Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Five-layer architecture diagram for knowledge graph-based library intelligent data management.

The architectural structure consists of five layers (color-coded): Data Layer (light green) for integration of multiple data sources, Data Processing Layer (dark green) for ETL processes, Knowledge Graph Layer (gold) for ontology-based knowledge development; Intelligent Service Layer (purple) for AI-based services, Application Layer (coral) for user interfaces. Black arrows denote data flow; purple demonstrates feedback for improvement.

More »

Fig 1 Expand

Fig 2.

System operation example: Illustration of personalized recommendation service scenarios.

The graph shows personalized recommendation processes designed for a graduate student (top path) and an undergraduate (bottom path) having varying levels of expertise because of differences in their academic backgrounds. The books (dark green), journals (blue), and attributes (orange ovals) are interlinked through using semantic links (edge labels). The recommended items have confidence scores (88%−96%) calculated through using paths in the knowledge graph. The recommendations vary depending upon historical usage, level of expertise, as well as research interest of the user.

More »

Fig 2 Expand

Table 1.

System evaluation index system and measurement methods.

More »

Table 1 Expand

Table 2.

User experience feedback data.

More »

Table 2 Expand

Fig 3.

Comprehensive comparison of multi-dimensional evaluation results.

More »

Fig 3 Expand

Fig 4.

Performance comparison between traditional systems and knowledge graph systems.

More »

Fig 4 Expand

Table 3.

Analysis of system performance and technical indicator achievement.

More »

Table 3 Expand