Abstract: Systems and methods for prioritizing enhancement and/or improvements of features of a user application are disclosed. In at least one embodiment, a method includes retrieving analytics data generated by an analytics engine, where the analytics data includes data relating to user interactions with a feature of the user application. A plurality of vectors is generated from the analytics data. The plurality of vectors include vectors corresponding to user interactions with the feature. A priority is assigned to enhancing and/or improving the feature of the user application based on a weighted sum of the plurality of vectors.

Abstract: As an example, a server hosting a search engine may receive a search query and determine a searched time interval, a searched object, and a searched event. The server may select, based on the searched time interval, a portion of an object-event bipartite graph that was created using information gathered from social media sites. The server may compare attributes of individual events in the portion with attributes of the searched event to identify a set of relevant events. The server may determine objects associated with the relevant events and compare attributes of individual objects with the attributes of the searched object to identify a set of relevant objects. The search engine may provide search results that include the set of relevant objects ordered according to their similarity to the searched object.

Abstract: The present disclosure provides the planning of the next generation network which complements an existing telecom deployment to achieve the desired KPIs from the combined network for both macro and small cell planning in an existing network in a cost-effective method to deploy ODSC cells and Macro Cells in a heterogeneous network. Planning a next-generation network for an existing telecom operator is a large undertaking, utilizing precious man-hours and most importantly, weeks of work. Using an automated planning methodology to plan macro and small cells for a region like a city, state or even country, planners can deploy solutions to make the most optimum use of existing infrastructure. The invention proposes an automated approach to plan the preferred overlay telecom solutions in an area A being part of an existing telecom deployment.

Abstract: A system and method automatically refactor mature program code having interdependent features to remove instructions pertaining to features that are no longer used. To facilitate reduction of the number of feature dependencies to test, instrumentation data are analyzed to determine which of the available features are in actual use. A graph of feature dependencies is built based on the program configuration, and the program code is simulated, according to existing testing protocols, with various combinations of features disabled to determine whether the program continues to function without error. When features are found that can be safely removed, the codebase is automatically refactored to eliminate the implementing code corresponding to the features. The refactored code then may be further automatically retested and deployed into the production environment.

Abstract: A system of one or more computers that are configured to generate documentation for microservice-based applications is disclosed. In at least one embodiment, usage information relating to actual usage by one or more users of a plurality of microservices, features extracted from user story information in a backlog tracker, and a call-context graph including information identifying calling functions and called functions in the plurality of microservices are used to generate data that is provided to a natural language generator, which uses the information to automatically generate documentation for the microservice based application.

Abstract: This application relates to apparatus and methods for automatically determining and providing carousels specifically curated for a user. In some examples, a computing device obtains user transaction data identifying in-store and/or online transactions, and user engagement data identifying user interactions with items and carousels from user's prior sessions. The computing device determines a sequential order for presentation of carousels with a set of item recommendations. For example, the computing device scores each potential carousel based on prior user interactions and transactions with items and carousels. The carousels are then ranked and subsequently presented to the user based on their corresponding scores.

Abstract: A method including receiving a basket including basket items selected by a user from an item catalog. The method also can include grouping the basket items of the basket into categories based on a respective item category of each of the basket items. The method additionally can include randomly sampling a respective anchor item from each of the categories. The method further can include generating a respective list of complementary items for the respective anchor item for the each of the categories based on a respective score for each of the complementary items generated using two sets of trained item embeddings for items in the item catalog and using trained user embeddings for the user. The two sets of trained item embeddings and the trained user embeddings can be trained using a triple embeddings model with triplets.

Abstract: Approaches are described for ranking images against image effects. An image effect is identified from a plurality of image effects. Each image effect includes instructions defining steps of modifying visual data of an input image to produce an output image. Preview images are generated, where for each data object of a plurality of data objects the instructions of the image effect are applied to a respective image corresponding to the data object to generate a preview image of the data object. Ranking scores are determined, where for each data object visual data of the respective image is analyzed using a set of evaluation criteria associated with the image effect to determine a ranking score of the image effect for the data object. Data is transmitted which causes at least one of the preview images to be presented on a user device based on the ranking scores.

Abstract: An apparatus comprises a processing device configured to select a given notification to be delivered from a first computing device to a second computing device and to determine (i) first notification metrics associated with one or more previous notifications delivered to a set of one or more computing devices including the second computing device and (ii) second notification metrics associated with a current status of the second computing device. The processing device is also configured to provide the first and second notification metrics to one or more machine learning models, to identify recommendations for modifying delivery of the given notification from the first computing device to the second computing device based on output of the one or more machine learning models, and to modify the delivery of the given notification from the first computing device to the second computing device based on the identified recommendations.

Abstract: In some examples, a server may determine a browsing history associated with a user, identify activities associated with purchasing a device, and determine features of the device. Individual features may be assigned a corresponding priority based on the browsing history. A machine learning algorithm may predict a configuration of the device based on the features and the corresponding priorities. The server may create a web page that describes a specification of the device based on the configuration and includes a comparison of at least some of the features of the device with other features of similar devices. The server may send a notification with a link to the web page. The web page may enable the user to modify the configuration and modify a price of the device. The server may receive a purchase order to purchase the device and instruct a manufacturing facility to build-to-order the device.

