Natural Language Workflow Generation with Step-Specific Program Logic

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing workflow generation techniques are time-intensive, compute-intensive, and often result in inaccurate and inefficient workflows that waste computing resources due to ad hoc development and subjective decision-making, leading to varying outcomes and inefficiencies.

Innovation Solution

A two-phase process is employed using a natural language model to generate workflows, first creating an outline and then specifying each step with programmatic definitions, incorporating platform-specific adaptations and eliminating redundant states or transitions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If ad hoc development and subjective decision-making are used for workflow generation, then flexibility in development is maintained, but workflow accuracy and efficiency deteriorate

Engineering Contradiction:

Improveworkflow accuracyVSAvoiddevelopment process complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent replaces manual ad hoc workflow development with an automated system that uses natural language processing and operational characteristic analysis to generate workflows programmatically. This substitution eliminates subjective decision-making while maintaining development flexibility through automated interpretation of operational requirements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables workflows to be generated automatically by analyzing operational characteristics and naturally describing the desired workflow. The automation service performs the entire workflow generation process without requiring manual intervention, thereby improving accuracy while managing complexity through systematic automation.

Inventive Principle:

Principle #25Self-service

2Productivity

If comprehensive operational characteristics are analyzed for each workflow step, then workflow efficiency is improved, but computing resources consumed during generation increase

Engineering Contradiction:

Improveworkflow efficiencyVSAvoidcomputing resource consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent performs preliminary analysis of operational characteristics during the workflow generation phase rather than during execution. By pre-analyzing and storing the relationship between operational characteristics and workflow steps, the system achieves efficient workflow execution without consuming excessive computing resources during runtime.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system segments the workflow generation process into distinct phases: analyzing operational characteristics, identifying relevant portions, and generating workflow steps. This segmentation allows comprehensive analysis to be performed systematically, improving workflow efficiency while managing computing resource consumption through structured processing.

Inventive Principle:

Principle #1Segmentation

3Loss of energy

If redundant states and transitions are eliminated from workflows, then computing resource wastage during execution is reduced, but the complexity of workflow design increases

Engineering Contradiction:

Improvecomputing resource wastageVSAvoidworkflow design complexity

Core Design Contradiction:

Loss of energyVSDevice complexity

Solution Approach 1:

The patent replaces manual workflow design with automated generation that systematically identifies and eliminates redundant states and transitions. The automated system analyzes operational characteristics to generate optimized workflows without redundant elements, reducing computing resource wastage during execution while managing design complexity through algorithmic optimization.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system incorporates feedback mechanisms that analyze the generated workflow for redundancies and optimize it iteratively. By continuously evaluating and refining the workflow based on operational characteristics, the system eliminates redundant states and transitions, reducing computing resource wastage while managing design complexity through systematic optimization loops.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20260023615A1Generating Workflows from Natural Language

Publication Date: 2026.01.22 SERVICENOW INC

AI summary

An embodiment may involve receiving a textual description of a workflow; determining, based on the textual description and operational characteristics associated with a computing system, a workflow outline that represents respective steps of the workflow; for each of the respective steps of the workflow, identifying a respective portion of the operational characteristics based on determining that the respective portion satisfies a relevance criterion; obtaining, from a natural language model and based on the respective portions of the operational characteristics, a respective programmatic representation for each of the respective steps of the workflow; and updating the workflow outline based on the respective programmatic representations.