Dockless bike sharing (DBS) has the free-floating feature and large-scale fleet, which poses significant challenges to repositioning. This paper finds the Matthew mechanism of bike floating based on real-world trip data in Nanjing, China, and then proposes an integrated method for the large-scale DBS repositioning problem. Firstly, trip origins are analyzed by the first layer clustering to identify thousands of virtual stations. Secondly, the novel index of bike density and turnover rate are used in target inventory estimation for higher future usage. Lastly, the second-level clustering algorithm assigns workload-balanced tasks to truck drivers, and an advanced neighborhood search algorithm is applied to design the truck route. Results show that there are about three hundred pick-up stations and about three thousand drop-off stations for Nanjing DBS repositioning. And the proposed method is demonstrated to provide a better solution for increasing future usage and improving driver workload balance.