Method and system for classifying illegal voice based on C4.5 algorithm

The invention discloses a method and a system for classifying illegal voices based on a C4.5 algorithm. According to the embodiment of the invention, voices in a communication network are recorded and then converted into voice texts, and feature data extraction is performed on the voice texts by adopting a data feature engineering mode; and inputting feature data extracted from the voice text into an illegal voice recognition model based on a C4.5 algorithm to obtain a voice recognition result, the voice recognition result including whether the voice is illegal voice or not and the category of the illegal voice. According to the embodiment of the invention, the category of the illegal voice in the communication network can be accurately identified. 本申请公开了一种基于C4.5算法对非法语音进行分类的方法及系统，本申请实施例对通信网络中的语音进行录音后转换为语音文本，采用数据特征工程方式对语音文本进行特征数据的提取；将从语音文本中提取的特征数据输入到基于C4.5算法的非法语音识别模型中，得到所述语音的识别结果，所述语音的识别结果包括所述语音是否为非法语音及非法语音的类别。这样，本申请实施例就可以准确识别出通信网络中的非法语音的类别。