Dynamic Data Visualization for Text Fact Validation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current data visualization processes are cumbersome, requiring manual search and integration of data and visualizations, and existing technologies often rely on preloaded data or static content, failing to automatically generate visualizations that validate and support factual statements in written text.

Innovation Solution

An analytics program that uses natural language processing to identify facts in text documents, retrieves supporting datasets, and generates dynamic data visualizations to insert into the text, validating the accuracy and relevance of the visualizations in real-time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual search and integration of data and visualizations is used, then data accuracy can be validated, but the process complexity and time consumption increase significantly

Engineering Contradiction:
Improvedata accuracy validationVSAvoidprocess complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system automatically validates data accuracy by having the visualization generation process itself query the information source and compare retrieved data with source text facts, eliminating the need for separate manual validation steps. The analytics program performs self-validation by tracing data back to its source and verifying consistency.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system pre-loads and indexes information from multiple sources before visualization is needed, creating a ready-to-query knowledge base. This preliminary data preparation enables rapid validation during the actual visualization generation process without adding complexity to the user workflow.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If manual search and integration of data and visualizations is used, then data accuracy can be validated, but the time consumption increases significantly

Engineering Contradiction:
Improvedata accuracy validationVSAvoidtime consumption
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs data validation continuously during the automated visualization generation process rather than as a separate manual step. The analytics program continuously queries information sources and validates data consistency throughout the workflow, making validation an integrated part of the automation rather than an additional time-consuming phase.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The system replaces manual mechanical search and validation processes with automated electronic querying and comparison algorithms. The analytics program automatically retrieves data from information sources and validates it against source text, substituting human manual work with automated computational processes that are both faster and more reliable.

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

3Productivity

If automated visualization generation is implemented, then productivity increases, but the ability to validate facts against source text may be compromised

Engineering Contradiction:
Improvevisualization generation speedVSAvoidfact validation accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system implements automated feedback loops where the analytics program generates visualizations and simultaneously validates them against the source text by querying information sources. The validation results feed back into the generation process, ensuring that only factually accurate visualizations are produced. This automated feedback maintains both speed and accuracy.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system introduces an intermediary validation layer between data retrieval and visualization output. The analytics program acts as a mediator that queries information sources, validates retrieved data against source text facts, and only proceeds with visualization generation when validation succeeds. This intermediary ensures factual accuracy without compromising automated productivity.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS11487801B2Dynamic data visualization from factual statements in text
Publication Date: 2022.11.01 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US11487801B2 patent drawing
  • US11487801B2 patent drawing
  • US11487801B2 patent drawing

AI summary

A method, computer system, and a computer program product for dynamic data visualization is provided. The present invention may include identifying at least one set of facts in a human-readable text document. They present invention may then include retrieving, from an information source, a dataset associated with the at least one identified set of facts. The present invention may also include, in response to determining that the retrieved dataset includes a fact-supporting dataset, wherein the fact-supporting dataset is configured to validate the at least one identified set of facts, generating at least one data visualization based on the retrieved dataset. The present invention may further include providing the at least one generated data visualization for inserting into the human-readable text document to support the at least one identified set of facts.