| Summary: | 碩士 === 南台科技大學 === 資訊管理系 === 96 === In the past only the minority person positively to use the library resources, it’s unable the sufficient share use library huge resources. With flourishing development science and technology, tradition library which waited for readers borrow books develop the initiative recommendation books, the library utilization ratio therefore rises. Data mining is an analytic skill that can analyze and fund out the potential information among the original data and materials. Library own much readers borrow data, these data usually conceal the relevance of tendency to borrow books between readers. We use data mining technology find out these relevance, from relationship rule show tender characteristic, but exhume this a reader personalize adaptability books recommend, and further promote get-up the utility rate of library.
In this thesis, we use readers’ borrowing history records as the source data of mining. Each borrowing history record contains a reader ever borrowed books. Under considering interests of borrowing books, we use classification analysis with weighted interest-items to find adaptive recommendations of borrowing books from two aspects. One is to let one reader as the target of mining, and we present a method to construct a decision tree that shows whichever book items to have association with the reader. The reader’s adaptive book items which under considering interests of reader are found from the decision tree. The other is to let one book as the target of mining, and we present a method to construct a decision tree that shows whichever book items to have association with the book. The adaptive readers of borrowing the book which under considering interests of borrowing books are found from the decision tree. Finally we present a method to construct a decision tree and considering interests of borrowing books in the dynamic database. According to the first two methods, a mining system is designed and constructed for finding adaptive recommendations of borrowing books. The results of the mining can provide very useful information to plan the adaptive recommendations of borrowing books for libraries.
|
|---|
