jieba Python library is an excellent third-party Chinese sub thesaurus, word jieba supports three modes: fine mode, full mode and search engine model, the following are the characteristics of three models.
Precise mode: the most accurate statement is trying to segmentation, redundant data does not exist for doing text analysis
Full mode: The statement is the word of all possible words are cut points out, very fast, but there are redundant data
Search engine mode: On the basis of the precise mode of long-term be segmented again