AI Workflow Engine for Non-Expert Process Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing AI solutions require domain knowledge and expert skills for implementation and integration into processes, making it difficult for non-technical users to utilize and deploy AI capabilities effectively, especially in process modeling stages.
Innovation Solution
A method utilizing a user-driven workflow engine with multiple modules to define context, generate context information, and execute data collection workflows, allowing users to create and optimize AI models without specialized knowledge, enabling the integration of AI into processes through automatic interpretation and self-improvement of AI models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing AI solutions are used, then AI capabilities can be applied to processes, but domain knowledge and expert skills are required for implementation and integration
Solution Approach 1:
The patent introduces an AI model that acts as an intermediary between process data and decision-making. The AI model automatically learns from process data and provides recommendations, eliminating the need for users to have domain knowledge in AI. The system mediates between raw process data and actionable insights through automated learning and interpretation.
Solution Approach 2:
The AI model performs self-learning and self-improvement by automatically analyzing process data and updating its predictions. The system serves itself by autonomously identifying patterns, making predictions, and improving accuracy over time without requiring expert intervention for model training or optimization.
2Productivity
If AI-capable process modeling tools are implemented, then process optimization is enhanced, but implementation is restricted to methodical experts
Solution Approach 1:
The patent replaces complex manual AI implementation processes with automated computational systems. Instead of requiring experts to manually configure and train AI models, the system automatically performs data processing, model training, and optimization through computational algorithms, substituting mechanical expert processes with automated digital systems.
Solution Approach 2:
The system automatically adjusts AI model parameters and configurations based on process data characteristics. The AI model dynamically modifies its internal parameters through learning algorithms, adapting to different process contexts without requiring manual parameter tuning by experts.
3Reliability
If AI solutions require additional tools or knowledge for deployment, then AI functionality is enhanced, but user dependency on external expertise increases
Solution Approach 1:
The AI model serves multiple functions within a single integrated system: it collects process data, learns from data, makes predictions, and provides recommendations. This multi-functional approach eliminates the need for separate tools for data collection, model training, and deployment, enabling users to achieve reliable AI results with a single self-contained system.
Data Source
AI summary
The invention relates to a method of performing a process using artificial intelligence. The method comprises running, by a computing device, an application configured to perform a process which uses an artificial intelligence model for processing signals and defining at least one parameter set for performing the at least one process; running, by the computing device, a user-driven workflow engine which comprises multiple modules including at least a first and second module; defining, by the first module, a context of the process and generating corresponding context information, providing the artificial intelligence model based on the generated context information of the process; and using, by the second module, the artificial intelligence model in a user-driven workflow within the application while executing the process. Advantageously, the combination of these modules describes an end-to-end connection which is self-learning and self-improving and is targeted at users with no expertise in the AI domain.