Port Recommendation System for Alternative Container Port Destinations Using a Novel Neural Language-Based Algorithm

Qiang Mei,Hailin Zheng,Zhisheng Hu,Qinyou Hu,Chun Yang

doi:10.1109/access.2020.3035503

Abstract

Shipping containers are tokens of multimodal international transportation and rapid logistics. Container deliveries are scheduled to satisfy rapidly changing requirements. Unpredictable increases in costs and unforeseeable events such as pandemics compel ship owners and managers to adopt risk minimization measures. This study addresses one issue: how to determine an alternative port of call from massive data to offer a realistic destination change recommendation for a container vessel. Recommendation algorithms have become ubiquitous and are used effectively in other fields, but there is no such model for the port of call selection or recommendation. Large scale automatic identification system (AIS) data are readily available. We developed a computational framework based on a novel natural language programming algorithm that was tailored to support port recommendation rather than use a conventional adjacency matrix method. We mined large scale AIS data to construct sequential berth records for container vessels and mapped each port onto a vector in an embedded space. The natural language neural programming algorithm can suggest ports similar to the scheduled ports of call that were unable to offer service. The recommendations were validated with geo-analysis of sailing distance and could offer viable alternative ports to shipping managers.

Highlights

Shipping containers are a consequence of the modernization of transportation and logistics that began when the shipping industry entered the megaship era in 2007
To meet the demands of efficiency and environmental protection, even coal and grain shipments, which have always been shipped by bulk cargo vessels, are gradually becoming a part of the global logistics chain of container ships and rail transportation [1]
We describe our research into providing alternative port recommendations using big data

Summary

INTRODUCTION

Shipping containers are a consequence of the modernization of transportation and logistics that began when the shipping industry entered the megaship era in 2007. Containers can be distributed into this zone by land transportation (train and truck) or vessels of local shipping lines These ports have many similarities, and one may be substituted for another. The text documents contained sequential berth records (Figure 4), which we merged with the port of call records of all container ships throughout the world to form a training data set. Ports with similar contexts (i.e., ports at which vessels of the same type had previously berthed or were scheduled to berth) were mapped onto neighboring vectors in the embedding space and were identified as potential recommendations using geo-analysis. 200,000 berth records of container ships for 2018 were extracted from the data provided by AIS-equipped vessels throughout the world.

RESEARCH METHODOLOGY

TRAINING PORT VECTORS AND CALCULATING SIMILARITIES BETWEEN VECTORS

CONCLUSION