Machine Learning Model Integration with Open World Temporal Logic for Process Automation

TL;DR

This work tackles the challenge of turning perceptual ML outputs into explainable, timely decisions within open-world automation. It introduces PyReason, a Python-based open-world temporal logic framework that operates on generalized annotated logic with real-valued truth intervals $[L,U]$, enabling real-time reasoning over knowledge graphs with temporal dynamics. The authors present a standardized integration pipeline using LogicIntegrationBase and TemporalLogicIntegratedClassifier to convert ML outputs into annotated facts and trigger a fixpoint-based minimal model refresh, demonstrated in welding defect detection and a card-drawing game. The approach yields fully explainable inference traces and modular neuro-symbolic pipelines, supporting real-time decision making and potential integration with external solvers for broader industrial and business process automation.

Abstract

Recent advances in Machine Learning (ML) have produced models that extract structured information from complex data. However, a significant challenge lies in translating these perceptual or extractive outputs into actionable and explainable decisions within complex operational workflows. To address these challenges, this paper introduces a novel approach that integrates the outputs of various machine learning models directly with the PyReason framework, an open-world temporal logic programming reasoning engine. PyReason's foundation in generalized annotated logic allows for the incorporation of real-valued outputs (e.g., probabilities, confidence scores) from a diverse set of ML models, treating them as truth intervals within its logical framework. Crucially, PyReason provides mechanisms, implemented in Python, to continuously poll ML model outputs, convert them into logical facts, and dynamically recompute the minimal model to enable decision-making in real-time. Furthermore, its native support for temporal reasoning, knowledge graph integration, and fully explainable interface traces enables an analysis of time-sensitive process data and existing organizational knowledge. By combining the strengths of perception and extraction from ML models with the logical deduction and transparency of PyReason, we aim to create a powerful system for automating complex processes. This integration is well suited for use cases in numerous domains, including manufacturing, healthcare, and business operations.

Figures (5)

• Figure 1: A conceptual overview of the proposed integration framework. (1) Machine learning models provide perceptual outputs (e.g., tensor, probabilities). (2) The PyReason framework converts these outputs into logical facts with truth-value intervals. (3) These facts are used within a temporal logic program to derive actionable, reasoned decisions. The feedback loop illustrates the continuous polling mechanism for real-time adaptation
• Figure 2: Conversion from probabilities to annotated bounds
• Figure 3: Background model-polling and inference loop
• Figure 4: Welding example flowchart
• Figure 5: Workflow diagram for the card game simulation.