arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.04888cs.DLcs.AIcs.LG
收藏

科技学术会议的知识图谱与精准画像构建

Knowledge Graph and Accurate Portrait Construction of Scientific and Technological Academic Conferences

Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, School of Computer Science (National Pilot School of Software Engineering), Beijing University of Posts and Telecommunications(北京智能电信软件与多媒体重点实验室,计算机学院(国家软件工程试点学院),北京邮电大学)

Runyu Yu, Zhe Xue, Ang Li

AI总结:

针对科技学术会议海量数据致研究人员难高效获有价值信息的问题,运用深度学习、知识图谱等技术,综述构建会议知识图谱与精准画像的关键技术,助力会议知识服务构建及研究人员快速获取科学信息。

摘要:

近年来,随着科技不断进步,科研成果数量迅速增加。作为科研成果交流平台和媒介,科技学术会议日益丰富。学术会议召开带来大量论文、研究人员、机构、项目及研究主题,但海量会议数据使研究人员难以高效获取有价值信息。利用深度学习、知识图谱技术、语义相似度计算和画像建模从会议数据挖掘核心信息很有意义。本文综述了构建科技学术会议知识图谱和精准画像的关键技术,包括命名实体识别、语义文本相似度、趋势预测、图存储、搜索引擎及可视化组件。这些技术共同支持会议知识服务构建,助研究人员更快获取科学信息。

英文摘要:

In recent years, with the continuous progress of science and technology, the number of scientific research achievements has increased rapidly. As an exchange platform and medium for scientific research achievements, scientific and technological academic conferences have become increasingly abundant. The convening of academic conferences brings large numbers of papers, researchers, institutions, projects, and research topics, but massive conference data also makes it difficult for researchers to obtain valuable information efficiently. It is therefore meaningful to use deep learning, knowledge graph technology, semantic similarity calculation, and portrait modeling to mine core information from conference data. This paper reviews the key technologies for constructing knowledge graphs and accurate portraits of scientific and technological academic conferences, including named entity recognition, semantic text similarity, trend prediction, graph storage, search engines, and visualization components. These techniques jointly support the construction of conference knowledge services that help researchers acquire scientific information more quickly.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