ACTIVE LEARNING-BASED DEFECT LOCATION IDENTIFICATION

    公开(公告)号:WO2022101051A1

    公开(公告)日:2022-05-19

    申请号:PCT/EP2021/080304

    申请日:2021-11-02

    Abstract: A method and apparatus for identifying locations to be inspected on a substrate is disclosed. A defect location prediction model is trained using a training dataset associated with other substrates to generate a prediction of defect or non-defect and a confidence score associated with the prediction for each of the locations based on process-related data associated with the substrates. Those of the locations determined by the defect location prediction model as having confidences scores satisfying a confidence threshold are added to a set of locations to be inspected by an inspection system. After the set of locations are inspected, the inspection results data is obtained, and the defect location prediction model is incrementally trained by using the inspection results data and process-related data for the set of locations as training data.

    PREDICTION OF OUT OF SPECIFICATION BASED ON SPATIAL CHARACTERISTIC OF PROCESS VARIABILITY

    公开(公告)号:WO2020094385A1

    公开(公告)日:2020-05-14

    申请号:PCT/EP2019/078689

    申请日:2019-10-22

    Abstract: Described herein is a method for determining a probabilistic model configured to predict a characteristic (e.g., defects, CD, etc.) of a pattern of a substrate subjected to a patterning process. The method includes obtaining a spatial map of a distribution of a residue corresponding to a characteristic of the pattern on the substrate, determining a zone of the spatial map based on a variation of the distribution of the residue within the spatial map, and determining the probabilistic model based on the zone and the distribution of the residue values or the values of the characteristic of the pattern on the substrate within the zone.

Patent Agency Ranking