随着计算机软件的规模不断扩大,手工获取、开发和维护软件所需的信息越来越困难。数据挖掘技术可从软件工程数据中自动发现所需信息,加快软件开发进程。对软件工程数据挖掘的研究进展进行了综述。概述了软件工程数据挖掘的基本概念与技术挑战 详细评述了在软件工程各个阶段,数据挖掘技术所能发现的信息/知识,以及获取这些信息/知识的意义、难点、步骤和方法,重点介绍了数据预处理和数据表示方法 对软件工程数据挖掘研究的发展趋势进行了展望。 -With the growing size of computer software, manual acquisition, development and maintenance of software required information increasingly difficult. Data mining technology from software engineering data automatically discover the information they need to accelerate the software development process. Data mining software engineering studies were reviewed. Outlines the basic data mining software engineering concepts and technical challenges　reviewed in detail the various stages in software engineering, data mining technology can find information/knowledge, and access to such information/knowledge Significance, Difficulties, procedures and methods, focusing on data preprocessing and data representation　software engineering data mining research trends were discussed.