Abstract: An operation management apparatus includes: a plan generator that generates a travel plane for each of a plurality of vehicles which form a vehicle line and which travel autonomously along a prescribed travel path; a communication device that transmits the travel plan to a corresponding vehicle; and a judging unit that judges necessity of an addition of a vehicle to the vehicle line and an elimination of a vehicle from the vehicle line. When it is judged that the addition of the vehicle is necessary, the plan generator determines a position of addition of a new vehicle in the vehicle line based on at least one of travel information and passenger information transmitted from each of the plurality of vehicles, and generates a travel plan for adding the new vehicle at the position of addition.

Abstract: The present disclosure provides a method comprising receiving a ride request from a user having a user profile, the ride request including a requested drop-off location within a service area and the user profile specifying at least one drop-off location preference parameter; querying a database to obtain data regarding a condition of the requested drop-off location, wherein the data is collected by a plurality of vehicles traversing the service area and equipped with at least one sensor and at least one imaging device; determining whether the obtained data satisfies the at least one drop-off location preference parameter; and determining at least one alternative drop-off location within a first distance from the requested drop-off location if the obtained data does not satisfy the at least one drop-off location preference parameter.

Abstract: Techniques and architectures for managing one or more data structures and/or distributing real-time data associated with the one or more data structures are discussed herein. For example, the techniques and architectures may implement data structures to manage data associated with one or more data-streaming events. The techniques and architectures may provide visualizations to view aspects of the data structures, the one or more data-streaming events, and/or other data associated with the data structures. The techniques and architectures may also facilitate control access to the data structures and/or data associated therewith.

Abstract: Embodiments of the invention are directed to systems, methods, and computer program products for utilizing machine learning to calculate product replacement cycle times and predict resource transfers associated with said product replacements. As such, the system allows for receipt of resource transfer datasets which are processed along with historical datasets via a machine learning engine. The system may then identify data trends and generate predictions of future resource transfers associated with product or service lifecycles. Furthermore, the system may also identify potential merchants or other third-party systems which may be associated with the predicted future transfers.

Abstract: Provided is a process including obtaining a set of geographic places of interest, obtaining a set of location identifiers of devices, determining a set of tiles based on the set of geographic places of interest, and determining a subset of the set of location identifiers of devices based on members of the subset of the set of location identifiers. The process also includes determining a subset of the devices based on the subset of the set of location identifiers of devices and determining a set of dwell-based values based on the subset of the set of devices. The process also includes determining a set of threshold-satisfying tiles based on the set of dwell-based values and storing the set of threshold-satisfying tiles in a computer system.

Abstract: A method and apparatus for managing events. A stream of event data for a plurality of events corresponding to an entity is received. A timeline for the plurality of events is generated based on the stream of the event data. A set of event chains is identified based on the timeline, the event data, and a set of policies. A trigger related to an event belonging to an event chain of the set of event chains is detected. A number of effects of the trigger is identified in which the number of effects includes at least one of a number of insights, a number of actions, or a number of opportunities.

Abstract: This document describes techniques and apparatuses for enhancing data-analytic visualizations of a data analytics system. A computing device captures input data and output data associated with a data-analytic visualization generated by an advanced user using the data analytics system. The input data and output data are mapped together for defining the data-analytic visualization generated. A machine learning model is trained relative to the mapped input data and output data for generating the data-analytic visualization. During a normal usage of the data analytics system by a user, the trained model generates data-analytic visualizations to suggest to the user responsive to input data from the user. An optional threshold is set and applied relative to the data-analytic visualizations generated. If a data-analytic visualization meets the threshold, the data analytics system reports the data-analytic visualization.

Abstract: Techniques are described for automatically generating meta-alerts based on operational and security risk alert volumes for an entity. In particular, a central device receives entity alert information from other devices in a computer system of an enterprise business, which may have office branches that are each staffed by employees. The central device compares alert volumes of a given entity for a given period of time (e.g., a month) to one or more baseline thresholds determined based on the average alert volume of peer entities during the same period of time and the entity's own historical alert volumes to identify spikes or increases in the volume of alerts for the given entity. If the entity is trending high for the period of time, the central device generates a meta-alert to bring awareness to the relatively high volume of alerts identified for that entity.

Abstract: A neurological profile associated with introversion/extroversion levels, simultaneous visual element processing capability, and/or dynamism processing capability, etc., is determined to select market categories and stimulus material targeted to the particular neurological profile. The neurological profile is determined using information such as user input, user activity, social and environmental factors, genetic and developmental factors, and/or neuro-response data. The neurological profile can be matched with corresponding neurological profile templates to select market categories and stimulus material.

Abstract: Methods and systems for controlling production resources in a supply chain are described. The system automatically generates predicted supply chain operational metrics across a nodes of a supply chain. The system automatically infers causal factors that impact the predicted supply chain operational metrics. The causal factors include a change to a utilization of the production resource. The system communicates a user interface including production runs being scheduled on the production resource including a user interface element representing the scheduling of the production run associated with a value at risk. The system receives input causing a change to the utilization of the production resource. The change to the utilization of the production resource impacts the predicted supply chain operational metrics including the value at risk associated with the scheduling of the production run.

