US 12,450,144 B1
Model card system
Allie Joelle DeLonay, Madison, WI (US); Maribel Costa, Espoo (FI); Christopher Thomas Rackley, Anniston, AL (US); and Sierra Frances Shell, Raleigh, NC (US)
Assigned to SAS Institute Inc., Cary, NC (US)
Filed by SAS Institute Inc., Cary, NC (US)
Filed on Dec. 27, 2024, as Appl. No. 19/003,023.
Application 19/003,023 is a continuation in part of application No. 18/445,673, filed on Aug. 7, 2024.
Int. Cl. G06F 11/34 (2006.01); G06F 9/451 (2018.01)
CPC G06F 11/3447 (2013.01) [G06F 9/451 (2018.02)] 37 Claims
OG exemplary drawing
 
1. A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, the computer-program product including instructions operable to cause a computing system to:
receive a trained computer model trained on a training dataset, wherein the training dataset indicates inputs for variables in a training system and outputs of the training system;
obtain a selection of an assessment type, wherein the assessment type comprises more than one component for determining an overall assessment of the trained computer model according to the assessment type;
generate, responsive to receiving the trained computer model, an overall training assessment of the trained computer model according to the assessment type by:
obtaining multiple component assessments, wherein the multiple component assessments comprise at least one assessment for each of the more than one components for determining the overall assessment, wherein a first assessment of the at least one assessment assesses elements of the training dataset pertaining to one or more model terms in the trained computer model or assesses a model performance for the trained computer model; and
generating the overall training assessment based on the multiple component assessments; and
generate a first graphical representation comprising visual representation of both the overall training assessment and the multiple component assessments;
receive a selection of a performance monitoring criteria for the trained computer model applied to data other than the training dataset, wherein the performance monitoring criteria has multiple component criteria;
generate an overall monitoring assessment specific to the performance monitoring criteria by:
generating a respective assessment for each of the multiple component criteria; and
generating the overall monitoring assessment based on the respective assessment for each of the multiple component criteria; and
generate a second graphical representation comprising the overall monitoring assessment and the multiple component criteria; and
display the first graphical representation and the second graphical representation in a model card visualization, wherein the model card visualization comprises:
textual and graphical representations of the trained computer model; and
textual and graphical representations of the training dataset.