SkillExtract – Development of a machine learning based Skill Relationship Extraction algorithm for unstructured text data
Future working life is shaped by project work and knowledge intensity. The efficiency of the economy will depend on staffing new projects with the right specialists in a timely manner. However, manual management of specialist skills and project content is impossible due to the complexity of implicit knowledge. For this purpose, important content can be identified using machine learning processes from unstructured data such as project descriptions or specification sheets and specialist skills can be compared with project content. In the project, an algorithm is being developed that will use this data to discover important relationships between specialist content and extract it as context information. This can answer questions like “Which employee has already used technology X in branch Y?” This helps to solve challenges more quickly and to find suitable employees for new tasks, which benefits companies’ ability to innovate.
• smarTransfer GmbH, Dr. René Wegener (Coordinatior)
• Kassel University, Chair of Information Systems, Prof. Dr. Jan Marco Leimeister
This project (HA project no .: 628 / 18-51) is funded as part of Hessen ModellProjekte with funds from the LOEWE – State Offensive for the Development of Scientific and Economic Excellence, funding line 3: SME joint projects.
Further information at www.innovationsfoerderung-hessen.de