Researchers have done extensive work on establishing an accurate user profile, which has been verified an effective way to implement the user marketing accurately and effectively. In this paper, we will present a feature extraction method based on the fusion of Word2Vec and TF-IDF, and try to establish a user profile. The vector space model (VSM) contains the word vector calculated by Word2Vec, and the weight vector represented by TF-IDF. Based on this idea, we deduce the user's basic information by analyzing the user's search logs in a period of time. The experiments demonstrate the efficiency of the new method