MUMBAI, India, June 30 -- Intellectual Property India has published a patent application (202641076173 A) filed by Vellore Institute Of Technology on June 19, 2026, for System And Method For Explainable Candidate Evaluation And Ranking In Recruitment Platforms.
Inventors include E. P. Ephzibah; Sakthivel N; and Edward C.
The application for the patent was published on June 26, 2026, under issue no. 26/2026.
Abstract: The present invention relates to a system (100) and method for explainable candidate evaluation and ranking. The system (100) comprises a data extraction layer configured to extract candidate attributes from resume information and job requirement information, a knowledge representation layer configured to generate structured representations of extracted information, a machine learning evaluation engine configured to generate a first suitability score, a graph reasoning engine configured to generate a second suitability score through semantic reasoning performed on relationships among skills, technologies, certifications, professional domains, and job roles, and a rule evaluation engine configured to generate a third suitability score using recruitment evaluation rules and adaptive rule weighting. A hybrid decision fusion layer combines the generated scores to produce a unified candidate suitability score. An explainability layer generates decision traces associated with the unified candidate suitability score. The invention further provides structured candidate ranking based on the unified candidate suitability score.
Disclaimer: Curated by HT Syndication.
