Chinese word vector modeling method

The invention discloses a Chinese word vector modeling method. The invention relates to a Chinese word vector modeling method, which comprises the following steps: carrying out adaptive combination onChinese strokes by utilizing a BPE algorithm, constructing a Chinese character sub-block, and finishing combination and representation of an internal structure of a Chinese character by utilizing anattention mechanism; carrying out information extraction on the completed Chinese character representation through a CNN structure, and carrying out fine-grained information enhancement by utilizing high-power network; considering the complexity of Chinese grammar, a bidirectional LSTM structure is constructed at a semantic extraction stage for semantic coding, and an end-to-end deep neural language model taking a Chinese character adaptive combination layer, a morphological information extraction layer, a fine-grained information enhancement layer and a semantic information extraction layer as basic components is cons