In recent years, China’s government has encouraged the adoption of the TOT (Transfer-Operate-Transfer) model to realize the marketization of China’s public service stock projects. The TOT model is a cooperation mechanism through sharing investment, revenue and risks between the government and private partner. Therefore, a fair and reasonable revenue sharing method (RSM) is the key to the success of the TOT project. This paper aims to provide a fair and reasonable RSM based on a modified Shapley value with a triangular symmetric fuzzy structure element, which has better motivation, flexibility, forecasting function and dynamic precise distribution function. According to the factors that affect revenue sharing, the Shapley value is improved with initial correction coefficient composed of investment ratio, risk-sharing ratio, execution degree, and fuzzy payment to achieve fairness and reasonableness. The methodology is illustrated by a case study of a TOT project selected from Laohekou city of Hubei province, China. The results testify that the revenue-sharing ratios of participants is positively correlated with the initial correction coefficient, which make the RSM more motivating; and the Shapley value with fuzzy payment by using triangular symmetric fuzzy element function make the RSM more flexible, and it has both forecasting function and precise dynamic distribution function under project revenue uncertainty.

In order to standardize public resource trading activities and improve the operating efficiency of public resource trading platforms, this paper conducts research on the performance of public resource trading platforms. A three-level and 28-dimension performance evaluation index system for public resource trading platform is established by considering the four levels of input-process-output-effect. Besides, entropy weight method, gray clustering, and fuzzy comprehensive evaluation are integrated on this basis. Entropy weight method is used to determine the index weight, and the degree value of membership for indexes on gray class is determined based on gray clustering method and converted into a matrix. Then, fuzzy comprehensive evaluation method is used to determine the evaluation value and finally carry out the platform performance evaluation, which provides theoretical support for academic researchers to conduct follow-up research on the performance evaluation of public resource trading platforms.

This study addresses the limitations of existing machine learning and deep learning methods in construction safety risk assessment, particularly their limited generalization across diverse contexts and their difficulty in handling complex, high‐dimensional data. A hybrid ensemble learning framework that integrates the social network search (SNS) algorithm and t‐distributed stochastic neighbor embedding (t‐SNE) technology is proposed to enhance prediction accuracy and computational efficiency. A comprehensive, multi‐dimensional risk assessment database was developed through questionnaire surveys and on‐site data collection. t‐SNE was employed to reduce data dimensionality and extract key features, which were then used to train a hybrid ensemble model combining extreme gradient boosting (XGBoost), a backpropagation neural network (BPNN), random forest (RF), and CatBoost. The SNS algorithm was applied to optimize model parameters, further improving predictive performance. Results indicate that the proposed approach achieves high accuracy and strong generalization capability, outperforming traditional single‐model methods. This framework offers a practical and effective tool for supporting construction safety management, enabling proactive risk prevention, and contributing to safer construction environments.