中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

59 records (took 0.022 seconds)

    MACHINE LEARNING MODEL PROMPT DEMONSTRATION SELECTION
    1.
    发明申请
    MACHINE LEARNING MODEL PROMPT DEMONSTRATION SELECTION 有权

    公开(公告)号：US20250124352A1

    公开(公告)日：2025-04-17

    申请号：US18916442

    申请日：2024-10-15

    Applicant: SRI International

    Inventor： Anirudh Som ,  Karan Sikka ,  Ajay Divakaran ,  Helen Gent ,  Andreas Kathol ,  Dimitra Vergyri

    IPC: G06N20/00

    Abstract: Techniques are described for a machine learning system configured to generate respective sample embeddings for a plurality of sample statements. The machine learning system may further be configured to generate a statement embedding for a statement. The machine learning system may further be configured to determine, based on the sample embedding and the statement embedding, respective similarity scores for the sample embeddings. The machine learning system may further be configured to select, based on the respective similarity scores for the sample embeddings, one or more sample statements from the plurality of sample statements. The machine learning system may further be configured to generate a prompt including the one or more sample statements, the statement, and at least one of respective ground-truth information or respective paraphrases for the selected one or more sample statements. The machine learning system may further be configured to provide the prompt to a machine learning model.

    System and method for content comprehension and response
    2.
    发明授权
    System and method for content comprehension and response 有权

    公开(公告)号：US11934793B2

    公开(公告)日：2024-03-19

    申请号：US17516409

    申请日：2021-11-01

    Applicant: SRI International

    Inventor： Ajay Divakaran ,  Karan Sikka ,  Yi Yao ,  Yunye Gong ,  Stephanie Nunn ,  Pritish Sahu ,  Michael A. Cogswell ,  Jesse Hostetler ,  Sara Rutherford-Quach

    IPC: G06F40/35 ,  G06F16/33 ,  G06N5/04

    CPC classification number: G06F40/35 ,  G06F16/3335 ,  G06N5/04

    Abstract: A method, apparatus and system for training an embedding space for content comprehension and response includes, for each layer of a hierarchical taxonomy having at least two layers including respective words resulting in layers of varying complexity, determining a set of words associated with a layer of the hierarchical taxonomy, determining a question answer pair based on a question generated using at least one word of the set of words and at least one content domain, determining a vector representation for the generated question and for content related to the at least one content domain of the question answer pair, and embedding the question vector representation and the content vector representations into a common embedding space where vector representations that are related, are closer in the embedding space than unrelated embedded vector representations. Requests for content can then be fulfilled using the trained, common embedding space.

    Aligning symbols and objects using co-attention for understanding visual content
    3.
    发明授权
    Aligning symbols and objects using co-attention for understanding visual content 有权

    公开(公告)号：US11210572B2

    公开(公告)日：2021-12-28

    申请号：US16717497

    申请日：2019-12-17

    Applicant: SRI International

    Inventor： Ajay Divakaran ,  Karan Sikka ,  Karuna Ahuja ,  Anirban Roy

    IPC: G06K9/62 ,  G06K9/46 ,  G06K9/72 ,  G06N3/08 ,  G06K9/66

    Abstract: A method, apparatus and system for understanding visual content includes determining at least one region proposal for an image, attending at least one symbol of the proposed image region, attending a portion of the proposed image region using information regarding the attended symbol, extracting appearance features of the attended portion of the proposed image region, fusing the appearance features of the attended image region and features of the attended symbol, projecting the fused features into a semantic embedding space having been trained using fused attended appearance features and attended symbol features of images having known descriptive messages, computing a similarity measure between the projected, fused features and fused attended appearance features and attended symbol features embedded in the semantic embedding space having at least one associated descriptive message and predicting a descriptive message for an image associated with the projected, fused features.

    USER TARGETED CONTENT GENERATION USING MULTIMODAL EMBEDDINGS
    4.
    发明申请
    USER TARGETED CONTENT GENERATION USING MULTIMODAL EMBEDDINGS 有权

    公开(公告)号：US20210297498A1

    公开(公告)日：2021-09-23

    申请号：US17191698

    申请日：2021-03-04

    Applicant: SRI International

    Inventor： Ajay Divakaran ,  Karan Sikka ,  Arijit Ray ,  Xiao Lin ,  Yi Yao

    IPC: H04L29/08

    Abstract: A method, apparatus and system for determining user-content associations for determining and providing user-preferred content using multimodal embeddings include creating an embedding space for multimodal content by creating a first modality vector representation of the multimodal content having a first modality, creating a second modality vector representation of the multimodal content having a second modality, creating a user vector representation, as a third modality, for each user associated with at least a portion of the multimodal content, and embedding the first and the second modality vector representations and the user vector representations in the common embedding space using at least a mixture of loss functions for each modality pair of the first, the at least second and the third modalities that pushes closer co-occurring pairs of multimodal content. Embodiments can further include generating content using determined attributes of a message to be conveyed and features of the user-preferred content.

Patent Agency Ranking