A task manager using an ontological framework for a HARMS-based system

摘要

Recently, conversational interaction with technology has made its way into popular commercial use. Advancements in natural language processing have made that possible. Now, imagine a future where the average person can have a team of robots and smart devices working together to accomplish daily tasks and all one has to do is interact with the system naturally. For this theoretical team to exist, an interaction system must be developed that can translate utterances and autonomously organize and direct the agents into completing the task. This paper presents a task manager that uses on ontology to divide tasks into subtasks and finds the most capable agent to complete the task. The task manager is an extension of a robust dialogue manager that users can communication naturally with. Two ontologies were developed as initial steps towards a task manager for a multi-agent system. An experiment was conducted to test the combination of the dialogue manager and the task manager.