Abstract: In one aspect, an example method includes: (i) a computing system obtaining media content; (ii) the computing system extracting from the obtained media content, audio content; (iii) the computing system using at least the extracted audio content to obtain sentiment data associated with the audio content; (iv) the computing system using the obtained sentiment data as a basis to modify a video content component of the media content, thereby generating a modified version of the media content; and (v) the computing system outputting for presentation the generated modified media content.

Abstract: In one aspect, an example method includes (i) receiving, from a content-distribution system, video comprising a watermark; (ii) extracting the watermark from the video; (iii) based on the extracted watermark, determining a content-creation attribute of the video that indicates a process by which the video was created, wherein the determining comprises using the watermark to select the content-creation attribute from among a set of two or more content-creation attributes comprising organically-generated video and synthetically-generated video; and (iv) in response to determining the content-creation attribute of the video, causing a content-presentation device to perform an action.

Abstract: Disclosed herein are system, method and/or computer program product embodiments, and/or combinations thereof, for stochastic multi-period multi-objective optimization based recommendation system. An embodiment assigns a respective plurality of stochastic parameters to a plurality of recommendation objectives. The embodiment further associates each program of a plurality of programs with one or more recommendation objectives of the plurality of recommendation objectives, and selects, during a first recommendation time period, a first set of operative recommendation objectives from the plurality of recommendation objectives based on the plurality of stochastic parameters. The embodiment then generates a first ordered list of recommended programs from the plurality of programs based on the first set of operative recommendation objectives.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for mitigating performance degradation of a computing device. In an embodiment, configuration setting(s) for mitigating performance degradation of the computing device are received from a data source external to the computing device. An order of actions for mitigating the performance degradation is determined based on the configuration setting(s). A notification that utilization of at least one compute resource of the computing device has met a degradation condition is received. Action(s) to mitigate the performance degradation are performed based on the notification in accordance with the determined order of actions.

Abstract: System, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, generate a prediction based on a query. A query is provided to a deep machine learning (ML) model. The deep ML model generates a plurality of query projection embeddings by projecting the query into each of a plurality of different query embedding spaces and generates the prediction based at least on the plurality of query projection embeddings. Each of a plurality of query projection embedding layers of the deep ML may generate a corresponding one of the query projection embeddings by applying a hash function associated with the query projection layer to the query to generate a vector representation of the query, and applying a set of weights associated with the query projection layer to the vector representation to generate a query projection embedding in the plurality of query projection embeddings.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product aspects, and/or combinations and sub-combinations thereof, for reducing prompt-based interruptions for a user of a media device having an operating system (OS). An example aspect operates by configuring a user interface (UI) of an OS based on a first-user OS profile corresponding to a first user, wherein the first-user OS profile is associated with a unique identifier of the first user. The embodiment receives a command to launch a first application. The embodiment, in response to receiving the command, determines that a unique identifier of a most recent active profile used on the media device matches the unique identifier of the first user. The embodiment, in response to the determining, configures a UI of the first application based on the most recent active profile. The embodiment then outputs the UI of the first application.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for preserving channel lock while performing dynamic ad insertion (DAI) in a multi-device setup. An example embodiment operates by identifying a secondary device that loses a channel lock on a channel based on a primary device performing DAI on the channel. The embodiment determines that that the primary device is configured to perform a DAI to replace a portion of multimedia content in the channel with a replacement portion of multimedia content. The embodiment modifies an automated content recognition (ACR) behavior for the secondary device based on the determining, thereby preventing the secondary device from losing channel lock on the channel. The embodiment then modifies a DAI behavior for the secondary device in response to the modifying the ACR behavior for the secondary device.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for user-based content filtering. A type of content indicated by a user profile associated with a request for a content item may be identified. An occurrence of the type of content within the content item may be identified. Filtering data that comprises one or more instructions for a media device to modify (e.g., blur, alter, obfuscate, etc.) a visual representation of the identified occurrence of the type of content during playback may be generated. The content item and the filtering data may be sent to a media device associated with the user profile.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for controlling a backlight apparatus in a media device with driver ICs. In some embodiments, the media device can include a display screen and the backlight apparatus. In some embodiments, the backlight apparatus can include first and second LEDs in a first horizontal zone and third and fourth LEDs in a second horizontal zone. The backlight apparatus can include a first driver IC connected to the first and third LEDs and configured to turn on the first LED during a first time period and the third LED during a second time period. The backlight apparatus can include a second driver IC connected to the second and fourth LEDs and configured to turn on the second LED during the first time period and the fourth LED during the second time period.

