°ÇÃ൵½Ã°ø°£¿¬±¸¼Ò

Architecture & Urban Research Institute

pdf¿ø¹®º¸±â ¿¡·¯ ÇØ°á¹æ¹ý ¹Ù·Î°¡±â



¹®ÇåȨ > ¿¬±¸³í¹® > »ó¼¼

[¿ø¹®º¸±â½Ã ¼ÒºñµÇ´Â Æ÷ÀÎÆ® : 100 Æ÷ÀÎÆ®] ¹Ì¸®º¸±â Àοë

´ëÇÑÅä¸ñÇÐȸ|´ëÇÑÅä¸ñÇÐȸ³í¹®Áý 2026³â 8¿ù

³í¹®¸í »ý¼ºÇü ÀΰøÁö´É ±â¹Ý °Ç¼³ÇöÀå À§Ç輺Æò°¡ ¹× ½Ã°¢ÀÚ·á Áö¿ø½Ã½ºÅÛ °³¹ß / Development of a Generative AI-Based Support System for Risk Assessment and Visual Materials at Construction Sites
ÀúÀÚ¸í À̰­Çõ(Lee, Kanghyeok) ; Á¶ÀçÈ«(Cho, Jaehong) ; ±è¿µÈ¯(Kim, Yeonghwan) ; °­»óÇõ(Kang, Sanghyeok)
¹ßÇà»ç ´ëÇÑÅä¸ñÇÐȸ
¼ö·Ï»çÇ× ´ëÇÑÅä¸ñÇÐȸ³í¹®Áý, v.46 n.4 (2026-08)
ÆäÀÌÁö ½ÃÀÛÆäÀÌÁö(351) ÃÑÆäÀÌÁö(11)
ISSN 10156348
ÁÖÁ¦¾î À§Ç輺Æò°¡, ÀΰøÁö´É, °Ë»öÁõ°­»ý¼º, ¾ÈÀü°ü¸®, À§ÇèÀÎÀÚ ; Safety management, Artificial Intelligence (AI), Retrieval-Augmented Generation (RAG), Risk assessment, Hazard factors
¿ä¾à1 °Ç¼³»ê¾÷Àº Àü »ê¾÷ °¡¿îµ¥ »ê¾÷ÀçÇØ »ç¸ÁÀÚ ºñÁßÀÌ °¡Àå ³ôÀº »ê¾÷À¸·Î, °Ç¼³ÇöÀåÀÇ ¾ÈÀü°ü¸® °­È­ ¹× »ê¾÷ÀçÇØ ¿¹¹æÀ» À§ÇØ À§Ç輺Æò°¡°¡ ¹ýÀûÀ¸·Î Àǹ«È­µÇ¾ú´Ù. ±×·¯³ª °Ç¼³ÇöÀå¿¡¼­´Â Àη°ú ½Ã°£ÀÇ Á¦¾àÀ¸·Î À§Ç輺Æò°¡°¡ Çü½ÄÀûÀ¸·Î ÀÌ·ç¾îÁö±â ½¬¿ì¸ç, ¾ÈÀü°ü¸®ÀÚÀÇ ÁÖ°üÀû ÆÇ´Ü¿¡ ÀÇÁ¸ÇØ Æò°¡ÀÇ Àϰü¼ºÀÌ ÀúÇ쵃 ¿ì·Á°¡ ÀÖ´Ù. º» ¿¬±¸´Â À§Ç輺Æò°¡ÀÇ È¿°ú¼ºÀ» ³ôÀ̰í ÀÛ¾÷ÀÚÀÇ À§Çè°¨¼ö¼ºÀ» Çâ»óÇϱâ À§ÇØ »ç°í»ç·Ê ¹× ¹ý·É µ¥ÀÌÅ͸¦ ÀÓº£µù ¸ðµ¨(text-embedding-3-large)·Î º¤ÅÍÈ­ÇÏ¿© º¤ÅÍ µ¥ÀÌÅͺ£À̽º¸¦ ±¸ÃàÇÏ¿´´Ù. À̸¦ ±â¹ÝÀ¸·Î »ç¿ëÀÚ ÁúÀÇ¿Í À¯»çÇÑ »ç·Ê¸¦ °Ë»öÁõ°­»ý¼º(Retrieval Augmented Generation, RAG) ¹æ½ÄÀ¸·Î ÃßÃâÇϰí, »ý¼ºÇü ÀΰøÁö´É ¸ðµ¨(GPT-4o)À» ÅëÇØ °ü·Ã¼ºÀ» °ËÁõÇÏ¿© À§Ç輺Æò°¡Ç¥¸¦ ÀÚµ¿ »ý¼ºÇÏ´Â ½Ã½ºÅÛÀ» °³¹ßÇÏ¿´´Ù. ¾Æ¿ï·¯ ¹ý·É ¹× Ãß°¡ »ç°í»ç·Ê °Ë»ö ±â´É°ú ´õºÒ¾î, »ç°í »óȲÀ» Á÷°üÀûÀ¸·Î ½Ã°¢È­ÇÏ´Â À̹ÌÁö »ý¼º ±â´ÉÀ» ÅëÇÕÇÏ¿© Á¦°øÇÑ´Ù. À§Ç輺Æò°¡ ½Ç¹« °æÇèÀ» º¸À¯ÇÑ ¾ÈÀü°ü¸®ÀÚ 9¸íÀ» ´ë»óÀ¸·Î ½Ã½ºÅÛÀ» Æò°¡ÇÑ °á°ú, ±³À°¼º 4.56Á¡, È¿À²¼º 4.33Á¡, ¸¸Á·µµ 4.11Á¡, ½Å·Ú¼º 3.89Á¡, È¿°ú¼º 3.78Á¡À¸·Î ³ªÅ¸³ª ±âÁ¸ ¹æ½Ä ´ëºñ °³¼± °¡´É¼ºÀ» È®ÀÎÇÏ¿´´Ù. Á¤¼ºÀû Æò°¡¿¡¼­µµ °£´ÜÇÑ ÀԷ¸¸À¸·Î »ç°í»ç·Ê¿Í ¹ý·É Á¤º¸¸¦ ½Å¼ÓÇÏ°Ô È®ÀÎÇÒ ¼ö ÀÖ¾î ¹®¼­ ÀÛ¼º ºÎ´ãÀ» ÁÙÀÏ ¼ö ÀÖÀ¸¸ç, »ç°í»ç·Ê ±â¹Ý ½Ã°¢ÀÚ·á°¡ À§Çè¿äÀο¡ ´ëÇÑ ÀÌÇØ¸¦ ³ôÀ̰í ÀÛ¾÷ÀÚ ¾ÈÀü±³À°¿¡ È¿°úÀûÀ̶ó´Â Æò°¡°¡ ³ªÅ¸³µ´Ù. º» ½Ã½ºÅÛÀº °Ç¼³ÇöÀåÀÇ À§Ç輺Æò°¡ ½ÇÈ¿¼ºÀ» ³ôÀ̰í ÀÛ¾÷ÀÚ ¾ÈÀü±³À°À» Áö¿øÇÏ´Â µµ±¸·Î Ȱ¿ëµÉ ¼ö ÀÖÀ¸¸ç, ÇâÈÄ ´Ù¾çÇÑ °øÁ¾°ú °Ç¼³ÇöÀåÀ» ´ë»óÀ¸·Î Àû¿ë ¹üÀ§¸¦ È®´ëÇØ °ËÁõÇÒ Çʿ䰡 ÀÖ´Ù.
