Hashtag Metadata Model for Sparse Content Categorization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods struggle to accurately categorize 'sparse-info' Internet content items, such as short sentences, images, and videos, due to the lack of textual information, which are essential for traditional categorization techniques.

Innovation Solution

A content item categorizer system builds a metadata model that maps hashtags to content categories using machine-learning techniques, leveraging information from previously categorized items to categorize sparse-info items based on their associated hashtags.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional categorization methods are used, then categorization accuracy is improved for content items with sufficient textual information, but sparse-info items cannot be accurately categorized due to lack of textual information

Engineering Contradiction:
Improvecategorization accuracyVSAvoidapplicability to sparse-info items
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent introduces hashtags as intermediary elements that bridge sparse-info items and content categories. Hashtags serve as metadata that carry categorical information, enabling items with minimal text to be categorized through their associated hashtags rather than relying solely on textual analysis

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent transitions from traditional single-dimension textual analysis to multi-dimensional categorization by incorporating hashtag metadata as an additional dimension. This allows the system to categorize items based on both their textual content and their hashtag associations, providing robust categorization even when text is sparse

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If more textual information is required for categorization, then categorization accuracy is improved, but the scope of categorizable items is reduced to exclude sparse-info items

Engineering Contradiction:
Improvecategorization accuracyVSAvoidnumber of categorizable items
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent creates a universal categorization framework that handles both rich-text items and sparse-info items through a unified approach. The system processes all content items through the same hashtag-based methodology, eliminating the need for separate handling procedures and enabling broad applicability across diverse content types

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Device complexity

If traditional categorization methods are applied to sparse-info items, then device complexity is minimized, but categorization reliability deteriorates due to insufficient information

Engineering Contradiction:
Improvecategorization system complexityVSAvoidcategorization reliability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent performs preliminary categorization work by building a comprehensive mapping between hashtags and content categories from previously categorized items. This pre-computed hashtag-to-category mapping serves as a ready-reference knowledge base that enables reliable categorization of sparse-info items without requiring complex real-time analysis

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9384259B2Categorizing hash tags
Publication Date: 2016.07.05 VERIZON PATENT & LICENSING INC
  • US9384259B2 patent drawing
  • US9384259B2 patent drawing
  • US9384259B2 patent drawing

AI summary

A content item categorizer system retrieves content items from Internet sources. If a retrieved content item includes sufficient information for traditional categorization methods, then the system assigns one or more categories to the content item using such traditional methods. The system creates a metadata model, based on information about traditionally-categorized content items, that maps at least hashtags from the content items to one or more content categories. When the system retrieves a sparse-info item that does not include sufficient information for traditional categorization, the system applies the metadata model to categorize the content item using at least hashtags in the sparse-info item. The metadata model may also include information indicating mappings between categories and coincidence of hashtags and additional content item attributes. Also, the metadata model may provide information for categorizing sparse-info items based on multiple hashtags in the sparse-info item metadata.