PERSONALIZED MULTI DOCUMENT TEXT SUMMARIZATION USING DEEP LEARNING TECHNIQUES

The invention introduces a deep learning-based system for Personalized Multi-Document Text Summarization, leveraging the GPT-4o model to generate concise, coherent, and user-customized summaries. The system processes multiple text documents, extracts key information, and generates summaries based on user-defined preferences such as length, focus areas, and keywords.

GPT-4o, a state-of-the-art transformer model, enhances the summarization process by understanding contextual relationships and semantic structures within large text corpora. Unlike traditional summarization methods, this approach incorporates reinforcement learning to refine summaries based on user feedback, ensuring continuous improvement and relevance. The system supports various domains, including academic research, journalism, and business intelligence, making it adaptable to diverse needs.

The architecture consists of a Flask-based backend integrated with GPT-4o for text processing and an HTML-CSS-based frontend, allowing users to upload documents and retrieve personalized summaries in real time. The model is trained on vast datasets to optimize coherence, readability, and factual accuracy. By leveraging advanced deep learning techniques, this system offers a scalable, efficient, and interactive solution for managing large volumes of textual information, significantly reducing manual effort while improving summary quality.

Key Words:  Multi-document summarization, GPT-4o, deep learning, personalized summaries, reinforcement learning, text processing, NLP, automation.

. GPT-4o a state-of-the-art transformer model enhances the summarization process by understanding contextual relationships and semantic structures within large text corpora. Unlike traditional summarization methods this approach incorporates reinforcement learning to refine summaries based on user feedback ensuring continuous improvement and relevance. The system supports various domains including academic research journalism and business intelligence making it adaptable to diverse needs. The architecture consists of a Flask-based backend integrated with GPT-4o for text processing and an HTML-CSS-based frontend allowing users to upload documents and retrieve personalized summaries in real time. The model is trained on vast datasets to optimize coherence readability and factual accuracy. By leveraging advanced deep learning techniques this system offers a scalable efficient and interactive solution for managing large volumes of textual information significantly reducing manual effort while improving summary quality. Key Words:  Multi-document summarization GPT-4o deep learning personalized summaries reinforcement learning text processing NLP automation.