<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Rational hospital human resource allocation planning is important to improve the efficiency of China’s health human resource allocation and reduce the losses caused by staff waste and shortage. In this paper, we take the medical and nursing configuration of a general tertiary hospital in X city as a guiding framework and use inductive and deductive methods to summarize the factors affecting medical and nursing staffing and the experience of management in the previous period. By proposing an adaptive algorithm based on learning rate for improving BP neural network with differentiated learning rate, the dynamic adjustment of weights between different nodes is achieved. Finally, through database design and module design, two functional modules of human resource management and human resource prediction are constructed. The results of the case validation show that the HR demand forecasting model has the best prediction effect for health technicians, and the relative errors are all less than 5%, with an average relative error of 1.23% and a minimum value of only 0.25%. The relative error between the predicted and actual values of the ARIMA (2, 2, 2) dataset for practicing (assistant) physicians is less than 0.005. It shows that the HR model constructed in this paper has a certain quantitative guidance value for the rational planning of human resource allocation for hospital positions.</p>
</abstract>

Rational hospital human resource allocation planning is important to improve the efficiency of China’s health human resource allocation and reduce the losses caused by staff waste and shortage. In this paper, we take the medical and nursing configuration of a general tertiary hospital in X city as a guiding framework and use inductive and deductive methods to summarize the factors affecting medical and nursing staffing and the experience of management in the previous period. By proposing an adaptive algorithm based on learning rate for improving BP neural network with differentiated learning rate, the dynamic adjustment of weights between different nodes is achieved. Finally, through database design and module design, two functional modules of human resource management and human resource prediction are constructed. The results of the case validation show that the HR demand forecasting model has the best prediction effect for health technicians, and the relative errors are all less than 5%, with an average relative error of 1.23% and a minimum value of only 0.25%. The relative error between the predicted and actual values of the ARIMA (2, 2, 2) dataset for practicing (assistant) physicians is less than 0.005. It shows that the HR model constructed in this paper has a certain quantitative guidance value for the rational planning of human resource allocation for hospital positions.

Study on the Rationalization of Human Resources Allocation in Hospitals in the Post-Epidemic Era

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Rational hospital human resource allocation planning is important to improve the efficiency of China’s health human resource allocation and reduce the losses...

Study on the Rationalization of Human Resources Allocation in Hospitals in the Post-Epidemic Era

Publicado en línea: 09 oct 2023

Páginas: -

Recibido: 25 nov 2022

Aceptado: 19 abr 2023

DOI: https://doi.org/10.2478/amns.2023.2.00534

Palabras clave
Hospital human resources, Learning rate, BP neural network, Demand forecasting model

© 2023 Haiyan Jiao et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Study on the Rationalization of Human Resources Allocation in Hospitals in the Post-Epidemic Era

Publicado en línea: 09 oct 2023

Páginas: -

Recibido: 25 nov 2022

Aceptado: 19 abr 2023

DOI: https://doi.org/10.2478/amns.2023.2.00534

Palabras claveHospital human resources, Learning rate, BP neural network, Demand forecasting model

© 2023 Haiyan Jiao et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Palabras clave
Hospital human resources, Learning rate, BP neural network, Demand forecasting model