A method for predicting users' off-site access location based on cross-city POI matching

Abstract

The invention discloses a method for predicting user's remote access location based on cross-city interest point matching, which comprises the following steps: constructing an interest point-category bipartite graph, and obtaining an embedded representation of the interest point in a low-dimensional continuous vector space based on a word-hopping model ;Construct a directed weighted POI network, sample POI collections from different cities based on random walks; realize cross-city POI matching based on the maximum mean difference theory; use Bayesian personalized ranking to model the check-in behavior of users in different cities ; Realize the migration of user's check-in preference between different cities through multi-task joint modeling; train the model; calculate the user's check-in probability for different points of interest in the target city according to the model parameters, and select the point of interest corresponding to the top-K probability value An ordered list is formed as the final prediction result. The method of the invention can effectively predict the user's visiting location in a non-resident city.

Description

technical field [0001] The invention belongs to the technical field of user access location prediction, and in particular relates to a location-based information service provider-oriented user access location prediction method based on cross-city point-of-interest matching. Background technique [0002] With the advancement of transportation technology, people's travel time has been greatly shortened, and it has become more and more common for users to "unlock" new cities. Predicting the check-in behavior of users of mobile information services in different places helps to understand user behavior patterns at a higher level, thereby improving the quality and user experience of location-based services. However, location-based information services usually have localization characteristics. Existing solutions mostly focus on predicting the user's access location in the local area (residential city), and prediction solutions for users' access location in other places (non-reside...

AI Technical Summary

Problems solved by technology

However, location-based information services usually have localization characteristics. Existing solutions focus more on the prediction of users' access locations in the local area (settled cities), and the prediction solutions for users' access locations in remote places (non-settled cities) are relatively scarce.

The intuitive strategy to solve the problem of user location prediction in different places is to transfer the user's check-in mode in the settled city to the target city. Because different cities have different cultural and regional characteristics, users often show different interest preferences in different cities, so the simple Knowledge transfer is difficult to solve the problem of user interest deviation

[0003] Existing schemes realize cross-city migration of user access preferences by modeling users’ check-in behavior in settled cities and non-settled cities. However, the precondition of these schemes is that users not only have sufficient check-in records in settled cities, but also The assumption that there are positional trajectories to model does not match reality

Since different cities have different cultural and regional characteristics, simple knowledge transfer is difficult to solve the problem of user interest deviation

Considering that there are differences between cities, users often show different interest preferences in different cities, so it may be counterproductive to directly migrate the check-in preferences of users in the settled city to the target city, resulting in "negative migration"

To sum up, there are two major challenges in user remote access location prediction

[0004] First, users often do not have check-in behavior in non-settled cities, resulting in extremely sparse location trajectories, and it is difficult to use existing methods to directly model users' check-in behavior in different places; Its own inherent mobile behavior mode is also restricted by the local cultural and geographical environment. Existing technical solutions cannot simultaneously take into account the migration of user interest preferences (city-shared characteristics) and the transformation of interest preferences (city-specific characteristics)

Images