Dynamically adjusting quality of service using cognitive focus of attention detection

    公开(公告)号:GB2541056A

    公开(公告)日:2017-02-08

    申请号:GB201606806

    申请日:2016-04-19

    Applicant: IBM

    Abstract: The invention adjusts the quality level of applications (typically real time media such as video), in applications such as video conferencing and streaming. A model of the cognitive focus of user attention is fed information such as gaze/eye tracking, open and in focus application windows, presence in a room (see Fig. 3) and so forth in order to determine user attention 202. Actual quality of service (QoS) (e.g. data rate) is determined for programs 204. A perceived QoS (pQoS) is determined using the determined user attention 206 and thence the invention determines allowable adjustments to the actual QoS which will maintain the same perceived QoS 210 and applies them to the application. The invention allows efficient use of network bandwidth whilst maintaining a perceived quality of service for the user.

    User interface sound emanation activity classification

    公开(公告)号:GB2578079A

    公开(公告)日:2020-04-15

    申请号:GB202001744

    申请日:2018-07-06

    Applicant: IBM

    Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining an audio input, the audio input representing sound emanating from a key press based user interface; generating a context pattern based on the audio input; performing classification of the context pattern to classify the context pattern as belonging to a signature pattern classification, wherein the signature pattern classification specifies a user activity; and providing an output based on the performing classification.

    User interface sound emanation activity classification

    公开(公告)号:GB2578079B

    公开(公告)日:2020-10-21

    申请号:GB202001744

    申请日:2018-07-06

    Applicant: IBM

    Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining an audio input, the audio input representing sound emanating from a key press based user interface; generating a context pattern based on the audio input; performing classification of the context pattern to classify the context pattern as belonging to a signature pattern classification, wherein the signature pattern classification specifies a user activity; and providing an output based on the performing classification.

Patent Agency Ranking