MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202621068908 A) filed by Symbiosis International Deemed University on June 01, 2026, for A System And Method For Multimodal Agentic Ai-Based Context-Aware Legal Reasoning And Judicial Decision Support.
Inventors include Arav Saxena; Adesh Jain; Khushi Kashyap; Kartik Mehta; Dr. Shivali Amit Wagle; Dr. Shruti Patil; and Dr. Ketan Kotecha.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: ABSTRACT A SYSTEM AND METHOD FOR MULTIMODAL AGENTIC AI-BASED CONTEXT-AWARE LEGAL REASONING AND JUDICIAL DECISION SUPPORT The present invention discloses the Legal-Search System (100), a multimodal, agentic, explainable artificial intelligence-based framework for context-aware legal reasoning and judicial decision support within the Indian judiciary. The system processes heterogeneous legal inputs including textual documents, scanned records, and voice-based oral submissions through a Legal Document Acquisition Module (110) and Multimodal Input Handler (120). A Preprocessing and Embedding Generation Module (130) employing a Domain-Adapted Legal Language Model (130A) generates domain-specific semantic embeddings. A Hybrid Retrieval Engine (140) combining BM25 and dense semantic search retrieves relevant precedents from a Legal Knowledge Repository (190). An Agentic AI Reasoning Module (150) comprising chain-of-thought, entity extraction, and statement consistency agents performs multi-step legal inference. A Hierarchical Temporal Legal Consistency Graph Engine (160) computes Legal Entity Drift Scores to detect loopholes and validates inferences through Cascading Validation Agents (160C). An Explainable AI Layer (170) provides citation-backed transparent outputs presented through a Judicial Review Interface (180), enabling efficient, transparent, and reliable judicial decision support. [
Disclaimer: Curated by HT Syndication.
