The Internet of Things Service Recommendation Based on Tripartite Graph with Mass Diffusion

With the increasing presence and adoption of the smart device in the Internet of Things (IoT), the service recommendation is becoming more and more important. In this paper, we proposed a service recommendation scheme based on the mass diffusion dynamic tag tripartite graph. We extracted the users' habit features of using the IoT device service as the dynamic tag and then built the tripartite graph. Through the positive and backward mass diffusion on the tripartite graph, we got the resource value of the service. We finally obtained the recommendation list through the comprehensive calculation of the energy state, the user similarity, the bearing capacity, and the service resource value of the mass diffusion results. The experiments showed that the recommendation precision of the service recommendation scheme we proposed was at least 12% higher than the other algorithms.