Edge Computing Oriented Decision and Optimization Method for Efficient and Intelligent Human Resource Management and Analysis

Abstract

Modern enterprises face significant challenges in achieving real-time, intelligent workforce management due to the limitations of centralized cloud-based solutions in dynamic operational environments. This paper proposes an edge computing-oriented decision and optimization method for efficient and intelligent human resource management and analysis. First, we design a hierarchical edge-cloud architecture comprising infrastructure, edge, cloud, and application layers, specifically optimized for workforce data processing through localized decision modules. Second, we develop a TinyML-enhanced multi-objective optimization method that concurrently addresses the intelligent HR data sentiment analysis and optimal resource decision towards privacy and latency minimization, as well as F1 score maximization. Specifically, we establish the data analysis model, based on which we construct the problem as a multi-objective decision model to be addressed and obtain the optimization solution. Lastly, we carry out rich experiments which show that the proposed method achieves better performance than the compared methods, including achieving the F1 score over 90% and reducing the population size of model parameters greatly.