AI Narrative Generation Mapping Visualization to Story Configurations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional data visualization tools are limited in communicating complex data insights, as they rely on manual captioning by humans, which is time-consuming and prone to variability in quality, and existing automated solutions fail to provide deep or meaningful explanations.

Innovation Solution

Integration of artificial intelligence-driven natural language generation technology within visualization platforms to automatically generate narrative text based on visualization data, using data structures that map visualization types to story configurations, enabling the creation of context-specific narratives.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual captioning by humans is used, then narrative quality and depth are improved, but time consumption and productivity deteriorate

Engineering Contradiction:

Improvenarrative qualityVSAvoidcaptioning speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system enables automated self-service generation of narrative captions through AI-driven natural language generation technology. The visualization platform automatically analyzes visualization data, determines appropriate story configurations, and generates narrative text without requiring manual human intervention, thus resolving the contradiction between narrative quality and productivity

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical human captioning process with an automated computational system. The AI-driven natural language generation technology substitutes human cognitive and creative processes with algorithmic analysis and text generation, enabling high-speed automated captioning that maintains or improves upon human-generated narrative quality

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If existing automated captioning solutions are used, then productivity is improved, but narrative depth and meaningfulness deteriorate

Engineering Contradiction:

Improveautomation speedVSAvoidnarrative depth

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system dynamically adapts the narrative generation process based on the specific visualization data and type. It uses dynamic story configuration selection that adjusts to different visualization contexts, enabling the automated system to produce deep and meaningful narratives tailored to each specific case rather than applying generic templates

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes key parameters of the automated generation process by implementing AI-driven natural language generation technology with configurable story types and parameters. This allows the system to adjust narrative depth, style, and content based on the visualization data characteristics, thereby improving narrative quality while maintaining automation productivity

Inventive Principle:

Principle #35Parameter changes

3Productivity

If generic automated narrative generation is used, then scalability is improved, but adaptability to specific visualization types deteriorates

Engineering Contradiction:

ImprovescalabilityVSAvoidcontext-specific accuracy

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system implements a universal story configuration framework that can handle multiple visualization types and contexts through a single adaptable architecture. The configurable story types and parameters enable the same core system to generate appropriate narratives for different visualization formats while maintaining scalability across diverse applications

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11188588B1Applied artificial intelligence technology for using narrative analytics to interactively generate narratives from visualization data

Publication Date: 2021.11.30 SALESFORCE INC

AI summary

Narrative generation techniques can be used in connection with data visualization tools to automatically generate narratives that explain the information conveyed by a visualization of a data set. In example embodiments, new data structures and artificial intelligence (AI) logic can be used by narrative generation software to map different types of visualizations to different types of story configurations that will drive how narrative text is generated by the narrative generation software.