Position prediction method based on user movement mode

Abstract

The invention relates to a position prediction method based on a user movement mode, and belongs to the field of machine learning. The method comprises the following steps: mining an individual movement mode of each user by adopting an Apriori algorithm, and finding out an internal cause influencing the sign-in of the user; calculating the similarity between the individual movement modes of the user by using a dynamic time warping algorithm DTW; grouping the individual movement modes of the users through clustering to obtain a central mode of each group, and finding out an external cause influencing sign-in; respectively training a Markov model by using the individual movement mode and the overall movement mode; training a Markov chain model based on IMP and AMP, and predicting the next position of the user; considering the influence of external weather, and creating a weather total feature; calculating the similarity between the weather of the current place and the weather of other places by using a Gaussian kernel function, and correcting a prediction result; and setting an evaluation standard and a reference method. According to the invention, the prediction result is more suitable for the actual life.

Description

technical field [0001] The invention belongs to the field of machine learning and relates to a position prediction method based on user movement patterns. Background technique [0002] With the popularization of mobile terminals, it is easier to obtain human mobility data. Location-based social networking platforms have also collected a large amount of user check-in data. Research on human mobility patterns has become a hot topic, and it has become possible to study people's mobility patterns. Among them, location prediction is more common. Through location prediction, users' mobile preferences can be known in advance, and the mobile tendency of people can also be understood, which can not only provide targeted services to users, but also bring benefits to businesses. Existing research mainly analyzes the user's behavior through the user's check-in history, finds the user's movement rule, and then predicts the location. Among them, most of the factors considered are time, ...

AI Technical Summary

Problems solved by technology

In addition, most studies are based on the prediction of the user's personal mobility patterns. If the user goes to a place that has never been there, there is no data available to train the model; some researchers also use the overall check-in data to train the model, so that the model It can be applied to the location prediction of all users. However, the prediction based on the overall data is too coarse-grained. If the user is currently in the same place, the final prediction result is the same place, which is inconsistent with the actual situation.

[0003] Aiming at the problem that the traditional position prediction model based on discrete state sequences cannot predict the position well, the present invention considers the correlation between different positions in the user check-in trajectory, and excavates the individual user's movement pattern and the overall position from the user historical check-in data. mobile mode, that is, the internal and external factors that affect user sign-in

Images