-
公开(公告)号:US20230223323A1
公开(公告)日:2023-07-13
申请号:US17979480
申请日:2022-11-02
发明人: Kyungsoo KIM , Kyenhee LEE
IPC分类号: H01L23/498 , H01L23/48 , H01L23/538 , H01L25/07 , H01L23/00
CPC分类号: H01L23/49816 , H01L23/481 , H01L23/49844 , H01L23/5384 , H01L25/07 , H01L24/16 , H01L24/05 , H01L2224/16146 , H01L2224/0401 , H01L2224/05025 , H01L2924/15311
摘要: A semiconductor package is provided. The semiconductor package includes: a first semiconductor chip including a first bonding structure; , a first front-end level layer including a first integrated circuit device; a first sub-back-end level layer including a plurality of first metal wire layers, an input and output device level layer including a two-dimensional input and output device, and a second sub-back-end level layer including a plurality of second metal wire layers electrically connected to the first integrated circuit device and the two-dimensional input and output device. The semiconductor package also includes a second semiconductor chip including a bonding structure that is bonded to the first bonding structure; a second front-end level layer including a second integrated circuit device, and a second back-end level layer including a plurality of third metal wire layers electrically connected to the second integrated circuit device.
-
公开(公告)号:US20230169641A1
公开(公告)日:2023-06-01
申请号:US17842206
申请日:2022-06-16
发明人: Kyenhee LEE , Mincheol KANG , Sooryong LEE
CPC分类号: G06T7/001 , G06T7/11 , G06T7/97 , G06N3/0454 , G06T2207/30148 , G06T2207/10061 , G06T2207/20081 , G06T2207/20221 , G06T2207/10024 , G06T2207/20084
摘要: The inventive concept provides a defect detection method of a semiconductor element, capable of promptly and accurately detecting a defect, and predicting a type of the defect with respect to various defects of the semiconductor element, and a semiconductor element manufacturing method including the defect detection method. The defect detection method is capable of promptly and accurately detecting the defect, and predicting the type of the defect with respect to various defects of the semiconductor element, by generating a first segmentation image and a second segmentation image; converting the first segmentation image and the second segmentation image into an image of a first color and a second color, respectively; generating a combination image; classifying the type of a defect; generating a defect detection model by using deep learning, and detecting a defect of the semiconductor element by using a defect detection process using the defect detection model.
-