This paper focuses on the application of human–computer interaction technology in construction project safety management. Through bibliometric methods, we carried out an in-depth analysis of 286 relevant papers from Web of Science and Google Scholar from 2000 to 2024. The research results indicate that human–computer interaction technology has achieved remarkable development in four aspects: intelligent monitoring systems, risk assessment and management, ergonomics and cognitive psychology, as well as computer simulation and virtual reality. Meanwhile, this research has given rise to a series of new research topics, such as the safety operation decision-making method for intelligent construction machinery, the application of human action behavior recognition technology, and the application of Internet of Things technology in the safety control of smart construction sites. Additionally, future research modules have been identified, including personalized safety training, digital twin technology, and multimodal data analysis. This study not only summarizes the existing research achievements but also puts forward targeted suggestions for future development trends in the field of construction safety management from a practical perspective, aiming to promote the in-depth application and development of human–computer interaction technology in construction safety management.

Accurately evaluating the vulnerability of prefabricated components in prefabricated buildings is the basis of scientific management of its supply chain. Thus, a novel vulnerability evaluation method for the suppliers of prefabricated components in the context of prefabricated buildings was proposed in this study. First, a vulnerability evaluation index system was identified and constructed by the pressure–state–response (PSR) model. With the clear logic and strong applicability of PSR, this system, including 18 indexes, was easy to understand and exhibited strong practicability. The weights were then determined via the multiplicative analytic hierarchy process with the expansion of a probabilistic language terminology set (PLTS). PLTS could describe decision information more comprehensively, so the evaluation result is more scientific. Subsequently, the probability of the vulnerability level was superimposed in a parallel bottom-to-top method via the controlled interval and memory (CIM) models, and these were extended by the PLTS. This set handled the uncertain information in the decision-making process more efficiently and accurately, and finally determined the vulnerability distribution. Ultimately, the probability of each vulnerability level was determined by combining the weight information. The reconstruction and resettlement housing construction project of urban shanty towns in the Taohua South Road Community in Xihu District, Nanchang City, was selected as a case study. The case study proves the effectiveness of this method, which has higher resolution and is more convenient for managers to make decisions.

Vulnerability assessments of public service buildings (PSBs) are critical to life cycle management. An accurate evaluation can substantially improve the quality of public services and reduce the government’s financial burden. We proposed a WBS-VBS framework to build a vulnerability decomposition matrix for PSBs. A Chinese vocational education center relocation case study validated the method. Structural equation modeling (SEM) was used to normalize the path coefficients and obtain the index weights. The matter-element extension method was utilized to calculate correlation functions and determine the vulnerability levels of different indicators. The case study results demonstrate the effectiveness of the model.

The assembly quality of scaffolding systems directly governs the safety of personnel on construction sites. According to construction safety statistics, scaffolding-related accidents account for approximately 30–40% of construction fatalities globally, with geometric assembly deviations being a contributing factor in over 60% of scaffold collapse incidents. Traditional scaffolding inspections rely heavily on manual measurements, which are inherently inefficient, hazardous, and difficult to scale comprehensively. This study presents an automated evaluation framework that integrates computer vision with structural mechanics simulations. First, an object detection model based on the SegFormer encoder architecture is developed to precisely identify scaffolding standards, ledgers, and couplers against complex site backgrounds. Its hierarchical Transformer encoder and global self-attention mechanism enable the model to capture long-range topological relationships, achieving a mean Average Precision (mAP@0.5) of 95.2% on a custom dataset with an inference speed of 45 FPS per 640 × 640 image patch. For complete high-resolution frame processing including tiling and geometric extraction, the end-to-end pipeline requires approximately 8–12 s per frame. Second, a simplified Hough transform with a restricted parameter domain is introduced. Integrated with a dual-track image processing workflow, this algorithm performs sub-pixel centerline fitting to automatically extract critical geometric parameters, including lift height and bay width, maintaining a relative measurement error within 3.5% compared to manual ground truth. Finally, a parameterized finite element model is established. An automated mapping middleware dynamically injects the extracted as-built parameters into the simulation environment. Comparative simulation analysis indicates that a 14.7% deviation in standard lift height, coupled with an initial tilt defect of 1/150, precipitates a 22.4% reduction in the predicted structural stability factor, illustrating the framework’s capability for assessing relative capacity degradation between design intent and as-built conditions. This framework establishes a robust, closed-loop pipeline spanning visual perception and structural safety assessment, indicating potential for automated construction site safety management.

To address challenges such as complex background interference, limited long-range modeling capabilities of CNNs, and poor generalization in steel-concrete cross-material scenarios, this study proposes an enhanced detection framework. This framework integrates a TAPFormer with morphological reasoning rules. The method utilizes TAPFormer as the backbone network. It captures global topological features of cracks through a Task-Aware Query mechanism. This approach compensates for the deficiencies of traditional convolutional operators in modeling the continuity of thin and long cracks. Furthermore, a mask reasoning module based on geometric priors is developed to handle unstructured interferences, such as marker pen marks, welds, and concrete holes. This module defines logical criteria, including edge curvature consistency, axial aspect ratios, and endpoint extension directions. These criteria are used to perform topological repair and filter false positives in the initial segmentation masks. A hybrid dataset containing 4500 cross-material damage images was used for validation. The results show that the proposed method achieves a mean IoU of 86.72% and an F1-score of 90.36%. Notably, the method filters over 91.0% of false positives caused by manual marker pen marks in interference-rich scenarios. Compared to mainstream state-of-the-art models, the IoU improves by at least 5.48%. The results show that the proposed framework improves the robustness and logical self-consistency of crack identification in complex engineering environments.