TEXT INTENT RECOGNITION METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM

摘要

A text intent recognition method and apparatus, an electronic device, and a storage medium, relating to the technical field of artificial intelligence, and also relating to the technical field of blockchain, a session text being stored in a blockchain node. The method comprises: acquiring a session text, and performing entity recognition on the session text to obtain a plurality of entities (S11); on the basis of the session text, generating a first text vector containing a context feature and, on the basis of the plurality of entities, generating an entity feature vector (S12); by means of a convolution operation, converting the first text vector into a second text vector of multiple granularities (S13); performing feature extraction on the second text vector of multiple granularities to obtain a semantic feature vector, and splicing the semantic feature vector and the entity feature vector to obtain a template feature vector (S14); and, on the basis of the template feature vector, determining an intent category corresponding to the session text (S15). The present method determines the intent category of the session text by means of converting the session text to a semantic feature vector and an entity feature vector and splicing same, entity features being added to assist the intent classification to thereby improve the recognition accuracy of intent recognition.