MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122467 A) filed by Malla Reddy (MR) Deemed to be University; Malla Reddy Engineering College For Women; Malla Reddy College Of Engineering And Technology; Malla Reddy Vishwavidyapeeth; and Malla Reddy University, Malkajgiri, Telangana, on Dec. 5, 2025, for 'neural symbolic engine for semantic search on academic repositories.'
Inventor(s) include Dr. Shaik Javed Parvez; Mr. Kalyana Chakravarthi Agnihothram; Manoj Kumar Gottimukkala; Mr. Santi Satyanarayana; and Dr. S. Ravi Kumar.
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: "A neural-symbolic engine for performing semantic search and contextual reasoning processes is designed and applied with better accuracy and interpretability over repositories of scholarly literature. The framework is a combination of neural representation of language (which relies on statistics) and representations of logic and symbolic inference to bridge the gap between statistical learning in logic. It interprets complex user queries and connects them to domain specific ontologies and retrieves contextual relevant research materials beyond a primitive search by keyword. Academic papers, abstract, citations and metadata are used by the system to construct the hybrid semantic knowledge graph. Neural aspects pick up some of the linguistic and semantic embeddings, while symbolic layers of reasoning carry information about relationships (connection: authorship, methodology, topic hierarchy, etc.). During query processing, the engine matches the input natural language input with the structured for elucidating the retrieval path thus the user can track how the results were arrived at. This hybrid reasoning model enables the level of precision, openness and cross-domain linkage discovery to be increased in various scientific disciplines. Scalable learning: Orencio also has an architecture that supports scalable indexing, adaptive learning and ontology expansion which make it compatible with larger institutional databases and digital libraries. Comparative evaluations reveal substantial improvement over retrieval depth and interpretability and user trust variables as compared to traditional keyword and neural only search systems. The framework gives a robust and explainable basis to intelligent academic information discovery."
Disclaimer: Curated by HT Syndication.
