US 11,868,899 B2
System and method for model configuration selection preliminary class
Sofiia Kovalets, Kyiv (UA); Stanislav Barabanov, Ramat Gan (IL); Yuval Shalev, Kfar-Saba (IL); and Alexander Apartsin, Rehovot (IL)
Assigned to Saferide Technologies Ltd., Herzliya (IL)
Filed by Saferide Technologies Ltd., Herzliya (IL)
Filed on Feb. 27, 2023, as Appl. No. 18/174,657.
Claims priority of application No. 290977 (IL), filed on Feb. 28, 2022.
Prior Publication US 2023/0274152 A1, Aug. 31, 2023
Int. Cl. G06N 3/088 (2023.01); G06N 3/0985 (2023.01)
CPC G06N 3/088 (2013.01) [G06N 3/0985 (2023.01)] 18 Claims
OG exemplary drawing
 
1. A model configuration selection system, the model configuration selection system comprising a processing circuitry configured to:
(A) obtain: (a) one or more model configurations, each model configuration includes a set of parameters utilized to generate respective models, and (b) a training data-set comprising a plurality of unlabeled records, each unlabeled record including a collection of features describing a given state of a physical entity;
(B) cluster the training data-set into two or more training data-set clusters using a clustering algorithm;
(C) label (a) the unlabeled records of a subset of the training data-set clusters with a synthetic normal label, giving rise to a normal training data-set, and (b) the unlabeled records of the training data-set clusters not included in the subset with a synthetic abnormal label, wherein the subset of the training data-set clusters is selected from the training data-set clusters randomly;
(D) train, for each model configuration, using the normal training data-set, a corresponding model utilizing the corresponding set of parameters, each model capable of receiving the unlabeled records, and determining, for each of the unlabeled records, a corresponding normal label or abnormal label, wherein the normal label being indicative of conformity of the respective unlabeled record with an allowed state of the physical entity and the abnormal label being indicative of conformity of the respective unlabeled record with a disallowed state of the physical entity;
(E) determine, for each model, a score, associated with an ability of the corresponding model to determine labels to the unlabeled records of the training data-set in accordance with the synthetic normal labels and with the synthetic abnormal labels; and
(F) perform an action, based on the scores, wherein the action includes, upon calculating a second overall score for a respective model configuration of a given model of the models, changing the respective model configuration of the given model by changing at least one parameter of the set of parameters, based on the score determined for the given model being below a second threshold, and repeating steps (D) to (F) until the second overall score is equal or above the second threshold.