Beijing Yojaja Software Technology Development Co., Ltd.

Beijing Hulu Software Technology Development Co., Ltd.

Chenyu Tian

Tongyu Dai

Si Chen

Lemei Huang

Wenhao Zhang

Renfei Shang

In some embodiments, a method receives quality metric values for profile levels in a plurality of profile levels for a segment of content. An available bandwidth and associated bitrates of profile levels in the plurality of profile levels are evaluated to select a first profile level. The quality metric values for profile levels in the plurality of profile levels are evaluated to select a second profile level. The method selects a profile level in the plurality of profile levels based on the first profile level and the second profile level. The profile level that is selected is requested for the segment.

Adaptive bitrate streaming using video quality information

In some embodiments, a method receives a network trace from a playback session of a delivery of content being managed by a content management system. The network trace is decomposed into a first sub-trace and a second sub-trace based on a threshold. The threshold is used to divide the network trace into the first sub-trace and the second sub-trace. A value is extracted for a feature for the network trace based on the first sub-trace. The method classifies the network trace into a category based on the value and performs an action based on the category for the content management system.

Network trace categorization in content delivery

In some embodiments, a method determines training data from first nearline features for a first sliding time window and a fixed time window. The first sliding time window changes during a first time period and the fixed time window is static during the first time period. A prediction model is trained using the training data. The prediction model is trained for a second time period in the first time period. The method determines values for second nearline features for a second sliding time window and a fixed time window for a request for a current session that is received during the second time period. The second sliding time window is based on a time for the request. The values are input for the second nearline features into the prediction model to generate a prediction. The method performs an action for the current session based on the prediction.

Content playback optimization using nearline information

In some embodiments, a method determines an input value for a request for content and retrieves a plurality of states for a plurality of content delivery networks. The state includes a component that is based on variance. A plurality of scores for a plurality of content delivery networks is generated based on the input value and the plurality of states. A score for a content delivery network is generated using a parameter value for the component and the input value. The method selects a content delivery network from the plurality of content delivery networks based on the score for the content delivery network and outputs information for the selected content delivery network to cause the selected content delivery network to service the request to deliver the content.

Growing community of inventors

Beijing, China

Chenyu Tian