Automated user modeling for intelligent interface

doi:10.1080/10447319609526151

1996-07-01

PRE

Kenichi Yoshida

Hiroshi Motoda

DOI：10.1080/10447319609526151

原文链接

原文求助

摘要

En 中文

The analysis of user behavior is one important function of the user-adaptive interface. Such analysis enables understanding of the user's intention and releases the user from tedious tasks often required when using a nonadaptive interface. The acquisition of the user behavior model is crucial. Most studies meant to develop a user-adaptive interface system only analyze the sequence of user behaviors (i.e., command sequence) from which to automate the repetitions. Because the command sequence sometimes does not typify the user's behavior, the user model constructed only from the command sequence does not adequately reproduce the user behavior. This article presents a new framework that also analyzes the computational processes activated by the user commands to build the user behavior model. An important feature of the proposed framework is the analysis of data dependency between the user commands. A user-adaptive interface system, ClipBoard, was developed to show the adequacy of this framework. It analyzes the I/O relations between commands in the past task history, selects the next command, and creates scripts that enable complex task execution by a single command.