Association Analysis of Abnormal Behavior of Electronic Invoice Based on K-Means and Skip-Gram
2019 IEEE Fourth International Conference on Data Science in Cyberspace (DSC)(2019)
摘要
Electronic invoice is the product of the information age. The issuance of electronic invoice greatly saves the cost of enterprises and provides more convenient services for consumers. At present, our country is vigorously promoting electronic invoices, but there are also some abnormal behaviors in the process of circulation of electronic invoices, such as false invoices reimbursement, over-quota invoices and so on. This paper designed and implemented a deep fusion analysis method of electronic invoices based on K-means and Skip-gram. On the basis of abnormal behavior of electronic invoices, it carries out correlation analysis, excavates abnormal relationship between users and enterprises in the process of electronic invoices circulation, and provides support for the normal operation of electronic invoice service system. In this paper, the model is trained on the abnormal behavior data of electronic invoices. The accuracy of the model is 76% in the inter-enterprise association analysis and 85% in the inter-user association analysis.
更多查看译文
关键词
electronic invoice,abnormal behavior,association analysis,K-means,Skip-gram
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要