Abstract: Mechanisms are provided, in a data processing system comprising a fusion sensor service and a human computer interaction (HCI) device, for responding to a user input. The HCI device receives a user input from a first sensor monitoring a monitored environment. The fusion sensor service captures, via one or more second sensors different from the first sensor, sensor data representing characteristics of one or more entities within the monitored environment indicative of a condition within the monitored environment. The fusion sensor service determines whether the user input is specifically directed to the HCI device based on the captured sensor data. The HCI device performs an operation in response to the data processing system determining that the user input is specifically directed to the HCI device based on the capture sensor data.

Abstract: Provided is method, system, and computer program product for reducing telecommunication network congestion during a high call volume event by prioritizing subscriber calls. A processor may receive a notification of an ongoing emergency at a location. The processor may activate an emergency mode at one or more call stations near the location. The processor may receive a plurality of calls at the one or more call stations from one or more callers, wherein the calls are not directed to an emergency service provider. The processor may determine a priority order for each of the calls based on a priority level assigned to each respective caller. The processor may allow the calls to be completed according to the priority order.

Abstract: An approach is provided that identifies a current mood state of a requestor from whom a question has been submitted to a question answering (QA) system. The approach determines, based on the identified mood state, an urgency associated with the requestor. Data pertaining to a number of candidate answers is analyzed with the candidate answers being generated by the QA system. The analysis results in an urgency characteristic that pertains to each of the candidate answers. Scoring of the candidate answers is adjusted based on a comparison of the requestor's urgency and the urgency characteristic associated with the candidate answers. Answers are selected from the candidate answers and returned to the requestor with the selected answers based on the adjusted scoring.

Abstract: Mechanisms are provided, in a smart speaker system having at least one smart speaker device comprising an audio capture device, and smart speaker system logic, for processing audio sample data captured by the audio capture device. The audio capture device captures an audio sample from a monitored environment and one or more sensor devices capture sensor data representing non-verbal attention indicators associated with a speaker of a speech portion of the audio sample. The smart speaker system logic evaluates the non-verbal attention indicators of the sensor data to determine whether or not the speech portion of the audio sample is directed to the smart speaker device. In response to determining that the speech portion of the audio sample is directed to the smart speaker device, a cognitive system associated with the smart speaker system generates a response to the speech portion.

Abstract: Mechanisms are provided, in a smart speaker system having at least one smart speaker device comprising an audio capture device, and smart speaker system logic, for processing audio sample data captured by the audio capture device. The audio capture device captures an audio sample from a monitored environment and one or more sensor devices capture sensor data representing non-verbal attention indicators associated with a speaker of a speech portion of the audio sample. The smart speaker system logic evaluates the non-verbal attention indicators of the sensor data to determine whether or not the speech portion of the audio sample is directed to the smart speaker device. In response to determining that the speech portion of the audio sample is directed to the smart speaker device, a cognitive system associated with the smart speaker system generates a response to the speech portion.

Abstract: Mechanisms are provided, in a data processing system comprising a fusion sensor service and a human computer interaction (HCI) device, for responding to a user input. The HCI device receives a user input from a first sensor monitoring a monitored environment. The fusion sensor service captures, via one or more second sensors different from the first sensor, sensor data representing characteristics of one or more entities within the monitored environment indicative of a condition within the monitored environment. The fusion sensor service determines whether the user input is specifically directed to the HCI device based on the captured sensor data. The HCI device performs an operation in response to the data processing system determining that the user input is specifically directed to the HCI device based on the capture sensor data.

Abstract: An approach is provided that identifies a current mood state of a requestor from whom a question has been submitted to a question answering (QA) system. The approach determines, based on the identified mood state, an urgency associated with the requestor. Data pertaining to a number of candidate answers is analyzed with the candidate answers being generated by the QA system. The analysis results in an urgency characteristic that pertains to each of the candidate answers. Scoring of the candidate answers is adjusted based on a comparison of the requestor's urgency and the urgency characteristic associated with the candidate answers. Answers are selected from the candidate answers and returned to the requestor with the selected answers based on the adjusted scoring.