¿ä¾à2 The construction industry records the highest proportion of occupational fatalities among all industries, and risk assessment has been made legally mandatory to strengthen on-site safety management and prevent industrial accidents. However, risk assessments are often conducted in a perfunctory manner due to limitations in manpower and time, and evaluation consistency may be compromised by reliance on the subjective judgment of individual safety managers. To improve the effectiveness of risk assessment and enhance workers' risk awareness, this study constructed a vector database from accident case and legal data using the Text-Embedding-3-Large model. Relevant cases were retrieved through retrieval-augmented generation (RAG)-based similarity search, and a multimodal generative AI-based support system was developed to automatically generate risk assessment sheets after verifying the relevance of accident cases using GPT-4o. The system also integrates legal information search, additional accident case search, and accident case-based visual material generation using the gpt-image-1 model. A survey conducted with nine safety managers with risk assessment experience yielded scores of 4.56 for educational effectiveness, 4.33 for efficiency, 4.11 for satisfaction, 3.89 for reliability, and 3.78 for effectiveness, confirming its potential for improvement over conventional methods. Respondents also noted that the system reduces repetitive documentation burden by enabling rapid access to accident cases and legal information through simple inputs, and that accident case-based visual materials were effective in improving understanding of hazard factors and supporting worker safety education. The proposed system can serve as a tool to enhance the practical effectiveness of risk assessment and support worker safety education at construction sites, and future research should expand its application to a wider range of trades and construction environments.
¼ÒÀåó ´ëÇÑÅä¸ñÇÐȸ
¾ð¾î Çѱ¹¾î
DOI https://doi.org/10.12652/Ksce.2026.46.4.0351