DocumentCode :
3658456
Title :
Verification of Patent Document Similarity of Using Dictionary Data Extracted from Notification of Reasons for Refusal
Author :
Kyoko Yanagihori;Kazuhiko Tsuda
Author_Institution :
Grad. Sch. of Bus. Sci., Univ. of Tsukuba, Tokyo, Japan
Volume :
3
fYear :
2015
fDate :
7/1/2015 12:00:00 AM
Firstpage :
349
Lastpage :
354
Abstract :
Claims are written very difficult to read by the convention. Therefore, Claim sentences are difficult to understand. Because, compound nouns are frequent in the patent documents. When the degree of similarity of the patent document is measured using only morphological, most documents are similar. Characteristic nouns such as "features", "device", "means" and "method" have appeared for most of the patent documents. It is not possible to make an efficient search. Thus, It is necessary to apply the search using the compound nouns in the patent document. However, there is a disadvantage that the compound noun is less frequently appear in the document. To make up for this disadvantage, it is sufficient that the compound noun is to be identified as similar. Therefore, we decided to take advantage of the "notice of reasons for refusal ". The notice of reasons for refusal has patent examiner clearly contrasts point. Mostly shows a compound noun in the portion of the invention. Dictionary data of a similar compound noun was made based on this. Compound nouns and verbs were extracted from claims as a dependence phrase. On the basis of dictionary data, similarities of documents are confirmed. As a result, the difference between the similar document numbers is indicated by presence or absence of phrases aggregation. Furthermore, it is effective to take advantage of the "notice of reasons for refusal" that are automatically stored when patent refusal causes.
Keywords :
"Patents","Compounds","Authentication","Dictionaries","Technological innovation","Aggregates","Linear discriminant analysis"
Publisher :
ieee
Conference_Titel :
Computer Software and Applications Conference (COMPSAC), 2015 IEEE 39th Annual
Electronic_ISBN :
0730-3157
Type :
conf
DOI :
10.1109/COMPSAC.2015.162
Filename :
7273383
Link To Document :
بازگشت