Revealing the hidden correlations of elements in intelligent transportation systems with a novel knowledge graph-based path calculation approach

Abstract

Intelligence has emerged as an integral trend within Intelligent Transportation Systems (ITS), making the comprehension of interrelations among its key elements critical for unveiling potential influence mechanisms. To foster research in this domain, we present an innovative method aimed at unearthing explainable correlations among these pivotal ITS elements. Our approach is underpinned by two primary stages: the construction of a knowledge graph drawn from ITS-related patents, followed by the application of an enhanced breadth-first path calculation algorithm. This novel algorithm carefully balances consideration between element correlations and the structural nuances of the knowledge graph. To verify the robustness of our algorithm, we engage in meticulous node similarity calculations and undertake an assessment of its effectiveness using an array of performance indicators. Furthermore, to provide practical insight, we offer two case studies exploring the correlation among elements within the realms of Vehicle-to-Everything (V2X) communication system and smart logistics center. These case studies not only validate the method’s effectiveness but also illustrate its broad applicability. Our method’s utility extends beyond merely unraveling evolution mechanisms and forecasting development trends within transportation systems, and it has the potential to significantly contribute to correlation research across a broad spectrum of fields.