Thai Hom Mali rice has good quality， high taste quality and nutritional value， which is loved by consumers all over the world. However， bad phenomena such as shoddy and adulteration often appear in the market. Establishing a rapid identification method of Thai Hom Mali rice is of great significance to promote the sustainable and healthy development of high-quality rice industry. In this study， based on the multi-source information fused by near infrared spectra and conventional indexes of Thai Hom Mali rice， the eigenvectors of the first derivative preprocessed near-infrared spectrum and the conventional index of 155 samples of Thai Hom Mali rice and 194 samples of Non-Thai Hom Mali rice were fused to form a 349 row and 14 column vector matrix， which was used as the input vector matrix of support vector machine classifier， and the fusion model of multi-source information was established. The identification results showed that the recognition rate of calibration set and verification set model was 100%， which solved the problem of low accuracy in the identification of Thai Hom Mali rice by common methods such as near infrared spectrum information， and realized the rapid and accurate qualitative identification of Thai Hom Mali rice. It has important application value in the identification of Thai Hom Mali rice adulteration.