Abilities of data mining technology discover new ways to overcome technological challenges oil companies are facing. In order to obtain maximum effect thoughtful strategy for integrating these technologies in existing business processes is obligatory. This paper presents priority of cognitive technologies integration in the Upstream Division of Gazprom Neft PJSC. The article outlines the key steps from searching of relevant technologies for business challenges to solutions. In this paper noted that the most effective way to search for new relevant technologies in the artificial intelligence field is to cooperate with leaders in the digital technologies area such as leading Russian and international universities and research centers. For the formation of internal competencies in cognitive technologies the oil companies need to develop active cooperation with the innovative environment: participation in forums, specialized conferences, organization of seminars, technology sessions and roundtable discussion. The article also mentioned that the greatest effect of the cognitive technologies introduction could be achieved only when they are organic supplement of traditional knowledge and tools of petroleum engineering. It is noted that intellectualization changes the paradigm of field evolution: from digital based on partial automation to intellectual, not requiting human intervention in the most of decision-making processes. The digitalization of the oil and gas industry determines the course of petroleum engineer evolution: perform stream operations to the system integrated analysis with support of artificial intelligence.
1. Khasanov M.M., Prokof'ev D.O., Ushmaev O.S. et al., Promising Big Data technologies in petroleum engineering: the experience of the Gazprom Neft PJSC (In Russ.), Neftyanoe khozyaystvo = Oil Industry, 2016, no. 12, pp. 76–79.
2. Yakovlev V.V., Khasanov M.M., Prokof'ev D.O., Shushkov A.V., Technological development in Upstream Division of Gazprom Neft PJSC (In Russ.), Neftyanoe khozyaystvo = Oil Industry, 2016, no. 12, pp. 6–10.
3. Zaid Rawi, Machinery predictive analytics, SPE 128559, 2010.
4. Akande Kabiru O., Comparative analysis of feature selection-based machine learning techniques in reservoir characterization, SPE 178006-MS, 2015.
5. Gaganis V., Machine learning methods to speed up compositional reservoir simulation, SPE 154505-MS, 2012.6. The most important Big Data concepts and what they mean, URL: http://datafloq.com/read/important-big-data-concepts-what-they-mean/2988