AI-Based Question Paper Analysis and Generator with Authentication

The main goal of this study is to improve and expedite the question paper preparation process. The system starts by consuming digital or scanned documents that include a wide range of textual material, including academic resources, textbooks, and past year’s exam questions. The system turns these papers into machine-readable text by using optical character recognition (OCR) technology, which allows for the extraction of important content for question creation. For question classification, the random forest algorithm a flexible ensemble learning method is utilized. It divides the extracted text into several topic categories, difficulty levels, and subject areas. Question assembly is aided by the K-nearest neighbors algorithm, a potent technique for similarity analysis. KNN facilitates the creation of well-organized and well-balanced question papers by locating related questions and answers. Python and other machine learning libraries were used in the development of this question paper generator system. It enables teachers to indicate their standards and inclinations for the creation of question papers, including the quantity, degree of difficulty, and range of topics covered. Instructors have the flexibility to customize question papers generated by the system through an intelligent assembly of questions.