图书情报工作 ›› 2022, Vol. 66 ›› Issue (20): 20-31.DOI: 10.13266/j.issn.0252-3116.2022.20.003

• 北京大学信息管理系成立75周年学术专辑 • 上一篇    下一篇

大数据环境下知识融合技术体系研究

陈沫, 李广建   

  1. 北京大学信息管理系 北京 100081
  • 收稿日期:2022-07-29 修回日期:2022-08-26 出版日期:2022-10-20 发布日期:2022-11-17
  • 通讯作者: 李广建,教授,博士,博士生导师, 通信作者,E-mail:ligj@pku.edu.cn。
  • 作者简介:陈沫,博士研究生
  • 基金资助:
    本文系国家社会科学基金重大项目"大数据时代知识融合的体系架构、实现模式及实证研究"(项目编号:15ZDB129)研究成果之一。

Research on the Knowledge Fusion Technology Taxonomy in Big Data Environment

Chen Mo, Li Guangjian   

  1. Department of Information Management, Peking University, Beijing 100871
  • Received:2022-07-29 Revised:2022-08-26 Online:2022-10-20 Published:2022-11-17

摘要: [目的/意义] 研究在大数据环境下多源知识融合的关键技术,结合不同领域多源知识对象的特点构建出一整套技术体系,为知识融合的落地实现提供技术支撑和解决方案。[方法/过程] 运用定性分析法对现有的相关研究进行分析,再对相关内容进行归纳和演绎,利用文献分析法,梳理知识融合要解决的问题,归纳总结知识融合的任务类型以及实现各种任务所需的工作流程及其涉及的具体技术,形成知识融合技术体系。[结果/结论] 综合考虑各种技术的自身特性、适用的知识对象、应用的抽象层次,建立具有计算层、功能层和任务层三个层次的技术体系架构。这三个层次相互联系、相互影响、环环相扣,向上可以抽象,可以与知识融合的具体问题(任务)相关联;向下可以具化,即找到解决知识融合具体问题的可操作、可计算的技术方法。

关键词: 知识融合, 技术体系, 大数据

Abstract: [Purpose/Significance] This paper mainly studies the key technologies of multi-source knowledge fusion in the big data environment, and proposes a complete set of technology taxonomy based on the characteristics of multi-source knowledge objects in different fields to provide technical support and solutions for the realization of knowledge fusion. [Method/Process] The study utilized qualitative analysis method to analyze the existing related research, and then within the same hierarchical level on the related contents of induction and deduction, used literature analysis method, to solve the problem of combing knowledge fusion, sum up the knowledge integration of task type and implement various tasks involved in the work process and its specific technology, and form a knowledge fusion system. [Result/Conclusion] Considering all kinds of technology's own characteristics, applicable knowledge objects, the application of abstraction of knowledge, the paper establishes the calculating layer, function layer and mission layer-three levels of technical architecture. These three layers contact each other, influence each other and interlock each other. The upper layer can be abstracted and associated with specific problems (tasks) of knowledge fusion. The lower layer can be embodied, that is, to find operational and computable technical methods to solve specific problems of knowledge fusion.

Key words: knowledge fusion, technology system, big data

中图分类号: