Dynamic Ontology Classification for Private Companies
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current industry classification systems, such as NAICS and GICS, are static and unable to evolve with time, lacking the ability to classify companies to a degree of belonging to an industry, are not applicable to private companies, and require significant human resources for manual data curation, leading to inefficiencies and inaccuracies.
Innovation Solution
A data classification system using an ontology manager that generates models to predict classifications based on natural language descriptions of entities, allowing for dynamic updates and new classifications, reducing the need for human intervention and increasing scalability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual classification by analysts is used, then classification accuracy is improved, but productivity deteriorates due to difficulty in scaling to thousands of companies
Solution Approach 1:
The patent replaces the mechanical manual classification system with an automated machine learning-based classification system. The system uses trained models to automatically classify companies into industries, eliminating the need for manual analyst intervention while maintaining consistent application of classification criteria across all companies.
Solution Approach 2:
The classification system is designed to be self-service, automatically processing company data and generating classifications without requiring human analysts. The system handles data ingestion, model inference, and classification output autonomously, enabling scalable processing of thousands of companies simultaneously.
2Stability of the object's composition
If static classification systems like NAICS and GICS are used, then classification consistency is improved, but adaptability deteriorates as systems cannot evolve with emerging industries
Solution Approach 1:
The patent implements a dynamic classification system where the ontology and classification models can evolve over time. The system periodically retrains models with new data, incorporates emerging industry classifications, and adapts to changing business landscapes while maintaining consistent classification methodologies through standardized processing procedures.
Solution Approach 2:
The system performs preliminary actions by continuously monitoring emerging companies and industries, preparing updated classification categories and model training data in advance. This allows the system to be ready to classify new industry types as they emerge, rather than waiting for manual updates to static systems.
3Reliability
If detailed manual curation is performed, then classification quality is improved, but loss of time increases due to extensive human resource requirements
Solution Approach 1:
The system performs preliminary actions by pre-training classification models on extensive datasets of company information and industry classifications. This preliminary training enables the models to quickly and accurately classify new companies without requiring time-consuming manual analysis, while maintaining high classification quality through the use of sophisticated algorithms and comprehensive training data.
Data Source
AI summary
A method, apparatus, system, and computer program product for method for dynamically managing an ontology for classifying data is provided. The ontology is generated from the classifications of a plurality of entities. Models are generated that predict classifications according to the ontology and natural language descriptions of the entities. Unclassified entities are modelled by according to the models to identify at least one classification within the ontology. Responsive to identifying a plurality of probable classifications within the ontology, a new classification is generated based on the plurality of probable classifications, an updated ontology is generated that includes the new classification, and the unclassified entity is classified according to the new classification.