Machine-Learned Data Enrichment for Diversity Entity Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems in corporate environments, including cloud-based systems, face challenges in efficiently managing and connecting diverse entities, such as minority-owned businesses, due to system compatibility issues, which hinders meeting diversity goals and unlocking business opportunities.
Innovation Solution
A data enrichment platform that uses machine-learned models to aggregate diversity data from raw data providers like Dun & Bradstreet, creating a summary table with custom fields that align with organizational diversity goals, enabling efficient access and management of diverse entities through front-end tools.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional data management systems are used to manage entity data, then system compatibility is maintained, but efficiency in finding and managing diverse entities is poor
Solution Approach 1:
The patent introduces an intermediary layer between raw data providers and the summary table. This intermediary processes raw entity data through machine learning models to automatically derive and populate custom fields in the summary table, enabling efficient diversity entity management without direct system complexity
Solution Approach 2:
The system performs preliminary data processing and enrichment before data is needed for analysis. By pre-processing raw data to create enriched summary tables with derived custom fields, the system prepares data in advance for efficient querying and analysis of diverse entities
2Loss of time
If manual data processing is used to create summary tables, then data accuracy can be ensured, but time consumption is excessive
Solution Approach 1:
The patent replaces manual mechanical data processing with automated machine learning models. These models automatically derive custom field values from raw data, eliminating time-consuming manual operations while maintaining data accuracy through algorithmic consistency and validation
Solution Approach 2:
The system enables self-service data enrichment where the machine learning models automatically process and enrich raw data without human intervention. The models derive custom fields autonomously, updating summary tables automatically, which reduces time loss while maintaining accuracy through automated validation
3Loss of information
If comprehensive diversity data is collected from multiple providers, then completeness of diversity information is improved, but system compatibility issues increase
Solution Approach 1:
The patent creates a universal summary table structure that can accommodate diversity data from multiple providers. The machine learning models process and normalize data from different sources into a common format, enabling the system to handle multiple data providers universally without compatibility issues
Solution Approach 2:
The system transforms raw data parameters from different providers into standardized custom field parameters. By changing the parameter format and structure through machine learning processing, the system maintains data completeness while ensuring compatibility across different data sources
Data Source
AI summary
A method of processing raw data as it is received from a data provider via an input channel is disclosed. Values are derived from the raw data as it is received from the data provider via the input channel. The derived values correspond to custom fields of a summary table. The summary table is configured to store a summary of the raw data. The custom fields correspond to data capable of improving an analysis of an entity by an analysis tool. The derived values are inserted into the custom fields of the summary table. Access to the summary table is provided as enriched data for use by the analysis tool to improve the analysis of the entity.