Memory-Based Meta-Level Reasoning for Interactive Knowledge Capture

摘要

Current knowledge acquisition tools are oblivious to the process or strategy that the user may be following in entering new knowledge, and are unaware of the users' progress during a session. Users have to make up for these shortcomings by keeping track of the status, progress, potential problems, and possible courses of actions by themselves. The author presents a novel extension to existing systems that does the following: (1) keeps track of past problem solving episodes and relates them to user-entered knowledge, (2) assesses the current status of the knowledge and the problem solving using such relations, and (3) provides assistance to the user based on the assessment. The author applied this approach in developing an intelligent assistant for decision making tasks. The resulting interaction shows that the system guides the knowledge authoring process in terms of making the knowledge more useful, adapting the knowledge to dynamic changes over time, and making overall problem solving more successful.