Rresearch‎ > ‎

CSE Tools

 CTA Interviewer Agent(インタビューエージェント)

インタビューは他人から情報を引き出すために良く用いられる方法であるが,これを実際に準備,実施するには非常に労力がかかるだけでなく,スキルも必要とされる.エキスパートの状況認識や意思決定などの認知的側面を分析することはCognitive Task Analysis (CTA:認知タスク分析)と呼ばれ,インタビューが頻繁に用いられる.本研究では,このCTAを自動で行うエージェントの開発を行っている.対話エージェントの技術に1)インタビュー技法(Critical Decision Method),会話研究における発話機能や出現パターンに関する知見,3)熟練インタビュアのノウハウ,を実装し,「災害時の看護活動における情報処理行動」に関するインタビュー等の様々な課題に適用して人間に劣らない情報獲得効率を確認している.本研究では単にインタビュアの代行ツールの開発を目的としているだけではなく,対話分析ツールとして用いることも目的としている.エージェントの応答に対する人が感じる違和感に注目,分析することによって,人がなぜエージェントの対話に違和感を抱くのか,自然な対話とは何か,といった対話の暗黙コードに関する研究も行っている.

A chat-based interviewer agent to elicit know-how of subject matter experts(SMEs) was developed. This agent automatically generates questions and responses to the answers from the human interviewee. This automatic response is based on the shallow intelligence or artificial non-intelligence incorporating an interview method of cognitive task analysis as well as pattern matching to the dialogue characteristics specific to interview dialogues. A four-layered framework was proposed for the evaluation of the interviewer agent. The agent was tested with 6 SMEs and evaluated by the proposed framework. The result showed that the agent effectively elicited experts' knowledge while it still has a limitation in generating natural human like responses.


System Architecture
Dialogue Example

Integrating Simulation and Persona Method(ペルソナ自動作成)


This study is to propose a method to integrate human modeling and simulation with persona method in order to efficiently predict human behavior with different personalities under various situations. We applied the method to predict residents’ behavior in an emergency situation for designing emergency announcement strategies and confirmed that this method semi-automatically constructed several different personas and their behavior scenarios successfully. This method provides a systematic procedure to create personas and is expected to reduce time and cost for designing process. One of the disadvantages in human modeling and simulation as used in this study was that it is virtually impossible to validate it because of the lack of actual data to compare with. It is therefore difficult to directly apply this method to predicting human behavior for the serious issues like in the case study that require critical decision makings. Because however the proposed method utilizes the simulation as a means to create a resident scenario for a persona, the disadvantage becomes less critical. That is, because a persona aims to stimulate designer’s imagination to predict human behavior and to find potential problems, a resident scenario is not required high reliability. In that sense, the proposed method is an example to utilize less reliable human modeling and simulation for a real-life and practical problem.