Generic Template Node for Developing and Deploying Model Software Packages Made Up Of Interconnected Working Nodes

• US 20150347096A1
• Filed: 06/02/2015
• Published: 12/03/2015
• Est. Priority Date: 06/02/2014
• Status: Active Grant

• Current Assignee: Blackwatch International
• Original Assignee: Blackwatch International
• Inventors: Hanna, Michael
• Granted Patent: US 10,360,000 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 8/20 Software design
• CPC Class Codes: G06F 8/34 Graphical or visual programming
• CPC Class Codes: G06F 8/36 Software reuse
• CPC Class Codes: G06F 8/61 Installation
• CPC Class Codes: G06F 9/547 Remote procedure calls [RPC]; Web services
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: Y04S 40/18 Network protocols supporting networked applications, e.g. including control of end-device applications over a network

Abstract

A generic template node for developing and deploying model software packages made up of interconnected working nodes derived from modifying copies of a generic template node. In one embodiment, a generic template node comprises: a plurality of definable input and output channels; at least one modifiable process routine capable of executing instructions for integrating into the generic template node at least one of, (i) a custom process, (ii) a canned common function, e.g., Sum and/or Average, and (iii) a third-party software package; a setup routine; and a plurality of definable output channels. The setup routine is operably linked to a host process to perform setup initialization of the generic template node. The generic template node is executable using at least one processor in communication with at least one memory having instructions to modify the generic template node in response to user requests.

Claims

1. A generic template node comprising:

a plurality of definable input and output channels;

at least one user-modifiable process routine capable of executing instructions for integrating into the generic template node at least one of, (i) a custom process, (ii) a canned common function, and (iii) a third-party software package; and

a setup routine, operably linked to a host process to perform setup initialization of the generic template node, and

wherein the generic template node is stored on at least one memory in communication with at least one processor.

2. The generic template node of claim 1, wherein the user-modifiable process routine is modifiable to allow a user to modify the process routine and the input and output channels to convert the generic template node into a working node.

3. The generic template node of claim 1, wherein the process user-modifiable process routine comprises an overridable setup routine.

4. A method of modular software development by modifying a plurality of generic template nodes according to claim 1 to create a model made up of interconnected working nodes, wherein a compiler is not required in developing the working nodes.

5. A method of modular software development by individually modifying a plurality of generic template node templates to create a model made up of interconnected working nodes, comprising:

(a) providing a generic template node of claim 1;

(b) modifying the process routine to create a working node by executing instructions for integrating into the generic template node at least one of, (i) a custom process, and (ii) integrating a third-party software package;

(c) repeating steps (a) and (b) to create a plurality of working nodes; and

(d) providing connectivity between the working nodes,

wherein the host process controls the working nodes to create a model software package.

6. A method of predicting the presence of improvised explosive devices (IEDs) in an external environment, the method comprising:

modifying a plurality of generic template nodes of claim 1 to develop a model for,

determining the location of the external environment;

classifying the location based on predetermined location types to provide a location type;

receiving historical data on previous actual detection of IEDs in the location and performing an age analysis of the historical data;

performing a weight risk analysis based on age of the historical data and location type;

detecting presence of IEDs in response to raw detection data received via one or more sensors;

calculating Positive Predictive Value (PPV) and Negative Predictive Value (NPV) for each detected IED;

calculating a confidence value for each detected IED based on PPV verses NPV;

weighting the confidence value of each detected IED based on location type and age analysis of the location to provide a weighted confidence value;

performing a cut-off value for each weighted confidence value to predict one or more IEDs in said location; and

outputting the predicted locations of IEDs.

7. The method according to claim 6 further comprising the step of classifying the likely type of each predicted IED based on the historical data on previous actual detection of IEDs in the location.

8. The method according to claim 6, wherein the step of outputting the reportable detections of IEDs includes outputting instructions for a bomb disposal crew to deploy to examine at least one predicted IEDs

9. The method according to claim 6, wherein a development platform is used to generate computer code to perform said method, wherein the platform comprises at least one generic template node.

10. A system for executing a plurality of generic template nodes, comprising:

one or more memories having a generic node template according to claim 1 stored thereon; and

one or more processors operably connected to the one or more memories.

