The high number of annual safety accidents and casualties reflects the problems of slow detection of safety accidents and untimely early warnings in current construction safety management, and China urgently needs new methods and technologies to improve the safety management efficiency of the construction industry. However, there are fewer achievements in the use of new technologies for intelligent construction safety management, and most of the research focuses on intrusion detection and specific event alarms, which cannot be well implemented for systematic early warning functions. Based on the existing research and the characteristics of early warning scenarios, this study introduces the convolutional neural network (CNN) to build a video image recognition and classification model to give early safety warnings for intrusion behavior in hazard areas of construction and demonstrates the warning effect and accuracy with practical cases. First, it clarifies the early warning demand information, such as the attributes of construction personnel and hazard areas. Then, the construction model is realized by multi-scale hierarchical feature extraction mapping, the Softmax classification function, and the argmax function. Finally, from the empirical analysis, it can be seen that an early safety warning based on the CNN model has an accurate ability to identify the intrusion behavior of construction site personnel, which can reduce the probability of construction safety accidents to a certain extent, and provide enlightenment for further realization of intelligent construction sites.

In the midst of sweeping economic transformation, owing to the increasing strategic importance of environmental issues, directors’ green experience is crucial for green innovation. This paper proposes the concept of interlocking directors’ green experience richness (IDGER), considering both the number of directors with green experience and their green linkage strength from the director network. This paper conducts theoretical exploration and empirical research on the impact of IDGER on the companies’ green innovation efficiency. The findings reveal (1) IDGER significantly enhances the green innovation efficiency of Chinese listed companies, and the result is also validated through robustness tests. This study expands the antecedents of green innovation from a board governance perspective. (2) IDGER can enhance green innovation efficiency by increasing executive environmental attention, reducing managerial myopia, and alleviating financing constraints. (3) Media attention can positively moderate the relationship between IDGER and company green innovation efficiency. This expands the understanding of the role of directors’ green experience in corporate green innovation and provides new ideas for emerging market companies on how to promote green innovation by optimizing the composition of their board of directors for achieving sustainable development goals.

With the aggravation of the global climate problem, various countries are gradually formulating relevant policies and targets for carbon emission reduction in the infrastructure industry. Some countries or cities may have the problem of insufficient investment in infrastructure construction or blind investment, so it is urgent to carry out related research on the efficiency of infrastructure investment. From the perspective of carbon emission constraints, this study takes Chinese cities as the research case, and uses the unexpected output ultra-efficiency SBM model to measure the infrastructure investment efficiency and total-factor productivity from 2010 to 2020, and analyzes the influencing factors of infrastructure investment efficiency. The study found that (1) the regions with high infrastructure investment efficiency have the following two characteristics: the first relates to the cities with high investment, high output and fewer carbon emissions, and these cities rank at the forefront of economic development and scientific and technological level in the country. The second relates to the cities with high investment, high output and large carbon emissions. These cities have a large urban scale, their industrial structure is dominated by the secondary and tertiary industries, and their high output level plays a benign leading role. (2) Cities with low infrastructure investment efficiency are mainly manifest a large input of some infrastructure resources, low output level, high carbon emissions, and insufficient scale efficiency. (3) Economic level, industrial structure and fiscal expenditure play a positive role in improving the efficiency of infrastructure investment, and the development strategy of policies also affects the infrastructure investment mode. Finally, there are recommendations for the sustainable and high-quality development of infrastructure investment in developing countries.

Exploring pathways for sustainable synergistic development is a challenging issue for the construction industry, which is currently in a critical period of transformation. Current research has confirmed that industrial clusters are an important organizational form for promoting sustainable synergistic development. However, the existing research on construction industry clusters has overly focused on cluster attribute analysis and evaluation. Investigating the core mechanisms of synergistic development within construction industry clusters is particularly crucial. From the perspectives of ecological and synergetic theories, this paper constructs the ecosystem of the construction industry cluster and analyzes its synergistic development process. It identifies the driving factors of the synergistic development of the construction industry cluster and uses the ISM model to determine the structural hierarchical relationships among factors. Taking Shandong Province as the data sample, this study employs the Haken model to conduct an empirical investigation of the level of synergy and its driving mechanisms, establishing a three-stage framework for the driving mechanisms. The results show the following results: (1) Operating efficiency and innovation ability are the top factors to promote the synergistic development of the construction industry. (2) Market demand, as an order parameter, is an important condition for triggering and amplifying fluctuations in the construction industry cluster system, and it acts as a controlling factor to promote the system’s self-organization evolution to a new ordered and stable state. (3) The construction industry cluster in Shandong Province is in the initial stage of low synergy and is gradually evolving to moderate synergy. From a new research perspective, this study helps construction industry planners and policymakers understand the mechanisms of evolution and key driving factors of construction industry clusters.

Against the background of profound transformation within the construction industry, the construction industry ecosystem serves as a vital vehicle for regional economic development. Its resilience has become a key factor in influencing the sustainable development of industry. From an ecological perspective, this paper integrated the cusp catastrophe model and Fuzzy-Set Qualitative Comparative Analysis (fsQCA) method, using data from Shandong Province to investigate the evolutionary state of the construction industry ecosystem and the diverse concurrent paths driving the system toward high levels of functionality. This study found that: (1) the resilient development of the construction industry ecosystem in Shandong Province presented a differentiated pattern, characterized by dual-core leadership, relative strength in the east, and weakness in the west, and localized catch-up. (2) The results from the cusp catastrophe model indicated that construction industry ecosystems in different regions were primarily undergoing stable evolution, though some cities faced the risk of functional degradation due to the combined effects of insufficient resilience and severe shocks. (3) fsQCA identified three equivalent configuration paths for achieving high system functionality: the “resilience accumulation path”, “resilience synergy path”, and “resilience transition path”, as well as three equivalent configuration paths for low system functionality: the “low resilience-low shocks dependency path”, “low-resilience, fixed-type path”, and “low resilience-high shocks imbalance path”. (4) These paths demonstrated that recovery was the key factor determining a system’s level of functionality.