A method for implementing a probabilistic model as a relational database

TLDR

The paper proposes a method to implement probabilistic inference using an extended relational data model. The approach represents the probability model as a generalized relational database, enabling probabilistic queries to be executed as standard relational queries. The model unifies diverse applications—including dynamic programming, sparse linear equation solving, and constraint propagation—and can be implemented on conventional database systems.

Abstract

This paper discusses a method for implementing a probabilistic inference system based on an extended relational data model. This model provides a unified approach for a variety of applications such as dynamic programming, solving sparse linear equations, and constraint propagation. In this framework, the probability model is represented as a generalized relational database. Subsequent probabilistic requests can be processed as standard relational queries. Conventional database management systems can be easily adopted for implementing such an approximate reasoning system.