Research on Librarian Demand Prediction Based on the GM (1,1) Model and BP Neural Network Combined Model

With the development of science and technology, the automation level of library is constantly improving, and the number of librarians is decreasing year by year. As one of the most important human resources to promote the sustainable development of library, librarians are particularly important, therefore, it is necessary to research its changing trend. This study constructs a GM(1, 1)-BP Neural Network combined model, and takes the library of Sichuan University as case study. The simulation results show that, compared with a single prediction model, the GM (1, 1)-BP Neural Network combined model has higher prediction accuracy and smaller errors, which can further improve the prediction accuracy.