Abstract: A low power Bidirectional Encoder Representations from Transformers (BERT) model natural language processor is provided. The methodology includes: creating a set of non-sequential data points from user data including numerical features; first binning overlapping types of numerical features from the non-sequential data points into consecutive numbers; first allocating the consecutive numbers as binned into a plurality of quantiles; first assigning a first category token to each of the plurality of quantiles, each of the first category tokens being BERT compatible; creating a time ordered sequence of transactions of the user including text features and numerical features; second assigning second category tokens to the time ordered sequence of user transactions; concatenating the first category tokens and the second category tokens into a sequence; pre-training the BERT model based on the sequence; and submitting a query including text features and numerical features to the trained BERT model.

Abstract: Technology disclosed herein describes a system and method for aggregating event information in an industrial automation system for analysis and response. In an implementation, industrial automation devices perform industrial automation processes in an industrial automation environment. A computing device receives event data relating to events that occurred on an associated industrial automation device of the industrial automation devices. The computing device normalizes the event data to generate normalized event data which describes the events. The computing device supplements the normalized event data with context information relevant to the associated industrial automation device to generate complete event data. The computing device identifies an anomaly for an industrial automation device of the industrial automation devices based on analyzing the complete event data associated with the industrial automation device.

Abstract: Technology disclosed herein describes a system and method for aggregating event information in an industrial automation system for analysis and response. In an implementation, industrial automation devices perform industrial automation processes in an industrial automation environment. A computing device receives event data relating to events that occurred on an associated industrial automation device of the industrial automation devices. The computing device normalizes the event data to generate normalized event data which describes the events. The computing device supplements the normalized event data with context information relevant to the associated industrial automation device to generate complete event data. The computing device identifies an anomaly for an industrial automation device of the industrial automation devices based on analyzing the complete event data associated with the industrial automation device.