Biomechanics-inspired utilization 5G multimedia for intelligent title recommendations in low carbon smart libraries through collaborative filtering algorithms
Abstract
With the popularization of e-readers, electronic reading rooms, digital libraries, and other new ways of reading in libraries and society, libraries have also entered a new stage of development because of “low-carbon” construction. The low-carbon development of intelligent libraries reduces the application of traditional literature carriers, increases the popularity and application of modern equipment, makes the replacement of paper materials, and reduces its own energy consumption. To achieve personalized recommendations in the lending system, this paper, inspired by biomechanical concepts, constructs a tree intelligent recommendation system via a collaborative filtering algorithm. This system functions like a neural network in a biological system, processing and analyzing data to make informed decisions. By verifying the system with actual borrowing data of students, it proves effective, much like how a biomechanical adaptation is tested and validated in nature. This approach offers a valuable reference for intelligent book management in universities, aligning library operations with the principles of efficient resource utilization and adaptation seen in the biomechanical world. book management in universities. In addition to these advancements, integrating biomechanics into the design and operation of smart libraries can enhance user experience and engagement. Understanding the biomechanics of reading—such as posture, hand movements, and eye tracking—can inform the development of ergonomic reading spaces and devices. For instance, optimizing seating arrangements and reading environments based on biomechanical principles can reduce physical strain and improve comfort for users. Moreover, incorporating biomechanical feedback into the recommendation system could personalize user interactions further. By analyzing how different users engage with reading materials—considering factors like reading speed, preferred formats, and physical interactions with devices—libraries can refine their recommendation algorithms. This approach not only enhances the effectiveness of title recommendations but also promotes a healthier reading experience, aligning with the low-carbon goals of reducing physical strain and energy consumption associated with inefficient reading practices.
References
1. Zhao F. Design of book bibliography recommendation system for universities based on collaborative filtering algorithm (Chinese). Microcomputer Applications. 2022; 38(12): 67–69+73.
2. Zhu M, Zhang X. Design of library bibliographic recommendation system based on computer network technology (Chinese). Modern Electronic Technology. 2022; 45(05): 182–186.
3. Wang T, Hao J. Research and reflection on bibliographic recommendation of book commercial institutions in China (Chinese). Library Research. 2021; 51(06): 20–28.
4. Ye Y. Exploration of personalized bibliographic recommendation method for reading promotion review data (Chinese). New Century Library. 2021; 10: 31–36.
5. Hong Y. Analysis of book borrowing based on association mining (Chinese). Library Research and Work. 2021; 4: 75–79.
6. Yang X. A personalized recommendation system for library bibliography based on collaborative filtering (Chinese). Microcomputer Applications. 2021; 37(09): 169–171+175.
7. Cao Y. Collaborative library bibliographic recommendation system based on artificial intelligence technology (Chinese). Modern Electronic Technology. 2020; 43(15): 168–170+174.
8. Wang Z, Li J. Research on collaborative filtering recommendation of university library titles based on user context (Chinese). Library Research and Work. 2021; 1: 63–68.
9. Li P, Peng S. Library bibliography recommendation based on readers’ personalized characteristics (Chinese). Modern Electronic Technology. 2018; 41(17): 182–186.
10. Zhao J. Exploring how to scientifically recommend books in university libraries (Chinese). Culture industry. 2018; 21: 50–51.
11. Chai R. Research on the design and implementation of collaborative intelligent recommendation system for library bibliography (Chinese). Microcomputer Applications. 2020; 36(04): 133–135+139.
12. Pang Y, Zhou Y. Research on the characteristics of reading recommended books in high school libraries (Chinese). Shandong Library Journal. 2020; 1: 73–76+101.
13. Jia W, Liu X, Xu T. A recommendation service integrating user smart tags and social tags (Chinese). Intelligence Science. 2019; 37(10): 120–125.
14. Chang Y, Liu J, Liu X. Spark-based bibliographic recommendation system for university libraries (Chinese). Modern Electronic Technology. 2019; 42(14): 64–67+73.
15. Xie K. Library bibliographic recommendation based on data mining of readers’ personalized features (Chinese). Modern Electronic Technology. 2018; 41(06): 34–36.
16. Zhu Y. Research on personalized recommendation model of university library based on data mining (Chinese). Time Finance. 2017; 26: 310–311.
17. Liu M. Bibliographic recommendation service for higher education libraries (Chinese). Journal of Jintu. 2015; 6: 24–27.
18. Liu Y. Research on bibliographic recommendation based on data mining (Chinese). Innovative Technology. 2017; 4: 91–93.
19. Pan X. Library bibliographic recommendation service based on clustering algorithm (Chinese). Journal of Library Science. 2013; 35(11): 109–111+138.
20. Liu Y. A collaborative library bibliographic recommendation system based on machine learning algorithm (Chinese). Modern Electronic Technology. 2020; 43(14): 180–182+186.
21. Zhang Y, Over S. Bibliographic recommendation strategy and algorithm based on classification frequent pattern mining (Chinese). Intelligence Science. 2012; 30(12): 1804–1806+1811.
22. Huang Y. Research and design of library bibliographic recommendation system (Chinese). Jiangxi Library Journal. 2011; 41(02): 92–96.
23. Ye F, Shi Z. Application of maximum frequent pattern mining algorithm in personalized library information service (Chinese). Journal of Changchun College of Engineering (Natural Science Edition). 2012; 13(03): 98–101.
24. Zhao L. Design and implementation of a bibliographic recommendation system based on maximum frequent pattern mining algorithm (Chinese). Modern Library and Information Technology. 2010; 5: 23–28.
25. Carrie X, Jia C. A fast personalized bibliographic recommendation method. Modern Library and Information Technology (Chinese). 2010; 2: 79–84.
26. Chen D, Zhu W. Association rules and library bibliographic recommendation (Chinese). Intelligence Theory and Practice. 2009; 32(06): 81–84.
Copyright (c) 2025 Author(s)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.
Submit a Paper
