Dynamically adjusting quality of service using cognitive focus of attention detection

A computer program product for managing a quality of service (QoS) of a video conferencing application, the computer program product comprising a computer readable storage device having program instructions stored in the computer readable storage device, the program instructions are executed by a central processing unit (CPU) of a computer system to cause the computer system to perform a method comprising the steps of:

• the computer system determining a user is communicating with a first participant and not with one or more other participants, wherein the user, the first participant, and the one or more other participants are participants in a video conference provided by the video conferencing application via a computer network;
• the computer system receiving data from (1) a speech recognition tool that recognizes speech of the user or the first participant or (2) a monitoring device that tracks eye movements of the user, wherein the step of determining the user is communicating with the first participant and not with the one or more other participants is based on the received data that recognizes the speech or tracks the eye movements of the user;
• the computer system determining a resolution of peripheral vision of the user;
• based on the user communicating with the first participant, the computer system generating a model of a cognitive focus of attention of the user, the model including a specification of the resolution of the peripheral vision of the user, the cognitive focus of attention being a region of a display presenting the video conference, the region including a face of the first participant;
• the computer system determining a first actual QoS for other regions of the display that are outside the region that includes the face of the first participant;
• the computer system determining a second actual QoS for the region that includes the face of the first participant;
• based on the model of the cognitive focus of attention of the user, the computer system determining an estimation of a perceived QoS for the video conferencing application, the perceived QoS being a level of quality of service being perceived by the user via the cognitive focus of attention;
• based on the model of the cognitive focus of attention of the user, including the specification of the resolution of the peripheral vision of the user, and further based on the first actual QoS for the other regions and the second actual QoS, the computer system determining an adjustment to the first actual QoS, without adjusting the second actual QoS, and while maintaining unchanged the estimation of the perceived QoS;
• and
• the computer system performing the adjustment by matching a resolution of the other regions of the display that are outside the region that includes the face of the first participant to the resolution of the peripheral vision of the user by delaying or dropping a set of packets that specify the other regions, the delayed or dropped set of packets not being perceived by the user based on the resolution of the other regions matching the resolution of the peripheral vision of the user, wherein the step of delaying or dropping the set of packets that specify the other regions includes reducing a video bit rate of the other regions that are outside the region that includes the face of the first participant.