04-07-2023 дата публикации
Номер: CN116383378A
Принадлежит:
The embodiment of the invention discloses a text classification method and device, a storage medium and a terminal, a standard graph structure can be determined in advance based on a large number of sample texts, character node features of sample characters are used as corresponding graph nodes in the standard graph structure, and edges in the standard graph structure are relationships among the sample character node features; the method comprises the steps of firstly obtaining a target text, then obtaining target characters in the target text, determining target character node features corresponding to the target characters in the target text based on a standard graph structure and a target graph structure containing the relation between the target character node features, and finally conducting neural network calculation on the target graph structure, and then determining the category of the target text based on a calculation result. In this way, the target text can be classified.
Подробнее