Abstract: Systems and methods for executing queries on a bitmap index are disclosed. The system may receive a first data stream from a database and generate a bitmap index based on the first data stream. The system may receive an input selection of one or more data conditions from a user device and generate a Boolean expression based on the input selection. The system may query the bitmap index using the Boolean expression and generate a bitmap vector. The system may output a first data subset represented by the generated bitmap vector to a graphical user interface. The bitmap index may include probabilistic entries, and the system may validate the probabilistic entries by receiving a second data stream, identifying one or more entries correlated to the probabilistic entries, determining a divergence between the identified entries and the probabilistic entries, and updating parameters of a classifier model associated with the probabilistic entries.

Abstract: A system comprising: a skills data store; an employee action data store; at least one hardware processor; and one or more software modules that are configured to, when executed by the at least one hardware processor, retrieve skills data and employee action data from the skills data store and employee action data store, train a classification model, wherein training a classification model comprises performing feature preprocessing, generating an LDA topic vector and TF/IDF Word2Vec similarity scoring, and use AutoML to train ML models, and infer employee skills and levels based on the classification model and employee action data.

Abstract: Systems and computer-implemented methods are described for modeling card inactivity. For example, hierarchical modeling may be used in which a first level classifier may be trained and validated to predict whether a card will be inactive. For cards predicted to become inactive by the first level classifier, a second level classifier may be trained and validated to predict when the card will become inactive. The first level classifier may include a binary classifier that generates two probabilities that respectively predict that the card will and will not become inactive. The second level classifier may include a multi-class classifier that generates a first probability that the card will become inactive at a first time period (such as one or more months in the future) and a second probability that the card will become inactive at a second time period. The multi-class classifier may generate other probabilities corresponding to other time periods.

Abstract: Embodiments of systems and methods for resolving remote meeting conflicts using learned attributes and context information are described. In some embodiments, an Information Handling System (IHS) may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution by the processor, cause the IHS to: determine, based upon context information collected by the IHS, that a user of the IHS is more likely to attend a first remote meeting than a second remote meeting, where the first and second remote meetings are scheduled to take place, at least in part, concurrently; and in response to the determination, apply one or more settings to the IHS that are associated with the first remote meeting.

Abstract: Certain aspects of the present disclosure provide techniques for training and using predictive models to predict the occurrence of an event within a software application. An example method generally generating a spatially sampled data set for a set of users of a software application. The spatially sampled data set includes, for each respective user of the set of users, an amount of time the user has spent, a number of discrete portions of the software application the user has visited, and an indication of whether the user has completed a defined task. A spatio-temporally sampled data set for users in the spatially sampled data set is generated, including, for each respective user in the spatially sampled data set, a plurality of candidate timestamps. A predictive model is trained based on the spatio-temporally sampled data set.

Abstract: Systems and methods associated with providing content personalization are disclosed. In one embodiment, an exemplary method may comprise receiving first data including content preferences associated with an audience, receiving second data including an initial digital message being proposed for transmission to the audience, generating a recommendation data set based at least in part on the first data and the second data, wherein the recommendation data set identifies at least one recommended content type and at least one recommended message type, determining via a natural language generation machine learning model suggested content for the audience, and providing the suggested content for dissemination to the audience.

Abstract: Methods and systems are described herein for receiving a document (e.g., a technical paper), identifying sections of the document, and inputting each section into a corresponding machine learning model that has been trained using previously reviewed documents to process text and other data within a specific section. The machine learning model may output a score indicating the degree of compliance to a particular standard of a particular document. In addition, various recommendations for content to be added to the document may be identified and provided to the user along with the score for each section.

Abstract: The disclosure includes systems and methods for determining a change window for taking an application off-line. The systems and methods include mapping application programming interfaces (APIs) to one or more applications, and based on the API mapping, determining a priority level for each of the applications. A network traffic volume for each of the APIs mapped to the applications is predicted. Based on the predicted network traffic volume and the priority level of each of the applications, the systems and methods determine a change window for taking the applications off-line.

Abstract: Systems, methods, and apparatus for machine learning task compartmentalization and classification are disclosed. An example method comprises receiving, from a first computing device, user defined parameters associated with at least one user, receiving, from a second computing device different from the first computing device, auxiliary data associated with the at least one user, generating, by a third computing device, at least one work profile based on the received user defined parameters and auxiliary data, and determining, by the third computing device, an affinity between a task component and the generated at least one work profile.

Abstract: Implementations described herein relate to methods, systems, and computer-readable media to generate an alert or recommendation based on an activity log. In some implementations, a computer-implemented method includes receiving, at a processor, an activity log associated with one or more enterprise sub-processes for a first time period, determining, at the processor, change context data based on a comparison of the entity data and the associated interaction data with corresponding entity data and associated interaction data of a second time period, analyzing the change context data to determine atomic event data, providing the atomic event data associated with the enterprise process as input to a trained machine learning model, determining, using the trained machine learned model and the atomic event data, a predicted future state of the enterprise process, and generating and transmitting an alert or recommendation to one or more data sinks associated with the enterprise process.

