The　performance　of　the　shift　strategy　can　reduce　the　energy　consumption　of　two　automatic　manual　transmissions　(AMT)　electric　vehicles　while　meeting　the　needs　of　various　drivers.　Hence,　the　adjustment　of　the　shift　strategy　is　complicated　due　to　the　uncertain　driver　behavior.　To　address　the　above　issue,　an　online　driver　behavior　adaptive　shift　strategy　based　on　dynamic　corrected　factors　is　proposed.　Firstly,　the　simplified　models　of　the　power　system　and　conventional　shift　strategies　are　constructed　for　electric　vehicles.　Secondly,　principal　component　analysis　and　k-means　algorithms　are　implemented　to　classify　driver　styles.　Next,　Learning　Vector　Quantization　neural　network　and　Fuzzy　neural　network　are　applied　to　identifying　driving　style　and　driving　intention　in　real-time.　Then,　according　to　the　driver　behavior,　a　dynamic　corrected　factor　is　introduced.　The　dynamic　corrected　factors　of　different　driver　styles　are　modified　to　adjust　the　proportion　of　power　and　economy　in　the　shifting　process.　As　a　result,　the　proposed　shift　strategy　based　on　dynamic　corrected　factors　achieves　a　compromise　between　power　and　economy　for　two-speed　AMT　electric　vehicles.　The　numerical　validation　results　demonstrate　that　the　proposed　shift　strategy　is　energy-saving　compared　with　the　conventional　shift　strategy　and　can　satisfy　the　requirements　of　various　driver　styles.　©　2021　Elsevier　Ltd