Intelligent Big Information Retrieval of Smart Library Based on Graph Neural Network (GNN) Algorithm.

Area of Science:

• Computer Science
• Information Science
• Artificial Intelligence

Background:

• Libraries face challenges in managing and extracting value from big data.
• Existing information retrieval methods lack the intelligence and humanization required for modern big data services.

Purpose of the Study:

• To propose an intelligent big information retrieval method for smart libraries.
• To leverage graph neural network (GNN) algorithms for enhanced big data knowledge services.
• To improve the efficiency and value mining of library information.

Main Methods:

• Utilized graph neural network (GNN) algorithms for information recommendation.
• Explored technical solutions for information retrieval within a smart library context.
• Applied GNNs to address key challenges in big data knowledge management.

Main Results:

• The proposed GNN-based intelligent information retrieval method demonstrated an 80% improvement over previous general methods.
• Graph neural networks proved advantageous for tasks like node classification and link prediction.
• The method significantly boosted the overall efficiency of information retrieval.

Conclusions:

• Graph neural networks offer a powerful algorithmic framework for intelligent information retrieval in smart libraries.
• The GNN approach facilitates better management and value extraction from big data knowledge services.
• This research highlights the potential of GNNs to revolutionize library information services.