Abstract: An autonomic function executing in an artificial intelligence environment determines that a fused model responsive to a new problem space has below a threshold level of accuracy in the new problem space. A spliced layer in the fused model is autonomically cloned, the spliced layer having been extracted from a second model and inserted at a location in the fused model. The cloned layer is autonomically inserted at a second location in the fused model. An automatically constructed vector transformation transforms an output vector of a previous layer in an immediately previous location in the model relative to the second location. The cloned layer is automatically fused in the fused model using the transformed output vector as input to the cloned layer, forming a deep fused model that has a revised accuracy that is higher than the accuracy relative to an ontology of the new problem space.

Abstract: Aspects of the present invention disclose a method for routing one or more autonomous vehicles to minimize a density of autonomous vehicles and passengers passing through network areas with oversubscribed bandwidth. The method includes one or more processors determining a bandwidth requirement of a first autonomous vehicle. The method further includes determining respective bandwidth requirement for one or more additional autonomous vehicles utilizing a wireless network. The method further includes determining a total bandwidth capacity of one or more nodes of the wireless network. The method further includes determining routing instructions from a current location of the first autonomous vehicle to a destination of the first autonomous vehicle based at least in part on the bandwidth requirement of the first autonomous vehicle and the total bandwidth capacity of the one or more nodes of the wireless network.

Abstract: A method, computer system, and a computer program product for filtering a phone call are provided. An incoming phone call to a phone is detected. Call metadata from the incoming phone call is received. The call metadata is compared to entries of a learned relationship filter. The entries of the learned relationship filter are obtained by monitoring behavior of a phone user on the phone during previous calls to the phone and application usage on the phone so that learned relationships to the phone user are identified and saved. The learned relationship filter provides a filtering response. The filtering response is performed to the incoming phone call.

Abstract: Machine learning model training corpus debiasing includes identifying an attribute of input text selected from the training corpus, the attribute including word(s) of the input text, and the attribute corresponding to an attribute class encompassing different possible class values, recognizing bias in the input text with respect to the attribute class, and generating output text corresponding to the attribute and imparting diversity with respect to the attribute class and relative to the input text, where generating the output text uses an optimization function based on loss objectives to minimize loss in the generated output text as compared to the input text.

Abstract: Non-intrusive image identification includes acquiring an image and connectivity data at a network-connected computing node via a data communications network. The image is captured by an image-capturing device remotely located from the computing node. The connectivity data is associated with one or more devices located within a predetermined vicinity of the image-capturing device. Connectivity data can be correlated with electronically stored networking data associated with the one or more devices to determine an identity of one or more device users. The correlating includes electronically searching one or more network-connected sources of networking data and, based on the connectivity data, matching the one or more devices to the one or more device users. Image-tagging data corresponding to one or more selected individual device users is generated, and the image is tagged with the image-tagging data for identifying one or more individuals appearing in the image.

Abstract: A method, system, and computer program product for generating context-based tailored emoticons within a communication scenario are provided. The method receives detects an emotion of a user within a communication stream. A set of candidate emojis are generated. A set of emoticons are generated from the set of candidate emojis and a representation of the user. The set of emoticons are presented to the user in a user interface on a computing device associated with the user. The method incorporates a selected emoticon of the set of emoticons into the communication stream with the selected emoticon being selected by the user from the user interface.

Abstract: Provided is a method, computer program product, and system for modifying an input command by a virtual assistant. A processor may receive an input command from a user. The processor may determine a contextual environment surrounding a virtual assistant. The processor may detect, based on the contextual environment, sensitive information in the input command. The processor may replace the sensitive information with generic information. The processor may respond to the input command with an output response based, in part, on the generic information.

Abstract: A method, a computer program product, and a computer system transmit an authenticated communication. The method being performed by a sending device includes transmitting a request to an authentication server indicating that the authenticated communication is to be transmitted. The method includes receiving a security token from a security device that is co-located with the sending device. The security token is received by the security device from the authentication server. The method includes generating the authenticated communication by incorporating the security token in a communication. The method includes transmitting the authenticated communication to a recipient device.

Abstract: Provided is a method, system, and computer program product for analyzing an electronic health record (EHR) using robotic process automation (RPA). A processor may analyze an EHR associated with a user. The processor may identify, based on analyzing the EHR, one or more health parameters that are outside of a threshold range. The processor may determine a set of recommended actions that may be performed to cause the health parameter to fall within the threshold range. The processor may analyze activity data associated with the user. The processor may identify, based on the activity data, a set of known activities performed by the user. The processor may correlate the recommended actions with the known activities to identify a subset of personalized actions that are specific to the user. The processor may send the subset of personalized actions to the user.

