Abstract: Smart speaker mechanisms are provided for processing audio sample data captured by the audio capture device is provided. The mechanisms capture one or more audio samples from a monitored environment and store the captured one or more audio samples in the audio sample buffer. The one or more captured audio samples are analyzed to determine whether the one or more captured audio samples represent a potential wake sound for initiating a responsive action by the smart speaker device. The potential wake sound is a variable sound determined to not be a normal ambient sound of the monitored environment. In response to determining that the one or more captured audio samples represent a potential wake sound for initiating a responsive action by the smart speaker device, the mechanisms initiate performance of the responsive action by the smart speaker device.

Abstract: Smart speaker system mechanisms, associated with a smart speaker device comprising an audio capture device, are provided for processing audio sample data captured by the audio capture device. The mechanisms receive, from the audio capture device of the smart speaker device, an audio sample captured from a monitored environment. The mechanisms classify a sound in the audio sample data as a type of sound based on performing a joint analysis of a plurality of different characteristics of the sound and matching results of the joint analysis to criteria specified in a plurality of sound models. The mechanisms determine, based on the classification of the sound, whether a responsive action is to be performed based on the classification of the sound. In response to determining that a responsive action is to be performed, the mechanisms initiate performance of the responsive action by the smart speaker system.

Abstract: A request to determine a drone's capability may be received. A request type of the request and service context may be determined. A challenge may be generated based on the request type and the service context. The challenge may be presented to a drone and causing the drone to attempt the challenge. Information may be received from the drone, the information indicating the drone's response to the challenge attempted by the drone. The drone may be controlled to perform a given task or not perform the given task, based on the information.

Abstract: A method for collaborative messaging including natural delays includes receiving, by a computer, a message from a sender intended for a recipient using a collaborative messaging application, determining, by the computer, message characteristics, sender characteristics, and recipient characteristics, based on the determined message characteristics, sender characteristics, and recipient characteristics, dividing the message into one or more segments, based on the determined message characteristics, sender characteristics, recipient characteristics and segment size, determining a time delay for each of the one or more segments, and transmitting the message to the recipient one segment at a time, wherein successive segments are separated by the time delay corresponding to each segment.

Abstract: In a given computing node comprising at least one processor operatively coupled to a memory and implemented in a given vehicle, the method comprises obtaining at the given computing node data from at least one of: (i) one or more sensors on the given vehicle; (ii) one or more computing nodes associated with one or more other vehicles via at least one vehicle-to-vehicle communication protocol; and (iii) one or more data sources along the path of the given vehicle. The given computing node utilizes at least a portion of the obtained data to compute a risk assessment for the given vehicle with respect to an operational safety level of a proposed vehicle action. The given computing node initiates or prevents the proposed vehicle action for the given vehicle based on the computed risk assessment.

Abstract: A cohort associated with a user is identified. A virtual object is generated according to the cohort. An augmented reality setting of a location is generated in relation to the user. A context of the location is determined. The virtual object is modified in the augmented reality setting according to the context and the cohort.

Abstract: A computer-implemented method includes detecting, by one or more sensors of a robot, one or more characteristics of a current point on a surface on which the robot travels. A feature vector is constructed to describe the current point on the surface on which the robot travels, based on the one or more characteristics. The feature vector is mapped to a confidence level that a hazard exists at the current point on the surface. It is determined that the confidence level meets a threshold confidence. An alert is issued in association with the current point on the surface, based on the confidence level meeting the threshold confidence.

Abstract: Disclosed is a novel system and method for indicating a probability of errors in multimedia content. The system determines a user state or possible user distraction level. The user distraction level is indicated in the multimedia content. In one example, work is monitored being performed on the multimedia content. Distractions are identified while the work is being monitored. A probability of errors is calculated in at least one location of the multimedia content by on the distractions that have been identified. Annotations are used to indicate of the probability of errors. In another example, the calculating of probability includes using a function F(U,S,P) based on a combination of: i) a determination of user state (U), ii) a determination of sensitivity (S) of user input, and iii) a determination of user characteristics stored in a profile (P).

Abstract: A method and/or computer program product identifies and/or predicts a cognitive state of a user. A buffer on a device is loaded with a predetermined set of sensor readings for a user. A hardware receiver receives a “push” signal from the device. The “push” signal is transmitted by the user in response to the user subjectively experiencing a user-defined cognitive state. The “push” signal causes readings from the buffer to be loaded as pushed sensor readings onto a data matrix. One or more processors analyze the pushed sensor readings to identify a sensor pattern of the pushed sensor readings. In response to detecting a subsequent set of sensor readings that match the sensor pattern of the pushed sensor readings, a signal transmitter transmits a cognitive state signal that indicates a prediction of a particular cognitive state of the user.

