Systems and methods for correcting errors in caption text

    公开(公告)号:US12225248B2

    公开(公告)日:2025-02-11

    申请号:US18389315

    申请日:2023-11-14

    Abstract: Systems and methods are described to address shortcomings in conventional systems by correcting an erroneous term in on-screen caption text for a media asset. In some aspects, the systems and methods identify the erroneous term in a text segment of the on-screen caption text, and identify one or more video frames of the media asset corresponding to the text segment. The systems and methods further identify a contextual term related to the erroneous term from the one or more video frames. By accessing a knowledge graph, the systems and methods identify a candidate correction based on the contextual term and a portion of the text segment. Lastly, the systems and methods replaces the erroneous term with the candidate correction.

    Systems and methods for enabling communications in an extended reality environment

    公开(公告)号:US12225086B2

    公开(公告)日:2025-02-11

    申请号:US18493532

    申请日:2023-10-24

    Inventor: Charles Dasher

    Abstract: Systems and methods are described herein for generating for display, at an extended reality (XR) device executing an application, an XR environment comprising an entity and associated with an XR session of a user profile. Execution of the application enables the XR device, while generating for display the XR environment, to transmit data to, and receive data from, a particular device using a first communication protocol, and transmit data to, and receive data from, the entity using a second communication protocol. Based on monitored activity of the user profile during the XR session, the XR device may be enabled to transmit data, received at the XR device from the entity using the second communication protocol, to the particular device using the first communication protocol, and transmit data, received at the XR device from the particular device using the first communication protocol, to the entity using the second communication protocol.

    SYSTEMS AND METHODS FOR PROVIDING INTERACTIVE CONTENT DURING A PRESENTATION OF A LIVE PROGRAM

    公开(公告)号:US20250047946A1

    公开(公告)日:2025-02-06

    申请号:US18228391

    申请日:2023-07-31

    Abstract: Systems, methods, and apparatuses are described herein for generating, for presentation at a particular computing device, a display of a live program and determining that the display of the live program at the particular computing device is delayed in relation to a live program stream of the live program. Interactive content related to a particular event that is to occur in the live program stream of the live program may be received, the interactive content enabling selection of a predicted outcome of the particular event. Prior to presentation of the particular event in the display of the live program at the particular computing device, the interactive content may be generated for presentation at the particular computing device, and a selection of the predicted outcome is received. Based on determining an outcome of the particular event, an indication of whether the predicted outcome was correct may be generated for presentation.

    DEEP REINFORCEMENT LEARNING FOR PERSONALIZED SCREEN CONTENT OPTIMIZATION

    公开(公告)号:US20250047944A1

    公开(公告)日:2025-02-06

    申请号:US18917798

    申请日:2024-10-16

    Inventor: Kyle Miller

    Abstract: Systems and methods are described for selecting content item identifiers for display. The system may identify a set of content items that are likely to be requested in the future based on a history of content item requests. The system then selects a first plurality of content categories using a category selection neural net and selects a first set of recommended content items for the first plurality of content categories. The system increases a reward score for the first plurality of content categories based on receiving a request for a content item that is included in the first set of recommended content items. The system also decreases the reward score for the first plurality of content categories based on determining that the requested content item is included in the set of content items that are likely to be requested in the future. The neural net is trained based on the reward score of the first plurality of content categories to reinforce reward score maximization. The trained neural net is the used to select content items for display.

    SYSTEM AND METHOD FOR CLASSIFYING RECORDED CONTENT FOR DELETION

    公开(公告)号:US20250047931A1

    公开(公告)日:2025-02-06

    申请号:US18917843

    申请日:2024-10-16

    Abstract: Systems and methods are disclosed herein for classifying, based on most recent information associated with recorded content, the recorded content to an appropriate deletion classifier. A media guidance application may receive information about an event that is associated with a recorded media asset. The media guidance application may determine, based on the event and a current deletion classifier associated with the recorded media asset, whether the current deletion classifier associated with the recorded media asset needs to be updated to a new deletion classifier. The media guidance application may make this determination by accessing a deletion classification database containing rules for classifying recorded media assets into a variety of deletion classifiers. Upon determining that the current deletion classifier associated with the recorded media asset needs to be updated to a new deletion classifier, the media guidance application may update the current deletion classifier to the new deletion classifier.

    SYSTEMS AND METHODS FOR VIEWING-SESSION CONTINUITY

    公开(公告)号:US20250047913A1

    公开(公告)日:2025-02-06

    申请号:US18925852

    申请日:2024-10-24

    Abstract: The present disclosure is generally directed to media systems configured to receive and play media assets. In particular, methods and systems are provided for improved media asset session continuity across such media systems. Systems and methods are provided herein for continuing media asset sessions across media systems or media devices in a way designed to minimize manual intervention, for example, by determining a likelihood (e.g., a probability) of a user requesting media session continuation of an ongoing media asset or a segment thereof across two or more devices.

    Systems and methods for conflict detection based on user preferences

    公开(公告)号:US12219220B2

    公开(公告)日:2025-02-04

    申请号:US18237643

    申请日:2023-08-24

    Inventor: Ti-Shiang Wang

    Abstract: Systems and methods for detecting a conflict between viewing selections of two users before viewing a media asset. In some aspects, the method comprises receiving an audio input through an audio channel, detecting a first utterance from a first user and a second utterance from a second user in the input of the audio channel, parsing the first utterance and the second utterance, analyzing the first utterance and the second utterance to determine context about the first media asset and the second media asset, and presenting a conflict to the users to display on the media asset.

Patent Agency Ranking