Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë
ÇѱÛÁ¦¸ñ(Korean Title) |
ƯÇã ¹®¼ ÅؽºÆ®·ÎºÎÅÍÀÇ ±â¼ú Æ®·»µå ŽÁö¸¦ À§ÇÑ ¾ð¾î ¸ðµ¨ ¹× ´Ü¼ ±â¹Ý ±â°èÇнÀ ¹æ¹ý |
¿µ¹®Á¦¸ñ(English Title) |
A Language Model and Clue based Machine Learning Method for Discovering Technology Trends from Patent Text |
ÀúÀÚ(Author) |
Àü¿µ½Ç
±è¿µÈ£
Á¤À±Àç
·ùÁöÈñ
¸Í¼ºÇö
Yingshi Tian
Youngho Kim
Yoonjae Jeong
Jihee Ryu
Sunghyon Myaeng
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 36 NO. 05 PP. 0420 ~ 0429 (2009. 05) |
Çѱ۳»¿ë (Korean Abstract) |
ƯÇã ¹®¼´Â °úÇбâ¼ú ¹ßÀüÀ» ŽÁöÇÏ°í ±âÁ¸ Æ®·»µå¸¦ ÀÌÇØÇÔÀ¸·Î½á ¹Ì·¡ÀÇ Æ®·»µå¸¦ ¿¹ÃøÇϴµ¥ À¯¿ëÇÑ ÀÚ¿øÀÌ´Ù. º» ¿¬±¸¿¡¼´Â ´ÜÀ§ ±â¼úÀ» ¡°¹®Á¦Á¡¡±°ú ¡°ÇØ°á¹æ¹ý¡±À¸·Î ±¸¼ºµÇ¾î ÀÖ´Ù°í º¸°í, ¾ð¾îÀû ´Ü¼(linguistic clue)¿Í ¾ð¾î ¸ðµ¨(language model)À» °áÇÕÇÑ È¥ÇÕ ¸ðµ¨À» »ç¿ëÇÏ¿© À̵鿡 ÇØ´çÇÏ´Â ÀÇ¹Ì Çٽɹ®±¸(semantic keyphrase)¸¦ ã°í, ÀÇ¹Ì Çٽɹ®±¸·Î Ç¥ÇöµÇ´Â ´ÜÀ§ ±â¼úÀ» ÃßÃâÇÏ¿´´Ù. ÃßÃâµÈ °á°ú¿¡ ±Ù°ÅÇÏ¿© ºñÁöµµ ÇнÀ(unsupervised learning) ¹æ¹ýÀ¸·Î °úÇбâ¼úµéÀÇ Æ®·»µå¸¦ ¹ß°ßÇÏ´Â »õ·Î¿î Á¢±Ù¹æ¹ý(Technological Trend Discovery, TTD)À» Á¦¾ÈÇÑ´Ù. ½ÇÇè °á°ú¿¡ µû¸£¸é º» ¿¬±¸¿¡¼ Á¦¾ÈÇÑ ¹æ¹ýÀ¸·Î °úÇÐ ±â¼úÀ» ³ªÅ¸³»´Â ÀǹÌÀû ÇÙ½É ¹®±¸¸¦ ÃßÃâÇϴµ¥ 77%ÀÇ R-Á¤È®·üÀ» ´Þ¼ºÇÏ¿´°í °á°úÀûÀ¸·Î ÀǹÌÀÖ´Â °úÇбâ¼ú Æ®·»µå¸¦ ¹ß°ßÇÒ ¼ö ÀÖ¾ú´Ù. |
¿µ¹®³»¿ë (English Abstract) |
Patent text is a rich source for discovering technological trends. In order to automate such a discovery process, we attempt to identify phrases corresponding to the problem and its solution method which together form a technology. Problem and solution phrases are identified by a SVM classifier using features based on a combination of a language modeling approach and linguistic clues. Based on the occurrence statistics of the phrases, we identify the time span of each problem and solution and finally generate a trend. Based on our experiment, we show that the proposed semantic phrase identification method is promising with its accuracy being 77% in R-precision. We also show that the unsupervised method for discovering technological trends is meaningful. |
Å°¿öµå(Keyword) |
ƯÇã
ÅؽºÆ® ¸¶ÀÌ´×
°úÇбâ¼ú Æ®·»µå ŽÁö
ÀÇ¹Ì Çٽɹ®±¸ ÃßÃâ
Patent
textual-data mining
technological trend discovery
semantic keyphrase extraction
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|