Universal knowledge discovery from big data using combined dual-cycle

Many people hold a vision that big data will provide big insights and have a big impact in the future. However, how to turn big data into deep insights with tremendous value still remains obscure. Here I highlight universal knowledge discovery from big data. The new concept focuses on discovering universal knowledge, which exists in the statistical analyses of big data and provides valuable insights into big data. Universal knowledge comes in different forms, e.g., universal patterns, rules, correlations, models and mechanisms. To accelerate big data assisted scientific discovery, a unified research paradigm should be built based on techniques and paradigms from related research domains, especially big data mining and complex systems science. Therefore, I propose a dual-cycle methodology with three types of cycle-driven UKD process, i.e., big-data-cycle-driven, mechanism-cycle-driven and combined-dual-cycle-driven mining. A case study is also given to illustrate the effectiveness of the proposed processes. This paper lays a foundation for the future development of universal knowledge discovery, and offers a pathway to the discovery of “treasure-trove” hidden in big data.