MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641106132 A) filed by Dr. R. Murugadoss on September 03, 2026, for Adaptive Semantic Talent Intelligence Using Knowledge Graphs And Artificial Intelligence.
Inventors include Dr. R. Murugadoss; Ms. Akshaya Dharshini M; Ms. Dhivyabharathi A; Ms. Akalya R; Ms. Devarasi S; Ms. Bruntha R; and Ms. Divyaa N.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: An artificial intelligence computing system maps, analyses, and predicts human capital capabilities through a multidimensional Semantic Talent DNA (STDNA) architecture. The system utilizes an automated ingestion and normalization pipeline to ingest unstructured, semi-structured, and highly disparate talent data streams— including professional histories, academic credentials, open-source code repositories, project portfolios, and real-time enterprise performance metrics. A neural semantic parsing engine converts these inputs into granular, vectorized "genetic" talent markers. These markers define explicit skills, implicit competencies, behavioural traits, and experiential context. An adaptive graph construction module projects these markers into a multi-layered, interconnected talent knowledge graph. This graph maps complex, non-linear relationships across four distinct semantic planes: Individual Talent Profiles (the candidate/employee node layer),Skill Taxonomies and Adjacencies (the capability node layer),Organizational Roles and Hierarchies (the demand node layer),Macro-Economic Market Trends (the external environmental layer).A machine learning framework utilizing Graph Neural Networks (GNNs) continuously recalculates the structural topology, node vector weights, and directional edge strengths of the knowledge graph. This automated adaptation captures real-time technological shifts, evolving job definitions, and skill obsolescence cycles without requiring manual ontology updates. An AI inference and predictive matching engine applies semantic distance and graph-traversal algorithms to execute: Contextual talent matching based on implicit skill adjacencies rather than explicit keyword correlation, Predictive career trajectory modelling to identify internal high- potential employees, Proactive workforce gap analysis and automated learning pathway generation. A closed-loop feedback interface captures post-hire performance data, interviewer assessments, and human-in-the-loop validation metrics. This data is fed back into the system to dynamically retrain the AI models, optimize semantic alignment precision, and systematically discover and mitigate algorithmic bias.
Disclaimer: Curated by HT Syndication.
