With the form of new data sources on the Internet, integrating data from heterogeneous data repositories has become critical. However, multiple sources of data introduce problems such as redundancy, conflicts, or missing data reports. The two major categories of challenges for large scale data integration systems are heterogeneous data and conflicting data. Inaccurate results and poor decision making may occur during the integration process; during integration process the data is redundant and inconsistent. The solutions for heterogeneous data have been researched for many years, but the challenges of conflicting data are not well explored yet. We aim at improving the quality of information integration via data inconsistency detection method and information design process through experimental results. © 2018 [International Journal of Artificial Intelligence].