Human Drivers Knowledge Integration in a Logistics Decision Support Tool

Abstract

The logistics sector is a very dynamic and complex domain with large impact in our day-to-day life. It is also very sensitive to the market changes, so tools that can improve their processes are needed. This paper describes a decision support tool for a Spanish Logistics Company. The tool takes the knowlege from the human drivers, i.e. the address used to deliver a package, integrates and exploits it into the decision process. However, this is precisely the data that is often wrongly introduced by the drivers. The tool analyses and detects different mistakes (i.e. misspellings) in the addresses introduced, groups by zones the packages that have to be delivered, and proposes the routes that the drivers should follow. To achieve this, the tool combines three different techniques from Artificial Intelligence. First, Data Mining techniques are used to detect and correct addresses inconsistencies. Second, Case-Based Reasoning techniques that are employed to separate and learn the most frequent areas or zones that the experienced drivers do. And finally, we use Evolutionary Computation (EC) to plan optimal routes (using the human drivers past experiences) from the learned areas, and evaluate those plans against the original route executed by the human driver. Results show that the tool can automatically correct most of the misspelling in the data.