Automated support for intelligence in asymmetric operations: Requirements and experimental results

This paper presents some findings of the NATO RTO Task Group on information fusion in asymmetric operations. It briefly describes the functional processing steps in military intelligence presenting the underlying aspects of information processing and fusion and revealing main challenges for automatic support of the required functionalities. The extraction and structuring of relevant information from unstructured text documents is shown to be one of the fundamental features where human operators need assistance. As an example of the state of the art the interactive tools PARANOID and CoALA are presented. They provide the basic information and knowledge structure for all subsequent information processing like link analysis and social network analysis. The use and benefit of CoALA will be illustrated by results from a military experiment. Finally, with respect to further research, open questions and new approaches for the support of intelligence production are discussed concerning automatic information structuring and discovery as well as pattern and behaviour based threat assessment.