• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ÄÄÇ»ÅÍ ¹× Åë½Å½Ã½ºÅÛ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ÄÄÇ»ÅÍ ¹× Åë½Å½Ã½ºÅÛ

Current Result Document : 9 / 747 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ÀΰøÁö´É ¼­ºñ½º ¿î¿µÀ» À§ÇÑ ½Ã½ºÅÛ Ãø¸é¿¡¼­ÀÇ ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A Study on the System for AI Service Production
ÀúÀÚ(Author) È«¿ë±Ù   Yong-Geun Hong  
¿ø¹®¼ö·Ïó(Citation) VOL 11 NO. 10 PP. 0323 ~ 0332 (2022. 10)
Çѱ۳»¿ë
(Korean Abstract)
AI ±â¼úÀ» È°¿ëÇÑ ´Ù¾çÇÑ ¼­ºñ½º°¡ °³¹ßµÇ¸é¼­, AI ¼­ºñ½º ¿î¿µ¿¡ ¸¹Àº °ü½ÉÀÌ ÁýÁߵǰí ÀÖ´Ù. ÃÖ±Ù¿¡´Â AI ±â¼úµµ ÇϳªÀÇ ICT ¼­ºñ½º¸¦ º¸°í, ¹ü¿ëÀûÀÎ AI ¼­ºñ½º ¿î¿µÀ» À§ÇÑ ¿¬±¸°¡ ¸¹ÀÌ ÁøÇàµÇ°í ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ÀϹÝÀûÀÎ ±â°èÇнÀ °³¹ß ÀýÂ÷ÀÇ ¸¶Áö¸· ´Ü°èÀÎ ±â°èÇнÀ ¸ðµ¨ ¹èÆ÷ ¹× ¿î¿µ¿¡ ÃÊÁ¡À» µÎ°í AI ¼­ºñ½º ¿î¿µÀ» À§ÇÑ ½Ã½ºÅÛ Ãø¸é¿¡¼­ÀÇ ¿¬±¸ °á°ú¸¦ ±â¼úÇÏ¿´´Ù. 3´ëÀÇ ¼­·Î ´Ù¸¥ Ubuntu ½Ã½ºÅÛÀ» ±¸ÃàÇÏ°í, ÀÌ ½Ã½ºÅÛ»ó¿¡¼­ ¼­·Î ´Ù¸¥ AI ¸ðµ¨(RFCN, SSD-Mobilenet)°ú ¼­·Î ´Ù¸¥ Åë½Å ¹æ½Ä(gRPC, REST)ÀÇ Á¶ÇÕÀ¸·Î 2017 validation COCO datasetÀÇ µ¥ÀÌÅ͸¦ ÀÌ¿ëÇÏ¿© °´Ã¼ °ËÃâ ¼­ºñ½º¸¦ Tensorflow servingÀ» ÅëÇÏ¿© AI ¼­ºñ½º¸¦ ¿äûÇÏ´Â ºÎºÐ°ú AI ¼­ºñ½º¸¦ ¼öÇàÇÏ´Â ºÎºÐÀ¸·Î ³ª´©¾î ½ÇÇèÇÏ¿´´Ù. ´Ù¾çÇÑ ½ÇÇèÀ» ÅëÇÏ¿© AI ¸ðµ¨ÀÇ Á¾·ù°¡ AI ¸Ó½ÅÀÇ Åë½Å ¹æ½Äº¸´Ù AI ¼­ºñ½º Ãß·Ð ½Ã°£¿¡ ´õ Å« ¿µÇâÀ» ¹ÌÄ¡°í, °´Ã¼ °ËÃâ AI ¼­ºñ½ºÀÇ °æ¿ì °ËÃâÇÏ·Á´Â À̹ÌÁöÀÇ ÆÄÀÏ Å©±âº¸´Ù´Â À̹ÌÁö ³»ÀÇ °´Ã¼ °³¼ö¿Í º¹Àâµµ¿¡ µû¶ó AI ¼­ºñ½º Ãß·Ð ½Ã°£ÀÌ ´õ Å« ¿µÇâÀ» ¹Þ´Â´Ù´Â °ÍÀ» ¾Ë ¼ö ÀÖ¾ú´Ù. ±×¸®°í, AI ¼­ºñ½º¸¦ ·ÎÄÃÀÌ ¾Æ´Ñ ¿ø°Ý¿¡¼­ ¼öÇàÇÏ¸é ¼º´ÉÀÌ ÁÁÀº ¸Ó½ÅÀ̶ó°í ÇÏ´õ¶óµµ ·ÎÄÿ¡¼­ ¼öÇàÇÏ´Â °æ¿ìº¸´Ù AI ¼­ºñ½º Ãß·Ð ½Ã°£ÀÌ ´õ °É¸°´Ù´Â °ÍÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù. º» ¿¬±¸ °á°ú¸¦ ÅëÇÏ¿© ¼­ºñ½º ¸ñÇ¥¿¡ ÀûÇÕÇÑ ½Ã½ºÅÛ ¼³°è¿Í AI ¸ðµ¨ °³¹ß ¹× È¿À²ÀûÀÎ AI ¼­ºñ½º ¿î¿µÀÌ °¡´ÉÇØÁú °ÍÀ¸·Î º»´Ù.
¿µ¹®³»¿ë
(English Abstract)
As various services using AI technology are being developed, much attention is being paid to AI service production. Recently, AI technology is acknowledged as one of ICT services, a lot of research is being conducted for general-purpose AI service production. In this paper, I describe the research results in terms of systems for AI service production, focusing on the distribution and production of machine learning models, which are the final steps of general machine learning development procedures. Three different Ubuntu systems were built, and experiments were conducted on the system, using data from 2017 validation COCO dataset in combination of different AI models (RFCN, SSD-Mobilenet) and different communication methods (gRPC, REST) to request and perform AI services through Tensorflow serving. Through various experiments, it was found that the type of AI model has a greater influence on AI service inference time than AI machine communication method, and in the case of object detection AI service, the number and complexity of objects in the image are more affected than the file size of the image to be detected. In addition, it was confirmed that if the AI service is performed remotely rather than locally, even if it is a machine with good performance, it takes more time to infer the AI service than if it is performed locally. Through the results of this study, it is expected that system design suitable for service goals, AI model development, and efficient AI service production will be possible.
Å°¿öµå(Keyword) ÀΰøÁö´É   °´Ã¼ °ËÃâ   AI Ã߷Р  AI ¿î¿µ   ¿¡Áö ÄÄÇ»Æà     Artificial Intelligence   Object Detection      AI Inference   AI Production   Edge Computing  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå