从用户需求语句建立问题可拓模型的研究

准确地建立待解决问题的可拓模型是可拓策略生成的关键步骤。目前的可拓策略生成系统在建立可拓模型时因自然语言理解的困难,未能充分理解用户需求,所以较难自动建立问题的可拓模型。提出了解析用户自然语言需求语句、并自动建立可拓模型的方法。该方法的核心包括4步:1)对用户需求语句进行组块分析得到短语序列;2)对短语序列进行分类;3)使用匹配规则抽取分类后的短语,得到便于计算机处理的需求信息;4)结合数据库技术进行可拓模型的建立。以租房问题为案例,实现了该方法。实验结果表明,该方法能较好地理解用户需求信息并成功建立租房问题可拓模型。

Research on building an extension model from user requirements

Building an effective extension model to solve a problem is a key step in generating an extension strategy. Due to the complexity of natural language processing, the current extension strategy generation system is insufficiently clear with respect to user requirements, so it is hard to automatically build an extension model. In this paper, we propose a method for parsing the user requirement sentence in order to then automatically build the extension model. This method contains four core steps. First, chunk parsing is performed on the sentence containing the user requirements to obtain the phrase sequence. Secondly, the phrase sequence is classified with a classifier. Thirdly, based on the matching rule, information is extracted from the classified phrase to obtain the information required for computer processing. Next, database technology is used to build the extension model. Using a tenement building as an example, we implemented and tested our proposed method. Based on our experimental results, we proved that the proposed method is effective for understanding user requirements in order to build an extension model.