从感性的视角进行创新产品研发（即感性工程）将对我国制造转型升级产生深远影响。本项目研究互联网环境下产品在线评论驱动的不确定性动态感性工程。首先，以产品在线评论为切入点，通过情感分析的方法来获得产品的感性属性结构及其评价信息；其次，基于DST证据理论和马尔科夫链模型来构建以KANO模型形式表示的消费者不确定性动态感性偏好模型；再次，基于DST证据理论来构建不确定性动态QFD模型以获得产品物理属性的优先权演化特性；然后，依据感性属性和物理属性的演化特性，构建不确定性动态感性新产品研发模型，以获得“物理属性-感性属性”之间以不确定性自然语言形式表达的动态定量关系；最后，以智能手机产品为案例，探讨面向目标产品的不确定性动态感性新产品研发支持方案。该研究能为企业提供敏捷感性新产品研发模式，发现感性新产品研发中消费者感性偏好的动态变化，实现需求驱动的感性创新产品研发；提供知识表示能力更强的模型和方法。

Kansei based new product development (NPD), also known as Kansei Engineering (KE), will play a great role in the transformation and upgrading of China’s manufacturing industry. This study focuses on online reviews driven uncertain dynamic KE under the Internet environment. To do so, the online reviews are firstly used to derive products’ Kansei attributes and Kansei evaluations. Secondly, an uncertain dynamic KANO model is built to derive the levels of Kansei needs, the priority information of Kansei needs, and their dynamic evolutions, based on the evidence theory and Markov chain model. Thirdly, an uncertain dynamic QFD model is built to obtain the dynamic evolutions of products’ physical attributes, based on the evidence theory and Markov chain model. Fourthly, according to the dynamic evolutions of Kansei attributes and physical attributes, an uncertain linguistic decision tree model is built to derive the uncertain dynamic relationships between physical attributes and Kansei attributes, so as to derive an uncertain dynamic Kansei NPD methodology. Finally, a case study of mobile phones is used to illustrate the proposed study. The proposed study is able to (1) help enterprises conduct agile and lean Kansei NPD; (2) discover the dynamic changes of customer needs and realize the customer needs driven Kansei NPD; (3) provide direct, transparent and easily understood models with a high-level knowledge representation framework and better Kansei decision support to designers.