The Study Of Personalized Location Recommendation Algorithm Based On The Integration Of Multi-factor

With the rapid development of the online social networks, users can easily share photos, documents, videos and so on. Location-based social networks add the location dimension based on traditional online social networks, which can enable users to share the embedded location information. However, it is very difficult to find the information that users are interested in from the vast information. Different users have different needs, the degree of interest for location information are also different. Personalized recommendation algorithms can dig out the interest based on users’ behavior characteristics, and help users choose the interested information, which becomes more and more important in domain of location-based social networks. At present, there are four types of recommendation which are common in location-based social networks: location recommendation, user recommendation, activity recommendation and social media recommendation. Location recommendation has become one of the most popular research areas.In this paper, the user check-in data of social networks is focused on. We analyze the human movement and try to get the different influence factors from it. We explore the influence of social ties on human movement. From the perspective of geographical location, we study the relationship between human geographic movement and social ties. Based on this basis, this paper proposes a new personalized location recommendation algorithm, which combines location information and social ties. Various factors such as user preference, social ties influence, current location and time interval are syncretized into the algorithm. The algorithm can improve the accuracy of location recommendation.Compared to the existing location recommendation algorithms, our algorithm proposed in this paper works better than some other location recommendation algorithms on the experimental parameters and results. The algorithm considers the human movement, which can adapt to users’ current location, predict users’ future activity and give the personalized location recommendation to specific individual.