Long text classification method and system, storage medium and equipment

• Main Authors: GUO PENGCHENG, HU HUA, YANG LI, ZHOU YICONG, SUN TAO
• Format: Patent
• Language: Chinese; English
• Published: 23.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a long text classification method and system, a storage medium and equipment, and the method comprises the following steps: obtaining a to-be-classified long text, carrying out the keyword extraction and sentence segmentation of the to-be-classified long text, and correspondingly obtaining a plurality of keywords and a plurality of sentences; performing subject information representation on the plurality of keywords based on a subject information learner to obtain a subject vector; performing full-text information representation on the plurality of sentences based on a full-text information learner to obtain a full-text vector; fusing the topic vector and the full-text vector based on a classifier to perform long text classification; the problems that in long text classification, text information is lost, text information cannot be fully learned, and time complexity is high are solved. 本发明公开了一种长文本分类方法、系统、存储介质及设备，其方法包括以下步骤：获取待分类长文本，并对所述待分类长文本进行关键词提取及分句，对应获取多个关键词及多个句子；基于主题信息学习器对多个所述关键词进行