图书情报工作 ›› 2019, Vol. 63 ›› Issue (23): 106-112.DOI: 10.13266/j.issn.0252-3116.2019.23.012

• 情报研究 • 上一篇    下一篇

高校图书馆复杂网络构建与智慧化应用探索

施国良1, 谢泽宇1, 杨小莉2   

  1. 1. 河海大学商学院 南京 211100;
    2. 河海大学图书馆 南京 211100
  • 收稿日期:2019-03-03 修回日期:2019-07-02 出版日期:2019-12-05 发布日期:2019-12-05
  • 通讯作者: 谢泽宇(ORCID:0000-0003-4330-0815),硕士研究生,通讯作者:E-mail:18260062705@163.com
  • 作者简介:施国良(ORCID:0000-0001-7585-640X),副教授,博士;杨小莉(ORCID:0000-0001-8939-7232),技术部主任,副研究馆员,硕士。

The Construction and Intelligent Applications of Complex Network in University Library

Shi Guoliang1, Xie Zeyu1, Yang Xiaoli2   

  1. 1. Business School, Hohai University, Nanjing 211100;
    2. Hohai University Library, Nanjing 211100
  • Received:2019-03-03 Revised:2019-07-02 Online:2019-12-05 Published:2019-12-05

摘要: [目的/意义] 高校图书馆信息化水平高,但数据挖掘与智慧化水平有待提升。复杂网络以图数据库为存储和图查询的载体,对图结构数据进行统一组织和挖掘。图嵌入、图算法技术相较于传统机器学习方法能够充分挖掘图结构数据中的隐含联系。本研究运用复杂网络技术融合多源数据,探索图嵌入技术、图算法等图结构数据挖掘方法在提升图书馆智慧化水平中的作用。[方法/过程] 首先基于可获取的数据进行数据特征分析与清洗;其次结合数据特征构建复杂网络概念模型,采用Neo4j批量导入技术实现网络构建和存储;最后探索图算法、图嵌入技术在图结构数据挖掘中的应用。[结果/结论] 以图结构融合多源数据构建图书馆复杂网络,并以图数据库作为存储介质。图算法与图嵌入技术在在用户画像分析、精准推荐、智能问答等图书馆智能化应用等方面具有独特优势。

关键词: 复杂网络, 图数据库, 图算法, 图嵌入, 智慧图书馆

Abstract: [Purpose/significance] The informatization level of university libraries is high, but the level of data mining and intelligence needs to be improved. The complex network uses graph database as the carrier of storage and graph query to organize and mine graph structure data. Compared with traditional machine learning methods, graph embedding and graph algorithm techniques can discover hidden connections in graph. This study uses complex network to integrate multi-source data and explores the role of graph data mining methods such as graph embedding and graph algorithms in improving library intelligence level.[Method/process] First of all, this study clarifies and analyzes the characteristics of the data based on the available data. Secondly, combined with the characteristics of data, construct a complex network conceptual model, and use Neo4j batch import technology to realize network construction and storage. Finally, explore the application of graph algorithm and graph embedding technology in graph structure data mining.[Result/conclusion] The multi-source data is combined with the graph structure to construct the complex network of the library, and the graph database is used as the storage medium. Graph algorithm and graph embedding technology have unique advantages in user image analysis, accurate recommendation, intelligent QA, and other intelligent applications of the library.

Key words: complex network, graph database, graph algorithms, graph embedding, intelligent library

中图分类号: