Abstract: In some embodiments, apparatuses and methods are provided herein useful for event detection relative to catalog items available for commercial sale. In some embodiments, there is provided a system for event detection relative to catalog items available for commercial sale including an interface; a memory; and the first control circuit. The first control circuit configured to execute the computer-implemented code to: receive event data corresponding to one or more events referred to in one or more online sources; determine a corresponding score for each of the event data based on a relative level of negativity; identify one or more topics and key phrases of one or more of the event data having at least a specified score; identify one or more catalog items that have a similarity to the one or more topics and key phrases; and output an indication.

Abstract: Systems and methods for unified attribute extraction are disclosed. A set of product data including at least one text-based description of each of the products in the set of products is received and at least one closed list attribute is extracted from the at least one text-based description of each of the products. The at least one closed list attribute is extracted by an attribute extraction model configured to implement an extended conditional random field (XCRF) process. A set of attributes including each of the at least one closed list attributes extracted from the at least one text-based description of each of the products in the set of products is output.

Abstract: This application relates to apparatus and methods for training machine learning models using supervised, or semi-supervised, learning. In some examples, a computing device obtains training data that includes labelled, and unlabeled, data for training a machine learning model. The computing device applies the machine learning model to the training data to generate output data. The machine learning model executes with a plurality of coefficients applied to a plurality of hyperparameters. The computing device further applies a loss model to the training data and the output data to generate a loss value. Based on the loss values, the computing device determines updated values for the plurality of coefficients of the machine learning model. The computing device may continue to determine updated values for the plurality of coefficients until one or more conditions are satisfied. The computing device may then store the final coefficient values in a data repository.

Abstract: Systems and methods for unified attribute extraction are disclosed. A set of product data including at least one text-based description of each of the products in the set of products is received and at least one closed list attribute is extracted from the at least one text-based description of each of the products. The at least one closed list attribute is extracted by an attribute extraction model configured to implement an extended conditional random field (XCRF) process. A set of attributes including each of the at least one closed list attributes extracted from the at least one text-based description of each of the products in the set of products is output.

Abstract: System and methods for personalizing an application include an application server for hosting an application that is executed on a wireless device, the server being configured to monitor usage of a user interface including an interaction between a user of the application and one or more user interface elements and present an updated user interface comprising one or more additional user-interface elements based on the usage.

Abstract: The disclosed embodiments illustrate a method for real time management of transportation services. The method includes determining a discrete control process with respect to a plurality of states of a vehicle. Each state in the plurality of states corresponds to a station and a count of vacant seats in the vehicle at the station. A set of rules is generated to maximize a key performance parameter of the vehicle, based on at least the determined discrete control process. A valuation parameter is determined, in real time, for one or more vacant seats in the vehicle at each of one or more subsequent stations based on the generated set of rules. The determined valuation parameter for the one or more vacant seats corresponding to each of the one or more subsequent stations is transmitted to a plurality of mobile computing devices associated with a plurality of commuters.

Abstract: System and methods for personalizing an application include an application server for hosting an application that is executed on a wireless device, the server being configured to monitor usage of a user interface including an interaction between a user of the application and one or more user interface elements and present an updated user interface comprising one or more additional user-interface elements based on the usage.

Abstract: The disclosed embodiments illustrate a method for real time management of transportation services. The method includes determining a discrete control process with respect to a plurality of states of a vehicle. Each state in the plurality of states corresponds to a station and a count of vacant seats in the vehicle at the station. A set of rules is generated to maximize a key performance parameter of the vehicle, based on at least the determined discrete control process. A valuation parameter is determined, in real time, for one or more vacant seats in the vehicle at each of one or more subsequent stations based on the generated set of rules. The determined valuation parameter for the one or more vacant seats corresponding to each of the one or more subsequent stations is transmitted to a plurality of mobile computing devices associated with a plurality of commuters.