In recent years, China’s construction industry has achieved rapid development, while the problem of safety accident risks brought by construction projects has also arisen. In this paper, based on natural language processing technology, using a graph neural network algorithm, we constructed a graph data model of safety accident reports in construction engineering and generated a database of association rules of safety risk factors in construction engineering to identify and classify the risk of safety accidents in actual construction engineering. The pictures of safety risk behaviors at the construction site are processed with feature mapping and inputted into a convolutional neural network to build a construction engineering safety warning model. Through simulation experiments, the identification results of risk factors for the model constructed in this paper and the effective degree of safety warning are tested. The top five factors in the centrality ranking of risk factors of construction engineering safety accidents are S17, S6, S1, S9, and S8, with centrality levels of 1.9779, 1.8626, 1.8204, 1.6332 and 1.4534, and the factor attribute of S6 is the outcome factor. The warning model constructed in this paper is measured against the level of safety risk of the construction project under the non-adoption of the warning model. The safety risk is reduced by 35.8% after the adoption of the safety accident warning model, which shows that the model in this paper has a certain inhibition effect on the risk of safety accidents.