Personalized place and route recommendation method related with time

Abstract

The invention discloses a personalized place and route recommendation method related with time, and the method comprises the following implementation steps: (1), building a three-dimensional sign-in tensor; (2), reconstructing the three-dimensional sign-in tensor; (3), obtaining a candidate place list; (4), obtaining the coarse grit time distribution of places and the fine grit time distribution; (5), calculating the coarse grit time information divergence of the places; (6), calculating the fine grit time information divergence of the places; (7), calculating the possibility that a to-be-recommended user visits the places; (8), obtaining a recommendation path. The method carries out the mining of places with effective time, in which a user is interested in, according to the time information of the interest of the user and places, enables the user to obtain the recommendation path which accords with the interest of the user, and can be used for the place and path recommendation service in a social network based on places.

Description

technical field [0001] The invention belongs to the technical field of data processing, and further relates to a time-related personalized location route recommendation method in the technical field of social networking. The present invention can be applied to location route push service in location-based social network. Background technique [0002] With the development of information technology and mobile terminal technology, as well as the emergence and progress of wireless network and location-aware technology, location-based services, such as Foursquare, have developed rapidly. Location-based services can record and track the user's spatial movement trajectory through sign-in. At the same time, with the expansion of urbanization, the number of locations contained in the city is increasing, and users may only know and be familiar with a certain area of ​​the city. When users arrive at other areas in the city, service providers are required to recommend routes. With a ...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the recommendation results through the TF-IDF algorithm are relatively single and lack diversity; without considering the time information of route access, the route generated by the recommendation system may be invalid

The disadvantage of this method is that in the process of route recommendation according to the user's preference information, the current time information of the user and the time information of the route are not considered, and the route that meets the time requirements cannot be well provided for the user.

Images