Abstract
Purpose – To tackle Photovoltaic (PV) construction inefficiency and payroll inequity, this study proposes an Automatic Daily Salary Settlement System (ADSSS). ADSSS synergizes Lean Construction’s (LC) human-centric behavioral management principles with Artificial Intelligence of Things (AIoT) via a triple-loop feedback mechanism, synchronizing worker behavior, management efficacy, and algorithmic evolution with LC goals for equitable and efficient salary management.
Design/methodology/approach – This study employs design science research and case study methodologies. Building upon LC behavioral management principles, worker behavior is categorized into operational, quality, and safety dimensions. The linkage between these behavioral dimensions and project performance informs the design of the overall ADSSS framework. Meanwhile, AIoT enabled intelligent safety helmets facilitate real-time data acquisition, while the YOLO algorithm automates data processing for daily salary computation. Case validation confirms the system’s operational feasibility and effectiveness.
Findings – The integration of LC theory and AIoT technology establishes both a theoretical foundation and implementation framework for the ADSSS. This system institutes a differentiated compensation mechanism based on behavioral metrics while achieving efficient daily automation. Empirical results demonstrate that the ADSSS not only accurately quantifies individual performance differentials to incentivize efficiency, quality, and safety compliance but also significantly improves overall project deliverables.
Originality/value – This study pioneers a differentiated, incentive-driven salary system with automated daily settlement capabilities. The framework strategically attracts skilled personnel through competitive remuneration, enhances salary satisfaction while eliminating payment arrears, and concurrently boosts PV construction labor productivity alongside comprehensive project performance improvements in schedule adherence, quality control, and safety management.
Design/methodology/approach – This study employs design science research and case study methodologies. Building upon LC behavioral management principles, worker behavior is categorized into operational, quality, and safety dimensions. The linkage between these behavioral dimensions and project performance informs the design of the overall ADSSS framework. Meanwhile, AIoT enabled intelligent safety helmets facilitate real-time data acquisition, while the YOLO algorithm automates data processing for daily salary computation. Case validation confirms the system’s operational feasibility and effectiveness.
Findings – The integration of LC theory and AIoT technology establishes both a theoretical foundation and implementation framework for the ADSSS. This system institutes a differentiated compensation mechanism based on behavioral metrics while achieving efficient daily automation. Empirical results demonstrate that the ADSSS not only accurately quantifies individual performance differentials to incentivize efficiency, quality, and safety compliance but also significantly improves overall project deliverables.
Originality/value – This study pioneers a differentiated, incentive-driven salary system with automated daily settlement capabilities. The framework strategically attracts skilled personnel through competitive remuneration, enhances salary satisfaction while eliminating payment arrears, and concurrently boosts PV construction labor productivity alongside comprehensive project performance improvements in schedule adherence, quality control, and safety management.
| Original language | English |
|---|---|
| Journal | Engineering, Construction and Architectural Management |
| Publication status | Accepted/In press - 27 Oct 2025 |
