Text classification method and device

The invention discloses a text classification method and device. The method comprises the steps of obtaining a text for model training; determining a number corresponding to each character in the textfor model training according to a preset corresponding relationship between the characters and the numbers; generating first format data according to the number corresponding to each character in thetext for model training, the position of each character in the text for model training and the classification of the text for model training; and training a text classification model by taking the first format data as training data and adopting a preset machine learning algorithm, so as to perform text classification according to the trained text classification model. Compared with the prior art,the text classification method has the advantages that the classification precision and the classification speed are improved. 本发明公开了一种文本分类方法及装置，该方法包括：获取用于模型训练的文本；根据预设的文字与数字之间的对应关系确定所述用于模型训练的文本中的每个字对应的数字；根据所述用于模型训练的文本中的每个字对应的数