DSpace

Now showing 1 - 3 of 3

Learning construction-planning knowledge from experience
(1997)
Dzeng, RJ
;
Chen, WT
;
土木工程學系
;
Department of Civil Engineering
The evolution of a construction product throughout ifs engineering life cycle requires many experts in different fields. A training process for a novice to become an expert requires tremendous cost and time. When an expert leaves or retires, knowledge that is accumulated through years of experience is also gone, or stored as various documents that are unorganized and hard to find. Human planners are one type of experts that require such a learning process, which is slow and inefficient. This paper uses construction-planning knowledge as an example to describe an knowledge acquisition system that extracts planning knowledge through generalization of existing construction schedules with human annotation.
Intelligent agent for supporting construction procurement negotiation
(2004)
Dzeng, RJ
;
土木工程學系
;
Department of Civil Engineering
Negotiation is commonly required in the procurement of construction materials for general contractors. However, people often reach suboptimal agreements, thereby "leaving money on the table". As E-commerce is becoming popular, an automated system that could evaluate bids, conduct negotiation to finalize the bid, and value the characteristics of negotiating parties would be useful to both contractor and suppliers. This paper presents an agent-based system that allows negotiating parties to define their preferences of negotiable issues and options, and suggests the most beneficial agreement using the genetic algorithm. Experiments were also conducted to evaluate the system's performance on effectiveness and efficiency.
Learning search pattern for construction procurement using keyword net
(2005)
Dzeng, RJ
;
Wang, SS
;
土木工程學系
;
Department of Civil Engineering
As more and more procurement websites become available on the Internet, seeking information from websites has become an essential part of a contractor's procurement undertaking. Several e-markets, specifically for construction, have also been established, including bLiquid.com and ProcureZone. However, most websites provide only two primary ways of searching for information, namely by index/menu or by keyword. Instead of relying on the primitive search engines found in most procurement websites, a search guide system could help a user's keyword search by reducing the number of keywords required to find the desired information. Our research recognized that professional procurement experience helped users more effectively carry out website information searches, by using fewer keywords. We planned to capture such experience in order to guide inexperienced users in their search. The research goal was to improve search effectiveness by guiding the user's search using three approaches, namely correction, specification and extension. Based on these three approaches, this research applied the following guides: correction; specification-by-equivalence; specification-by-detail; extension-by-time; extension-by-location; extension-by-team; and extension-by-component. The paper will describe how we classified users for learning credibility, and the learning framework for recording expert users' search patterns. Twelve professionals, using 14 procurement packages, with 64 items in total, evaluated the proposed framework. It will be demonstrated that the proposed learning keyword guide facilitated a dynamic, customized menu and indexing system, and reduced the number of keywords required for the professionals to find the information they desired.

學術出版;;Publications

Browse

Filters

Settings

Sort By

Results per page

🏛️國立陽明交通大學機構典藏

Search Results