| 摘要: |
| 针对已有基于模式结构的模式匹配方法的局限性,提出了一种利用模式结构信息和已有匹配知识的模式匹配模型——SKM(schema and reused knowledge based matching model).在该模型中,借鉴神经网络元之间的影响过程实现语义匹配推理;通过重用已有匹配知识深入挖掘模式元素之间的深层语义关系;基于已有匹配知识自动缩减不确定阈值区之间来确定匹配阈值,有效减少人工干涉;给出了简单的确定模式元素之间匹配关系的方法;同时通过自适应式迭代模型,进一步挖掘求精已有匹配知识.实验结果表明,SKM模型切实可行. |
| 关键词: 模式匹配 知识重用 语义推理 数据集成 数据挖掘 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant No.60673139 (国家自然科学基金); the National High-Tech Research and Development Plan of China under Grant No.2008AA01Z146 (国家高技术研究发展计划(863)) |
|
| SKM: A Schema Matching Model Based on Schema Structure and Known Matching Knowledge |
|
SHEN De-Rong,YU En-Yun,ZHANG Xu,KOU Yue,NIE Tie-Zheng,YU Ge
|
| Abstract: |
| To make up the limitations of existing schema matching methods based on schema structure information, a schema matching model called SKM (schema and reused knowledge based matching model) is proposed based on schema structure information and known matching knowledge. In this model, neural network influence procedure is imitated to realize semantic matching reasoning. The known matching knowledge is reused to mine the deep semantic relation between two schemas. It is also reused to curtail uncertain threshold interval automatically to specify the threshold for decreasing manual intervention. A simple approach of specifying matching relation between two matching elements is given. In the meantime, a self-learning adaptive and iterative model is presented to mine and enrich the known matching knowledge. Experimental results show that the SKM is feasible. |
| Key words: schema matching knowledge reuse semantic inference data integration data mining |
