A hybrid AI approach to staff scheduling

Assigning nursing staff to specific duties according to their contract, qualifications, skills, etc. within a working environment characterised by multi-disciplinarity and statutory regulations is problematic. Factors involved in making effective assignments include individual and corporate procedures, guidelines and constraints. Manual rostering commonly proceeds through a process of reasoning in which a number of consecutive stages occur to progressively refine and repair the work schedule. This paper discusses an approach to nurse rostering, using a strategy of distributing the computational effort required in the scheduling process. The technique involves a hybrid approach that devolves responsibility for different aspects of the problem to a heuristic component and a constraint solver. In the pre-processing stage, the staff to be rostered are treated as semi-autonomous agents, each with individual responsibility for their initial assignment, and communicating with a global constraint satisfaction agent. This has proved to be intuitive to build and effective in use