MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123124 A) filed by Malla Reddy (MR) Deemed to be University; Malla Reddy University; Malla Reddy College Of Engineering And Technology; Malla Reddy Vishwavidyapeeth; Malla Reddy Engineering College For Womens; and Dr. S. Mahipal, Medchal-Malkajgiri, Telangana, on Dec. 6, 2025, for 'ai enabled semantic search engine for legal case retrieval.'
Inventor(s) include Dr. S. Mahipal; Dr. K. Asish Vardhan; G. Likitha; Mrs. Sheetal Kulkarni; Mr. Venkata Ramana S; and K. Jyothi.
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: "Legal professionals frequently search through immense bodies of case laws, statues, judgments, and legal commentaries with the aim of finding information relevant to a particular argument or legal question. Traditional keyword-based search engines will often return incomplete or irrelevant results because of the complexity of legal language and the dependency on the context of that language as well as the various and nuanced interpretations of the same language. An AI-powered semantic search engine overcomes these limitations by examining the meaning, intent and relationship in context of the texts in the legal domain, not just as a search engine based on keyword. The system constructs legal documents in terms of semantics, leveraging the power of natural language processing along with both natural language domain-specific embeddings and contextual similarity models. When a query is entered, the engine interprets the legal issue underlying this query and identifies relevant principles and retrieves cases that were similar to the conceptual meaning, not the surface level wording. The approach makes it possible to better identify precedents, even if different terminology is applied in different jurisdictions or time periods. The engine contains relevance scoring mechanisms that consider such factors as the legal context, hierarchy of cases, jurisdictional weight, stage in the procedures, and similarity to factual patterns presented in the query. The models of machine learning technology are continually improving the accuracy of retrievals depending on user interactions, citation patterns, and the input right from legal professionals. By focusing on conceptual understanding rather than the search of literal keywords, the system dramatically decreases the amount of time spent on research while increasing the precision of case retrieval. The framework also supports courts, law firms and academic researchers, as well as compliance teams by providing reliable results which are delivered in their workplace or fewer instances and are context-aware because ones are aligned with legal reasoning rather than with simple textual similarity."
Disclaimer: Curated by HT Syndication.
