Biological Classification System Knowledge Graph and Semi-automatic Construction of Its Invertebrate Fossil Branches  

作　　者：Shaochun Dong Yukun Shi Yizao Ran Haijun Wu Yiying Deng Junxuan Fan Xinyu Dai 

机构地区：[1]School of Earth Sciences and Engineering,Frontiers Science Center for Critical Earth Material Cycling,Nanjing University,Nanjing,210046,China [2]Jiangsu Deep-Time Digital Earth Research Center for Excellence,Suzhou,215004,China [3]School of Computer Science,Nanjing University,Nanjing,210046,China [4]School of Resources and Environmental Engineering,Hefei University of Technology,Hefei,230009,China [5]State Key Laboratory for Mineral Deposits Research,Nanjing,210046,China [6]National Key Laboratory for Novel Software Technology,Nanjing,210046,China

出　　处：《Journal of Earth Science》2024年第6期2119-2128,共10页地球科学学刊（英文版）

基　　金：supported by the National Key R&D Program of China(No.2018YFE0204201);the National Natural Science Foundation of China(Nos.92255301,42302001);Jiangsu Innovation Support Plan for International Science and Technology Cooperation Programm(No.BZ2023068)。

摘　　要：Biological classification is the foundation of biology and paleontology,as it arranges all the organisms in a hierarchy that humans can easily follow and understand.It is further used to reconstruct the evolution of life.A biological classification system(BCS)that includes all the established fossil taxa would be both useful and challenging for uncovering the life history.Since fossil taxa were originally recorded in various published books and articles written by natural languages,the primary step is to organize all those taxa information in a manner that can be deciphered by a computer system.A Knowledge Graph(KG)is a formalized description framework of semantic knowledge,which represents and retrieves knowledge in a machine-understandable way,and therefore provides an eligible method to represent the BCS.In this paper,a model of the BCS KG including the ontology and fact layers is presented.To put it into practice,the ontology layer of the invertebrate fossil branches was manually developed,while the fact layer was automatically constructed by extracting information from 46 volumes of the Treatise of Invertebrate Paleontology series with the help of natural language processing technology.As a result,27348 taxa nodes spanning fourteen taxonomic ranks were extracted with high accuracy and high efficiency,and the invertebrate fossil branches of the BCS KG was thus installed.This study demonstrates that a properly designed KG model and its automatic construction with the help of natural language processing are reliable and efficient.

关 键 词：biological classification system knowledge graph ONTOLOGY invertebrate fossil big data 

分 类 号：Q915.2[天文地球—古生物学与地层学]