Abstract: Systems and methods for classifying gaps in network activity as normal or anomalous are disclosed. A computer system can identify time gaps between successive network events, which can comprise communications or interactions between entities or devices on a network. The computer system can identify network event data records corresponding to network events that occurred both before and after the identified time gaps. The computer system can use data contained in network event data records corresponding to these network events to derive data features that can be used to train a machine learning to classify time gaps based on those features. After training the machine learning model, the computer system can then extract data features corresponding to unlabeled time gaps, and input those data features into the trained machine learning model in order to classify those time gaps as normal or anomalous.

Abstract: A method, system and computer program product for data deduplication in a travel and transportation data processing system includes loading into memory for comparison from a database of a multiplicity of multi-field records, a pair of two different multi-field records and submitting the pair to a similarity model that correlates a companion passenger with a specified individual so as to indicate a probability of duplication whenever the companion passenger appears in a pair of records submitted to the model for comparison. Thereafter, if the model produces a high probability, the pair is automatically merged into a single record without manual intervention, but if the model produces a medium probability, the pair is placed in a queue pending manual intervention and manual merging, and if the similarity model produces a low probability, the pair is omitted from consideration of merging. Finally, the process repeats for each other pair of different multi-field records in the database.

Abstract: A text classification method includes loading a corpus of text that different words organized as different collections of comments and concurrently submitting each of the comments to a topic modeler and a sentiment analysis engine, and receiving for each of the comments, a set of topics likely to be associated with a corresponding one of the comments and an associated sentiment. Then, a visualization is generated of each of the comments, and each of the comments are represented in the visualization with a respective graphical image. Groups of the graphical images are clustered according to topic common to associated ones of the comments, arranged by sentiment, and a corresponding common topic is displayed in connection with each clustered group. In response to an activation of one of the graphical images, at least a portion of a represented one of the comments are displayed in a window of the user interface.

Abstract: A method, system and computer program product for data deduplication in a travel and transportation data processing system includes loading into memory for comparison from a database of a multiplicity of multi-field records, a pair of two different multi-field records and submitting the pair to a similarity model that correlates a companion passenger with a specified individual so as to indicate a probability of duplication whenever the companion passenger appears in a pair of records submitted to the model for comparison. Thereafter, if the model produces a high probability, the pair is automatically merged into a single record without manual intervention, but if the model produces a medium probability, the pair is placed in a queue pending manual intervention and manual merging, and if the similarity model produces a low probability, the pair is omitted from consideration of merging. Finally, the process repeats for each other pair of different multi-field records in the database.

Abstract: A method for predicting risk in a tour operation includes first ingesting into memory of a computing system, textual observations from past tour operations and then correlating the textual observations to a corresponding one of the past tour operations. Thereafter, each of the past tour operations may be classified according to risk to personal safety and each correlation and an associated risk may be stored in an index. Consequently, tour commentary of a contemporaneously offered tour may be later loaded into memory of the computing system, and the terms of the tour commentary matched to the textual observations of at least one of the past tour operations. Finally, an associated risk is retrieved for an entry in the index corresponding to the at least one of the past tour operations, a predicted risk is computed based upon the retrieved risk value, and the predicted risk is displayed in a display of the computing system in connection with the contemporaneously offered tour.

Abstract: Embodiments of the invention provide a method, system and computer program product for voyage-level prediction of a net promoter score (NPS) data set for a collection of passengers scheduled for transport by a vehicle. The method includes classifying a past set of completed voyages according to a discrete set of classifications, each referring to a different characteristic of a corresponding one of the completed voyages, ingesting survey responses from passengers of the completed voyages and correlating the responses to an associated one of the different classifications, scheduling a new voyage for a specific vehicle, determining a set of classifications for the new voyage, extrapolating hypothetical survey responses for the new voyage based upon the determined set of classifications for the new voyage and displaying the hypothetical survey responses in a display of an onboard computing system of the specific vehicle.