Aimed at the problem that the basic probability assignment of multiple sensors cooperation with target identification in practical application is liable to cause low decision-making reliability, a reasoning mechanism of multiple sensors cooperation with target identification based on BP neural network and D-S evidence theory is presented. Firstly, BP neural network theory and D-S evidence theory are summarized simply. And then, target identification reasoning frame is built, and the algorithm's feasibility is reasoned. At last, an actual example is simulated, and by information fusing the basic probability assignment of uncertainty drops to 0.0008, the analysis and the simulation show that the reasoning mechanism is effective.