Knowledge graph-based intelligent data management and information innovation service model for university library...

Area of Science:

• Library and Information Science
• Computer Science
• Data Science

Background:

• Digitalization presents data management challenges for university libraries.
• Traditional methods struggle to meet personalized information needs.
• Adapting to big data is crucial for modern academic libraries.

Purpose of the Study:

• To develop a knowledge graph-based intelligent data management and information innovation service model for university libraries.
• To address limitations in traditional library data management and enhance personalized services.
• To propose a solution for university libraries facing big data challenges.

Main Methods:

• A hierarchical five-layer model: data source, processing, knowledge construction, service application, and user interaction.
• Integration of multi-source heterogeneous data with a unified knowledge representation framework.
• Dynamic fusion of large language models and graph embedding for data integration and personalized recommendations.

Main Results:

• Significant improvement in user experience (45.2% increase).
• Enhanced search result accuracy (41.1% increase).
• Improved service quality (32.5%) and learning effectiveness (41.7%), with all 16 technical indexes exceeding standards.

Conclusions:

• The proposed model offers a practical solution for university libraries to manage big data.
• It facilitates intelligent service transformation and enhances personalized information delivery.
• The model effectively addresses heterogeneous data integration and improves overall library performance.