Invention Grant
- Patent Title: Generating hypotheses and recognizing events in data sets
-
Application No.: US17059985Application Date: 2019-05-31
-
Publication No.: US11887018B2Publication Date: 2024-01-30
- Inventor: David M. Hartley , Nili S. Yossinger , Ophir Frieder
- Applicant: GEORGETOWN UNIVERSITY
- Applicant Address: US DC Washington
- Assignee: Georgetown University
- Current Assignee: Georgetown University
- Current Assignee Address: US DC Washington
- Agency: Blank Rome LLP
- International Application: PCT/US2019/034824 2019.05.31
- International Announcement: WO2019/232317A 2019.12.05
- Date entered country: 2020-11-30
- Main IPC: G06F16/35
- IPC: G06F16/35 ; G06F16/33 ; G06F16/36 ; G06F16/31 ; G06N5/04

Abstract:
A hypotheses generation and event recognition system that enables event recognition by analyzing documents to construct one or more qualitative metrics (e.g., frequency of keywords, changes in sentiment, occurrence of ontological terms, evolution of topics, etc.), establishing a baseline for the qualitative metric(s), and outputting changes to that baseline for display. In aggregate, those qualitative metrics comprise temporal and/or spatial signals that, when combined, define signatures of events of interest. Accordingly, the user and/or the system may identify an event of interest based on the change in baseline. The system may further provide functionality to generate hypotheses by coding data according to an ontology, populating an ontology space, and using an optimization algorithm to rank points or neighborhoods in the coded ontology space. The system may further store links between ontological terms and qualitative metrics to provide functionality to test generated hypotheses that include those linked ontological terms.
Public/Granted literature
- US20210232953A1 GENERATING HYPOTHESES AND RECOGNIZING EVENTS IN DATA SETS Public/Granted day:2021-07-29
Information query