基于机器学习的ERP财务管理系统异常检测  

Abnormality Detection of ERP Financial Management System Based on Machine Learning

作　　者：陈鹏岗[1] 李游 曹海信[3] 王科 CHEN Penggang;LI You;CAO Haixin;WANG Ke(The Second Affiliated Hospital of Xi’an Jiaotong University,Xi’an 710000,China;Zhongshan Nuclear Industry Group Geological Survey Institute Co.,Ltd.,Xi’an 710100,China;School of Physical Education,Xi’an Shiyou University,Xi’an 710000,China;School of Computer Science and Technology,Shandong University of Technology,Zibo 255000,China)

机构地区：[1]西安交通大学第二附属医院,陕西西安710000 [2]中陕核工业集团地质调查院有限公司,陕西西安710100 [3]西安石油大学体育学院,陕西西安710000 [4]山东理工大学计算机科学与技术学院,山东淄博255000

出　　处：《微型电脑应用》2024年第12期59-62,共4页Microcomputer Applications

基　　金：国家重点研发计划(2018YFC130078);陕西省中医药管理局课题项目(2020-yj010)。

摘　　要：财务管理关系到财务安全,对医院正常化运转影响巨大。传统财务管理异常检测存在主观性强、准确率低的问题,及时、精准检测医院财务管理系统异常至关重要。因此,对医院ERP财务管理系统模块进行分析,基于D-S证据理论构建财务管理系统异常检测模型,并将提出的财务管理系统异常检测模型用于某三甲医院财务管理系统历史数据的分析。将此模型与支持向量机模型进行对比,结果表明,D-S证据理论构建的系统异常检测模型具有更佳的异常检测性能,这为提升医院ERP财务管理系统异常检测的准确率、确保医院财务管理决策提供了有益的参考。Financial management is related to financial security and has a significant impact on the normal operation of hospitals.Traditional financial management abnormality detection has the problems of strong subjectivity and low accuracy.Timely and accurate detection of hospital financial management system abnormality is crucial.This paper analyzes the modules of the hospital ERP financial management system and constructs an abnormality detection model for the financial management system based on the D-S evidence theory.The proposed abnormality detection model for financial management systems is applied to analyze historical data in a third class hospital’s financial management system.Compared with the support vector machine model,the results show that the system abnormality detection model constructed by D-S evidence theory has better abnormality detection performance,which provides a reference for improving the accuracy of abnormality detection in the hospital ERP financial management system and ensuring the improvement of the hospital’s financial management level.

关 键 词：财务管理系统 异常检测 D-S证据理论 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]