Abstract: The present invention relates to a computer-implemented method of monitoring the performance of a computing device. The method comprises determining an actual device usage for processing a plurality of requests; obtaining a predicted device usage for processing the plurality of requests by inputting a request volume of the plurality of requests into a model of the operation of the computing device; comparing the actual device usage and the predicted device usage; selecting a margin of error for the predicted device usage; and raising an alert if the actual device usage is greater than the predicted device usage and the actual device usage is not within the margin of error.

Abstract: An identification and management system for log entries may filter historical data and generate closed log entries as a reference dataset. A dynamic learning engine may perform statistical modelling using the reference dataset to assign predetermined categories to each of a number of open log entries. An automation index may be generated for each of the open log entries. The automation index is indicative of accuracy of the assigned categories. Some of the open log entries may be identified as priority log entries which are representative of a group of the open log entries. The assigned category of the priority log entries may be analyzed for accuracy and the results of the analysis may be used to train the statistical model so that the open log entries may be iteratively assigned and re-assigned a category until the category of each open log entry reaches a desired accuracy.

Abstract: Implementations are directed to providing categorization of transactional data, and include actions of providing a plurality of word embeddings based on domain-relevant text data, clustering word embeddings of the plurality of word embeddings into a plurality of clusters, receiving, in real-time, transactional data representative of a transaction, providing a category that is to be assigned to the transaction based on the transactional data, and the plurality of clusters, processing the category, the transactional data, the text data, and the plurality of clusters using a semantic search to provide reason text data, the reason text data representing a reason for selection of the category assigned to the transaction, and storing the transaction data, the category, and the reason text data in a transaction database.

Abstract: Implementations are directed to providing categorization of transactional data, and include actions of providing a plurality of word embeddings based on domain-relevant text data, clustering word embeddings of the plurality of word embeddings into a plurality of clusters, receiving, in real-time, transactional data representative of a transaction, providing a category that is to be assigned to the transaction based on the transactional data, and the plurality of clusters, processing the category, the transactional data, the text data, and the plurality of clusters using a semantic search to provide reason text data, the reason text data representing a reason for selection of the category assigned to the transaction, and storing the transaction data, the category, and the reason text data in a transaction database.

Abstract: An identification and management system for log entries may filter historical data and generate closed log entries as a reference dataset. A dynamic learning engine may perform statistical modelling using the reference dataset to assign predetermined categories to each of a number of open log entries. An automation index may be generated for each of the open log entries. The automation index is indicative of accuracy of the assigned categories. Some of the open log entries may be identified as priority log entries which are representative of a group of the open log entries. The assigned category of the priority log entries may be analyzed for accuracy and the results of the analysis may be used to train the statistical model so that the open log entries may be iteratively assigned and re-assigned a category until the category of each open log entry reaches a desired accuracy.