Research On Location Based Services Recommended System

Positioning technology has became a popular field of study in recent years.Through various targeting methods,researchers can gather targeting location and trajectory of the users.The new technology allows us to simulated users' behavior patterns and analyze the user's interests.In this context,we can use location based technology among the recommended system.Recommended system was produced to help users from the mass of data among data users to find their own needs.In such demand among the various types of classical algorithm frequently emerge for the user's own interest as well as the user's own characteristics were sustained and in-depth excavation.Initially users are considered among the group,and to produce a final set of recommendations for the user according to property groups.But with the continuous development of society,it's no longer able to make such a recommendation to meet customers' satisfaction.In such a case,the personalized recommendation system became the key to solve the problems.The user's own labels are no longer been regarded as the only reference standard.How to find the user's own preferences and interests from the hidden informations became the breakthrough of research.In addition,providing recommendations based from the users' past-interest no longer able to meet the user demand for the newly emerged things.The intend that not only give users recommendation from familiar territory,but also areas that have not been touched by the users,has shown the research direction we need to considerA combination of two newborn and evolving technologies,we propose a location-based service recommendation algorithm.Among the new algorithm,the positioning technology allows us reserach the tendency and interests of users from a new direction,this new feature will eventually merge with classical recommendation algorithms,obtained a brand new recommendation algorithm.Having reached the new algorithm,we design experiments to verify the results of the recommendation,obtain the recommended quality and new algorithms compare with the traditional recommendation algorithm conclusions.