In manufacturing industries, various problems may occur during the production process. Aproblem is a complex status, which involves relevant context in working environments. Aproblem-solving process is often initiated to create a solution for achieving the desired status; inthis process, determining how to obtain a solution from the various candidate solutions is animportant issue. In such uncertain working environments, context information provides richclues for problem-solving decision making. Therefore, this work uses a selection approach foran optimized problem-solving process to assist workers in choosing a reasonable solution. Acontext-based utility model explores the problem context information to obtain the candidatesolutions’ actual utility values; a multi-criteria decision analysis uses the actual utility values todetermine the optimal selection order of candidate solutions. The selection order is presented tothe worker as an adaptive knowledge recommendation. The worker chooses a reasonableproblem-solving solution based on the selection order. This paper uses a high-tech company’sknowledge base log as the analysis data. The experimental results show that thechosen approach to an optimized problem-solving solution selection is effective. Thecontribution of this research is in demonstrating a method, which is easy to implement in aproblem-solving knowledge recommendation system for selecting a reasonable solution.