The design of library resource personalised recommendation system based on deep belief network Online publication date: Thu, 19-Oct-2023
by Min Fu
International Journal of Applied Systemic Studies (IJASS), Vol. 10, No. 3, 2023
Abstract: Aiming at the problems of low accuracy and user satisfaction of traditional library resource recommendation system, this paper designs a library resource personalised recommendation system based on deep belief network. Firstly, the architecture of library resource personalised recommendation system is designed and real-time recommendation module is added. For the real-time recommendation module, the probability function of the best resource in the deep belief network is obtained by combining several limited Boltzmann machines and maximum likelihood principles. The bias value and weight of the visible layer and the hidden layer of the deep belief network are corrected by the contrast divergence method to make the recommendation result more accurate. The experimental results show that the recommendation accuracy of the system can reach more than 97%, the recall rate can reach 92.5%, and the user satisfaction is more than 94.8%, indicating that the system has effectively improved the recommendation effect.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Applied Systemic Studies (IJASS):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook