Detection method for user group behavior rules based on stay places in mobile trajectory

Abstract

The invention discloses a detection method for user group behavior rules based on stay places in a mobile trajectory. The method comprises the following steps: firstly, receiving multi-user trajectory data from a data collector; secondarily, extracting stay place sequences from the trajectory data, and transforming the stay place sequences into place preference vectors which represent user schedule behaviors; then extracting schedule behavior vectors, and using a weighted average method to calculate schedule behavior pattern vectors; finally, calculating similarities among users based on schedule behavior patterns, and using a Kmeans clustering algorithm to detect behavior rule patterns of user groups. According to the invention, the similarities among the users are calculated by using the schedule behavior patterns based on the stay places to solve the problem of nonoverlapping of user stay areas, so that the behavior rule patterns of the user groups can be effectively detected.

Description

technical field [0001] The invention relates to a method for detecting user group behavior rules, more specifically, to a method for detecting user group behavior rules based on stay points in a moving track. Background technique [0002] In recent years, using trajectory data to mine user behavior rules has received more and more attention. Long-term behavioral patterns reflect users' living habits and are high-level contextual information that can help location-aware applications better adapt to their users' needs. For example, a recommendation system can recommend friends, places, or other location-related information to users based on patterns of behavior. The information push system can push and share relevant information to users with similar life patterns. [0003] The user's short-term behavior (such as eating, walking, etc.) based on the detection of acceleration sensors cannot reflect their long-term behavior and living habits; overlap, it is impossible to measu...

AI Technical Summary

Problems solved by technology

[0003] The user's short-term behavior (such as eating, walking, etc.) based on the detection of acceleration sensors cannot reflect their long-term behavior and living habits; overlap, it is impossible to measure the similarity of users without overlapping access (such as users living in different cities); based on reverse geocoding technology, the user's physical trajectory is converted into a semantic trajectory, and then the sequence pattern is extracted from the semantic trajectory, The method of measuring the similarity of user behavior based on the longest semantic trajectory mode, although the restriction on the overlapping of user visit areas, is limited to the analysis of short-term motion behavior of users, and the personalized semantics of user visit locations (such as home, work, etc.) location, etc.) cannot be obtained through reverse geocoding; moreover, user behavior is diverse and complex, and it is difficult to grasp its trend and regularity by relying on data alone

Therefore, the technology of using trajectory data to effectively mine and display user behavior, calculate the similarity of user behavior, and then detect the behavior rules of user groups needs to be further studied and discussed.

Images