With the rapid development of machine-to-machine (M2M) mobile smart terminals, M2M services can be used in a wide range of industries, including such as tele-medicine, remote meter reading and public security. Since different industries and enterprise users have different requirements for M2M specific applications, the security identity authentication of M2M mobile terminals is particularly worthy of attention. Existing methods can effectively solve the unsustainable problem of one-time verification, however they cannot address the dynamic relevance characteristics of user behavior sufficiently. Thus, the accuracy of user identity authentication needs to be further improved. In this paper, we propose a terminal identity authentication technology based on user association behavior analysis. In order to identify the abnormal login during each behavior process of authenticated user, we take largest coincident part of the user behavior sequence and short coincide into consideration. In addition, we propose Behavior Common Subsequence Sequence Similarity Algorithm based on the traditional sequence pattern of Behavior Common Subsequence(BCS). The experimental results demonstrate that the proposed method can effectively improve the accuracy of user’s behavioral sequence, and prove the uniqueness of different sequences on the other hand.

随着机器对机器（M2M）移动智能终端的迅猛发展，M2M服务可用于众多行业，包括远程医疗，远程抄表和公共安全。由于不同的行业和企业用户对M2M特定应用有不同的要求，因此M2M移动终端的安全身份认证尤其值得关注。现有方法可以有效地解决一次性验证不可持续的问题，但是不能充分解决用户行为的动态相关性。因此，需要进一步提高用户身份认证的准确性。本文提出了一种基于用户关联行为分析的终端身份认证技术。为了识别经过身份验证的用户的每个行为过程中的异常登录，我们考虑了用户行为序列中最大的重合部分，并考虑了短重合。另外，基于行为公共子序列（BCS）的传统序列模式，提出了行为公共子序列序列相似性算法。实验结果表明，该方法可以有效提高用户行为序列的准确性，同时可以证明不同序列的唯一性。