Text classification model training method and device and text classification method and device

The embodiment of the invention provides a text classification model training method and device and a text classification method and device. The model training method comprises the steps that the type of a current classification model is determined; classifying the unclassified sample data based on the current classification model; determining whether a next classification model is added or not according to the classified sample data and the unclassified sample data; if yes, determining the type of the next classification model; classifying the remaining unclassified sample data based on the next classification model until it is determined that a new classification model does not need to be added; and combining the classification models to form a text classification model according to the order of determining the types of the classification models. According to the invention, full-amount classification of the sample data can be realized. 本申请的实施例提供了一种文本分类模型训练方法、文本分类方法、装置，模型训练方法包括：确定当前分类模型的种类；基于当前分类模型对未分类的样本数据进