Confidential information protection method of commercial information physical system based on edge computing

• Published in: Neural computing & applications Vol. 33; no. 3; pp. 897 - 907
• Main Authors: Zhang, Xiaheng, Lu, Jiazhong, Li, Doudou
• Format: Journal Article
• Language: English
• Published: London Springer London 01.02.2021; Springer Nature B.V
• Subjects: Access control; Artificial Intelligence; Authentication; Business information; Cloud computing; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data analysis; Data Mining and Knowledge Discovery; Edge computing; Electronic devices; Image Processing and Computer Vision; Internet of Things; Mobile computing; Privacy; Probability and Statistics in Computer Science; S.i. : Atci 2020; Security; Security management; Special Issue on ATCI 2020; Confidential protection; Data security; Identity authentication; Business information physical system; Edge computing
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-020-05272-0

With the rapid integration and wide application of the enterprise Internet of Things, big data and 5G-class large networks, traditional enterprise cloud computing systems cannot timely process various mass information data generated by connecting with network edge electronic devices. There are obvious technical disadvantages. In order to effectively solve this complex problem, edge mobile computing came into being. The purpose of this article is to study the protection methods of commercial confidential information, using the security relationship between data information in edge technology computing and the technical characteristics of data privacy information protection. This paper proposes a theoretical system and technical architecture centered on the use of data security technology. The three key technologies of access control, identity authentication and information privacy security protection are researched on the privacy protection processing methods of commercial information security physical systems. The experimental data show that the recognition errors mainly occur in identifying non-anomalous data as abnormal data. The analysis and identification of abnormal information data are basically accurate, and it can quickly complete various processing tasks to eliminate abnormal information data to meet the requirements. The experimental data show that the abnormal data can be used to monitor the security of the commercial information physical system, and it is also a good security protection method for commercial confidential information. It has guiding significance for the confidential information protection of commercial information physical systems. In the next few years, more than 50% of major data applications will need to be analyzed, processed and data stored at the edge of the network. Cloud computing technologies at the edge are widely used.