Host: The Japanese Society for Artificial Intelligence
Name : The 36th Annual Conference of the Japanese Society for Artificial Intelligence
Number : 36
Location : [in Japanese]
Date : June 14, 2022 - June 17, 2022
In a society where the number of elderly is increasing, it is necessary to train physiotherapists who are specialists in medical rehabilitation to support the independent lives of the elderly. To train novice physiotherapists efficiently, it is important to utilize the practical knowledge acquired from the practical experience of skilled physiotherapists. To respond to such demands, we proposed a method for acquiring and sharing practical knowledge to support novice physiotherapists in improving their observation and logical organization skills. The proposed method targets motion analysis texts in which a physiotherapist describes the results of analyzing problems by observing a patient walking. To represent and share practical knowledge, we defined the smallest unit of physiotherapist knowledge as a Problem-based Physiotherapy Unit (PBPU), extracted PDPUs from the text, and visualized them by focusing on the causal relationship between "observation" and "inference."We showed the obtained network to an experienced physiotherapist for qualitative evaluation. As a result, it was suggested that the visualization of the causal relationship between observation and inference using PBPU is effective in understanding the difference in logical structure caused by the presence or absence of practical knowledge in motion analysis.