Building expert systems in case-based law

摘要

This paper is based on a course about legal reasoning and artificial intelligence, taught by the authors to second and third year students at the University of British Columbia Faculty of Law. The course outlines and compares two approaches to the construction of legal expert systems: rule-based systems and case-based reasoners. A systematic, step-by-step procedure for the construction of a legal expert system linked to a database of legal cases is taught using a sample system on the law relating to damage arising from land use. On the basis of factual information supplied by the user, the system determines possible causes of action to pursue, assesses the likelihood of success, and displays relevant cases that support its predictions. The domain knowledge is represented by rules derived from a deep structure analysis of legal doctrines governing the law in this area.