The invention discloses a standardized sampling method for extracting pathological speech MFCC features for artificial intelligence analysis, and the method comprises the following steps: collecting speech data, carrying out speech data collection on 82 standard Chinese syllables according to the sequence of a standard Chinese speech evaluation system vocabulary, editing the acquired speech data,so that editing work of 82 syllables is finished, then classifying and filing, carrying out signal extraction on the 82 edited syllables, extracting MFCC features of each syllable through specified pre-emphasis, framing, windowing, fast Fourier transform, a triangular band-pass filter and extended framing processing, and forming an MFCC voice library by using the processed data. According to the method, specific MFCC features of each syllable are extracted through a standardized process method, a digitized, standardized and structured speech feature database is constructed, the method can serve pathological speech feature big data and various applications of artificial intelligence analysis, and objectivity and efficiency of pathological speech research and application are improved.