Hypothesis Generation

OVERVIEW

Researchers at Georgetown University Medical Center Division of Integrated Biodefense along with the Department of Computer Science have developed a novel automated turnkey system to recognize threats earlier than any current technology, enabling real-time or near-real-time surveillance of massive amounts of data. This method allows the data itself to define a space of possible hypotheses, optionally merges and groups similar hypotheses, and then weighs and selects a subset of relevant hypotheses for further consideration.

The system enables human and/or machine event recognition by analyzing data to construct one or more qualitative metrics, establishing a baseline for the qualitative metric(s), identifying additional data over time, identifying an updated baseline, and outputting the adjusted baseline for display to the user. This system thus identifies known signatures of threats in massive data sets and identifies hypotheses that can explain observed data to identify unknown threats. Rather than bringing an a priori conceived hypothesis, it lets the data itself define a ranked set of possible hypotheses.

BACKGROUND

The amount of digital information on global networks is increasing exponentially and the demand for processing large amounts of digital data in real time is particularly heightened especially for identifying emerging risks and threats, particularly in the area of national security. At present, a lot of surveillance focuses on “horizon scanning” methods, which are human-based schemes for monitoring both proprietary and open-source data streams thought to be relevant to known or unknown risks or threats. While these conventional methods are the norm, they are often inefficient and cannot identify surprises, latest developments, or novel plots because these searches rely on a human conception and a defined set of interests or knowledge that a computer-aided search treats as prior knowledge. Such pre-set boundaries limit the capability of a search to detect and identify unexpected events. Thus, there is a need for an improved system to identify relevant hypotheses in data, including surprising hypotheses, and to recognize known and emergent event signatures and enable human and/or machine event recognition of safety and related events.

Benefit

• The proposed system has the ability to monitor the internet and other data continuously; discover hypotheses potentially explaining data; detect leading indicators of threats and use these as signatures of nascent events; and notify users of identified and potential threats
• This approach to hypothesis generation in security is:
  • Applicable to threats broadly defined (e.g., food fraud/adulteration, chemical and biological poisoning, supply chain vulnerability, etc.)
  • Applicable to textual (and potentially other) data
  • Executable in real time or near-real time and scalable to large applications
  • Has sound theoretical basis that users can understand and trust

Market Application

System having the ability to explain data through hypothesis generation, with broad applications in national security and other areas.

Publications

• U.S. Patent UTILITY No. 10,521,727
• U.S. Patent CIP No. 11,106,878
• U.S. Patent CONT No. 17/387,090