Introduction: The telecommuting experience and job performance have been significantly impacted by the COVID-19 pandemic, and job performance stability of telecommuting employees has become a critical concern.
Objective: A decision model for telecommuting experience service design was constructed based on a backpropagation (BP) neural network to provide a theoretical basis for enterprises to evaluate telework performance and the psychological health of employees.
Methods: The analytic hierarchy process (AHP) was used to determine the core stakeholders. The grey relational analysis (GRA) method and the NASA Task Load Index (NASA-TLX) scale were used to measure the factors affecting employees’ telecommuting experience and job performance. A BP neural network relationship model of employees’ telecommuting experience was established to predict its impact on employees’ job performance.
Results: Based on the model prediction results, a service system map was created, and the potential to enhance the telework performance of employees was evaluated.
Discussion: It was concluded that the factors affecting the telecommuting experience were diverse, but emotions had the dominant influence. Significant positive correlations were found between emotional impact and temporal perception, execution difficulty, and communication barriers.
Conclusion: The proposed decision model for telecommuting experience service design accurately predicted the impact of telecommuting efficiency, providing an effective approach for innovative remote management.
Keywords: design decision, job performance, telecommuting experience, BP neural networks, NASA-TLX scale