Microservices Enterprise Architecture Design with AI-Powered OCR for Improving Fixed Broadband Complaint Handling: A Telco Company Case Study

The rapid growth of internet users in Indonesia has increased the demand for efficient broadband services. This study proposes a microservices-based enterprise architecture integrating AI-powered Optical Character Recognition (OCR) and Natural Language Processing (NLP) with the Integrated Customer Management System (ICMS) and Knowledge Management System (KMS). The architecture addresses challenges arising from Fixed Mobile Convergence (FMC), which introduced complexities in customer service. Automating complaint categorization and solution retrieval through AIbased recommender systems improves accuracy, response times, and operational efficiency, supporting digital transformation goals. The current customer service processes rely heavily on manual intervention, causing inefficiencies like long wait times, especially on digital platforms. Leveraging TOGAF, this research designs a scalable architecture where OCR extracts data from unstructured sources, and NLP enables intelligent categorization and recommendations. Using Design Science Research Methodology, the study demonstrates the architecture's potential to enhance customer experience, streamline workflows, and optimize telco operations in a rapidly evolving technological landscape.