Abstract: A method, computer program product, and a system where a processor(s) obtains data from one or more sources, wherein a portion of the one or more sources comprise training data for a first artificial intelligence decision-making system. The processor(s) ingest data from each source into a corpus and ingest metadata corresponding to the data, into a volume accessible to a second artificial intelligence decision-making system. The processor(s) search public sources and obtain information describing quality and non-objective influence of the data from each source. The processor(s) provide as inputs to the second artificial intelligence decision-making system, the information and the metadata, to classify the quality and the non-objective influence of each source. The processor(s) obtains outputs comprising, for each source, a first rating classifying the quality of the source of the one or more sources.

Abstract: According to one embodiment, a method, computer system, and computer program product for identifying cloud storage destination. The embodiment may include identifying content of a data file being created or updated. The embodiment may include identifying cloud storage criteria of the data file. The embodiment may include determining whether an existing storage solution within a cloud storage service provider (CSSP) knowledge corpus is applicable to the data file. In response to determining that an existing storage solution is not applicable to the data file, the embodiment may include creating a new storage solution for the data file based on the identified content and cloud storage criteria of the data file.

Abstract: By analyzing execution of a set of transactions by an application, a set of actual code execution paths of the application are determined. From the set of actual code execution paths, a set of predicted execution paths of the application are predicted using an execution prediction model. The set of predicted execution paths includes the set of actual code execution paths. By determining that paths in the set of predicted execution paths have above a threshold similarity to each other, a cluster of predicted execution paths is identified. The cluster of predicted execution paths is recommended, using a recommendation model, for implementation as a single execution path in a revised version of the application.

Abstract: A computer-implemented method for automatically migrating a cloud-based solution onto a datacenter is provided. The method may include populating and maintaining a corpus of datacenters. The method may further include implementing a machine-learning algorithm to identify different types of users and to generate a user profile for each type of user based on machine-learned user profile data. The method may further include detecting user experience with the cloud-based solution on one or more datacenters from the corpus of datacenters for each type of user based on the machine-learned user experience data. The method may further include correlating the machine-learned user profile data and user experience data with the current and previous computing capabilities and performance of each datacenter in the corpus. The method may also include automatically migrating the cloud-based solution onto the datacenter from the corpus of datacenters for the specific type of user based on the correlation.

Abstract: Head movements can be detected by various sensors. The head movements are tracked over time, and the data is stored in a knowledgebase. User actions are also detected and tracked in the knowledgebase. Therefore, associations between head movements and user actions can be learned and predicted. Upon detecting a head movement associated with a user action, the user action can be executed.

Abstract: An embodiment for determining a drop-off location of a passenger is provided. The embodiment may include receiving a pick-up location and drop-off location from one or more passengers. The embodiment may also include identifying the one or more passengers to be picked up from a passenger profile. The embodiment may further include identifying one or more factors associated with each passenger. The embodiment may also include in response to determining the drop-off location is not appropriate, notifying the one or more passengers of an alternative drop-off location. The embodiment may further include in response to determining the drop-off location is appropriate, dropping the one or more passengers off at the drop-off location. The embodiment may also include in response to determining the one or more passengers are not responsive to the notification, dropping each passenger who did not respond off at the alternative drop-off location.

Abstract: Aspects of the present invention provide devices that identify a question in a text message of a chat session between a plurality of computing devices, wherein each of the plurality of computing devices includes an identifier of a user of a corresponding computing device in the text message, analyze digital data to determine a relationship between the users of the plurality of computing devices, construct search parameters for digital content external to the chat session according to the identified question and determined relationship, search for the digital content over a network according to the constructed search parameters to obtain search results, rank the search results according to the determined relationship, and distribute the ranked search results according to the determined relationship to at least one of the plurality of computing devices in an overlay of the chat session.

Abstract: Embodiments disclosed herein include a method for managing haptic effects. The method generates a first graphical representation of a first haptic effect generation pattern in a mixed reality environment, wherein the first haptic effect generation pattern comprises factors for generating a first haptic effect at a first haptic device. The method receives a user alteration to the first haptic effect generation pattern from a first user. The method changes the graphical representation based on the user alteration.

Abstract: Methods for intelligent management of asset workflows are disclosed herein. One method includes predicting that a user is going to perform a predetermined action based on one or more user movements included in a signal received from a wearable sensing device and generating, by a processor, a warning of one or more consequences of the user performing the predetermined action. The method further includes displaying, on augmented reality glass, the warning to the user prior to the user actually performing the predetermined action. Also disclosed herein are systems and apparatus that can include, perform, and/or implement the operations of the methods.

