Abstract: A computer vision approach for detecting anomalies in computing components. A model is trained to learn what healthy computing components look like using corrupted images generated from a healthy image. The model is trained to generate healthy data for each of the corrupted images. A test image of a computing component under test or evaluation is generated and corrupted images of the test image are input to the trained model. The output of the trained model is compared to the test image. Differences are indicative of anomalies in the computing component under test.

Abstract: Methods, apparatus, and processor-readable storage media for predicting device components for repair and/or replacement using artificial intelligence techniques are provided herein.

Abstract: One example method includes accessing input data elements from logs that identify user problems with computing system components, the data elements each associated with a respective original class label that identifies a class of computing system components to which the data element relates, the respective original class labels forming a group of class labels, and a first of the original class labels is overrepresented in the group, and reducing overrepresentation of the first original class label in the group by creating an arbitrary aggregation of some of the class labels that includes the first original class label. The method includes creating, based on a hierarchical modeling structure, prepared data in which an original class label is replaced by the aggregation. Next a hierarchical model and benchmark model are trained, and each model generates respective predictions for comparison. An inferencing process is performed to determine which predicted label will be used.

Abstract: Methods, apparatus, and processor-readable storage media for detecting device component defects and generating corresponding recommendations using artificial intelligence techniques are provided herein.

Abstract: Facilitating reduction of noise in non-standard printed circuit board assembly component descriptions using a zero-shot model to identify salient component class descriptions is presented herein.

Abstract: A corpus of textual data records, labeled by experts as corresponding to a defined characteristic, that comprise descriptions of problems with an item are collected. A language model generates a plurality of n-grams from the corpus. Frequently occurring n-grams are analyzed using a zero-shot learning model to determine similarity to the defined characteristic. N-grams highly similar to the defined characteristic may be selected as defined phrases. N-grams highly similar to another characteristic may also be selected to reduce false positives. The zero-shot model may also be used to determine a weighting factor for each defined phrase for each record. A relevance score is determined for a record by multiplying the weighting factors for each phrase that has a similarity score relative to the record above a threshold based on the expert labeling. The relevancy score may be used to automatically diagnose problems with the item.

Abstract: Facilitating reduction of noise in non-standard printed circuit board assembly component descriptions using a zero-shot model to identify salient component class descriptions is presented herein.

Abstract: A corpus of textual data records, labeled by experts as corresponding to a defined characteristic, that comprise descriptions of problems with an item are collected. A language model generates a plurality of n-grams from the corpus. Frequently occurring n-grams are analyzed using a zero-shot learning model to determine similarity to the defined characteristic. N-grams highly similar to the defined characteristic may be selected as defined phrases. N-grams highly similar to another characteristic may also be selected to reduce false positives. The zero-shot model may also be used to determine a weighting factor for each defined phrase for each record. A relevance score is determined for a record by multiplying the weighting factors for each phrase that has a similarity score relative to the record above a threshold based on the expert labeling. The relevancy score may be used to automatically diagnose problems with the item.

Abstract: One example method includes accessing input data elements from logs that identify user problems with computing system components, the data elements each associated with a respective original class label that identifies a class of computing system components to which the data element relates, the respective original class labels forming a group of class labels, and a first of the original class labels is overrepresented in the group, and reducing overrepresentation of the first original class label in the group by creating an arbitrary aggregation of some of the class labels that includes the first original class label. The method includes creating, based on a hierarchical modeling structure, prepared data in which an original class label is replaced by the aggregation. Next a hierarchical model and benchmark model are trained, and each model generates respective predictions for comparison. An inferencing process is performed to determine which predicted label will be used.

Abstract: An apparatus includes at least one processing device configured to obtain information regarding a given asset to be repaired, to generate a recommended troubleshooting action to be performed on the given asset, and to provide the recommended troubleshooting action and the obtained information regarding the given asset as input to an encoder of a machine learning model implementing an attention mechanism. The at least one processing device is also configured to receive, from a decoder of the machine learning model, a predicted success of the recommended troubleshooting action. The at least one processing device is further configured to determine whether the predicted success of the recommended troubleshooting action meets designated criteria, to perform the recommended troubleshooting action responsive to the predicted success meeting the designated criteria, and, to modify the recommended troubleshooting action responsive to the predicted success not meeting the designated criteria.

Abstract: An apparatus includes at least one processing device configured to obtain information regarding a given asset to be repaired, to generate a recommended troubleshooting action to be performed on the given asset, and to provide the recommended troubleshooting action and the obtained information regarding the given asset as input to an encoder of a machine learning model implementing an attention mechanism. The at least one processing device is also configured to receive, from a decoder of the machine learning model, a predicted success of the recommended troubleshooting action. The at least one processing device is further configured to determine whether the predicted success of the recommended troubleshooting action meets designated criteria, to perform the recommended troubleshooting action responsive to the predicted success meeting the designated criteria, and, to modify the recommended troubleshooting action responsive to the predicted success not meeting the designated criteria.