
| Research Institution | Saga University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
大島 千佳 佐賀大学, 理工学部, 客員研究員 (10395147)
大村 廉 豊橋技術科学大学, 工学(系)研究科(研究院), 准教授 (10395163)
杉原 太郎 東京工業大学, 環境・社会理工学院, 准教授 (50401948)
|
|---|
| Project Period (FY) |
2017-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥17,810,000 (Direct Cost: ¥13,700,000、Indirect Cost: ¥4,110,000)
Fiscal Year 2020: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2019: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2018: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2017: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
|
|---|
| Keywords | 高齢者生活 / 介護支援 / 対話ロボット |
|---|
| Outline of Final Research Achievements |
We developed a system that complements the "care knowledge," which quickly notices the physical and mental condition of a care recipient and responds to them appropriately, of care staff in care homes. The developed sensor network to grasp the behavior of the care recipient was enabled to detect call actions to care staff with a high accuracy rate (F value: 89.6%). We also developed a learned model that can discriminate the sign of begin-to-talk actions based on coordinate data of characteristics points of the person (the precision ratio: 81%). The method will be useful to estimate the physical and mental condition of care recipients. Finally, we implemented a robot that can nod at an appropriate time in a conversation (accuracy rate: 98%). The robot is expected to become to appropriately intervene with the conversation among care recipients and caregivers.
|
| Academic Significance and Societal Importance of the Research Achievements |
高齢化による慢性的な人手不足，および，その解消方法が見つかっていない介護業界では，介護スタッフの負担を減らしつつ要介護者の心身の状態にいち早く気が付く技術が求められている．本研究では，カメラからの画像情報とマイクからの音声情報に基づき，人工知能を用いて，介護現場において重要な要介護者の心身の状態変化をいち早く検知するための要素技術を明らかにした．この技術により介護スタッフを支援することで，これまで人手不足のため気が付かれなかった要介護者の変化を人工知能が検知し，介護スタッフに提示できるようになる．この結果，介護スタッフの負担を減らしつつ，より良い介護を実現すると期待される．
|
Report
(5 results)
Research Products
(38 results)
