Abstract: A processor may receive first sensor data associated with detected movement of a user in an environment. The processor may determine, using an AI model, based on the first sensor data, that the movement of the user is associated with a first object. The processor may retrieve sensory data associated with the first object from a repository. In some embodiments, the sensory data may include at least one of auditory, olfactory, and haptic data associated with historical user interactions with the first object. The processor may provide a first sensory signal to the user to indicate a location of the first object relative to a first location of the user.

Abstract: A method, computer system, and a computer program product for handheld demonstration is provided. The present invention may include creating an artificial human. The present invention may include determining that assistance of the artificial human is needed by a user. The present invention may include projecting the artificial human onto an augmented reality (AR) or virtual reality (VR) device of the user. The present invention may include monitoring the user's behavior. The present invention may include modifying the projected artificial human based on the user's monitored behavior.

Abstract: Data transformation and data quality checking is provided by reading data from a source datastore and storing the data into memory, performing in-memory processing of the data stored in memory, where the data is maintained in-memory for performance of the in-memory processing thereof, and where the in-memory processing includes performing one or more transformations on the data stored in memory, in which the data stored in memory is transformed and stored back into the memory and applying one or more data quality rules to the data stored in-memory, and based on performing the in-memory processing of the data stored and maintained in memory for the in-memory processing, loading to a target datastore at least some of the data processed by the in-memory processing.

Abstract: A computer-implemented method for displaying advertisements. The method includes associating feature metadata with a product video advertisement of a product. The method includes identifying, based on the feature metadata, a feature of the product corresponding with a section of the product video advertisement when a triggering event is detected during playing of the product video advertisement. The method includes displaying a second product video advertisement of a second product that includes the feature of the product.

Abstract: An approach is provided that trains an artificial intelligence (AI) system with a set of eating characteristics corresponding to a human subject. The eating characteristics include one or more eating patterns, health data, and activity data. The trained AI system generates a meal recommendation corresponding to the human subject. The meal recommendation includes a recommended meal time, and one or more food recommendations that are based upon a determined set of caloric needs pertaining to the human subject. The system automatically provides the generated meal recommendation at a time that is based on the recommended meal time using a voice-enabled virtual assistant that is accessible by the AI system.

Abstract: This disclosure relates to method and system for improving Wi-Fi performance in co-existing communication networks using learning methodologies. In recent times, most of telecom operators have expressed interest in deploying LTE (Long-Term Evolution) over the unlicensed spectrum. However, simultaneous use of unlicensed band (by operators using LTE and other Wi-Fi) presents coexistence challenges in terms of network performance especially for the Wi-Fi. The disclosed techniques enable improving the Wi-Fi performance in the co-existing communication networks based on learning methodologies. The disclosed techniques improve Wi-Fi performance based on several steps that includes detecting an interfering channel, and further identifying an optimal channel to mitigate the interference caused by the detected interfering channel. The optimal channel is identified based on an optimization technique, wherein the optimization technique is a reinforcement learning technique based on a Q-learning.

Abstract: Aspects of the present invention disclose a method for identifying items that can utilize stabilized delivery in a delivery system. The method includes one or more processors obtaining data indicating a delivery item from an internet of things (IoT) enabled device. The method further includes determining information associated with the delivery item. The method further includes determining whether the information of the delivery item is associated with stabilized delivery. The method further includes scheduling delivery of the delivery item with a delivery vehicle, based at least in part on the information associated with the delivery item.

Abstract: An embodiment for generating an electronic coupon based on user preferences is provided. The embodiment may include receiving real-time and historical data relating to one or more reward coupons. The embodiment may also include identifying a contextual situation of the user and one or more preferences of the user regarding a coupon reward type. The embodiment may further include identifying one or more vendors that match with the one or more preferences of the user. The embodiment may also include generating one or more electronic coupons and presenting the one or more generated electronic coupons to the user. The embodiment may further include in response to determining the one or more generated electronic coupons match at least one preference of the user, adding the one or more generated electronic coupons that match the at least one preference of the user to an account of the user.

Abstract: Embodiments for delay-induced miscommunication reduction are provided.

Abstract: State of the art networking solutions are tightly coupled and proprietary in nature due to multiple vendors in the networking domain. Embodiments of the present disclosure provide a method and system for management and orchestration of heterogeneous network environment using dynamic, robust and network aware microservices. The method enables a platform for automatically and dynamically identifying appropriate group of microservices in accordance with network type and service type specified by the user, thus providing a solution that generates network aware microservices for each network in the heterogeneous network landscape. Furthermore, the system manages the identified microservices for each of the network by managing the life cycle of these microservices. The right life cycle management and coordination of the microservices for the network is in-line with desired goals/business logic, in a reliable and scalable manner, in heterogeneous network environments.

