DYNAMICALLY ADJUSTING QUALITY OF SERVICE USING COGNITIVE FOCUS OF ATTENTION DETECTION

• US 20160315842A1
• Filed: 04/27/2015
• Published: 10/27/2016
• Est. Priority Date: 04/27/2015
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated (Kyndryl Holdings, Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Boss, Gregory J., Dawson, Christopher J., Hamilton, Rick A. II, Kozloski, James R.
• Granted Patent: US 10,009,405 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 43/0894 Packet rate
• CPC Class Codes: H04L 43/16 Threshold monitoring
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04L 65/80 Responding to QoS

Abstract

An approach is provided for managing a quality of service (QoS) of an application running in a networked computing environment. Based on information received from monitoring devices or tools that monitor a state of a user, a model of a cognitive focus of attention of the user is generated. An actual QoS for a software application is determined. Based on the model, a perceived QoS is determined. A current usage by the user of software application is determined. Based on the model, the actual QoS, and the current usage, an adjustment to the actual QoS is determined, while maintaining unchanged the perceived QoS.

Claims

1. A method of managing a quality of service (QoS) of an application running in a networked computing environment, the method comprising the steps of:

a computer generating a model of a cognitive focus of attention of a user, the model based on information received from one or more hardware monitoring devices external to the computer or one or more software tools that monitor one or more respective states of the user, and the one or more states corresponding to one or more respective software applications running on a computer network;

the computer determining one or more respective measurements of an actual QoS for the one or more software applications;

based on the model of the cognitive focus of attention of the user, the computer determining one or more estimations of a perceived QoS for the one or more software applications, the perceived QoS being a level of quality of service being perceived by the user via the cognitive focus of attention;

the computer determining one or more respective current usages by the user of the one or more software applications; and

based on the generated model of the cognitive focus of attention of the user, the one or more measurements of the actual QoS for the one or more software applications, and the one or more current usages by the user of the one or more software applications, the computer determining an adjustment to the actual QoS of a software application included in the one or more software applications, while maintaining unchanged an estimation of a perceived QoS for the software application, the estimation included in the one or more estimations.

2. The method of claim 1, further comprising performing the adjustment to the actual QoS of the software application, which increases an efficiency of sending packets to the software application via the computer network.

3. The method of claim 1, wherein the step of determining the adjustment to the actual QoS of the software application includes determining a decrease or an increase in a rate of sending packets to the software application via the computer network.

4. The method of claim 1, wherein the step of determining the adjustment to the actual QoS of the software application includes:

determining first and second sets of packets as packets being sent to the software application via the computer network to provide first and second portions, respectively, of a presentation that includes at least one of an audio component and a video component;

determining a decrease in a first rate of sending the first set of packets to the software application via the computer network;

determining a maintenance of a second rate of sending the second set of packets to the software application via the computer network so that the second rate is unchanged; and

determining the adjustment to the actual QoS to include the decrease in the first rate and the maintenance of the second rate.

5. The method of claim 1, further comprising the computer determining the user is not currently utilizing the software application or is utilizing the software application at a rate that is less than a predetermined threshold rate, wherein the step of determining the adjustment includes determining a decrease in a rate of sending packets to the software application via the computer network, based on the user not currently utilizing the software application or utilizing the software application at a rate that is less than the threshold rate.

6. The method of claim 1, further comprising the computer determining the cognitive focus of attention which indicates a video content of the software application is not in a visual range of the user, but an audio content of the software application is within an audio range of the user, wherein the step of determining the adjustment includes determining a decrease in a rate of the video content being sent to the software application via the computer network but maintaining unchanged a rate of the audio content being sent to the software application via the computer network.

7. The method of claim 1, further comprising the step of providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer readable program code in the computer, the program code being executed by a processor in the computer to implement the steps of generating the model, determining the one or more respective measurements of the actual QoS, determining the one or more estimations of the perceived QoS, determining the one or more respective current usages, and determining the adjustment to the actual QoS.

8. A computer system comprising:

a central processing unit (CPU);

a memory coupled to the CPU; and

a computer readable storage device coupled to the CPU, the storage device containing instructions that are executed by the CPU via the memory to implement a method of managing a quality of service (QoS) of an application running in a networked computing environment, the method comprising the steps of;

the computer system generating a model of a cognitive focus of attention of a user, the model based on information received from one or more hardware monitoring devices external to the computer or one or more software tools that monitor one or more respective states of the user, and the one or more states corresponding to one or more respective software applications running on a computer network;

the computer system determining one or more respective measurements of an actual QoS for the one or more software applications;

based on the model of the cognitive focus of attention of the user, the computer system determining one or more estimations of a perceived QoS for the one or more software applications, the perceived QoS being a level of quality of service being perceived by the user via the cognitive focus of attention;

the computer system determining one or more respective current usages by the user of the one or more software applications; and

based on the generated model of the cognitive focus of attention of the user, the one or more measurements of the actual QoS for the one or more software applications, and the one or more current usages by the user of the one or more software applications, the computer system determining an adjustment to the actual QoS of a software application included in the one or more software applications, while maintaining unchanged an estimation of a perceived QoS for the software application, the estimation included in the one or more estimations.

9. The computer system of claim 8, wherein the method further comprises performing the adjustment to the actual QoS of the software application, which increases an efficiency of sending packets to the software application via the computer network.

10. The computer system of claim 8, wherein the step of determining the adjustment to the actual QoS of the software application includes determining a decrease or an increase in a rate of sending packets to the software application via the computer network.

