A study on intelligent dialogue agent for older adults' preventive care - Towards development of a comprehensive preventive care system

Abstract

Preventive care approaches have attracted much attention in Japan, which is one of the world's most super-aged societies. These approaches aim to decrease the number of people who require nursing care or other human support. Our research group has developed several kinds of preventive care systems, including a fall prevention system, a cognitive training system, and an Intelligent Dialogue Agent (IDA). In this paper, we focus on familiarizing older adults with the IDA - a conversational agent that encourages older adults to engage it in natural conversations, while monitoring their health in the process - and we introduce a Speech Content Coordinating Function (SCCF) to the IDA to further improve older adult's familiarity with and interest in the agent. We also have a plan to develop a Comprehensive Preventive Care System (CPCS) which can encourage proactive conversation and provide effective monitoring of older adults as well as habitual cognitive training. To evaluate the basic characteristics and impressions of the CPCS, a prototype version that consists of the IDA and the Mechanism for Cognitive Training (MCT) is developed. The results of the experiments indicated that the SCCF can adequately adjust speech content depending on the user's circumstances. We also confirmed that the prototype CPCS achieves synergistic effects (e.g., more detailed monitoring of older adult's health condition, increased frequency of cognitive training) when its components are used together.