11. A system according to claim 10, wherein the one or more processors are connected in parallel.

12. A system according to claim 10, for predicting the presence of improvised explosive devices (IEDs) in an external environment, made by method of:

modifying a plurality of generic template nodes of claim 1 to develop a model for,

determining the location of the external environment;

classifying the location based on predetermined location types to provide location type;

receiving historical data on previous actual detection of IEDs in the location and performing an age analysis of the historical data;

performing a weight risk analysis based on age of the historical data and location type;

detecting presence of IEDs in response to raw detection data received via one or more sensors;

calculating Positive Predictive Value (PPV) and Negative Predictive Value (NPV) for each detected IED;

calculating a confidence value for each detected IED based on PPV verses NPV;

weighting the confidence value of each detected IED based on location type and age analysis of the location to provide a weighted confidence value;

performing a cut-off value for each weighted confidence value to provide reportable detections of IEDs, and

outputting the reportable detections of IEDs.

13. A system according to claim 10, for predicting the presence of improvised explosive devices (IEDs) in an external environment, adapted to perform the method comprising the steps of:

modifying a plurality of generic template nodes of claim 1 to develop a model to detect IEDs;

using the model to obtain history data for a selected external environment and raw IED detection data obtained from the selected external environment;

combining the history data and raw detection data;

generating cluster data and clustered detection data;

performing PPV and NPV analysis of the clustered detection data to obtain confidence detection data;

calculating combined confidence data based on a combination of clustered detection data, confidence detection data, and cluster data to provide detection count data and detection combined confidence data, with cluster data remaining unchanged;

feeding detection count data and detection combined confidence data to a recurrent neural network to provide detection result data for each cluster;

generating polygon data from the detection result data for each cluster; and

outputting the polygon data to a display system.

14. A system according to claim 10, for predicting the presence of improvised explosive devices (IEDs) in an external environment, adapted to perform the method comprising the steps of:

modifying a plurality of generic template nodes of claim 1 to develop a model for,

determining the location of the external environment,

classifying the location based on predetermined location types to provide location_type, and

receiving historical data on previous actual detection of IEDs in the location and performing an age analysis of the historical data;

a preprocessing layer for,

performing a weight risk analysis based on age of the historical data and location_type, and

detecting presence of IEDs in response to raw detection data received via one or more sensors;

a cognition layer having a processor associated therewith and having memory with instructions therein for,

calculating Positive Predictive Value (PPV) and Negative Predictive Value (NPV) for each detected IED,

calculating a confidence value for each detected IED based on PPV verses NPV;

weighting the confidence value of each detected IED based on location_type and age analysis of the location to provide a weighted confidence value, and

applying a cut-off value for each weighted confidence value to provide reportable detections of IEDs; and

an output layer having a processor associated therewith and having memory with instructions therein for outputting the reportable detections of IEDs.

15. A method of providing the building blocks of a cyber security comprising:

modifying a plurality of generic template nodes of claim 1 to provide,

a file access node,

a normalization node,

an event clustering node, and

an cyber RNN node.

16. The method of claim 15, wherein the file access node includes an Execution Trigger inherited from a generic node template.

17. The method of claim 15, wherein the normalization node includes an Execution Trigger inherited from a generic node template.

18. The method of claim 15, wherein the event clustering node includes an Execution Trigger inherited from a generic node template.

19. The method of claim 13, wherein the cyber RNN node includes an Execution Trigger inherited from a generic node template.

20. A method of providing the building blocks of a predicting the presence of improvised explosive devices (IEDs) comprising:

modifying a plurality of generic template nodes of claim 1 to provide,

a History Node node,

a Location Node,

a Clustering Node,

a Probability Node,

a Probability Combiner Node, and

a Neural Network Node.

21. The method of claim 20, wherein the Probability Node is a Probability from Accuracy Node.

22. A method of providing the building blocks of a predicting the presence of improvised explosive devices (IEDs) comprising:

modifying a plurality of generic template nodes of claim 1 to provide,

a History Node node,

a Location Node,

a Clustering Node,

a Probability from Accuracy Node,

a Probability Combiner Node,

a Neural Network Node,

a Polygon Generator Node, and

a GMap Display Node.