Chart Explanation System for Visual Data Comprehension

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Individuals, particularly children and those with low education or mathematical understanding, face difficulties in interpreting visual charts and graphical data, which hinders their comprehension of mathematical concepts and decision-making processes.

Innovation Solution

A computer-implemented method and system that selects a chart, interprets its contents, searches for additional information sources, extracts relevant data, and generates a textual description to assist users in understanding the chart, utilizing cloud computing and combining computer vision with natural language processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If visual charts are used to present data, then information density and presentation efficiency are improved, but comprehension difficulty increases for users with low education or mathematical understanding

Engineering Contradiction:
Improveinformation presentation efficiencyVSAvoidchart interpretation difficulty
Core Design Contradiction:
ProductivityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent introduces an intermediary system (chart explanation system) that mediates between the visual chart and the user. The system automatically generates textual explanations that bridge the gap between graphical data representation and user comprehension, particularly helping users with limited mathematical or educational background understand chart contents without requiring specialized knowledge

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical cognitive process of manually interpreting visual charts with an automated computational system. Instead of relying on users to manually analyze graphical elements, the system uses image processing and natural language generation to automatically create explanatory text, substituting human cognitive effort with automated information processing

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

2Ease of operation

If automated chart interpretation systems are implemented, then user understanding is improved, but system complexity increases

Engineering Contradiction:
Improvechart understanding easeVSAvoidinterpretation system complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent creates a universal system that can handle multiple types of charts (bar charts, line graphs, pie charts, etc.) and various data representations through a single multi-functional platform. The system is designed to be adaptable to different chart formats and styles, reducing the need for multiple specialized tools while maintaining ease of use across diverse scenarios

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

Solution Approach 2:

The system employs self-service mechanisms through automated image processing, optical character recognition, and natural language generation. The chart explanation system autonomously analyzes visual elements, extracts data, and generates explanations without requiring manual configuration or complex user setup, thereby simplifying operation despite the underlying system complexity

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS10025980B2Assisting people with understanding charts
Publication Date: 2018.07.17 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US10025980B2 patent drawing
  • US10025980B2 patent drawing
  • US10025980B2 patent drawing

AI summary

Aspects of the present invention include a method, system and computer program product. The method includes a method includes selecting a chart, and interpreting contents within the selected chart. The method also includes searching for additional sources of information, and extracting information from the additional sources of information. The method further includes combining the interpreted chart contents with the extracted information, and generating a textual description of the selected chart.