公开(公告)号：US20230238262A1

公开(公告)日：2023-07-27

申请号：US17695299

申请日：2022-03-15

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Hsiao-Ying YANG ,  Ching-Pei LIN ,  Chung-Yi CHIU ,  Ming-Wei CHEN ,  Te-Hsuan CHEN ,  Chia-Wei CHEN ,  Wen-Shan HUANG

IPC: H01L21/67 ,  G06N20/00

CPC classification number: H01L21/67276 ,  G06N20/00

Abstract: A semiconductor manufacturing process prediction method and a semiconductor manufacturing process prediction device are provided. The semiconductor manufacturing process prediction method includes the following steps. A plurality of process data are obtained. According to the process data, a machine learning model is used to execute prediction and obtain a prediction confidence and a prediction yield. Whether the prediction confidence is lower than a predetermined level is determined. If the prediction confidence is lower than the predetermined level, the machine learning model is modified. According to the process data, the prediction yield is adjusted.

公开(公告)号：US20230236553A1

公开(公告)日：2023-07-27

申请号：US17695255

申请日：2022-03-15

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Chia-Wei CHEN ,  Ching-Pei LIN ,  Chung-Yi CHIU ,  Te-Hsuan CHEN ,  Ming-Wei CHEN ,  Hsiao-Ying YANG

IPC: G05B13/04 ,  H01L21/66

CPC classification number: G05B13/048 ,  H01L22/14 ,  H01L22/12

Abstract: A training method of a semiconductor process prediction model, a semiconductor process prediction device, and a semiconductor process prediction method are provided. The training method of the semiconductor process prediction model includes the following steps. The semiconductor process was performed on several samples. A plurality of process data of the samples are obtained. A plurality of electrical measurement data of the samples are obtained. Some of the samples having physical defects are filtered out according to the process data. The semiconductor process prediction model is trained according to the process data and the electrical measurement data of the filtered samples.

公开(公告)号：US20220222162A1

公开(公告)日：2022-07-14

申请号：US17180897

申请日：2021-02-22

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Ching-Pei LIN ,  Ji-Fu KUNG ,  Te-Hsuan CHEN ,  Yi-Lin HUNG

IPC: G06F11/32 ,  G06F11/34 ,  G06F11/30 ,  G06K9/62

Abstract: An operation method and an operation device of a failure detection and classification (FDC) model are provided. The operation method of the FDC model includes the following steps. A plurality of raw traces are continuously obtained. If the raw traces have started to be changed from the first waveform to the second waveform, whether at least N pieces in the race traces have been changed to the second waveform is determined. If at least N pieces in the raw traces have been changed to the second waveform, the raw traces which have been changed to the second waveform are automatically segmented to obtain several windows. An algorithm is automatically set for each of the windows. Through each of the algorithms, an indicator of each of the windows is obtained. The FDC model is retrained based on these indicators.

公开(公告)号：US20230410047A1

公开(公告)日：2023-12-21

申请号：US17866595

申请日：2022-07-18

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Ching-Pei LIN ,  Te-Hsuan CHEN

IPC: G06Q10/10 ,  G06Q10/06 ,  H04L12/18

CPC classification number: G06Q10/103 ,  G06Q10/06 ,  H04L12/1822

Abstract: An execution method of an online discussion board and a server using the same are provided. The server includes an information collection unit, an analyzing unit, a discussion board management unit and a recording unit. The information collection unit is configured to obtain a plurality of process problem messages. The analyzing unit is configured to automatically obtain a process analysis report according to the process problem messages. The discussion board management unit is configured to automatically create the online discussion board. At least two users are invited to enter the online discussion board. The process analysis report is shown in the online discussion board. The recording unit is configured to store a discussion record on the online discussion board. The online discussion board is held for a period of time.

公开(公告)号：US20210358071A1

公开(公告)日：2021-11-18

申请号：US16906263

申请日：2020-06-19

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Yu-Chi LIN ,  Li-Hsin YANG ,  Ching-Pei LIN ,  Ming-Wei CHEN ,  Wei-Hong ZHU

IPC: G06T1/00 ,  G06T7/20 ,  G06T7/00

Abstract: An automatic adjusting method for equipment and a smart adjusting device using the same are provided. The automatic adjusting method of the equipment includes the following steps. A template frame from the equipment is obtained in an initial period. Several clear frames are obtained in one window period. Each of the template frame and the clear frame has a pixel variation. The pixel variation of the template frame is the largest in the initial period. The pixel variation of each of the clear frame is greater than a threshold. Each of the clear frame is compared with the template frame to obtain an offset. A statistical value of the offsets is calculated. A parameter of the equipment is adjusted to reduce the statistical value.

公开(公告)号：US20220398410A1

公开(公告)日：2022-12-15

申请号：US17343798

申请日：2021-06-10

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Ching-Pei LIN ,  Ming-Tsung YEH ,  Chuan-Guei WANG ,  Ji-Fu KUNG

IPC: G06K9/62 ,  G06K9/32 ,  G06N5/04

Abstract: A manufacturing data analyzing method and a manufacturing data analyzing device are provided. The manufacturing data analyzing method includes the following steps. Each of at least one numerical data, at least one image data and at least one text data is transformed into a vector. The vectors are gathered to obtain a combined vector. The combined vector is inputted into an inference model to obtain a defect cause and a modify suggestion.

公开(公告)号：US20220004180A1

公开(公告)日：2022-01-06

申请号：US16988747

申请日：2020-08-10

Applicant: UNITED MICROELECTRONICS CORP.

Inventor： Ching-Pei LIN

IPC: G05B23/02 ,  H01L21/67

Abstract: An automatic detecting device and an automatic detecting method of a manufacturing equipment are provided. The automatic detecting method of the manufacturing equipment includes the following steps. A detection curve of the manufacturing equipment executing several recipe steps is obtained. The detection curve is aligned to the recipe steps, such that the detection curve is divided into several process segments. At least one peak or at least one valley in each of the process segments is searched to obtain several sub-step segments. According to the sub-step segments, a Fault Detection Classification analysis (FDC) is performed to obtain an analysis result. Based on the analysis result, a predict health information of the manufacturing equipment is outputted.