面向旅游人文信息集成的Web数据源选择

Web data source selection for humanities information integration of tourism

人文信息集成对提升一个景点的文化内涵有重要意义,为提升集成数据的效用和效率,提出了一种面向人文信息集成的数据源选择策略。基于名人、人文主题、信息长度和标记词构建人文信息摘要;基于人物扩展策略丰富人文摘要内容;基于名人人文信息增量设计了相应的数据源选择策略。利用领域数据集进行实验的结果表明所提方法准确率较高。

Humanities information integration is import to enhance the cultural connotation of a landscape. To enhance the effectiveness and efficiency of data integration,we propose a data source selection strategy for humanities-oriented information integration. First,building a humanities information summary based on celebrities,cultural themes,message length and mark words; Second,proposing an expansion strategy to rich cultural content of the summary; Finally,selecting data sources based on information gain of celebrities. We conduct a number of experiments based on the data collections of tourism,and the result shows that our methods accuracy is high.