Abstract: A graphical user interface (GUI) for a sponsor portal system includes a first display area that persistently displays a list of a plurality of tabs and a second display area. When the GUI is executed by a computing device of a sponsor of the plurality of sponsors, the second display area is dynamically updatable to display a scrollable list of customers of the sponsor, a list of vendors approved by the sponsor, and a list of active offers. In response to selection of an active offer, the GUI is configured to display a draft offer message and an approval control. In response to selection of the approval control, the sponsor engine is configured to transmit an interactive graphic to mobile computing devices, the interactive graphic configured to communicate information to the mobile computing devices for display on a screen of limited size.

Abstract: A system and method for identifying a user is described. The system identifies collaboration metrics based on user interaction data of users of an application from an enterprise. The system accesses enterprise organizational data of the enterprise and identifies topic data from the user interaction data and the enterprise organizational data. The system trains a machine learning model based on the collaboration metrics, the enterprise organizational data, and the topic data.

Abstract: An invention is referred to systems and methods of digital calculations or data processing, specifically designated for special functions, for systems and methods, which allow a consolidated search for information and data base structuring in particular, collection of data and its registration in a digitalized form for the further input into hardware-software system and displaying on devices of users on demand. The system and method use hardware-software system including a hardware module and a data processing module. The hardware module contains central server and a complex of external devices of users, connected with the mentioned central server by data interchange means. The central server is connected with external e-mail servers by e-mail sending/receiving media.

Abstract: The present application includes a method and system for real-time scheduling reallocation. The system receives a schedule which allocates customer service representatives (CSRs) to channels and queues based on analytics rules as well as the forecast work patterns and information on CSR skills and shift patterns. The system then monitors adherence to the schedule by comparing the difference between forecast and current volume and type of work to a reallocation threshold at predetermined intervals. If the difference extends beyond the reallocation threshold, the system reallocates CSRs to update the schedule.

Abstract: The present disclosure provides systems and methods that learn a loss function that, when (approximately) minimized over the training data, produces a model that performs well on test data according to some error metric. The error metric need not be differentiable and may be only loosely related to the loss function. In particular, the present disclosure presents a convex-programming-based algorithm that takes as input observed data from training a small number of models and produces as output a loss function. This algorithm can be used to tune loss function hyperparameters and/or to adjust the loss function on-the-fly during training.

Abstract: Arrangements for synchronously tracking and controlling events across multiple computer systems are provided. In some examples, a user may register with a system and user data may be received. In some arrangements, historical data associated with the user may also be received. Machine learning may be used to analyze the historical data and/or user data and a first recommendation for an item may be generated and transmitted to the user. Upon receiving acceptance of the recommendation, the system may request data from one or more entities. For instance, entity data associated with current inventory, availability of items, layout of locations, and the like, may be received. Based on the received data, a list of items for capture and/or an item capture route may be generated. In some examples, the item capture route may include step-by-step or map-based instructions to capture the items on the list.

Abstract: Systems and methods for calculating and displaying implicit popularity of products are disclosed. In embodiments, a computer-implemented method, comprises: determining, by a computing device, a set of consumer actions related to a product based on recorded consumer interaction data, wherein the set of consumer actions comprise a plurality of different physical actions of multiple consumers over a span of time; aggregating, by the computing device, the set of consumer actions by type of physical action over time to produce aggregated action event data; calculating, by the computing device, an implicit popularity number for the product based on the aggregated action event data; and sending, by the computing device, a display category to a product display device associated with the product based on the implicit popularity number, wherein the display category represents a measure of consumer popularity of the product.

Abstract: Examples apparatus disclosed herein are to determine a plurality of weights based on a data structure having elements corresponding to pairings of ones of a plurality of demographic partition statistics and ones of a plurality of baseline demographic statistics obtained for a target population, the demographic partition statistics corresponding to a plurality of demographic partitions of a sample population, a first element of the data structure to combine a first one of the demographic partition statistics with a first one of the baseline demographic statistics of the target population based on a first value corresponding to a numerator term of an expression and a second value corresponding to a denominator term of the expression, the weights corresponding respectively to the demographic partitions of the sample population. Disclosed example apparatus are also to adjust the attribute data based on the weights to determine ratings data for the target population.

Abstract: Embodiments of the invention are directed to techniques that include predicting, by a computer system, a number of predicted opportunities and signatures of the predicted opportunities expected in a time window. Based on the signatures of the predicted opportunities, the computer system generates a listing of entities ranked according to signatures of the predicted opportunities. The computer system selects the entities to be assigned to the predicted opportunities based, at least in part, on computing capacity related to sales while accounting for any current opportunities having been assigned to the entities.

Abstract: The present application includes a method and system for real-time predictive scheduling. The system receives information from at least one workload input and at least one personnel input, calculating an initial schedule based on the information and on analytics rules in a scheduling analytics engine. The system then allocates incoming workloads to customer service representatives according to the initial schedule, while monitoring adherence to the initial schedule by calculating deviation from schedule adherence. If the deviation from schedule adherence exceeds an acceptable deviation from schedule adherence within the analytics rules, the system calculates an updated schedule.