JISE


  [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] [14]


Journal of Information Science and Engineering, Vol. 39 No. 6, pp. 1421-1436


Inconsistency Detection for Spatiotemporal Knowledge Graph with Entity Semantics and Spatiotemporal Features


XIAO-WEN ZHANG1,2, JING SHAN2, WEN-YI TANG1, LI YAN2
AND ZONGMIN MA2,+
1State Key Laboratory of Air Traffic Management System and Technology
Nanjing, 210007 P.R. China

2College of Computer Science and Technology
Nanjing University of Aeronautics and Astronautics
Nanjing, 211106 P.R. China


Knowledge graph (KG) can model and manage the massive metadata, have received a lot of attention in recent years. Information in the real world is not always static, aim to model and manage the dynamic information (e.g., time interval, location), some research works for spatiotemporal KG have been proposed. Due to the spatiotemporal knowledge is constantly changing, data operations will be more frequent in the process of spatiotem-poral KG construction and management, therefore, inconsistency may exist in spatiotemporal KG. The current work on handling the inconsistencies in spatiotemporal KG mainly focuses on providing consistency constraints and fixing rules when operating the spatio-temporal KG, and no work on actively detects the existing inconsistency in spatiotemporal KG. In this paper, we discuss and summarize the inconsistency in spatiotemporal KG firstly. Then we design algorithms to extract inconsistency semantic feature in spatiotem-poral KG, and finally we propose a spatiotemporal KG inconsistency detection model. The experimental results show that our method is scientific and effective.


Keywords: spatiotemporal knowledge graph, entity semantics, inconsistency detection, multi-classification, feature extraction

  Retrieve PDF document (JISE_202306_13.pdf)