Parallel object-oriented decision tree system

Abstract

A data mining decision tree system that uncovers patterns, associations, anomalies, and other statistically significant structures in data by reading and displaying data files, extracting relevant features for each of the objects, and using a method of recognizing patterns among the objects based upon object features through a decision tree that reads the data, sorts the data if necessary, determines the best manner to split the data into subsets according to some criterion, and splits the data.

1 . A decision tree based data mining system for processing data that uncovers statistically significant structures in the data by recognizing patterns among objects in the data based upon features of the data; comprising: 
 a multiplicity of processors,    an object oriented pattern recognition algorithms module for pattern recognition by recognizing patterns among objects in the data based upon features of the data, comprising:    a multiplicity of data files including features in the data,    a decision tree system including    an object oriented module operatively connected to said processors and connected to said data files to read said data and partition said data files among said multiplicity of processors,    an object oriented module operatively connected to said processors to parallel sort said data using said multiplicity of processors, if sorting is necessary,    an object oriented module operatively connected to said processors to determine the best manner to split said data according to some criterion, and    an object oriented module operatively connected to said processors to split said data, and    a data mining system, having    a storage module, and    an object oriented linking module for linking said decision tree system and said storage module.    
     
     
         2 . The decision tree system of  claim 1  wherein said object oriented module to determine the best manner to split said data is based on tests on single attributes of said data.  
     
     
         3 . The decision tree system of  claim 1  wherein said object oriented module to determine the best manner to split said data is based on a OC1 algorithm.  
     
     
         4 . The decision tree system of  claim 1  wherein said object oriented module to determine the best manner to split said data is based on a CART-LC algorithm.  
     
     
         5 . The decision tree system of  claim 1  wherein said object oriented module to determine the manner to best split said data is based on an evolutionary algorithm.  
     
     
         6 . The decision tree system of  claim 1  wherein said criterion is the Gini index.  
     
     
         7 . The decision tree system of  claim 1  wherein said criterion is the information gain.  
     
     
         8 . The decision tree system of  claim 1  wherein said criterion is the information ratio.  
     
     
         9 . (canceled)  
     
     
         10 . A decision tree based data mining system for processing data that uncovers statistically significant structures in the data by recognizing patterns among objects in the data based upon features of the data; comprising: 
 a multiplicity of processors,    an object oriented pattern recognition algorithms module for pattern recognition by recognizing patterns among objects in the data based upon features of the data, comprising:    a multiplicity of data files including features in the data,    a decision tree system including    a parallel object oriented module operatively connected to said processors and connected to said data files to read said data and partition said data files among said multiplicity of processors, said data containing data items with features,    a parallel object oriented module operatively connected to said processors to parallel sort said data using said multiplicity of processors, if sorting is necessary,    a parallel object oriented module operatively connected to said processors to determine the best manner to split said data into subsets according to some criterion,    a parallel object oriented module operatively connected to said processors to split said data, and    a data mining system, having    a storage module to store the features for each data item,    a parallel object oriented linking module for linking said decision tree system and said storage module.    
     
     
         11 . The decision tree system of  claim 10  wherein said parallel object oriented module to determine the best manner to split said data is based on tests on single attributes of said data.  
     
     
         12 . The decision tree system of  claim 10  wherein said parallel object oriented module to determine the best manner to split said data is based on a OC1 algorithm.  
     
     
         13 . The decision tree system of  claim 10  wherein said parallel object oriented module to determine the best manner to split said data is based on a CART-LC algorithm.  
     
     
         14 . The decision tree system of  claim 10  wherein said parallel object oriented module to determine the manner to best split said data is based on an evolutionary algorithm.  
     
     
         15 . The decision tree system of  claim 10  wherein said criterion is the Gini index.  
     
     
         16 . The decision tree system of  claim 10  wherein said criterion is the information gain.  
     
     
         17 . The decision tree system of  claim 10  wherein said criterion is the information ratio.  
     
     
         18 . (canceled)  
     
     
         19 . A decision tree based data mining method for processing data utilizing a multiplicity of processors by uncovering statistically significant structures in the data by recognizing patterns among objects in the data based upon features of the data, comprising the steps of: 
 providing data files containing objects having relevant features,    recognizing patterns among said objects based upon said relevant features,    creating a decision tree system,    using said multiplicity of processors for reading said data from said data files using an object oriented module,    using said multiplicity of processors for partitioning said data files among said multiplicity of processors,    using said multiplicity of processors for parallel sorting said data using an object oriented module and said multiplicity of processors if sorting is necessary,    determining the best manner to split said data into subsets according to some criterion using an object oriented module, and    splitting said data using an object oriented module.    
     
     
         20 . The decision tree method of  claim 19  wherein said parallel object oriented module to determine the best manner to split said data is based on tests on single attributes of said data.  
     
     
         21 . The decision tree method of  claim 19  wherein said parallel object oriented module to determine the best manner to split said data is based on a OC1 algorithm.  
     
     
         22 . The decision tree method of  claim 19  wherein said parallel object oriented module to determine the best manner to split said data is based on a CART-LC algorithm.  
     
     
         23 . The decision tree method of  claim 19  wherein said parallel object oriented module to determine the manner to best split said data is based on an evolutionary algorithm.  
     
     
         24 . The decision tree method of  claim 19  wherein said criterion is the Gini index.  
     
     
         25 . The decision tree method of  claim 19  wherein said criterion is the information gain.  
     
     
         26 . The decision tree method of  claim 19  wherein said criterion is the information ratio.  
     
     
         27 . (canceled)  
     
     
         28 . A decision tree based data mining method for processing data utilizing a multiplicity of processors by uncovering statistically significant structures in the data by recognizing patterns among objects in the data based upon features of the data, comprising the steps of: 
 using said multiplicity of processor for reading and displaying data files, said data files containing objects having at least one feature,    partitioning said data files among said multiplicity of processors,    identifying said objects in said data files,    extracting at least one feature for each of said objects    recognizing patterns among said objects based upon said features, and    creating a decision tree, said decision tree including    using said multiplicity of processor for reading said data,    using said multiplicity of processor for parallel sorting said data using said multiplicity of processors, if sorting is necessary,    determining the best manner to split said data into subsets according to some criterion, and    splitting said data.    
     
     
         29 . The decision tree method of  claim 28  wherein said step of determining the best manner to split said data is based on tests on single attributes of said data.  
     
     
         30 . The decision tree method of  claim 28  wherein said step of determining the best manner to split said data is based on a OC1 algorithm.  
     
     
         31 . The decision tree method of  claim 28  wherein said step of determining the best manner to split said data is based on a CART-LC algorithm.  
     
     
         32 . The decision tree method of  claim 28  wherein said step of determining the manner to best split said data is based on an evolutionary algorithm.  
     
     
         33 . The decision tree method of  claim 28  wherein said criterion is the Gini index.  
     
     
         34 . The decision tree method of  claim 28  wherein said criterion is the information gain.  
     
     
         35 . The decision tree method of  claim 28  wherein said criterion is the information ratio.  
     
     
         36 . (canceled)