Answers are grounded in this paper and cite their sources.
Computational evaluation reveals improved recommendation accuracy and spatial service allocation in digital libraries, highlighting a viable strategy for modern intelligent library management.
In the context of the digital era, libraries face competition from Internet search engines, online databases, and other digital information services. Only by innovating management modes and providing higher-quality, convenient, and personalized services can libraries remain competitive. In this study, “personalized service” specifically refers to (i) recommending book categories that match each reader’s interest profile (preference-fit recommendation) and (ii) prioritizing space-service suggestions (area ranking) based on readers’ recent borrowing frequency and recency signals, thereby improving service efficiency for both users and staff. Based on this, the study proposes a personalized recommendation system for book borrowing management by combining the K-means clustering algorithm and factor analysis. In addition, a temporal decay weighting function inspired by the Ebbinghaus forgetting curve is used to model borrowing recency and frequency when estimating short-term space-service demand. Experimental results show that the proposed method maintains stable time consumption as the bibliographic search scale increases, with a peak time of 20 s at 3,000 iterations and a minimum of 3 s at 1,600 iterations. The retrieval accuracy for users’ spatial management needs shows an overall increasing trend, reaching 91.09% at 2,500–3,000 searches, with the minimum accuracy of 78.89% observed at 1,000–1,500 retrievals. These results indicate that the proposed model can improve personalized recommendation effectiveness and spatial service efficiency, providing a practical reference for intelligent library management innovation.
No takes yet. Share an insight, caveat, or question.
Han et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: