Abstract: An evaluation method of craniofacial asymmetry index based on artificial intelligence is disclosed and includes: a craniofacial image shooting step: obtaining a craniofacial model file of a patient; an artificial intelligence head shape identification and feature point marking step: importing the craniofacial model file into an artificial intelligence algorithm, performing identification and feature point marking on a craniofacial image in the craniofacial model file to generate at least one feature point; a craniofacial space coordinate axis establishment step: including a coordinate axis y-z plane establishment step, a coordinate axis origin establishment step and a z-axis orientation definition step; and an artificial intelligence skew degree estimation step: inputting the craniofacial model file and corresponding coordinate axes into an artificial intelligence skew degree evaluation algorithm simultaneously, and presenting a craniofacial skew degree in a data visualization manner.