摘要
随着脑科学相关问题的研究逐年增长,与脑科学领域的相关文本信息越来越多。由此,如何利用知识图谱技术实现脑科学领域知识的集成、分析、挖掘与再利用受到了研究者们的关注。为了解目前知识图谱的方法在脑科学领域的应用状况,通过调研现有相关文献,有如下总结:在方法应用上,知识图谱的相关方法在脑科学领域的应用主要集中在实体以及实体关系抽取上,很少被用于后续的数据挖掘与推理;在平台的构建上,存在着平台缺乏良好维护的问题;而在认知功能脑知识图谱上,大多都是与脑灰质相关,未能很好地联系到脑白质,忽略了脑白质所处的作用。此外,该文简述了现有利用知识图谱相关技术所构建的应用与工具,并对比分析了它们的优缺点。综合以上调研,针对脑科学领域的知识图谱应用与发展,提出对未来的展望。
As the research on brain science-related issues grows year by year,more and more relevant literature in the field of brain science.Therefore,how to use knowledge graph technology to realize the integration,analysis,mining and reuse of literature knowledge in the brain science field has attracted the attention of researchers.In order to understand the application status of the current knowledge graph method in the field of brain science,the following summary is made by investigating the existing relevant literature.First of all,from an application perspective,the application of knowledge graph in the field of brain science mainly focuses on entity and entity relationship extraction,and is rarely used for subsequent data mining and reasoning at the current stage.In the construction of the platform,there is a lack of good maintenance of the platform.On the cognitive function brain knowledge map,most of them are related to the gray matter of the brain,and fail to take the white matter into consideration which ignores the role of the white matter in human cognition.Secondly,we briefly describe the current applications and tools constructed by using knowledge graph-related technologies,and analyze and compare their advantages and disadvantages.Finally,for the construction and development of knowledge graphs in the field of brain science,we propose a prospect for the future.
作者
王婷
何松泽
杨川
WANG Ting;HE Song-ze;YANG Chuan(School of Computer Science,Chengdu University of Information Technology,Chengdu 610225,China)
出处
《计算机技术与发展》
2022年第11期1-7,共7页
Computer Technology and Development
基金
国家自然科学基金资助项目(61806029)。
关键词
知识图谱
自然语言处理
脑科学
机器学习
深度学习
knowledge graph
natural language processing
brain science
machine learning
deep learning
作者简介
通讯作者:王婷(1990-),女,副教授,硕导,博士,研究方向为功能磁共振图像分析处理。
