Metadata Tag Scoring Using ML and Weighted Knowledge Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining metadata tag scores are manual, labor-intensive, inflexible, and lack scalability, necessitating time-consuming updates for new data, tags, and features.
Innovation Solution
An automated process using machine learning models and weighted knowledge graphs to generate metadata tag scores by analyzing domain-specific data, extracting features and relationships, and assigning weights to compute scores for data instances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual methods are used to determine metadata tag scores, then expertise and judgment can be applied, but the process becomes labor-intensive and time-consuming
Solution Approach 1:
The patent replaces manual mechanical processes with an automated computational system. A machine learning model processes domain-specific data to automatically generate metadata tag scores, eliminating the need for manual expert analysis while maintaining scoring accuracy through algorithmic evaluation of multiple data features and relationships.
Solution Approach 2:
The system enables self-service by automatically determining metadata tag scores without requiring human intervention. The automated process retrieves domain-specific data, processes it through the machine learning model, and generates tag scores independently, allowing the system to serve itself rather than relying on external expert resources.
2Reliability
If manual updates are performed for new data, tags, and features, then control and accuracy can be maintained, but the process lacks scalability and flexibility
Solution Approach 1:
The system implements dynamics by automatically adapting to new data, tags, and features without requiring manual reconfiguration. The machine learning model dynamically processes incoming domain-specific data and adjusts metadata tag scores based on learned relationships, enabling the system to evolve with changing data requirements while maintaining reliable control through consistent algorithmic application.
Solution Approach 2:
The automated system achieves universality by handling multiple functions within a single process: it processes various types of domain-specific data, generates metadata tag scores for different tags, and adapts to new features automatically. This multi-functional approach replaces multiple manual processes with a single scalable system that can handle diverse metadata tagging requirements.
3Productivity
If automated machine learning models are used, then scalability and efficiency are improved, but system complexity increases
Solution Approach 1:
The patent uses an automated computing system as an intermediary between domain-specific data and metadata tag scores. This intermediary process automatically retrieves data, applies machine learning algorithms, and generates scores, simplifying the overall system architecture by consolidating multiple manual steps into a single automated pipeline that improves productivity without requiring complex human coordination.
Data Source
AI summary
Systems and methods are provided for automated metadata tag score determination that leverages machine learning (ML) models and weighted knowledge graphs to obtain and assign metadata tag scores to instances of underlying data. Examples include generating a domain-specific knowledge graph related to a particular domain. The domain-specific knowledge graph comprising a plurality of domain-specific features connected via a plurality of domain-specific relationships. Responsive to receiving an input tag, examples extract domain-specific features of the plurality of domain-specific features associated with the input tag and a subset of domain-specific relationships of the plurality of domain-specific relationships corresponding to the subset of domain-specific features. The examples then determine metadata tag score corresponding to the input tag for items of the particular domain based on the subset of domain-specific features and the subset of domain-specific relationships and update metadata for each item to include the determined metadata tag scores.