Abstract: A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media. The method can include training two sets of item embeddings for items in an item catalog and a set of user embeddings for users, using a triple embeddings model, with triplets. The triplets each include a respective first user of the users, a respective first item from the item catalog, and a respective second item from the item catalog, in which the respective first user selected the respective first item and the respective second item in a respective same basket. The method also can include randomly sampling an anchor item from a category of items selected by a user. The method additionally can include generating a list of complementary items using a query vector associated with the user and the anchor item.

Abstract: At least one embodiment of the disclosed system is directed to a computer-implemented method for operating a light projection technology keyboard of an Information Handling System. The computer-implemented method may include receiving electronic environmental condition data at a keyboard configuration system, and processing the electronic environmental condition data through a neural network of an adaptive configuration engine. The neural network may output one or more functions and/or visual settings to be used in configuring operation of the light projection technology keyboard. The light projection technology keyboard may be controlled based on the one or more functions and/or visual settings output by the neural network. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the methods.

Abstract: An apparatus comprises at least one processing device configured to perform steps of receiving a request to determine a path to a given web element of a web page of a web application and parsing the web page to detect web elements of the web page including the given web element and one or more additional web elements. The at least one processing device is also configured to perform steps of identifying one or more of the additional web elements having designated characteristics and selecting one of the identified web elements based at least in part on locations of the identified web elements, relative to the given web element, in a tree structure of the web page. The at least one processing device is further configured to perform the step of determining the path to the given web element from the selected web element.

Abstract: A system and method include migrating, by a migration controller, a first entity of a first subset of entities from a source site to a target site in a virtual computing system based on an asynchronous mode of replication. The system and method also include replicating, by the migration controller, data of a second entity of a second subset of entities from the source site to the target site based on a synchronous mode of replication in parallel with the migration of the first entity for dynamically adjusting a recovery time objective parameter.

Abstract: Methods, apparatus, and processor-readable storage media for detecting cashback and other related reimbursement frauds are provided herein.

Abstract: A method including building a recommendation triggering model. The method can include receiving, via a user device of a user through a network, an add-to-cart command associated with an anchor item for the user. The method further can include determining, in real-time after receiving the add-to-cart command, a recommendation for one or more complementary items of the anchor item for the user. The method also can include determining, in real-time after determining the recommendation, a recommendation confidence for the recommendation. The method additionally can include after determining the recommendation confidence, when the recommendation confidence is positive, transmitting, in real-time through the network, the one or more complementary items to be presented to the user via the user device. The method likewise can include after determining the recommendation confidence, when the recommendation confidence is not positive, refraining from transmitting the one or more complementary items to the user.

Abstract: A machine learning (ML) module that automates the screening of the news articles in the search results received from an online news aggregator and intelligently selects only those articles for presentation to a user that are really important in creating potentially new business transactions with the user's clients. Other non-relevant or marginally-relevant news are removed to avoid distractions. The ML module analyzes commercial information—such as, for example, the product/service offerings (current and in the near future) of the corporate entity employing the user, historical sales and marketing information related to the user's client, current account status of the client, and past business transactions with the client—to intelligently select the most relevant news articles for the user. The ML module goes beyond the existing news aggregator platforms by curating the aggregator-provided results and selecting only those news articles that hold promise in exploring new business opportunities with a client.

Abstract: Methods and systems are disclosed for migrating tasks between edge devices in an Internet of Things (IoT) system in a manner to generally minimize the total amount of time to execute and migrate the tasks. At least one embodiment includes a computer-implemented method for receiving a task for execution at an edge device; detecting whether a task migration condition exists at the edge device; dividing the task into a plurality of subtasks of equal data size b; and migrating at least some of the subtasks of data size b to a further edge device for execution. At least one embodiment designates 1˜n subtasks of size b for execution by the edge device and n+1˜N subtasks of data size b for execution by the further edge device and optimizes the total time for execution of the subtasks is optimized as a function of n.

Abstract: Methods and systems are disclosed for allocating tasks between apparatus in an IoT system in a manner to generally minimize the total amount of time to execute the tasks. At least one embodiment includes a computer-implemented method for allocating task processing between an internet of things (IoT) device and an edge device. The computer-implemented method includes collecting data from one or more sensors to execute a task having data size Xt; predicting a space complexity data size Xc for the task based on data size Xt, and allocating data for processing between the IoT device and edge device as a function of Xc. In at least one embodiment, the space complexity data size Xc is determined by applying Xt to the input of a long short-term memory neural network.

Abstract: In one embodiment, a method includes receiving, from a client system of a user, a user input comprising a plurality of n-grams, parsing the user input to identify one or more overall intents, hidden intents, and slots associated with the one or more n-grams, wherein at least one of the hidden intents is non-resolvable for being associated with partial slot information corresponding to an n-gram that has not been resolved to a particular entity identifier, wherein the partial slot information is associated with two more entity identifiers of two or more entities, respectively, sending, to the client system, instructions for prompting the user to select one of the entities to be associated with the non-resolvable hidden intent, resolving the non-resolvable hidden intent based on the entity identifier of the entity selected by the user, and generating a response to the user input based on the resolved hidden intent.