Research On Tacit Knowledge Explicit Case Matching In Knowledge Management

The forms of knowledge are various and complex.To effectively acquire,store,organize,and apply knowledge,it is necessary to manage knowledge efficiently.Low clarity and subject dependence make tacit knowledge management and application relatively difficult.The effective organization and application of tacit knowledge has become the focus that people are increasingly concerned about.However,the indirect management customarily used in the industry for tacit knowledge is ineffective and contains a risk of degradation.Visualizing tacit knowledge as cases and providing tacit knowledge explicit case matching for knowledge users for their application requirements are the key issues to be solved in the knowledge management model and practice system.In view of this,this thesis draws on the case-based reasoning(CBR)system thinking in the artificial intelligence(AI)field to visualize tacit knowledge as a case;Based on this,considering the difference in demand characteristics of user's knowledge applications,this thesis establish aspect similarity and view similarity model respectively based on the principle of "precision priority" and "time effectiveness first",then design and propose the aspect sets reduction algorithm of tacit knowledge explicit cases.Firstly,this thesis analyzes the background of the study's topic selection.Briefly expounds the important position of knowledge as the core production material,and analyzes the lack of management and weakness of current tacit knowledge in the industry.After discussing the existing problems and their causes as well as the future development trends,the thesis targeted put forward the starting point,research content and method strategies of this study.As the research basis,the thesis reviewed the related theories such as knowledge,tacit knowledge,and CBR.And briefly discussed the principles and methods of rough set and entropy method.Then,based on the systematic thinking and technical characteristics of case-based reasoning,the dissertation puts forward the idea of explicit cases of tacit knowledge,and improves the logical structure of explicit cases.On this basis,combining the respective features of rough set and entropy weight method,this thesis designs and proposes a fusion algorithm with both advantages to calculate the tacit knowledge explicit case view.Which lays a solid foundation for the matching calculation of tacit knowledge explicit case.Finally,This thesis designs and proposes a aspect similarity algorithm for tacit knowledge explicit case with different aspect types.Based on this,combining the viewing angle of quantity closing with the viewing angle of angles approaching,the view similarity algorithm is proposed fusing the Euclidean distance and the included angle cosine.Which realizes the two dimensions of the view similarity calculation of tacit knowledge explicit case,and provides effective support for case matching under the principle of "precision priority" for knowledge users;On the other hand,considering the knowledge application requirements under the principle of "time effectiveness first",based on the knowledge representation system reduction algorithm in rough set theory,an efficient matching algorithm for tacit knowledge explicit case is designed and presented.Finally the verification of the aforementioned related models and methods was completed by example analysis.