Abstract: A method, computer program, and computer system are provided for data facet generation. Data associated with a dataset is received. The received data includes one or more data entries having one or more elements. The one or more elements are associated with one or more data types. One or more data facets are generated for each of the data entries with the received data based on the associated data type. One or more transformations are generated for the data facet corresponding to a machine learning task associated with the dataset. A recommendation is provided to a user based on the generated transformation. The provided recommendation includes generated computer code corresponding to an optimal transformation associated with the machine learning task.

Abstract: An embodiment of the present invention monitors a process across a plurality of systems associated with a supply chain. A context is determined for an order, where at least one of the features of the context includes information from a networked sensing device. One or more first machine learning models identify a plurality of orders of an order history having features corresponding to the order. A second machine learning model is trained with the identified plurality of orders to predict the monitoring interval for the order. The second machine learning model predicts the monitoring interval for the order based on the context of the order. The monitoring interval for the order is dynamically adjusted based on the predicted monitoring interval, and the order is monitored through an order fulfillment process across the plurality of systems associated with the supply chain in accordance with the adjusted monitoring interval.

Abstract: An embodiment of the present invention monitors a process across a plurality of systems associated with a supply chain. A context is determined for an order, where at least one of the features of the context includes information from a networked sensing device. One or more first machine learning models identify a plurality of orders of an order history having features corresponding to the order. A second machine learning model is trained with the identified plurality of orders to predict the monitoring interval for the order. The second machine learning model predicts the monitoring interval for the order based on the context of the order. The monitoring interval for the order is dynamically adjusted based on the predicted monitoring interval, and the order is monitored through an order fulfillment process across the plurality of systems associated with the supply chain in accordance with the adjusted monitoring interval.

Abstract: Provided are techniques for domain specific correction of output from automatic speech recognition. An output of an automatic speech recognition engine is received. An alphanumeric sequence is extracted from the output, where the alphanumeric sequence represents an erroneous translation by the automatic speech recognition engine. Candidates for the alphanumeric sequence are generated. The candidates are ranked based on scores associated with the candidates. A candidate of the candidates having a highest score of the scores is selected. The output is corrected by replacing the alphanumeric sequence with the selected candidate. The corrected output is returned.

Abstract: Using a computing device to convert verbal communications including non-standard speech to text. The computing device receives an audio recording of voice and generates a standard text log. A standard word dictionary is retrieved. Non-standard words not found in the word dictionary are determined. Portions of the audio recording corresponding to the non-standard words are retrieved. Portions of the audio recording corresponding to non-standard words into input into a natural language understanding model. The computing device utilizes the results of the natural language understanding model to determine a best-match non-standard dictionary. One or more portions of the audio recording are used to generate a non-standard text log. The standard text log and non-standard text log are merged.

Abstract: Provided are techniques for domain specific correction of output from automatic speech recognition. An output of an automatic speech recognition engine is received. An alphanumeric sequence is extracted from the output, where the alphanumeric sequence represents an erroneous translation by the automatic speech recognition engine. Candidates for the alphanumeric sequence are generated. The candidates are ranked based on scores associated with the candidates. A candidate of the candidates having a highest score of the scores is selected. The output is corrected by replacing the alphanumeric sequence with the selected candidate. The corrected output is returned.

Abstract: Using a computing device to convert verbal communications including non-standard speech to text. The computing device receives an audio recording of voice and generates a standard text log. A standard word dictionary is retrieved. Non-standard words not found in the word dictionary are determined. Portions of the audio recording corresponding to the non-standard words are retrieved. Portions of the audio recording corresponding to non-standard words into input into a natural language understanding model. The computing device utilizes the results of the natural language understanding model to determine a best-match non-standard dictionary. One or more portions of the audio recording are used to generate a non-standard text log. The standard text log and non-standard text log are merged.