A method for mining frequent patterns of indoor trajectories based on fuzzy mesh sequence

Abstract

The invention discloses an indoor trajectory frequent pattern mining method based on a fuzzy mesh sequence, which comprises the following steps: adopting a regular hexagonal mesh to partition a map; according to the vertical projection distance, the mesh is divided into accurate area and blurred area. Traversing every track in the track database, converting the track data into fuzzy mesh sequenceaccording to the mesh of the sample points in the track; the index position of each grid in the trajectory is recorded and its support degree is calculated, and the grid whose support degree exceeds the minimum support degree is added to the candidate set. A projection database is established for each grid in the candidate set, and the support degree of the newly generated candidate trajectory patterns is calculated. Repeat these steps until all trajectory frequent patterns are mined. The invention has the advantages that: since the distance between the center of the regular hexagonal grid andthe center of the adjacent grid is equal, the map is divided into regular hexagonal grids to ensure the equality of all grids; according to the vertical projection distance, the mesh is divided intoaccurate and fuzzy regions, which effectively solves the mesh boundary problem faced by the traditional methods. Under any support degree, the number of frequent pattern mining is considerable, and the mining efficiency is high. The invention is applicable to mining frequent patterns of moving object trajectories in an indoor environment, and has universality.

Description

technical field [0001] The invention relates to a method for mining frequent patterns of indoor trajectories based on a fuzzy grid sequence, which is a method for mining moving object trajectories in an indoor environment, and belongs to the cross field of engineering application and information science. Background technique [0002] With the popularization of various mobile positioning devices, location-based services (LBS) have widely existed in daily life. According to the data provided by Nokia, people spend 87% to 90% of their time in indoor spaces in their lives. Everyone has seen the huge business opportunities brought by indoor positioning technology. Related companies around the world are actively Move closer to the indoor location service industry. [0003] Although there have been some research results on the trajectory of moving objects, most of them focus on the outdoor environment, and there are very few researches on the trajectory of moving objects in the in...

AI Technical Summary

Problems solved by technology

This method makes full use of the trajectory data of indoor moving objects, solves the grid boundary problem that is not considered in traditional methods, and independently selects multiple parameters to mine frequent patterns of indoor trajectories, which can better promote location-based services (LBS). The development of the industry, and reduce the risk of user's track privacy leakage and even protect the user's track privacy from infringement

Images