View in EDS

A Study of Knowledge Graph and IoT Integration-Based Anomalous Event Tracking Method for Digital Platforms.

Saved in:
Bibliographic Details
Title: A Study of Knowledge Graph and IoT Integration-Based Anomalous Event Tracking Method for Digital Platforms.
Authors: Zhou, Digui1 (AUTHOR) diguicsg@126.com, Tan, Qiwen1 (AUTHOR), Huang, Hualin1 (AUTHOR), Huang, Qi1 (AUTHOR), Qin, Ning1 (AUTHOR)
Source: International Journal of High Speed Electronics & Systems. Dec2025, Vol. 34 Issue 4, p1-24. 24p.
Subjects: Association rule mining, Knowledge graphs, Convolutional neural networks, Flowgraphs, Digital platforms, Graph algorithms
Abstract: In digital platforms, abnormal events involve multiple data sources and complex information types, and the difficulty of tracking them increases due to the similarity and interaction between components, operations, and user behavior. Therefore, in order to achieve precise tracking and efficient processing of abnormal events, and thereby improve the stability and security of the platform, a digital platform abnormal event tracking method based on a knowledge graph is proposed. First, using data mining and association rule techniques, abnormal event data in the digital platform are effectively collected and integrated. Subsequently, the data are input into a model that integrates residual atrous convolutional neural networks and conditional random fields to achieve precise identification of key entities. On the basis of entity recognition, the correlation between entities is extracted and a knowledge graph architecture for abnormal events is constructed, providing a solid foundation for subsequent deep analysis. Through a visual interface, the knowledge graph of abnormal events can be intuitively displayed, making it easy for users to quickly understand the full picture of the event. At the same time, the knowledge graph subgraph matching algorithm is adopted, combined with flow graph indexing and optimal matching sequence, to achieve accurate tracking and recognition of abnormal events. The experimental results show that this method can effectively track abnormal events in the digital platform. The first detection time is relatively short, with a mishandling time of 8.3 s and data duplication of 7.9 s. The continuous tracking time is long, with a security vulnerability of 50 min. The false alarm rate is low, with the highest being 2.1% for data duplication, and the false miss rate is also low, with the highest being 0.8% for mishandling. This method can identify the number of abnormal events, which helps to understand the stability and health status of the platform. By timely and effectively preventing abnormal events, the frequency of their occurrence can be reduced, and the overall security and stability of the platform can be improved. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of High Speed Electronics & Systems is the property of World Scientific Publishing Company and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:In digital platforms, abnormal events involve multiple data sources and complex information types, and the difficulty of tracking them increases due to the similarity and interaction between components, operations, and user behavior. Therefore, in order to achieve precise tracking and efficient processing of abnormal events, and thereby improve the stability and security of the platform, a digital platform abnormal event tracking method based on a knowledge graph is proposed. First, using data mining and association rule techniques, abnormal event data in the digital platform are effectively collected and integrated. Subsequently, the data are input into a model that integrates residual atrous convolutional neural networks and conditional random fields to achieve precise identification of key entities. On the basis of entity recognition, the correlation between entities is extracted and a knowledge graph architecture for abnormal events is constructed, providing a solid foundation for subsequent deep analysis. Through a visual interface, the knowledge graph of abnormal events can be intuitively displayed, making it easy for users to quickly understand the full picture of the event. At the same time, the knowledge graph subgraph matching algorithm is adopted, combined with flow graph indexing and optimal matching sequence, to achieve accurate tracking and recognition of abnormal events. The experimental results show that this method can effectively track abnormal events in the digital platform. The first detection time is relatively short, with a mishandling time of 8.3 s and data duplication of 7.9 s. The continuous tracking time is long, with a security vulnerability of 50 min. The false alarm rate is low, with the highest being 2.1% for data duplication, and the false miss rate is also low, with the highest being 0.8% for mishandling. This method can identify the number of abnormal events, which helps to understand the stability and health status of the platform. By timely and effectively preventing abnormal events, the frequency of their occurrence can be reduced, and the overall security and stability of the platform can be improved. [ABSTRACT FROM AUTHOR]
ISSN:01291564
DOI:10.1142/S0129156425403146