Abstract: A computer-implemented method includes: receiving, by a computer device, and from a head position sensor, head position information that indicates a position of a user's head; receiving, by the computer device, and from an eye position sensor, eye position information that indicates a position of a sensed eye of the user; producing, by the computer device, eye image data that represents a desired eye image based on the head position information and the eye position information; and transmitting, by the computer device, the eye image data to a wearable device worn by the user.

Abstract: An approach is provided in which a cognitive system engages in a conversation that includes multiple participants. The cognitive system detects a diversion indicator during the conversation that is a trigger to the cognitive system perform a diversion action. The cognitive system identifies the diversion action that corresponds to the diversion indicator and performs the diversion action during the conversation accordingly.

Abstract: A first user communication request by a first user is detected. The first user communication request is directed to a computer response system. In response to detecting the first user communication request a profile associated with the first user is determined. A first set of computing resources of the computer response system is allocated to a first automated respondent. The allocation is based on the determined profile. A communication between the first user and the first automated responded is assigned based on the determined profile.

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: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining chat session data of a chat session having a first participant provided by a patron user and a second participant provided by an enterprise user; detecting, subsequent to a connectivity failure, that a network connection supporting the chat session has been restored; presenting in response to the detecting a prompt to the first participant, the prompt being in dependence on the chat session data; deciding an authentication action in dependence on a received response of the first participant in response to the presented prompt; and performing the authentication action in accordance with the deciding.

Abstract: Cognitive software and/or machine learning software are monitored in a cognitive computing environment. Open interface management of virtual agent nodes is performed in the cognitive computing environment.

Abstract: An approach for securing sensitive information in communication data is provided. In an embodiment, communication data is received from an ongoing communication (e.g., phone conversation, exchange of text messages, etc.) between a user and at least one other person. Contextual input is derived based on the content of the communication data and historical data from one or more external sources. A sensitivity index score for each element (e.g., portion) of the communication data is derived based on an assessment of the contextual input. The elements of the communication data having a sensitivity index score greater than a predefined threshold value are deemed to be security sensitive and, therefore, are encoded prior to transmission to its intended recipient.

Abstract: For linguistic alignment in specific user targeted messaging, a linguistics preference set is calculated for a specific user using cognitive models with specific user data as input. A messaging channel is selected according to the linguistics preference set, where the linguistics preference set includes one or more sets of linguistic traits preferred by the specific user. A location of the specific user is determined. A set of linguistic traits applicable to a customized message is determined based on the linguistics preference set for the specific user and the location of the specific user. The customized message is generated to incorporate the set of linguistic traits and sent only to the specific user over the selected messaging channel, providing a multi-level linguistic alignment between the specific user and the linguistics used in the message.

Abstract: An approach is provided in which a lens system captures a set of sensory data corresponding to an area proximate to a user wearing glasses. Next, the lens system matches the set of sensory data to a situational context entry stored in a storage area and, in turn, adjusts an appearance of the lens system based on a set of lens configuration attributes corresponding to the matched situational context entry.

Abstract: A method includes: receiving information from a source; determining a situational context for usage of UE devices in a specific area based on the received information, the UE devices communicating over a communication network and utilizing bandwidth of the communication network; predicting a location of the UE devices, the predicting being based on the received information and the determined situational context; predicting a bandwidth usage of the UE devices at the predicted location; predicting that a current bandwidth of the communications network is insufficient to provide the predicted bandwidth usage to the UE devices, the predicting that the current bandwidth is insufficient being based on the received information and the determined situational context; and deploying an aerial device that provides additional bandwidth to the communication network, the additional bandwidth being provided at the predicted location of the UE devices.

Abstract: A system and method for aiding a user in troubleshooting a problem includes extracting one or more entities and actions from a problem statement received from a user computing device, wherein, in response to the extracting: mapping, the one or more entities and actions to one or more images related to the one or more entities and actions, and ordering, the one or more entities and actions into a user action sequence, creating a pictorial sequence of user-taken actions to correct the problem, comparing the pictorial sequence of user-taken actions to correct the problem with a correct pictorial sequence to correct the problem, to identify a correct action that the user failed to perform, and isolating a portion of the correct pictorial sequence that corresponds to the correct action that the user failed to perform, for displaying to the user on the user computing system.

