Scholarlink

<p>University libraries contain vast information, yet students often struggle to locate relevant resources efficiently to support their academic learning needs. Traditional search and recommendation systems suffer from low personalization and limited handling of vague or uncertain user preferences, reducing their effectiveness in complex educational environments. To address these limitations, this research proposes the Fuzzy Deep Learning-Based Intelligent Library Resource Recommendation Framework (FDLILRRF), which integrates fuzzy logic and deep learning techniques to enhance the accuracy and relevance of information retrieval in university libraries. The research focuses on developing smart systems to retrieve information and recommend educational resources tailored to individual needs. The core problem identified is the inadequacy of keyword-based search engines to deliver personalized and context-aware resource suggestions within large digital library systems. The FDLILRRF framework uses fuzzy logic to handle unclear user input and deep learning to learn from interactions and content, ensuring personalized recommendations. This hybrid approach enables the generation of more accurate and context-sensitive recommendations. Potential applications of this framework include university digital libraries, online learning platforms, and research support systems, offering significant benefits in academic resource discovery and user satisfaction. Experimental evaluation using a student interaction dataset demonstrated that FDLILRRF improved recommendation accuracy by 14.6% over traditional collaborative filtering methods. Enhanced performance in precision and recall metrics further confirms the framework’s effectiveness for real-world educational applications. This research provides an intelligent, adaptive solution to optimize information access in academic library systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Intelligent Recommendation of Information Resources in University Libraries Based on Fuzzy Logic and Deep Learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月1日

查看全文
  • Yanfang Yang

摘要

University libraries contain vast information, yet students often struggle to locate relevant resources efficiently to support their academic learning needs. Traditional search and recommendation systems suffer from low personalization and limited handling of vague or uncertain user preferences, reducing their effectiveness in complex educational environments. To address these limitations, this research proposes the Fuzzy Deep Learning-Based Intelligent Library Resource Recommendation Framework (FDLILRRF), which integrates fuzzy logic and deep learning techniques to enhance the accuracy and relevance of information retrieval in university libraries. The research focuses on developing smart systems to retrieve information and recommend educational resources tailored to individual needs. The core problem identified is the inadequacy of keyword-based search engines to deliver personalized and context-aware resource suggestions within large digital library systems. The FDLILRRF framework uses fuzzy logic to handle unclear user input and deep learning to learn from interactions and content, ensuring personalized recommendations. This hybrid approach enables the generation of more accurate and context-sensitive recommendations. Potential applications of this framework include university digital libraries, online learning platforms, and research support systems, offering significant benefits in academic resource discovery and user satisfaction. Experimental evaluation using a student interaction dataset demonstrated that FDLILRRF improved recommendation accuracy by 14.6% over traditional collaborative filtering methods. Enhanced performance in precision and recall metrics further confirms the framework’s effectiveness for real-world educational applications. This research provides an intelligent, adaptive solution to optimize information access in academic library systems.