Abstract: A system with deep reinforcement learning based control determines optimal actions for major components in a commercial building to minimize operation costs while maximizing comprehensive comfort levels of occupants. An unsupervised deep Q-network method is introduced to handle the energy management problem by evaluating the influence of operation costs on comfort levels considering the environment factors at each time slot. An optimum control decision can be derived that targets both immediate and long-term goals, where exploration and exploitation are considered simultaneously.

Abstract: A data quality assessment and monitoring tool addresses inconsistency in large data sets from differing sources, determining data quality attributes such as completeness, conformity, validity, and accuracy. Flexible taxonomies and rollup strategies accommodate diverse business unit needs across a complex enterprise, and provides insight into individual entities' performance. An exemplary tool comprises a data importer for importing data from a data lake; a rules manager for generating rules and rule sets; a scoring engine for generating data quality scores; a job manager; a data profiler for running data assessment tasks and collating the data quality scores for a plurality of hierarchical data entity units; a hierarchical scoring aggregator for aggregating sets of data quality scores into a plurality of first tier aggregate data quality scores and to further aggregate the first tier aggregate data quality scores into one or more second tier aggregate data quality scores; and a reporting component.

Abstract: A method of transportation, comprising advertising to obtain customers to text or e-mail requests for transportation and receiving requests by text messaging for a ride from potential customers for transportation is disclosed. Responding to potential customers is by way of a response comprising ride information. Such ride information is also sent to a driver.

Abstract: A parking lot free parking space predicting method, apparatus, electronic device and storage medium are provided. The method comprises: building a parking lot association graph for parking lots in a region to be processed; as for any parking lot i, performing the following processing respectively: determining local space correlation information of the parking lot i at a current time according to environment context features of the parking lot i and neighboring parking lots which are in the parking lot association graph and connected to the parking lot i through edges; determining time correlation information of the parking lot i at the current time according to the local space correlation information, and predicting free parking space information of the parking lot i at at least one future time step according to the time correlation information of the parking lot i at the current time.

Abstract: Systems and methods described herein may involve receiving creative elements, each creative element comprising a visual element and a time. Each of the plurality of creative elements may overlap in time with each other. The visual elements of the associated creative elements may be displayed together in a time slot of a calendar corresponding to the overlapping time.

Abstract: Systems and methods are provided for scheduling objects having pair-wise and cumulative constraints. The systems and methods presented can utilize a directed acyclic graph to increase or maximize a utilization function. The objects can comprise satellites in a constellation of satellites. In some implementations, the satellites are imaging satellites, and the systems and methods for scheduling can use human collaboration to determine events of interest for acquisition of images. In some implementations, dominant edges are removed from the directed acyclic graph. In some implementations, dynamic weights are assigned to nodes associated with downlink events in the directed acyclic graph.

Abstract: Systems as described herein may include making recommendations for patterned purchases. Transaction information for a user that is associated with a plurality of merchants in a geographic location may be received. Frequencies of visits and transaction patterns associated with the plurality of merchants may be determined. Risk factors and a success rate that the user to complete shopping successfully may be determined. In a variety of embodiments, after detecting that the success rate falls below a threshold value, a recommendation for the user to shop at an alternative merchant and alternative time/date may be presented to the user.

Abstract: Methods and systems for operating a machine learning system are described. In an example, a device can receive an image and assign a set of pixels in the image as a digital representation of a livestock. The device can further train a machine learning model using the digital representation. The device can further run the machine learning model to generate prediction data relating to the livestock. The device can further generate output data relating to at least one activity among a livestock value chain. The at least one activity can correspond to a process to generate a commodity based on the livestock.

Abstract: Systems and methods are disclosed for providing a product to consumers by receiving the product from a manufacturer located in a first country; matching the products with a seller in the second country; managing delivery logistics by matching available third-party truckers and third-party warehouses in a second country based on proximity; forecasting demand using one or more neural networks for the manufacturer, the logistics organization, and the warehouses; and managing logistics for the manufacturer through a dashboard populated by the forecasted demand from the one or more neural networks.

Abstract: Systems and methods for identifying and mitigating non-compliances include determining an agent location of a money service business for review, obtaining a photograph and geographic coordinates of the agent location, and collecting field data at the agent location through a mobile application. Such information are sent from the mobile application to a central server of a third party vendor for a series of quality checks and stored at the central server. Such information may be used for further corrective action against the agent location reviewed.

Abstract: Embodiments for facilitating ride scheduling by a processor. An occurrence of an event associated with a user may be predicted based on user data. One or more ride scheduling parameters relating to the event may be determined. One or more ride scheduling models may be determined satisfying the ride scheduling parameters. Facilitate scheduling a vehicle for the user according to the ride scheduling models.

