Research On User Behavior Analysis And Prediction Theory Based On Mobile Social Environment

In mobile social environment,users of a friend circle can exchange various information anytime and anywhere.Due to similar interests or mutual influences,they are regarded as each other's correlated users.On the other hand,with the increase of services,it is difficult for users to find their interested services,which is known as information overloading problem.As the core of personalized recommendation systems,user service behavior analysis and prediction can effectively solve the above problem and greatly improve user QoE.Therefore,based on mobile social environment of a target user,extensive behavior samples of its correlated users are utilized to achieve scientific analyses and accurate predictions of its service behaviors.The main works of this thesis are given as follows.I.The related contents of mobile social environment are introduced,and then the current researches of user behavior analysis and prediction are surveyed respectively.Furthermore,the research idea and content organization of this thesis are given.II.A coding Apriori theory based user behavior analysis and prediction algorithm is proposed.First,a coding based two-dimensional Apriori theory is presented to comprehensively analyze user service behaviors: on one hand,the correlation analysis based on behavior history of a target user is performed;on the other hand,an effectiveness factor is formulated to obtain the optimal correlation set of target user,and then the correlation analysis between the target user and each correlated user from its optimal correlation set is performed.Second,for integrating the above correlation analysis results,an improved weighted fusion method based on effectiveness factors is presented,so as to achieve accurate predictions of user behaviors.Extensive simulations results verify the effectiveness of proposed algorithm.III.An improved Apriori theory based user behavior analysis and prediction algorithm is proposed.First,two optimization models based on similarity degree and interaction degree are respectively formulated to select the corresponding optimal correlated users for analyzing two main factors of a target user's behaviors(i.e.long-term habits and short-term influences);furthermore,an adaptive update strategy based on fuzzy theory is proposed to describe the importance of two factors in real time and quantitative manners.Second,an improved Apriori theory is introduced to predict user next service behaviors accurately;particularly,a new update mechanism of Apriori sample database is constructed to effectively integrate the samples of optimal correlated users.Extensive simulations results verify the effectiveness of proposed algorithm.IV.An Apriori theory based user behavior multiple analysis and optimal prediction algorithm is proposed.First,for each social group of a target user,an optimization model based on representativeness degree is formulated to select the most representative correlated user from this social group for analyzing the service behaviors of target user caused by the corresponding social attribute;particularly,the representativeness degree consists of Kendall coefficient based similarity degree and interaction statistics based interaction degree.Second,by using Apriori theory,the correlation analyses for target user and its most representative correlated users are performed respectively,and then a least-square model based weighted fusion method is presented to integrate the above correlation analysis results optimally and predict user next behaviors accurately.Extensive simulations results verify the effectiveness of proposed algorithm.Finally,the conclusions are summarized,and the future research directions are given.