Natural-Language Visual Workflow Generation with DAG Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional workflow automation systems require technical proficiency and lack a comprehensive natural language-based interface, hindering user accessibility and efficiency.
Innovation Solution
A system and method for automatic visual workflow model generation and management using multimodal inputs, generative AI models for natural language understanding and generation, and a chat interface to refine and visualize workflows, constructing a directed acyclic graph (DAG) for clear task interdependencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional software solutions are used for workflow automation, then workflow functionality can be achieved, but user accessibility deteriorates due to the requirement of coding expertise and technical proficiency
Solution Approach 1:
The patent introduces a natural language processing intermediary that mediates between the user's simple text input and the complex workflow automation system. Users can describe workflows in natural language without coding expertise, and the system translates these descriptions into executable automation logic, thus resolving the contradiction between maintaining workflow functionality and improving user accessibility
Solution Approach 2:
The patent replaces the mechanical system of manual workflow configuration (drag-and-drop interfaces, coding) with an AI-based natural language processing system. This substitution allows users to interact with workflow automation through conversational text rather than technical interfaces, significantly improving ease of operation while preserving full workflow automation capability
2Manufacturing precision
If traditional coding methodologies are used, then precise workflow control can be achieved, but the learning curve increases and efficiency deteriorates
Solution Approach 1:
The system performs self-service by automatically generating, validating, and optimizing workflow logic based on natural language descriptions. The AI model autonomously handles the complex tasks of translating user intent into precise workflow control structures, eliminating the need for users to manually code while maintaining high precision in workflow execution
Solution Approach 2:
The patent changes the fundamental parameter of user input from structured code syntax to unstructured natural language. This parameter change enables users to focus on describing workflow intent rather than syntax details, improving efficiency while the AI model ensures precise control by translating natural language into rigorously structured automation logic
3Device complexity
If comprehensive natural language interface is not provided, then system complexity can be reduced, but user-system communication efficiency deteriorates
Solution Approach 1:
The natural language processing system serves multiple functions simultaneously: it acts as the user interface for input, the specification language for workflow definition, and the validation mechanism for logic correctness. This multi-functionality enables comprehensive user-system communication without significantly increasing system complexity, as the same NLP infrastructure handles all these tasks
Data Source
AI summary
A method for automatic visual workflow model generation and management is disclosed that utilizes multimodal inputs and user feedback. The method further comprises receiving, through a processor, descriptions using an advanced AI model, generating elaborate plans that visually organize sequential tasks. User feedback via natural language on these plans refines them, establishing connections between detailed plans and numerous sub-skills. The processor constructs a directed acyclic graph (DAG) visualizing sub-skill execution order based on the established mapping, culminating in an executable workflow model. The method further comprises seamlessly translating user descriptions into detailed plans, refine them iteratively, and generate an executable workflow model, all driven by user interactions and advanced AI techniques supporting natural language understanding and generation.