Method and system for spatial behavior modification based on geospatial modeling

• US 20080104005A1
• Filed: 10/29/2007
• Published: 05/01/2008
• Est. Priority Date: 04/04/2005
• Status: Active Grant

• Current Assignee: Maxar Mission Solutions Incorporated (Galileo Parent, Inc.)
• Original Assignee: Spadac Inc.
• Inventors: Dalton, Jason
• Granted Patent: US 7,801,842 B2
• Time in Patent Office: Days
• US Class Current: 706/45
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/00 Administration; Management
• 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 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06T 17/05 Geographic models
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G09B 29/007 using computer methods

Abstract

Behavioral influences are determined and real-world variables modified according to the present invention. A forecasting engine and method assists in forecasting occurrences of identifiable events and/or results based on signature and/or pattern matching. The present invention derives signature for event-types based on a comparison of actual event data with pre-established representational surfaces. The surfaces represent functional measurements and analysis associated with elements of the geospatial boundary being considered. In one embodiment, the present invention assists in the determination of possible real-world factor influence opportunities in order to influence desired behavior.

Claims

1. A method for influencing the likelihood of a future event occurring in or away from a specified geospatial area, comprising the steps of:

establishing a geospatial boundary representative of an area of interest (AOI);

establishing at least one layer imposed upon the boundary, the layer being indicative of geospatial characteristics of at least one modifiable variable of interest;

receiving geospatial information pertaining to one or more past events of the event type, including location information for the one or more past events;

determining a likelihood associating the event type'"'"'s relative proximity to the modifiable variable of interest;

determining whether the modifiable variable of interest is capable of influencing the event type; and

upon determining that the modifiable variable of interest is capable of influencing the event type, initiating a real-world modification to the variable of interest.

2. The method of claim 1 wherein a plurality of layers are imposed upon the boundary, each of which is indicative of geospatial characteristics of at least one modifiable variable of interest, wherein the likelihood determination step is applied to each of the modifiable variables of interest, and wherein real-world modifications are initiated on a plurality of the variables of interest.

3. The method of claim 1 wherein the step of initiating a real-world modification to the variable of interest is restricted by one or more constraints.

4. The method of claim 1 wherein the step of initiating a real-world modification to the variable of interest is performed within only a portion of the AOI.

5. The method of claim 1 wherein the step of determining whether the modifiable variable of interest is capable of influencing the event type is performed using one or more computer simulations.

6. The method of claim 1 further including the step of assigning a relative weight to the variable of interest based upon the step of determining whether the modifiable variable of interest is capable of influencing the event type.

7. The method of claim 1 including the steps of:

deriving and solving an objective function to determine one or more optimal modifications for the variable of interest so as to minimize or maximize the likelihood of the future event occurring in or away from the specified geospatial area.

8. The method of claim 1 wherein the event can be an activity, a behavior, a customer set, a threat.

9. The method of claim 1 wherein the at least one variable of interest is influenced at a given time.

10. The method of claim 1 wherein the step of artificially influencing the at least one variable involves an informational event.

11. The method of claim 1 wherein the step of artificially influencing the at least one variable involves a physical process.

12. A computerized method for selectively increasing or decreasing the likelihood of a future event occurring in a specified geospatial area, comprising the steps of:

providing programming capable of making probability assessments of a given event-type for a given geospatial area of interest (AOI) based on the geospatial characteristics of at least one variable of interest (VOI) and past geospatial data for the event-type;

determining whether the at least one VOI is modifiable and causal of the event-type; and

upon determining that the at least one VOI is modifiable and causal of the event-type, iteratively executing the programming and modifying a characteristic of the VOI until the desired likelihood of the event type is obtained.

13. The method of claim 12 wherein the step of modifying a characteristic of the at least one VOI includes modifying a weight factor applied to the VOI.

14. The method of claim 12 wherein the step of modifying a characteristic of the at least one VOI includes increasing or decreasing the number of instances of the VOI within the AOI.

15. The method of claim 12 wherein the step of modifying a characteristic of the at least one VOI is performed within pre-established constraints on the VOI.

16. The method of claim 12 wherein the programming is capable of making a probability assessment based on the geospatial characteristics of a plurality of variables of interest (VOIs), and wherein the step of iteratively executing the programming and modifying a quantitative characteristic applies to a plurality of VOIs that are modifiable and causal of the event-type.

17. A system for influencing the likelihood of a future event occurring in or away from a specified geospatial area, comprising:

a boundary component for establishing a geospatial boundary representative of an area of interest (AOI);

a layer component for establishing at least one layer imposed upon the boundary, the layer being indicative of geospatial characteristics of at least one modifiable variable of interest;

a signature derivation component for receiving geospatial information pertaining to one or more past events of the event type, including location information for the one or more past events, and for determining a likelihood associating the event type'"'"'s relative proximity to the modifiable variable of interest; and

an influence component for determining whether the modifiable variable of interest is capable of influencing the event type and upon determining that the modifiable variable of interest is capable of influencing the event type, initiating a real-world modification to the variable of interest.

18. A system for selectively increasing or decreasing the likelihood of a future event occurring in a specified geospatial area, comprising:

a signature derivation component having programming for making probability assessments of a given event-type for a given geospatial area of interest (AOI) based on the geospatial characteristics of at least one variable of interest (VOI) and past geospatial data for the event-type; and

an influence component for determining whether the at least one VOI is modifiable and causal of the event-type and upon determining that the at least one VOI is modifiable and causal of the event-type, iteratively executing the programming and modifying a characteristic of the VOI until the desired likelihood of the event type is obtained.