Abstract: A method deploys a road safety flare near a faulty self-driving vehicle (SDV). One or more processors detect a driving problem severity level for a faulty SDV. One or more processors assess environmental conditions at the location of the faulty SDV. One or more processors determine an opportune position for deploying the road safety flare based on the environmental conditions at the location of the faulty SDV and then deploy, according to directions from the faulty SDV, a road safety flare at the opportune position.

Abstract: Systems and methods for providing privacy control for digital capture of a recording include identifying a person within a digital capture that is a recording of a person within an environment based on received information regarding the person. A disposition tag is associated with an identified person in the recording. The disposition tag references a privacy control action to take according to privacy constraints for the person. Coordinates in the recording where the privacy control action is to be applied are determined.

Abstract: A music practice feedback system, comprising, a processor; and a memory storing instructions that cause the processor to perform, monitoring an outcome of a playing of a sheet music by a user, and based on the outcome, suggesting a type of improvement to increase a success rate of playing the sheet music.

Abstract: A music practice feedback system, includes a processor; and a memory storing instructions that cause the processor to perform, forecasting an ability to retain playing skills of a sheet music by a user via machine learning and changing a display of the sheet music based on the forecasted ability.

Abstract: A method, apparatus and computer program for presenting locations of individuals in an interface are described. A region of interest is determined by a location and an orientation of a portable device in an environment. The region of interest is a cone of interest radiating away from the location of the portable device in a direction of orientation of the portable device. A set of locations of one or more individuals of interest with respect to the cone of interest in the environment is determined. An orienting background and a first set of representations against the orienting background are presented in an interface on the display. Each representation is of a respective individual of interest in the cone of interest. The interface is presented according to the location and orientation of the display. The orienting background contains a positional cue of a landmark of the environment which the portable device is oriented toward.

Abstract: An unmanned aerial vehicle for aerial transportation of delivery items. The unmanned aerial vehicle includes an attachment device to fasten and unfasten one or more delivery items to the unmanned aerial vehicle, a motor to aerially transport the one or more delivery items along a delivery route, a sensor mounted on the unmanned aerial vehicle to detect at least one environmental variable during the delivery route, and an alert system to generate a status associated with the unmanned aerial vehicle along the delivery route to an observer when the environmental variable exceeds a predetermined threshold.

Abstract: Systems and methods for automated personalized customer service are disclosed. In embodiments, a method comprises: determining, by a computing device, at least one object from a plurality of objects within a venue matches a search query received from a user; assigning to the user, by the computing device, a select lighting type from a plurality of available lighting types, wherein the select lighting type is not available for the computing device to assign to other users while assigned to the user; providing, by the computing device, a notification to the user regarding the select lighting type; selecting, by the computing device, a target lighting device from a plurality of lighting devices within the venue, the target lighting device being associated with the at least one object; initiating, by the computing device, a first illumination event of the target lighting device based on the select lighting type.

Abstract: Embodiments of the present invention disclose a method, computer program product, and system for a social connection recommendation based on a similar order of life events. The computer may determine a plurality of life events for a user and a set of other users through an opt-in fashion. The plurality of life events for the user and the plurality of life events of the set of other users may be compared. It may be determined whether a correlation exists between the user and at least one individual from the set of other users. In response to determining the correlation exists between the user and the at least one individual from the set of other users, a recommendation may be provided to the user for a social connection between the user and the at least one individual from the set of other users.

Abstract: Machine-implemented assistance is provided in interaction among multiple parties. This assistance can include recording of evidence of communication, and in particular to recording of evidence of language-based communication between humans and machines. Further, machine-implemented facilitation of dispute resolution based on the recorded evidence may be provided.

Abstract: A method and system are provided. The method includes analyzing, by a hardware processor, one or more images to determine cognitive characteristics related to the one or more images and to a user. The method further includes forming, by the hardware processor, a composable template relating to the cognitive characteristics. The method also includes performing, by the hardware processor or another hardware processor, an amelioration action with respect to a displaying on a display device of at least one image from the one or more images, based on the composable template. The amelioration action is selected from a set of amelioration actions that include transmitting the at least one image to the disturbing image repository.

Abstract: A computer-implemented method comprising: determining, by a computing device, characteristics of a social media message; selecting, by the computing device, a particular image, of a plurality of images, based on the characteristics of the social media message and characteristics of the particular image; and outputting, by the computing device, information identifying the selected image to incorporate the selected image in a user's social media profile.