Method and device for voice recognition text multi-label classification

The invention discloses a method and a device for voice recognition text multi-label classification, and relates to the field of computers. The method for voice recognition text multi-label classification comprises the following steps: receiving voice data; performing voice recognition on the voice data to generate a voice text; performing preprocessing on the voice text to generate a preprocessedvoice text; training by using the preprocessed voice text and machine learning to generate a label classification model; and predicting the newly generated preprocessed voice text by using the labelclassification model to generate a label set corresponding to the newly generated preprocessed voice text. 本发明公开了一种用于语音识别文本多标签分类的方法和装置，涉及计算机领域。用于语音识别文本多标签分类的方法包括：接收语音数据；对所述语音数据执行语音识别，以生成语音文本；对所述语音文本执行预处理，以生成预处理的语音文本；利用所述预处理的语音文本，使用机器学习进行训练，生成标签分类模型；使用所述标签分类模型对新生成的预处理的语音文本进行预测，以生成与所述新生成的预处理的语音文本相对应的标签集合。