Systems and methods for semiconductor chip hole geometry metrology
AssigneeYangtze Memory Technologies Co., Ltd.
InventorsLe Wang, Yuanxiang Zou, Jun Zhang, Wei Zhang, Yi Zhou
Life of this patent
Estimating the term…
Abstract
Embodiments of systems and methods for measuring a geometric attribute of a hole structure in a semiconductor chip are disclosed. In an example, an optical spectrum signal corresponding to the hole structure in the semiconductor chip is received. The optical spectrum signal is characterized by one or more optical features. The geometric attribute of the hole structure is determined based, at least in part, on the optical features using a model. The model is trained from a plurality of training samples each including a pair of an optical spectrum signal and a labeled reference signal both corresponding to a same hole structure.
Claims20
A method for measuring a geometric attribute of a hole structure in a semiconductor chip, comprising:
- receiving, by at least one processor, an optical spectrum signal corresponding to the hole structure in the semiconductor chip;
- characterizing, by the at least one processor, the optical spectrum signal by one or more optical features;
- and
- determining, by the at least one processor, the geometric attribute of the hole structure based, at least in part, on the optical features using a model, wherein the model is trained from a plurality of training samples each comprising a pair of an optical spectrum signal and a labeled reference signal both corresponding to a same hole structure.
A system for measuring a geometric attribute of a hole structure in a semiconductor chip, comprising:
- an optical spectrometer configured to provide an optical spectrum signal corresponding to the hole structure in the semiconductor chip;
- and
- at least one processor configured to:
- characterize the optical spectrum signal by one or more optical features;
- and
- determine the geometric attribute of the hole structure based, at least in part, on the optical features using a model, wherein the model is trained from a plurality of training samples each comprising a pair of an optical spectrum signal and a labeled reference signal both corresponding to a same hole structure.
Dependencies are inferred from the claim text.