Large language model-based automated knowledge extraction and prediction system using Artificial Intelligence

Abstract

The rapid proliferation of unstructured data on digital platforms has generated an urgent demand for intelligent systems that can extract meaningful knowledge and produce accurate predictions. This study presents an automated knowledge extraction and prediction system using the advancements in Artificial Intelligence (AI) tools, which is referred to as APEX-LLM. The proposed system uses the latest architectures based on transformers for processing massive textual data, mining relevant entities, relationships, and patterns, and structuring them into knowledge-based representations. The framework integrates knowledge retrieval, natural language understanding, and machine learning techniques for immediate retrieval of knowledge from other sources such as documents, web content and databases. Furthermore, there is an integration of elements related to predictive modelling to analyze the knowledge extracted and predict trends, outcomes, or an action in various regions. It is a scalable, domain-independent system which can be customized and applied to health, financial and business sectors, and education. The experimental analysis demonstrates that the proposed method is much more accurate and efficient than the traditional rule-based and statistical methods. The results demonstrate that the LLM-based system has an overall automation rate of 99.2%, which is significantly higher than the 90.7% for rule-based and 83.9% for statistical methods, thereby minimizing the human factor by 99.6% and enhancing the accuracy of decision-making to 99.4%. This APEX-LLM will be added to the emerging branch of AI-enabled knowledge systems, offering a single solution for extraction and prediction tasks.