Database creation of test-item's statistical information set and the statistical analysis using natural-language-processing technology

(1)我们已经建立了一个全面的系统，表明国家中心的测试项目，其统计数据存储在信息数据库中，通过我们的本地网络。也可以检索公立和私立大学入学考试试题。(2)基于自然语言处理的推荐系统技术成为本课题的组成部分之一，验证了该技术的有效性。作为实证研究，我们使用随机森林对全国中心测试的分数进行了统计分析，并在研究会上公布了结果。(3)由于我们确信随机森林方法应该被认为是包含缺失数据的数据分析技术的标准之一，因此我们进行了实证研究，例如上下文信息的插补，并对新技术进行了研究。研究成果在许多国际研究会议上发表。

(1) We have built a comprehensive system which indicates national-center-test items linking their statistics stored in information database through our local network. Public and private university entrance examination test items can also be retrieved.(2) Judging that the technology of recommendation system with natural-language-processing becomes one of the components of our subject, we verified the validity of the technique. As an empirical study, we use Random Forests to the scores of national center test, and announced the result to research meeting.(3) Since convincing that Random Forests method should be recognized to one of the standards of the data-analysis technique containing missing data, we performed positive researches, such as an imputation of context information, and investigated the new technique. The results of research were presented at many refereed international research conferences.