Multi-modal travel mode fusion recommendation method based on dynamic traffic network

Abstract

The invention discloses a multi-modal travel mode fusion recommendation method based on a dynamic traffic network, and the method comprises the steps: firstly constructing a user space-time travel track into a heterogeneous information network, and considering a continuously changing dynamic traffic network in a travel process; preprocessing the historical track data according to the heterogeneous information network; key element paths are extracted from a network mode corresponding to the heterogeneous information network to enrich feature embedding of objects; meta-path feature aggregation is realized through an aggregation function; dynamically modeling a user and a travel mode by using a meta-path guided graph neural network to obtain feature embedding with rich interaction information; and embedding and inputting the final features of the user and the travel mode into the MLP, fully learning the preference of the user for the travel mode in the space-time travel trajectory, and recommending the travel mode meeting the personalized requirements to the user. According to the method, the personalized preference of the user on the travel mode is described in a fine-grained manner, meanwhile, the traffic pressure is relieved, and the traffic toughness is improved.

Description

technical field [0001] The invention belongs to the intersection field of traffic travel mode recommendation and heterogeneous graph neural network, and specifically relates to a multi-modal travel mode fusion recommendation model based on a dynamic traffic network. Background technique [0002] With the continuous development of urbanization and the improvement of economic level, people's travel needs are becoming more and more diverse. When the demand exceeds the carrying capacity of the transportation system, various traffic problems and even environmental problems will arise, such as traffic jams and vehicle exhaust pollution. The complex choice behavior of people in the multi-modal transportation network determines the distribution of travel demand on the transportation network. From the perspective of balancing the distribution of transportation demand, it is of great research value to recommend personalized travel modes. [0003] Nowadays, in the era of big data, the ...

Images