User's Personal Preferences Research Articles

1208 注目点を考慮した嗜好の探索法

We propose a scheme to evaluate design parameters based on a user's personal preferences. The scheme works through an interaction between the user and a computer system. The objective of the scheme is to help a layman set design parameters by simple evaluation of displayed samples. An important feature of this method is that the design attributes which a user pays more attention estimated with Rough Sets Theory and are reflected while refining the search. New design candidates are generated by the user's evaluation of design samples generated at random. While values of already evaluated attributes are fixed in the refined samples, the unevaluated ones are generated at random. This interaction continues until the samples converge to a satisfactory design. Thus, a personal and subjective feature is evaluated by this efficient search process. This method is applied to camera work and suitable lighting for 3D production model and a comparison with Interactive GA will be demonstrated by an operational experiment.

An Intelligent Agent for Prioritizing E-Mail Messages

The proliferation of telecommunication networks, like Internet and Bitnet, has promoted mail e-mail into a viable business communication tool with widespread use that traverses all levels of management. In some organizations, e-mail users are being overwhelmed with a barrage of useless messages or electronic junk mail. This interferes with a user's information processing capability and causes a negative effect on usefulness of this communication tool. This paper addresses the issue of time management by reducing information overload in email. A knowledge-based agent, called AIMS, was developed to prioritize e-mail messages. AIMS is different from other systems in three ways: 1 it does not burden users with the task of creating or maintaining message prioritizing rules, 2 it uses a user's personal knowledge or preferences with organizational considerations for prioritizing messages, and 3 it was evaluated at an academic institution with a group of 46 e-mail users who found the prioritized list generated by AIMS highly accurate.