MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202621069795 A) filed by Bharati Vidyapeeth Deemed To Be University College Of Engineering, Pune on June 03, 2026, for A System And Method For Privacy-Preserving Offline Language-To-Visualization Conversion.
Inventors include Priyanka Paygude; Manisha Kasar; Milind Gayakwad; Rohini Khalkar; Harshada Mhetre; Dr. Sachin Chavan; and Sandeep Dasnam.
The application for the patent was published on July 24, 2026, under issue no. 30/2026.
Abstract: ABSTRACT A SYSTEM AND METHOD FOR PRIVACY-PRESERVING OFFLINE LANGUAGE-TO-VISUALIZATION CONVERSION The present disclosure relates to a system and method for privacy-preserving offline language-to-visualization conversion. The system (100) operates in an offline mode without internet connectivity and without transmitting any intermediate representation of a natural language query outside a local computing device. The system (100) includes a user interface (102) configured to receive the natural language query and a locally deployed small language model processing engine (104) executable by a processor (106). The processor (106) extracts one or more data entities, determines a visualization intent, and converts the extracted data entities and visualization intent into a machine- executable structured database query executed against a locally accessible data repository. The processor (106) analyzes structural characteristics of a query result set and automatically determines a visualization configuration comprising a chart type and rendering parameters. The query result set and visualization configuration are rendered on a display of the system (100). FIG. 1 will be the reference figure.
Disclaimer: Curated by HT Syndication.