Abstract: An expert system incorporates multiple virtual-agent experts, each trained in a particular field or domain. When a user enters a block of input, an interactive front-end infers the semantic meaning of the input and creates a chat-table record that stores the inferred meaning and other characteristics of the input. A distributed virtual-assistant manager (DVAM) module uses that record to identify the domain of the input and, after retrieving cross-reference information stored in a virtual-assistant intent (VAI) table, selects a virtual-agent expert trained in the identified domain. If necessary, the DVAM directs the front-end to seamlessly switch the user to the newly selected expert. As the session continues, the system continues to dynamically switch the user to different experts as the session traverses different domains. The system may also consider the domain history of the entire session when selecting a domain.

Abstract: Pairing a user response and associated context with a neural network associated with a virtual assistant computer during a dynamic text conversation with an end user. The virtual assistant computer receives a detected user generated text input; determines context of the detected user generated text input; compares the context of the detected user generated text input by comparing a confidence score representing context of the user generated input to a classification associated with each of a plurality of existing nodes of a neural network. For confidence scores below a threshold relative to the classification associated with each of the existing nodes of the neural network, the virtual assistant computer creates a new node within the neural network and assigns the context of the user generated text to the new node.

Abstract: Provided are techniques for building and fixing a dynamic application topology. Log files are received from multiple sources comprising any of services and nodes. Information is extracted from the log files. An application topology is created for a particular point in time for an application that provides hierarchical relationships of components for executing the application using the extracted information. One or more problems in the application topology are identified. A solution is applied to each of the one or more problems.

Abstract: The present disclosure includes using cognitive data analytics for communication between vehicular devices using a 5G (fifth generation cellular network technology) telecommunications network. In a defined area, using an Internet of Things (IoT) enabled device in a first vehicle traveling in a direction, the present disclosure detects a second vehicle traveling in another direction in the defined area. Data is collected in the defined area using the detected IoT devices in the first and second vehicles. The collected data is analyzed to provide content data related to driving conditions for the first and second vehicles. The content data is exchanged between the IoT devices of the first vehicle and the second vehicle in the defined area, thereby providing real-time information related to the driving conditions to a vehicle traveling in another direction, and the exchanging of the content data, using the service orchestration layer of the 5G telecommunications network.

Abstract: A method and system for virtually detecting and modifying technical issues is provided. The method includes enabling virtual software of a hardware controller with respect to a software layer of a fifth generation (5G) telecom communication network. A signal is enabled by a 5G apparatus and a handshaking processes between the hardware controller and the 5G apparatus is executed. In response, metadata structures are parsed and classified. Technical issues associated with hardware and software of devices connected to the 5G telecom communication network are identified and the virtual software is modified for managing and repairing the technical issues. Self-learning software code for executing future processes associated with executing virtual detection and issue modification is generated.

Abstract: A system and method compare performance of virtual assistants. A user selects metrics for evaluating two or more virtual assistants, and these metrics may be weighted by the user. One or more chat sessions from each virtual assistant are then analyzed using the weighted metrics to generate a score for each chat session. The scores of chat sessions of different virtual assistants are then compared according to the selected weighted metrics, and a recommendation of a virtual assistant may be made based on the score comparison. The evaluation of multiple virtual assistants allows comparing these virtual assistants to determine which provides the better customer service according to the selected weighted metrics.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: transmitting, during a media streaming session, streaming media to a user equipment (UE) device of a user, the transmitting streaming media including simultaneously transmitting a first media stream and a second media stream to the UE device; subjecting the first media stream to processing by natural language processing to provide a topic extracted from the first media stream; subjecting the second media stream to processing by natural language processing to provide an extracted topic extracted from the second media stream; identifying a match between the topic and the extracted topic; and providing one or more output in response to the identifying the match between the topic and the extracted topic.

Abstract: An approach is provided for controlling content delivery. Stream data and associated metadata are received from one or more sources. The stream data is converted into a text format. The converted stream data is processed in an artificial intelligence system to detect emotions of the stream data. The emotions of the stream data are mapped to a set of rules for a geographic area. Unacceptable content in the stream data is identified based on the emotions and the set of rules for the geographic area. Content delivery servers are notified to discard the unacceptable content so that the unacceptable content is not delivered through content distribution channels and is not viewed by an end user.

Abstract: A method, apparatus, system, and computer program product for generating an audio communication. An urgency for a user is determined by a computer system in response to detecting a trigger event in a verbal communication from the user. A frequency modulator is selected by the computer system from a plurality of frequency modulators based on the urgency determined to form a selected frequency modulator. A frequency of words in an audio communication is modulated by the computer system using the selected frequency modulator to form a modulated audio communication, wherein the modulated audio communication comprises a natural language response generated in response to the trigger event. The modulated audio communication is sent by the computer system to an audio output device.