Combined Feature Creation to Increase Data Mining Signal in Hybrid Datasets
AssigneeInternational Business Machines Corporation
InventorSteven George Barbee
Life of this patent
Estimating the term…
Abstract
Embodiments of the invention may be used to produce a data mining signal by generating hybrid dataset representing data related to tools used during a semiconductor fabrication process. By selectively combining similar processes, the data mining signal strength of each tool used to perform the steps of the fabrication process may be increased. A combined process variable may be used to represent the group of tools and processes, collectively. A set of rules may be composed to determine which processes used in the semiconductor fabrication process should be combined in the hybrid dataset.
Claims21
A method of processing data collected for a semiconductor fabrication process, comprising:
- retrieving a collection of process data specifying one or more tools used to perform a sequence of semiconductor fabrication steps, and specifying which of the one or more tools was used to perform each of the one or more fabrication steps, relative to one or more wafers, and further specifying a yield percentage obtained from each of the one or more wafers;
- retrieving one or more rules specifying a group of semiconductor fabrication steps to combine in a hybrid dataset;
- transforming the collection of process data to generate the hybrid dataset, wherein the hybrid dataset specifies a count value representing how many times each of the one or more tools performed any of the fabrication steps, relative to each of the one or more wafers;
- and
- storing the hybrid dataset for use by a data mining engine.
A computer-readable medium containing a program which, when executed on a processor, performs an operation for processing data collected for a semiconductor fabrication process, the operation comprising:
- retrieving a collection of process data specifying one or more tools used to perform a sequence of semiconductor fabrication steps, and specifying which of the one or more tools was used to perform each of the one or more fabrication steps, relative to one or more wafers, and further specifying a yield percentage obtained from each of the one or more wafers;
- retrieving one or more rules specifying a group of semiconductor fabrication steps to combine in a hybrid dataset;
- transforming the collection of process data to generate the hybrid dataset, wherein the hybrid dataset specifies a count value representing how many times each of the one or more tools performed any of the fabrication steps, relative to each of the one or more wafers;
- and
- storing the hybrid dataset for use by a data mining engine.
A system, comprising:
- a processor;
- and
- a memory containing a program configured to perform an operation for processing data collected for a semiconductor fabrication process, the program being configured to:
- retrieve a collection of process data specifying one or more tools used to perform a sequence of semiconductor fabrication steps, and specifying which of the one or more tools was used to perform each of the one or more fabrication steps, relative to one or more wafers, and further specifying a yield percentage obtained from each of the one or more wafers,
- retrieve one or more rules specifying a group of semiconductor fabrication steps to combine in a hybrid dataset,
- transform the collection of process data to generate the hybrid dataset, wherein the hybrid dataset specifies a count value representing how many times each of the one or more tools performed any of the fabrication steps, relative to each of the one or more wafers, and
- store the hybrid dataset for use by a data mining engine.
Dependencies are inferred from the claim text.