中文摘要：

三维虚拟环境被广泛的应用于各个领域并发展成为了一个故事表达的新媒介，然而如何构建这类的虚拟环境仍需要专业人士，这在一定程度上限制了虚拟环境技术的应用。由于意识到以传统的菜单界面为主的三维场景制作软件的局限性，采用自然语言为用户界面的三维虚拟环境制作技术受到了研究者的重视。本文介绍了一种方法，该方法通过基于文字的输入并对环境的视觉特征进行操作，进而能使非专业人员制作一个可交互的三维虚拟环境。我们提出了将文字的含义作为视觉再现的主要资源，这种文字 - 概念 - 视觉信息的直接联想模式可用来对知识的再现展示，建立一个可扩展的视觉语义的数据表现模型中间层的来联结语 言含义和视觉图形的再现。

英文摘要：

The increasing developments of 3D virtual environment as a popular concept have been used in a variety of ways and it also appears as a new medium for storytelling. But how to build this kind of virtual environment still lies in the domain of highly skilled professionals and limit their benefits. As real-time graphics applications of future become more complex, the possibilities for integrating a natural language has been considered in improved virtual environment user-interfaces. This paper introduces an approach that enables non- professionals to create an interactive 3D virtual scene through manipulating visual features of the aspects of environment by using language based input. The meaning of the words is considered as a primitive resource for visualization, and this direct association word-concept- visual is used for knowledge representations. An original extendable intermediate visual semantic representation provides a link between meaning of natural language and graphic visualization.