With the development of the Internet and the explosive growth of business data, there are massive Network User Virtual Identities (NUVIs) on Internet when network user accessing different applications. Compared with previous methods, we will propose an algorithm to analyze which NUVIs belong to the same person. What's more, our approach is based on the cloud computing platform and the cluster system, including the Hadoop Distributed File System (HDFS) and the parallel processing software framework MapReduce.