基于图划分的分布式推荐系统OA

[Objective]It is of great significance to design a recommender system with high data process-ing efficiency.[Methods]The graph structure is used to simulate the user preference relation-ship in the recommender system.Through the graph partition algorithm processing,the infor-mation value of the data in the recommender system can be further mined,and the obtained sub-graph data with load balancing can be used as the input of the distributed system.Finally,a dis-tributed recommender system is implemented through the fusion of an adaptive aggregation module.[Results]The system can improve the processing efficiency of the recommender algo-rithm for large-scale data.On the premise that the prediction accuracy does not decline,the al-gorithm can improve the efficiency 6.4 times in a cluster training consisting of 16 CPUs com-pared with a single CPU training.[Conclusions]The experimental results show that the system is effective in rec-ommendation efficiency.