Generative AI Workflow Assistant for Natural Language Problem Solving

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing workflow systems require specialized knowledge and technical skill to create workflows, limiting their use and increasing the likelihood of errors and process inefficiency. Additionally, users often struggle to determine the appropriate workflow and template to address specific problems.

Innovation Solution

A workflow assistant system that employs generative artificial intelligence to create workflows within a workflow system. This system allows users to specify problems in natural language, and using machine learning models, it infers a suitable workflow template, requests and receives necessary data, populates the template, and triggers the generation of the workflow.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If workflow systems use templates to reduce creation burden, then workflow creation becomes easier, but users still require specialized knowledge and technical skill

Engineering Contradiction:
Improveworkflow creation easeVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces a natural language processing intermediary that mediates between the user's problem description and the workflow template selection. Instead of requiring users to directly interact with complex template systems, the NLP intermediary translates natural language problems into appropriate workflow templates, eliminating the need for users to have specialized knowledge of workflow creation while maintaining ease of operation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If workflow systems require specialized knowledge for creation, then workflow reliability improves, but productivity and accessibility decrease

Engineering Contradiction:
Improveworkflow reliabilityVSAvoidworkflow creation productivity
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system enables self-service workflow creation by allowing users to describe their needs in natural language without requiring specialized knowledge. The system automatically analyzes the problem, selects appropriate templates, and configures workflows, making the process accessible to anyone while maintaining reliability through automated template selection and configuration validation.

Inventive Principle:
Principle #25Self-service

3Manufacturing precision

If users must determine appropriate workflows and templates manually, then customization accuracy improves, but time consumption increases

Engineering Contradiction:
Improveworkflow customization accuracyVSAvoidworkflow creation time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-configuring workflow templates with common parameters and structures before users need them. When a user describes a problem in natural language, the system has already prepared multiple potential templates and can quickly match the user's needs, eliminating the time-consuming manual search and configuration process while maintaining customization accuracy through automated parameter filling.

Inventive Principle:
Principle #10Preliminary action

4Adaptability or versatility

If workflow systems provide extensive templates, then versatility improves, but system complexity and difficulty in selection increase

Engineering Contradiction:
Improveworkflow template versatilityVSAvoidtemplate system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical system of manual template selection and configuration with an automated NLP-based system. Instead of users navigating complex template categories and making selection decisions, the natural language processing system automatically interprets user problems and selects appropriate templates, maintaining versatility while reducing the perceived complexity for users.

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

Data Source

PatentUS20250139417A1Workflow assistant with generative artificial intelligence
Publication Date: 2025.05.01 INTUIT INC
  • US20250139417A1 patent drawing
  • US20250139417A1 patent drawing
  • US20250139417A1 patent drawing

AI summary

Certain aspects of the disclosure pertain to workflow creation assistance with generative artificial intelligence. A problem statement can be received that is specified by a user in a natural language. At least one machine learning model can infer a workflow template that maps to the problem statement. Workflow template parameters can be determined, and parameter values generated based on the problem statement. Additional interaction with the user in the natural language can be performed to request and receive further data associated with the workflow template with the at least one machine-learning model. Subsequently, the workflow template can be populated with generated parameter values and provided to a workflow system that generates a workflow based on the workflow template.