AI Project Plan Generation From Natural Language Tasks

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current project planning applications require significant time, skill, and domain knowledge for creating and updating project plans, necessitating extensive adjustments to templates.

Innovation Solution

Utilizing a text generation model, such as a transformer-based neural network, to automatically generate project plans and updates based on user descriptions, incorporating prompt templates and script execution for repetitive tasks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If project plan templates are used to assist in creation, then project plan structure is standardized, but extensive adjustments and modifications are required making the process effort-intensive

Engineering Contradiction:

Improveease of project plan creationVSAvoidtime required for template adjustments

Core Design Contradiction:

Ease of manufactureVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical adjustments of template elements with an AI-based automated system. The generative AI model processes natural language descriptions and automatically generates project plans with proper structure, eliminating the need for manual copying, moving, deleting, and adding of template elements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables users to create project plans by simply describing their needs in natural language, while the AI system autonomously performs the complex tasks of structuring, scheduling, and organizing project elements without requiring user intervention in the technical adjustments.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If manual project plan creation is performed, then customization to specific project needs is achieved, but significant time and domain knowledge are required

Engineering Contradiction:

Improvecustomization to project needsVSAvoidtime required for plan development

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent replaces manual planning processes requiring domain knowledge with an AI system that uses natural language processing and generative models. Users provide high-level descriptions of project needs, and the AI automatically generates detailed, customized project plans including schedules, milestones, and task breakdowns without requiring user expertise.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The generative AI model acts as an intermediary between the user's simple natural language descriptions and the complex project plan structure. It translates high-level requirements into detailed project management documentation, bridging the gap between user needs and professional planning standards.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If detailed project plans with multiple data structures are created, then project management comprehensiveness is improved, but complexity of data structure management increases

Engineering Contradiction:

Improvecompleteness of project plan dataVSAvoidcomplexity of data structure management

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces manual management of multiple interconnected data structures (schedule, scope, cost, risk, resource breakdowns) with an AI system that automatically generates and maintains these structures. The generative AI model creates coherent, interrelated data structures that reflect project realities without requiring users to manually manage their complexity and relationships.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250390815A1Task determination using generative ai

Publication Date: 2025.12.25 SAP SE

AI summary

Systems and methods include reception of a description of a project, instruction of a text generation model to generate text describing a plurality of tasks based on the description, determination of a hierarchical structure of the plurality of tasks from the generated text, and generation of a project plan file including the hierarchical structure and the plurality of tasks.