Data mining shape based data
First Claim
Patent Images
1. A method for data mining shape based data, the method comprising:
- receiving, by a processor, a shape data for each of a plurality of data entries;
creating, by the processor, a first abstract from the shape data for each of the plurality of data entries, wherein the first abstract is a graphic illustration of a location of a detected error on a semiconductor chip;
organizing, by the processor, the first abstracts into a plurality of groups based on a first criterion, wherein the first criterion is the location of the detected error;
creating, by the processor, a second abstract for each data entry in the plurality of groups based on a second criterion, wherein the second criterion is the shape of the detected error, and information derived from the first abstract, wherein the second abstract is a visual representation of the detected error on the semiconductor chip that illustrates a more detailed view of a common location of detected errors; and
determining a correlation between each of the data entries in the group based on the second abstract, wherein similarities in the shapes of the detected errors in the common location indicate that the detected errors are not random defects.
1 Assignment
0 Petitions
Accused Products
Abstract
Embodiments of the disclosure include a method for data mining shape based data, the method includes receiving shape data for each of a plurality of data entries and creating a first abstract from the shape data for each of the plurality of data entries. The method also includes organizing the first abstracts into a plurality of groups based on a criterion and creating a second abstract for each data entry in the plurality of groups based on the criterion and information derived from the first abstract.
-
Citations
6 Claims
-
1. A method for data mining shape based data, the method comprising:
-
receiving, by a processor, a shape data for each of a plurality of data entries; creating, by the processor, a first abstract from the shape data for each of the plurality of data entries, wherein the first abstract is a graphic illustration of a location of a detected error on a semiconductor chip; organizing, by the processor, the first abstracts into a plurality of groups based on a first criterion, wherein the first criterion is the location of the detected error; creating, by the processor, a second abstract for each data entry in the plurality of groups based on a second criterion, wherein the second criterion is the shape of the detected error, and information derived from the first abstract, wherein the second abstract is a visual representation of the detected error on the semiconductor chip that illustrates a more detailed view of a common location of detected errors; and determining a correlation between each of the data entries in the group based on the second abstract, wherein similarities in the shapes of the detected errors in the common location indicate that the detected errors are not random defects. - View Dependent Claims (2, 3, 4, 5, 6)
-
Specification