ABSTRACT
The most fundamental innovation of products is the innovation of functional principle. Learning from the functional information of existing patents plays an important role in the design of product innovation and patent circumvention. This paper proposed a similar patent search method of fusion function information. The method firstly screening candidate words, the candidate word is the word which is of great contribution to judge whether a sentence contains functional information; the short text classification method based on the candidate words was proposed to judge the functional sentences, and the functional expression rules were combined to determine the patent's functional phrase. Finally, based on the functional expression sentences, this paper proposed a sentence similarity computing method based on word2vec and syntactic dependency to search for the patents which have similar functional information. Experiments show that the proposed method has a certain accuracy and validity in the automatic extraction of functional information and search for similar patent.
- Yanhong Liang,Runhua,Tan,Jianhong Ma, Study on patent text classification for product innovative design{J}. Computer Integrated Manufacturing Systems, 2013,19(02):382-390.Google Scholar
- Zhaoxia Wang,Qingying Qiu, Peien Feng,et al. Information extraction method of technical solution from mechanical product patent{J}. Journal of Mechanical Engineering, 2009,45(10):198-206.Google ScholarCross Ref
- Yiqun Chen,Ruqi Zhou,Weiheng Zhu,et al. Mining patent knowledge for automatic keyword extraction{J}. Journal of Computer Research and Developmen, 2016,53(08):1740-1752.Google Scholar
- Feng Liu,Ruihong Wu,Chuan Xu,et al. Keyword extraction of patent document:an improved approach{j}. Journal of Intelligence, 2014,33(12):36-40.Google Scholar
- Shuanglong YANG,Xueqiang Lv,Zhuo Li,et al. Automatic recognition of terms in chinese patent literature{J}. Journal of Chinese Information Processing, 2016,30(03):111-117+124.Google Scholar
- Zhen Zeng, Xueqiang Lv,Zhuo Li. A field terminology extraction method for patent abstracts{J}. Computer Applications and Software, 2016,33(03):48-51.Google Scholar
- Dongpu Sun, Minghua Zhu, Hongfei Lin. Chinese patent attribute-value extraction technology and its application{J}. Computer Engineering and Science, 2016,(04):800-806.Google Scholar
- Apei Hu, Jing Zhang,Xiaoping Lei,et al. A review of technical topic analysis based on text mining{J}. Journal of Intelligence, 2013,32(12):88-92+61.Google Scholar
- Chao Yang,Donghua Zhu,Xuefeng Wang,et al. Technical topic analysis in patents:SAO-based LDA modeling{J}. Library and Information Service, 2017,61(03):86-96.Google Scholar
- Lingen Meng,Ying Li,Yanqing He,et al. Research on patent topics extraction based on semantic role labeling{J}. Library and Information Service, 2014,(19):19-24.Google Scholar
- Huitao Fu, Moydin Kamil. Study and design of an improved text feature selection method{J}. Computer Applications and Software, 2011,28(04):239-241.Google Scholar
- Zhu Xin,Yajian Zhou. Study and improvement of mutual information for feature selection in text categorization{J}. Journal of Computer Applications, 2013,33(S2):116-118+152.Google Scholar
- Junfei Qiao,Sanyi Li,Wenjing Li. Mutual information based weight initialization method for sigmoidal feedforward neural networks{J}. Neurocomputing, 2016. Google ScholarDigital Library
- Xiaojun Zhao,Pengjian Shang,Aijing Lin. Transfer mutual information: A new method for measuring information transfer to the interactions of time series{J}. Physica A: Statistical Mechanics and its Applica-tions, 2016.Google Scholar
- Jiali Du,Ppingfang Yu. Towards linear parsing of english garden path sentences:--an analysis based on stanford parser{j}. Ludong University Journal (Philosophy and Social Sciences Edition), 2017,(05):39-46.Google Scholar
- Min Zhao.TRIZ Enhancement and Practical Applications{M}. Beijing:China Machine Press, 2016.Google Scholar
- Duanming Li,Lian Wei. Research on heterogeneous resource ontology construction based on FCA and Word2vec{J}. Information Science, 2017,35(03):69-75.Google Scholar
- Dongchuan Huang,Jiali Wang. An approach on Chinese microblog entity linking combining baidu encyclopaedia and word2vec{J}. Procedia Computer Science, 2017. Google ScholarDigital Library
- Fernando Enríquez,José A. Troyano,Tomás López-Solaz. An approach to the use of word embeddings in an opinion classification task{J}. Expert Systems With Applications, 2016,66. Google ScholarDigital Library
- Xiao Li,Hui Xie, Lijie Li. Research on sentence semantic similarity calculation based on Word2vec{J}. Computer Science, 2017,(09):256-260.Google Scholar
Index Terms
- Similar Patent Search Method Based on a Functional Information Fusion
Recommendations
An investigation of decompounding for cross-language patent search
SIGIR '11: Proceedings of the 34th international ACM SIGIR conference on Research and development in Information RetrievalDecompounding has been found to improve information retrieval (IR) effectiveness in general domains for languages such as German or Dutch. We investigate if cross-language patent retrieval can profit from decompounding. This poses two challenges: i) ...
A target intention recognition method based on information classification processing and information fusion
AbstractIntention recognition of non-cooperative target is an important basis for battlefield command decision-making. Recent advances suggest recognizing target intention from a perspective of data-driven. However, existing data-driven models do not ...
Highlights- An artificial neural network model with information classification processing and information fusion is constructed for target intention recognition.
- An interactive feature-level fusion method is proposed to model the fine-grained ...
Cross-language patent matching via an international patent classification-based concept bridge
Patent documents with sophisticated technical information are valuable for developing new technologies and products. They can be written in almost any language, leading to language barrier problems during retrieval. Traditionally, cross-language ...
Comments