A preform cover glass shape prediction device for predicting a shape of a preform cover glass, the device includes a preform cover glass prediction model generator trained to obtain input data representing a training curved cover glass and a training preform cover glass, to generate cover glass characteristic data based on the input data, and to generate a predicted design specification of a target preform cover glass based on the cover glass characteristic data, and a preform cover glass shape predictor configured to generate a predicted design specification for a preform cover glass corresponding to a target curved cover glass based on the cover glass characteristic data and characteristic data of the target curved cover glass.

The present disclosure relates to a mold for manufacturing a glass container including a left mold and a right mold, wherein the left mold includes a left fixed mold; and a left separated mold positioned on a side surface of the left fixed mold, the right mold includes a right fixed mold; and a right separated mold positioned on a side surface of the right fixed mold, the left separated mold is movable forwardly and backwardly while the left fixed mold is stationary, and the right separated mold is movable forwardly and backwardly while the right fixed mold is stationary.

A method of forming a glass-based article comprises depositing molten glass onto a first molding member and pressing the molten glass between the first and second molding members by moving the first molding member and the second molding member towards one another. The pressing of the molten glass comprises moving a portion of one of the first and second molding members relative to a remaining portion thereof to form a first reduced-area pressing zone and, after formation of the first reduced-area pressing zone, moving the portion relative to the remaining portion to form a second reduced-area pressing zone where the molten glass is compressed between the first and second molding members.