Intellectual Property India Publishes Patent Application for System And Method For Explainable Causal Inference Using Hybrid Symbolic-Ai And Machine Learning Pipelines

MUMBAI, India, Sept. 22 -- Intellectual Property India has published a patent application (202641109046 A) filed by T. Laxmiprasanna; Dr. Arjunarao Rajanala; Dr. Suvarna Lakshmi C; Dr. A. Arulkumar; Roshan Chitranshi; Dr. K. Nandhini; Dr. V. Sabaresan; Dr. R Murugadoss; Dr. P Rizwan Ahmed; Yaddarabullah; Ajaykumar Jagdishbhai Barot; Dr. Bosco Nirmala Priya; Battula Ramesh; and Dr. K. Saranya on September 11, 2026, for System And Method For Explainable Causal Inference Using Hybrid Symbolic-Ai And Machine Learning Pipelines.

Inventors include T. Laxmiprasanna; Dr. Arjunarao Rajanala; Dr. Suvarna Lakshmi C; Dr. A. Arulkumar; Roshan Chitranshi; Dr. K. Nandhini; Dr. V. Sabaresan; Dr. R Murugadoss; Dr. P Rizwan Ahmed; Yaddarabullah; Ajaykumar Jagdishbhai Barot; Dr. Bosco Nirmala Priya; Battula Ramesh; and Dr. K. Saranya.

The application for the patent was published on September 18, 2026, under issue no. 38/2026.

Abstract: The present invention provides a system for explainable causal inference using a hybrid symbolic-artificial-intelligence and machine-learning processing arrangement. An input interface unit receives heterogeneous observational, temporal, contextual, and intervention-related data, while a data conditioning unit validates, aligns, normalizes, and converts the data into a common machine-readable representation. A causal representation storage unit stores variable nodes and directed relationships. A symbolic reasoning processor evaluates logical, domain, and temporal constraints, and a machine-learning processor generates candidate dependency information. A causal inference processor evaluates the candidate dependency information against the constraints to determine causally admissible relationships. An intervention processing unit evaluates modified conditions and corresponding target-variable responses, while an inference validation circuit validates causal relationships. An explanation generation unit generates electronically readable causal explanations identifying causal paths, contributing variables, intervention conditions, inference bases, and validation information. A provenance storage unit stores source, model, constraint, and processing information associated with the causal inference.

Disclaimer: Curated by HT Syndication.