Haobai Sun, Jingyi Shi, Hou Shu, Weixiao Hu

Hou Shu

August 31, 2025

Big data clustering technology, Historical press articles, Engineering-oriented management, Knowledge discovery, Data preprocessing, Feature engineering, Cluster analysis, Knowledge graph.

With the rapid development of information technology, press institutions have accumulated vast amounts of historical article data. However, traditional manual management models face significant challenges in processing efficiency and deep Knowledge Discovery, urgently necessitating intelligent solutions. This study proposes and validates an engineering-oriented management optimization scheme for historical press articles based on big data clustering technology. The scheme aims to significantly enhance the management efficiency and knowledge discovery potential of Historical Press Articles through automated data processing workflows and intelligent knowledge organization methods. Core components encompass: a rigorous data preprocessing pipeline, feature engineering integrating traditional statistical features and deep learning semantic features, clustering algorithm selection and optimization strategies, a multi-dimensional clustering result evaluation system, and application scenario design tailored to practical management needs. Through empirical analysis using real-world cases, this study validates the effectiveness and practicality of the scheme in improving historical press article management efficiency, optimizing knowledge organization structures, and enhancing knowledge service capabilities. The research outcomes provide actionable technical pathways and engineering paradigms for press institutions to revitalize historical data assets and build knowledge-centric management systems.

© 2025, the Authors. Published by ISCCAC

This is an open access article distributed under the CC BY-NC license