Interest point recommendation method and device based on position and time information

Abstract

The invention belongs to the field of social network interest recommendation, and relates to an interest point recommendation method and device based on position and time information, and the method comprises the steps: obtaining a data source related to user information, interest point information and the interaction information of a user and an interest point; extracting feature attributes of users and interest points in the data source; utilizing an interest point position information modeling model to predict an interest point set which is possibly interested by the user and is not accessed; modeling by utilizing the sign-in time information of the interest points, and calculating the similarity between different interest points and the popularity of the interest points; synthesizing the prediction values of the two models, and recommending the comprehensively predicted interest points to the user. According to the invention, on one hand, individual users are helped to rapidly explore and be familiar with new places and areas, and on the other hand, merchants are helped to master user behavior characteristic distribution and analyze potential users, so that good economic and social benefits are obtained.

Description

technical field [0001] The invention belongs to the field of social network interest recommendation, and relates to a point of interest recommendation method and device based on location and time information. Background technique [0002] In the information age, with the rapid development of Internet technology and positioning technology and the rapid development of social economy, people choose more and more travel methods and travel locations. People's point of interest (POI) such as: tourist attractions, cinemas, museums, restaurants, etc. are also increasing. However, in the face of a large number of POIs, how people quickly select POIs related to their interests according to their personal preferences has become a problem. A problem for users. Based on such an environment, location-based social networks (LBSNs) recommendation technology and related application services have emerged as the times require. At present, the more popular LBSNs include Foursquare, Gowalla, Ge...

AI Technical Summary

Problems solved by technology

Only considering the location information of POIs and users and the location information between POIs, ignoring the temporal characteristics of POIs, thus ignoring the implicit patterns of POIs, and cannot accurately recommend suitable new interests for target users Point collection, for example, few users will go to bars, KTV and other places in the morning or in the morning

[0007] 3. Dynamic time limit of points of interest

In point of interest recommendation, user-based collaborative filtering is used to calculate the similarity between users through user information, social relations, etc. to generate recommendations, without better consideration of the implicit mode of point of interest

Images