Research On Classification Algorithm Based On Web Query Intention

With the development of Internet and E-commerce, the ways in our live, study and work have changed a lot. At the mean time the amount of information on the web grows dramatically and the information on web is updated frequently. The problem users are faced with today is no longer the lack of useful information but that of finding information pertinent to their personal needs. Traditional Information Retrieval technologies have satisfied people to some extent, but they are still suffering from low recall and precision problems. It is a very important research subject that how to get information we are interested in. Nowadays, understanding the user's query is the way of solving with the problems of "information overload" and "information bewilderment" in acquiring information. More and more people are doing some researching on how to get the users' intention. This paper presents algorithms and techniques to get user's intention with classification.This paper discussed the characteristics of the query intention classification, the model and algorithm of query classification which based on the systematic analysis of current domestic and foreign literature related to the classification based on the query intent. And then the system architecture and functional requirements of each module are proposed, through the investigation and statistical analysis on the specific e-commerce search engine, and in accordance with requirements of the project. At last, a classification system and a classification framework based on the query is obtained by integrated several dimensions to classify the query intent. The automatic classification framework using exact match, machine learning, and computational linguistics methods make up with the advantages of various algorithms according to some strategy.Results are presented showing that our classification approach can be successfully applied to a significant portion of the query stream, making it possible for search services to leverage it for improving search effectiveness and efficiency.