Knowledge-Based Decision Model Construction for Hierarchical Diagnosis: A Preliminary Report

TL;DR

This paper introduces a uniform, value-driven approach for the incremental construction of decision models in hierarchical diagnosis, formulated as a stochastic process using influence diagrams to optimize fault detection and repair.

Contribution

It presents a novel method that automates dynamic decision model construction for hierarchical diagnosis, integrating probe actions with model evaluation in a unified framework.

Findings

Effective incremental decision model construction demonstrated

Optimizes fault localization and repair costs

Integrates meta-level and base-level decision tasks

Abstract

Numerous methods for probabilistic reasoning in large, complex belief or decision networks are currently being developed. There has been little research on automating the dynamic, incremental construction of decision models. A uniform value-driven method of decision model construction is proposed for the hierarchical complete diagnosis. Hierarchical complete diagnostic reasoning is formulated as a stochastic process and modeled using influence diagrams. Given observations, this method creates decision models in order to obtain the best actions sequentially for locating and repairing a fault at minimum cost. This method construct decision models incrementally, interleaving probe actions with model construction and evaluation. The method treats meta-level and baselevel tasks uniformly. That is, the method takes a decision-theoretic look at the control of search in causal pathways and structural hierarchies.