This document shows the concept for a broad topic and ambiguous query, different types of users may have different search goals when they submit the query to the search engine. The inference and analysis of user search goals can be very useful in improving search engine relevance information and user experience. In this paper, we propose a novel approach to infer user search goals by analyzing search engine query logs. First, we propose a framework to search different user search goals for a query by making cluster to the proposed feedback sessions. Feedback sessions are constructed from user click-through logs i.e. user response and can efficiently reflect the information needs to users. Second, we propose a novel approach to create pseudo-documents to better represent the feedback sessions for clustering. Finally, we propose a new criterion Classified Average Precision (CAP) to calculate the performance of inferring user search goals. Experimental results are presented using user click-through logs from a commercial search engine to check the effectiveness of our proposed methods