知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.012 seconds)

    USING A LARGE LANGUAGE MODEL TO IMPROVE TRAINING DATA
    1.
    发明申请
    USING A LARGE LANGUAGE MODEL TO IMPROVE TRAINING DATA 有权

    公开(公告)号：US20250045535A1

    公开(公告)日：2025-02-06

    申请号：US18423789

    申请日：2024-01-26

    Applicant: Roku, Inc.

    Inventor： Kapil Kumar ,  Abhishek Majumdar ,  Nitish Aggarwal ,  Srimaruti Manoj Nimmagadda

    IPC: G06F40/40

    Abstract: Training data can significantly impact the performance of machine learning models. Its impact may be more significant in transfer learning. Different data sources can be used to generate training data used in transfer learning. The training data originating from user interaction logs may be subject to presentation bias. The training data originating from model generated labeled data may have false positives. Poor quality training data may cause the machine learning model to perform poorly. To address some of these concerns, a checker having one or more models can check for false positives and for labeled data entries that may have been subject to presentation bias. Such entries may be removed or modified. In some cases, the checker can generate a test that can be used to test the machine learning model and penalize the machine learning model if the model generates an incorrect prediction.

    RETRIEVAL STRATEGY SELECTION OPTIMIZATION USING REINFORCEMENT LEARNING
    2.
    发明申请
    RETRIEVAL STRATEGY SELECTION OPTIMIZATION USING REINFORCEMENT LEARNING 有权

    公开(公告)号：US20250103943A1

    公开(公告)日：2025-03-27

    申请号：US18423834

    申请日：2024-01-26

    Applicant: Roku, Inc.

    Inventor： Yuxi Liu ,  Abhishek Majumdar ,  Nitish Aggarwal

    IPC: G06N20/00

    Abstract: Retrieving content items in response to a query in a way that increases user satisfaction and increases chances of users consuming a retrieved content item is not trivial. One content item retrieval system can combine different retrieval strategies. The content item retrieval system can retrieve a number of content items using different retrieval strategies and combining the content items together as the final results of the search. A naïve approach is to show fixed numbers of content items retrieved using the different retrieval strategies for any query. User engagement can be improved if the numbers can be tuned or optimized for a given query. Reinforcement learning can be used to train and implement an agent model that can choose the optimal numbers of content items retrieved using different retrieval strategies for a given query.

    REINFORCEMENT LEARNING (RL) MODEL FOR OPTIMIZING LONG TERM REVENUE
    3.
    发明公开
    REINFORCEMENT LEARNING (RL) MODEL FOR OPTIMIZING LONG TERM REVENUE 审中-公开

    公开(公告)号：US20240273575A1

    公开(公告)日：2024-08-15

    申请号：US18108090

    申请日：2023-02-10

    Applicant: ROKU, INC.

    Inventor： ABHISHEK BAMBHA ,  Weicong Ding ,  Ronica Jethwa ,  Rohit Mahto ,  Abhishek Majumdar ,  Amit Verma ,  Zidong Wang ,  Fei Xiao

    IPC: G06Q30/0251

    CPC classification number: G06Q30/0269 ,  G06Q30/0261

    Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for optimizing user experience/engagement and revenue. An example embodiment operates by a computer-implemented method for providing one or more advertisements to a media device. The method includes receiving, by at least one computer processor, a user state associated with a user of the media device, where the user state corresponds to a time step. The method further includes receiving a revenue value associated with the user of the media device, where the revenue value corresponds to the time step. The method also include determining an action associated with the user based on the user state and the revenue value. The action includes one or more parameters associated with the one or more advertisements. The method further includes providing the action to the user.

    SEARCH SYSTEMS BASED ON USER RELEVANCE AND REVENUE GENERATION
    4.
    发明申请
    SEARCH SYSTEMS BASED ON USER RELEVANCE AND REVENUE GENERATION 有权

    公开(公告)号：US20240430538A1

    公开(公告)日：2024-12-26

    申请号：US18744191

    申请日：2024-06-14

    Applicant: Roku, Inc.

    Inventor： Rahul AGARWAL ,  Abhishek Majumdar ,  Yu Zhou ,  Ratul Ray ,  Yuzhong Li ,  Nitish Aggarwal ,  Srimaruti Manoj Nimmagadda

    IPC: H04N21/482 ,  H04N21/466 ,  H04N21/472

    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 a list of recommended items in response to a user query. An embodiment can generate an ordered relevance list of items, and determine an initial reward value based on an array of relevance scores and an array of revenue values corresponding to the ordered relevance list of items, a parameter alpha assigned to the array of relevance scores, and a parameter beta assigned to the array of revenue values. The embodiment can generate a next list of recommended items from an initial list of recommended items, and further calculate a next reward value associated with the next list of recommended items, and determine a list of recommended items in response to the query based on a comparison of the initial reward value and the next reward value.

