Hierarchical Multi-Faceted Classification for Media Tagging

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing digital media classification systems are inadequate for commercial use as they rely on user-initiated tagging and multi-faceted taxonomies, which do not provide a complete decomposition of the semantic space, leading to insufficient categorization and tagging accuracy.

Innovation Solution

A hierarchical multi-faceted classification structure is constructed using a multi-relational reference ontology that accounts for various relationships, allowing for the categorization of media artifacts into visual categories and refining labels based on faceted ontology relationships, enabling precise and reliable automated tagging.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If user-initiated content tagging is used, then ease of operation is improved, but measurement precision deteriorates

Engineering Contradiction:

Improveease of taggingVSAvoidtagging accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs automated tagging without requiring user initiation. The computer executes algorithms that automatically analyze content and assign tags, making the system self-sufficient for the tagging function while eliminating the need for manual user input.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual user tagging (mechanical human action) with automated computational algorithms. The system uses computer-based image analysis and natural language processing to substitute human tagging operations with machine-based automated classification.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If multi-faceted taxonomies are used, then adaptability is improved, but manufacturing precision deteriorates

Engineering Contradiction:

Improvecategorization flexibilityVSAvoidclassification precision

Core Design Contradiction:

Adaptability or versatilityVSManufacturing precision

Solution Approach 1:

The patent segments the classification task into multiple independent facets or dimensions. Each facet represents a specific aspect of content classification, allowing the system to handle complex categorization by breaking it down into manageable, specialized components that can be processed independently and then integrated.

Inventive Principle:

Principle #1Segmentation

3Productivity

If automated classification systems are implemented, then productivity is improved, but measurement precision deteriorates

Engineering Contradiction:

Improvecataloging speedVSAvoidclassification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent merges multiple classification algorithms and data sources into a unified system. By combining different approaches (e.g., image analysis, text processing, metadata extraction) into an integrated automated classification system, the patent achieves both high productivity through automation and improved precision through the synergistic effect of multiple methods.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS9710760B2Multi-facet classification scheme for cataloging of information artifacts

Publication Date: 2017.07.18 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A system and method for constructing a hierarchical multi-faceted classification structure includes organizing a plurality of visual categories into a multi-relational reference ontology that accounts for a plurality of different types of relationships. Media artifacts are categorized into the plurality of visual categories. The categories of artifacts are refined based on faceted ontology relationships or constraints from the multi-relational reference ontology. The multi-relational reference ontology and the one or more media artifacts with relationships are stored as the hierarchical multi-faceted classification structure in computer readable memory storage.