In order to guarantee the information security of the mobile phone, a user identity authentication scheme based on multi-sensor information fusion is proposed. Firstly, the signal features are extracted from the attitude angle changes, range of motion, and the rotation degree of user′s gesture. Then the dynamic time warping(DTW) recognition results of each single feature are used as independent evidence to construct the basic probability distribution function, respectively. And the Dempster/Shafer evidence theory is used for decision fusion. Also, a weighted evidence method is introduced in this work to alleviate conflict among the evidences, which can avoid the negative impact of this phenomenon. The conflict degrees between each pair of evidences are measured by calculating the similarity between them, by which the evidence credibility is determined. Afterwards, the evidence weights are revised to depress the negative effects of the evidences with low credibility when making the fusion process. Hence the final decision can be made according to the fusion result. The simulation results show that the performance of the proposed algorithm is better than the compared algorithms, which can effectively recognize the user's identity of mobile phone.