Agent-based Intelligent Messaging Systems, Natural Language Generation, Markov Decision Processes, Verification, Machine Learning

基于代理的智能消息系统、自然语言生成、马尔可夫决策过程、验证、机器学习

• 批准号: 520347-2017
• 负责人: Bentahar, Jamal
• 金额: $ 4.48万
• 依托单位: Concordia University
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2018
• 资助国家: 加拿大
• 起止时间: 2018-01-01 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=645200
• 关键词: Agent; based; Intelligent; Messaging; Systems

This project addresses the design and development of an intelligent messaging system used as an interactive tutoring module. The objectives of the project are: (1) to specify, develop, and verify software design of the rational agents to deploy Natural Language Generation (NLG) while interacting with human learners; (2) develop real-time decision making and reinforcement learning to empower agents to better interact with learners and carry on a productive conversation; and (3) enable intelligent guidance and perform real time messaging mechanisms that effectively navigate through a logic decision tree.

本计画旨在设计与开发一个智慧型讯息系统，做为互动式教学模组。该项目的目标是：（1）指定，开发和验证理性代理的软件设计，以在与人类学习者交互时部署自然语言生成（NLG）;（2）开发实时决策和强化学习，使代理能够更好地与学习者交互并进行富有成效的对话;以及（3）实现智能引导并执行有效地导航通过逻辑决策树的真实的时间消息传递机制。