An Approach to a Knowledge Reconstruction Engine for Supporting Event Planning

The main goal of our research is to establish “methodology for investigation of event” and to construct “a knowledge reconstruction system” to provide event planners with “chances” to design effective and attractive events. The methodology described here is to articulate gaps between event planners’ intention and event visitors’ mental impression at real event sites. Visitors’ interactions with event objects were observed and their verbal reports (protocol data) and their actions were recorded with wearable computers and ordinary digital video camera, incorporation with Dentsu Inc. Their cognitive processes were analyzed with retrospective report method of protocol analysis. In this paper, we are going to describe the methodology adopted for investigating Visitors’ Mental Transition (VMT) in the real world and examples of obtained results. From analysis of the data, we obtained a prospect that our microscopic approach is useful and effective toward event-planning in the real world. Concepts and prototype of “knowledge reconstruction system” are described. Introduction Every year, event-planning companies hold various events. So far event-planning is conducted with implicit knowledge of experienced planners and effectiveness of events is measured only by questionnaires. In actual situations, it is said that planners cannot obtain adequate and proper knowledge for future planning from statistical data derived from questionnaires because: The questions are composed of only what the planners pay attention to in advance. That means they fail to obtain something unexpected. The planners cannot understand how and why the data was produced. It makes it difficult for the planners to utilize the knowledge. Even though free-answer questionnaires are adopted, at real event sites it is difficult to let the visitors answer the questions in detail. That means planners are unable to evaluate events they design. Planners need to know what visitors to events actually Copyright c 2002, American Association for Artificial Intelligence (www.aaai.org). All rights reserved. feel and how they behave when they are at the event booth to construct strategies for next event-planning. This is because knowledge itself cannot be applied to real situations if it does not have a context where it was produced(Fischer & Ostwald 2001). Though quantitative data is powerful to form a conclusion, it should be accompanied by qualitative data as a reason so that planners can utilize the knowledge. Qualitative data and quantitative data should complement with each other. In this paper, we are going to propose a methodology to grasp visitors’ mental transitions (VMT) and “a knowledge reconstruction system” through applying the framework of creativity support to actual event designing works. As its first step, experiments were conducted at actual event sites: “Tokyo Motor Show 2001” and “World PC Expo 2001”, in cooperation with Dentsu Inc. Visitors’ interactions with the event objects were observed and their verbal reports (protocol data) and behavior were recorded. And furthermore, concepts and a prototype of “knowledge reconstruction system” are described.