Abstract: Determining a time-state metric includes receiving a stream of raw data values of an attribute. Each received raw data value of the attribute is associated with a timestamp. It further includes converting the received stream of raw data values into a timeline representation of the attribute over time. The timeline representation comprises a sequence of spans. A span comprises a span start time, a span end time, and a span value. The span value comprises an encoding of one or more values of the attribute over a time interval determined by the span start time and the span end time. It further includes determining a time-state metric according to a timeline request configuration. The timeline request configuration comprises one or more timeline operations. The time-state metric is computed at least in part by performing a timeline operation on the timeline representation of the attribute.

Abstract: Generating automatic diagnostics alerts is disclosed. At a first time, a set of quality metrics for a plurality of groups of streaming sessions is computed. An anomaly is identified at least in part by performing anomaly detection using the set of quality metrics and historical information. A cause of the identified anomaly is diagnosed. An alert is generated based at least in part on the diagnosis.

Abstract: Per-viewer engagement-based video optimization is disclosed. A request for content associated with a first client is received. A model associated with the first client is obtained. The obtained model comprises at least one of behavior and playback preferences of a viewer associated with the first client. The obtained model is used to determine, for the first client, an optimal set of instructions usable to obtain content. A different set of instructions is determined to be optimal for a second client. The optimal set of instructions determined for the client is provided as output. The first client is configured to obtain content according to the optimal set of instructions determined for the first client.

Abstract: Generating automatic diagnostics alerts is disclosed. At a first time, a set of quality metrics for a plurality of groups of streaming sessions is computed. An anomaly is identified at least in part by performing anomaly detection using the set of quality metrics and historical information. A cause of the identified anomaly is diagnosed. An alert is generated based at least in part on the diagnosis.

Abstract: Correlating information associated with playback of video segments is disclosed. Information associated with playback of a first video segment is obtained. Information associated with playback of a second video segment is obtained. The information associated with playback of the first video segment is correlated with the information associated with playback of the second video segment based at least in part on at least one of a client application identifier, a video session identifier, and a set of timestamps. Output is provided based at least in part on the correlating.

Abstract: Correlating information associated with playback of video segments is disclosed. Information associated with playback of a first video segment is obtained. Information associated with playback of a second video segment is obtained. The information associated with playback of the first video segment is correlated with the information associated with playback of the second video segment based at least in part on at least one of a client application identifier, a video session identifier, and a set of timestamps. Output is provided based at least in part on the correlating.

Abstract: Correlating information associated with playback of video segments is disclosed. Information associated with playback of a first video segment is obtained. Information associated with playback of a second video segment is obtained. The information associated with playback of the first video segment is correlated with the information associated with playback of the second video segment based at least in part on at least one of a client application identifier, a video session identifier, and a set of timestamps. Output is provided based at least in part on the correlating.

Abstract: Automatic diagnostics alerts for streaming multiple types of content is disclosed. At a first time, a set of metrics for a plurality of groups of streaming sessions is computed. A streaming session in a group is associated with streaming of a piece of content encoded by an entity. The streaming of the piece of content encoded by the entity is associated with streaming of another piece of content. An anomaly is identified at least in part by performing anomaly detection using the set of metrics. A cause of the identified anomaly is diagnosed. An alert is generated based at least in part on the diagnosis.

Abstract: Automatic diagnostics alerts for streaming multiple types of content is disclosed. At a first time, a set of metrics for a plurality of groups of streaming sessions is computed. A streaming session in a group is associated with streaming of a piece of content encoded by an entity. The streaming of the piece of content encoded by the entity is associated with streaming of another piece of content. An anomaly is identified at least in part by performing anomaly detection using the set of metrics. A cause of the identified anomaly is diagnosed. An alert is generated based at least in part on the diagnosis.

Abstract: Remote multi-target client monitoring for streaming content is disclosed. Raw data generated within a remote client device is received from the client device. The raw data is associated with content playback. An adaptor is used to translate the raw data into a unified data model. The translating comprises determining, from the raw data, a designation of at least one of a start and an end of a monitoring session.

Abstract: Remote multi-target client monitoring for streaming content is disclosed. Raw data generated within a remote client device is received from the client device. The raw data is associated with content playback. An adaptor is used to translate the raw data into a unified data model. The translating comprises determining, from the raw data, a designation of at least one of a start and an end of a monitoring session.

Abstract: Generating automatic diagnostics alerts is disclosed. At a first time, a set of quality metrics for a plurality of groups of streaming sessions is computed. An anomaly is identified at least in part by performing anomaly detection using the set of quality metrics and historical information. A cause of the identified anomaly is diagnosed. An alert is generated based at least in part on the diagnosis.

Abstract: Generating automatic diagnostics alerts is disclosed. At a first time, a set of quality metrics for a plurality of groups of streaming sessions is computed. An anomaly is identified at least in part by performing anomaly detection using the set of quality metrics and historical information. A cause of the identified anomaly is diagnosed. An alert is generated based at least in part on the diagnosis.

Abstract: Generating streaming decisions at one or more remote servers on behalf of a local client is disclosed. An indication of a content request, multi-dimensional client information, and local state information are received from a client device. A record specific to the client device is generated, in a data store, using the received local state information. The data store includes a plurality of records corresponding to respective different client devices. A set of instructions usable by the client device to obtain and play content is determined based at least in part the local state information received from the client device. The determined set of instructions is transmitted to the client device.

Abstract: Facilitating a decision of a content player is disclosed. In some cases, performance information associated with a content player is received. The information is received from a client. A determination is made that an update should be sent to the client. The update is sent to the client. In other cases, information is received from an external entity. Based at least in part on the received information, an instruction is sent to a content player.

Abstract: Selecting an optimal bitrate range is disclosed. A request for content from a first client is received. An optimal subset of bitrates for the first client is determined. The optimal subset of bitrates for the first client is determined based at least in part on one or more real-time quality measures. A different optimal subset of bitrates is determined for a second client. An indication of the optimal subset of bitrates determined for the first client is provided to the first client. The first client is configured to obtain content according to the indication of the optimal subset of bitrates.

Abstract: Providing network insights is disclosed. A mapping between a device identifier and one or more nodes in a network topology associated with a network service provider is obtained. End user experience data associated with the device identifier is obtained. Based at least in part on the device identifier. at least some of the obtained end user experience data is associated with at least some of the one or more nodes in the network topology associated with the network service provider. Processing is performed based at least in part on the association of the at least some of the obtained end user experience data with the at least some of the one or more nodes in the network topology associated with the network service provider. Output is provided based at least in part on the processing.

Abstract: Facilitating a decision of a content player is disclosed. In some cases, performance information associated with a content player is received. The information is received from a client. A determination is made that an update should be sent to the client. The update is sent to the client. In other cases, information is received from an external entity. Based at least in part on the received information, an instruction is sent to a content player.

Abstract: Per-viewer engagement-based video optimization is disclosed. A request for content associated with a first client is received. A model associated with the first client is obtained. The obtained model comprises at least one of behavior and playback preferences of a viewer associated with the first client. The obtained model is used to determine, for the first client, an optimal set of instructions usable to obtain content. A different set of instructions is determined to be optimal for a second client. The optimal set of instructions determined for the client is provided as output. The first client is configured to obtain content according to the optimal set of instructions determined for the first client.

Abstract: Correlating information associated with playback of video segments is disclosed. Information associated with playback of a first video segment is obtained. Information associated with playback of a second video segment is obtained. The information associated with playback of the first video segment is correlated with the information associated with playback of the second video segment based at least in part on at least one of a client application identifier, a video session identifier, and a set of timestamps. Output is provided based at least in part on the correlating.