Ericsogate: Advancing Analytics and Management of Data from Diverse Sources within Ericsson Using Knowledge Graphs

As data in the telecommunications industry becomes more voluminous and complex, extracting insightful information requires efficient and scalable systems that can effectively link and manage this data. This paper introduces a novel, multi-layered approach to managing interlinked data for Cloud Radio Access Network (CloudRAN) at Ericsson, utilizing Knowledge Graphs (KGs). Our system is structured into six distinct layers, each focusing on a specific aspect of managing interlinked data. This division enhances clarity and manageability, and promotes effective teamwork and collaborative development. A cornerstone of our architecture is its modularity, which enables the flexible exchange of components, such as the triple store, with minimal impact on the system's operations, ensuring longevity and adaptability to evolving technological trends. Moreover, we introduce novel applications in knowledge graph summarization and semantic search, specifically engineered for industrial decision-making. These innovations provide concise insights and actionable intelligence, fostering rapid and informed decision-making processes crucial for industry professionals. Finally, we discuss the lessons learned from deploying and utilizing this six-layer framework.