Path recommendation method and device

Abstract

An embodiment of the invention discloses a path recommendation method and device. The path recommendation method includes: according to acquired historical trajectory data, establishing a corresponding directed graph under the condition that a target site is determined, wherein segments corresponding to any two adjacent nodes contained in the directed graph have corresponding steering probabilityvalues; according to a maximum-probability pathfinding algorithm, selecting one path with the maximum probability value from a starting node to the target site as a recommended path. The problem aboutcomplex and changeful road conditions is solved by no longer being limited to using prior knowledge to build a large number of models; compared with a method that existing mainstream navigation adopts trajectory planning generated from calculation of algorithm models and strategies, the method has the advantages that patterns of user travel are mined by analyzing the historical trajectory data, complex changes of the road conditions in real environment are met, the most popular path, namely the recommended path can be mined according to the established directed graph, and travel requirementsof users can be well met.

Description

technical field [0001] The present invention relates to the technical field of path planning, in particular to a path recommendation method and device. Background technique [0002] With the widespread use of mobile communication devices such as smart phones and the rapid development of mobile communication technology, the mobile Internet and its applications have shown a blowout trend in recent years. According to authoritative data, the number of mobile Internet users in China reached 759 million in January 2016, surpassing the total number of traditional PC users and forming a huge market with a trillion-scale output value. Subsequently, location-based services (Location based Service) represented by various map applications have become popular tools, profoundly changing people's work and lifestyle. When using these services, a large number of records are persisted to the enterprise server. These records contain information such as location, time, direction, speed, etc.,...

AI Technical Summary

Problems solved by technology

However, complex models lead to high maintenance costs. With the complexity of application scenarios, it is difficult to define the applicable boundary of the model when using mechanized models. For example, 8:00 am to 10:00 am is defined as the morning peak period, and the morning peak model is used, 7:59 Just use the non-morning peak model, obviously this kind of artificial division of the model is not reasonable

Images