Abstract: A route from a first physical location to a second physical location is divided into a set of segments using a route optimization engine. Using a user response analysis model, a response to a physical environment associated with a segment in the set of segments is scored, the scoring resulting in a score. Using a content generation model and the score, the physical environment is augmented, the augmenting combining the physical environment and a generated environment.

Abstract: Classification and visualization of user interactions with an interactive computing platform is provided by building and providing a graphical user interface (GUI) of graphical elements for display on a display device. The graphical elements present (i) visualizations of user interactions between users and an interactive computing platform in progression of the users through tasks based on the user interactions and (ii) identified features of the user interactions relative to the tasks and progression of the users therethrough. The building and providing includes, for each of the tasks, building and providing a respective task element that reflects identified features of a set of user interactions of one or more users in progressing through that task. Building a task element for a task includes building the task element as a polygon having vertices corresponding to subtasks of the task and edges between the vertices.

Abstract: A request is received from a user to search a document for at least one search term. The document is analyzed to determine contextual meanings associated with the at least one search term. An ordered set of contexts of the at least one search term is constructed. An option of disambiguation is then prompted to the user to select a context of the ordered set of contexts. Search results are presented to the user associated with the selected context of the at least one search term.

Abstract: Aspects of the present invention disclose a method for identifying indications of an attack on a cellular network. The method includes one or more processors scanning a geographic area of a cellular network, wherein the geographic area includes a plurality of transceivers of the cellular network. The method further includes identifying a symptom that impacts a transceiver of the cellular network based at least in part on connectivity between a computing device and the plurality transceivers of the cellular network. The method further includes performing one or more assessments on the transceiver of the cellular network impacted by the symptom. The method further includes determining whether the symptom of the cellular network is associated with an attack on the cellular network based at least in part on the one or more assessments.

Abstract: Systems, methods, and computer programming products for versioning machine learning models. Changes between new and existing datasets are detected, quantified and compared using statistical and semantic feature comparisons. Recommendations for versioning existing models are in response to detecting changes between the feature importance of datasets used in the application of the machine learning model and new datasets that introduce new features or features that evolve over time in such a manner that feature importance has shifted away from one or more features of the first dataset to the new dataset. Based on the changes in feature importance, statistical changes and semantic feature comparisons, the recommendations provided describe whether models should be updated with a re-trained model, or that the existing features of the model do not indicate a need for re-training.

Abstract: The present invention may include a computer receives multimedia data. The computer parses the multimedia data into an audio stream. The computer analyzes the audio stream to identify recognized patterns. The computer calculates a probability of an undesired content based on the recognized patterns and taking an action based on determining the probability is above a threshold.

Abstract: Provided is a method, a system, and a program product for determining a policy using semi-supervised reinforcement learning. The method includes observing a state of an environment by a learning agent. The method also includes taking an action by the learning agent. The method further includes observing a new state of the environment and calculating a reward for the action taken by the learning agent. The method also includes determining whether a policy related to the learning agent should be changed. The determination is conducted by a teaching agent that inputs the state of the environment and the reward as features. The method can also include changing the policy related to the learning agent upon a determination that a label outputted by the teaching agent exceeds a reward threshold.

Abstract: According to one embodiment, a method, computer system, and computer program product for dynamically modifying interactive digital content based on viewer sentiment is provided. The present invention may include measuring, by one or more sensors, characteristics of viewers associated with a viewed portion of the interactive digital content, while the viewers are viewing the interactive digital content; inferring the sentiment of the viewers with respect to the viewed portion of the interactive digital content based on the measured characteristics; predicting content satisfying to the viewers based on the sentiment; and modifying the interactive digital content in real time based on the predicted content.

Abstract: Embodiments for managing user concentration in a work environment are described. Information associated with a user is received. At least one characteristic of a task of the user is identified based on the information associated with the user. A concentration risk level associated with the user performing the task is determined based on the at least one characteristic of the task. A computing environment associated with the user performing the task is provided based on based on the concentration risk level.

Abstract: From a first sensor in a set of sensors, a set of sensor measurements corresponding to a wearer of a garment is collected. Using a model and the set of sensor measurements, a performance deviation index corresponding to the wearer is determined, the performance deviation index corresponding to a deviation from a baseline performance level of the wearer. Responsive to the performance deviation index being above a threshold, a characteristic of the garment is altered.

Abstract: A computer-implemented system and method for device discovery and recovery in a secure network comprises registering a plurality of devices, where the devices form the secure network at a location. Communication between the plurality of registered devices is enabled, and messages passed between the plurality of devices are collected. The method further comprises determining which one of the plurality of devices is a compromised device by using a consensus network that includes the plurality of devices of the secure network.