The invention relates to a text division method and device and
electronic equipment. The method comprises the steps that sentences in a
target text are recognized, the sentences are converted into
sentence vectors, position codes for representing the positions of the sentences in the
target text are constructed, the mapping relation among the
sentence vectors, the sentences and the position codes is established,
semantic clustering is conducted on the
sentence vectors, multiple theme class clusters are generated, and a preset large
language model is used for generating a plurality of theme class clusters based on the sentence vectors in the theme class clusters. The method comprises the following steps: generating a subject tag corresponding to each subject class cluster, converting the subject tag of the subject class cluster into a corresponding subject tag vector for each subject class cluster, calculating the similarity between the subject tag vector and a sentence vector in the subject class cluster, and dividing a
target text based on the similarity and position codes. According to the scheme provided by the invention, the advantages of the
semantic clustering algorithm and the large
language model can be fully utilized, the recognition accuracy of each theme in the text is improved, and the accurate division of the text according to the theme is realized.