Abstract: A computer-implemented method is described and includes automatically creating a group profile for an account associated with a streaming service platform, wherein the group profile is informed by a plurality of individual user profiles associated with the account, wherein each of the individual user profiles is associated with a different one of a plurality of users; presenting via a user interface (UI) of the streaming service platform representations of each of the group profile and the individual user profiles; prompting one of the users to select one of the profiles to use to view content items via the streaming service platform; and, subsequent to selection by the user of the group profile, presenting via the UI a collection of content item recommendations, wherein the content item recommendations are informed by contents of the individual user profiles collectively.

Abstract: Kalman filters are used to control paced content delivery, in which a content delivery platform delivers content to a specific subset of end users. A content provider can arrange with the platform to deliver content to a portion of the platform's users. The content provider may specify certain criteria or objectives for the content delivery strategy, e.g., targeting criteria, engagement, or reach. Kalman filters may be used to control the content delivery strategy. For example, a first control knob controlled by a first Kalman filter may be tied to pace, and a second control knob controlled by a second Kalman filter may be tied to a performance objective.

Abstract: User information can be determined based on a user input received from a user, a user profile about the user, and a profile of a user community including the user. Metadata associated with a media content can indicate a first portion of the media content to be of a first content category, and a second portion of the media content to be of a second content category different from the first content category. The media content can include an audio stream and a video stream, and the first content category or the second content category can be determined based on the audio stream or the video stream of the media content. Based on the metadata and the user information, a first action can be performed for playing the first portion of the media content and a second action can be performed for playing the second portion of the media content.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for synchronizing playback of audiovisual media. An example process includes receiving, via at least one microphone, a first signal that is outputted from at least one external speaker that is coupled to a display device; determining, based on the first signal, a latency associated with the at least one external speaker, wherein the latency corresponds to a difference between a transmission time of the first signal by the display device to the at least one external speaker and an output time of the first signal by the at least one external speaker; and providing the latency to the display device, wherein the display device is configured to adjust at least one of a video playback timing and an audio playback timing of an audiovisual media content item based on the latency.

Abstract: The present disclosure is directed to systems and methods for modulating the quality of media content based on aggregate data usage. For example, a method may include: collecting usage data information from a plurality of locations; determining a data cap for each of the plurality of locations; training a machine learning model using the usage data information and the data cap; predicting, using the machine learning model, whether a location is going to exceed its associated data cap, the location being a new location or an existing one of the plurality of locations; and determining whether the modulate a quality of media content transmitted to the location based on the prediction.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method, and computer program product embodiments for modifying the functionality of an alternating current (AC) controlling device. An example computer-implemented method includes determining whether an electrical terminal of an AC controlling device is connected to a grounded conductor. In response to determining that the electrical terminal is connected to the grounded conductor, the example computer-implemented method includes generating a first control signal configured to permit the AC controlling device to perform a function. In response to determining that the electrical terminal is not connected to the grounded conductor, the example computer-implemented method includes generating a second control signal configured to prevent the AC controlling device from performing the function.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for determining an number of slots for achieving a desired reach specified in a media content delivery schedule. The system, apparatus, article of manufacture, method, and/or computer program product aspects is designed with a simulation framework tuned to predict an estimate the needed number of slots based on a reach specified in the delivery schedule.

Abstract: Disclosed are mechanisms for selecting a recommended item for a current item being viewed by a user account based on a view history of the user account with reduced bias. For a current item being viewed by the user account represented by a current node of a co-watch graph, embodiments can select a recommended item represented by an associated node in the co-watch graph likely being viewed by the user account, and determine a probability of the recommended item likely being viewed. The co-watch graph can be generated based on a view history of the user account. An edge between a first node and a second node of the co-watch graph can have a weight representing a number of co-occurrence times when the first item represented by the first node and the second item represented by the second node are viewed in sequence within a predetermined time interval.

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 enhancing the presentation of media content based on the detection of a trigger phrase during playing of the media content. An example embodiment operates by a media device receiving the trigger phrase from a user and generating a content enhancement protocol based on the trigger phrase and a user-supplied enhancement effect. During presentation of the media content, the media device may monitor content metadata associated with the media content to detect the trigger phrase, and upon detection, the media device may initiate the content enhancement protocol on the media content.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for deep video understanding with large language models. An example embodiment operates by determining a relationship between respective first and second visual elements for each of a plurality of frames of a content item based on respective element types and respective locations for the respective first and second visual elements. For each of the plurality of frames, a respective visual prompt is generated describing the relationship between the respective first and second visual elements. Based on an audio-to-text conversion of audio content associated with the frame or classification of aural elements of the audio content, a respective audio prompt describing the audio content associated with each frame is generated.