Abstract: A first message is detected. The first message is directed towards a first messaging recipient in a messaging application. The first message contains one or more content items. A set of one or more candidate messaging recipients is determined based on the first message and based on a content analysis of the one or more content items. A second messaging recipient is identified from the set of one or more candidate messaging recipients. The identification is based on the content analysis. The first message is routed to the second messaging recipient. The first message is routed in response to the identifying the second messaging recipient.

Abstract: Fifth generation and beyond (5G+) systems are expected to adopt new network architectures, services, and deployment schemes for compatibility with the latest technologies and end user's needs. With increase in user equipment (UE), also come variety of advanced applications and use-cases, wherein each application type has its own KPI requirements. Existing resource allocation schemes in cellular networks are not able to handle such dynamic requirements due to which network slice can lead to unwanted mismanagement of resources. Present application provides systems and methods for application-aware dynamic slicing in radio access network (RAN), wherein RAN slicing is proactively managed by learning historical slice demands and consumptions. Once slices are created, the system allocates resources to user equipment by following optimal inter-slice and intra-slice mechanisms based on application type(s), traffic demand(s) and wireless characteristics of UE.

Abstract: A method includes: determining, by the computing device, an activity associated with a physical object in a physical environment, the physical object being a physical object about which a user lacks knowledge; retrieving, by the computing device and from a digital library, a digital object that is associated with the activity; personalizing, by the computing device, the digital object, the personalizing being based on feedback from prior interactions of the user with the digital object; generating, by the computing device, an augmented reality activity including the determined activity, the augmented reality activity comprising a reactive association between the personalized digital object and the physical object; and generating, by the computing device, an augmented reality animation that comprises the augmented reality activity, the physical object, and the personalized digital object.

Abstract: A computer-implemented method according to one embodiment includes receiving a training data set to be applied to a model; selecting a subset of the training data set as a sample set; for each of a plurality of predetermined augmentations, applying the predetermined augmentation to the sample set to create an augmented sample set, training the model with the augmented sample set, determining a performance of the trained model, and assigning a weight to the predetermined augmentation for the training data set, based on the determined performance; and selecting one or more of the plurality of predetermined augmentations to be applied to the training data set before the training data set is applied to the model, based on the weight assigned to each of the plurality of predetermined augmentations.

Abstract: A computer-implemented method according to one embodiment includes applying a predetermined augmentation to the sample set of training data to create an augmented sample set, training a model with the augmented sample set, determining a performance of the trained model, and assigning a weight to the predetermined augmentation for the training data set based on the determined performance. A determination is made as to whether to apply the predetermined augmentation to a larger training data set before the training data set is applied to the model, based on the weight assigned to the predetermined augmentation.

Abstract: Recommendations are made for granular traffic thresholds for a plurality of DDoS attack mitigation appliances that act as a set appliances. The set of appliances can be those commonly found in highly available networks, active-active or active-passive appliances, disaster recovery data centers, backup appliances, etc.

Abstract: A system may monitor an appendage gesture with a smart device, extrapolate a gesture direction, select an item on a display based on the gesture direction, and display the item on a second display on the smart device.

Abstract: An approach is provided in which the approach establishes a geo-fence around a user in response to the user invoking a video conversation corresponding to a conversational context. The approach determines an action in response to detecting an entity crossing the geo-fence. The action is based on the entity and the conversational context of the video conversation. The approach invokes the action by transmitting a message to a device in proximity to the entity.

Abstract: A device may receive customer data, and may identify unique communication channels associated with the customer data. The device may determine, based on the customer data, an optimal order for a Markov chain model, and may determine a model accuracy of the Markov chain model based on the optimal order. The device may transform transitions in the Markov chain model, based on the customer data, to generate transformed transitions, and may process the customer data, with a multi-level indexing model and based on the unique communication channels and the transformed transitions, to generate sparse matrices. The device may determine removal effects and steady state values for the sparse matrices, and may determine attribution weights for the unique communication channels based on the Markov chain model with the optimal order, the removal effects, and the steady state values. The device may perform actions based on the attribution weights.

Abstract: Aspects of the present invention disclose a method for managing aggregated comments of a forwarded media based on the sentiments of the forwarded media and relevance to a user. The method includes one or more processors identifying a user based at least in part on information provided by the user. The method further includes accessing user activity data utilizing the information provided by the user. The method further includes generating a first profile corresponding to the user based at least in part on the user activity data. The method further includes determining one or more preferences of the user based at least in part on the generated first profile. The method further includes identifying segments of textual data of forwarded media the user receives based at least in part on the preferences of the user, wherein the textual data corresponds to a comment associated with the forwarded media.