Abstract: A method for safeguarding confidential information during a screen share between two computing devices each having a screen. The method includes receiving, from a first computer, a request to share content of one or more applications displayable on a screen of a second computer. The method further includes summarizing the content to be displayed by the one or more applications, and transmitting, by the first computer, the summarized content to be shared by the one or more applications with the second computer. In exemplary embodiments, the summarized content may be password protected. The method may further include prompting, by the second computer, a password entry and displaying, by the second computer, the summarized content based on a password match.

Abstract: For locations along a route a user will be traveling, the alert system for environmental changes compares first and second sets of images associated with first and second timestamps, respectively. The alert system determines degrees of environmental changes for the locations based on the comparisons. The alert system then generates and sends an alert to a user device. In determining the degrees of environment changes, the alert system retrieves first and second set of images matching a given location and associated with first and second timestamps. The alert system identifies first and second sets of objects and extracts first and second sets of attributes for the first and second sets of images. The alert system compares the first and second sets of attributes and the first and second set of objects, and determines a given degree of environmental changes at the given location based on the comparisons.

Abstract: The present disclosure provides for medical device administration and interaction by identifying a medical event affecting a first individual, a medical device associated with treating the medical event, and an initial attentiveness level of an administering individual; outputting a tutorial for how to use the medical device to treat the medical event with a first control level, wherein the first control level based on the initial attentiveness level of the administering individual; and in response to receiving a triggering event while outputting the tutorial: determining a current attentiveness level for the administering individual; and in response to the current attentiveness level indicating a change from the initial attentiveness level, adjusting the tutorial based on a second control level, different than the first control level, based on the change from the initial attentiveness level.

Abstract: A system and method for assessing a potential problem associated with information in a document. In an embodiment, a document for analysis may be received, the document being part of a corpus of one or more documents stored in an electronic format. The document may be analyzed to identify reference(s) in the document, wherein the reference(s) are each selected from the group comprising a natural language statement, a reference in a first part of the document to a second part of the document, or a reference to or from another document. Based on the reference(s), a knowledge graph may be generated to represent information in the document. A risk assessment of a reference in the document may be determined using the knowledge graph. A visual indicator may be applied to the document that emphasizes a potential problem with the reference based on the risk assessment.

Abstract: Aspects of the present invention disclose a method for determining whether to perform mute/unmute functions to secure voice communication on multiple devices to allow for safeguarding of sensitive information of a user. The method includes one or more processors identifying one or more audio communications from a first user to a second user, wherein the one or more audio communications is transmitted utilizing a first computing device. The method further includes determining an objective of the first user based at least in part on the audio communication of the first user. The method further includes determining a set of conditions corresponding to the one or more audio communications and the objective, wherein the set of conditions indicate a vulnerability of personal data of the first user. The method further includes prohibiting the first computing device from transmitting audio data that includes the personal data of the first user.

Abstract: A method includes generating, at a controller, a snapshot of content displayed at a user interface screen. The content associated with a domain for a particular service. The method also includes performing user interface element recognition on the snapshot to identify a user interface element in the content. The method further includes associating the user interface element with a user interface element intent and associating the user interface element intent with a particular phrase based on the domain. The method also includes generating an automated interactive support prompt based on the particular phrase to be output for user interaction. The user interaction is usable for performance of the particular service.

Abstract: An embodiment trains a machine-learning model using a first training corpus of general items indicative of varying levels of confidence. The embodiment also prepares a second training corpus that includes domain-specific items indicative of varying levels of confidence extracted from communications from members of a project group associated with a project. The embodiment retrains the machine-learning model using the second training corpus and generates a confidence score for the project based on confidence values assigned by the machine-learning model to each of a plurality of project-related communication items from members of the project group. The embodiment also detects that the confidence score is below a predetermined threshold confidence level and, in response, initiates a communication to members of the project group conveying information regarding an automated remedial action for the project.

Abstract: Provided are techniques for alert generation based on a cognitive state and a physical state. Wearables data, text communications, voice communications, and images of a caregiver providing care to a patient are obtained. The wearables data, the text communications, the voice communications, and the images are analyzed to identify a cognitive state and a physical state of the caregiver. The cognitive state and the physical state are compared to one or more care rules associated with tasks of the caregiver for the patient. In response to the comparison indicating any one of the cognitive state and the physical state prevent the caregiver from executing the tasks, an alert is generated. One or more recommendations for resolving the alert based on one or more recommendation rules are generated.

Abstract: A method, system and computer program product for amplifying a single voice during an audio conversation. One embodiment of the method may comprise receiving, by a computing device, an audio sample of speech from a user, and generating, by the computing device, a user-specific acoustic model for enhancement of speech by the user based upon the audio sample. The method may further comprise receiving a live audiovisual stream, the live audiovisual stream including live speech by the user during an audio conversation, wherein the live audiovisual stream includes background noise, and using, by the computing device, the user-specific acoustic model to selectively amplify the live speech during the live audiovisual stream without amplifying the background noise.

