Semantic Information Management Systems

Tactical networks face significant challenges in dynamic, contested environments, where variable performance, adversarial actions, and mobile infrastructure strain reliable communications. Efficient data management is critical, as the volume of generated data often exceeds available bandwidth. Traditional rule-based Information Management Systems (IMS) prioritize data flows based on attributes like provenance and priority, but fail to consider semantic content, creating a gap between commanders' needs and system functionality. This paper introduces a novel multi-modal Semantic Information Management System (SIMS) architecture to address these challenges. By incorporating semantic queries and subscriptions, the system enables content-driven information exchange, prioritizing critical data based on its semantic value. Key technologies include Machine Learning-driven transformations and Large Language Model-enabled semantic analysis, ensuring enhanced situational awareness and mission coordination. Experimental evaluations demonstrate the architecture's accuracy in semantic extraction and potential to transform tactical network communications, paving the way for more resilient and effective information management strategies in modern warfare. This paper was originally presented at the NATO Science and Technology Organization Symposium (ICMCIS) organized by the Information Systems Technology (IST)Scientific and Technical Committee, IST-209-RSY - the ICMCIS, held in Oeiras, Portugal, 13-14 May 2025.