Method and system for user-oriented streaming of content

A method in a networking environment of generating a user-specific data streaming mechanism for a user-equipment (UE), the method comprising:

• simulating content playback based on synthetic network traces and at least one standard adaptive bitrate (ABR) logic;
• logging a plurality of input and output states associated with the simulated content playback to create a log of labelled data;
• generating at least a first type of model based on training through a first machine learning (ML) based criteria using the log of labelled data;
• re-simulating content playback at least based on real network traces and one or more bit-rate selected based on the first model;
• and
• generating a second model by training the first model through a reinforcement ML criteria directed to improve a quality of experience, the training being based on analysis of results of the re-simulation of the content-playback.

A system configured to selectively deploy an application facilitating quality-of-experience (QoE) of streaming multimedia content in a networking environment comprising a user-equipment (UE) and a networking node including a predictive analysis module, the system comprising:

• a capturing module configured to capture parameters pertaining to the UE from at least one of:
• a version of the predictive analysis module with respect to the UE;
• a current processor occupancy within the UE;
• a power level within the UE;
• an observation module configured to observe one or more network-conditions pertaining to the access network being accessed by the UE;
• an inference module configured to:
• analyze one or more of the captured parameters and the observed network conditions;
• and
• inference, based on the analysis, to select between the predictive analysis model of the UE and of the networking node to enable a customized streaming of multimedia content at the UE.

A system operating in a networking environment to generate a user specific data streaming mechanism for a user equipment (UE), the system comprising:

• a synthetic network traces and labelled data generator configured to:
• simulate content playback based on synthetic network traces and at least one standard adaptive bitrate (ABR) logic;
• and
• logging a plurality of input and output states associated with the simulated content playback to create a log of labelled data;
• a supervised learning (SL) based machine learning module configured to generate a first type of model based on training through a first machine learning (ML) based criteria using the log of labelled data;
• and
• a reinforcement learning module configured to:
• simulate content playback at least based on real network traces and one or more bit-rate selected based on the first model;
• and
• generate a second model by training the first model through a reinforcement ML criteria directed to improve a quality of experience (QoE), the training based on analysis of results of the re-simulation of the content playback.