Neural Network Business Name Categorization via Dictionary Reducer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current energy management systems face challenges in efficiently categorizing businesses for effective energy usage management, especially when business types are unknown, requiring extensive computing resources and manual validation, which is labor-intensive and prone to errors.
Innovation Solution
An energy management system utilizing a neural network and dictionary reducer to calculate weights for single-word terms from training data business names, predicting business categories with high confidence, and eliminating unessential terms for accurate categorization, thereby reducing the need for extensive computing resources and manual validation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional business name categorization methods are used, then categorization accuracy can be maintained, but extensive computing resources and manual validation are required
Solution Approach 1:
The patent extracts and eliminates unessential single-word terms from business names before processing. The dictionary reducer identifies and removes stop words and non-descriptive terms, keeping only the essential words that contribute to accurate categorization. This extraction process reduces the input data size and complexity while maintaining categorization accuracy.
Solution Approach 2:
The patent segments business names into individual single-word terms and processes them independently through the neural network. Each word is assigned a weight indicating its likelihood of correlating with specific business categories. This segmentation allows the system to handle complex business names by breaking them down into manageable, analyzable units.
2Measurement precision
If traditional business name categorization methods are used, then comprehensive analysis can be performed, but manual validation is labor-intensive and prone to errors
Solution Approach 1:
The system performs self-validation through the neural network's predictive model, which automatically determines business categories based on weighted word correlations. The model iteratively processes business names and assigns categories without requiring manual validation, thereby eliminating labor-intensive human review while maintaining high accuracy through the trained neural network weights.
3Measurement precision
If all single-word terms from business names are processed, then categorization completeness is achieved, but excessive memory and processing power are required
Solution Approach 1:
The dictionary reducer extracts and removes unessential single-word terms from business names before neural network processing. By eliminating stop words, common articles, and non-descriptive terms, the system significantly reduces the volume of data that requires computational processing while retaining all words that are essential for accurate categorization.
Solution Approach 2:
The patent applies partial processing by focusing computational resources only on the essential words identified by the dictionary reducer, rather than processing every single word in business names. This selective approach processes only the necessary subset of terms that contribute to categorization accuracy.
Data Source
AI summary
An energy management system includes a neural network, a predictive model, and a dictionary reducer. The network iteratively calculates weights, resulting in a final set, for each of a plurality of single-word terms taken from training data business names, where each of the weights is indicative of a likelihood of correlating one of a plurality of business categories. The predictive employs sets of the weights to predict a first corresponding one of the plurality of business categories for each of the training data business names until employment of the final set accurately predicts a correct business category for the each of the training data business names, and subsequently employs the final set of the weights to predict a second corresponding one of the plurality of business categories for each of a plurality of operational business names. The dictionary reducer eliminates unessential terms taken to determine the plurality of single-word terms.