On 3rd March 2018, Total completed the acquisition of Maersk Oil. This reinforced the Group’s existing leading positions in the U.K. and in Norway, as well as to enter Denmark. This makes Total the second largest operator in the North Sea with an output of 500,000 boe/d by 2020. As a result of the acquisition, an entire oil company’s 4 petabyte data set, amounting to more than 300M files, needed to be quickly and efficiently absorbed and integrated within Total, with minimum disruption to ongoing operations. The presentation will examine how Total worked with Flare Solutions to absorb a vast amount of content and deploy content clean-up, taxonomies, classification, analytics and machine learning techniques to deliver relevant content to support the technical project teams. This presentation provides an overview of the challenges addressed in handling such a huge influx of data, documents and other content, residing in non-connected infrastructures within a limited timeframe, while maintaining business as usual. The approach that was developed delivered a high-quality data set in a highly efficient manner, involving: - Crawling source network drives - Loading directory/file structures into the selected solution - Using graph database technology to search and identify areas for migration, archival or deletion - Re-structuring directory views - Identification on non-entitled data - Use analytics & ML to verify, augment and improve content.