Internet　of　Vehicles　is　new　concept　proposed　in　recently　year　extended　from　Internet　of　Things.　It　plays　an　important　role　in　improving　traffic　situation.　This　system　is　respected　as　a　part　of　Internet　of　Vehicles　aimed　to　identify　road　rage,　fatigue　driving　or　drunk　driving　and　so　on　by　recognizing　drivers＇　facial　expression.　With　Internet　of　Things　architecture,　this　system　has　a　multi-function　system　module.　By　combining　AJAX　with　SSH2　framework,　the　web　service　of　this　system　is　established.　PCA　and　KNN　are　the　core　algorithm　of　facial　expression　recognition　and　the　related　parameters　is　optimized.　According　to　the　topological　graph　of　the　system　network,　this　system　has　been　deployed　in　a　certain　vehicle　network　company　and　it　performed　stable,　efficient　and　accurate.