摘要
招生工作作为高职院校发展的关键,如何招收到更多优秀生源,合理分配招生计划已经成为困扰高职院校发展的突出问题。针对这个问题,设计实现了基于数据仓库的高职院校招生管理系统。以云南省某高职院校2021—2023年的招生信息为数据源,首先进行数据清洗,通过Hive数据仓库实现数据分层存储,借助Spark数据计算引擎的MLlib机器学习库实现FP-Growth算法挖掘数据的关联规则,进而实现了对学校招生信息数据的管理、分析、决策功能。
As the key to the development of higher vocational colleges,how to recruit more excellent students and reasonably allocate enrollment plans has become a prominent problem that has plagued the development of higher vocational colleges.In view of this problem,the admission management system for higher vocational colleges based on data warehouse is designed and implemented.The system takes the admission information of a higher vocational college in Yunnan Province from 2021 to 2023 as the simulation data.Firstly,data cleaning is carried out,and the hierarchical storage of data is realized through Hive data warehouse.With the help of MLlib machine learning library of Spark data computing engine,the association rules of data are mined by FPG-rowth algorithm,and then the management,analysis and decision-making functions of school admission information data are realized.
作者
刘发稳
容会
杨涓海
吴芸
殷洪杰
Liu Fawen;Rong Hui;Yang Juanhai;Wu Yun;Yin Hongjie(Faculty of Computer Information,Kunming Metallurgy College,Kunming 650033,China;Department of Admission and Employment,Kunming Metallurgy College,Kunming 650033,China;Marxism College of Yunnan Light and Textile Industry Vocational College,Kunming 650033,China)
出处
《现代计算机》
2024年第13期89-94,共6页
Modern Computer
基金
昆明冶金高等专科学校科研基金项目(2020XJZK05、2021XJZK06、2021XJZK11)。