This report consider identifying critical errors problem in a complex project design with a large number of performers. We offer a multi-stage scheme for extracting semantic data from a large number of documents with interdependent sections. At the first stage, we estimate the complexity of the primary analysis of data from these sections. Then we will clarify this complexity in view of the identified data from adjacent sections. Based on this, the final breakdown of a large document data set is formed into clusters with alignment of their complexity. The selection and distribution of clusters between experts are in such a way as to ensure the maximum criterion of analysis efficiency in accordance with the existing time and financial resources. We used the proposed approach when developing large-scale transport projects.