Proactive spatiotemporal resource allocation and predictive visual analytics system

Patent metadata

Field	Value
Publication number	US-12073341-B2
Application number	US-202016792785-A
Country	US
Kind code	B2
Filing date	Feb 17, 2020
Priority date	Nov 13, 2014
Publication date	Aug 27, 2024
Grant date	Aug 27, 2024

Abstract

Disclosed herein is a visual analytics system and method that provides a proactive and predictive environment in order to assist decision makers in making effective resource allocation and deployment decisions. The challenges involved with such predictive analytics processes include end-users' understanding, and the application of the underlying statistical algorithms at the right spatiotemporal granularity levels so that good prediction estimates can be established. In the disclosed approach, a suite of natural scale templates and methods are provided allowing users to focus and drill down to appropriate geospatial and temporal resolution levels. The disclosed forecasting technique is based on the Seasonal Trend decomposition based on Loess (STL) method applied in a spatiotemporal visual analytics context to provide analysts with predicted levels of future activity. A novel kernel density estimation technique is also disclosed, in which the prediction process is influenced by the spatial correlation of recent incidents at nearby locations.

First claim

The invention claimed is:

1. A method, comprising:
receiving an input, the input comprising a geospatial template digital file representing a desired geospatial resolution and a temporal template digital file representing a desired temporal resolution;
selectively subdividing the geospatial template digital file based on a defined criteria to produce a plurality of digital geospatial subdivisions;
generating a digital time series historical signal for each of the plurality of digital geospatial subdivisions within the geospatial template digital file, the digital time series signal defined by the temporal template digital file and based on historical activity data;
forecasting probability of occurrence of a predetermined event based on the generated digital time series and thus generating a set of forecast results from each of the digital time series associated with selective spatiotemporal variations of each of the plurality of digital geospatial subdivisions; and
providing the set of forecast results as visual output on an electronic display to a user.

2. The method of claim 1 , wherein the visual output comprises a graphical representation of each of the plurality of digital geospatial subdivisions and an indicator of the forecast result for each of the plurality of digital geospatial subdivisions, the indicator displayed within a corresponding digital geospatial subdivision.

3. The method of claim 2 , the indicator comprising a color, the color dependent on the forecast result.

4. The method of claim 2 , wherein the visual output comprises a choropleth map.

5. The method of claim 2 , wherein the visual output comprises a heat map.

6. The method of claim 1 , wherein the geospatial template digital file defines a geospatial region having an incident activity level above a first threshold.

7. The method of claim 1 , wherein said incident activity level corresponds to crime incidents.

8. The method of claim 1 , wherein said incident activity level corresponds to health care need incidents.

9. The method of claim 1 , wherein the temporal template defines a time period having an incident activity level above a first threshold.

10. The method of claim 1 , wherein the Currently Amended time series signal comprises historical event incidence vs. time step signals.

11. The method of claim 1 , wherein the digital time series signal comprises kernel value vs. time step signals.

12. The method of claim 1 , wherein said generating a set of forecast results is determined based on seasonal trend decomposition using loess.

13. The method of claim 1 , wherein said defined criteria are law enforcement jurisdictions.

14. The method of claim 1 , further comprising: providing visual feedback to the user on a display to indicate if the historical activity data is insufficient to produce forecast results having an accuracy above an accuracy threshold.

15. The method of claim 1 , wherein the geospatial template digital file or temporal template digital file is based on a predetermined confidence interval.

16. A system, comprising:
a computer processor; a memory;
an input device; and
an electronic display
wherein the computer processor is configured to:
receive an input, the input comprising a geospatial template digital file representing a desired geospatial resolution and a temporal template digital file representing a desired temporal resolution;
selectively subdivide the geospatial template digital file based on a defined criteria to produce a plurality of digital geospatial subdivisions;
generate a digital time series historical signal for each of the plurality of digital geospatial subdivisions within the geospatial template digital file, the digital time series signal defined by the temporal template digital file;
forecast probability of occurrence of a predetermined event based on the generated digital time series and thus generate a set of forecast results from each of the digital time series associated with selective spatiotemporal variations of each of the plurality of digital geospatial subdivisions; and
provide the set of digital forecast results as visual output on the electronic display to a user.

17. The system of claim 16 , wherein the visual output comprises a graphical representation of the digital geospatial subdivisions and an indicator of the forecast result for each of the digital geospatial subdivisions, the indicator displayed within a corresponding digital geospatial subdivision.

18. The system of claim 17 , the indicator comprising a color, the color dependent on the forecast result.

19. The system of claim 17 , wherein the visual output comprises a choropleth map.

20. The system of claim 17 , wherein the visual output comprises a heat map.

21. The system of claim 16 , wherein the geospatial template digital file defines a geospatial region having an incident activity level above a first threshold.

22. The system of claim 16 , wherein said incident activity level corresponds to crime incidents.

23. The system of claim 16 , wherein said incident activity level corresponds to health care need incidents.

24. The system of claim 16 , wherein the temporal template digital file defines a time period having an incident activity level above a first threshold.

25. The system of claim 16 , wherein the digital time series signal comprises historical event incidence vs. time step signals.

26. The system of claim 16 , wherein the digital time series signal comprises kernel value vs. time step signals.

27. The system of claim 16 , wherein said defined criteria are law enforcement jurisdictions.

28. The system of claim 16 , wherein the computer processor is configured to: provide visual feedback to the user using the display to indicate if the historical activity data is insufficient to produce forecast results having an accuracy above an accuracy threshold.

29. The system of claim 16 , wherein the geospatial template digital file or temporal template digital file is based on a predetermined confidence interval.

Assignees

• Purdue Research Foundation

Inventors

• Ebert David Scott
• Malik Abish
• Towers Sherry
• Maciejewski Ross

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q10/06 Primary

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title