The article describes a process of designing software for the aggregation of data (macroeconomic and statistical indicators) from distributed heterogeneous sources and their analysis based on the previously developed ontology of innovation activity and economic potential. The software includes a data aggregation system (supporting the user’s markup process of PDF, HTML, and XLS documents and texts for further automated collection), an ontology automatic replenishment system and a system of semantic search for data subsets according to certain criteria.