Scalable Conversational Ai System Enabling Automated Generation and Delivery of Personalised Instructional Educational Content

Abstract

This research investigates the construction of a scalable system for the generation of instruction knowledge-based content in learning contexts using a communications model. This research aims to study the implementation of a scalable automated generation system for instructional knowledge abstract content in learning contexts based on a conversational model. The study is descriptive in nature, employing secondary qualitative data that consists of structured lesson text, keywords, lesson_type, difficulty_level, and target Attributes from a Teaching dataset in the English language. Techniques of data analysis are used, such as text length analysis, extraction of word frequency, and word cloud visualization. The proposed new system combines NLP, Rag, and LLM to provide adaptive and context-relevant learning content. The results show that the dataset enables buildup of structured and scaled content for multi-level arenas. It serves to improve the automation, personalization, and efficiency of delivering education, ensuring the quality and uniformity of instruction for a variety of students in digital education systems.