知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

58 条记录 (耗时 0.038 秒)

    HYBRID QUERY AND INDEX FOR HIGH PERFORMANCE IN A CLOUD
    3.
    发明公开
    HYBRID QUERY AND INDEX FOR HIGH PERFORMANCE IN A CLOUD 审中-公开

    公开(公告)号：US20240220465A1

    公开(公告)日：2024-07-04

    申请号：US18091570

    申请日：2022-12-30

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Sheng Yan Sun ,  Peng Hui Jiang ,  Xiao Xiao Chen ,  Ying Zhang

    IPC分类号： G06F16/22 ,  G06F16/242 ,  G06F16/2457 ,  G06F18/2323

    CPC分类号： G06F16/22 ,  G06F16/2425 ,  G06F16/24578 ,  G06F18/2323

    摘要： A computer-implemented method, including receiving, by a processor set, a query including a query string for a system catalog; identifying, by the processor set, a default index structure of the system catalog; executing, by the processor set, the query based on the default index structure of each index in the system catalog; ranking, by the processor set, a performance of each execution of the query by each index; mapping, by the processor set, a query pattern to a corresponding index of the system catalog; selecting, by the processor set, the index to perform the query using a machine learning (ML) model trained with a knowledge base that includes the ranking and the mapping; executing, by the processor set, the query on the selected index; and in response to executing the query on the selected index, returning, by the processor set, a result of the query.

    SYSTEMS AND METHODS FOR UNSUPERVISED PARAPHRASE MINING
    4.
    发明公开
    SYSTEMS AND METHODS FOR UNSUPERVISED PARAPHRASE MINING 审中-公开

    公开(公告)号：US20240020485A1

    公开(公告)日：2024-01-18

    申请号：US18366890

    申请日：2023-08-08

    申请人： Recruit Co., Ltd.

    发明人： Behzad GOLSHAN ,  Chen Chen ,  Wang-Chiew Tan ,  Danni Ma

    IPC分类号： G06F40/35 ,  G06F40/268 ,  G06F40/284 ,  G06F18/2323

    CPC分类号： G06F40/35 ,  G06F40/268 ,  G06F40/284 ,  G06F18/2323

    摘要： Disclosed embodiments relate to aligning pairs of sentences. Techniques can include receiving a plurality of sentences; generating a graph for each of at least two sentences of the plurality of sentences, wherein generating a graph for each sentence of the at least two sentences comprises: identifying one or more tokens for the sentence; and connecting via edges the one or more tokens; generating a combined graph for the at least two sentences wherein generating a combined graph comprises: aligning the identified tokens of the at least two sentences of the plurality of sentences; identifying matching and non-matching tokens between the at least two sentences based on the alignment; and merging matching tokens into a combined graph node.

    Framework for few-shot temporal action localization
    7.
    发明授权
    Framework for few-shot temporal action localization 有权

    公开(公告)号：US11727686B2

    公开(公告)日：2023-08-15

    申请号：US17481248

    申请日：2021-09-21

    申请人： International Business Machines Corporation

    发明人： Chuang Gan ,  Ming Tan ,  Yang Zhang ,  Dakuo Wang

    IPC分类号： G06V20/40 ,  G06N3/08 ,  G06F18/2323 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44

    CPC分类号： G06V20/41 ,  G06F18/2323 ,  G06F18/24147 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V20/44

    摘要： Systems and techniques that facilitate few-shot temporal action localization based on graph convolutional networks are provided. In one or more embodiments, a graph component can generate a graph that models a support set of temporal action classifications. Nodes of the graph can correspond to respective temporal action classifications in the support set. Edges of the graph can correspond to similarities between the respective temporal action classifications. In various embodiments, a convolution component can perform a convolution on the graph, such that the nodes of the graph output respective matching scores indicating levels of match between the respective temporal action classifications and an action to be classified. In various embodiments, an instantiation component can input into the nodes respective input vectors based on a proposed feature vector representing the action to be classified. In various cases, the respective temporal action classifications can correspond to respective example feature vectors, and the respective input vectors can be concatenations of the respective example feature vectors and the proposed feature vector.