Distributed Hypothesis Generation and Evaluation

点击翻译按钮获取中文摘要

This PhD is developing approaches to support analysts and semi-automated agents in collaboratively performing hypothesis generation and evaluation in an intelligence scenario. The approaches utilise argumentation theory, a mathematical construction representing conflicts between arguments. Argumentation can be represented computationally as an ontology which allows a linked data approach to distributed analysis.Approaches have been developed to allow analysts with expertise to contribute their knowledge to different parts of an intelligence analysis in a collaborative manner by generating sub-arguments which are coherent with the analysis as a whole. Analysts or agents, using a well-defined theory of abstract argumentation, may then evaluate the hypotheses, which may suggest further collection of information or require refinement of hypotheses. Intelligence analysis is considered as a cycle and therefore all stages of the process should be compatible with collaborative and distributed analysis. The approaches developed should be validated against other intelligence analysis techniques. Care has been taken to mitigate the potential for biases in the system.The intelligence cycle consists of understanding the information available, generating hypotheses, based on the analysts' situational understanding and the intelligence available and evaluating these hypotheses using the available evidence and structural analytical techniques, eg Analysis of Competing Hypotheses. In each of these steps, analysts, and in future semi-autonomous agents, perform reasoning based on different intelligence available and their background knowledge. Allowing analysts to collaborate effectively on intelligence problems could improve the quality of analyses and reduce biases in an analysis.