Abstract: In an approach to collaborative discourse, responsive to receiving a collaborative discourse, a document corpora of the collaborative discourse is analyzed. A picture metadata is analyzed for each image in a graphic repository. A machine learning model is derived based on the analysis of the document corpora and the analysis of the picture metadata. Appropriate images are selected from the graphic repository based on the machine learning model, where the appropriate images closely align with the collaborative discourse.

Abstract: A resource allocation method comprises using resources with a used resource quantity of a machine learning system to execute a first experiment which has a first minimum resource demand, receiving an experiment request associated with a target dataset, deciding a second experiment according to the target dataset, deciding a second minimum resource demand of the second experiment, allocating resources with a quantity equal to the second minimum resource demand for an execution of the second experiment when a total resource quantity of the machine learning system meets a sum of the first minimum resource demand and the second minimum resource demand and a difference between the total resource quantity and the used resource quantity meets the second minimum resource demand, determining that the machine learning system has an idle resource, and selectively allocating said the idle resource for at least one of the first experiment and the second experiment.

Abstract: Dynamic prioritization of an action item can include retrieving an electronically rendered text from one or more sampled text sources in response to recognizing a user-related task conveyed within the electronically rendered text. Dynamic prioritization of an action item can also include generating an action item corresponding to the user-related task and prioritizing the action item by assigning to the action item a priority computed based on one or more priority factors corresponding to the user-related task. Each of the one or more priority factors can be automatically selected from a collection of predetermined priority factors. Additionally, dynamic prioritization of an action item can include recomputing the priority assigned to the action item in response to a change in task-related circumstances, as determined based on other electronically rendered text.

Abstract: A cell activation reactor and a cell activation method are provided. The cell activation reactor includes a body, a rotating part, an upper cover, a microporous film, and multiple baffles. The body has an accommodating space, which is suitable for accommodating multiple cells and multiple magnetic beads. The rotating part is disposed in the accommodating space and includes multiple impellers. The microporous film is disposed in the accommodating space and covers multiple holes of the accommodating space. The baffles are disposed in the body. When the rotating part is driven to rotate, the interaction between the baffles and the impellers separates the cells and the magnetic beads.

Abstract: A method, a structure, and a computer system for location-driven social network boosting. The exemplary embodiments may include generating a network graph corresponding to a user of a social network and identifying a destined location of the user that differs from a current location of the user. The exemplary embodiments may further include identifying one or more gaps in the social network of the user at the destined location and augmenting the social network to fill the one or more gaps at the destined location.

Abstract: A computer system monitors users to capture contextual and environmental data for managing adverse events of those users. A level of risk for occurrence of an adverse event from performing a medical related activity is determined based on the medical related activity, a medical profile, and a risk profile of the user. The user is monitored to capture environmental and contextual information for the adverse event. The captured information is stored to associate the captured information with the adverse event. In response to occurrence of the adverse event, the user is prompted to provide information pertaining to conditions surrounding the adverse event. The stored information for the adverse event is updated with the user-provided information, and is transmitted to a provider associated with the medical related activity. Embodiments of the present invention further include a method and program product for managing adverse events in substantially the same manner described above.

Abstract: A payment card system for authorization and authentication is provided. A computing device monitors one or more transactions to detect various security threats comprising one or more accounts. A computing device determines to elevate a security level associated, at least, with one account based, at least, in part, on detection of, at least, one security threat. A computing device generates at least one temporary personal identification number based, at least, on determination to elevate a security level associated, at least, with one account.

Abstract: By analyzing a set of actions of a meeting attendee, a set of accommodation rules for the meeting attendee is determined. Responsive to determining, using a set of facility data, that a meeting request for the meeting attendee violates an accommodation rule in the set of accommodation rules, the meeting request is modified, the modified meeting request conforming to the set of accommodation rules. A meeting location and a meeting time are assigned according to the modified meeting request.

Abstract: Scheduling events with multiple invitees includes: identifying a plurality of invitees for an event in a calendar system having at least one processor; searching an availability associated with each of the invitees to determine a number of periods of availability in the calendar system, at least some of the invitees being available during each period of availability; creating a separate instance of the event in the calendar system for each identified period of availability; and for each invitee available during at least one of the periods of availability, assigning the invitee to one said instance of the event for which that invitee is available with the calendar system.

Abstract: A method and system for validating a software application is provided. The method includes monitoring user interaction patterns of a user with respect to software being executed by an electronic device. Content of the software is scanned, and usage attributes of the software are analyzed. Virtual entry points executed via the user interaction patterns with respect to accessing the software application are validated and associated metadata is generated. In response an error condition associated with the user interaction patterns is detected and an automated corrective action associated with correcting the error condition is executed.

Abstract: A computing device that receives a real-time chat discourse. The computing device analyses the real-time chat discourse by consecutively applying a topic analysis technique, a corpus linguistics technique and a cosine similarity technique. The computing device derives a discourse decision forking component (DDFC) based on comparing the analyzed real-time chat discourse to a similarity threshold value and determines one or more discourse forks using the DDFC.