数据挖掘
计算机科学
标准化
大数据
规范化(社会学)
数据建模
原设备制造商
政府(语言学)
数据科学
情报检索
数据库
语言学
哲学
社会学
人类学
操作系统
作者
Keiin Sa,Yu Bai,Chenggang Wang
标识
DOI:10.1109/qrs54544.2021.00114
摘要
In order to acquire the required knowledge from the vast amounts of government affairs data, accurate data mining has important practical significance. Therefore, a precision mining method of government affairs big data based on E-OEM model is studied. The method firstly uses web crawlers to capture the vast amounts of government data. Government data then performs data cleaning, pattern normalization, format standardization, index information collection and pre-processing, and finally, according to the purpose of data mining, the Kirkpatrick model is used to complete the mining effect evaluation. Experimental comparison specifically includes correlation analysis, cluster analysis, classification analysis, exception analysis and evolution analysis as well as five others. The results show that: compared with the three methods in previous studies, the F1-score obtained by the application of the research method is higher (0.852), which proves that the quality of government affairs big data mining is better.
科研通智能强力驱动
Strongly Powered by AbleSci AI