Content personalization based on reinforcement learning

    公开(公告)号:US12206944B2

    公开(公告)日:2025-01-21

    申请号:US18102573

    申请日:2023-01-27

    Abstract: Methods and systems are provided herein for providing media asset recommendations to a user based on user input in real time and using a reinforcement learning model or media asset recommendation model. The model includes a plurality of states, each having a set of media asset recommendations, a plurality of available user input options, and a state value. During a browsing session, a first set of media asset recommendations is provided to a user based on a current state corresponding to the browsing session. The user then selects a user input option, and a second set of media asset recommendations is determined based on the received user input option. The second set of media asset recommendations is then provided to the user during the browsing session.

    Systems and methods for distributed media streaming

    公开(公告)号:US12206913B2

    公开(公告)日:2025-01-21

    申请号:US18400540

    申请日:2023-12-29

    Abstract: Systems and methods are described for identifying a first network (associated with an edge server comprising a cache) and a second network available to a user equipment device. A request to access at least a portion of a media asset may be received from the user equipment device. In response to determining that the at least a portion of the media asset is not stored in the cache, a determination may be made whether the edge server, via the first network, or whether the user equipment device, via the second network, should obtain such at least a portion of the media asset. Such at least a portion of the media asset may be obtained using the selected server via the first network or using the selected user equipment device via the second network, caused to be stored at the cache, and generated for display at the user equipment device.

    SYSTEMS AND METHODS FOR GUIDING PERSPECTIVES FOR MULTI-PERSPECTIVE CONTENT

    公开(公告)号:US20250021157A1

    公开(公告)日:2025-01-16

    申请号:US18903944

    申请日:2024-10-01

    Abstract: A method of guiding perspectives in a multi-perspective content delivery system. The method includes receiving profile data associated with an end-user multi-perspective content consumption device and identifying a preference for content based upon the profile data. Multi-perspective content is transmitted to a device associated with the first profile data, the multi-perspective content representing a first perspective of a plurality of time-coincident VR perspectives. The VR system determines whether the first perspective correlates with the preference for content by at least a predetermined amount. In response to determining that the first perspective does not correlate with the preference for content by at least the predetermined amount, determining a second perspective of the plurality of perspectives that correlates to a greater degree with the preference for content than the first perspective, and transmitting from the end-user device a cue for recommending a change in perspective to the second perspective.

    Systems and methods for improved video captions

    公开(公告)号:US12200395B2

    公开(公告)日:2025-01-14

    申请号:US17185422

    申请日:2021-02-25

    Abstract: Systems and methods for improved video captions are disclosed. The methods for providing timed text comprise obtaining a plurality of subtitles for a media asset; determining a playback rate of the media asset; determining a relevance index based on the playback rate; and selecting a set of the plurality of subtitles based on the relevance index. The methods may further comprise determining an indication of priority of subtitles within the set of subtitles, rendering the set of subtitles according to the indication of priority, wherein the highest priority subtitles are rendered first.

    Methods and systems for separate delivery of segments of content items

    公开(公告)号:US12200281B2

    公开(公告)日:2025-01-14

    申请号:US18219989

    申请日:2023-07-10

    Abstract: Systems and methods are described herein for transmitting a content item to a user device using multiple delivery protocols. The system receives, at a content source, a request for the content item from the user device. The system splits a digital stream of the content item into a first video signal and a second video signal. The system then transmits, via a unicast server, the first video signal for the content item to the user device, and transmits, via a multicast server, the second video signal for the content item to the user device. The system then causes for presentation on the user device the first video signal followed by the second video signal. In other embodiments, the system is optimized between the unicast delivery of a content item and a peer-to-peer delivery.

    Systems and methods for mesh geometry prediction for high efficiency mesh coding

    公开(公告)号:US12198273B2

    公开(公告)日:2025-01-14

    申请号:US17974863

    申请日:2022-10-27

    Inventor: Zhu Li Tao Chen

    Abstract: Systems and methods are provided for efficiently encoding geometry information for 3D media content. An illustrative system generates a low-resolution polygon mesh from a high-resolution polygon mesh. The system uses a vertex occupancy prediction network to generate, from vertices of the low-resolution polygon mesh, approximated vertices of the high-resolution polygon mesh. The system uses a connectivity prediction network to generate, from approximated vertices of the high-resolution polygon mesh, approximated connections of the high-resolution polygon mesh. The system computes vertex errors between the approximated vertices and the vertices of the high-resolution polygon mesh, and connectivity errors between the approximated connections and the connections of the high-resolution polygon mesh. The system transmits, to a receiver over a communication network, bitstreams of the low-resolution polygon mesh, the vertex errors, and the connectivity errors for reconstruction of the high-resolution polygon mesh and display of the 3D media content.

Patent Agency Ranking