Predictive analytic method and apparatus

• US 7,822,747 B2
• Filed: 01/12/2006
• Issued: 10/26/2010
• Est. Priority Date: 01/12/2005
• Status: Expired due to Fees

• Current Assignee: Métier Ltd.
• Original Assignee: Métier Ltd.
• Inventors: Walton, Zachary, Gipson, Brian, Clark, Douglas, Pieslak, Brian
• Primary Examiner(s): Jalil; Neveen Abel
• Assistant Examiner(s): Hoang; Son T
• Application Number:
  US11/330,337
• Publication Number:
  US 20060184483A1
• Time in Patent Office: 1,748 Days
• Field of Search: None
• US Class Current: 707/736
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Abstract

A computerized project management analytical system and method that develops and manages an ontology that links objects and is capable of being mined. The ontology is comprised of a project ontology framework, a matching engine and a project status matrix that illustrates a multi-relational view of the project status, of confidence levels, or interdiction points and/or positions on project timelines.

Claims

1. A computerized assessment method for providing current and future project status, the method comprising the steps of:

generating, through a computer processor, a project ontology framework (POF) having a plurality of classes and subclasses, where each of said classes and subclasses are linked to at least one other class or subclass;

receiving data into a memory connected to said computer processor;

mapping data into the POF, comprising the steps of;

classifying said data in a computer processor based on a source of said data;

routing the data into a memory based on its classification to at least one of a parsing function, a mapping function, and into echoes comprising data mapped into the POF; and

generating, through a computer processor, a status matrix on an output device connected to the computer from the data mapped into the project ontology framework by comparing the mapped data to data in a predetermined base POF, generating a match score, and modifying an operational POF by incorporating the mapped data if a match exceeds a certain threshold, the status matrix providing the current and future project status information including information about points of weakness,

wherein the classification step includes said computer processor classifying the data as a particular predetermined message type including a plurality of trusted parsed directed, trusted parsed processed, assigned confidence, no assigned confidence and fragment, and

wherein the trusted parsed directed data is data that is already parsed and mapped to the POF, the trusted parsed processed data is data that is already parsed, and the assigned confidence data, the no assigned confidence data and the fragment data are data that has not been parsed or mapped, and

wherein the trusted parsed directed data is routed into echoes, bypassing the parsing function and the mapping function, the trusted parsed processed directed data is routed to the mapping function, bypassing the parsing function, and the assigned confidence data, the no assigned confidence data and the fragment data are routed to the parsing function.

2. The method according to claim 1, further comprising parsing said data using natural language processing.

3. The method according to claim 2, wherein said parsing step comprises parsing by tagging words of the data as to a part of speech, definition and time.

4. The method according to claim 3, wherein said parsing step uses a tree traversal parsing to tag the part of speech.

5. The method according to claim 3, further comprising evaluating and extracting the tagged words for mapping.

6. The method according to claim 5, wherein data that includes the tagged words is formatted into a format consistent with at least one of the portfolio, the lexicon, the project template, the activity and the role classes or subclasses.

7. The method according to claim 6, further comprising generating an echo for each piece of formatted data encompassing the classes and subclasses of the project ontology framework.

8. The method according to claim 1, wherein said method is carried out to predict threat activities.

9. A computer based assessment method for providing current and future project status, the method comprising:

generating a project ontology framework having a plurality of classes and subclasses, where each of said classes and subclasses are linked to at least one other class or subclass;

receiving intelligence data;

classifying said data in a computer processor based on a source of said data into a particular predetermined message type including a plurality of trusted parsed directed, trusted parsed processed, assigned confidence, no assigned confidence and fragment message type;

routing the data based on said classification to at least one of the parsing function, mapping function and the project ontology framework;

evaluating the data for extraction;

extracting and formatting the evaluated data for the classes and subclasses of the project ontology framework for mapping;

generating echoes comprising data mapped into of the project ontology framework using the formatted data and a learning algorithm that tests the formatted data against a base project ontology frame work and creates echoes based on matches; and

generating a status matrix on an output device which provides the current and future project status information based on one of the echoes of the project ontology framework,

wherein the trusted parsed directed data is data that is already parsed and mapped to the project ontology framework, the trusted parsed processed data is data that is already parsed, and the assigned confidence data, the no assigned confidence data and the fragment data are data that has not been parsed or mapped, and

wherein the trusted parsed directed data is routed to the project ontology framework, bypassing the parsing function and the mapping function, the trusted parsed processed directed data is routed to the mapping function bypassing the parsing function, and the assigned confidence data, the no assigned confidence data and the fragment data are routed to the parsing function.

