Neural Networked Assisted Tree Search for the Personnel Rostering Problem

Journal of Scheduling manuscript No. (will be inserted by the editor) Abstract The personnel rostering problem is the problem on which branch to choose next and to prune the search of finding an optimal way to assign employees to tree. The problem has received significant attention in the literature and is addressed by a large number of exact and 1 Introduction metaheuristic methods. In order to make the complex and costly design of heuristics for the personnel rostering In various occupations and work scenarios, arranging problem automatic, we propose a new method employees to different shifts is a difficult job. The difficulty combined Deep Neural Network and Tree Search. By is that different employees have different requirements treating schedules as matrices, the neural network can for life and work, which leads to preference of predict the distance between the current solution and each employee. And there are also requirements of the the optimal solution. It can select solution strategies by law that must be followed or diverse properties of different analyzing existing (near-)optimal solutions to personnel occupations. These regulations are what we call soft rostering problem instances.