MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202641099280 A) filed by K. Tulasi Krishna Kumar on August 17, 2026, for A System And Method For Ai-Based Internship Recommendation Using Explainable Ai And Multi-Agent Learning.
Inventors include K. Tulasi Krishna Kumar; Mrs. Sandhya Gandi; Pinnamraju T S Priya; Mugi Satish; Bhumana Sujatha; Pyla Uma; and Eluri Sravya.
The application for the patent was published on August 28, 2026, under issue no. 35/2026.
Abstract: ABSTRACT: Title: A SYSTEM AND METHOD FOR AI-BASED INTERNSHIP RECOMMENDATION USING EXPLAINABLE AI AND MULTI-AGENT LEARNING A computer-implemented system and method are disclosed for AI-based internship recommendation for students of higher education institutions. The system comprises a Data Ingestion and Pre-processing Layer, a domain-specific Knowledge Graph, a Large Language Model based Semantic Understanding Module, a Multi-Agent Orchestration Framework, a Machine Learning Prediction Engine, an Explainable Artificial Intelligence Module, a Skill-Gap and Upskilling Recommendation Module, and a Continuous Feedback and Adaptive Learning Module. Student academic records, resumes, certifications, projects, and internship requirements are processed to construct semantic profiles and relationships within the Knowledge Graph. The Multi-Agent Orchestration Framework coordinates profile construction, requirement mining, matching, prediction, explanation, and feedback processing. The Machine Learning Prediction Engine determines internship suitability, completion probability, employer satisfaction probability, and offer-conversion probability. The Explainable Artificial Intelligence Module generates human-readable recommendation rationale, quantified contributing factors, and skill-gap information. The system further provides personalised upskilling recommendations and continuously updates the Knowledge Graph and prediction models using post-internship employer and student feedback, thereby providing transparent, predictive, adaptive, and continuously improving internship recommendations.
Disclaimer: Curated by HT Syndication.