Abstract: Disclosed herein are system, apparatus, method and/or computer program product embodiments for a multimedia environment that includes a computing device to display multiple multimedia segments within multiple display areas of a display device. The computing device may determine a first multimedia segment including a plurality of frames, and display the first multimedia segment within a first display area of the display device. The computing device may further determine, based on a user profile or content of the first multimedia segment, a second multimedia segment related to the first multimedia segment to be displayed within a second display area of the display device within the predetermined time interval.

Abstract: Embodiments described herein include a method that operates by receiving, at a media device, one or more signals from a remote control. The media device identifies a user currently using the remote control based on the signals. Then, the media device selects content to make available based on the identified user. In some embodiments, the media device identifies the user by using the signals to identify the remote control. Then, the media device determines that a user associated with the identified remote control is the user currently using the remote control.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for switching the output of an overriding multimedia device from a first input to a second input or a combination of the first input and the second input. An example embodiment operates by receiving data relating to a multimedia switching event. The example embodiment further operates by determining that the data corresponds to a multimedia switching action. In response, the example embodiment operates by generating a multimedia switching actuation signal that instructs an overriding multimedia device to switch its output from the first multimedia signal to the second multimedia signal. Subsequently, the example embodiment operates by transmitting the multimedia switching actuation signal to the overriding multimedia device.

Abstract: Disclosed herein are system, method, and computer program product embodiments that evaluate quality of metadata elements for use in a content selection graphical user interface. The metadata elements are processed using a deep neural network (DNN) trained to generate quality labels or scores for the metadata elements. Training metadata elements are processed using a large language model to generate asset embeddings corresponding to the training metadata elements. Similarity scores between pairs of the asset embeddings are computed. Training metadata elements having asset embeddings outside of first and second score thresholds are labeled with a first label indicative of “bad” metadata, and training metadata elements having asset embeddings between the thresholds are labeled with a second label indicative of “good” metadata. The DNN is trained to perform the generation of the quality labels or scores using supervised learning, based on the labeled training metadata elements.

Abstract: A display system adjusts picture quality settings to provide an improved and more consistent viewer experience. Different display manufacturers have different default picture quality settings, and a content display device learns the settings of a connected display and adjusts the picture to reduce variation across different displays. A mobile device may be used to capture environmental data (e.g., ambient light), and a content display device adjusts picture quality based on the captured data.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for high dynamic range brightness control. An example embodiment operates by determining, by at least one computer processor, a darkness level of a video frame, determining a brightness adjustment level based on the darkness level of the video frame, and adjusting a brightness level of a later frame based on at least the brightness adjustment level. The brightness level for the later video is adjusted within two video frames from the video frame.

Abstract: Techniques for selecting data for pre-loading onto a device and pre-loading the data into memory of the device. Certain devices, such as streaming sticks, offer a large number of apps. Pre-loading app data into memory can improve response time to load the app and offer an improved user experience. However, the memory is not large enough to pre-load app data for many apps simultaneously. As described herein, a neural network is used to determine the most likely apps for a user to load. The likelihoods are considered in combination with speedup value to pre-loading the app data as well as memory needed to pre-load the app data. A knapsack algorithm may be used to identify a set of app data for pre-loading.

Abstract: Television sound quality has a poor reputation, sometimes due to the designs getting thinner. Common issues include distortion, clipping, muddy dialogue, and lack of bass. Some issues are due to or made worse by errors in tuning. The errors may come from improper measurements, lack of understanding, and prioritization of incorrect metrics. To address this issue, a data driven and objective predictive model is implemented to offer a consistent and scalable way to determine perceived sound quality of a wide range of audio systems. The predictive model can be used to determine optimal tuning parameters that would yield the best perceived sound quality of the audio system.

Abstract: Television sound quality has a poor reputation, sometimes due to the designs getting thinner. Common issues include distortion, clipping, muddy dialogue, and lack of bass. Some issues are due to or made worse by errors in tuning. The errors may come from improper measurements, lack of understanding, and prioritization of incorrect metrics. To address this issue, a data driven and objective predictive model is implemented to offer a consistent and scalable way to determine perceived sound quality of a wide range of audio systems. The predictive model can be used to determine optimal tuning parameters that would yield the best perceived sound quality of the audio system.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for modifying one or more parameters of a data streaming bitrate selection algorithm based on machine learning. An example embodiment operates by training and operating a first machine learning model to predict a sustainable network bandwidth. A second machine learning model is trained to receive the sustainable network bandwidth and predict a likelihood that this network bandwidth will not empty a data buffer of streaming data. A bitrate is selected based on the likelihood being below a threshold percentage, such as 50%.