Model training method, long text multi-label classification method and related equipment

• Main Authors: MA CHAO, DENG ZEGUI, JIANG NING, XIAO BING
• Format: Patent
• Language: Chinese; English
• Published: 23.05.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a model training method, a long text multi-label classification method and related equipment, which are used for training a text classification model capable of being used for a long text multi-label task and accurately predicting multiple labels corresponding to a long text through the text classification model. The training method comprises the following steps: acquiring a long text corpus and multiple tags corresponding to the long text corpus; splitting the long text corpus to obtain a plurality of short text corpuses; performing iterative training on a first short text classification model based on the multiple tags and the multiple short text corpora, and determining a mapping relationship between the multiple short text corpora and the multiple tags based on classification information output by the first short text classification model in the iterative training process, obtaining a single tag corresponding to each short text corpus; and training a second short text classificatio