Multiagent decision methods for innovative solutions to environmental management and personalized e-service problems

本研究计划旨在发展多智能体决策技术，以创造性地解决环境管理和个性化电子服务问题。代理可以是人类决策者，也可以是自主软件代理。更具体地说，将设计正式的多智能体决策方法和支持这些技术的计算机化系统。本研究计划主要由两部分组成：开展社会环境系统可持续管理研究和设计网络用户导航数据挖掘方法以开发个性化电子服务。首先，基于参与式技术、系统思维和适应性管理，将构建新的环境管理方法和工具，以解决以冲突、复杂性、深度不确定性和风险为特征的复杂社会环境系统问题。其次，将设计挖掘网络用户（客户）导航数据的技术和原型系统，以开发个性化的电子服务，提高客户满意度和客户忠诚度，并提供以客户为中心的服务。环境管理、电子服务、电子商务和其他领域的实际决策问题将利用新的决策技术进行研究。本研究所发展的决策技术，可协助决策者处理多主体决策问题，并可为社会环境问题的永续管理的实务人员、研究人员和决策者所利用，并可改善从事电子服务和电子商务的企业的绩效。研究生将被训练创建多智能体决策技术，开发决策支持系统，和/或应用新的和改进的技术来解决具有挑战性的工程问题。

The proposed research program aims to develop multiagent decision making techniques for creatively addressing environmental management and personalized e-service problems. Agents can be human decision makers or autonomous software agents. More specifically, formal multiagent decision methods and computerized systems to support these techniques will be designed. The proposed research program is composed of two main components: carrying out research on sustainable management of societal-environmental systems and devising methods for mining Web users' navigational data to develop personalized e-service. First, novel environmental management approaches and tools will be constructed based on participatory techniques, systems thinking, and adaptive management, for tackling complex societal-environmental system problems which are characterized by the presence of conflict, complexity, and deep uncertainty and risks. Second, techniques and prototype systems for mining Web users' (customers') navigational data for developing personalized e-service to enhance customer satisfaction and customer loyalty and to provide customer-centric services, will be devised. Practical decision problems in environmental management, e-service, e-commerce, and other areas will be studied utilizing new decision making techniques. The decision technologies developed in the proposed research can be used to assist decision makers who are involved in multiagent decision problems and can be utilized by practitioners, researchers, and decision makers in sustainable management of societal-environmental problems, and to improve the performance of firms engaged in providing e-service and e-commerce. Graduate students will be trained to create multiagent decision techniques, develop decision support systems, and/or apply the new and improved techniques to challenging engineering problems.