為了能夠挖掘並且瞭解大量資料中所隱含的資訊,其中是以關聯法則為基礎的方法最為著名且廣泛地運用,而最廣為人知的應用則是藉由找出大量資料間的特殊關係來進行分類以達到預測的目的。大多數研究都著重於利用時間點的資料進行序列探勘的分類法則,然而,在實際應用的例子中,不可忽略事件與事件發生時相互呼應而產生時間的關聯性、順序性,例如:電器的使用時間、患者病症發作時間。事件資料之間具有順序性的序列資料,因其大量出現於生活中,於是我們相當注重這一議題。在本篇研究當中,我們利用時間端點表示法來表示事件與事件之間的關係,採用P-TPMiner (Probabilistic Temporal Pattern Miner)來找尋所有頻繁之時間序列,整合樣式探勘與分類方法之模型,藉此制訂分類規則的計算機制,進行預測序列資料所屬之類別。從實驗結果可得知,此序列資料分類方法不只有效率且可擴性高,並且預測結果具有可靠的正確率。 Most classification methods on sequential pattern mining are revolved about time point-based event data. Few researches utilize discovered temporal pattern for classifying. However, in many real world applications, there are relationships between events. In this paper, these relationships are simulated using a coincidence representation that extends Allen’s interval algebra. Moreover, we employ an efficient pattern mining algorithm called P-TPMiner (Probabilistic Temporal Pattern Miner) is designed to discover frequent time-interval based patterns. Exploiting the discovered temporal patterns, we proposed a classification method which is based on interval pattern. Experiments result is not only efficient and scalable, but also the accuracy is great on both synthetic and real datasets.