Enterprise Information Fusion for Real-time Business Intelligence

摘要

We define, describe and motivate an emerging business intelligence need, which we call Enterprise Information Fusion: As a consequence of the growth and popularity of social media such as Twitter, news events of even minor or highly local import are often reported here by reporters as well as the general public. Similarly, conversations in specialized blogs and discussion forums often mention specific faults or difficulties being faced by consumers of products or services. We argue how such publicly available data can potentially be of tremendous operational value for large enterprises across diverse industries, such as manufacturing, retail or insurance. At the same time, in order to assess the impact of external events it is also important to correlate these in real-time with known facts about the internal operations and transactions of the enterprise and its ecosystem. We describe a framework for Enterprise Information Fusion that exploits traditional AI techniques, such as the blackboard architecture (used often for information fusion), as well as newer ones, such as locality sensitive hashing. Lastly we describe preliminary experience in developing selected components of our Enterprise Information Fusion (EIF) framework while also outlining the future research needed to complete the desired solution.