MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122167 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'hybrid deep learning system for legal document summarization.'
Inventor(s) include Dr. Nalinin; Mr. Sanjeev Ragunathan; Mr. Rohan Murali; and Ms. Gursheen Pal.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a hybrid deep learning system for legal document summarization. The system includes a preprocessing module configured to tokenize legal documents into sentences, a feature extraction module having a domain-specific legal language model embedding generator configured to generate semantic embeddings for each sentence and a legal dictionary scoring component configured to assign importance scores based on legal terminology presence, a hybrid scoring mechanism configured to combine semantic embeddings and dictionary-based scores to generate unified sentence ranking scores, a graph construction module configured to create sentence similarity graphs where nodes represent sentences and edges represent semantic relationships, a graph neural network configured to process the graphs and rank sentences based on contextual relevance for extractive summarization, and a transformer-based abstractive summarization module configured to refine extractive summaries into coherent final summaries."
Disclaimer: Curated by HT Syndication.
