Abstract: [Abstract]: Firstly, based on establishing a risk assessment system of IT projects, the article proposes a multi-target synthetic assessment model based on artificial neural network (ANN). Secondly, a trained ANN can endue risk assessment model with expert assessment knowledge in the way of joint weight, through its learning and adapting capability. Finally, the risk assessment model is capable to simulate expert assessment method by verifying the data of IT projects assessment.

Key words: expert assessment method, IT project, artificial neural network (ANN), risk assessment model

摘要： [摘要]：首先本文在构建IT项目风险评价体系的基础上,提出一种基于人工神经网络的多指标综合风险评价模型。其次，利用神经网络的自学习和自适应能力，经过训练的神经网络系统能够将专家评价思想以连接权的方式赋予风险评价模型。最后，通过实际IT项目评价数据的验证，该风险评价模型能够准确地按照专家评价法进行工作。

关键词: 专家评价法, IT项目, 人工神经网络, 风险评价模型