Abstract: Embodiments present techniques for determining a list of recommended items in response to a user query. An embodiment can determine a first ordered list of items including a plurality of items stored by a content platform. Based on a reward discount parameter, a first total discounted future reward for the first ordered list of items can be determined. Based on a risk discount parameter, a first risk estimate for the first ordered list of items can be determined. Similarly, a second ordered list of items can have a second total discounted future reward and a second risk estimate. The second ordered list of items can be the list of recommended items when the second total discounted future reward is larger than or equal to the first total discounted future reward, and the second risk estimate is less than or equal to the first risk estimate.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for reducing active user or active content category bias in content recommendation systems. An example embodiment operates by modifying a streaming event data set by selecting a voting algorithm. The voting algorithm reduces an impact of highly occurring data points by sampling the streaming event data set to generate a sampled streaming event data set, wherein the highly occurring data points comprise data points generated by the active users or the active content categories. The embodiment further trains, by a machine learning engine and based on the sampled streaming event data set, a machine learning model to generate a reduced bias content recommendation model and generates, based on the reduced bias content recommendation model, content recommendations for subsequent selection and rendering on a media device.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method, and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for demographic predictions for content items. An example embodiment operates by assigning weights representing demographics to a first plurality of nodes of a predictive model and assigning predictive values representing predicted demographics to a second plurality of nodes of the model. Pairwise distances between the predictive values for the nodes of the second plurality of nodes and the weighted values of the first plurality of nodes may be calculated and the shortest calculated pairwise distances may be used to assign demographics for content items corresponding to nodes of the first plurality of nodes to content items corresponding nodes of the second plurality of nodes. When content is requested, a content item for which the same demographic has been assigned may be recommended to the requestor.

Abstract: In one aspect, a method includes using a Wi-Fi module of a computing device to detect that an end-user has exited a monitored environment of the computing device, where the monitored environment comprises an Internet of Things (IoT) device communicatively coupled to the computing device over an IoT network. The method also involves in response to detecting that the end-user has exited the monitored environment, triggering a first IoT action at the IoT device. The method also involves after detecting that the end-user has exited the monitored environment and triggering the first IoT action, using the Wi-Fi module of the computing device to detect that the end-user has reentered the monitored environment. The method also involves in response to detecting that the end-user has reentered the monitored environment, triggering a second IoT action at the IoT device.

Abstract: Disclosed herein are system, apparatus, article-of-manufacture, method and/or computer program product embodiments, and/or combinations/sub-combinations thereof, for personalized multimodal analysis for content item recommendation. An embodiment operates by identifying playback of a first content item by a user device, and simulating playback of a second content item with a modality feature that matches the first content items. Affinity for a modality of the second content item is identified based on weights assigned to the different modalities according to the simulated playback. Respective similarity scores are generated for a plurality of content items based on a similarity between a vector for an embedding indicative of the modality for the second content item and a respective vector for an embedding indicative of the modality generated for the content items. Indication of a set of content items with respective similarity scores that satisfy a similarity score threshold is sent to the user device.

Abstract: Surround sound systems can dramatically expand the size of a user's sound field. Much surround sound content is mixed in a simplistic way where the front audio is copied to the rear, at a lower volume. It can be difficult for users to appreciate the value proposition of a surround sound system without more compelling spatially complex content. Quantifying surround sound complexity of various content items based on an audio spatial complexity scoring system can address this issue. Algorithms can be implemented to determine an audio spatial complexity score based on audio channels of a content item. Large catalog of content items can be analyzed, and audio spatial complexity scores can be associated with various content items. If a user has a surround sound system, content items with a high audio spatial complexity can be retrieved or recommended to the user to demonstrate the surround sound system's value better.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for utilizing a single storage buffer for a dynamic number of players, each using a dynamically sized virtual buffer. For example, a system includes a buffer management controller that receives a request to initiate at least one player instance for displaying a content item. The buffer management controller creates a virtual buffer having a maximum capacity for the player instance. Finally, the buffer management controller identifies one or more available regions of the single storage buffer and maps the virtual buffer to the one or more available regions in response to determining that address space in the one or more available regions matches or exceeds the maximum capacity of the virtual buffer.

Abstract: Disclosed herein are system, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for performing context classification of streaming content using machine learning (ML). In an embodiment, a streaming media client receives an audio/video (A/V) stream that represents a portion of content to be played back by the client. The client reconstructs a sequence of video frames from the A/V stream, extracts audio information from the A/V stream, and executes an ML based classifier to predict a context label associated with the portion of content based at least on one or more video frames from the sequence of video frames and the audio information. The client then transmits the context label to a streaming media service. The service may use the context label to select an advertisement or content recommendation to send to the client or to select a set of content streaming parameters for the client.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for utilizing a content recommendation system powering a streaming media publisher channel to enhance an ad creative being shown to the user via awareness or performance campaigns. This method allows the platform to present the most relevant Machine Language (ML) personalized in-channel content to the publisher platform users in endemic banners that run on the platform which then correspondingly helps drive user reach. An example embodiment operates by implementing personalized content banners that may act as a hook for channel users opening their streaming device, both active and lapsed, to enter back into the channel.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for utilizing a content recommendation system powering a streaming media publisher channel to enhance an ad creative being shown to the user via awareness or performance campaigns. This method allows the platform to present exploratory personalized in-channel content to the publisher platform users in endemic banners that run on the platform which then correspondingly helps drive user reach. An example embodiment operates by implementing personalized content banners that may act as a hook for channel users opening their streaming device, both active and lapsed, to enter back into the channel.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for dynamically adjusting sound output of a multi-speaker configuration of a display device. The adjustment may be performed to optimize the sound output based on the physical position of the display device in relation to one or more microphones within a physical environment. An example embodiment operates by the speakers within the display device emitting calibration sound waves and receiving sound data associated with the calibration sound waves. The sound data includes characteristics of the calibration sound waves within the physical environment. The display device may then adjust sound output of speakers within the multi-speaker configuration based on the sound output characteristics.