INTERPOLATIVE VERTICAL CATEGORIZATION MECHANISM FOR ENERGY MANAGEMENT

摘要

An energy management system includes a neural network, a predictive model, andadictionary reducer. The network iteratively calculates weights, resulting in afinal set,for each of a plurality of single-word terms taken from training data businessnames,where each of the weights is indicative of a likelihood of correlating one ofa plurality ofbusiness categories. The predictive employs sets of the weights to predict afirstcorresponding one of the plurality of business categories for each of thetraining databusiness names until employment of the final set accurately predicts a correctbusinesscategory for the each of the training data business names, and subsequentlyemploysthe final set of the weights to predict a second corresponding one of theplurality ofbusiness categories for each of a plurality of operational business names. Thedictionary reducer eliminates unessential terms taken to determine theplurality ofsingle-word terms.