In the field of Internet and communication, the existing service fault location technology is based on out-of-band measurement, cannot really reproduce the problem points. This paper presents a network business quality intelligent assessment and fault location method based on IFIT. According to the performance data and device data reported by the IFIT, the end-to-end quality intelligent evaluation model based on AI technology is used to evaluate the end-to-end service quality and detect the service status. If the end-to-end service quality status is poor or interrupted, adjust the detection mode to hop-by-hop mode, determine the link and port where the specific quality is poor or interrupted, and then determine the area where the fault occurs. The evaluation results show that, and values of the methods in this paper are all over 85%, higher than the traditional methods, and the comprehensive comparison results show the method of this paper are 10% higher than traditional method, which prove the validity and reliability of the method presented in this paper.