MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202641098611 A) filed by Indian Institute Of Technology Madras Iit Madras on August 14, 2026, for System And Method For Automated Report Generation From Multimodal Input Data.
Inventors include Rengaswamy, Jayaganthan; Guduguntla, Jyotsna Sree; and Kabra, Apoorva.
The application for the patent was published on August 21, 2026, under issue no. 34/2026.
Abstract: Disclosed herein are a system (100) and a method (300) for automated report generation from multimodal input data. The method comprises receiving, by an input parser and router module, the multimodal input data comprising a plurality of images and metadata corresponding to the plurality of images. The method further comprises retrieving, by a knowledge retrieval module using the plurality of images and the metadata, a candidate concept shortlist and associated knowledge graph information from a biomedical knowledge graph. The method further comprises generating, by a signal encoder module, a respective vision score for each candidate concept in the candidate concept shortlist. The method further comprises generating, by a knowledge graph-signal fusion module, a re-ranked candidate concept shortlist by applying the associated knowledge graph information to vision scores and generating, by a multi-agent report generation module using the re-ranked candidate concept shortlist, the automated report including a plurality of findings. FIG. 3
Disclaimer: Curated by HT Syndication.