    PERSONALIZED RETRIEVAL SYSTEM
    5.
    发明公开
    PERSONALIZED RETRIEVAL SYSTEM 审中-公开

    公开(公告)号：US20240346084A1

    公开(公告)日：2024-10-17

    申请号：US18398495

    申请日：2023-12-28

    Applicant: Roku, Inc.

    Inventor： Kapil Kumar ,  Abhishek Majumdar ,  Danish Shaikh ,  Nitish Aggarwal ,  Srimaruti Manoj Nimmagadda ,  Aniruddha Das

    IPC: G06F16/9035 ,  G06F16/9038 ,  G06F40/40

    CPC classification number: G06F16/9035 ,  G06F16/9038 ,  G06F40/40

    Abstract: Disclosed are system, method and/or computer program product embodiments that retrieve items for a user based on a query using a two-tower deep machine learning model. An example embodiment provides input to a context tower, wherein the input includes the query and one or more of a query embedding corresponding to the query or a graph user embedding corresponding to the user. The context tower generates a context embedding in a vector space based on the input. The model determines a measure of similarity between the context embedding and each of a plurality of item embeddings in the vector space that are generated by an item tower and represent a plurality of candidate items. A relevancy score is calculated for each candidate item based on the measure of similarity between the context embedding and the corresponding item embedding. The relevancy scores are used for item retrieval and/or ranking.

    ENHANCING TRANSFER LEARNING FOR LARGE LANGUAGE MODELS
    7.
    发明申请
    ENHANCING TRANSFER LEARNING FOR LARGE LANGUAGE MODELS 有权

    公开(公告)号：US20250045575A1

    公开(公告)日：2025-02-06

    申请号：US18423802

    申请日：2024-01-26

    Applicant: Roku, Inc.

    Inventor： Abhishek Majumdar ,  Kapil Kumar ,  Nitish Aggarwal ,  Danish Nasir Shaikh ,  Manasi Deshmukh ,  Apoorva Jakalannanavar Halappa Manjula

    IPC: G06N3/08

    Abstract: Pre-trained large language models may be trained on a large data set which may not necessarily align with specific tasks, business goals, and requirements. Pre-trained large language models can solve generic semantic relationship or question-answering type problems but may not be suited for content item retrieval or recommendation of content items that are semantically relevant to a query. It is possible to build a machine learning model while using transfer learning to learn from pre-trained large language models. Training data can significantly impact the performance of machine learning models, especially machine learning models developed using transfer learning. The training data can impact a model's performance, generalization, fairness, and adaptation to specific domains. To address some of these concerns, a popularity bucketing strategy can be implemented to debias training data. Optionally, an ensemble of models can be used to generate diverse training data.

    HETEROGENEOUS GRAPH NEURAL NETWORK USING OFFSET TEMPORAL LEARNING FOR SEARCH PERSONALIZATION
    8.
    发明公开
    HETEROGENEOUS GRAPH NEURAL NETWORK USING OFFSET TEMPORAL LEARNING FOR SEARCH PERSONALIZATION 审中-公开

    公开(公告)号：US20240346309A1

    公开(公告)日：2024-10-17

    申请号：US18582249

    申请日：2024-02-20

    Applicant: Roku, Inc.

    Inventor： Abhishek Majumdar ,  Kapil Kumar ,  Nitish Aggarwal ,  Srimaruti Manoj Nimmagadda

    IPC: G06N3/08 ,  G06N3/042

    CPC classification number: G06N3/08 ,  G06N3/042

    Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for training a heterogenous graph neural network (GNN) to generate user embeddings corresponding to users and item embeddings corresponding to items. An example embodiment generates a first user interaction graph for a first time window and a second user interaction graph for a second time window, wherein each graph represents users and items as nodes and user-item interactions within the respective time window as edges, samples user-item node pairs from the second user interaction graph, and trains the heterogeneous GNN based on user-item node pairs from the first user interaction graph that correspond to the sampled user-item node pairs from the second user interaction graph. User and item embeddings generated by the trained GNN may be used to determine a relevancy of a given item with respect to a given user.

Patent Agency Ranking