Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

An approach to task-oriented knowledge recommendation based on multi-granularity fuzzy linguistic method

An approach to task-oriented knowledge recommendation based on multi-granularity fuzzy linguistic... Purpose – In organizations, knowledge intensive activities are mainly task oriented. Finding relevant completed tasks to the new task and providing task-related knowledge to workers facilitate the knowledge reuse. However, relevant tasks are not easily found in the huge amount of completed tasks. The purpose of this paper is to assist the worker to find the required knowledge for the task at hand by reusing the knowledge related to relevant competed tasks. Design/methodology/approach – First, the task profile is constructed. Relevant degrees to categories which tasks to are derived by multi-granularity fuzzy linguistic method. The stages of completed tasks are identified by the modified KNN method. Second, similar completed tasks on categories are retrieved and then the relevant tasks are selected from the retrieved similar tasks by multi-granularity fuzzy linguistic method. Third, the worker’s current task stage is derived by calculating the similarity between the rated knowledge and the knowledge in the stage of completed tasks. Finally, the knowledge is recommend based on stage relevance, relevance of the completed tasks and importance of the knowledge. Findings – The proposed method helps the worker find the knowledge related to the task at hand by finding and reusing the completed tasks. The experimental results show that the proposed method performs well and can fulfill the worker’s’ knowledge needs. The use of the linguistic term set with preferred granularities instead of precise numbers facilitates the expression of the opinions. The recommendation stage by stage makes the knowledge recommended more precisely. The obtained linguistic weight of the knowledge makes the recommended results understood more easily than the numerical values. Research limitations/implications – In the study, the authors just focus on the codified knowledge recommendation. However, there is another kind of knowledge named tacit knowledge, which exists in the mind of the experts. The constructing and updating of the expert profile can be investigated. Meanwhile, the new recommendation method which considers more factors also needs to be studied further. Practical implications – The paper includes implications for the development of the knowledge management system. The proposed approach can be applied as a tool of knowledge sharing. It facilitates the finding of the knowledge that is related to the task at hand. Originality/value – The paper provides new ways to find the relevant tasks and the related knowledge to the task at hand. Meanwhile, the new method to recommend the knowledge stage by stage is also proposed. It expands the research in the knowledge sharing and knowledge recommendation. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Kybernetes Emerald Publishing

An approach to task-oriented knowledge recommendation based on multi-granularity fuzzy linguistic method

Li, Ming; Yuan, Mengyue; Xu, Yingcheng
Kybernetes , Volume 44 (3): 15 – Mar 2, 2015
Download PDF
15 pages

Loading next page...
 
/lp/emerald-publishing/an-approach-to-task-oriented-knowledge-recommendation-based-on-multi-kF01sCNPqH

References (28)

Publisher
Emerald Publishing
Copyright
Copyright © Emerald Group Publishing Limited
ISSN
0368-492X
DOI
10.1108/K-10-2014-0207
Publisher site
See Article on Publisher Site

Abstract

Purpose – In organizations, knowledge intensive activities are mainly task oriented. Finding relevant completed tasks to the new task and providing task-related knowledge to workers facilitate the knowledge reuse. However, relevant tasks are not easily found in the huge amount of completed tasks. The purpose of this paper is to assist the worker to find the required knowledge for the task at hand by reusing the knowledge related to relevant competed tasks. Design/methodology/approach – First, the task profile is constructed. Relevant degrees to categories which tasks to are derived by multi-granularity fuzzy linguistic method. The stages of completed tasks are identified by the modified KNN method. Second, similar completed tasks on categories are retrieved and then the relevant tasks are selected from the retrieved similar tasks by multi-granularity fuzzy linguistic method. Third, the worker’s current task stage is derived by calculating the similarity between the rated knowledge and the knowledge in the stage of completed tasks. Finally, the knowledge is recommend based on stage relevance, relevance of the completed tasks and importance of the knowledge. Findings – The proposed method helps the worker find the knowledge related to the task at hand by finding and reusing the completed tasks. The experimental results show that the proposed method performs well and can fulfill the worker’s’ knowledge needs. The use of the linguistic term set with preferred granularities instead of precise numbers facilitates the expression of the opinions. The recommendation stage by stage makes the knowledge recommended more precisely. The obtained linguistic weight of the knowledge makes the recommended results understood more easily than the numerical values. Research limitations/implications – In the study, the authors just focus on the codified knowledge recommendation. However, there is another kind of knowledge named tacit knowledge, which exists in the mind of the experts. The constructing and updating of the expert profile can be investigated. Meanwhile, the new recommendation method which considers more factors also needs to be studied further. Practical implications – The paper includes implications for the development of the knowledge management system. The proposed approach can be applied as a tool of knowledge sharing. It facilitates the finding of the knowledge that is related to the task at hand. Originality/value – The paper provides new ways to find the relevant tasks and the related knowledge to the task at hand. Meanwhile, the new method to recommend the knowledge stage by stage is also proposed. It expands the research in the knowledge sharing and knowledge recommendation.

Journal

Kybernetes – Emerald Publishing

Published: Mar 2, 2015

There are no references for this article.