# US 2013/0159948 A1 · Layout-specific classification and prioritization of recommended rules violations > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2013/0159948 A1 - Document ID: US20130159948A1 - Status: Published application - Kind: A1 - Application number: 13/328,942 - Filed: 2011-12-16 - Published: 2013-06-20 - Earliest claimed: 2011-12-16 - Assignees: International Business Machines Corporation - Inventors: Kanak Behari Agarwal; Sani Richard Nassif - Web page: https://patentgrep.com/patent/US20130159948A1 ## CPC - G06F 30/398: Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM] (optical proximity correction [OPC] design processes G03F1/36) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A method, system, and computer program product for classifying and prioritizing a set of recommended rule (RR) violations in an integrated circuit (IC) design are provided in the illustrative embodiments. The set of RR violations is received. A layout corresponding to the IC design is received. A set of features is selected in the layout. A classification model corresponding to the set of features is selected. Using the set of features and the classification model, the first RR violation is classified into a classification from a set of classifications. The classification is prioritized in an order of priority such that the first RR violation in the classification is recommended for remedying in the order of priority. ## Claims ### Claim 1 A method for classifying and prioritizing a set of recommended rule (RR) violations in an integrated circuit (IC) design, the method comprising: receiving the set of RR violations; receiving a layout corresponding to the IC design; selecting a set of features in the layout; selecting a classification model corresponding to the set of features; classifying, using the set of features and the classification model, the first RR violation into a classification from a set of classifications; and prioritizing the classification in an order of priority such that the first RR violation in the classification is recommended for remedying in the order of priority. ### Claim 2 (depends on 1) The method of claim 1, further comprising: training, using a machine learning algorithm, a model for RR violation classification, wherein the training comprises: supplying the machine learning algorithm with at least one training set of a training layout, training RR violations, training features, and training classifications; outputting from the machine learning algorithm, the model; and encoding the model to execute in the data processing system and perform the classifying. ### Claim 3 (depends on 2) The method of claim 2, wherein the model, when supplied with the layout and the set of RR violations, identifies the geometric feature and the classification. ### Claim 4 (depends on 3) The method of claim 3, wherein the model further determines an area surrounding the first RR violation within which to analyze an effect of remedying the first RR violation on the layout. ### Claim 5 (depends on 3) The method of claim 3, further comprising: supplying the layout, the set of RR violations, the set of classifications, and the geometric feature as a second training set to the machine learning algorithm, the supplying improving the model to an improved model; encoding the improved model to execute in the data processing system; and classifying a second layout, having a second set of RR violations, using the improved model. ### Claim 6 (depends on 1) The method of claim 1, wherein the prioritizing further comprises: receiving a prioritization rule, the prioritization rule being related to the layout, wherein the prioritizing occurs in compliance with the prioritization rule. ### Claim 7 (depends on 1) The method of claim 1, wherein the set of features and the classification model are received from a data source. ### Claim 8 (depends on 1) The method of claim 1, wherein the set of features is a set of vertices in a defined area surrounding an RR in the set of RRs, and wherein the classification model uses a threshold value for a number of members of the set of features to classify the RR. ### Claim 9 A computer usable program product comprising a computer usable storage medium including computer usable code for classifying and prioritizing a set of recommended rule (RR) violations in an integrated circuit (IC) design, the computer usable code comprising: computer usable code for receiving the set of RR violations; computer usable code for receiving a layout corresponding to the IC design; computer usable code for selecting a set of features in the layout; computer usable code for selecting a classification model corresponding to the set of features; computer usable code for classifying, using the set of features and the classification model, the first RR violation into a classification from a set of classifications; and computer usable code for prioritizing the classification in an order of priority such that the first RR violation in the classification is recommended for remedying in the order of priority. ### Claim 10 (depends on 9) The computer usable program product of claim 9, further comprising: computer usable code for training, using a machine learning algorithm, a model for RR violation classification, wherein the computer usable code for training comprises: computer usable code for supplying the machine learning algorithm with at least one training set of a training layout, training RR violations, training features, and training classifications; computer usable code for outputting from the machine learning algorithm, the model; and computer usable code for encoding the model to execute in the data processing system and perform the classifying. ### Claim 11 (depends on 10) The computer usable program product of claim 10, wherein the model, when supplied with the layout and the set of RR violations, identifies the geometric feature and the classification. ### Claim 12 (depends on 11) The computer usable program product of claim 11, wherein the model further determines an area surrounding the first RR violation within which to analyze an effect of remedying the first RR violation on the layout. ### Claim 13 (depends on 11) The computer usable program product of claim 11, further comprising: computer usable code for supplying the layout, the set of RR violations, the set of classifications, and the geometric feature as a second training set to the machine learning algorithm, the supplying improving the model to an improved model; computer usable code for encoding the improved model to execute in the data processing system; and computer usable code for classifying a second layout, having a second set of RR violations, using the improved model. ### Claim 14 (depends on 9) The computer usable program product of claim 9, wherein the computer usable code for prioritizing further comprises: computer usable code for receiving a prioritization rule, the prioritization rule being related to the layout, wherein the prioritizing occurs in compliance with the prioritization rule. ### Claim 15 (depends on 9) The computer usable program product of claim 9, wherein the set of features and the classification model are received from a data source. ### Claim 16 (depends on 9) The computer usable program product of claim 9, wherein the computer usable code is stored in a computer readable storage medium in a data processing system, and wherein the computer usable code is transferred over a network from a remote data processing system. ### Claim 17 (depends on 9) The computer usable program product of claim 9, wherein the computer usable code is stored in a computer readable storage medium in a server data processing system, and wherein the computer usable code is downloaded over a network to a remote data processing system for use in a computer readable storage medium associated with the remote data processing system. ### Claim 18 A data processing system for classifying and prioritizing a set of recommended rule (RR) violations in an integrated circuit (IC) design, the data processing system comprising: a storage device including a storage medium, wherein the storage device stores computer usable program code; and a processor, wherein the processor executes the computer usable program code, and wherein the computer usable program code comprises: computer usable code for receiving the set of RR violations; computer usable code for receiving a layout corresponding to the IC design; computer usable code for selecting a set of features in the layout; computer usable code for selecting a classification model corresponding to the set of features; computer usable code for classifying, using the set of features and the classification model, the first RR violation into a classification from a set of classifications; and computer usable code for prioritizing the classification in an order of priority such that the first RR violation in the classification is recommended for remedying in the order of priority. ### Claim 19 (depends on 18) The data processing system of claim 18, further comprising: computer usable code for training, using a machine learning algorithm, a model for RR violation classification, wherein the computer usable code for training comprises: computer usable code for supplying the machine learning algorithm with at least one training set of a training layout, training RR violations, training features, and training classifications; computer usable code for outputting from the machine learning algorithm, the model; and computer usable code for encoding the model to execute in the data processing system and perform the classifying. ### Claim 20 (depends on 19) The data processing system of claim 19, wherein the model, when supplied with the layout and the set of RR violations, identifies the geometric feature and the classification.