Abstract: A computer-implemented method modifies physical classroom resources in a classroom. One or more processors identify and quantify physical classroom resources in the classroom based on sensor readings received from sensors in a classroom. The processor(s) determine physical classroom resource constraints that impede learning by students in the classroom based on the sensor readings from the sensors in the classroom. The processor(s) detect one or more of the physical classroom resource constraints in the physical classroom resources identified by the sensor readings, and then adjust the one or more physical classroom resources based on the one or more detected physical classroom resource constraints.

Abstract: The present invention is associated with a computerized system that takes a subsequence of a credit card number, in particular the suffix (or last n digits), and transaction data associated with the cardholder. For each subsequence of the credit card number, a set of data may be used in order to uniquely identify the cardholder. The identification of the cardholder may be performed in a particular search space that is composed of all possible credit card numbers and includes the transaction data associated with the cardholder. In an exemplary embodiment, the computerized system is used to promote engagements between individual cardholders and merchants by effectuating marketing actions in combination with commercial transactions when products or subscriptions are purchased.

Abstract: Computerized systems for synchronizing multiple calendars are provided. User activity is monitored via sensors and user devices associated with the user. Monitoring user activity includes detecting calendar activity associated with a set of calendars that includes a first calendar. A first calendar event associated with the first calendar is detected. A second calendar included in the set of calendars and associated with the first event is determined. The second calendar is determined based on the user activity, the first calendar, or the first event. The second calendar may be determined based on a synchronization profile associated with the first calendar. The second calendar is updated to include at least a portion of the first event. The first event is synchronized and/or shared with the second calendar. Only selective portions of the event data of the first event may be provided to the second calendar.

Abstract: Examples provide a multi-stage cluster component that performs a multi-stage clustering analysis on a plurality of items in a category associated with a selected item using a set of interrelationship factors. The multi-stage cluster component generates a cluster of non-substitute item-pairs, a cluster of traditional substitute item-pairs, and a cluster of variety item-pairs. The set of interrelationship factors includes at least one of measure of association, brand similarity, pack-size similarity, demographic similarity, item description similarity, lift, and/or percentage same-basket variable. A propensity score is generated for each item-pair. The propensity score is utilized to identify traditional substitute items and variety substitute items. Each substitute item is ranked based on the generated propensity score. The ranking is used to identify potential low-performance items for removal from inventory.

Abstract: In some embodiments, image input data is received from multiple sources. The received image input data may then be aggregated and mapped to create a set of image input data. An event in the set of image input data may be automatically detected, such as by being triggered by a rule and an associated tag. An image mining result database may be updated by adding an entry to the database identifying each detected event and the triggering rule. An indication associated with the image mining result database may then be transmitted to a plurality of risk applications.

Abstract: Methods and apparatus to conduct surveys are disclosed. An example apparatus includes an activity sensor to generate activity information, and a location sensor to generate location information corresponding to a portable device carried by the person. The apparatus further includes a processor to: generate media monitoring information indicative of exposure of the person to at least one of an advertisement or a product; determine a number of exposures the person has had based on the media monitoring information; identify a survey question based on the number of exposures; determine a speed of travel of the person based on at least one of the location information or the activity information; and compare the speed of travel to a threshold. The apparatus also includes a communication interface to automatically offer the survey question via the portable device when the processor determines the speed of travel is beneath the threshold.

Abstract: Methods for providing multi-objective experiments with dynamic group assignment are provided. In one aspect, a method includes receiving, from a configuration component of an experiment management system, a plurality of objectives and at least one constraint for an experiment. The method also includes assigning a test population of the experiment into a plurality of groups. The method also includes determining a progress summary that predicts completion rates for the plurality of objectives according to the at least one constraint. The method also includes modifying a prioritization of the plurality of objectives to optimize the predicted completion rates. The method also includes receiving a request to add additional users into the test population. The method also includes distributing the additional users into the plurality of groups according to the modified prioritization. Systems and machine-readable media are also provided.

Abstract: A multi-dimensional human resource allocation adviser integrates with one or more employee skill set data sources and processes and aggregates both initial/static and dynamic skill set data from those sources. Machine learning algorithms are then used to normalize and rank the aggregated employee skills with respect to the skill set and requirements associated with a given task, project, or case. The set of employees determined to have employee skill sets that most closely match the skill set and other requirements associated with the given project, task, or case are then filtered based on rules and constraints determined by the requirements of the business and/or the client. The best employee match, or matches, remaining after the rules and constraints filtering are then recommended for assignment/allocation to the given task, project, or case.

Abstract: Systems and methods are described for automatically assigning roles for an incident to user profiles using machine learning techniques to optimize the overall suitability of the automatic role assignments and to adapt to manual role reassignments. One or more roles of a plurality of roles for an incident are automatically assigned to each user profile of a plurality of user profiles by the computer-based system applying a combinatorial optimization routine. An indication is displayed on a screen of a determined relative suitability of a first user profile for each role of the plurality of roles. The computer-based system is configured to receive a manual reassignment selection of a different role of the plurality of roles to be assigned to the first user profile and the combinatorial optimization routine is updated based on the manual reassignment selection.