10. The method according to claim 9, wherein the data is formatted into a format consistent with at least one of the portfolio, the lexicon, the project template, the activity, and the role classes or subclasses.

11. The method according to claim 9, wherein said generating echoes step comprises generating a candidate, working, or operational project ontology framework echoes based on weight and confidence cutoffs.

12. The method according to claim 11, wherein the operational project ontology framework is the ontology with the highest confidence level.

13. The method according to claim 9, wherein said method is carried out to predict threat activities.

14. An assessment system comprising:

a computer processor coupled to a project assessment unit, the project assessment unit having;

a project ontology framework having a plurality of classes and subclasses, where each of said classes and subclasses are linked to at least one other class or subclass;

a receiver for receiving intelligence data;

a classifier of said intelligence data based on a source of said data into a particular predetermined message type;

a router for routing said data based on said classification to at least one of a parsing function, mapping function and the project ontology framework;

an echo generator that generates echoes comprising data mapped into the project ontology framework by matching the intelligence data to data in a base project ontology framework;

a promoter that modifies an operational project ontology framework if the echoes match the base project ontology framework to a greater degree than the operational project ontology framework; and

a matrix generator for generating a status matrix which provides the current and future project status information based on one of the echoes of the project ontology framework,

wherein the predetermined message type is one of trusted parsed directed data comprising data that is alread arsed and mapped to the project ontology framework, trusted parsed processed data comprising data that is already parsed, and assigned confidence data, no assigned confidence data and fragment data comprising data that has not been parsed or mapped, and

wherein the trusted parsed directed data is routed to the project ontology framework, bypassing the parsing function and the mapping function, the trusted parsed processed directed data is routed to the mapping function, bypassing the parsing function, and the assigned confidence data, the no assigned confidence data, and the fragment data are routed to the parsing function.

15. The system according to claim 14, wherein the data is formatted into a format consistent with at least one of the portfolio, the lexicon, the project template, the activity and the role classes or subclasses.

16. The system accordingly to claim 14, wherein said echo generator generates a candidate, working, or operational project ontology framework echoes based on weight and confidence cutoffs.

17. The method according to claim 16, wherein the operational project ontology framework is the ontology with the highest confidence level.

18. The method according to claim 14, wherein said system is used to predict threat activities.

19. A computer program, stored on a computing device, for providing current and future project status, said program comprising:

a project ontology framework having a plurality of classes and subclasses, where each of said classes and subclasses are linked to at least one other class or subclass;

a receiver module, executed by the computing device, that receives data;

a classification module, executed by the computing device, that classifies said data based on a source of said data;

a routing module, executed by the computing device, that routes the data based on its classification to at least one of a parsing function, a mapping function, and into echoes;

a state generation module, executed by the computing device, that generates echoes of data mapped into the project ontology framework based on matches between the data and a base project ontology framework;

an echo maintenance module, executed by the computing device, that modifies an operational project ontology framework if the generated echoes match the base project ontology framework to a greater degree than the operational project ontology framework; and

a matrix generation module, executed by the computing device, that generates a status matrix which provides the current and future project status information including information about points of weakness based on one of the echoes of the project ontology framework,

wherein the classification module classifies data into predetermined message types including trusted parsed directed data comprising data that is already parsed and mapped to the project ontology framework trusted parsed processed data corn rising data that is alread parsed, assigned confidence data, no assigned confidence data, and fragment data, and

wherein the trusted parsed directed data is routed to into echoes, bypassing the parsing function and the mapping function, the trusted parsed processed directed data is routed to the mapping function, bypassing the parsing function, and the assigned confidence data, the no assigned confidence data and the fragment data are routed to the parsing function.