Personalised recommendation algorithm of network resources based on collaborative knowledge map
by Xiaofei Liu; Shaohui Zhong
International Journal of Autonomous and Adaptive Communications Systems (IJAACS), Vol. 16, No. 2, 2023

Abstract: In order to overcome the problems of wide coverage of network resources and confusion of semantic information, resulting in low precision of recommendation and low recall rate, a personalised recommendation algorithm based on collaborative knowledge map is proposed. The collaborative knowledge map is introduced into the research field of network resources, the knowledge features of network resources are extracted specifically. The collaborative knowledge ontology database of network resources field is constructed according to the entity division relationship in the research field. Entities and relationships are extracted from network resources, to build a knowledge map based on relational database, quantify the network resources in the knowledge map, extract semantic information of network resources with collaborative filtering algorithm, so as to achieve the purpose of personalised recommendation of network resources. The simulation results show that the recommended precision is more than 98%, and the recall rate and comprehensive evaluation index are better.

Online publication date: Wed, 24-May-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
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 Autonomous and Adaptive Communications Systems (IJAACS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your 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