基于文本过滤技术的多来源高校财务数据智能聚合方法  

Intelligent aggregation method of multi-source university financial databased on text filtering technology

作　　者：何秀楠 薛亚琴 陈晓红[2] HE Xiunan;XUE Yaqin;CHEN Xiaohong(Department of Finance,Nantong University,Nantong 226000,China;School of Information Science and Technology,Nantong University,Nantong 226000,China)

机构地区：[1]南通大学财务处,江苏南通226000 [2]南通大学信息科学技术学院,江苏南通226000

出　　处：《无线互联科技》2024年第21期107-109,共3页Wireless Internet Science and Technology

摘　　要：高校财务数据来源广泛且数量庞大,影响了财务数据的利用效率。针对这一问题,文章提出了基于文本过滤技术的多来源高校财务数据智能聚合方法,先爬取并预处理多来源高校财务文本数据,利用朴素贝叶斯分类器,结合类别阈值设计文本过滤技术,过滤多来源高校财务数据中的不良文本;然后通过Jaro-Winkler相似度匹配算法将过滤后文本聚合在一起,实现多来源高校财务数据智能聚合。实验结果表明,应用该方法后,多来源高校财务数据智能聚合结果的归一化互信息高达0.918,聚合效果优越。The extensive and massive sources of financial data in universities have affected the efficiency of financial data utilization.In response to this issue,this study proposes an intelligent aggregation method for financial data from multiple sources of universities based on text filtering technology.Firstly,crawl and preprocess financial text data from multiple sources of universities,use naive Bayesian classifiers,and design text filtering techniques combined with category thresholds to filter out bad texts in financial data from multiple sources of universities.Then,the filtered text is aggregated together using the Jaro Winkler similarity matching algorithm to achieve intelligent aggregation of multi-source university financial data.The experimental results show that after applying this method,the normalized mutual information of the intelligent aggregation results of financial data from multiple sources of universities is as high as 0.918,and the aggregation effect is superior.

关 键 词：文本过滤技术 多来源数据 高校财务数据 数据聚合 智能聚合方法 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]