Knowledge Graph Content Fitting for Intent-Aligned Presentations

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing slide presentation generation methods require substantial manual effort and lack granular control over the flow and structure, often resulting in presentations that do not align with the user's intent, even when using generated content.

Innovation Solution

A system that generates a detailed, editable presentation outline based on a user's input, retrieves relevant templates annotated with slide archetypes, and uses a knowledge graph to accurately place content elements, ensuring alignment with the user's intent while offering fine-tuned control over the presentation's development.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated presentation generation is implemented, then productivity is improved, but manufacturing precision deteriorates due to lack of control over flow and structure

Engineering Contradiction:
Improvepresentation generation efficiencyVSAvoidalignment with user intent
Core Design Contradiction:
ProductivityVSManufacturing precision

Solution Approach 1:

The patent introduces a knowledge graph as an intermediary structure that bridges automated generation and user intent. The knowledge graph stores structured relationships between presentation elements, templates, and content requirements, enabling the system to generate presentations automatically while maintaining alignment with user expectations through structured constraints and relationships defined in the knowledge graph.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system changes parameters by transforming unstructured user input into structured presentation outlines with defined attributes (title, content, template associations). This parameter transformation enables automated generation while maintaining precision through structured data representation and template parameter matching.

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If manual control over presentation structure is provided, then manufacturing precision is improved, but device complexity increases due to multiple editing steps

Engineering Contradiction:
Improvecontrol over presentation flowVSAvoidnumber of manual steps
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent segments the presentation creation process into distinct, manageable components: outline generation, template selection, and content fitting. Each segment can be independently controlled and edited, allowing users to intervene at specific stages without managing the entire complex process manually. This segmentation reduces perceived complexity while maintaining precision through structured intermediate representations.

Inventive Principle:
Principle #1Segmentation

3Manufacturing precision

If detailed presentation outlines are generated automatically, then manufacturing precision is improved, but loss of time increases due to outline review and editing

Engineering Contradiction:
Improvealignment with user intentVSAvoidoutline review time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by generating structured presentation outlines with pre-assigned templates and content suggestions before the user begins detailed editing. This preliminary structuring reduces the time needed for review and editing by pre-resolving template selection and content placement, allowing users to focus only on refinement rather than complete construction.

Inventive Principle:
Principle #10Preliminary action

4Manufacturing precision

If template annotation with slide archetypes is implemented, then manufacturing precision is improved, but device complexity increases due to knowledge graph construction

Engineering Contradiction:
Improvecontent placement accuracyVSAvoidannotation system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The knowledge graph serves multiple functions: it stores template annotations, defines slide archetype relationships, guides content fitting, and enables automated generation. This multi-functionality reduces the need for separate systems for each task, thereby reducing overall complexity while maintaining high precision through a unified structured representation.

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

Data Source

PatentUS20260105656A1Presentation generation using knowledge graph-informed content fitting
Publication Date: 2026.04.16 ADOBE INC
  • US20260105656A1 patent drawing
  • US20260105656A1 patent drawing
  • US20260105656A1 patent drawing

AI summary

A method, apparatus, non-transitory computer readable medium, and system for generating presentations includes obtaining an input prompt describing a topic and generating, using a text generation model, a presentation outline based on the input prompt. A presentation structure is then generated based on the presentation outline, where the presentation structure includes a structured attribute indicating a slide layout element. A presentation on the topic is generated based on the presentation structure, wherein the presentation comprises a slide including the slide layout element.