School of Management Engineering, Zhengzhou University, Zhengzhou, Henan 450001, China.
School of Management, Shanghai University, Shanghai 200444, China.
Comput Intell Neurosci. 2022 Aug 3;2022:9402472. doi: 10.1155/2022/9402472. eCollection 2022.
This study aims to analyze the influencing factors and mechanisms of investment and financing risks in transportation projects so that regions do not restrict the transportation investment and financing risk models in all areas to achieve intelligent transportation financial risk assessment. Firstly, the investment and financing modes are studied and analyzed. According to the analysis of intellectual investment and the financing report of traffic engineering infrastructure, a traffic engineering investment and a financing model based on intelligent computing is established, which is based on artificial intelligence (AI) big data analysis technology. Secondly, the investment and the financing risk model of traffic engineering is established based on multimodal learning. Finally, the urban traffic engineering of Xi'an is taken as the research object. Based on its investment and financing data in the construction of urban roads, the risk assessment is carried out. Combined with risk influencing factors, the accuracy of the intelligent calculation in the risk assessment model is calculated. Different grades of urban transportation projects have different risks in the investment and financing of transportation projects. The results show that different levels of urban transport projects have different risks in the investment and financing (IAF) performance of transport projects. Among them, the risk index of the first-class project is the highest, reaching 0.55. The risk index of the second-class project is 0.49. The results before and after using the flow engineering IAF risk model are compared. In the test results of traffic engineering risk, all target risks did not increase after the AI-based traffic engineering IAF is tested. The model test results for credit risk and financial risk are the highest at 70 and 60, respectively. Combined with the actual urban development situation, this study can provide investment and financing risk models for urban transportation projects in different regions and provide a reference for the resource control of transportation projects. This study uses AI to learn and analyze traffic engineering investment and financing data and more accurately provide data references for traffic engineering investment and financing risk models.
本研究旨在分析交通项目投融资风险的影响因素和机制，使各地区不局限于所有地区的交通投融资风险模式，实现智能交通财务风险评估。首先，研究和分析投资和融资模式。根据智力投资和交通工程基础设施融资报告的分析，建立了一种基于智能计算的交通工程投资和融资模型，该模型基于人工智能（AI）大数据分析技术。其次，基于多模态学习建立交通工程投资和融资风险模型。最后，以西安市城市交通工程为研究对象，根据其在城市道路建设中的投融资数据进行风险评估。结合风险影响因素，计算智能计算在风险评估模型中的准确率。不同等级的城市交通工程项目在交通项目的投融资中存在不同的风险。结果表明，不同等级的城市交通工程项目在交通项目的投融资（IAF）绩效方面存在不同的风险。其中，一级项目的风险指数最高，达到 0.55。二级项目的风险指数为 0.49。比较使用流量工程 IAF 风险模型前后的结果。在交通工程风险的测试结果中，所有目标风险在基于 AI 的交通工程 IAF 测试后并未增加。信用风险和财务风险的模型测试结果最高，分别为 70 和 60。结合实际城市发展情况，本研究可为不同地区的城市交通项目提供投融资风险模型，为交通项目的资源控制提供参考。本研究利用 AI 学习和分析交通工程投融资数据，更准确地为交通工程投融资风险模型提供数据参考。
