基于类比设计的专利知识挖掘算法

发布时间：2018-04-27 08:45

本文选题：专利挖掘 + 类比设计　；参考：《计算机集成制造系统》2017年11期

【摘要】：为解决发明专利因缺少完善的理论体系和相关技术文献而难以实现技术突破和创新的难题,提出一种基于类比设计的专利挖掘算法。以具有相同特征和相似功能的成熟技术专利为数据源进行文本挖掘,首先,从数据源中提取实现功能和问题解决方案(PSC),建立基于PSC的词频—逆向文件频率(TF-IDF)值的向量空间模型;然后,根据专利文献间的相似度制成基于PSC的专利地图;最后,分别对PSC进行可行性分析,根据分析结果选择合理的方法,用类比的思想进行技术创新。给出了专利知识挖掘应用系统的架构设计,并采用统一建模语言描述了专利挖掘系统的动态执行过程,获得了专利挖掘系统的时序图。应用系统采用关系型数据库MySQL存储数据,运用Java编程语言开发了应用系统,以无线充电技术专利和无线传感技术专利为源数据测试系统。实验结果表明,所提算法比基于专利的类比方法具有更好的时间性能,并能获得更具创新性的创新方案。
[Abstract]:In order to solve the problem that the patent of invention is difficult to realize the breakthrough and innovation due to the lack of perfect theoretical system and related technical documents, a patent mining algorithm based on analogical design is proposed. Text mining is carried out with mature technology patent with the same characteristics and similar functions. Firstly, the realization function and problem solving scheme are extracted from the data source, and the vector space model of word frequency reverse file frequency and TF-IDF value based on PSC is established. Then, the patent map based on PSC is made according to the similarity between patent documents. Finally, the feasibility analysis of PSC is carried out, and the reasonable method is selected according to the results of the analysis, and the technology innovation is carried out with the idea of analogy. The architecture design of patent knowledge mining application system is given, and the dynamic execution process of patent mining system is described by using unified modeling language, and the timing diagram of patent mining system is obtained. The application system uses relational database MySQL to store data, and uses Java programming language to develop the application system. The data testing system is based on wireless charging technology patent and wireless sensing technology patent. The experimental results show that the proposed algorithm has better time performance than the patent-based analogy method and can obtain more innovative and innovative schemes.
【作者单位】：贵州大学现代制造技术教育部重点实验室;贵州大学机械工程学院;
【基金】：国家自然科学基金资助项目(61640209,51475097) 贵州省科技计划资助项目(黔科合LH字[2016]7433号,黔科合JZ字[2014]2001号,黔科合人才[2015]4011号,黔科合JZ字[2014]2004号,黔科合人字[2015]13号)~~
【分类号】：TP311.52;TP391.1

【相似文献】