基于類比設(shè)計的專利知識挖掘算法
發(fā)布時間:2018-04-27 08:45
本文選題:專利挖掘 + 類比設(shè)計。 參考:《計算機集成制造系統(tǒng)》2017年11期
【摘要】:為解決發(fā)明專利因缺少完善的理論體系和相關(guān)技術(shù)文獻而難以實現(xiàn)技術(shù)突破和創(chuàng)新的難題,提出一種基于類比設(shè)計的專利挖掘算法。以具有相同特征和相似功能的成熟技術(shù)專利為數(shù)據(jù)源進行文本挖掘,首先,從數(shù)據(jù)源中提取實現(xiàn)功能和問題解決方案(PSC),建立基于PSC的詞頻—逆向文件頻率(TF-IDF)值的向量空間模型;然后,根據(jù)專利文獻間的相似度制成基于PSC的專利地圖;最后,分別對PSC進行可行性分析,根據(jù)分析結(jié)果選擇合理的方法,用類比的思想進行技術(shù)創(chuàng)新。給出了專利知識挖掘應(yīng)用系統(tǒng)的架構(gòu)設(shè)計,并采用統(tǒng)一建模語言描述了專利挖掘系統(tǒng)的動態(tài)執(zhí)行過程,獲得了專利挖掘系統(tǒng)的時序圖。應(yīng)用系統(tǒng)采用關(guān)系型數(shù)據(jù)庫MySQL存儲數(shù)據(jù),運用Java編程語言開發(fā)了應(yīng)用系統(tǒng),以無線充電技術(shù)專利和無線傳感技術(shù)專利為源數(shù)據(jù)測試系統(tǒng)。實驗結(jié)果表明,所提算法比基于專利的類比方法具有更好的時間性能,并能獲得更具創(chuàng)新性的創(chuàng)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.
【作者單位】: 貴州大學現(xiàn)代制造技術(shù)教育部重點實驗室;貴州大學機械工程學院;
【基金】:國家自然科學基金資助項目(61640209,51475097) 貴州省科技計劃資助項目(黔科合LH字[2016]7433號,黔科合JZ字[2014]2001號,黔科合人才[2015]4011號,黔科合JZ字[2014]2004號,黔科合人字[2015]13號)~~
【分類號】:TP311.52;TP391.1
【相似文獻】
相關(guān)期刊論文 前10條
1 丁月華,文貴華,郭煒強;基于核向量空間模型的專利分類[J];華南理工大學學報(自然科學版);2005年08期
2 王萌,何婷婷,張偉;基于概念向量空間模型的中文自動文摘系統(tǒng)[J];計算機工程與應(yīng)用;2005年01期
3 張玉連;張敏;張波;;一種擴展的向量空間模型-隱含語義索引模型研究[J];燕山大學學報;2006年01期
4 李雪峰;劉魯;張f,
本文編號:1810040
本文鏈接:http://www.sikaile.net/kejilunwen/ruanjiangongchenglunwen/1810040.html
最近更新
教材專著