Research On Patent Knowledge Mining Technology And Application Of Mechanical And Electrical Products

Patent is one of the important way to record the progress of human civilization,the patent knowledge mining is an important research hotspot in the field of text mining.Nowadays the patent knowledge discovery machine learning algorithms and models are very mature.The patent documents about mechanical and electronic products contain rich product optimization and innovation of information technology,which has an important value of reference and inspiration to improve the products and innovation.How to acquire and represent patent knowledge effectively is one of the key technologies in patent auxiliary product innovation.Without scientific theoretical system and enough technical paper,it is hard to make an innovation in a new technology field.In order to resolve the problem,an algorithm of patent mining based on the new technology using analogy is designed.The source data are patents in mature technology whose properties or functions are similar to the new technology.Firstly,extract Problem Solution Concepts(PSCs)from source data and create Vector Space Model(VSM)based on PSCs’ TF-IDF values.Then,build a patent map based on the similarity among the patents.Finally,calculate the opportunity score and choose the PSC which has a high opportunity score to create a new innovation scheme on the new technology using analogy.The algorithm proposed in the article is measured by a patent mining test between wireless charger patents and wireless sensing patents.It turns out that the suggested algorithm can create a more innovational scheme than what the comparative algorithm can do.In this article,a patent mining system has been designed and implemented with the object-oriented software design methods.The system uses the MVC three-tier architecture model for system architecture,using Browser/Server model for the communication between the terminal and the server...