基于文本-语义相似度的云制造资源功能匹配

Function Matching of Cloud Manufacturing Resources Based on Text Semantic Similarity

云制造资源功能匹配受到高计算量的影响,导致匹配性能大大降低。为了提高云制造资源功能匹配性能,提出了基于文本-语义相似度的云制造资源功能匹配。将云制造资源的概念进行抽象化,通过定义类别与属性之间的关系,构建云制造资源本体模型,利用处理函数对云制造资源进行归一化处理,得到多维功能匹配向量;根据文本向量和语义向量的位置关系,分析影响向量之间关系的主要因素,计算云制造资源文本向量与语义向量之间的相似度,通过从输入输出匹配和前提效果匹配两个方面,计算了云制造资源功能之间的相似度,实现云制造资源功能的匹配。实验结果表明,基于文本-语义相似度的云制造资源功能匹配方法在匹配效率和匹配精度方面,具有较高的匹配性能。

The effect of high computational load on cloud manufacturing resource function matching causes low matching performance. Therefore, this paper proposes a function matching method of cloud manufacturing resources based on text semantic similarity. The concept of cloud manufacturing resources was abstracted. According to the relationship between the defined categories and attributes, the ontology model of cloud manufacturing resources was established. The processing function was applied to normalize the cloud manufacturing resources to get the vector of multi-dimensional function matching. The main factors affecting the relationship between vectors were analyzed in detail by the position relationship between text vector and semantic vector, and the similarity between them was also calculated. Based on the matching of input and output and premise effect, the similarity between cloud manufacturing resource functions was calculated to achieve the matching of cloud manufacturing resource functions. The experimental results show that the method has high matching efficiency and performance, excellent matching performance.