As part of my Project Work 1 at DHBW at dmTECH, I explored the feasibility of implementing semantic search for a new Customer Service Management (CSM) tool. The goal of the project was to better understand customer queries and improve the relevance of search results.
For the practical implementation, Python scripts were used to process data, convert it into vectors, and store it in a vector database. Additionally, tests were developed to simulate queries and examine the system’s behavior. Visualizations helped to assess the quality of the data and the semantic structure of the vectors.
The project illustrates how modern machine learning methods can be applied in practice and provides a foundation for the further development of a semantically enhanced CSM tool.