DNN-based hospital service satisfaction using GCNNs learning

Hospital patient service satisfaction prediction technology based on supervised learning can obtain higher accuracy by training image data. This paper proposes a deep neural network continuous sample data to predict in hospitals, which overcomes the problem of high cost collecting additional labeled while improving Furthermore, our model converts samples into images reflecting characteristics and trains resulting dataset, avoiding overfitting. Results experimental show that networks general-domain methods is than classical using same collection. At level practical application, system we propose provides patients with indicators evaluate their experience choosing hospital reference for hospitals rationally arrange medical triage.