Abstract: An IC structure comprises a substrate, a first dielectric structure, a second dielectric structure, a first via structure, and a memory cell structure. The substrate comprises a memory region and a logic region. The first dielectric structure is over the memory region. The second dielectric structure laterally extends from the first dielectric structure to over the logic region. The second dielectric structure has a thickness less than a thickness of the first dielectric structure. The first via structure extends through the first dielectric structure. A top segment of the first via structure is higher than a top surface of the first dielectric structure. The first memory cell structure is over the first via structure.

Abstract: A device includes a resistance switching layer, a capping layer, a top electrode, a first spacer, and a second spacer. The resistance switching layer is over a substrate. The capping layer is over the resistance switching layer. The top electrode is over the capping layer. The first spacer lines the resistance switching layer and the capping layer. The second spacer lines the first spacer. The capping layer is in contact with the top electrode, the first spacer, and the second spacer.

Abstract: A method and a device for establishing a weak pattern severity model are provided. The method for establishing the weak pattern severity model includes the following steps. A plurality of weak patterns are obtained. A plurality of experiments are performed on each of the weak patterns with a plurality of parameter setting values of at least one process parameter to obtain a plurality of experimental results. According to the experimental results, a plurality of defects are obtained. According to the defects and the corresponding parameter setting values, a severity level of each of the weak patterns is analyzed. The weak patterns are labeled the severity levels. Machine learning is performed to train a weak pattern severity model.

Abstract: A module for predicting semiconductor physical defects includes a defect diagnosis unit used to detect at least one failure circuit in a semiconductor circuit structure; an information acquisition unit used for obtaining a semiconductor mask layout for forming the semiconductor circuit structure, and obtaining a failure path configuration diagram corresponding to the failure circuits and the location information corresponding to the failure path configuration diagram; a feature classification unit used for extracting a plurality of cutting images of the failure path configuration diagram, and performing feature classification on these cutting images to obtain a plurality of image groups; and a failure risk assessment unit used for performing a risk pre-assessment to select at least one high-risk group therefrom, and performing a failure risk analysis to predict at least one high failure risk position in the semiconductor mask layout according to the analysis results and the location information.

Abstract: The invention provides an operation method of a semiconductor system, which includes providing a system which includes a layout pattern to scanning electron microscope (SEM) pattern prediction model (LS model) and a novelty detection model (ND model), inputting a layout pattern to the ND model, and the ND model judges whether the layout pattern is a novel layout pattern, and if the layout pattern is confirmed as the novel layout pattern after judgment, performing a process step on the novel layout pattern to form an SEM (scanning electron microscope) pattern.

Abstract: The invention provides an operation method of a semiconductor system, which includes providing a system which includes a layout pattern to scanning electron microscope (SEM) pattern prediction model (LS model) and a novelty detection model (ND model), inputting a layout pattern to the ND model, and the ND model judges whether the layout pattern is a novel layout pattern, and if the layout pattern is confirmed as the novel layout pattern after judgment, performing a process step on the novel layout pattern to form an SEM (scanning electron microscope) pattern.

Abstract: A mask weak pattern recognition apparatus and a mask weak pattern recognition method are provided. The mask weak pattern recognition apparatus includes a receiving unit, an overlapping unit, an analyzing unit and a training unit. The receiving unit is used for receiving a mask layout and an inspection image of a mask. The overlapping unit is used for overlapping the mask layout and the inspection image to obtain an overlapped image. The analyzing unit is used for obtaining a plurality of risk patterns and a plurality of risk scores each of which corresponds one of the risk patterns according to the overlapped image. The training unit is used for training a recognition model according to the risk patterns and the risk scores.

Abstract: A mask weak pattern recognition apparatus and a mask weak pattern recognition method are provided. The mask weak pattern recognition apparatus includes a receiving unit, an overlapping unit, an analyzing unit and a training unit. The receiving unit is used for receiving a mask layout and an inspection image of a mask. The overlapping unit is used for overlapping the mask layout and the inspection image to obtain an overlapped image. The analyzing unit is used for obtaining a plurality of risk patterns and a plurality of risk scores each of which corresponds one of the risk patterns according to the overlapped image. The training unit is used for training a recognition model according to the risk patterns and the risk scores.