Open AccessWeb Service Recommendation Technology Based on Knowledge Graph Representation Learning
Author(s) -
Xinghao Qiao,
Zhiying Cao,
Xiuguo Zhang
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1213/4/042015
Subject(s) - computer science , collaborative filtering , recommender system , graph , knowledge graph , representation (politics) , information retrieval , theoretical computer science , machine learning , data mining , artificial intelligence , politics , political science , law
This paper proposed a recommendation algorithm based on knowledge graph representation learning (RABKGRL).The algorithm embeds the entities and relationships of the knowledge graph into the low-dimensional vector space. The relationship information of services is incorporated into the recommendation algorithm by calculating the distance between the service entities. The association between services that is not considered when using the collaborative filtering algorithm can be supplemented, and the recommendation effect is enhanced. The experimental results show that this algorithm can not only effectively improve the accuracy rate, recall rate and coverage rate of recommendation, but also solve the cold start problem to some extent.