Automatic Summarization System for English News Based on Machine Learning and Hybrid Intrusion Detection

ABSTRACT With the rapid development of information technology, massive amounts of English news data continue to emerge, and the threat to network security is becoming increasingly serious. Hybrid intrusion detection technology is receiving increasing attention. This study aims to develop a system for autonomously generating English news summaries by combining machine learning and network security as a hybrid intrusion detection method. The study first conducts text summarization generation by constructing a powerful summarization generation model and utilizing grammar rules to process and compress news texts. In the research of hybrid intrusion detection, we extract the temporal features of network data to identify potential security threats and design a multi‐layer hybrid classification intrusion detection model to improve the accuracy and efficiency of detection. Afterwards, a system requirements analysis was conducted, and the overall process and functional design of the system were developed. Performance testing and evaluation were also conducted on the system. After system testing, we found that the generated English news summaries achieved the expected results in terms of information retention and conciseness. The hybrid intrusion detection model has successfully identified and defended against various network attacks, enhancing the security of the system.