摘要
针对传统知识匹配过程耗时长、效率低,不适用于大规模知识库匹配计算问题,研究隐性知识外显案例适配优化算法。首先,采用毕达哥拉斯模糊集(PFS)对知识属性值进行处理,建立知识表达系统;接着,运用K-Means算法对模糊C均值聚类算法(FCM)进行改进,压缩匹配空间、提升案例匹配效率;而后,基于PFS相关系数求解知识供需间的视图相似度,从而获得适配案例集,在此基础上构建随机森林适配模型,并采用粒子群算法对其优化,以确保适配效果。进一步通过与传统算法进行对比实验,验证证明优化算法具有比较优势。
Aiming at the time-consuming and low-efficiency of traditional knowledge matching process,which is not suitable for large-scale knowledge base matching calculation problem,the tacit knowledge explicit case adaptation optimization algorithm is studied.First,Pythagorean fuzzy set(PFS)is used to process the knowledge attribute values to establish a knowledge expression system;then,the K-Means algorithm is used to improve the fuzzy C-means clustering algorithm(FCM)to compress the matching space and improve the case matching efficiency;finally,based on the PFS correlation coefficient,the view similarity between knowledge supply and demand is calculated to obtain the adaptation case set.On this basis,the random forest adaptation model is constructed,and the particle swarm algorithm is used to optimize it to ensure effect.Further comparison experiments with traditional algorithms prove that the optimization algorithm has comparative advantages.
作者
张建华
杨俊晓
曹子傲
刘艺琳
Zhang Jianhua;Yang Junxiao;Cao Ziao;Liu Yilin(School of Management,Zhengzhou University,Zhengzhou 450001,China)
出处
《科技管理研究》
CSSCI
北大核心
2022年第18期136-143,共8页
Science and Technology Management Research
基金
国家社会科学基金项目“隐性知识深度服务体系研究”(19BTQ035)。
关键词
隐性知识
案例适配
随机森林
毕达哥拉斯模糊集
粒子群优化
模糊C均值
tacit knowledge
case adaptation
random forest
Pythagorean fuzzy sets
particle swarm optimization
fuzzy C-means
