Chinese text radical feature acquisition method in medical field

The invention discloses a medical field Chinese text causal relationship extraction method fusing radical information, and relates to the technical field of data mining, and the method comprises the following steps: obtaining a medical field Chinese text data set through a web crawler, preprocessing the obtained data, converting English professional nouns in a text into Chinese by adopting a Google translation technology, and extracting the Chinese text causal relationship; the method comprises the following steps: acquiring radicals of all characters by using an online Xinhua dictionary, performing incremental training on the radicals by using a Word2Vec architecture to obtain a radical feature representation, and performing causal relationship extraction on a data set by using a radical feature vector as an input of a causal relationship extraction model to obtain a causal relationship entity. The method solves the problem of effective causal relationship extraction of Chinese text data in the medical field