The rapid development of artificial intelligence technology has brought revolutionary changes to civil engineering construction. Especially in recent years, the application of computer technology and intelligent computing methods in the field of civil engineering has made continuous progress. This study first introduces the research status and future development trend of artificial intelligence widely used in the field of civil engineering in China. Secondly, through the analysis of examples, this paper will verify the importance of model parameter selection to the prediction effect, and explore the possible error sources in the process of model construction and training. Finally, based on the actual situation, this paper puts forward relevant countermeasures and suggestions, and compares the experimental test results. The test results show that the difference of strength prediction of cement is 8%, that of sand and stone is 7.2% and that of rebar is 3.1%. The quality pass rate of cement is 100%, the quality pass rate of sand and stone is 96% and the quality pass rate of steel is 98%. This provides a reference for technical support and quality control of civil engineering construction in China.