Font Size: a A A

The Chinese Patent Retrieval System Based On Pragmatic Information

Posted on:2012-01-20Degree:MasterType:Thesis
Country:ChinaCandidate:L P WuFull Text:PDF
GTID:2178330335960777Subject:Pattern Recognition and Intelligent Systems
Abstract/Summary:PDF Full Text Request
Patent information is the crystallization of human intelligence. It contains the most important technology achievement of almost every application field such as economic development, technology innovation and strategic decision. Nowadays, patent information has become the most necessary information resource in every country's economy development.This paper combined pragmatic information with patent information retrieval and gave pragmatic meaning to patent retrieval based on traditional information retrieval, which was searched by key words, in order to improve recall and precision ratio.The main contents of this paper include three points as follows:(1)According to the International Patent Classification rules, we collected a large of patent documents and constructed the patent corpus including the pragmatic information by hand, which laid the root for later research.(2)Through great quantity of research about pragmatic information, we defined the concept of pragmatic information in patent corpus and come up with the extraction methods and rules about it. The extracted pragmatic information was added to patent corpus, which was used for patent retrieval in order to improve the retrieval accuracy.(3)On the basis of technologies mentioned above, we constructed a Chinese patent retrieval system on the platform of QA system. The system can realize the efficient retrieval on patent information. Some experiments using the proposed method had been carried out, and the results showed that the precision and recall of patent retrieval based on the pragmatic information are higher than the one without using it.At the end of the paper, it is the conclusion of our work and the expectation of the further research in the future.
Keywords/Search Tags:pragmatic information, information extraction, NLP, patent retrieval
PDF Full Text Request
Related items