Abstract: Lighting devices and methods utilize multiple independently controllable groups of solid state light emitters of different dominant wavelengths, with operation of the emitter groups being automatically adjusted by processor(s) to provide desired illumination. Operation of the emitter groups may be further affected by sensors and/or user input commands (e.g., sound patterns, gesture patterns, or signal transmission). Operation may be adjusted to compensate for presence, absence, intensity, and/or color point of ambient or incident light. Presence of five or more groups of solid state light emitters provide desirable luminous flux, color point, correlated color temperature (CCT), color rendering index (CRI), CRI R9, and luminous efficacy characteristics of aggregate emissions over a wide range of CCT values, and may permit adjustment of vividness (e.g., relative gamut) and/or melatonin suppression characteristics for a selected color point or CCT.

Abstract: In one embodiment, a method includes receiving user behavior data and contextual information associated with the user behavior data, the contextual information including a first data portion associated with a first context type. The method includes generating, from the user behavior data and the contextual information using a hashing algorithm, a first heterogeneous hash code including a first portion representing the user behavior data and a second hash code portion representing the first data portion associated with the first context type. The method includes accessing a second heterogeneous hash code including a third hash code portion representing a second data portion associated with the first context type. The method includes comparing the first heterogeneous hash code with the second heterogeneous hash code including determining similarity between the second hash code portion of the first heterogeneous hash code and the third hash code portion of the second heterogenous hash code.

Abstract: This application relates to automatically scheduling timeslots, such as timeslots for scheduling item pickups and deliveries. The embodiments may employ machine learning process to determine, for each of a plurality of timeslots, a timeslot capacity. The embodiments may further determine a time as to when each of the plurality of timeslots become available for selection, such as on a webpage. In some examples, the time determined to make available for selection each of the plurality of timeslots is based on a predetermined amount of time before the timeslot. Further, the embodiments may provide for display each of the plurality of timeslots at the determined time. The embodiments may further include receiving a selection of one of the plurality of timeslots, and scheduling a pickup or delivery based on the selected timeslot. The machine learning processes may be trained with features generated from historical timeslot data and workforce availability.

Abstract: A method for predicting a price of any subtractively manufactured part utilizing artificial intelligence at a computing device. The method comprises receiving a manufacturing request datum, wherein the manufacturing request datum further comprises at least an element of user mechanical part data, selecting a correlated dataset containing a plurality of data entries. The method further comprises generating, at a clustering unsupervised machine-learning model, at least a first correlated compatible part element, receiving, at a supervised machine-learning model, a first training set, generating, at a supervised machine-learning model as a function of the first training set, an external price output, and determining a price ratio output, wherein determining the price ratio output further comprises generating a loss function of a part specific variable and minimizing the loss function.

Abstract: A method comprises receiving at least one natural language input corresponding to at least one task, and analyzing the at least one natural language input using one or more machine learning models to determine one or more parameters of the at least one task. One or more skills and/or availabilities of respective ones of a plurality of resources are identified. The method further comprises identifying at least a subset of the plurality of resources to perform the at least one task based at least in part on the one or more parameters and on the one or more skills and/or the availabilities. The at least one task is routed to one or more resources of the subset.

Abstract: Systems and methods for monitoring an operator of an asset are described herein. The method includes receiving training data, the training data comprising training sensor data associated with one or more tasks performed by a plurality of operators of different skill levels and under different performance impairments. The method can also include training a machine learning model to recognize one or more operator conditions based on the received training data and receiving sensor data from a plurality of sensors associated with the asset or the operator. The method can further include determining an operator condition of the operator based on the received sensor data and the machine learning model and taking one or more actions in response to the determined operator condition.

Abstract: Providing a method for real-time testing and monitoring of a business process management system in order to identify commonly failing parameters. Machine learning methods are used to run multiple rounds of testing of the business process management system to more accurately identify commonly failing parameters and to modify the business process by removing those identified parameters from future rounds of testing.

Abstract: Systems and methods are provided herein for performing one or more actions based on kinematic data. An operator management module may obtain video input data depicting a two-dimensional representation of a subject during performance of an activity. A set of points of the subject may be identified based at least in part on a machine-learning model. A 3D representation of the subject may be generated based at least in part on the points identified. Kinematic data related to the subject may be generated utilizing the 3D representation of the subject. Any suitable number of suggested actions may be performed based at least in part on the kinematic data.

Abstract: Methods and apparatus for autonomous vehicle scheduling are disclosed herein. An example apparatus includes memory including machine readable instructions and processor circuitry to execute the instructions to determine that a calendar request for a vehicle is associated with a location or a route previously associated with the vehicle, the calendar request to be generated via a user interface application; generate a predicted request for the vehicle in response to the determination that the calendar request is associated with the location or the route previously associated with the vehicle; and generate a prompt to be presented via the user interface application, the prompt associated with the predicted request for the vehicle.

Abstract: To reduce a leakage current of a transistor so that malfunction of a logic circuit can be suppressed. The logic circuit includes a transistor which includes an oxide semiconductor layer having a function of a channel formation layer and in which an off current is 1×10?13 A or less per micrometer in channel width. A first signal, a second signal, and a third signal that is a clock signal are input as input signals. A fourth signal and a fifth signal whose voltage states are set in accordance with the first to third signals which have been input are output as output signals.