知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

7591 条记录 (耗时 0.032 秒)

    Generating neural network outputs using insertion commands
    41.
    发明授权
    Generating neural network outputs using insertion commands 有权

    公开(公告)号：US12086715B2

    公开(公告)日：2024-09-10

    申请号：US18321696

    申请日：2023-05-22

    申请人： Google LLC

    发明人： William Chan ,  Mitchell Thomas Stern ,  Nikita Kitaev ,  Kelvin Gu ,  Jakob D. Uszkoreit

    IPC分类号： G06F40/30 ,  G06F40/237 ,  G06N3/04 ,  G06N3/08 ,  G06N3/084

    CPC分类号： G06N3/08 ,  G06F40/237 ,  G06N3/04 ,  G06N3/084

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing sequence modeling tasks using insertions. One of the methods includes receiving a system input that includes one or more source elements from a source sequence and zero or more target elements from a target sequence, wherein each source element is selected from a vocabulary of source elements and wherein each target element is selected from a vocabulary of target elements; generating a partial concatenated sequence that includes the one or more source elements from the source sequence and the zero or more target elements from the target sequence, wherein the source and target elements arranged in the partial concatenated sequence according to a combined order; and generating a final concatenated sequence that includes a finalized source sequence and a finalized target sequence, wherein the finalized target sequence includes one or more target elements.

    Generation of regular expressions
    43.
    发明授权
    Generation of regular expressions 有权

    公开(公告)号：US12086188B2

    公开(公告)日：2024-09-10

    申请号：US17372830

    申请日：2021-07-12

    申请人： salesforce.com, inc.

    发明人： Jonathan Dean Smith

    IPC分类号： G10L15/22 ,  G06F16/903 ,  G06F40/30

    CPC分类号： G06F16/90344 ,  G06F40/30

    摘要： A method is provided for generating regular expressions. In some embodiments, the method includes partitioning a first plurality of text strings into a plurality of substrings, each text string of the first plurality being malignant or benign. The method also includes generating a population list including a second plurality of text strings, each text string of the second plurality including at least one token. The method further includes creating subsequent iterations of the population list. Each iteration may include calculating a score for one or more text strings in the population list and removing one or more text strings from the population list. The method further includes in response to a determination to not update the population list, selecting, based on the one or more calculated scores, a third text string as a regular expression from a final iteration of the population list.

    Collaborative resolution framework
    44.
    发明授权
    Collaborative resolution framework 有权

    公开(公告)号：US12086169B2

    公开(公告)日：2024-09-10

    申请号：US17657442

    申请日：2022-03-31

    申请人： Dell Products L.P.

    发明人： Dhilip Kumar ,  Ponnayan Sekar ,  Hung Dinh ,  Bijan Kumar Mohanty

    IPC分类号： G06F16/332 ,  G06F40/20 ,  G06F40/30 ,  G06N20/20

    CPC分类号： G06F16/3329 ,  G06F40/20 ,  G06F40/30 ,  G06N20/20

    摘要： A method including: generating a conversation flow signature based on a set of communication transcripts, each of the communication transcripts being associated with a support request for a product, each of the communication transcripts being a text transcript of a communication between a respective customer and a respective customer support agent; classifying the conversation flow signature into one of a plurality of categories, the conversation flow signature being classified by using a machine learning classifier that is trained based on customer support records, each of the plurality of categories corresponding to a respective set of steps for configuring or repairing the product; and outputting an indication of the respective set of steps that is associated with the category in which the conversation flow signature is classified.

    EXTRACTING FINE-GRAINED TOPICS FROM TEXT CONTENT
    47.
    发明公开
    EXTRACTING FINE-GRAINED TOPICS FROM TEXT CONTENT 审中-公开

    公开(公告)号：US20240296291A1

    公开(公告)日：2024-09-05

    申请号：US18662775

    申请日：2024-05-13

    申请人： YAHOO AD TECH LLC

    发明人： Deven Santosh SHAH ,  Sukanya MOORTHY ,  Topojoy BISWAS

    IPC分类号： G06F40/30 ,  G06F40/166 ,  G06F40/242 ,  G06F40/284 ,  G06F40/40 ,  G06N3/08

    CPC分类号： G06F40/30 ,  G06F40/166 ,  G06F40/40 ,  G06N3/08 ,  G06F40/242 ,  G06F40/284

    摘要： The example embodiments are directed toward improvements in document classification. In an embodiment, a method is disclosed comprising generating a set of sentences based on a document; predicting a set of labels for each sentence using a multi-label classifier, the multi-label classifier including a self-attended contextual word embedding backbone layer, a bank of trainable unigram convolutions, a bank of trainable bigram convolutions, and a fully connected layer the multi-label classifier trained using a weakly labeled data set; and labeling the document based on the set of labels. The various embodiments can target multiple use cases such as identifying related entities, trending related entities, creating ephemeral timeline of entities, and others using a single solution. Further, the various embodiments provide a weakly supervised framework to train a model when a labeled golden set does not contain a sufficient number of examples.

    Information and dialog models for education
    50.
    发明授权
    Information and dialog models for education 有权

    公开(公告)号：US12080187B1

    公开(公告)日：2024-09-03

    申请号：US16047975

    申请日：2018-07-27

    申请人： Elemental Cognition Inc.

    发明人： David Ferrucci ,  David Melville ,  Gregory Burnham

    IPC分类号： G09B7/04 ,  G06F40/30 ,  G09B7/00 ,  G06N20/00

    CPC分类号： G09B7/04 ,  G06F40/30 ,  G09B7/00 ,  G06N20/00

    摘要： A reading comprehension system may include an authoring tool to help generate adaptable dialogs and a reading tool to conduct adaptable dialog sessions with students. The authoring tool may receive and process stories to generate labeled stories and information models. The information models may provide the conceptual structures that an effective reader should build while reading and understanding a story. The system may use dialog models for general dialogs and information models for story specific dialogs to guide adaptable dialog sessions with students. During the adaptable dialog sessions, the system may constantly assess and guide the student's progress in the understanding the current story and in general reading comprehension development. Using the labeled stories and dialog sessions as training data, the system may learn how to dialog effectively with the students, to gather an evolving understanding of the student's abilities, and to acquire knowledge about the world or the story.