The University of Edinburgh -
Division of Informatics
Forrest Hill & 80 South Bridge

PhD Thesis #9015

Title:A User Modelling Approach to Computer Based Advice Generation.
Date: 1990
Abstract:The need for intelligent advice, help and tutoring, generated automatically by computers is widely accepted. Recently, efforts to achieve these requirements have focused upon research into user models and improved user-machine interaction. This thesis develops a mechanism for detecting when an individual has a problem with the computer system, and generates hypotheses which describe possible problems that he may possess. The method uses Plan Recognition to suggest plans that a user may be following. A Chart Parser is used to achieve this plan recognition task. This technique is capable of detecting multiple, interleaved and incomplete plans, without prior knowledge of the user's intended goals. A model of users' beliefs is developed for part of the Unix2 operating system. This model is capable of representing misconceptions that users possess about the domain. The combination of these techniques and heuristics to suggest when the user is experiencing difficulty, enables the computer to initiate the advice process and determine the basis for the advice.

[Search These Pages] [DAI Home Page] [Comment]