With rapid development of Internet technology gradually penetrate to all areas; the number of electronic documents is largely increasing, resulting in contradictions between information overload and people's desire for knowledge. How to help users take full advantage of the existing full-text retrieval system to get required documents quickly and efficiently from the mass electronic literature has become the objective to the service providers of current digital academic literature. This paper, based on the analysis of relevant users' interest in behavior modeling technology and main recommended algorithm both domestic and abroad; the current status of full-text retrieval system and characteristics of users, raises a users' behavior-based personalized full-text retrieval system recommended algorithm. Its main idea is, under the environment of full-text search system, to collect and use users' implicit behavior data to build their interest model and conduct overall design on the prototype of personalized literature recommendation system supported by the theoretical model.
展开▼