Predictive analytic method and apparatus

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.

1 - 2 . (canceled) 
     
     
         3 . A computer system for providing current project status and predicting future project status, the tool comprising:
 a framework stored on a computer memory;   a computer processor that associates data with one or more classes or subclasses of words that are networked grammatically and cognitively, wherein the processor generates a status matrix providing a multi-relational representation of the current and future project status; and   a display configured to display the status matrix including future project status based on the project framework.   
     
     
         4 . The computer system of  claim 3 , wherein the status matrix includes a plurality of interdiction points, confidence levels, a current status and a position on the project timeline. 
     
     
         5 . The computer system of  claim 4 , wherein the framework is broken down into multiple classes including at least lexicon, portfolios, project templates, activities and roles. 
     
     
         6 . The computer system of  claim 3 , further comprising a neural network wherein data input in to the computer memory is subject to weight and confidence cutoff levels. 
     
     
         7 . The computer system of  claim 6 , wherein the neural network is a recurrent neural network. 
     
     
         8 . The computer system of  claim 6 , wherein the neural network is an echo state network. 
     
     
         9 . A computer based mapping engine, comprising:
 a data receipt module which classifies incoming data based on source of the data wherein a mapping algorithm is selected to prepare the data for mapping;   a routing module which routes the data into types based upon classified confidence levels;   a parsing module which uses statistical natural language processing to parse and tag the data types;   a mapping module which inputs the parsed data types to at least one recurrent neural network in order to test the data types against a project ontology framework and which outputs a formatted data type;   a state generation module for generating an echo or state output for each formatted data type; and   a states module which maintains the threshold values of the project ontology framework based on whether the echo or state output exceeds a threshold.   
     
     
         10 . The mapping engine of  claim 9 , wherein the data receipt module classifies data and provides a knowledge base about a subset of words in the vocabulary of a natural language. 
     
     
         11 . The mapping engine of  claim 10 , wherein received data classification includes the WordNet® database and entity and specialized lexicons mapped to the WordNet® database. 
     
     
         12 . The mapping engine of  claim 9 , wherein the received data classification includes lexicon networks which are networks/matrices of words that are networked grammatically and cognitively. 
     
     
         13 . The mapping engine of  claim 12 , wherein lexicon networks are constructed at a portfolio level, per project template, activity and role. 
     
     
         14 . The mapping engine of  claim 10 , wherein the class includes subclasses of sponsor, projects, roles, project template and lexicons not clearly associated with a project or an activity, related portfolios and other metadata. 
     
     
         15 . The mapping engine of  claim 14 , wherein the subclasses of the project template include at least a plurality of sponsor organizations, lexicons and roles that are not clearly associated with an activity class, and other meta data. 
     
     
         16 . The mapping engine of  claim 15 , wherein the activity class of the project ontology is comprised of at least one of verbs, nouns, adjectives, adverbs, roles, time sequence of events or actions, related activities and other meta data. 
     
     
         17 . The mapping engine of  claim 16 , wherein the role class of the project ontology is comprised of the subclasses of skills, functions, command relationship(s), tools, named individuals acting in this role, related roles and other meta data. 
     
     
         18 . The mapping engine of  claim 9 , further comprising: a base project ontology framework that is a complete project ontology framework structure without any mapping of data. 
     
     
         19 . The mapping engine of  claim 18 , wherein a class of the base project ontology framework can change depending on changes to the data and to a measured activity. 
     
     
         20 . The mapping engine of  claim 19 , wherein real time instances of the base project ontology framework are created by combining a learning algorithm with the base project ontology framework. 
     
     
         21 . The mapping engine of  claim 20 , wherein as data is input into the mapping engine, the learning algorithm is constantly generating echoes of the base project ontology framework. 
     
     
         22 . The mapping engine of  claim 9 , wherein the one or more processors are configured to perform functions including data receipt, routing, parsing and formatting, mapping, echo generation and echo maintenance. 
     
     
         23 . A computer system for threat prediction, comprising:
 a project ontology framework stored on a computer memory;   one or more computer processors configured to associate a given piece of data with a class or subclass within the project ontology, and to generate a status matrix providing a multi-relational representation of the current and future project status, the status matrix identifying at least one interdiction point representing a time when the threat has a weakness or an exposure point; and   a display configured to display the status matrix.   
     
     
         24 . A computer operated method for providing current project status and predicting future project status, the method comprising the steps of :
 storing a project framework in an electronic memory;   associating through a processor data with one or more classes or subclasses of words that are networked grammatically and cognitively;   generating through a processor a status matrix providing a multi-relational representation of the current project status and the future project status; and   displaying through an electronic display the status matrix including the future project status based on the stored project framework.   
     
     
         25 . A computerized mapping method, comprising the steps of:
 classifying inputted data in a data receipt module data based on source of the data;   selecting a mapping algorithm to prepare the classified data for mapping;   routing the data into types based upon classified confidence levels;   parsing the typed data using statistical natural language processing to parse and tag the data types;   mapping the parsed data types to at least one recurrent neural network in order to test the data types against a project ontology framework and output a formatted data type;   generating an echo or state output for each formatted data type; and   maintaining the threshold values of the project ontology framework based on whether the echo or state output exceeds a threshold.   
     
     
         26 . The method of  claim 25 , wherein the classifying data step further includes providing a knowledge base about a subset of words in the vocabulary of a natural language. 
     
     
         27 . The method of  claim 26 , further comprising the step of receiving data classifications including a WordNet® database, entity and specialized lexicons mapped to the WordNet® database. 
     
     
         28 . The method of  claim 27 , wherein the received data classification includes lexicon networks which are networks/matrices of words that are networked grammatically and cognitively. 
     
     
         29 . The method of  claim 28 , wherein lexicon networks are constructed at a portfolio level, per project template, activity and role. 
     
     
         30 . The method of  claim 29 , wherein the classified data include subclasses of sponsor, projects, roles and lexicons not clearly associated with a project or an activity, related portfolios and other meta data. 
     
     
         31 . The method of  claim 30 , wherein the subclasses of the project template include at least a plurality of sponsor organizations, lexicons and roles that are not clearly associated with an activity, and other meta data. 
     
     
         32 . The method of  claim 29 , wherein the activity class of the project ontology is comprised of at least one of verbs, nouns, adjectives, adverbs, roles, time sequence of events or actions, related activities and other meta data. 
     
     
         33 . The method of  claim 32 , wherein the role class of the project ontology is comprised of subclasses of skills, functions, command relationship(s), tools, named individuals acting in this role, related roles and other meta data. 
     
     
         34 . The method of  claim 25 , further comprising the step of generating a base project ontology framework that is a complete project ontology framework structure without any mapping of data. 
     
     
         35 . The method of  claim 34 , wherein a class of the base project ontology framework can change depending on changes to the data and to a measured activity. 
     
     
         36 . The method of  claim 35 , further comprising the step of combining a learning algorithm with the base project ontology framework wherein real time instances of the base project ontology framework are created. 
     
     
         37 . The method of  claim 36 , further comprising the step of inputting data in order that the learning algorithm is constantly generating echoes of the base project ontology framework.