基于搜索引擎的行业标签分类体系构建与扩展研究

Study on the Construction and Expansion of Industry Label Taxonomy Based on Search Engine

针对各种行业不同的需求,需要构建一个可以不断完善和不断学习的行业标签分类体系。分类体系主要通过分类标签来对属性相同的实体进行归类。行业标签分类体系的分类标签下包含两种实体,即URL和关键词。在行业标签分类体系的构建与扩展过程中,搜索引擎起到了重要的作用。目前,已经构建了一个初步的行业标签分类体系,并实现了一个自动扩增URL和关键词的系统。

According to the different needs of various industries, we demand a industry label taxonomy which is able to improve and refine continuously. Taxonomy mainly merge the entities with the same properties through the labels. Industry label taxonomy contains two kinds of entities, that is, URLs and keywords. In the process of the construction and expansion of industry label taxonomy, search engine plays an important role. At present, we have constructed a preliminary label industry taxonomy, and have implemented a system which helps the taxonomy to expand its URLs and keywords automatically.