Legal professionals face challenges in managing large case volumes, particularly in fast-track courts, necessitating efficient tools for analysis and decision-making. This research integrates NLP, DL, and ML techniques to enhance legal document analysis by automating key processes. PEGASUS summarization combined with DBSCAN and cosine similarity reduces redundancy and extracts essential content, while regex, spaCy, and SentenceTransformer improve entity recognition, syntactic parsing, and structured data generation. Among the tested models, ANN with SMOTE outperformed others, achieving an accuracy of 84.75/100 and an F1-score of 0.85 compared to conventional models with metadata integration, i.e. the summarised version than the entire document. The integration of structured data extraction and noise reduction from the case documents further enhanced classification performance. These advancements demonstrate the potential of AI-driven approaches in revolutionizing legal case management, improving judicial efficiency, and supporting faster decision-making in high-volume court environments.