A travel route recommendation method combined with short-term traffic forecasting

Abstract

The present invention provides a travel route recommendation method combined with short-term traffic prediction. The method is: download historical photo description information from a photo sharing website, use the DBScan clustering algorithm to cluster the photos, obtain points of interest with high photo density, and extract Historical travel routes based on historical photo description information. Based on the historical photo description information, a time series model of different time intervals for each point of interest is established. The probability transition matrix of the Markov model is generated based on the historical travel routes in the historical travel route collection in the area, and the probability transfer matrix is ​​generated through the user The photos and photo description information uploaded in real time update the probability transition matrix of the Markov model. Based on the updated probability transition matrix of the Markov model, the user is recommended points of interest with the highest transition probability. This method combines the short-term tourist flow of each point of interest to make route recommendations, which plays a role in dispersing passenger flow within the scenic spot.

Description

technical field [0001] The invention belongs to the technical field of data mining, and in particular relates to a travel route recommendation method combined with short-term traffic prediction. Background technique [0002] With the popularization of mobile smart devices such as smart phones, people's living standards are improving day by day. It has become a fashion for people to take photos to record the scenery of the journey during the journey. Thousands of people take a large number of photos every year. In addition to recording the scenery of people's journey, the photos also include meaningful data such as GPS information and shooting time. This provides a good data source for mining travel routes from photos and recommending them. [0003] Due to the development of the Internet, a large number of social networking sites and photo sharing platforms have flooded into people's lives. This provides a good Internet platform for the sharing of travel photos, which grea...

AI Technical Summary

Problems solved by technology

The recommended routes proposed in the above methods are all classic routes based on historical data, without considering the impact of tourist flow on route selection during the real-time travel process. When the flow of people in some scenic spots is too large, corresponding diversion strategies should be adopted, which will have a negative impact on tourism. rerouting

Images