工作階段知識支援：探勘與支援工作相關知識

Abstract

組織主要是處理知識密集工作來達成組織目標，而在工作為基礎的環境中，知識工作者常常以階段性完成工作。在工作執行過程中，不同階段有不同的工作需求。因此如何根據知識工作者在不同工作階段之需求，提供工作相關知識，為建構知識管理系統之重要議題。本研究改良階層式凝聚分群演算法，提出一工作階段探勘方法，從歷史工作資料發掘工作階段知識需求。依據所萃取之工作階段知識需求，進而建構工作階段需求特徵檔，提供知識工作者執行工作時各階段之相關知識。本文最後進行實驗比較以評估所提的方法在提供知識支援之有效性。

Organizations mainly conduct knowledge-intensive tasks to achieve organizational goals. In such task-based environments, knowledge workers usually accomplish their tasks by stages, while their task-needs may be different at various stages of task performance. Accordingly, an important issue of deploying Knowledge Management Systems is to extract knowledge from the historical task and further support task-relevant knowledge according to workers’ task-needs at different task-stages. This work proposed a task-stage mining method for discovering task-stage needs from historical task executions. The proposed method adopts information retrieval techniques and a modified hierarchical agglomerative clustering (HAC) algorithm to identify task-stage needs by analyzing codified knowledge (documents) accessed or generated during task performance. Task-stage profiles are generated to model workers’ task-stage needs and are used for delivering task-relevant knowledge at various task stages. Finally, we conduct empirical evaluations to demonstrate that the proposed method provides effective knowledge support based on task-stages.