計畫名稱: 計畫名稱:應用知識導向推薦技術於互動式代理人系統之研 究 - 以eNovelAdvisor為例
97-2221-E-468-005-
研究計畫英文摘要:
Keywords : recommender system, knowledge-based recommendation, interactive software agent, eNovelAdvisor
The concept of recommender systems is to provide advice to users about information from a large number of data. The well-known types of recommender systems are collaborative-, content-based, and knowledge-based type. The third type, knowledge- based recommender system, uses knowledge of users and items/products to perform a knowledge-based filtering technology to generating an advice. Studies have shown that knowledge-based recommender systems can be well applied on complex products such as financial services, digital products, and literatures, because users purchasing or searching these complex products need the explicit knowledge.
This proposal is aimed to investigate how to apply knowledge-based recommendation in the interactive software agent system. Furthermore, this project will develop an eNovelAdvisor software agent for an e-Novel system. The e-Novel system contains a number of novels for the Internet readers. A reader can firstly get a list of novels with simple criteria. As the reader chooses one novel, the eNovelAdvisor will present the novel for him and list novels that fulfill certain reader’s quality requirements. Moreover, eNovelAdvisor explains solutions for the reader if he needs. The explicit interaction between eNovelAdvisor and the reader is able to help him find novels.