Abstract: A computer-implemented method, a computer system and a computer program product dynamically change the user interface on a mobile device. The method includes displaying a user interface on a first device. The user interface includes a set of graphical controls corresponding to a plurality of functions of the first device. The method also includes connecting to the second device in response to a determination that the device includes a capability not included in the plurality of functions of the first device. The method further includes determining an aggregate function set for the first and second devices that includes the plurality of functions of the first device and is updated to include the capability of the second device. Finally, the method includes modifying the user interface of the first device based on the aggregate function set by adding a graphical control corresponding to the capability of the second device.

Abstract: Embodiments for implementing intelligent audio composition guidance for a video by a processor. One or more acoustic characteristics used in a plurality of video segments may be identified, from a corpus, as having similar acoustic, linguistic, and visual characteristics of a selected video segment.

Abstract: Methods and systems may provide for technology to recognize features of current content to be shared by a current user, determine a plurality of platforms that allow access to data by other users and select one or more of the plurality of platforms to store the current content based on the recognized features.

Abstract: At a first chatbot, a query expressed in natural language form is received. It is determined that responding to the query requires data external to the first chatbot. From a data source external to the first chatbot, response data corresponding to the query is obtained. Using the response data, the query is responded to in natural language form. Using the response data, the first chatbot is updated.

Abstract: A computer-implemented method includes: receiving, by a computing device, an input file defining correct spellings of one or more transliterated words; generating, by the computing device, suffix outputs based on the one or more transliterated words; generating, by the computing device, a dictionary that maps the suffix outputs to the one or more transliterated words; recognizing, by the computing device, an alternatively spelled transliterated word included in a document as one of the one or more correctly spelled transliterated words using the dictionary; and outputting, by the computing device, information corresponding to the recognized transliterated word.

Abstract: Aspects of the present disclosure relate to stream quality enhancement. A determination can be made that quality of an audio/video (A/V) stream being streamed to a first device falls below a quality threshold. A plurality of edge processing devices in an environment of the first device can be identified. Available computing resources of each of the edge processing devices can be determined. At least one edge processing device of the plurality of edge processing devices with sufficient computing resources for correcting quality of the A/V stream using a correction model can be selected. The selected at least one edge processing device can be instructed to correct the A/V stream using the correction model to generate a corrected A/V stream that satisfies the quality threshold. A command to transmit the corrected A/V stream to the first device can be issued.

Abstract: According to one embodiment, a method, computer system, and computer program product for computing device control. The embodiment may include segmenting an augmented reality (AR) view of an environment of a user into distinct segmented areas of the AR view. The AR view is created by an AR device of the user. The segmenting is performed using the AR device. The embodiment may include mapping a computing device within the environment to a distinct segmented area of the AR view. The mapping results in a user interface (UI) of the computing device being displayed within the distinct segmented area of the AR view. The embodiment may include controlling the computing device via the UI of the computing device displayed within the distinct segmented area of the AR view.

Abstract: By monitoring an in-person interaction using a first Internet of Things (IoT) device, an entity relationship between parties in the in-person interaction is identified. Using data resulting from the monitoring, a habit workflow corresponding to the entity relationship is generated, wherein the habit workflow comprises a sequence of habits and a habit in the sequence of habits comprises performance of a behavior. A second IoT device able to monitor execution of the habit workflow is identified. Using the second IoT device, execution of the habit workflow is monitored. A motivational method corresponding to the execution is identified from the monitored execution.

Abstract: A method, computer system, and a computer program product for task monitoring is provided. The present invention may include training an AI voice response system based on task performance data, wherein the task performance data originates from at least one monitoring device. The present invention may include receiving a request for instructions to complete a task from a user. The present invention may include monitoring a performance of the task by the user, wherein the performance of the task by the user is monitored utilizing at least one monitoring device. The present invention may include determining differences between the performance of the task by the user and a task sequence.

Abstract: The present invention may include a computer receives one or more communications and data from a sensor. The computer determines an activity of a user based on the received data, wherein the activity is determined by a trained neural network. The computer calculates a stress coefficient based on the activity and the data. The computer generates a cognitive notifications choreographer model from the stress coefficient and one or more communications and causes a communication software to reply to the one or more communications based on the cognitive notifications choreographer model determining the stress coefficient above a threshold value.

Abstract: Embodiments disclosed herein include a method for managing haptic effects. The method generates a first graphical representation of a first haptic effect generation pattern in a mixed reality environment, wherein the first haptic effect generation pattern comprises factors for generating a first haptic effect at a first haptic device. The method receives a user alteration to the first haptic effect generation pattern from a first user. The method changes the graphical representation based on the user alteration.