Abstract: Implementations include determining a set of routes for delivery of assets within a delivery network based on realized and forecasted demand for a period, during at least partial execution of the set of routes, receiving real-time data representative of delivery of assets, and updated demand forecasts, determining, by an optimization controller, a time-to-trigger, and a cut-off time, and an updated demand forecast, the time-to-trigger defining an interval, at which the set of routes for delivery of assets is to be reoptimized, in response to the time-to-trigger being achieved, re-optimizing, by a route optimization module of the continuous delivery platform, the set of routes to provide a revised set of routes, and conveying at least one route of the revised set of routes to a delivery personnel, the at least one route being different from any route in the set of routes, and being executed during the period.

Abstract: A method for processing digital transactions includes receiving, from one or more source systems, a plurality of uncategorized digital transactions; and prioritizing the uncategorized digital transactions according to a key performance indicator (KPI) of each uncategorized digital transaction. A subset of the prioritized uncategorized digital transactions is communicated to a labeling system configured to apply a category label to each digital transaction. A subset of categorized digital transactions corresponding to the subset of the prioritized uncategorized digital transactions is received from the labeling system. Category label and a label confidence value are applied to each transaction of a remaining set of uncategorized digital transactions based on the subset of categorized digital transactions. The label confidence value is indicative of a confidence that a given label was correctly applied to a given transaction.

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 include determining a set of routes for delivery of assets within a delivery network based on realized and forecasted demand for a period, during at least partial execution of the set of routes, receiving real-time data representative of delivery of assets, and updated demand forecasts, determining, by an optimization controller, a time-to-trigger, and a cut-off time, and an updated demand forecast, the time-to-trigger defining an interval, at which the set of routes for delivery of assets is to be reoptimized, in response to the time-to-trigger being achieved, re-optimizing, by a route optimization module of the continuous delivery platform, the set of routes to provide a revised set of routes, and conveying at least one route of the revised set of routes to a delivery personnel, the at least one route being different from any route in the set of routes, and being executed during the period.

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: A method for processing digital transactions includes receiving, from one or more source systems, a plurality of uncategorized digital transactions; and prioritizing the uncategorized digital transactions according to a key performance indicator (KPI) of each uncategorized digital transaction. A subset of the prioritized uncategorized digital transactions is communicated to a labeling system configured to apply a category label to each digital transaction. A subset of categorized digital transactions corresponding to the subset of the prioritized uncategorized digital transactions is received from the labeling system. Category label and a label confidence value are applied to each transaction of a remaining set of uncategorized digital transactions based on the subset of categorized digital transactions. The label confidence value is indicative of a confidence that a given label was correctly applied to a given transaction.

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.