System and method for detecting, collecting, analyzing, and communicating event-related information

• US 9,529,974 B2
• Filed: 07/27/2011
• Issued: 12/27/2016
• Est. Priority Date: 02/25/2008
• Status: Active Grant

• Current Assignee: Georgetown University
• Original Assignee: Georgetown University
• Inventors: Yoon, Jae I., Li, Peter C., Collmann, Jeffrey R., Blake, Jane W., Polyak, Mark G., Wilson, James M., Torii, Manabu, Thomas, Carla S.
• Primary Examiner(s): Maung, Zarni
• Application Number:
  US13/192,160
• Publication Number:
  US 20120197896A1
• Time in Patent Office: 1,980 Days
• Field of Search: 709/203, 709217-219, 709223-229, 709/250
• US Class Current: 1/1
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 50/26 Government or public services business processes related to the transportation industry G06Q50/40
• CPC Class Codes: G16H 50/80 for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

A system and method involves detecting operational social disruptive events on a global scale, assigning event staging and warnings to express data in more simplistic terms, modeling data in conjunction with linguistics analysis to establish responsive actions, generating visualization and modeling capabilities for communicating information, and modeling propagation of events for containment and forecasting purposes.

Claims

1. A computer implemented method for filtering open source documents to detect events, the method comprising:

storing, at a first server, indications and warnings associated with each of a plurality of event types, each of the event types being related to a disease or pest infestation affecting a plant or non-human animal;

receiving a selection of an event type;

receiving a selection of a surveillance location;

identifying information sources that may have data about the selected event type;

downloading publicly accessible data from the selected information sources;

filtering the data, using an alert generation module developed using Bayesian causal models, to identify a subset of the data containing indications and warnings that suggest that the disease or pest infestation is occurring;

creating and storing an event report identifying the disease or pest infestation based on the subset of the publicly accessible data containing the indications and warnings; and

outputting the event report over a communications network.

2. The method according to claim 1, wherein the surveillance location is one of a town, city, region, and country.

3. The method according to claim 1, wherein the information sources are web servers connected to the Internet.

4. The method according to claim 1, wherein the indications and warnings are individual or combinations of keywords.

5. The method according to claim 1, wherein the step of downloading data from the selected information sources comprises the steps of:

crawling the information sources;

encoding the data; and

storing the encoded data in a first database.

6. The method according to claim 5, further comprising the step of indexing the encoded data.

7. The method according to claim 1, further comprising the step of translating the data from a first language into a second language.

8. The method according to claim 1, further comprising assigning a scale value to the subset of the data indicating a degree of the event.

9. The method according to claim 8, wherein the scale value comprises an indicia selected from one of a word, a phrase, and a color.

10. The method according to claim 8, wherein the scale value is selected from one of an Advisory, a Watch, and a Warning.

11. The method according to claim 1, wherein the step of storing the event report comprises the steps of:

launching a template;

selecting metadata from a stored list of possible metadata;

if an event report exists, updating the existing event report using some of the subset of the data and the metadata; and

if an event report does not exist, storing a first summary of the event using some of the subset of the data and the metadata in an event report file.

12. The method according to claim 1, wherein the step of filtering comprises the steps of:

receiving a query search string;

comparing the query search string to an index; and

returning a list comprising the subset of the data using the query search string.

13. A system for filtering open source documents to detect events, comprising:

one or more document collection servers that download and store publicly accessible data from information sources;

a first server that stores indications and warnings associated with each of a plurality event types, each of the event types being related to a disease or pest infestation affecting a plant or non-human animal;

a graphical user interface that receives a selection of an event type and a selection of a surveillance location;

an alert generation module developed using Bayesian causal models that identifies a subset of the publicly accessible data containing indications and warnings that suggest that the disease or pest infestation is occurring;

an analysis and reporting subsystem that creates and outputs an event report identifying the disease or pest infestation based on the subset of the publicly accessible data containing the indications and warnings.

14. The system according to claim 13, wherein the surveillance location is one of a town, city, region, and country.

15. The system according to claim 13, wherein the information sources are web servers connected to the Internet.

16. The system according to claim 13, wherein the indications and warnings are individual or combinations of keywords.

17. The system according to claim 13, wherein the server downloads data from the information sources by:

crawling the information sources;

encoding the data; and

storing the encoded data in a first database.

18. The system according to claim 17, wherein the server indexes the encoded data.

19. The system according to claim 13, wherein the system translates the data from a first language into a second language.

20. The system according to claim 13, wherein the system assigns a scale value to the subset of the data indicating a degree of the event.

21. The system according to claim 20, wherein the scale value comprises an indicia selected from one of a word, a phrase, and a color.

22. The system according to claim 20, wherein the scale value is selected from one of an Advisory, a Watch, and a Warning.

23. The system according to claim 13, wherein the analysis and reporting subsystem creates the event report by:

launching a template;

selecting metadata from a stored list of possible metadata;

if an event report exists, updating the existing event report using some of the subset of the data and the metadata; and

if an event report does not exist, storing a first summary of the event using some of the subset of the data and the metadata in an event report file.

24. The system according to claim 13, wherein the alert generation module identifies the subset of the publicly accessible data containing indications and warnings that suggest that the disease or pest infestation is occurring by:

receiving a query search string;

comparing the query search string to an index; and

returning a list comprising the subset of the data using the query search string.