MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641081084 A) filed by Mlr Institute Of Technology on July 01, 2026, for Automated Resume Parsing And Ats-Based Candidate Ranking System Using Machine Learning And Natural Language Processing.
Inventors include Mr. B Devananda Rao; Ms. Ch. Chandana; Mr. B. Yashwanth Raj; and Mr. G. Vamshi.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: In this invention, “Automated Resume Parsing and ATS-Based Candidate Ranking System Using Machine Learning and Natural Language Processing” is disclosed as an intelligent recruitment and talent acquisition framework designed to automate resume screening, candidate evaluation, and hiring decision support. The invention receives resumes in multiple document formats, including PDF, DOC, DOCX, and text files, and processes them using advanced natural language processing techniques to extract structured candidate information such as personal details, educational qualifications, work experience, technical skills, certifications, projects, achievements, and professional competencies. The extracted information is standardized and transformed into machine-readable representations for efficient analysis. A job description processing module simultaneously analyzes employer requirements, identifying essential skills, educational criteria, experience levels, certifications, and role-specific competencies. The system employs machine learning algorithms to compare candidate profiles with job requirements and calculate suitability scores based on semantic similarity, skill relevance, experience alignment, educational compatibility, and overall job fitness. An Applicant Tracking System (ATS)-based ranking engine subsequently ranks candidates according to their computed scores and generates prioritized candidate lists for recruiter review. The invention further supports contextual skill matching, keyword optimization, candidate profiling, and intelligent filtering to improve recruitment accuracy and reduce dependency on manual screening processes. A feedback-driven learning mechanism continuously refines ranking performance using recruiter decisions, hiring outcomes, and historical recruitment data. The system additionally provides recruiter dashboards containing candidate insights, ranking explanations, hiring recommendations, recruitment analytics, and performance reports for informed decision-making. The proposed framework can be deployed across corporate organizations, recruitment agencies, educational institutions, government sectors, and online hiring platforms. By integrating automated resume parsing, natural language understanding, machine learning-based candidate evaluation, ATS-driven ranking, adaptive learning, and recruitment analytics within a unified platform, the invention significantly enhances hiring efficiency, improves candidate-job matching accuracy, reduces recruitment time and operational costs, minimizes human bias, and supports intelligent, scalable, and data-driven talent acquisition processes.
Disclaimer: Curated by HT Syndication.
