Automation Program Generation from Process Event Logs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automation systems require significant time and effort for creating automation programs, even for users with lesser software development experience, and there is a need to facilitate their development with greater efficiency and reduced user burden.
Innovation Solution
Systems and methods that utilize machine learning models to process event logs from process mining systems, identifying command packages and actions to automate tasks, reducing the need for extensive coding or programming skills.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional methods are used to create automation programs, then automation functionality can be achieved, but significant time and effort are required even for users with lesser software development experience
Solution Approach 1:
The patent replaces manual programming mechanisms with machine learning models. The command package model and action model use AI/ML algorithms to automatically generate automation programs from event logs, eliminating the need for users to manually write code. This substitution of mechanical programming with intelligent automation directly reduces both the time and effort required while maintaining ease of operation.
Solution Approach 2:
The system enables self-service automation program generation where the machine learning models automatically analyze event logs and produce automation programs without requiring user programming expertise. The models serve themselves by processing event data and generating appropriate automation commands, allowing users with lesser software development experience to create automation programs efficiently.
2Productivity
If machine learning models are used to automatically generate automation programs from event logs, then time and effort for program creation are significantly reduced, but the system complexity increases
Solution Approach 1:
The patent segments the automation program generation process into distinct functional components: a command package model that identifies high-level commands, an action model that determines specific actions, and an automation program generator that assembles the final program. This segmentation allows each component to specialize in specific tasks, improving overall productivity while managing system complexity through modular architecture.
Solution Approach 2:
The patent introduces machine learning models as intermediary components between event logs and automation programs. These models act as mediators that translate raw event data into structured automation commands, bridging the gap between data processing and program generation. This intermediary approach improves productivity by enabling automatic translation while containing complexity within specialized model components.
Data Source
AI summary
Systems and methods for producing programs and processes for performing tasks based on event data contained within event logs are disclosed. The systems and methods can involve processing event data such that relevant portions of the event data are provided to machine learning models to allow such systems to produce automation programs. The systems and methods can also involve providing instructions to a command package machine learning model, such as a large language model, that operates to propose command packages that contain automation actions, and providing instructions to an action machine learning model that selects automation actions, associated with the proposed command packages, to be incorporated within automation programs that can be used to automate the tasks.