11. The computer system of claim 8, wherein the step of determining the adjustment to the actual QoS of the software application includes:

determining first and second sets of packets as packets being sent to the software application via the computer network to provide first and second portions, respectively, of a presentation that includes at least one of an audio component and a video component;

determining a decrease in a first rate of sending the first set of packets to the software application via the computer network;

determining a maintenance of a second rate of sending the second set of packets to the software application via the computer network so that the second rate is unchanged; and

determining the adjustment to the actual QoS to include the decrease in the first rate and the maintenance of the second rate.

12. The computer system of claim 8, wherein the method further comprises the computer determining the user is not currently utilizing the software application or is utilizing the software application at a rate that is less than a predetermined threshold rate, wherein the step of determining the adjustment includes determining a decrease in a rate of sending packets to the software application via the computer network, based on the user not currently utilizing the software application or utilizing the software application at a rate that is less than the threshold rate.

13. A computer program product comprising:

a computer readable storage device; and

a computer readable program code stored in the computer readable storage device, the computer readable program code containing instructions that are executed by a central processing unit (CPU) of a computer system to implement a method of managing a quality of service (QoS) of an application running in a networked computing environment, the method comprising the steps of;

the computer system generating a model of a cognitive focus of attention of a user, the model based on information received from one or more hardware monitoring devices external to the computer or one or more software tools that monitor one or more respective states of the user, and the one or more states corresponding to one or more respective software applications running on a computer network;

the computer system determining one or more respective measurements of an actual QoS for the one or more software applications;

based on the model of the cognitive focus of attention of the user, the computer system determining one or more estimations of a perceived QoS for the one or more software applications, the perceived QoS being a level of quality of service being perceived by the user via the cognitive focus of attention;

the computer system determining one or more respective current usages by the user of the one or more software applications; and

based on the generated model of the cognitive focus of attention of the user, the one or more measurements of the actual QoS for the one or more software applications, and the one or more current usages by the user of the one or more software applications, the computer system determining an adjustment to the actual QoS of a software application included in the one or more software applications, while maintaining unchanged an estimation of a perceived QoS for the software application, the estimation included in the one or more estimations.

14. The computer program product of claim 13, wherein the method further comprises performing the adjustment to the actual QoS of the software application, which increases an efficiency of sending packets to the software application via the computer network.

15. The computer program product of claim 13, wherein the step of determining the adjustment to the actual QoS of the software application includes determining a decrease or an increase in a rate of sending packets to the software application via the computer network.

16. The computer program product of claim 13, wherein the step of determining the adjustment to the actual QoS of the software application includes:

determining first and second sets of packets as packets being sent to the software application via the computer network to provide first and second portions, respectively, of a presentation that includes at least one of an audio component and a video component;

determining a decrease in a first rate of sending the first set of packets to the software application via the computer network;

determining a maintenance of a second rate of sending the second set of packets to the software application via the computer network so that the second rate is unchanged; and

determining the adjustment to the actual QoS to include the decrease in the first rate and the maintenance of the second rate.

17. The computer program product of claim 13, wherein the method further comprises the computer determining the user is not currently utilizing the software application or is utilizing the software application at a rate that is less than a predetermined threshold rate, wherein the step of determining the adjustment includes determining a decrease in a rate of sending packets to the software application via the computer network, based on the user not currently utilizing the software application or utilizing the software application at a rate that is less than the threshold rate.

18. A method of managing a quality of service (QoS) of a video conferencing application, the method comprising the steps of:

a computer 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;

based on the user communicating with the first participant, the computer generating a model of a cognitive focus of attention 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 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 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 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; and

based on the model of the cognitive focus of attention of the user, the first actual QoS for the other regions, and the second actual QoS, the computer determining an adjustment to the first actual QoS, without adjusting the second actual QoS, and while maintaining unchanged the estimation of the perceived QoS.

19. The method of claim 18, further comprising the computer determining a resolution of peripheral vision of the user, wherein the step of determining the adjustment includes determining a delay or a dropping of a set of packets that specify the other regions so that a resolution of the other regions matches the resolution of the peripheral vision of the user.

20. The method of claim 18, further comprising performing the adjustment which decreases a cost of sending the set of packets to the video conferencing application.

21. The method of claim 18, further comprising the computer 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.

22. A method of managing a quality of service (QoS) of a video streaming application running in a networked computing environment, the method comprising the steps of:

a computer generating a model of a cognitive focus of attention of a user, the model including a specification of a foveated region of a display of content of the video streaming application, the foveated region corresponding to a visual fovea of the user, and the specification of the foveated region based at least in part on measurements of eye movements of the user, and the measurements received from a monitoring device which is external to the computer; and

based on the generated model including the specification of the foveated region, the computer determining an adjustment to an actual QoS of packets sent to present the display of the content of the video streaming application, the adjustment including a delay or dropping of a first set of packets that specify a portion of the display outside the foveated region and a maintenance of a rate of sending a second set of packets that specify the foveated region.

23. The method of claim 22, further comprising the computer determining a resolution of peripheral vision of the user, wherein the step of determining the adjustment includes determining the delay or dropping of the first set of packets so that a resolution of the portion of the display outside the foveated region matches the resolution of the peripheral vision of the user.

24. The method of claim 22, further comprising performing the adjustment which decreases a cost of sending the first set of packets to the video streaming application.

25. The method of claim 22, wherein the step of determining the adjustment includes determining a decrease in an actual QoS of the first set of packets while maintaining unchanged a perceived QoS for the video streaming application.