Browsing by Author "Meng, IH"

Now showing 1 - 5 of 5

Business agent
(2002)
Meng, IH
;
Yang, WP
;
Chen, WC
;
Chang, LP
;
資訊工程學系
The Internet and World Wide Web represent an increasingly important channel for retail commerce as well as business transactions. However, there are almost 5 billion pages or sites on the Internet and WWW. There lacks an integrated mediator business agent which is around the internet to connect between suppliers and users. Therefore, an intelligent business broking agent between supply and demand is needed for using and sharing the information efficiently and effectively. In this paper we proposed a new business agent architecture. The Business Spy Agent (BSA) captures the supply and demand information from e-commence sites automatically. Supply and Demand Analysis Mechanism (SDAM) uses NLP technologies to extract product and trading information. Domain ontology is used to classify between supply and demand and to divide them into subsets. A benefit model is proposed to handle the pairing between sub-supply and sub-demand. And a divide-and-conquer algorithm is proposed to handle the whole matching between supply and demand. In the negotiation process, the architecture uses NLP and template to produce negotiation text to handle negotiation through mail. Finally, Hidden Business Mining Mechanism (HBMM) adopts data mining technology to achieve hidden business mining. The architecture covers the four process of buying behavior including support and need identification, Product brokering, Merchant brokering, Negotiation.
Integrated business agents for processing free text information
(2004-03-01)
Meng, IH
;
Tseng, SM
;
Yang, WP
;
資訊工程學系
;
Department of Computer Science
The Internet functions as an increasingly important channel for retailing commerce and business transactions. Although nearly five billion web sites exist on the World Wide Web, an integrated mediator, called a business agent, is sought to negotiate between suppliers and buyers. Such an intelligent business broker is thus necessary to support efficient and effective sharing of information. This work proposes an entirely new business agent architecture comprised of five elements, namely Business Spy Agent, Supply and Demand Analysis, Supply and Demand Classification, Matching and Negotiation, and Hidden Business Mining. The proposed architecture encompasses four trading processes, including Supply and demand identification, product brokering, merchant brokering and negotiation. The architecture introduces the notion of ontology to increase the precision of classification and more the effectiveness of negotiation. Experiments involving the proposed business agent show a significant successful pairing rate of 82% among suppliers and buyers. Simulation results indicate that the options, including Negotiable, Designated Brand and Split Demand, affect the match ratio differently from various perspectives.
Text summarization using a trainable summarizer and latent semantic analysis
(2005-01-01)
Yeh, JY
;
Ke, HR
;
Yang, WP
;
Meng, IH
;
資訊工程學系
This paper proposes two approaches to address text summarization: modified corpus-based approach (MCBA) and LSA-based T.R.M. approach (LSA + T.R.M.). The first is a trainable summarizer, which takes into account several features, including position, positive keyword, negative keyword, centrality, and the resemblance to the title, to generate summaries. Two new ideas are exploited: (1) sentence positions are ranked to emphasize the significances of different sentence positions, and (2) the score function is trained by the genetic algorithm (GA) to obtain a suitable combination of feature weights. The second uses latent semantic analysis (LSA) to derive the semantic matrix of a document or a corpus and uses semantic sentence representation to construct a semantic text relationship map. We evaluate LSA + T.R.M. both with single documents and at the corpus level to investigate the competence of LSA in text summarization. The two novel approaches were measured at several compression rates on a data corpus composed of 100 political articles. When the compression rate was 30%, an average f-measure of 49% for MCBA, 52% for MCBA + GA, 44% and 40% for LSA + T.R.M. in single-document and corpus level were achieved respectively. (C) 2004 Elsevier Ltd. All rights reserved.
The CACTUS object server: Design and implementation issues
(1998)
Meng, IH
;
Yang, WP
;
Lin, SM
;
Chen, MA
;
Chen, SK
CACTUS is a compact and reliable object storage system based an peer-to-peer architecture with distributed transaction processing capability. The kernel is implemented with the multi-thread mechanisms to provide a high performance multi-transaction environment. All sites, installed with CACTUS, of the networked workstations are on an equal footing. The system can handle local and remote transactions including accessing remote objects or processing remote accesses. In this paper. we give an architectural overview of CACTUS and discuss some implementation issues. It mentions the special contributions such as transient large objects, the coarser lack granularity and its associated protocol. A cost model is developed to demonstrate that the new scheme yields performances which are superior in most common cases and inferior under certain situations.
The design and implementation of chinese question and answering system
(2003)
Meng, IH
;
Yang, WP
;
資訊工程學系
;
Department of Computer Science
Information retrieval has been proven effective in discovering specific passages within large collections of documents in response to a user query. Users frequently obtain brief answers to specific questions instead of obtaining the whole documents. The QA system can process the question statement in Chinese natural language fashion and find out the implicit intention of the user query, This study proposes a Chinese Question Answering system based on HowNet and Autotag. The experiment collected 900 Chinese News items from www.chinatimes.com and presented an excellent MRR (Mean Reciprocal Rate) value at 0.84.