Functional Image Archiving via Confidence Scoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional image management systems do not provide automatic functional image archiving and suggestions, leading to user dissatisfaction when functional images are displayed alongside non-functional images, disrupting the viewing experience.

Innovation Solution

A computer-implemented method and system that analyzes images to determine functional labels and confidence scores, automatically archiving functional images by associating an archive attribute with them, excluding them from display, and providing user interface suggestions for archiving based on functional image scores.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If functional images are displayed alongside non-functional images in digital albums, then all images are visible to users, but user viewing experience is disrupted and manual archiving effort increases

Engineering Contradiction:
Improveuser viewing experienceVSAvoidmanual archiving time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system performs self-service by automatically analyzing images, determining functional labels, calculating functional image scores, and archiving functional images without user intervention. The image management system autonomously separates functional images (receipts, documents, cards) from non-functional images based on confidence scores and thresholds, eliminating the need for manual user sorting while improving viewing experience.

Inventive Principle:
Principle #25Self-service

2Ease of operation

If automatic functional image archiving is implemented, then user viewing experience is improved by separating functional from non-functional images, but system complexity increases

Engineering Contradiction:
Improveuser viewing experienceVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system segments the image collection into functional and non-functional categories by analyzing each image independently. It divides the archiving process into distinct stages: image analysis, functional label determination, confidence score calculation, threshold comparison, and selective archiving. This segmentation manages complexity by handling images individually rather than requiring complex global optimization.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses parameter changes to manage complexity by adjusting confidence score thresholds for different functional labels. It determines functional image scores based on multiple parameters including label confidence scores, image content analysis, and category-specific thresholds. This parametric approach allows flexible control over archiving behavior without requiring complex decision logic.

Inventive Principle:
Principle #35Parameter changes

3Loss of information

If all images are displayed in album views, then complete image collection is accessible, but functional images interrupt the flow of viewing non-functional images

Engineering Contradiction:
Improveimage collection completenessVSAvoidviewing flow
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system extracts functional images from the main album view by automatically identifying them through image analysis and functional label determination. It separates functional images (receipts, documents, identification cards) from non-functional images and archives them in a distinct location, allowing users to view non-functional images in an uninterrupted flow while preserving access to functional images through separate retrieval mechanisms.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS11829404B2Functional image archiving
Publication Date: 2023.11.28 GOOGLE LLC
  • US11829404B2 patent drawing
  • US11829404B2 patent drawing
  • US11829404B2 patent drawing

AI summary

Some implementations related to archiving of functional images. In some implementations, a method includes accessing images and determining one or more functional labels corresponding to each of the images and one or more confidence scores corresponding to the functional labels. A functional image score is determined for each of the images based on the functional labels having a corresponding confidence score that meets a respective threshold for the functional labels. In response to determining that the functional image score meets a functional image score threshold, a functional image signal is provided that indicates that one or more of the images that meet the functional image score threshold are functional images. The functional images are determined to be archived, and are archived by associating an archive attribute with the functional images such that functional images having the archive attribute are excluded from display in views of the images.