Digital Photo Tagging via NLP Extraction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The increasing number of digital photographs stored on electronic devices poses challenges in organization and searchability, as existing technologies lack efficient methods for extracting and associating relevant information with images.

Innovation Solution

A method is implemented on electronic devices to detect digital photograph sharing events, receive and process text input related to the photographs using natural language processing, and store extracted information as metadata tags, allowing for improved search and organization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If the number of digital photographs stored on electronic devices increases, then the storage capacity is improved, but the organization and searchability of photographs deteriorates

Engineering Contradiction:
Improvenumber of digital photographsVSAvoidsearchability
Core Design Contradiction:
Quantity of substanceVSEase of operation

Solution Approach 1:

The system automatically extracts information from photographs and generates tags before the user needs to search, preparing the data structure in advance. This preliminary tagging action enables efficient searchability even as the number of photographs increases, resolving the contradiction between storage quantity and search ease.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary information extraction and processing system that acts between the stored photographs and the user search interface. This intermediary automatically processes image data, extracts relevant information, and creates searchable tags, thereby maintaining searchability without requiring direct user interaction with the raw image data.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If manual tagging of digital photographs is implemented, then the organization is improved, but the time and effort required increases

Engineering Contradiction:
ImproveorganizationVSAvoidtime for tagging
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system performs self-service by automatically extracting information from photographs and generating tags without requiring user intervention. The information extraction module autonomously processes images, identifies key features, and creates organizational tags, eliminating the time and effort that would otherwise be required for manual tagging while maintaining high organization quality.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical process of manual tagging with an automated information extraction system using optical character recognition and image processing technologies. This substitution eliminates the need for manual text entry and tag creation, significantly reducing the time investment required for photograph organization while maintaining or improving organization quality.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated information extraction is implemented, then the productivity is improved, but the device complexity increases

Engineering Contradiction:
Improvetagging efficiencyVSAvoidprocessing system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The information extraction module is designed with multi-functionality, serving multiple purposes: extracting text from images, identifying key objects, generating tags, and organizing photographs. By consolidating these functions into a single versatile module, the system achieves high tagging efficiency without proportionally increasing complexity, as the same core capabilities serve multiple organizational needs.

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

Data Source

PatentEP3144830B1Electronic device and method of tagging digital photograph information
Publication Date: 2024.05.08 MALIKIE INNOVATIONS LTD
  • EP3144830B1 patent drawingFigure 1
  • EP3144830B1 patent drawingFigure 2
  • EP3144830B1 patent drawingFigure 3

AI summary

A method of providing information relating to a digital photograph on an electronic device includes detecting, by a processor of the electronic device, a digital photograph sharing event for sharing the digital photograph, receiving text input related to the digital photograph, the text input comprising text entered at the electronic device or text received from the at least one other electronic device, in response to detecting and receiving text input related to the digital photograph, processing the text related to the digital photograph utilizing natural language processing to extract the information relating to the digital photograph, and storing the information that is extracted in association with the digital photograph.