AI-Planned Wizard Workflows for Complex Industrial Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wizards in industrial systems are limited by their hard-coded implementations, requiring users to have extensive experience and are inflexible in navigating complex workflows, restricting their applicability to predefined scenarios.
Innovation Solution
A dynamic wizard system that generates flexible workflows using a computing system with a wizard planning module, AI planner, and wizard engine, leveraging domain knowledge and user interactions to create goal-driven wizards that adapt to user inputs and system states, allowing for multiple plan generation and execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional hard-coded wizards are used, then the system structure is simple and reliable, but the adaptability and ease of operation deteriorate due to limited predefined workflows
Solution Approach 1:
The patent implements dynamic wizard generation by replacing static hard-coded workflows with AI-planned sequences that adapt in real-time. The wizard engine generates plans dynamically based on user goals and system state, allowing the workflow structure to change adaptively rather than following fixed predetermined paths.
Solution Approach 2:
The system performs self-service by automatically generating wizard plans without requiring user expertise. The AI planner autonomously analyzes the current system state, determines appropriate actions, and constructs workflow sequences, eliminating the need for users to manually navigate complex predefined wizard structures.
2Ease of operation
If complex sequences of interaction elements are provided, then the system functionality is comprehensive, but the ease of operation deteriorates requiring enormous user experience
Solution Approach 1:
The patent introduces an AI planner as an intermediary between the user's simple goal input and the complex system operations. The planner translates high-level user intentions into detailed sequences of interaction elements, shielding users from interface complexity while maintaining comprehensive system functionality.
Solution Approach 2:
The system performs preliminary action by pre-computing wizard plans and preparing interaction sequences before user execution. The AI planner analyzes system state and generates appropriate action sequences in advance, so users receive ready-to-follow instructions rather than navigating complex interfaces in real-time.
3Adaptability or versatility
If fixed predefined workflows are used, then the system reliability is high, but the adaptability to different user needs deteriorates
Solution Approach 1:
The patent implements feedback mechanisms where the AI planner continuously monitors system state changes and user inputs during workflow execution. This allows the wizard to adapt plans dynamically while maintaining reliability through systematic state verification and constraint checking at each decision point.
Solution Approach 2:
The system achieves adaptability through parameter changes by modifying workflow variables, action sequences, and system state representations based on user goals. The AI planner adjusts plan parameters dynamically while maintaining structural integrity and reliability through formal verification of state transitions.
Data Source
AI summary
In various software applications, wizards can assist users in navigating through selected, predefined workflows for automating some repetitive interaction patterns. It is recognized herein, however, that such conventional wizards are generally limited to few use cases that are hard-wired in a given wizard's implementation, such that user still needs to master the respective tool's complexity. In an example aspect, a computing system within an automation system can determine a goal state associated with a target application. The system can extract an initial state from the target application. Based on knowledge obtained by the system, the system can generate a plurality of plans. The plans can define respective sequences of actions for reaching the goal state from the initial state. The system can render options on a user interface of the target application. Based on the options, the system receives selections related to the sequences of actions so as to define selected actions. The system can perform the selected actions until the goal state is reached.